Added basic refining to video object and added lxml module to libs

pull/293/head
morpheus65535 5 years ago
parent 1c8377184b
commit 052ee77441

@ -15,7 +15,7 @@ import subliminal
import subliminal_patch
from datetime import datetime, timedelta
from subzero.language import Language
from subzero.video import parse_video
from subzero.video import parse_video, refine_video
from subliminal import region, score as subliminal_scores, \
list_subtitles
from subliminal_patch.core import SZAsyncProviderPool, download_best_subtitles, save_subtitles, download_subtitles
@ -63,6 +63,7 @@ def get_video(path, title, sceneName, use_scenename, providers=None, media_type=
video.used_scene_name = dont_use_actual_file
video.original_name = original_name
video.original_path = original_path
refine_video(video)
return video
except:

@ -0,0 +1,219 @@
#
# ElementTree
# $Id: ElementInclude.py 1862 2004-06-18 07:31:02Z Fredrik $
#
# limited xinclude support for element trees
#
# history:
# 2003-08-15 fl created
# 2003-11-14 fl fixed default loader
#
# Copyright (c) 2003-2004 by Fredrik Lundh. All rights reserved.
#
# fredrik@pythonware.com
# http://www.pythonware.com
#
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2004 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------
"""
Limited XInclude support for the ElementTree package.
While lxml.etree has full support for XInclude (see
`etree.ElementTree.xinclude()`), this module provides a simpler, pure
Python, ElementTree compatible implementation that supports a simple
form of custom URL resolvers.
"""
from lxml import etree
try:
from urlparse import urljoin
from urllib2 import urlopen
except ImportError:
# Python 3
from urllib.parse import urljoin
from urllib.request import urlopen
XINCLUDE = "{http://www.w3.org/2001/XInclude}"
XINCLUDE_INCLUDE = XINCLUDE + "include"
XINCLUDE_FALLBACK = XINCLUDE + "fallback"
XINCLUDE_ITER_TAG = XINCLUDE + "*"
##
# Fatal include error.
class FatalIncludeError(etree.LxmlSyntaxError):
pass
##
# ET compatible default loader.
# This loader reads an included resource from disk.
#
# @param href Resource reference.
# @param parse Parse mode. Either "xml" or "text".
# @param encoding Optional text encoding.
# @return The expanded resource. If the parse mode is "xml", this
# is an ElementTree instance. If the parse mode is "text", this
# is a Unicode string. If the loader fails, it can return None
# or raise an IOError exception.
# @throws IOError If the loader fails to load the resource.
def default_loader(href, parse, encoding=None):
file = open(href, 'rb')
if parse == "xml":
data = etree.parse(file).getroot()
else:
data = file.read()
if not encoding:
encoding = 'utf-8'
data = data.decode(encoding)
file.close()
return data
##
# Default loader used by lxml.etree - handles custom resolvers properly
#
def _lxml_default_loader(href, parse, encoding=None, parser=None):
if parse == "xml":
data = etree.parse(href, parser).getroot()
else:
if "://" in href:
f = urlopen(href)
else:
f = open(href, 'rb')
data = f.read()
f.close()
if not encoding:
encoding = 'utf-8'
data = data.decode(encoding)
return data
##
# Wrapper for ET compatibility - drops the parser
def _wrap_et_loader(loader):
def load(href, parse, encoding=None, parser=None):
return loader(href, parse, encoding)
return load
##
# Expand XInclude directives.
#
# @param elem Root element.
# @param loader Optional resource loader. If omitted, it defaults
# to {@link default_loader}. If given, it should be a callable
# that implements the same interface as <b>default_loader</b>.
# @param base_url The base URL of the original file, to resolve
# relative include file references.
# @throws FatalIncludeError If the function fails to include a given
# resource, or if the tree contains malformed XInclude elements.
# @throws IOError If the function fails to load a given resource.
# @returns the node or its replacement if it was an XInclude node
def include(elem, loader=None, base_url=None):
if base_url is None:
if hasattr(elem, 'getroot'):
tree = elem
elem = elem.getroot()
else:
tree = elem.getroottree()
if hasattr(tree, 'docinfo'):
base_url = tree.docinfo.URL
elif hasattr(elem, 'getroot'):
elem = elem.getroot()
_include(elem, loader, base_url=base_url)
def _include(elem, loader=None, _parent_hrefs=None, base_url=None):
if loader is not None:
load_include = _wrap_et_loader(loader)
else:
load_include = _lxml_default_loader
if _parent_hrefs is None:
_parent_hrefs = set()
parser = elem.getroottree().parser
include_elements = list(
elem.iter(XINCLUDE_ITER_TAG))
for e in include_elements:
if e.tag == XINCLUDE_INCLUDE:
# process xinclude directive
href = urljoin(base_url, e.get("href"))
parse = e.get("parse", "xml")
parent = e.getparent()
if parse == "xml":
if href in _parent_hrefs:
raise FatalIncludeError(
"recursive include of %r detected" % href
)
_parent_hrefs.add(href)
node = load_include(href, parse, parser=parser)
if node is None:
raise FatalIncludeError(
"cannot load %r as %r" % (href, parse)
)
node = _include(node, loader, _parent_hrefs)
if e.tail:
node.tail = (node.tail or "") + e.tail
if parent is None:
return node # replaced the root node!
parent.replace(e, node)
elif parse == "text":
text = load_include(href, parse, encoding=e.get("encoding"))
if text is None:
raise FatalIncludeError(
"cannot load %r as %r" % (href, parse)
)
predecessor = e.getprevious()
if predecessor is not None:
predecessor.tail = (predecessor.tail or "") + text
elif parent is None:
return text # replaced the root node!
else:
parent.text = (parent.text or "") + text + (e.tail or "")
parent.remove(e)
else:
raise FatalIncludeError(
"unknown parse type in xi:include tag (%r)" % parse
)
elif e.tag == XINCLUDE_FALLBACK:
parent = e.getparent()
if parent is not None and parent.tag != XINCLUDE_INCLUDE:
raise FatalIncludeError(
"xi:fallback tag must be child of xi:include (%r)" % e.tag
)
else:
raise FatalIncludeError(
"Invalid element found in XInclude namespace (%r)" % e.tag
)
return elem

@ -0,0 +1,20 @@
# this is a package
def get_include():
"""
Returns a list of header include paths (for lxml itself, libxml2
and libxslt) needed to compile C code against lxml if it was built
with statically linked libraries.
"""
import os
lxml_path = __path__[0]
include_path = os.path.join(lxml_path, 'includes')
includes = [include_path, lxml_path]
for name in os.listdir(include_path):
path = os.path.join(include_path, name)
if os.path.isdir(path):
includes.append(path)
return includes

@ -0,0 +1,337 @@
# cython: language_level=2
#
# ElementTree
# $Id: ElementPath.py 3375 2008-02-13 08:05:08Z fredrik $
#
# limited xpath support for element trees
#
# history:
# 2003-05-23 fl created
# 2003-05-28 fl added support for // etc
# 2003-08-27 fl fixed parsing of periods in element names
# 2007-09-10 fl new selection engine
# 2007-09-12 fl fixed parent selector
# 2007-09-13 fl added iterfind; changed findall to return a list
# 2007-11-30 fl added namespaces support
# 2009-10-30 fl added child element value filter
#
# Copyright (c) 2003-2009 by Fredrik Lundh. All rights reserved.
#
# fredrik@pythonware.com
# http://www.pythonware.com
#
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2009 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------
##
# Implementation module for XPath support. There's usually no reason
# to import this module directly; the <b>ElementTree</b> does this for
# you, if needed.
##
from __future__ import absolute_import
import re
xpath_tokenizer_re = re.compile(
"("
"'[^']*'|\"[^\"]*\"|"
"::|"
"//?|"
r"\.\.|"
r"\(\)|"
r"[/.*:\[\]\(\)@=])|"
r"((?:\{[^}]+\})?[^/\[\]\(\)@=\s]+)|"
r"\s+"
)
def xpath_tokenizer(pattern, namespaces=None):
default_namespace = namespaces.get(None) if namespaces else None
for token in xpath_tokenizer_re.findall(pattern):
tag = token[1]
if tag and tag[0] != "{":
if ":" in tag:
prefix, uri = tag.split(":", 1)
try:
if not namespaces:
raise KeyError
yield token[0], "{%s}%s" % (namespaces[prefix], uri)
except KeyError:
raise SyntaxError("prefix %r not found in prefix map" % prefix)
elif default_namespace:
yield token[0], "{%s}%s" % (default_namespace, tag)
else:
yield token
else:
yield token
def prepare_child(next, token):
tag = token[1]
def select(result):
for elem in result:
for e in elem.iterchildren(tag):
yield e
return select
def prepare_star(next, token):
def select(result):
for elem in result:
for e in elem.iterchildren('*'):
yield e
return select
def prepare_self(next, token):
def select(result):
return result
return select
def prepare_descendant(next, token):
token = next()
if token[0] == "*":
tag = "*"
elif not token[0]:
tag = token[1]
else:
raise SyntaxError("invalid descendant")
def select(result):
for elem in result:
for e in elem.iterdescendants(tag):
yield e
return select
def prepare_parent(next, token):
def select(result):
for elem in result:
parent = elem.getparent()
if parent is not None:
yield parent
return select
def prepare_predicate(next, token):
# FIXME: replace with real parser!!! refs:
# http://effbot.org/zone/simple-iterator-parser.htm
# http://javascript.crockford.com/tdop/tdop.html
signature = ''
predicate = []
while 1:
token = next()
if token[0] == "]":
break
if token == ('', ''):
# ignore whitespace
continue
if token[0] and token[0][:1] in "'\"":
token = "'", token[0][1:-1]
signature += token[0] or "-"
predicate.append(token[1])
# use signature to determine predicate type
if signature == "@-":
# [@attribute] predicate
key = predicate[1]
def select(result):
for elem in result:
if elem.get(key) is not None:
yield elem
return select
if signature == "@-='":
# [@attribute='value']
key = predicate[1]
value = predicate[-1]
def select(result):
for elem in result:
if elem.get(key) == value:
yield elem
return select
if signature == "-" and not re.match(r"-?\d+$", predicate[0]):
# [tag]
tag = predicate[0]
def select(result):
for elem in result:
for _ in elem.iterchildren(tag):
yield elem
break
return select
if signature == ".='" or (signature == "-='" and not re.match(r"-?\d+$", predicate[0])):
# [.='value'] or [tag='value']
tag = predicate[0]
value = predicate[-1]
if tag:
def select(result):
for elem in result:
for e in elem.iterchildren(tag):
if "".join(e.itertext()) == value:
yield elem
break
else:
def select(result):
for elem in result:
if "".join(elem.itertext()) == value:
yield elem
return select
if signature == "-" or signature == "-()" or signature == "-()-":
# [index] or [last()] or [last()-index]
if signature == "-":
# [index]
index = int(predicate[0]) - 1
if index < 0:
if index == -1:
raise SyntaxError(
"indices in path predicates are 1-based, not 0-based")
else:
raise SyntaxError("path index >= 1 expected")
else:
if predicate[0] != "last":
raise SyntaxError("unsupported function")
if signature == "-()-":
try:
index = int(predicate[2]) - 1
except ValueError:
raise SyntaxError("unsupported expression")
else:
index = -1
def select(result):
for elem in result:
parent = elem.getparent()
if parent is None:
continue
try:
# FIXME: what if the selector is "*" ?
elems = list(parent.iterchildren(elem.tag))
if elems[index] is elem:
yield elem
except IndexError:
pass
return select
raise SyntaxError("invalid predicate")
ops = {
"": prepare_child,
"*": prepare_star,
".": prepare_self,
"..": prepare_parent,
"//": prepare_descendant,
"[": prepare_predicate,
}
# --------------------------------------------------------------------
_cache = {}
def _build_path_iterator(path, namespaces):
"""compile selector pattern"""
if path[-1:] == "/":
path += "*" # implicit all (FIXME: keep this?)
cache_key = (path,)
if namespaces:
if '' in namespaces:
raise ValueError("empty namespace prefix must be passed as None, not the empty string")
if None in namespaces:
cache_key += (namespaces[None],) + tuple(sorted(
item for item in namespaces.items() if item[0] is not None))
else:
cache_key += tuple(sorted(namespaces.items()))
try:
return _cache[cache_key]
except KeyError:
pass
if len(_cache) > 100:
_cache.clear()
if path[:1] == "/":
raise SyntaxError("cannot use absolute path on element")
stream = iter(xpath_tokenizer(path, namespaces))
try:
_next = stream.next
except AttributeError:
# Python 3
_next = stream.__next__
try:
token = _next()
except StopIteration:
raise SyntaxError("empty path expression")
selector = []
while 1:
try:
selector.append(ops[token[0]](_next, token))
except StopIteration:
raise SyntaxError("invalid path")
try:
token = _next()
if token[0] == "/":
token = _next()
except StopIteration:
break
_cache[cache_key] = selector
return selector
##
# Iterate over the matching nodes
def iterfind(elem, path, namespaces=None):
selector = _build_path_iterator(path, namespaces)
result = iter((elem,))
for select in selector:
result = select(result)
return result
##
# Find first matching object.
def find(elem, path, namespaces=None):
it = iterfind(elem, path, namespaces)
try:
return next(it)
except StopIteration:
return None
##
# Find all matching objects.
def findall(elem, path, namespaces=None):
return list(iterfind(elem, path, namespaces))
##
# Find text for first matching object.
def findtext(elem, path, default=None, namespaces=None):
el = find(elem, path, namespaces)
if el is None:
return default
else:
return el.text or ''

Binary file not shown.

@ -0,0 +1,239 @@
# cython: language_level=2
#
# Element generator factory by Fredrik Lundh.
#
# Source:
# http://online.effbot.org/2006_11_01_archive.htm#et-builder
# http://effbot.python-hosting.com/file/stuff/sandbox/elementlib/builder.py
#
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2004 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------
"""
The ``E`` Element factory for generating XML documents.
"""
from __future__ import absolute_import
import lxml.etree as ET
from functools import partial
try:
basestring
except NameError:
basestring = str
try:
unicode
except NameError:
unicode = str
class ElementMaker(object):
"""Element generator factory.
Unlike the ordinary Element factory, the E factory allows you to pass in
more than just a tag and some optional attributes; you can also pass in
text and other elements. The text is added as either text or tail
attributes, and elements are inserted at the right spot. Some small
examples::
>>> from lxml import etree as ET
>>> from lxml.builder import E
>>> ET.tostring(E("tag"))
'<tag/>'
>>> ET.tostring(E("tag", "text"))
'<tag>text</tag>'
>>> ET.tostring(E("tag", "text", key="value"))
'<tag key="value">text</tag>'
>>> ET.tostring(E("tag", E("subtag", "text"), "tail"))
'<tag><subtag>text</subtag>tail</tag>'
For simple tags, the factory also allows you to write ``E.tag(...)`` instead
of ``E('tag', ...)``::
>>> ET.tostring(E.tag())
'<tag/>'
>>> ET.tostring(E.tag("text"))
'<tag>text</tag>'
>>> ET.tostring(E.tag(E.subtag("text"), "tail"))
'<tag><subtag>text</subtag>tail</tag>'
Here's a somewhat larger example; this shows how to generate HTML
documents, using a mix of prepared factory functions for inline elements,
nested ``E.tag`` calls, and embedded XHTML fragments::
# some common inline elements
A = E.a
I = E.i
B = E.b
def CLASS(v):
# helper function, 'class' is a reserved word
return {'class': v}
page = (
E.html(
E.head(
E.title("This is a sample document")
),
E.body(
E.h1("Hello!", CLASS("title")),
E.p("This is a paragraph with ", B("bold"), " text in it!"),
E.p("This is another paragraph, with a ",
A("link", href="http://www.python.org"), "."),
E.p("Here are some reserved characters: <spam&egg>."),
ET.XML("<p>And finally, here is an embedded XHTML fragment.</p>"),
)
)
)
print ET.tostring(page)
Here's a prettyprinted version of the output from the above script::
<html>
<head>
<title>This is a sample document</title>
</head>
<body>
<h1 class="title">Hello!</h1>
<p>This is a paragraph with <b>bold</b> text in it!</p>
<p>This is another paragraph, with <a href="http://www.python.org">link</a>.</p>
<p>Here are some reserved characters: &lt;spam&amp;egg&gt;.</p>
<p>And finally, here is an embedded XHTML fragment.</p>
</body>
</html>
For namespace support, you can pass a namespace map (``nsmap``)
and/or a specific target ``namespace`` to the ElementMaker class::
>>> E = ElementMaker(namespace="http://my.ns/")
>>> print(ET.tostring( E.test ))
<test xmlns="http://my.ns/"/>
>>> E = ElementMaker(namespace="http://my.ns/", nsmap={'p':'http://my.ns/'})
>>> print(ET.tostring( E.test ))
<p:test xmlns:p="http://my.ns/"/>
"""
def __init__(self, typemap=None,
namespace=None, nsmap=None, makeelement=None):
if namespace is not None:
self._namespace = '{' + namespace + '}'
else:
self._namespace = None
if nsmap:
self._nsmap = dict(nsmap)
else:
self._nsmap = None
if makeelement is not None:
assert callable(makeelement)
self._makeelement = makeelement
else:
self._makeelement = ET.Element
# initialize type map for this element factory
if typemap:
typemap = dict(typemap)
else:
typemap = {}
def add_text(elem, item):
try:
elem[-1].tail = (elem[-1].tail or "") + item
except IndexError:
elem.text = (elem.text or "") + item
def add_cdata(elem, cdata):
if elem.text:
raise ValueError("Can't add a CDATA section. Element already has some text: %r" % elem.text)
elem.text = cdata
if str not in typemap:
typemap[str] = add_text
if unicode not in typemap:
typemap[unicode] = add_text
if ET.CDATA not in typemap:
typemap[ET.CDATA] = add_cdata
def add_dict(elem, item):
attrib = elem.attrib
for k, v in item.items():
if isinstance(v, basestring):
attrib[k] = v
else:
attrib[k] = typemap[type(v)](None, v)
if dict not in typemap:
typemap[dict] = add_dict
self._typemap = typemap
def __call__(self, tag, *children, **attrib):
typemap = self._typemap
if self._namespace is not None and tag[0] != '{':
tag = self._namespace + tag
elem = self._makeelement(tag, nsmap=self._nsmap)
if attrib:
typemap[dict](elem, attrib)
for item in children:
if callable(item):
item = item()
t = typemap.get(type(item))
if t is None:
if ET.iselement(item):
elem.append(item)
continue
for basetype in type(item).__mro__:
# See if the typemap knows of any of this type's bases.
t = typemap.get(basetype)
if t is not None:
break
else:
raise TypeError("bad argument type: %s(%r)" %
(type(item).__name__, item))
v = t(elem, item)
if v:
typemap.get(type(v))(elem, v)
return elem
def __getattr__(self, tag):
return partial(self, tag)
# create factory object
E = ElementMaker()

Binary file not shown.

@ -0,0 +1,102 @@
"""CSS Selectors based on XPath.
This module supports selecting XML/HTML tags based on CSS selectors.
See the `CSSSelector` class for details.
This is a thin wrapper around cssselect 0.7 or later.
"""
from __future__ import absolute_import
from . import etree
try:
import cssselect as external_cssselect
except ImportError:
raise ImportError(
'cssselect does not seem to be installed. '
'See http://packages.python.org/cssselect/')
SelectorSyntaxError = external_cssselect.SelectorSyntaxError
ExpressionError = external_cssselect.ExpressionError
SelectorError = external_cssselect.SelectorError
__all__ = ['SelectorSyntaxError', 'ExpressionError', 'SelectorError',
'CSSSelector']
class LxmlTranslator(external_cssselect.GenericTranslator):
"""
A custom CSS selector to XPath translator with lxml-specific extensions.
"""
def xpath_contains_function(self, xpath, function):
# Defined there, removed in later drafts:
# http://www.w3.org/TR/2001/CR-css3-selectors-20011113/#content-selectors
if function.argument_types() not in (['STRING'], ['IDENT']):
raise ExpressionError(
"Expected a single string or ident for :contains(), got %r"
% function.arguments)
value = function.arguments[0].value
return xpath.add_condition(
'contains(__lxml_internal_css:lower-case(string(.)), %s)'
% self.xpath_literal(value.lower()))
class LxmlHTMLTranslator(LxmlTranslator, external_cssselect.HTMLTranslator):
"""
lxml extensions + HTML support.
"""
def _make_lower_case(context, s):
return s.lower()
ns = etree.FunctionNamespace('http://codespeak.net/lxml/css/')
ns.prefix = '__lxml_internal_css'
ns['lower-case'] = _make_lower_case
class CSSSelector(etree.XPath):
"""A CSS selector.
Usage::
>>> from lxml import etree, cssselect
>>> select = cssselect.CSSSelector("a tag > child")
>>> root = etree.XML("<a><b><c/><tag><child>TEXT</child></tag></b></a>")
>>> [ el.tag for el in select(root) ]
['child']
To use CSS namespaces, you need to pass a prefix-to-namespace
mapping as ``namespaces`` keyword argument::
>>> rdfns = 'http://www.w3.org/1999/02/22-rdf-syntax-ns#'
>>> select_ns = cssselect.CSSSelector('root > rdf|Description',
... namespaces={'rdf': rdfns})
>>> rdf = etree.XML((
... '<root xmlns:rdf="%s">'
... '<rdf:Description>blah</rdf:Description>'
... '</root>') % rdfns)
>>> [(el.tag, el.text) for el in select_ns(rdf)]
[('{http://www.w3.org/1999/02/22-rdf-syntax-ns#}Description', 'blah')]
"""
def __init__(self, css, namespaces=None, translator='xml'):
if translator == 'xml':
translator = LxmlTranslator()
elif translator == 'html':
translator = LxmlHTMLTranslator()
elif translator == 'xhtml':
translator = LxmlHTMLTranslator(xhtml=True)
path = translator.css_to_xpath(css)
etree.XPath.__init__(self, path, namespaces=namespaces)
self.css = css
def __repr__(self):
return '<%s %s for %r>' % (
self.__class__.__name__,
hex(abs(id(self)))[2:],
self.css)

@ -0,0 +1,507 @@
"""
lxml-based doctest output comparison.
Note: normally, you should just import the `lxml.usedoctest` and
`lxml.html.usedoctest` modules from within a doctest, instead of this
one::
>>> import lxml.usedoctest # for XML output
>>> import lxml.html.usedoctest # for HTML output
To use this module directly, you must call ``lxmldoctest.install()``,
which will cause doctest to use this in all subsequent calls.
This changes the way output is checked and comparisons are made for
XML or HTML-like content.
XML or HTML content is noticed because the example starts with ``<``
(it's HTML if it starts with ``<html``). You can also use the
``PARSE_HTML`` and ``PARSE_XML`` flags to force parsing.
Some rough wildcard-like things are allowed. Whitespace is generally
ignored (except in attributes). In text (attributes and text in the
body) you can use ``...`` as a wildcard. In an example it also
matches any trailing tags in the element, though it does not match
leading tags. You may create a tag ``<any>`` or include an ``any``
attribute in the tag. An ``any`` tag matches any tag, while the
attribute matches any and all attributes.
When a match fails, the reformatted example and gotten text is
displayed (indented), and a rough diff-like output is given. Anything
marked with ``+`` is in the output but wasn't supposed to be, and
similarly ``-`` means its in the example but wasn't in the output.
You can disable parsing on one line with ``# doctest:+NOPARSE_MARKUP``
"""
from lxml import etree
import sys
import re
import doctest
try:
from html import escape as html_escape
except ImportError:
from cgi import escape as html_escape
__all__ = ['PARSE_HTML', 'PARSE_XML', 'NOPARSE_MARKUP', 'LXMLOutputChecker',
'LHTMLOutputChecker', 'install', 'temp_install']
try:
_basestring = basestring
except NameError:
_basestring = (str, bytes)
_IS_PYTHON_3 = sys.version_info[0] >= 3
PARSE_HTML = doctest.register_optionflag('PARSE_HTML')
PARSE_XML = doctest.register_optionflag('PARSE_XML')
NOPARSE_MARKUP = doctest.register_optionflag('NOPARSE_MARKUP')
OutputChecker = doctest.OutputChecker
def strip(v):
if v is None:
return None
else:
return v.strip()
def norm_whitespace(v):
return _norm_whitespace_re.sub(' ', v)
_html_parser = etree.HTMLParser(recover=False, remove_blank_text=True)
def html_fromstring(html):
return etree.fromstring(html, _html_parser)
# We use this to distinguish repr()s from elements:
_repr_re = re.compile(r'^<[^>]+ (at|object) ')
_norm_whitespace_re = re.compile(r'[ \t\n][ \t\n]+')
class LXMLOutputChecker(OutputChecker):
empty_tags = (
'param', 'img', 'area', 'br', 'basefont', 'input',
'base', 'meta', 'link', 'col')
def get_default_parser(self):
return etree.XML
def check_output(self, want, got, optionflags):
alt_self = getattr(self, '_temp_override_self', None)
if alt_self is not None:
super_method = self._temp_call_super_check_output
self = alt_self
else:
super_method = OutputChecker.check_output
parser = self.get_parser(want, got, optionflags)
if not parser:
return super_method(
self, want, got, optionflags)
try:
want_doc = parser(want)
except etree.XMLSyntaxError:
return False
try:
got_doc = parser(got)
except etree.XMLSyntaxError:
return False
return self.compare_docs(want_doc, got_doc)
def get_parser(self, want, got, optionflags):
parser = None
if NOPARSE_MARKUP & optionflags:
return None
if PARSE_HTML & optionflags:
parser = html_fromstring
elif PARSE_XML & optionflags:
parser = etree.XML
elif (want.strip().lower().startswith('<html')
and got.strip().startswith('<html')):
parser = html_fromstring
elif (self._looks_like_markup(want)
and self._looks_like_markup(got)):
parser = self.get_default_parser()
return parser
def _looks_like_markup(self, s):
s = s.strip()
return (s.startswith('<')
and not _repr_re.search(s))
def compare_docs(self, want, got):
if not self.tag_compare(want.tag, got.tag):
return False
if not self.text_compare(want.text, got.text, True):
return False
if not self.text_compare(want.tail, got.tail, True):
return False
if 'any' not in want.attrib:
want_keys = sorted(want.attrib.keys())
got_keys = sorted(got.attrib.keys())
if want_keys != got_keys:
return False
for key in want_keys:
if not self.text_compare(want.attrib[key], got.attrib[key], False):
return False
if want.text != '...' or len(want):
want_children = list(want)
got_children = list(got)
while want_children or got_children:
if not want_children or not got_children:
return False
want_first = want_children.pop(0)
got_first = got_children.pop(0)
if not self.compare_docs(want_first, got_first):
return False
if not got_children and want_first.tail == '...':
break
return True
def text_compare(self, want, got, strip):
want = want or ''
got = got or ''
if strip:
want = norm_whitespace(want).strip()
got = norm_whitespace(got).strip()
want = '^%s$' % re.escape(want)
want = want.replace(r'\.\.\.', '.*')
if re.search(want, got):
return True
else:
return False
def tag_compare(self, want, got):
if want == 'any':
return True
if (not isinstance(want, _basestring)
or not isinstance(got, _basestring)):
return want == got
want = want or ''
got = got or ''
if want.startswith('{...}'):
# Ellipsis on the namespace
return want.split('}')[-1] == got.split('}')[-1]
else:
return want == got
def output_difference(self, example, got, optionflags):
want = example.want
parser = self.get_parser(want, got, optionflags)
errors = []
if parser is not None:
try:
want_doc = parser(want)
except etree.XMLSyntaxError:
e = sys.exc_info()[1]
errors.append('In example: %s' % e)
try:
got_doc = parser(got)
except etree.XMLSyntaxError:
e = sys.exc_info()[1]
errors.append('In actual output: %s' % e)
if parser is None or errors:
value = OutputChecker.output_difference(
self, example, got, optionflags)
if errors:
errors.append(value)
return '\n'.join(errors)
else:
return value
html = parser is html_fromstring
diff_parts = ['Expected:',
self.format_doc(want_doc, html, 2),
'Got:',
self.format_doc(got_doc, html, 2),
'Diff:',
self.collect_diff(want_doc, got_doc, html, 2)]
return '\n'.join(diff_parts)
def html_empty_tag(self, el, html=True):
if not html:
return False
if el.tag not in self.empty_tags:
return False
if el.text or len(el):
# This shouldn't happen (contents in an empty tag)
return False
return True
def format_doc(self, doc, html, indent, prefix=''):
parts = []
if not len(doc):
# No children...
parts.append(' '*indent)
parts.append(prefix)
parts.append(self.format_tag(doc))
if not self.html_empty_tag(doc, html):
if strip(doc.text):
parts.append(self.format_text(doc.text))
parts.append(self.format_end_tag(doc))
if strip(doc.tail):
parts.append(self.format_text(doc.tail))
parts.append('\n')
return ''.join(parts)
parts.append(' '*indent)
parts.append(prefix)
parts.append(self.format_tag(doc))
if not self.html_empty_tag(doc, html):
parts.append('\n')
if strip(doc.text):
parts.append(' '*indent)
parts.append(self.format_text(doc.text))
parts.append('\n')
for el in doc:
parts.append(self.format_doc(el, html, indent+2))
parts.append(' '*indent)
parts.append(self.format_end_tag(doc))
parts.append('\n')
if strip(doc.tail):
parts.append(' '*indent)
parts.append(self.format_text(doc.tail))
parts.append('\n')
return ''.join(parts)
def format_text(self, text, strip=True):
if text is None:
return ''
if strip:
text = text.strip()
return html_escape(text, 1)
def format_tag(self, el):
attrs = []
if isinstance(el, etree.CommentBase):
# FIXME: probably PIs should be handled specially too?
return '<!--'
for name, value in sorted(el.attrib.items()):
attrs.append('%s="%s"' % (name, self.format_text(value, False)))
if not attrs:
return '<%s>' % el.tag
return '<%s %s>' % (el.tag, ' '.join(attrs))
def format_end_tag(self, el):
if isinstance(el, etree.CommentBase):
# FIXME: probably PIs should be handled specially too?
return '-->'
return '</%s>' % el.tag
def collect_diff(self, want, got, html, indent):
parts = []
if not len(want) and not len(got):
parts.append(' '*indent)
parts.append(self.collect_diff_tag(want, got))
if not self.html_empty_tag(got, html):
parts.append(self.collect_diff_text(want.text, got.text))
parts.append(self.collect_diff_end_tag(want, got))
parts.append(self.collect_diff_text(want.tail, got.tail))
parts.append('\n')
return ''.join(parts)
parts.append(' '*indent)
parts.append(self.collect_diff_tag(want, got))
parts.append('\n')
if strip(want.text) or strip(got.text):
parts.append(' '*indent)
parts.append(self.collect_diff_text(want.text, got.text))
parts.append('\n')
want_children = list(want)
got_children = list(got)
while want_children or got_children:
if not want_children:
parts.append(self.format_doc(got_children.pop(0), html, indent+2, '+'))
continue
if not got_children:
parts.append(self.format_doc(want_children.pop(0), html, indent+2, '-'))
continue
parts.append(self.collect_diff(
want_children.pop(0), got_children.pop(0), html, indent+2))
parts.append(' '*indent)
parts.append(self.collect_diff_end_tag(want, got))
parts.append('\n')
if strip(want.tail) or strip(got.tail):
parts.append(' '*indent)
parts.append(self.collect_diff_text(want.tail, got.tail))
parts.append('\n')
return ''.join(parts)
def collect_diff_tag(self, want, got):
if not self.tag_compare(want.tag, got.tag):
tag = '%s (got: %s)' % (want.tag, got.tag)
else:
tag = got.tag
attrs = []
any = want.tag == 'any' or 'any' in want.attrib
for name, value in sorted(got.attrib.items()):
if name not in want.attrib and not any:
attrs.append('+%s="%s"' % (name, self.format_text(value, False)))
else:
if name in want.attrib:
text = self.collect_diff_text(want.attrib[name], value, False)
else:
text = self.format_text(value, False)
attrs.append('%s="%s"' % (name, text))
if not any:
for name, value in sorted(want.attrib.items()):
if name in got.attrib:
continue
attrs.append('-%s="%s"' % (name, self.format_text(value, False)))
if attrs:
tag = '<%s %s>' % (tag, ' '.join(attrs))
else:
tag = '<%s>' % tag
return tag
def collect_diff_end_tag(self, want, got):
if want.tag != got.tag:
tag = '%s (got: %s)' % (want.tag, got.tag)
else:
tag = got.tag
return '</%s>' % tag
def collect_diff_text(self, want, got, strip=True):
if self.text_compare(want, got, strip):
if not got:
return ''
return self.format_text(got, strip)
text = '%s (got: %s)' % (want, got)
return self.format_text(text, strip)
class LHTMLOutputChecker(LXMLOutputChecker):
def get_default_parser(self):
return html_fromstring
def install(html=False):
"""
Install doctestcompare for all future doctests.
If html is true, then by default the HTML parser will be used;
otherwise the XML parser is used.
"""
if html:
doctest.OutputChecker = LHTMLOutputChecker
else:
doctest.OutputChecker = LXMLOutputChecker
def temp_install(html=False, del_module=None):
"""
Use this *inside* a doctest to enable this checker for this
doctest only.
If html is true, then by default the HTML parser will be used;
otherwise the XML parser is used.
"""
if html:
Checker = LHTMLOutputChecker
else:
Checker = LXMLOutputChecker
frame = _find_doctest_frame()
dt_self = frame.f_locals['self']
checker = Checker()
old_checker = dt_self._checker
dt_self._checker = checker
# The unfortunate thing is that there is a local variable 'check'
# in the function that runs the doctests, that is a bound method
# into the output checker. We have to update that. We can't
# modify the frame, so we have to modify the object in place. The
# only way to do this is to actually change the func_code
# attribute of the method. We change it, and then wait for
# __record_outcome to be run, which signals the end of the __run
# method, at which point we restore the previous check_output
# implementation.
if _IS_PYTHON_3:
check_func = frame.f_locals['check'].__func__
checker_check_func = checker.check_output.__func__
else:
check_func = frame.f_locals['check'].im_func
checker_check_func = checker.check_output.im_func
# Because we can't patch up func_globals, this is the only global
# in check_output that we care about:
doctest.etree = etree
_RestoreChecker(dt_self, old_checker, checker,
check_func, checker_check_func,
del_module)
class _RestoreChecker(object):
def __init__(self, dt_self, old_checker, new_checker, check_func, clone_func,
del_module):
self.dt_self = dt_self
self.checker = old_checker
self.checker._temp_call_super_check_output = self.call_super
self.checker._temp_override_self = new_checker
self.check_func = check_func
self.clone_func = clone_func
self.del_module = del_module
self.install_clone()
self.install_dt_self()
def install_clone(self):
if _IS_PYTHON_3:
self.func_code = self.check_func.__code__
self.func_globals = self.check_func.__globals__
self.check_func.__code__ = self.clone_func.__code__
else:
self.func_code = self.check_func.func_code
self.func_globals = self.check_func.func_globals
self.check_func.func_code = self.clone_func.func_code
def uninstall_clone(self):
if _IS_PYTHON_3:
self.check_func.__code__ = self.func_code
else:
self.check_func.func_code = self.func_code
def install_dt_self(self):
self.prev_func = self.dt_self._DocTestRunner__record_outcome
self.dt_self._DocTestRunner__record_outcome = self
def uninstall_dt_self(self):
self.dt_self._DocTestRunner__record_outcome = self.prev_func
def uninstall_module(self):
if self.del_module:
import sys
del sys.modules[self.del_module]
if '.' in self.del_module:
package, module = self.del_module.rsplit('.', 1)
package_mod = sys.modules[package]
delattr(package_mod, module)
def __call__(self, *args, **kw):
self.uninstall_clone()
self.uninstall_dt_self()
del self.checker._temp_override_self
del self.checker._temp_call_super_check_output
result = self.prev_func(*args, **kw)
self.uninstall_module()
return result
def call_super(self, *args, **kw):
self.uninstall_clone()
try:
return self.check_func(*args, **kw)
finally:
self.install_clone()
def _find_doctest_frame():
import sys
frame = sys._getframe(1)
while frame:
l = frame.f_locals
if 'BOOM' in l:
# Sign of doctest
return frame
frame = frame.f_back
raise LookupError(
"Could not find doctest (only use this function *inside* a doctest)")
__test__ = {
'basic': '''
>>> temp_install()
>>> print """<xml a="1" b="2">stuff</xml>"""
<xml b="2" a="1">...</xml>
>>> print """<xml xmlns="http://example.com"><tag attr="bar" /></xml>"""
<xml xmlns="...">
<tag attr="..." />
</xml>
>>> print """<xml>blahblahblah<foo /></xml>""" # doctest: +NOPARSE_MARKUP, +ELLIPSIS
<xml>...foo /></xml>
'''}
if __name__ == '__main__':
import doctest
doctest.testmod()

@ -0,0 +1,223 @@
/* Generated by Cython 0.29.2 */
#ifndef __PYX_HAVE__lxml__etree
#define __PYX_HAVE__lxml__etree
struct LxmlDocument;
struct LxmlElement;
struct LxmlElementTree;
struct LxmlElementTagMatcher;
struct LxmlElementIterator;
struct LxmlElementBase;
struct LxmlElementClassLookup;
struct LxmlFallbackElementClassLookup;
/* "lxml/etree.pyx":318
*
* # type of a function that steps from node to node
* ctypedef public xmlNode* (*_node_to_node_function)(xmlNode*) # <<<<<<<<<<<<<<
*
*
*/
typedef xmlNode *(*_node_to_node_function)(xmlNode *);
/* "lxml/etree.pyx":334
* @cython.final
* @cython.freelist(8)
* cdef public class _Document [ type LxmlDocumentType, object LxmlDocument ]: # <<<<<<<<<<<<<<
* u"""Internal base class to reference a libxml document.
*
*/
struct LxmlDocument {
PyObject_HEAD
struct __pyx_vtabstruct_4lxml_5etree__Document *__pyx_vtab;
int _ns_counter;
PyObject *_prefix_tail;
xmlDoc *_c_doc;
struct __pyx_obj_4lxml_5etree__BaseParser *_parser;
};
/* "lxml/etree.pyx":683
*
* @cython.no_gc_clear
* cdef public class _Element [ type LxmlElementType, object LxmlElement ]: # <<<<<<<<<<<<<<
* u"""Element class.
*
*/
struct LxmlElement {
PyObject_HEAD
struct LxmlDocument *_doc;
xmlNode *_c_node;
PyObject *_tag;
};
/* "lxml/etree.pyx":1847
*
*
* cdef public class _ElementTree [ type LxmlElementTreeType, # <<<<<<<<<<<<<<
* object LxmlElementTree ]:
* cdef _Document _doc
*/
struct LxmlElementTree {
PyObject_HEAD
struct __pyx_vtabstruct_4lxml_5etree__ElementTree *__pyx_vtab;
struct LxmlDocument *_doc;
struct LxmlElement *_context_node;
};
/* "lxml/etree.pyx":2574
*
*
* cdef public class _ElementTagMatcher [ object LxmlElementTagMatcher, # <<<<<<<<<<<<<<
* type LxmlElementTagMatcherType ]:
* """
*/
struct LxmlElementTagMatcher {
PyObject_HEAD
struct __pyx_vtabstruct_4lxml_5etree__ElementTagMatcher *__pyx_vtab;
PyObject *_pystrings;
int _node_type;
char *_href;
char *_name;
};
/* "lxml/etree.pyx":2605
* self._name = NULL
*
* cdef public class _ElementIterator(_ElementTagMatcher) [ # <<<<<<<<<<<<<<
* object LxmlElementIterator, type LxmlElementIteratorType ]:
* """
*/
struct LxmlElementIterator {
struct LxmlElementTagMatcher __pyx_base;
struct LxmlElement *_node;
_node_to_node_function _next_element;
};
/* "src/lxml/classlookup.pxi":6
* # Custom Element classes
*
* cdef public class ElementBase(_Element) [ type LxmlElementBaseType, # <<<<<<<<<<<<<<
* object LxmlElementBase ]:
* u"""ElementBase(*children, attrib=None, nsmap=None, **_extra)
*/
struct LxmlElementBase {
struct LxmlElement __pyx_base;
};
/* "src/lxml/classlookup.pxi":210
* # Element class lookup
*
* ctypedef public object (*_element_class_lookup_function)(object, _Document, xmlNode*) # <<<<<<<<<<<<<<
*
* # class to store element class lookup functions
*/
typedef PyObject *(*_element_class_lookup_function)(PyObject *, struct LxmlDocument *, xmlNode *);
/* "src/lxml/classlookup.pxi":213
*
* # class to store element class lookup functions
* cdef public class ElementClassLookup [ type LxmlElementClassLookupType, # <<<<<<<<<<<<<<
* object LxmlElementClassLookup ]:
* u"""ElementClassLookup(self)
*/
struct LxmlElementClassLookup {
PyObject_HEAD
_element_class_lookup_function _lookup_function;
};
/* "src/lxml/classlookup.pxi":221
*
*
* cdef public class FallbackElementClassLookup(ElementClassLookup) \ # <<<<<<<<<<<<<<
* [ type LxmlFallbackElementClassLookupType,
* object LxmlFallbackElementClassLookup ]:
*/
struct LxmlFallbackElementClassLookup {
struct LxmlElementClassLookup __pyx_base;
struct __pyx_vtabstruct_4lxml_5etree_FallbackElementClassLookup *__pyx_vtab;
struct LxmlElementClassLookup *fallback;
_element_class_lookup_function _fallback_function;
};
#ifndef __PYX_HAVE_API__lxml__etree
#ifndef __PYX_EXTERN_C
#ifdef __cplusplus
#define __PYX_EXTERN_C extern "C"
#else
#define __PYX_EXTERN_C extern
#endif
#endif
#ifndef DL_IMPORT
#define DL_IMPORT(_T) _T
#endif
__PYX_EXTERN_C DL_IMPORT(PyTypeObject) LxmlDocumentType;
__PYX_EXTERN_C DL_IMPORT(PyTypeObject) LxmlElementType;
__PYX_EXTERN_C DL_IMPORT(PyTypeObject) LxmlElementTreeType;
__PYX_EXTERN_C DL_IMPORT(PyTypeObject) LxmlElementTagMatcherType;
__PYX_EXTERN_C DL_IMPORT(PyTypeObject) LxmlElementIteratorType;
__PYX_EXTERN_C DL_IMPORT(PyTypeObject) LxmlElementBaseType;
__PYX_EXTERN_C DL_IMPORT(PyTypeObject) LxmlElementClassLookupType;
__PYX_EXTERN_C DL_IMPORT(PyTypeObject) LxmlFallbackElementClassLookupType;
__PYX_EXTERN_C struct LxmlElement *deepcopyNodeToDocument(struct LxmlDocument *, xmlNode *);
__PYX_EXTERN_C struct LxmlElementTree *elementTreeFactory(struct LxmlElement *);
__PYX_EXTERN_C struct LxmlElementTree *newElementTree(struct LxmlElement *, PyObject *);
__PYX_EXTERN_C struct LxmlElementTree *adoptExternalDocument(xmlDoc *, PyObject *, int);
__PYX_EXTERN_C struct LxmlElement *elementFactory(struct LxmlDocument *, xmlNode *);
__PYX_EXTERN_C struct LxmlElement *makeElement(PyObject *, struct LxmlDocument *, PyObject *, PyObject *, PyObject *, PyObject *, PyObject *);
__PYX_EXTERN_C struct LxmlElement *makeSubElement(struct LxmlElement *, PyObject *, PyObject *, PyObject *, PyObject *, PyObject *);
__PYX_EXTERN_C void setElementClassLookupFunction(_element_class_lookup_function, PyObject *);
__PYX_EXTERN_C PyObject *lookupDefaultElementClass(PyObject *, PyObject *, xmlNode *);
__PYX_EXTERN_C PyObject *lookupNamespaceElementClass(PyObject *, PyObject *, xmlNode *);
__PYX_EXTERN_C PyObject *callLookupFallback(struct LxmlFallbackElementClassLookup *, struct LxmlDocument *, xmlNode *);
__PYX_EXTERN_C int tagMatches(xmlNode *, const xmlChar *, const xmlChar *);
__PYX_EXTERN_C struct LxmlDocument *documentOrRaise(PyObject *);
__PYX_EXTERN_C struct LxmlElement *rootNodeOrRaise(PyObject *);
__PYX_EXTERN_C int hasText(xmlNode *);
__PYX_EXTERN_C int hasTail(xmlNode *);
__PYX_EXTERN_C PyObject *textOf(xmlNode *);
__PYX_EXTERN_C PyObject *tailOf(xmlNode *);
__PYX_EXTERN_C int setNodeText(xmlNode *, PyObject *);
__PYX_EXTERN_C int setTailText(xmlNode *, PyObject *);
__PYX_EXTERN_C PyObject *attributeValue(xmlNode *, xmlAttr *);
__PYX_EXTERN_C PyObject *attributeValueFromNsName(xmlNode *, const xmlChar *, const xmlChar *);
__PYX_EXTERN_C PyObject *getAttributeValue(struct LxmlElement *, PyObject *, PyObject *);
__PYX_EXTERN_C PyObject *iterattributes(struct LxmlElement *, int);
__PYX_EXTERN_C PyObject *collectAttributes(xmlNode *, int);
__PYX_EXTERN_C int setAttributeValue(struct LxmlElement *, PyObject *, PyObject *);
__PYX_EXTERN_C int delAttribute(struct LxmlElement *, PyObject *);
__PYX_EXTERN_C int delAttributeFromNsName(xmlNode *, const xmlChar *, const xmlChar *);
__PYX_EXTERN_C int hasChild(xmlNode *);
__PYX_EXTERN_C xmlNode *findChild(xmlNode *, Py_ssize_t);
__PYX_EXTERN_C xmlNode *findChildForwards(xmlNode *, Py_ssize_t);
__PYX_EXTERN_C xmlNode *findChildBackwards(xmlNode *, Py_ssize_t);
__PYX_EXTERN_C xmlNode *nextElement(xmlNode *);
__PYX_EXTERN_C xmlNode *previousElement(xmlNode *);
__PYX_EXTERN_C void appendChild(struct LxmlElement *, struct LxmlElement *);
__PYX_EXTERN_C int appendChildToElement(struct LxmlElement *, struct LxmlElement *);
__PYX_EXTERN_C PyObject *pyunicode(const xmlChar *);
__PYX_EXTERN_C PyObject *utf8(PyObject *);
__PYX_EXTERN_C PyObject *getNsTag(PyObject *);
__PYX_EXTERN_C PyObject *getNsTagWithEmptyNs(PyObject *);
__PYX_EXTERN_C PyObject *namespacedName(xmlNode *);
__PYX_EXTERN_C PyObject *namespacedNameFromNsName(const xmlChar *, const xmlChar *);
__PYX_EXTERN_C void iteratorStoreNext(struct LxmlElementIterator *, struct LxmlElement *);
__PYX_EXTERN_C void initTagMatch(struct LxmlElementTagMatcher *, PyObject *);
__PYX_EXTERN_C xmlNs *findOrBuildNodeNsPrefix(struct LxmlDocument *, xmlNode *, const xmlChar *, const xmlChar *);
#endif /* !__PYX_HAVE_API__lxml__etree */
/* WARNING: the interface of the module init function changed in CPython 3.5. */
/* It now returns a PyModuleDef instance instead of a PyModule instance. */
#if PY_MAJOR_VERSION < 3
PyMODINIT_FUNC initetree(void);
#else
PyMODINIT_FUNC PyInit_etree(void);
#endif
#endif /* !__PYX_HAVE__lxml__etree */

Binary file not shown.

@ -0,0 +1,219 @@
/* Generated by Cython 0.29.2 */
#ifndef __PYX_HAVE_API__lxml__etree
#define __PYX_HAVE_API__lxml__etree
#ifdef __MINGW64__
#define MS_WIN64
#endif
#include "Python.h"
#include "etree.h"
static struct LxmlElement *(*__pyx_api_f_4lxml_5etree_deepcopyNodeToDocument)(struct LxmlDocument *, xmlNode *) = 0;
#define deepcopyNodeToDocument __pyx_api_f_4lxml_5etree_deepcopyNodeToDocument
static struct LxmlElementTree *(*__pyx_api_f_4lxml_5etree_elementTreeFactory)(struct LxmlElement *) = 0;
#define elementTreeFactory __pyx_api_f_4lxml_5etree_elementTreeFactory
static struct LxmlElementTree *(*__pyx_api_f_4lxml_5etree_newElementTree)(struct LxmlElement *, PyObject *) = 0;
#define newElementTree __pyx_api_f_4lxml_5etree_newElementTree
static struct LxmlElementTree *(*__pyx_api_f_4lxml_5etree_adoptExternalDocument)(xmlDoc *, PyObject *, int) = 0;
#define adoptExternalDocument __pyx_api_f_4lxml_5etree_adoptExternalDocument
static struct LxmlElement *(*__pyx_api_f_4lxml_5etree_elementFactory)(struct LxmlDocument *, xmlNode *) = 0;
#define elementFactory __pyx_api_f_4lxml_5etree_elementFactory
static struct LxmlElement *(*__pyx_api_f_4lxml_5etree_makeElement)(PyObject *, struct LxmlDocument *, PyObject *, PyObject *, PyObject *, PyObject *, PyObject *) = 0;
#define makeElement __pyx_api_f_4lxml_5etree_makeElement
static struct LxmlElement *(*__pyx_api_f_4lxml_5etree_makeSubElement)(struct LxmlElement *, PyObject *, PyObject *, PyObject *, PyObject *, PyObject *) = 0;
#define makeSubElement __pyx_api_f_4lxml_5etree_makeSubElement
static void (*__pyx_api_f_4lxml_5etree_setElementClassLookupFunction)(_element_class_lookup_function, PyObject *) = 0;
#define setElementClassLookupFunction __pyx_api_f_4lxml_5etree_setElementClassLookupFunction
static PyObject *(*__pyx_api_f_4lxml_5etree_lookupDefaultElementClass)(PyObject *, PyObject *, xmlNode *) = 0;
#define lookupDefaultElementClass __pyx_api_f_4lxml_5etree_lookupDefaultElementClass
static PyObject *(*__pyx_api_f_4lxml_5etree_lookupNamespaceElementClass)(PyObject *, PyObject *, xmlNode *) = 0;
#define lookupNamespaceElementClass __pyx_api_f_4lxml_5etree_lookupNamespaceElementClass
static PyObject *(*__pyx_api_f_4lxml_5etree_callLookupFallback)(struct LxmlFallbackElementClassLookup *, struct LxmlDocument *, xmlNode *) = 0;
#define callLookupFallback __pyx_api_f_4lxml_5etree_callLookupFallback
static int (*__pyx_api_f_4lxml_5etree_tagMatches)(xmlNode *, const xmlChar *, const xmlChar *) = 0;
#define tagMatches __pyx_api_f_4lxml_5etree_tagMatches
static struct LxmlDocument *(*__pyx_api_f_4lxml_5etree_documentOrRaise)(PyObject *) = 0;
#define documentOrRaise __pyx_api_f_4lxml_5etree_documentOrRaise
static struct LxmlElement *(*__pyx_api_f_4lxml_5etree_rootNodeOrRaise)(PyObject *) = 0;
#define rootNodeOrRaise __pyx_api_f_4lxml_5etree_rootNodeOrRaise
static int (*__pyx_api_f_4lxml_5etree_hasText)(xmlNode *) = 0;
#define hasText __pyx_api_f_4lxml_5etree_hasText
static int (*__pyx_api_f_4lxml_5etree_hasTail)(xmlNode *) = 0;
#define hasTail __pyx_api_f_4lxml_5etree_hasTail
static PyObject *(*__pyx_api_f_4lxml_5etree_textOf)(xmlNode *) = 0;
#define textOf __pyx_api_f_4lxml_5etree_textOf
static PyObject *(*__pyx_api_f_4lxml_5etree_tailOf)(xmlNode *) = 0;
#define tailOf __pyx_api_f_4lxml_5etree_tailOf
static int (*__pyx_api_f_4lxml_5etree_setNodeText)(xmlNode *, PyObject *) = 0;
#define setNodeText __pyx_api_f_4lxml_5etree_setNodeText
static int (*__pyx_api_f_4lxml_5etree_setTailText)(xmlNode *, PyObject *) = 0;
#define setTailText __pyx_api_f_4lxml_5etree_setTailText
static PyObject *(*__pyx_api_f_4lxml_5etree_attributeValue)(xmlNode *, xmlAttr *) = 0;
#define attributeValue __pyx_api_f_4lxml_5etree_attributeValue
static PyObject *(*__pyx_api_f_4lxml_5etree_attributeValueFromNsName)(xmlNode *, const xmlChar *, const xmlChar *) = 0;
#define attributeValueFromNsName __pyx_api_f_4lxml_5etree_attributeValueFromNsName
static PyObject *(*__pyx_api_f_4lxml_5etree_getAttributeValue)(struct LxmlElement *, PyObject *, PyObject *) = 0;
#define getAttributeValue __pyx_api_f_4lxml_5etree_getAttributeValue
static PyObject *(*__pyx_api_f_4lxml_5etree_iterattributes)(struct LxmlElement *, int) = 0;
#define iterattributes __pyx_api_f_4lxml_5etree_iterattributes
static PyObject *(*__pyx_api_f_4lxml_5etree_collectAttributes)(xmlNode *, int) = 0;
#define collectAttributes __pyx_api_f_4lxml_5etree_collectAttributes
static int (*__pyx_api_f_4lxml_5etree_setAttributeValue)(struct LxmlElement *, PyObject *, PyObject *) = 0;
#define setAttributeValue __pyx_api_f_4lxml_5etree_setAttributeValue
static int (*__pyx_api_f_4lxml_5etree_delAttribute)(struct LxmlElement *, PyObject *) = 0;
#define delAttribute __pyx_api_f_4lxml_5etree_delAttribute
static int (*__pyx_api_f_4lxml_5etree_delAttributeFromNsName)(xmlNode *, const xmlChar *, const xmlChar *) = 0;
#define delAttributeFromNsName __pyx_api_f_4lxml_5etree_delAttributeFromNsName
static int (*__pyx_api_f_4lxml_5etree_hasChild)(xmlNode *) = 0;
#define hasChild __pyx_api_f_4lxml_5etree_hasChild
static xmlNode *(*__pyx_api_f_4lxml_5etree_findChild)(xmlNode *, Py_ssize_t) = 0;
#define findChild __pyx_api_f_4lxml_5etree_findChild
static xmlNode *(*__pyx_api_f_4lxml_5etree_findChildForwards)(xmlNode *, Py_ssize_t) = 0;
#define findChildForwards __pyx_api_f_4lxml_5etree_findChildForwards
static xmlNode *(*__pyx_api_f_4lxml_5etree_findChildBackwards)(xmlNode *, Py_ssize_t) = 0;
#define findChildBackwards __pyx_api_f_4lxml_5etree_findChildBackwards
static xmlNode *(*__pyx_api_f_4lxml_5etree_nextElement)(xmlNode *) = 0;
#define nextElement __pyx_api_f_4lxml_5etree_nextElement
static xmlNode *(*__pyx_api_f_4lxml_5etree_previousElement)(xmlNode *) = 0;
#define previousElement __pyx_api_f_4lxml_5etree_previousElement
static void (*__pyx_api_f_4lxml_5etree_appendChild)(struct LxmlElement *, struct LxmlElement *) = 0;
#define appendChild __pyx_api_f_4lxml_5etree_appendChild
static int (*__pyx_api_f_4lxml_5etree_appendChildToElement)(struct LxmlElement *, struct LxmlElement *) = 0;
#define appendChildToElement __pyx_api_f_4lxml_5etree_appendChildToElement
static PyObject *(*__pyx_api_f_4lxml_5etree_pyunicode)(const xmlChar *) = 0;
#define pyunicode __pyx_api_f_4lxml_5etree_pyunicode
static PyObject *(*__pyx_api_f_4lxml_5etree_utf8)(PyObject *) = 0;
#define utf8 __pyx_api_f_4lxml_5etree_utf8
static PyObject *(*__pyx_api_f_4lxml_5etree_getNsTag)(PyObject *) = 0;
#define getNsTag __pyx_api_f_4lxml_5etree_getNsTag
static PyObject *(*__pyx_api_f_4lxml_5etree_getNsTagWithEmptyNs)(PyObject *) = 0;
#define getNsTagWithEmptyNs __pyx_api_f_4lxml_5etree_getNsTagWithEmptyNs
static PyObject *(*__pyx_api_f_4lxml_5etree_namespacedName)(xmlNode *) = 0;
#define namespacedName __pyx_api_f_4lxml_5etree_namespacedName
static PyObject *(*__pyx_api_f_4lxml_5etree_namespacedNameFromNsName)(const xmlChar *, const xmlChar *) = 0;
#define namespacedNameFromNsName __pyx_api_f_4lxml_5etree_namespacedNameFromNsName
static void (*__pyx_api_f_4lxml_5etree_iteratorStoreNext)(struct LxmlElementIterator *, struct LxmlElement *) = 0;
#define iteratorStoreNext __pyx_api_f_4lxml_5etree_iteratorStoreNext
static void (*__pyx_api_f_4lxml_5etree_initTagMatch)(struct LxmlElementTagMatcher *, PyObject *) = 0;
#define initTagMatch __pyx_api_f_4lxml_5etree_initTagMatch
static xmlNs *(*__pyx_api_f_4lxml_5etree_findOrBuildNodeNsPrefix)(struct LxmlDocument *, xmlNode *, const xmlChar *, const xmlChar *) = 0;
#define findOrBuildNodeNsPrefix __pyx_api_f_4lxml_5etree_findOrBuildNodeNsPrefix
#if !defined(__Pyx_PyIdentifier_FromString)
#if PY_MAJOR_VERSION < 3
#define __Pyx_PyIdentifier_FromString(s) PyString_FromString(s)
#else
#define __Pyx_PyIdentifier_FromString(s) PyUnicode_FromString(s)
#endif
#endif
#ifndef __PYX_HAVE_RT_ImportFunction
#define __PYX_HAVE_RT_ImportFunction
static int __Pyx_ImportFunction(PyObject *module, const char *funcname, void (**f)(void), const char *sig) {
PyObject *d = 0;
PyObject *cobj = 0;
union {
void (*fp)(void);
void *p;
} tmp;
d = PyObject_GetAttrString(module, (char *)"__pyx_capi__");
if (!d)
goto bad;
cobj = PyDict_GetItemString(d, funcname);
if (!cobj) {
PyErr_Format(PyExc_ImportError,
"%.200s does not export expected C function %.200s",
PyModule_GetName(module), funcname);
goto bad;
}
#if PY_VERSION_HEX >= 0x02070000
if (!PyCapsule_IsValid(cobj, sig)) {
PyErr_Format(PyExc_TypeError,
"C function %.200s.%.200s has wrong signature (expected %.500s, got %.500s)",
PyModule_GetName(module), funcname, sig, PyCapsule_GetName(cobj));
goto bad;
}
tmp.p = PyCapsule_GetPointer(cobj, sig);
#else
{const char *desc, *s1, *s2;
desc = (const char *)PyCObject_GetDesc(cobj);
if (!desc)
goto bad;
s1 = desc; s2 = sig;
while (*s1 != '\0' && *s1 == *s2) { s1++; s2++; }
if (*s1 != *s2) {
PyErr_Format(PyExc_TypeError,
"C function %.200s.%.200s has wrong signature (expected %.500s, got %.500s)",
PyModule_GetName(module), funcname, sig, desc);
goto bad;
}
tmp.p = PyCObject_AsVoidPtr(cobj);}
#endif
*f = tmp.fp;
if (!(*f))
goto bad;
Py_DECREF(d);
return 0;
bad:
Py_XDECREF(d);
return -1;
}
#endif
static int import_lxml__etree(void) {
PyObject *module = 0;
module = PyImport_ImportModule("lxml.etree");
if (!module) goto bad;
if (__Pyx_ImportFunction(module, "deepcopyNodeToDocument", (void (**)(void))&__pyx_api_f_4lxml_5etree_deepcopyNodeToDocument, "struct LxmlElement *(struct LxmlDocument *, xmlNode *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "elementTreeFactory", (void (**)(void))&__pyx_api_f_4lxml_5etree_elementTreeFactory, "struct LxmlElementTree *(struct LxmlElement *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "newElementTree", (void (**)(void))&__pyx_api_f_4lxml_5etree_newElementTree, "struct LxmlElementTree *(struct LxmlElement *, PyObject *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "adoptExternalDocument", (void (**)(void))&__pyx_api_f_4lxml_5etree_adoptExternalDocument, "struct LxmlElementTree *(xmlDoc *, PyObject *, int)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "elementFactory", (void (**)(void))&__pyx_api_f_4lxml_5etree_elementFactory, "struct LxmlElement *(struct LxmlDocument *, xmlNode *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "makeElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_makeElement, "struct LxmlElement *(PyObject *, struct LxmlDocument *, PyObject *, PyObject *, PyObject *, PyObject *, PyObject *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "makeSubElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_makeSubElement, "struct LxmlElement *(struct LxmlElement *, PyObject *, PyObject *, PyObject *, PyObject *, PyObject *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "setElementClassLookupFunction", (void (**)(void))&__pyx_api_f_4lxml_5etree_setElementClassLookupFunction, "void (_element_class_lookup_function, PyObject *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "lookupDefaultElementClass", (void (**)(void))&__pyx_api_f_4lxml_5etree_lookupDefaultElementClass, "PyObject *(PyObject *, PyObject *, xmlNode *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "lookupNamespaceElementClass", (void (**)(void))&__pyx_api_f_4lxml_5etree_lookupNamespaceElementClass, "PyObject *(PyObject *, PyObject *, xmlNode *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "callLookupFallback", (void (**)(void))&__pyx_api_f_4lxml_5etree_callLookupFallback, "PyObject *(struct LxmlFallbackElementClassLookup *, struct LxmlDocument *, xmlNode *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "tagMatches", (void (**)(void))&__pyx_api_f_4lxml_5etree_tagMatches, "int (xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "documentOrRaise", (void (**)(void))&__pyx_api_f_4lxml_5etree_documentOrRaise, "struct LxmlDocument *(PyObject *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "rootNodeOrRaise", (void (**)(void))&__pyx_api_f_4lxml_5etree_rootNodeOrRaise, "struct LxmlElement *(PyObject *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "hasText", (void (**)(void))&__pyx_api_f_4lxml_5etree_hasText, "int (xmlNode *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "hasTail", (void (**)(void))&__pyx_api_f_4lxml_5etree_hasTail, "int (xmlNode *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "textOf", (void (**)(void))&__pyx_api_f_4lxml_5etree_textOf, "PyObject *(xmlNode *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "tailOf", (void (**)(void))&__pyx_api_f_4lxml_5etree_tailOf, "PyObject *(xmlNode *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "setNodeText", (void (**)(void))&__pyx_api_f_4lxml_5etree_setNodeText, "int (xmlNode *, PyObject *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "setTailText", (void (**)(void))&__pyx_api_f_4lxml_5etree_setTailText, "int (xmlNode *, PyObject *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "attributeValue", (void (**)(void))&__pyx_api_f_4lxml_5etree_attributeValue, "PyObject *(xmlNode *, xmlAttr *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "attributeValueFromNsName", (void (**)(void))&__pyx_api_f_4lxml_5etree_attributeValueFromNsName, "PyObject *(xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "getAttributeValue", (void (**)(void))&__pyx_api_f_4lxml_5etree_getAttributeValue, "PyObject *(struct LxmlElement *, PyObject *, PyObject *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "iterattributes", (void (**)(void))&__pyx_api_f_4lxml_5etree_iterattributes, "PyObject *(struct LxmlElement *, int)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "collectAttributes", (void (**)(void))&__pyx_api_f_4lxml_5etree_collectAttributes, "PyObject *(xmlNode *, int)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "setAttributeValue", (void (**)(void))&__pyx_api_f_4lxml_5etree_setAttributeValue, "int (struct LxmlElement *, PyObject *, PyObject *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "delAttribute", (void (**)(void))&__pyx_api_f_4lxml_5etree_delAttribute, "int (struct LxmlElement *, PyObject *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "delAttributeFromNsName", (void (**)(void))&__pyx_api_f_4lxml_5etree_delAttributeFromNsName, "int (xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "hasChild", (void (**)(void))&__pyx_api_f_4lxml_5etree_hasChild, "int (xmlNode *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "findChild", (void (**)(void))&__pyx_api_f_4lxml_5etree_findChild, "xmlNode *(xmlNode *, Py_ssize_t)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "findChildForwards", (void (**)(void))&__pyx_api_f_4lxml_5etree_findChildForwards, "xmlNode *(xmlNode *, Py_ssize_t)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "findChildBackwards", (void (**)(void))&__pyx_api_f_4lxml_5etree_findChildBackwards, "xmlNode *(xmlNode *, Py_ssize_t)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "nextElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_nextElement, "xmlNode *(xmlNode *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "previousElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_previousElement, "xmlNode *(xmlNode *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "appendChild", (void (**)(void))&__pyx_api_f_4lxml_5etree_appendChild, "void (struct LxmlElement *, struct LxmlElement *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "appendChildToElement", (void (**)(void))&__pyx_api_f_4lxml_5etree_appendChildToElement, "int (struct LxmlElement *, struct LxmlElement *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "pyunicode", (void (**)(void))&__pyx_api_f_4lxml_5etree_pyunicode, "PyObject *(const xmlChar *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "utf8", (void (**)(void))&__pyx_api_f_4lxml_5etree_utf8, "PyObject *(PyObject *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "getNsTag", (void (**)(void))&__pyx_api_f_4lxml_5etree_getNsTag, "PyObject *(PyObject *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "getNsTagWithEmptyNs", (void (**)(void))&__pyx_api_f_4lxml_5etree_getNsTagWithEmptyNs, "PyObject *(PyObject *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "namespacedName", (void (**)(void))&__pyx_api_f_4lxml_5etree_namespacedName, "PyObject *(xmlNode *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "namespacedNameFromNsName", (void (**)(void))&__pyx_api_f_4lxml_5etree_namespacedNameFromNsName, "PyObject *(const xmlChar *, const xmlChar *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "iteratorStoreNext", (void (**)(void))&__pyx_api_f_4lxml_5etree_iteratorStoreNext, "void (struct LxmlElementIterator *, struct LxmlElement *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "initTagMatch", (void (**)(void))&__pyx_api_f_4lxml_5etree_initTagMatch, "void (struct LxmlElementTagMatcher *, PyObject *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "findOrBuildNodeNsPrefix", (void (**)(void))&__pyx_api_f_4lxml_5etree_findOrBuildNodeNsPrefix, "xmlNs *(struct LxmlDocument *, xmlNode *, const xmlChar *, const xmlChar *)") < 0) goto bad;
Py_DECREF(module); module = 0;
return 0;
bad:
Py_XDECREF(module);
return -1;
}
#endif /* !__PYX_HAVE_API__lxml__etree */

@ -0,0 +1,10 @@
__doc__ = """Legacy interface to the BeautifulSoup HTML parser.
"""
__all__ = ["parse", "convert_tree"]
from soupparser import convert_tree, parse as _parse
def parse(file, beautifulsoup=None, makeelement=None):
root = _parse(file, beautifulsoup=beautifulsoup, makeelement=makeelement)
return root.getroot()

File diff suppressed because it is too large Load Diff

@ -0,0 +1,90 @@
from __future__ import absolute_import
import optparse
import sys
import re
import os
from .diff import htmldiff
description = """\
"""
parser = optparse.OptionParser(
usage="%prog [OPTIONS] FILE1 FILE2\n"
"%prog --annotate [OPTIONS] INFO1 FILE1 INFO2 FILE2 ...",
description=description,
)
parser.add_option(
'-o', '--output',
metavar="FILE",
dest="output",
default="-",
help="File to write the difference to",
)
parser.add_option(
'-a', '--annotation',
action="store_true",
dest="annotation",
help="Do an annotation")
def main(args=None):
if args is None:
args = sys.argv[1:]
options, args = parser.parse_args(args)
if options.annotation:
return annotate(options, args)
if len(args) != 2:
print('Error: you must give two files')
parser.print_help()
sys.exit(1)
file1, file2 = args
input1 = read_file(file1)
input2 = read_file(file2)
body1 = split_body(input1)[1]
pre, body2, post = split_body(input2)
result = htmldiff(body1, body2)
result = pre + result + post
if options.output == '-':
if not result.endswith('\n'):
result += '\n'
sys.stdout.write(result)
else:
f = open(options.output, 'wb')
f.write(result)
f.close()
def read_file(filename):
if filename == '-':
c = sys.stdin.read()
elif not os.path.exists(filename):
raise OSError(
"Input file %s does not exist" % filename)
else:
f = open(filename, 'rb')
c = f.read()
f.close()
return c
body_start_re = re.compile(
r"<body.*?>", re.I|re.S)
body_end_re = re.compile(
r"</body.*?>", re.I|re.S)
def split_body(html):
pre = post = ''
match = body_start_re.search(html)
if match:
pre = html[:match.end()]
html = html[match.end():]
match = body_end_re.search(html)
if match:
post = html[match.start():]
html = html[:match.start()]
return pre, html, post
def annotate(options, args):
print("Not yet implemented")
sys.exit(1)

@ -0,0 +1,100 @@
"""
Legacy module - don't use in new code!
html5lib now has its own proper implementation.
This module implements a tree builder for html5lib that generates lxml
html element trees. This module uses camelCase as it follows the
html5lib style guide.
"""
from html5lib.treebuilders import _base, etree as etree_builders
from lxml import html, etree
class DocumentType(object):
def __init__(self, name, publicId, systemId):
self.name = name
self.publicId = publicId
self.systemId = systemId
class Document(object):
def __init__(self):
self._elementTree = None
self.childNodes = []
def appendChild(self, element):
self._elementTree.getroot().addnext(element._element)
class TreeBuilder(_base.TreeBuilder):
documentClass = Document
doctypeClass = DocumentType
elementClass = None
commentClass = None
fragmentClass = Document
def __init__(self, *args, **kwargs):
html_builder = etree_builders.getETreeModule(html, fullTree=False)
etree_builder = etree_builders.getETreeModule(etree, fullTree=False)
self.elementClass = html_builder.Element
self.commentClass = etree_builder.Comment
_base.TreeBuilder.__init__(self, *args, **kwargs)
def reset(self):
_base.TreeBuilder.reset(self)
self.rootInserted = False
self.initialComments = []
self.doctype = None
def getDocument(self):
return self.document._elementTree
def getFragment(self):
fragment = []
element = self.openElements[0]._element
if element.text:
fragment.append(element.text)
fragment.extend(element.getchildren())
if element.tail:
fragment.append(element.tail)
return fragment
def insertDoctype(self, name, publicId, systemId):
doctype = self.doctypeClass(name, publicId, systemId)
self.doctype = doctype
def insertComment(self, data, parent=None):
if not self.rootInserted:
self.initialComments.append(data)
else:
_base.TreeBuilder.insertComment(self, data, parent)
def insertRoot(self, name):
buf = []
if self.doctype and self.doctype.name:
buf.append('<!DOCTYPE %s' % self.doctype.name)
if self.doctype.publicId is not None or self.doctype.systemId is not None:
buf.append(' PUBLIC "%s" "%s"' % (self.doctype.publicId,
self.doctype.systemId))
buf.append('>')
buf.append('<html></html>')
root = html.fromstring(''.join(buf))
# Append the initial comments:
for comment in self.initialComments:
root.addprevious(etree.Comment(comment))
# Create the root document and add the ElementTree to it
self.document = self.documentClass()
self.document._elementTree = root.getroottree()
# Add the root element to the internal child/open data structures
root_element = self.elementClass(name)
root_element._element = root
self.document.childNodes.append(root_element)
self.openElements.append(root_element)
self.rootInserted = True

@ -0,0 +1,56 @@
try:
from collections.abc import MutableSet
except ImportError:
from collections import MutableSet
class SetMixin(MutableSet):
"""
Mix-in for sets. You must define __iter__, add, remove
"""
def __len__(self):
length = 0
for item in self:
length += 1
return length
def __contains__(self, item):
for has_item in self:
if item == has_item:
return True
return False
issubset = MutableSet.__le__
issuperset = MutableSet.__ge__
union = MutableSet.__or__
intersection = MutableSet.__and__
difference = MutableSet.__sub__
symmetric_difference = MutableSet.__xor__
def copy(self):
return set(self)
def update(self, other):
self |= other
def intersection_update(self, other):
self &= other
def difference_update(self, other):
self -= other
def symmetric_difference_update(self, other):
self ^= other
def discard(self, item):
try:
self.remove(item)
except KeyError:
pass
@classmethod
def _from_iterable(cls, it):
return set(it)

@ -0,0 +1,133 @@
# --------------------------------------------------------------------
# The ElementTree toolkit is
# Copyright (c) 1999-2004 by Fredrik Lundh
# --------------------------------------------------------------------
"""
A set of HTML generator tags for building HTML documents.
Usage::
>>> from lxml.html.builder import *
>>> html = HTML(
... HEAD( TITLE("Hello World") ),
... BODY( CLASS("main"),
... H1("Hello World !")
... )
... )
>>> import lxml.etree
>>> print lxml.etree.tostring(html, pretty_print=True)
<html>
<head>
<title>Hello World</title>
</head>
<body class="main">
<h1>Hello World !</h1>
</body>
</html>
"""
from lxml.builder import ElementMaker
from lxml.html import html_parser
E = ElementMaker(makeelement=html_parser.makeelement)
# elements
A = E.a # anchor
ABBR = E.abbr # abbreviated form (e.g., WWW, HTTP, etc.)
ACRONYM = E.acronym #
ADDRESS = E.address # information on author
APPLET = E.applet # Java applet (DEPRECATED)
AREA = E.area # client-side image map area
B = E.b # bold text style
BASE = E.base # document base URI
BASEFONT = E.basefont # base font size (DEPRECATED)
BDO = E.bdo # I18N BiDi over-ride
BIG = E.big # large text style
BLOCKQUOTE = E.blockquote # long quotation
BODY = E.body # document body
BR = E.br # forced line break
BUTTON = E.button # push button
CAPTION = E.caption # table caption
CENTER = E.center # shorthand for DIV align=center (DEPRECATED)
CITE = E.cite # citation
CODE = E.code # computer code fragment
COL = E.col # table column
COLGROUP = E.colgroup # table column group
DD = E.dd # definition description
DEL = getattr(E, 'del') # deleted text
DFN = E.dfn # instance definition
DIR = E.dir # directory list (DEPRECATED)
DIV = E.div # generic language/style container
DL = E.dl # definition list
DT = E.dt # definition term
EM = E.em # emphasis
FIELDSET = E.fieldset # form control group
FONT = E.font # local change to font (DEPRECATED)
FORM = E.form # interactive form
FRAME = E.frame # subwindow
FRAMESET = E.frameset # window subdivision
H1 = E.h1 # heading
H2 = E.h2 # heading
H3 = E.h3 # heading
H4 = E.h4 # heading
H5 = E.h5 # heading
H6 = E.h6 # heading
HEAD = E.head # document head
HR = E.hr # horizontal rule
HTML = E.html # document root element
I = E.i # italic text style
IFRAME = E.iframe # inline subwindow
IMG = E.img # Embedded image
INPUT = E.input # form control
INS = E.ins # inserted text
ISINDEX = E.isindex # single line prompt (DEPRECATED)
KBD = E.kbd # text to be entered by the user
LABEL = E.label # form field label text
LEGEND = E.legend # fieldset legend
LI = E.li # list item
LINK = E.link # a media-independent link
MAP = E.map # client-side image map
MENU = E.menu # menu list (DEPRECATED)
META = E.meta # generic metainformation
NOFRAMES = E.noframes # alternate content container for non frame-based rendering
NOSCRIPT = E.noscript # alternate content container for non script-based rendering
OBJECT = E.object # generic embedded object
OL = E.ol # ordered list
OPTGROUP = E.optgroup # option group
OPTION = E.option # selectable choice
P = E.p # paragraph
PARAM = E.param # named property value
PRE = E.pre # preformatted text
Q = E.q # short inline quotation
S = E.s # strike-through text style (DEPRECATED)
SAMP = E.samp # sample program output, scripts, etc.
SCRIPT = E.script # script statements
SELECT = E.select # option selector
SMALL = E.small # small text style
SPAN = E.span # generic language/style container
STRIKE = E.strike # strike-through text (DEPRECATED)
STRONG = E.strong # strong emphasis
STYLE = E.style # style info
SUB = E.sub # subscript
SUP = E.sup # superscript
TABLE = E.table #
TBODY = E.tbody # table body
TD = E.td # table data cell
TEXTAREA = E.textarea # multi-line text field
TFOOT = E.tfoot # table footer
TH = E.th # table header cell
THEAD = E.thead # table header
TITLE = E.title # document title
TR = E.tr # table row
TT = E.tt # teletype or monospaced text style
U = E.u # underlined text style (DEPRECATED)
UL = E.ul # unordered list
VAR = E.var # instance of a variable or program argument
# attributes (only reserved words are included here)
ATTR = dict
def CLASS(v): return {'class': v}
def FOR(v): return {'for': v}

@ -0,0 +1,741 @@
# cython: language_level=2
"""A cleanup tool for HTML.
Removes unwanted tags and content. See the `Cleaner` class for
details.
"""
from __future__ import absolute_import
import re
import copy
try:
from urlparse import urlsplit
from urllib import unquote_plus
except ImportError:
# Python 3
from urllib.parse import urlsplit, unquote_plus
from lxml import etree
from lxml.html import defs
from lxml.html import fromstring, XHTML_NAMESPACE
from lxml.html import xhtml_to_html, _transform_result
try:
unichr
except NameError:
# Python 3
unichr = chr
try:
unicode
except NameError:
# Python 3
unicode = str
try:
basestring
except NameError:
basestring = (str, bytes)
__all__ = ['clean_html', 'clean', 'Cleaner', 'autolink', 'autolink_html',
'word_break', 'word_break_html']
# Look at http://code.sixapart.com/trac/livejournal/browser/trunk/cgi-bin/cleanhtml.pl
# Particularly the CSS cleaning; most of the tag cleaning is integrated now
# I have multiple kinds of schemes searched; but should schemes be
# whitelisted instead?
# max height?
# remove images? Also in CSS? background attribute?
# Some way to whitelist object, iframe, etc (e.g., if you want to
# allow *just* embedded YouTube movies)
# Log what was deleted and why?
# style="behavior: ..." might be bad in IE?
# Should we have something for just <meta http-equiv>? That's the worst of the
# metas.
# UTF-7 detections? Example:
# <HEAD><META HTTP-EQUIV="CONTENT-TYPE" CONTENT="text/html; charset=UTF-7"> </HEAD>+ADw-SCRIPT+AD4-alert('XSS');+ADw-/SCRIPT+AD4-
# you don't always have to have the charset set, if the page has no charset
# and there's UTF7-like code in it.
# Look at these tests: http://htmlpurifier.org/live/smoketests/xssAttacks.php
# This is an IE-specific construct you can have in a stylesheet to
# run some Javascript:
_css_javascript_re = re.compile(
r'expression\s*\(.*?\)', re.S|re.I)
# Do I have to worry about @\nimport?
_css_import_re = re.compile(
r'@\s*import', re.I)
# All kinds of schemes besides just javascript: that can cause
# execution:
_is_image_dataurl = re.compile(
r'^data:image/.+;base64', re.I).search
_is_possibly_malicious_scheme = re.compile(
r'(?:javascript|jscript|livescript|vbscript|data|about|mocha):',
re.I).search
def _is_javascript_scheme(s):
if _is_image_dataurl(s):
return None
return _is_possibly_malicious_scheme(s)
_substitute_whitespace = re.compile(r'[\s\x00-\x08\x0B\x0C\x0E-\x19]+').sub
# FIXME: should data: be blocked?
# FIXME: check against: http://msdn2.microsoft.com/en-us/library/ms537512.aspx
_conditional_comment_re = re.compile(
r'\[if[\s\n\r]+.*?][\s\n\r]*>', re.I|re.S)
_find_styled_elements = etree.XPath(
"descendant-or-self::*[@style]")
_find_external_links = etree.XPath(
("descendant-or-self::a [normalize-space(@href) and substring(normalize-space(@href),1,1) != '#'] |"
"descendant-or-self::x:a[normalize-space(@href) and substring(normalize-space(@href),1,1) != '#']"),
namespaces={'x':XHTML_NAMESPACE})
class Cleaner(object):
"""
Instances cleans the document of each of the possible offending
elements. The cleaning is controlled by attributes; you can
override attributes in a subclass, or set them in the constructor.
``scripts``:
Removes any ``<script>`` tags.
``javascript``:
Removes any Javascript, like an ``onclick`` attribute. Also removes stylesheets
as they could contain Javascript.
``comments``:
Removes any comments.
``style``:
Removes any style tags.
``inline_style``
Removes any style attributes. Defaults to the value of the ``style`` option.
``links``:
Removes any ``<link>`` tags
``meta``:
Removes any ``<meta>`` tags
``page_structure``:
Structural parts of a page: ``<head>``, ``<html>``, ``<title>``.
``processing_instructions``:
Removes any processing instructions.
``embedded``:
Removes any embedded objects (flash, iframes)
``frames``:
Removes any frame-related tags
``forms``:
Removes any form tags
``annoying_tags``:
Tags that aren't *wrong*, but are annoying. ``<blink>`` and ``<marquee>``
``remove_tags``:
A list of tags to remove. Only the tags will be removed,
their content will get pulled up into the parent tag.
``kill_tags``:
A list of tags to kill. Killing also removes the tag's content,
i.e. the whole subtree, not just the tag itself.
``allow_tags``:
A list of tags to include (default include all).
``remove_unknown_tags``:
Remove any tags that aren't standard parts of HTML.
``safe_attrs_only``:
If true, only include 'safe' attributes (specifically the list
from the feedparser HTML sanitisation web site).
``safe_attrs``:
A set of attribute names to override the default list of attributes
considered 'safe' (when safe_attrs_only=True).
``add_nofollow``:
If true, then any <a> tags will have ``rel="nofollow"`` added to them.
``host_whitelist``:
A list or set of hosts that you can use for embedded content
(for content like ``<object>``, ``<link rel="stylesheet">``, etc).
You can also implement/override the method
``allow_embedded_url(el, url)`` or ``allow_element(el)`` to
implement more complex rules for what can be embedded.
Anything that passes this test will be shown, regardless of
the value of (for instance) ``embedded``.
Note that this parameter might not work as intended if you do not
make the links absolute before doing the cleaning.
Note that you may also need to set ``whitelist_tags``.
``whitelist_tags``:
A set of tags that can be included with ``host_whitelist``.
The default is ``iframe`` and ``embed``; you may wish to
include other tags like ``script``, or you may want to
implement ``allow_embedded_url`` for more control. Set to None to
include all tags.
This modifies the document *in place*.
"""
scripts = True
javascript = True
comments = True
style = False
inline_style = None
links = True
meta = True
page_structure = True
processing_instructions = True
embedded = True
frames = True
forms = True
annoying_tags = True
remove_tags = None
allow_tags = None
kill_tags = None
remove_unknown_tags = True
safe_attrs_only = True
safe_attrs = defs.safe_attrs
add_nofollow = False
host_whitelist = ()
whitelist_tags = {'iframe', 'embed'}
def __init__(self, **kw):
for name, value in kw.items():
if not hasattr(self, name):
raise TypeError(
"Unknown parameter: %s=%r" % (name, value))
setattr(self, name, value)
if self.inline_style is None and 'inline_style' not in kw:
self.inline_style = self.style
# Used to lookup the primary URL for a given tag that is up for
# removal:
_tag_link_attrs = dict(
script='src',
link='href',
# From: http://java.sun.com/j2se/1.4.2/docs/guide/misc/applet.html
# From what I can tell, both attributes can contain a link:
applet=['code', 'object'],
iframe='src',
embed='src',
layer='src',
# FIXME: there doesn't really seem like a general way to figure out what
# links an <object> tag uses; links often go in <param> tags with values
# that we don't really know. You'd have to have knowledge about specific
# kinds of plugins (probably keyed off classid), and match against those.
##object=?,
# FIXME: not looking at the action currently, because it is more complex
# than than -- if you keep the form, you should keep the form controls.
##form='action',
a='href',
)
def __call__(self, doc):
"""
Cleans the document.
"""
if hasattr(doc, 'getroot'):
# ElementTree instance, instead of an element
doc = doc.getroot()
# convert XHTML to HTML
xhtml_to_html(doc)
# Normalize a case that IE treats <image> like <img>, and that
# can confuse either this step or later steps.
for el in doc.iter('image'):
el.tag = 'img'
if not self.comments:
# Of course, if we were going to kill comments anyway, we don't
# need to worry about this
self.kill_conditional_comments(doc)
kill_tags = set(self.kill_tags or ())
remove_tags = set(self.remove_tags or ())
allow_tags = set(self.allow_tags or ())
if self.scripts:
kill_tags.add('script')
if self.safe_attrs_only:
safe_attrs = set(self.safe_attrs)
for el in doc.iter(etree.Element):
attrib = el.attrib
for aname in attrib.keys():
if aname not in safe_attrs:
del attrib[aname]
if self.javascript:
if not (self.safe_attrs_only and
self.safe_attrs == defs.safe_attrs):
# safe_attrs handles events attributes itself
for el in doc.iter(etree.Element):
attrib = el.attrib
for aname in attrib.keys():
if aname.startswith('on'):
del attrib[aname]
doc.rewrite_links(self._remove_javascript_link,
resolve_base_href=False)
# If we're deleting style then we don't have to remove JS links
# from styles, otherwise...
if not self.inline_style:
for el in _find_styled_elements(doc):
old = el.get('style')
new = _css_javascript_re.sub('', old)
new = _css_import_re.sub('', new)
if self._has_sneaky_javascript(new):
# Something tricky is going on...
del el.attrib['style']
elif new != old:
el.set('style', new)
if not self.style:
for el in list(doc.iter('style')):
if el.get('type', '').lower().strip() == 'text/javascript':
el.drop_tree()
continue
old = el.text or ''
new = _css_javascript_re.sub('', old)
# The imported CSS can do anything; we just can't allow:
new = _css_import_re.sub('', old)
if self._has_sneaky_javascript(new):
# Something tricky is going on...
el.text = '/* deleted */'
elif new != old:
el.text = new
if self.comments or self.processing_instructions:
# FIXME: why either? I feel like there's some obscure reason
# because you can put PIs in comments...? But I've already
# forgotten it
kill_tags.add(etree.Comment)
if self.processing_instructions:
kill_tags.add(etree.ProcessingInstruction)
if self.style:
kill_tags.add('style')
if self.inline_style:
etree.strip_attributes(doc, 'style')
if self.links:
kill_tags.add('link')
elif self.style or self.javascript:
# We must get rid of included stylesheets if Javascript is not
# allowed, as you can put Javascript in them
for el in list(doc.iter('link')):
if 'stylesheet' in el.get('rel', '').lower():
# Note this kills alternate stylesheets as well
if not self.allow_element(el):
el.drop_tree()
if self.meta:
kill_tags.add('meta')
if self.page_structure:
remove_tags.update(('head', 'html', 'title'))
if self.embedded:
# FIXME: is <layer> really embedded?
# We should get rid of any <param> tags not inside <applet>;
# These are not really valid anyway.
for el in list(doc.iter('param')):
found_parent = False
parent = el.getparent()
while parent is not None and parent.tag not in ('applet', 'object'):
parent = parent.getparent()
if parent is None:
el.drop_tree()
kill_tags.update(('applet',))
# The alternate contents that are in an iframe are a good fallback:
remove_tags.update(('iframe', 'embed', 'layer', 'object', 'param'))
if self.frames:
# FIXME: ideally we should look at the frame links, but
# generally frames don't mix properly with an HTML
# fragment anyway.
kill_tags.update(defs.frame_tags)
if self.forms:
remove_tags.add('form')
kill_tags.update(('button', 'input', 'select', 'textarea'))
if self.annoying_tags:
remove_tags.update(('blink', 'marquee'))
_remove = []
_kill = []
for el in doc.iter():
if el.tag in kill_tags:
if self.allow_element(el):
continue
_kill.append(el)
elif el.tag in remove_tags:
if self.allow_element(el):
continue
_remove.append(el)
if _remove and _remove[0] == doc:
# We have to drop the parent-most tag, which we can't
# do. Instead we'll rewrite it:
el = _remove.pop(0)
el.tag = 'div'
el.attrib.clear()
elif _kill and _kill[0] == doc:
# We have to drop the parent-most element, which we can't
# do. Instead we'll clear it:
el = _kill.pop(0)
if el.tag != 'html':
el.tag = 'div'
el.clear()
_kill.reverse() # start with innermost tags
for el in _kill:
el.drop_tree()
for el in _remove:
el.drop_tag()
if self.remove_unknown_tags:
if allow_tags:
raise ValueError(
"It does not make sense to pass in both allow_tags and remove_unknown_tags")
allow_tags = set(defs.tags)
if allow_tags:
bad = []
for el in doc.iter():
if el.tag not in allow_tags:
bad.append(el)
if bad:
if bad[0] is doc:
el = bad.pop(0)
el.tag = 'div'
el.attrib.clear()
for el in bad:
el.drop_tag()
if self.add_nofollow:
for el in _find_external_links(doc):
if not self.allow_follow(el):
rel = el.get('rel')
if rel:
if ('nofollow' in rel
and ' nofollow ' in (' %s ' % rel)):
continue
rel = '%s nofollow' % rel
else:
rel = 'nofollow'
el.set('rel', rel)
def allow_follow(self, anchor):
"""
Override to suppress rel="nofollow" on some anchors.
"""
return False
def allow_element(self, el):
if el.tag not in self._tag_link_attrs:
return False
attr = self._tag_link_attrs[el.tag]
if isinstance(attr, (list, tuple)):
for one_attr in attr:
url = el.get(one_attr)
if not url:
return False
if not self.allow_embedded_url(el, url):
return False
return True
else:
url = el.get(attr)
if not url:
return False
return self.allow_embedded_url(el, url)
def allow_embedded_url(self, el, url):
if (self.whitelist_tags is not None
and el.tag not in self.whitelist_tags):
return False
scheme, netloc, path, query, fragment = urlsplit(url)
netloc = netloc.lower().split(':', 1)[0]
if scheme not in ('http', 'https'):
return False
if netloc in self.host_whitelist:
return True
return False
def kill_conditional_comments(self, doc):
"""
IE conditional comments basically embed HTML that the parser
doesn't normally see. We can't allow anything like that, so
we'll kill any comments that could be conditional.
"""
bad = []
self._kill_elements(
doc, lambda el: _conditional_comment_re.search(el.text),
etree.Comment)
def _kill_elements(self, doc, condition, iterate=None):
bad = []
for el in doc.iter(iterate):
if condition(el):
bad.append(el)
for el in bad:
el.drop_tree()
def _remove_javascript_link(self, link):
# links like "j a v a s c r i p t:" might be interpreted in IE
new = _substitute_whitespace('', unquote_plus(link))
if _is_javascript_scheme(new):
# FIXME: should this be None to delete?
return ''
return link
_substitute_comments = re.compile(r'/\*.*?\*/', re.S).sub
def _has_sneaky_javascript(self, style):
"""
Depending on the browser, stuff like ``e x p r e s s i o n(...)``
can get interpreted, or ``expre/* stuff */ssion(...)``. This
checks for attempt to do stuff like this.
Typically the response will be to kill the entire style; if you
have just a bit of Javascript in the style another rule will catch
that and remove only the Javascript from the style; this catches
more sneaky attempts.
"""
style = self._substitute_comments('', style)
style = style.replace('\\', '')
style = _substitute_whitespace('', style)
style = style.lower()
if 'javascript:' in style:
return True
if 'expression(' in style:
return True
return False
def clean_html(self, html):
result_type = type(html)
if isinstance(html, basestring):
doc = fromstring(html)
else:
doc = copy.deepcopy(html)
self(doc)
return _transform_result(result_type, doc)
clean = Cleaner()
clean_html = clean.clean_html
############################################################
## Autolinking
############################################################
_link_regexes = [
re.compile(r'(?P<body>https?://(?P<host>[a-z0-9._-]+)(?:/[/\-_.,a-z0-9%&?;=~]*)?(?:\([/\-_.,a-z0-9%&?;=~]*\))?)', re.I),
# This is conservative, but autolinking can be a bit conservative:
re.compile(r'mailto:(?P<body>[a-z0-9._-]+@(?P<host>[a-z0-9_.-]+[a-z]))', re.I),
]
_avoid_elements = ['textarea', 'pre', 'code', 'head', 'select', 'a']
_avoid_hosts = [
re.compile(r'^localhost', re.I),
re.compile(r'\bexample\.(?:com|org|net)$', re.I),
re.compile(r'^127\.0\.0\.1$'),
]
_avoid_classes = ['nolink']
def autolink(el, link_regexes=_link_regexes,
avoid_elements=_avoid_elements,
avoid_hosts=_avoid_hosts,
avoid_classes=_avoid_classes):
"""
Turn any URLs into links.
It will search for links identified by the given regular
expressions (by default mailto and http(s) links).
It won't link text in an element in avoid_elements, or an element
with a class in avoid_classes. It won't link to anything with a
host that matches one of the regular expressions in avoid_hosts
(default localhost and 127.0.0.1).
If you pass in an element, the element's tail will not be
substituted, only the contents of the element.
"""
if el.tag in avoid_elements:
return
class_name = el.get('class')
if class_name:
class_name = class_name.split()
for match_class in avoid_classes:
if match_class in class_name:
return
for child in list(el):
autolink(child, link_regexes=link_regexes,
avoid_elements=avoid_elements,
avoid_hosts=avoid_hosts,
avoid_classes=avoid_classes)
if child.tail:
text, tail_children = _link_text(
child.tail, link_regexes, avoid_hosts, factory=el.makeelement)
if tail_children:
child.tail = text
index = el.index(child)
el[index+1:index+1] = tail_children
if el.text:
text, pre_children = _link_text(
el.text, link_regexes, avoid_hosts, factory=el.makeelement)
if pre_children:
el.text = text
el[:0] = pre_children
def _link_text(text, link_regexes, avoid_hosts, factory):
leading_text = ''
links = []
last_pos = 0
while 1:
best_match, best_pos = None, None
for regex in link_regexes:
regex_pos = last_pos
while 1:
match = regex.search(text, pos=regex_pos)
if match is None:
break
host = match.group('host')
for host_regex in avoid_hosts:
if host_regex.search(host):
regex_pos = match.end()
break
else:
break
if match is None:
continue
if best_pos is None or match.start() < best_pos:
best_match = match
best_pos = match.start()
if best_match is None:
# No more matches
if links:
assert not links[-1].tail
links[-1].tail = text
else:
assert not leading_text
leading_text = text
break
link = best_match.group(0)
end = best_match.end()
if link.endswith('.') or link.endswith(','):
# These punctuation marks shouldn't end a link
end -= 1
link = link[:-1]
prev_text = text[:best_match.start()]
if links:
assert not links[-1].tail
links[-1].tail = prev_text
else:
assert not leading_text
leading_text = prev_text
anchor = factory('a')
anchor.set('href', link)
body = best_match.group('body')
if not body:
body = link
if body.endswith('.') or body.endswith(','):
body = body[:-1]
anchor.text = body
links.append(anchor)
text = text[end:]
return leading_text, links
def autolink_html(html, *args, **kw):
result_type = type(html)
if isinstance(html, basestring):
doc = fromstring(html)
else:
doc = copy.deepcopy(html)
autolink(doc, *args, **kw)
return _transform_result(result_type, doc)
autolink_html.__doc__ = autolink.__doc__
############################################################
## Word wrapping
############################################################
_avoid_word_break_elements = ['pre', 'textarea', 'code']
_avoid_word_break_classes = ['nobreak']
def word_break(el, max_width=40,
avoid_elements=_avoid_word_break_elements,
avoid_classes=_avoid_word_break_classes,
break_character=unichr(0x200b)):
"""
Breaks any long words found in the body of the text (not attributes).
Doesn't effect any of the tags in avoid_elements, by default
``<textarea>`` and ``<pre>``
Breaks words by inserting &#8203;, which is a unicode character
for Zero Width Space character. This generally takes up no space
in rendering, but does copy as a space, and in monospace contexts
usually takes up space.
See http://www.cs.tut.fi/~jkorpela/html/nobr.html for a discussion
"""
# Character suggestion of &#8203 comes from:
# http://www.cs.tut.fi/~jkorpela/html/nobr.html
if el.tag in _avoid_word_break_elements:
return
class_name = el.get('class')
if class_name:
dont_break = False
class_name = class_name.split()
for avoid in avoid_classes:
if avoid in class_name:
dont_break = True
break
if dont_break:
return
if el.text:
el.text = _break_text(el.text, max_width, break_character)
for child in el:
word_break(child, max_width=max_width,
avoid_elements=avoid_elements,
avoid_classes=avoid_classes,
break_character=break_character)
if child.tail:
child.tail = _break_text(child.tail, max_width, break_character)
def word_break_html(html, *args, **kw):
result_type = type(html)
doc = fromstring(html)
word_break(doc, *args, **kw)
return _transform_result(result_type, doc)
def _break_text(text, max_width, break_character):
words = text.split()
for word in words:
if len(word) > max_width:
replacement = _insert_break(word, max_width, break_character)
text = text.replace(word, replacement)
return text
_break_prefer_re = re.compile(r'[^a-z]', re.I)
def _insert_break(word, width, break_character):
orig_word = word
result = ''
while len(word) > width:
start = word[:width]
breaks = list(_break_prefer_re.finditer(start))
if breaks:
last_break = breaks[-1]
# Only walk back up to 10 characters to find a nice break:
if last_break.end() > width-10:
# FIXME: should the break character be at the end of the
# chunk, or the beginning of the next chunk?
start = word[:last_break.end()]
result += start + break_character
word = word[len(start):]
result += word
return result

Binary file not shown.

@ -0,0 +1,131 @@
# FIXME: this should all be confirmed against what a DTD says
# (probably in a test; this may not match the DTD exactly, but we
# should document just how it differs).
# Data taken from http://www.w3.org/TR/html401/index/elements.html
# and http://www.w3.org/community/webed/wiki/HTML/New_HTML5_Elements
# for html5_tags.
empty_tags = frozenset([
'area', 'base', 'basefont', 'br', 'col', 'frame', 'hr',
'img', 'input', 'isindex', 'link', 'meta', 'param'])
deprecated_tags = frozenset([
'applet', 'basefont', 'center', 'dir', 'font', 'isindex',
'menu', 's', 'strike', 'u'])
# archive actually takes a space-separated list of URIs
link_attrs = frozenset([
'action', 'archive', 'background', 'cite', 'classid',
'codebase', 'data', 'href', 'longdesc', 'profile', 'src',
'usemap',
# Not standard:
'dynsrc', 'lowsrc',
])
# Not in the HTML 4 spec:
# onerror, onresize
event_attrs = frozenset([
'onblur', 'onchange', 'onclick', 'ondblclick', 'onerror',
'onfocus', 'onkeydown', 'onkeypress', 'onkeyup', 'onload',
'onmousedown', 'onmousemove', 'onmouseout', 'onmouseover',
'onmouseup', 'onreset', 'onresize', 'onselect', 'onsubmit',
'onunload',
])
safe_attrs = frozenset([
'abbr', 'accept', 'accept-charset', 'accesskey', 'action', 'align',
'alt', 'axis', 'border', 'cellpadding', 'cellspacing', 'char', 'charoff',
'charset', 'checked', 'cite', 'class', 'clear', 'cols', 'colspan',
'color', 'compact', 'coords', 'datetime', 'dir', 'disabled', 'enctype',
'for', 'frame', 'headers', 'height', 'href', 'hreflang', 'hspace', 'id',
'ismap', 'label', 'lang', 'longdesc', 'maxlength', 'media', 'method',
'multiple', 'name', 'nohref', 'noshade', 'nowrap', 'prompt', 'readonly',
'rel', 'rev', 'rows', 'rowspan', 'rules', 'scope', 'selected', 'shape',
'size', 'span', 'src', 'start', 'summary', 'tabindex', 'target', 'title',
'type', 'usemap', 'valign', 'value', 'vspace', 'width'])
# From http://htmlhelp.com/reference/html40/olist.html
top_level_tags = frozenset([
'html', 'head', 'body', 'frameset',
])
head_tags = frozenset([
'base', 'isindex', 'link', 'meta', 'script', 'style', 'title',
])
general_block_tags = frozenset([
'address',
'blockquote',
'center',
'del',
'div',
'h1',
'h2',
'h3',
'h4',
'h5',
'h6',
'hr',
'ins',
'isindex',
'noscript',
'p',
'pre',
])
list_tags = frozenset([
'dir', 'dl', 'dt', 'dd', 'li', 'menu', 'ol', 'ul',
])
table_tags = frozenset([
'table', 'caption', 'colgroup', 'col',
'thead', 'tfoot', 'tbody', 'tr', 'td', 'th',
])
# just this one from
# http://www.georgehernandez.com/h/XComputers/HTML/2BlockLevel.htm
block_tags = general_block_tags | list_tags | table_tags | frozenset([
# Partial form tags
'fieldset', 'form', 'legend', 'optgroup', 'option',
])
form_tags = frozenset([
'form', 'button', 'fieldset', 'legend', 'input', 'label',
'select', 'optgroup', 'option', 'textarea',
])
special_inline_tags = frozenset([
'a', 'applet', 'basefont', 'bdo', 'br', 'embed', 'font', 'iframe',
'img', 'map', 'area', 'object', 'param', 'q', 'script',
'span', 'sub', 'sup',
])
phrase_tags = frozenset([
'abbr', 'acronym', 'cite', 'code', 'del', 'dfn', 'em',
'ins', 'kbd', 'samp', 'strong', 'var',
])
font_style_tags = frozenset([
'b', 'big', 'i', 's', 'small', 'strike', 'tt', 'u',
])
frame_tags = frozenset([
'frameset', 'frame', 'noframes',
])
html5_tags = frozenset([
'article', 'aside', 'audio', 'canvas', 'command', 'datalist',
'details', 'embed', 'figcaption', 'figure', 'footer', 'header',
'hgroup', 'keygen', 'mark', 'math', 'meter', 'nav', 'output',
'progress', 'rp', 'rt', 'ruby', 'section', 'source', 'summary',
'svg', 'time', 'track', 'video', 'wbr'
])
# These tags aren't standard
nonstandard_tags = frozenset(['blink', 'marquee'])
tags = (top_level_tags | head_tags | general_block_tags | list_tags
| table_tags | form_tags | special_inline_tags | phrase_tags
| font_style_tags | nonstandard_tags | html5_tags)

@ -0,0 +1,884 @@
# cython: language_level=3
from __future__ import absolute_import
import difflib
from lxml import etree
from lxml.html import fragment_fromstring
import re
__all__ = ['html_annotate', 'htmldiff']
try:
from html import escape as html_escape
except ImportError:
from cgi import escape as html_escape
try:
_unicode = unicode
except NameError:
# Python 3
_unicode = str
try:
basestring
except NameError:
# Python 3
basestring = str
############################################################
## Annotation
############################################################
def default_markup(text, version):
return '<span title="%s">%s</span>' % (
html_escape(_unicode(version), 1), text)
def html_annotate(doclist, markup=default_markup):
"""
doclist should be ordered from oldest to newest, like::
>>> version1 = 'Hello World'
>>> version2 = 'Goodbye World'
>>> print(html_annotate([(version1, 'version 1'),
... (version2, 'version 2')]))
<span title="version 2">Goodbye</span> <span title="version 1">World</span>
The documents must be *fragments* (str/UTF8 or unicode), not
complete documents
The markup argument is a function to markup the spans of words.
This function is called like markup('Hello', 'version 2'), and
returns HTML. The first argument is text and never includes any
markup. The default uses a span with a title:
>>> print(default_markup('Some Text', 'by Joe'))
<span title="by Joe">Some Text</span>
"""
# The basic strategy we have is to split the documents up into
# logical tokens (which are words with attached markup). We then
# do diffs of each of the versions to track when a token first
# appeared in the document; the annotation attached to the token
# is the version where it first appeared.
tokenlist = [tokenize_annotated(doc, version)
for doc, version in doclist]
cur_tokens = tokenlist[0]
for tokens in tokenlist[1:]:
html_annotate_merge_annotations(cur_tokens, tokens)
cur_tokens = tokens
# After we've tracked all the tokens, we can combine spans of text
# that are adjacent and have the same annotation
cur_tokens = compress_tokens(cur_tokens)
# And finally add markup
result = markup_serialize_tokens(cur_tokens, markup)
return ''.join(result).strip()
def tokenize_annotated(doc, annotation):
"""Tokenize a document and add an annotation attribute to each token
"""
tokens = tokenize(doc, include_hrefs=False)
for tok in tokens:
tok.annotation = annotation
return tokens
def html_annotate_merge_annotations(tokens_old, tokens_new):
"""Merge the annotations from tokens_old into tokens_new, when the
tokens in the new document already existed in the old document.
"""
s = InsensitiveSequenceMatcher(a=tokens_old, b=tokens_new)
commands = s.get_opcodes()
for command, i1, i2, j1, j2 in commands:
if command == 'equal':
eq_old = tokens_old[i1:i2]
eq_new = tokens_new[j1:j2]
copy_annotations(eq_old, eq_new)
def copy_annotations(src, dest):
"""
Copy annotations from the tokens listed in src to the tokens in dest
"""
assert len(src) == len(dest)
for src_tok, dest_tok in zip(src, dest):
dest_tok.annotation = src_tok.annotation
def compress_tokens(tokens):
"""
Combine adjacent tokens when there is no HTML between the tokens,
and they share an annotation
"""
result = [tokens[0]]
for tok in tokens[1:]:
if (not result[-1].post_tags and
not tok.pre_tags and
result[-1].annotation == tok.annotation):
compress_merge_back(result, tok)
else:
result.append(tok)
return result
def compress_merge_back(tokens, tok):
""" Merge tok into the last element of tokens (modifying the list of
tokens in-place). """
last = tokens[-1]
if type(last) is not token or type(tok) is not token:
tokens.append(tok)
else:
text = _unicode(last)
if last.trailing_whitespace:
text += last.trailing_whitespace
text += tok
merged = token(text,
pre_tags=last.pre_tags,
post_tags=tok.post_tags,
trailing_whitespace=tok.trailing_whitespace)
merged.annotation = last.annotation
tokens[-1] = merged
def markup_serialize_tokens(tokens, markup_func):
"""
Serialize the list of tokens into a list of text chunks, calling
markup_func around text to add annotations.
"""
for token in tokens:
for pre in token.pre_tags:
yield pre
html = token.html()
html = markup_func(html, token.annotation)
if token.trailing_whitespace:
html += token.trailing_whitespace
yield html
for post in token.post_tags:
yield post
############################################################
## HTML Diffs
############################################################
def htmldiff(old_html, new_html):
## FIXME: this should take parsed documents too, and use their body
## or other content.
""" Do a diff of the old and new document. The documents are HTML
*fragments* (str/UTF8 or unicode), they are not complete documents
(i.e., no <html> tag).
Returns HTML with <ins> and <del> tags added around the
appropriate text.
Markup is generally ignored, with the markup from new_html
preserved, and possibly some markup from old_html (though it is
considered acceptable to lose some of the old markup). Only the
words in the HTML are diffed. The exception is <img> tags, which
are treated like words, and the href attribute of <a> tags, which
are noted inside the tag itself when there are changes.
"""
old_html_tokens = tokenize(old_html)
new_html_tokens = tokenize(new_html)
result = htmldiff_tokens(old_html_tokens, new_html_tokens)
result = ''.join(result).strip()
return fixup_ins_del_tags(result)
def htmldiff_tokens(html1_tokens, html2_tokens):
""" Does a diff on the tokens themselves, returning a list of text
chunks (not tokens).
"""
# There are several passes as we do the differences. The tokens
# isolate the portion of the content we care to diff; difflib does
# all the actual hard work at that point.
#
# Then we must create a valid document from pieces of both the old
# document and the new document. We generally prefer to take
# markup from the new document, and only do a best effort attempt
# to keep markup from the old document; anything that we can't
# resolve we throw away. Also we try to put the deletes as close
# to the location where we think they would have been -- because
# we are only keeping the markup from the new document, it can be
# fuzzy where in the new document the old text would have gone.
# Again we just do a best effort attempt.
s = InsensitiveSequenceMatcher(a=html1_tokens, b=html2_tokens)
commands = s.get_opcodes()
result = []
for command, i1, i2, j1, j2 in commands:
if command == 'equal':
result.extend(expand_tokens(html2_tokens[j1:j2], equal=True))
continue
if command == 'insert' or command == 'replace':
ins_tokens = expand_tokens(html2_tokens[j1:j2])
merge_insert(ins_tokens, result)
if command == 'delete' or command == 'replace':
del_tokens = expand_tokens(html1_tokens[i1:i2])
merge_delete(del_tokens, result)
# If deletes were inserted directly as <del> then we'd have an
# invalid document at this point. Instead we put in special
# markers, and when the complete diffed document has been created
# we try to move the deletes around and resolve any problems.
result = cleanup_delete(result)
return result
def expand_tokens(tokens, equal=False):
"""Given a list of tokens, return a generator of the chunks of
text for the data in the tokens.
"""
for token in tokens:
for pre in token.pre_tags:
yield pre
if not equal or not token.hide_when_equal:
if token.trailing_whitespace:
yield token.html() + token.trailing_whitespace
else:
yield token.html()
for post in token.post_tags:
yield post
def merge_insert(ins_chunks, doc):
""" doc is the already-handled document (as a list of text chunks);
here we add <ins>ins_chunks</ins> to the end of that. """
# Though we don't throw away unbalanced_start or unbalanced_end
# (we assume there is accompanying markup later or earlier in the
# document), we only put <ins> around the balanced portion.
unbalanced_start, balanced, unbalanced_end = split_unbalanced(ins_chunks)
doc.extend(unbalanced_start)
if doc and not doc[-1].endswith(' '):
# Fix up the case where the word before the insert didn't end with
# a space
doc[-1] += ' '
doc.append('<ins>')
if balanced and balanced[-1].endswith(' '):
# We move space outside of </ins>
balanced[-1] = balanced[-1][:-1]
doc.extend(balanced)
doc.append('</ins> ')
doc.extend(unbalanced_end)
# These are sentinals to represent the start and end of a <del>
# segment, until we do the cleanup phase to turn them into proper
# markup:
class DEL_START:
pass
class DEL_END:
pass
class NoDeletes(Exception):
""" Raised when the document no longer contains any pending deletes
(DEL_START/DEL_END) """
def merge_delete(del_chunks, doc):
""" Adds the text chunks in del_chunks to the document doc (another
list of text chunks) with marker to show it is a delete.
cleanup_delete later resolves these markers into <del> tags."""
doc.append(DEL_START)
doc.extend(del_chunks)
doc.append(DEL_END)
def cleanup_delete(chunks):
""" Cleans up any DEL_START/DEL_END markers in the document, replacing
them with <del></del>. To do this while keeping the document
valid, it may need to drop some tags (either start or end tags).
It may also move the del into adjacent tags to try to move it to a
similar location where it was originally located (e.g., moving a
delete into preceding <div> tag, if the del looks like (DEL_START,
'Text</div>', DEL_END)"""
while 1:
# Find a pending DEL_START/DEL_END, splitting the document
# into stuff-preceding-DEL_START, stuff-inside, and
# stuff-following-DEL_END
try:
pre_delete, delete, post_delete = split_delete(chunks)
except NoDeletes:
# Nothing found, we've cleaned up the entire doc
break
# The stuff-inside-DEL_START/END may not be well balanced
# markup. First we figure out what unbalanced portions there are:
unbalanced_start, balanced, unbalanced_end = split_unbalanced(delete)
# Then we move the span forward and/or backward based on these
# unbalanced portions:
locate_unbalanced_start(unbalanced_start, pre_delete, post_delete)
locate_unbalanced_end(unbalanced_end, pre_delete, post_delete)
doc = pre_delete
if doc and not doc[-1].endswith(' '):
# Fix up case where the word before us didn't have a trailing space
doc[-1] += ' '
doc.append('<del>')
if balanced and balanced[-1].endswith(' '):
# We move space outside of </del>
balanced[-1] = balanced[-1][:-1]
doc.extend(balanced)
doc.append('</del> ')
doc.extend(post_delete)
chunks = doc
return chunks
def split_unbalanced(chunks):
"""Return (unbalanced_start, balanced, unbalanced_end), where each is
a list of text and tag chunks.
unbalanced_start is a list of all the tags that are opened, but
not closed in this span. Similarly, unbalanced_end is a list of
tags that are closed but were not opened. Extracting these might
mean some reordering of the chunks."""
start = []
end = []
tag_stack = []
balanced = []
for chunk in chunks:
if not chunk.startswith('<'):
balanced.append(chunk)
continue
endtag = chunk[1] == '/'
name = chunk.split()[0].strip('<>/')
if name in empty_tags:
balanced.append(chunk)
continue
if endtag:
if tag_stack and tag_stack[-1][0] == name:
balanced.append(chunk)
name, pos, tag = tag_stack.pop()
balanced[pos] = tag
elif tag_stack:
start.extend([tag for name, pos, tag in tag_stack])
tag_stack = []
end.append(chunk)
else:
end.append(chunk)
else:
tag_stack.append((name, len(balanced), chunk))
balanced.append(None)
start.extend(
[chunk for name, pos, chunk in tag_stack])
balanced = [chunk for chunk in balanced if chunk is not None]
return start, balanced, end
def split_delete(chunks):
""" Returns (stuff_before_DEL_START, stuff_inside_DEL_START_END,
stuff_after_DEL_END). Returns the first case found (there may be
more DEL_STARTs in stuff_after_DEL_END). Raises NoDeletes if
there's no DEL_START found. """
try:
pos = chunks.index(DEL_START)
except ValueError:
raise NoDeletes
pos2 = chunks.index(DEL_END)
return chunks[:pos], chunks[pos+1:pos2], chunks[pos2+1:]
def locate_unbalanced_start(unbalanced_start, pre_delete, post_delete):
""" pre_delete and post_delete implicitly point to a place in the
document (where the two were split). This moves that point (by
popping items from one and pushing them onto the other). It moves
the point to try to find a place where unbalanced_start applies.
As an example::
>>> unbalanced_start = ['<div>']
>>> doc = ['<p>', 'Text', '</p>', '<div>', 'More Text', '</div>']
>>> pre, post = doc[:3], doc[3:]
>>> pre, post
(['<p>', 'Text', '</p>'], ['<div>', 'More Text', '</div>'])
>>> locate_unbalanced_start(unbalanced_start, pre, post)
>>> pre, post
(['<p>', 'Text', '</p>', '<div>'], ['More Text', '</div>'])
As you can see, we moved the point so that the dangling <div> that
we found will be effectively replaced by the div in the original
document. If this doesn't work out, we just throw away
unbalanced_start without doing anything.
"""
while 1:
if not unbalanced_start:
# We have totally succeeded in finding the position
break
finding = unbalanced_start[0]
finding_name = finding.split()[0].strip('<>')
if not post_delete:
break
next = post_delete[0]
if next is DEL_START or not next.startswith('<'):
# Reached a word, we can't move the delete text forward
break
if next[1] == '/':
# Reached a closing tag, can we go further? Maybe not...
break
name = next.split()[0].strip('<>')
if name == 'ins':
# Can't move into an insert
break
assert name != 'del', (
"Unexpected delete tag: %r" % next)
if name == finding_name:
unbalanced_start.pop(0)
pre_delete.append(post_delete.pop(0))
else:
# Found a tag that doesn't match
break
def locate_unbalanced_end(unbalanced_end, pre_delete, post_delete):
""" like locate_unbalanced_start, except handling end tags and
possibly moving the point earlier in the document. """
while 1:
if not unbalanced_end:
# Success
break
finding = unbalanced_end[-1]
finding_name = finding.split()[0].strip('<>/')
if not pre_delete:
break
next = pre_delete[-1]
if next is DEL_END or not next.startswith('</'):
# A word or a start tag
break
name = next.split()[0].strip('<>/')
if name == 'ins' or name == 'del':
# Can't move into an insert or delete
break
if name == finding_name:
unbalanced_end.pop()
post_delete.insert(0, pre_delete.pop())
else:
# Found a tag that doesn't match
break
class token(_unicode):
""" Represents a diffable token, generally a word that is displayed to
the user. Opening tags are attached to this token when they are
adjacent (pre_tags) and closing tags that follow the word
(post_tags). Some exceptions occur when there are empty tags
adjacent to a word, so there may be close tags in pre_tags, or
open tags in post_tags.
We also keep track of whether the word was originally followed by
whitespace, even though we do not want to treat the word as
equivalent to a similar word that does not have a trailing
space."""
# When this is true, the token will be eliminated from the
# displayed diff if no change has occurred:
hide_when_equal = False
def __new__(cls, text, pre_tags=None, post_tags=None, trailing_whitespace=""):
obj = _unicode.__new__(cls, text)
if pre_tags is not None:
obj.pre_tags = pre_tags
else:
obj.pre_tags = []
if post_tags is not None:
obj.post_tags = post_tags
else:
obj.post_tags = []
obj.trailing_whitespace = trailing_whitespace
return obj
def __repr__(self):
return 'token(%s, %r, %r, %r)' % (_unicode.__repr__(self), self.pre_tags,
self.post_tags, self.trailing_whitespace)
def html(self):
return _unicode(self)
class tag_token(token):
""" Represents a token that is actually a tag. Currently this is just
the <img> tag, which takes up visible space just like a word but
is only represented in a document by a tag. """
def __new__(cls, tag, data, html_repr, pre_tags=None,
post_tags=None, trailing_whitespace=""):
obj = token.__new__(cls, "%s: %s" % (type, data),
pre_tags=pre_tags,
post_tags=post_tags,
trailing_whitespace=trailing_whitespace)
obj.tag = tag
obj.data = data
obj.html_repr = html_repr
return obj
def __repr__(self):
return 'tag_token(%s, %s, html_repr=%s, post_tags=%r, pre_tags=%r, trailing_whitespace=%r)' % (
self.tag,
self.data,
self.html_repr,
self.pre_tags,
self.post_tags,
self.trailing_whitespace)
def html(self):
return self.html_repr
class href_token(token):
""" Represents the href in an anchor tag. Unlike other words, we only
show the href when it changes. """
hide_when_equal = True
def html(self):
return ' Link: %s' % self
def tokenize(html, include_hrefs=True):
"""
Parse the given HTML and returns token objects (words with attached tags).
This parses only the content of a page; anything in the head is
ignored, and the <head> and <body> elements are themselves
optional. The content is then parsed by lxml, which ensures the
validity of the resulting parsed document (though lxml may make
incorrect guesses when the markup is particular bad).
<ins> and <del> tags are also eliminated from the document, as
that gets confusing.
If include_hrefs is true, then the href attribute of <a> tags is
included as a special kind of diffable token."""
if etree.iselement(html):
body_el = html
else:
body_el = parse_html(html, cleanup=True)
# Then we split the document into text chunks for each tag, word, and end tag:
chunks = flatten_el(body_el, skip_tag=True, include_hrefs=include_hrefs)
# Finally re-joining them into token objects:
return fixup_chunks(chunks)
def parse_html(html, cleanup=True):
"""
Parses an HTML fragment, returning an lxml element. Note that the HTML will be
wrapped in a <div> tag that was not in the original document.
If cleanup is true, make sure there's no <head> or <body>, and get
rid of any <ins> and <del> tags.
"""
if cleanup:
# This removes any extra markup or structure like <head>:
html = cleanup_html(html)
return fragment_fromstring(html, create_parent=True)
_body_re = re.compile(r'<body.*?>', re.I|re.S)
_end_body_re = re.compile(r'</body.*?>', re.I|re.S)
_ins_del_re = re.compile(r'</?(ins|del).*?>', re.I|re.S)
def cleanup_html(html):
""" This 'cleans' the HTML, meaning that any page structure is removed
(only the contents of <body> are used, if there is any <body).
Also <ins> and <del> tags are removed. """
match = _body_re.search(html)
if match:
html = html[match.end():]
match = _end_body_re.search(html)
if match:
html = html[:match.start()]
html = _ins_del_re.sub('', html)
return html
end_whitespace_re = re.compile(r'[ \t\n\r]$')
def split_trailing_whitespace(word):
"""
This function takes a word, such as 'test\n\n' and returns ('test','\n\n')
"""
stripped_length = len(word.rstrip())
return word[0:stripped_length], word[stripped_length:]
def fixup_chunks(chunks):
"""
This function takes a list of chunks and produces a list of tokens.
"""
tag_accum = []
cur_word = None
result = []
for chunk in chunks:
if isinstance(chunk, tuple):
if chunk[0] == 'img':
src = chunk[1]
tag, trailing_whitespace = split_trailing_whitespace(chunk[2])
cur_word = tag_token('img', src, html_repr=tag,
pre_tags=tag_accum,
trailing_whitespace=trailing_whitespace)
tag_accum = []
result.append(cur_word)
elif chunk[0] == 'href':
href = chunk[1]
cur_word = href_token(href, pre_tags=tag_accum, trailing_whitespace=" ")
tag_accum = []
result.append(cur_word)
continue
if is_word(chunk):
chunk, trailing_whitespace = split_trailing_whitespace(chunk)
cur_word = token(chunk, pre_tags=tag_accum, trailing_whitespace=trailing_whitespace)
tag_accum = []
result.append(cur_word)
elif is_start_tag(chunk):
tag_accum.append(chunk)
elif is_end_tag(chunk):
if tag_accum:
tag_accum.append(chunk)
else:
assert cur_word, (
"Weird state, cur_word=%r, result=%r, chunks=%r of %r"
% (cur_word, result, chunk, chunks))
cur_word.post_tags.append(chunk)
else:
assert False
if not result:
return [token('', pre_tags=tag_accum)]
else:
result[-1].post_tags.extend(tag_accum)
return result
# All the tags in HTML that don't require end tags:
empty_tags = (
'param', 'img', 'area', 'br', 'basefont', 'input',
'base', 'meta', 'link', 'col')
block_level_tags = (
'address',
'blockquote',
'center',
'dir',
'div',
'dl',
'fieldset',
'form',
'h1',
'h2',
'h3',
'h4',
'h5',
'h6',
'hr',
'isindex',
'menu',
'noframes',
'noscript',
'ol',
'p',
'pre',
'table',
'ul',
)
block_level_container_tags = (
'dd',
'dt',
'frameset',
'li',
'tbody',
'td',
'tfoot',
'th',
'thead',
'tr',
)
def flatten_el(el, include_hrefs, skip_tag=False):
""" Takes an lxml element el, and generates all the text chunks for
that tag. Each start tag is a chunk, each word is a chunk, and each
end tag is a chunk.
If skip_tag is true, then the outermost container tag is
not returned (just its contents)."""
if not skip_tag:
if el.tag == 'img':
yield ('img', el.get('src'), start_tag(el))
else:
yield start_tag(el)
if el.tag in empty_tags and not el.text and not len(el) and not el.tail:
return
start_words = split_words(el.text)
for word in start_words:
yield html_escape(word)
for child in el:
for item in flatten_el(child, include_hrefs=include_hrefs):
yield item
if el.tag == 'a' and el.get('href') and include_hrefs:
yield ('href', el.get('href'))
if not skip_tag:
yield end_tag(el)
end_words = split_words(el.tail)
for word in end_words:
yield html_escape(word)
split_words_re = re.compile(r'\S+(?:\s+|$)', re.U)
def split_words(text):
""" Splits some text into words. Includes trailing whitespace
on each word when appropriate. """
if not text or not text.strip():
return []
words = split_words_re.findall(text)
return words
start_whitespace_re = re.compile(r'^[ \t\n\r]')
def start_tag(el):
"""
The text representation of the start tag for a tag.
"""
return '<%s%s>' % (
el.tag, ''.join([' %s="%s"' % (name, html_escape(value, True))
for name, value in el.attrib.items()]))
def end_tag(el):
""" The text representation of an end tag for a tag. Includes
trailing whitespace when appropriate. """
if el.tail and start_whitespace_re.search(el.tail):
extra = ' '
else:
extra = ''
return '</%s>%s' % (el.tag, extra)
def is_word(tok):
return not tok.startswith('<')
def is_end_tag(tok):
return tok.startswith('</')
def is_start_tag(tok):
return tok.startswith('<') and not tok.startswith('</')
def fixup_ins_del_tags(html):
""" Given an html string, move any <ins> or <del> tags inside of any
block-level elements, e.g. transform <ins><p>word</p></ins> to
<p><ins>word</ins></p> """
doc = parse_html(html, cleanup=False)
_fixup_ins_del_tags(doc)
html = serialize_html_fragment(doc, skip_outer=True)
return html
def serialize_html_fragment(el, skip_outer=False):
""" Serialize a single lxml element as HTML. The serialized form
includes the elements tail.
If skip_outer is true, then don't serialize the outermost tag
"""
assert not isinstance(el, basestring), (
"You should pass in an element, not a string like %r" % el)
html = etree.tostring(el, method="html", encoding=_unicode)
if skip_outer:
# Get rid of the extra starting tag:
html = html[html.find('>')+1:]
# Get rid of the extra end tag:
html = html[:html.rfind('<')]
return html.strip()
else:
return html
def _fixup_ins_del_tags(doc):
"""fixup_ins_del_tags that works on an lxml document in-place
"""
for tag in ['ins', 'del']:
for el in doc.xpath('descendant-or-self::%s' % tag):
if not _contains_block_level_tag(el):
continue
_move_el_inside_block(el, tag=tag)
el.drop_tag()
#_merge_element_contents(el)
def _contains_block_level_tag(el):
"""True if the element contains any block-level elements, like <p>, <td>, etc.
"""
if el.tag in block_level_tags or el.tag in block_level_container_tags:
return True
for child in el:
if _contains_block_level_tag(child):
return True
return False
def _move_el_inside_block(el, tag):
""" helper for _fixup_ins_del_tags; actually takes the <ins> etc tags
and moves them inside any block-level tags. """
for child in el:
if _contains_block_level_tag(child):
break
else:
# No block-level tags in any child
children_tag = etree.Element(tag)
children_tag.text = el.text
el.text = None
children_tag.extend(list(el))
el[:] = [children_tag]
return
for child in list(el):
if _contains_block_level_tag(child):
_move_el_inside_block(child, tag)
if child.tail:
tail_tag = etree.Element(tag)
tail_tag.text = child.tail
child.tail = None
el.insert(el.index(child)+1, tail_tag)
else:
child_tag = etree.Element(tag)
el.replace(child, child_tag)
child_tag.append(child)
if el.text:
text_tag = etree.Element(tag)
text_tag.text = el.text
el.text = None
el.insert(0, text_tag)
def _merge_element_contents(el):
"""
Removes an element, but merges its contents into its place, e.g.,
given <p>Hi <i>there!</i></p>, if you remove the <i> element you get
<p>Hi there!</p>
"""
parent = el.getparent()
text = el.text or ''
if el.tail:
if not len(el):
text += el.tail
else:
if el[-1].tail:
el[-1].tail += el.tail
else:
el[-1].tail = el.tail
index = parent.index(el)
if text:
if index == 0:
previous = None
else:
previous = parent[index-1]
if previous is None:
if parent.text:
parent.text += text
else:
parent.text = text
else:
if previous.tail:
previous.tail += text
else:
previous.tail = text
parent[index:index+1] = el.getchildren()
class InsensitiveSequenceMatcher(difflib.SequenceMatcher):
"""
Acts like SequenceMatcher, but tries not to find very small equal
blocks amidst large spans of changes
"""
threshold = 2
def get_matching_blocks(self):
size = min(len(self.b), len(self.b))
threshold = min(self.threshold, size / 4)
actual = difflib.SequenceMatcher.get_matching_blocks(self)
return [item for item in actual
if item[2] > threshold
or not item[2]]
if __name__ == '__main__':
from lxml.html import _diffcommand
_diffcommand.main()

Binary file not shown.

@ -0,0 +1,299 @@
from lxml.etree import XPath, ElementBase
from lxml.html import fromstring, XHTML_NAMESPACE
from lxml.html import _forms_xpath, _options_xpath, _nons, _transform_result
from lxml.html import defs
import copy
try:
basestring
except NameError:
# Python 3
basestring = str
__all__ = ['FormNotFound', 'fill_form', 'fill_form_html',
'insert_errors', 'insert_errors_html',
'DefaultErrorCreator']
class FormNotFound(LookupError):
"""
Raised when no form can be found
"""
_form_name_xpath = XPath('descendant-or-self::form[name=$name]|descendant-or-self::x:form[name=$name]', namespaces={'x':XHTML_NAMESPACE})
_input_xpath = XPath('|'.join(['descendant-or-self::'+_tag for _tag in ('input','select','textarea','x:input','x:select','x:textarea')]),
namespaces={'x':XHTML_NAMESPACE})
_label_for_xpath = XPath('//label[@for=$for_id]|//x:label[@for=$for_id]',
namespaces={'x':XHTML_NAMESPACE})
_name_xpath = XPath('descendant-or-self::*[@name=$name]')
def fill_form(
el,
values,
form_id=None,
form_index=None,
):
el = _find_form(el, form_id=form_id, form_index=form_index)
_fill_form(el, values)
def fill_form_html(html, values, form_id=None, form_index=None):
result_type = type(html)
if isinstance(html, basestring):
doc = fromstring(html)
else:
doc = copy.deepcopy(html)
fill_form(doc, values, form_id=form_id, form_index=form_index)
return _transform_result(result_type, doc)
def _fill_form(el, values):
counts = {}
if hasattr(values, 'mixed'):
# For Paste request parameters
values = values.mixed()
inputs = _input_xpath(el)
for input in inputs:
name = input.get('name')
if not name:
continue
if _takes_multiple(input):
value = values.get(name, [])
if not isinstance(value, (list, tuple)):
value = [value]
_fill_multiple(input, value)
elif name not in values:
continue
else:
index = counts.get(name, 0)
counts[name] = index + 1
value = values[name]
if isinstance(value, (list, tuple)):
try:
value = value[index]
except IndexError:
continue
elif index > 0:
continue
_fill_single(input, value)
def _takes_multiple(input):
if _nons(input.tag) == 'select' and input.get('multiple'):
# FIXME: multiple="0"?
return True
type = input.get('type', '').lower()
if type in ('radio', 'checkbox'):
return True
return False
def _fill_multiple(input, value):
type = input.get('type', '').lower()
if type == 'checkbox':
v = input.get('value')
if v is None:
if not value:
result = False
else:
result = value[0]
if isinstance(value, basestring):
# The only valid "on" value for an unnamed checkbox is 'on'
result = result == 'on'
_check(input, result)
else:
_check(input, v in value)
elif type == 'radio':
v = input.get('value')
_check(input, v in value)
else:
assert _nons(input.tag) == 'select'
for option in _options_xpath(input):
v = option.get('value')
if v is None:
# This seems to be the default, at least on IE
# FIXME: but I'm not sure
v = option.text_content()
_select(option, v in value)
def _check(el, check):
if check:
el.set('checked', '')
else:
if 'checked' in el.attrib:
del el.attrib['checked']
def _select(el, select):
if select:
el.set('selected', '')
else:
if 'selected' in el.attrib:
del el.attrib['selected']
def _fill_single(input, value):
if _nons(input.tag) == 'textarea':
input.text = value
else:
input.set('value', value)
def _find_form(el, form_id=None, form_index=None):
if form_id is None and form_index is None:
forms = _forms_xpath(el)
for form in forms:
return form
raise FormNotFound(
"No forms in page")
if form_id is not None:
form = el.get_element_by_id(form_id)
if form is not None:
return form
forms = _form_name_xpath(el, name=form_id)
if forms:
return forms[0]
else:
raise FormNotFound(
"No form with the name or id of %r (forms: %s)"
% (id, ', '.join(_find_form_ids(el))))
if form_index is not None:
forms = _forms_xpath(el)
try:
return forms[form_index]
except IndexError:
raise FormNotFound(
"There is no form with the index %r (%i forms found)"
% (form_index, len(forms)))
def _find_form_ids(el):
forms = _forms_xpath(el)
if not forms:
yield '(no forms)'
return
for index, form in enumerate(forms):
if form.get('id'):
if form.get('name'):
yield '%s or %s' % (form.get('id'),
form.get('name'))
else:
yield form.get('id')
elif form.get('name'):
yield form.get('name')
else:
yield '(unnamed form %s)' % index
############################################################
## Error filling
############################################################
class DefaultErrorCreator(object):
insert_before = True
block_inside = True
error_container_tag = 'div'
error_message_class = 'error-message'
error_block_class = 'error-block'
default_message = "Invalid"
def __init__(self, **kw):
for name, value in kw.items():
if not hasattr(self, name):
raise TypeError(
"Unexpected keyword argument: %s" % name)
setattr(self, name, value)
def __call__(self, el, is_block, message):
error_el = el.makeelement(self.error_container_tag)
if self.error_message_class:
error_el.set('class', self.error_message_class)
if is_block and self.error_block_class:
error_el.set('class', error_el.get('class', '')+' '+self.error_block_class)
if message is None or message == '':
message = self.default_message
if isinstance(message, ElementBase):
error_el.append(message)
else:
assert isinstance(message, basestring), (
"Bad message; should be a string or element: %r" % message)
error_el.text = message or self.default_message
if is_block and self.block_inside:
if self.insert_before:
error_el.tail = el.text
el.text = None
el.insert(0, error_el)
else:
el.append(error_el)
else:
parent = el.getparent()
pos = parent.index(el)
if self.insert_before:
parent.insert(pos, error_el)
else:
error_el.tail = el.tail
el.tail = None
parent.insert(pos+1, error_el)
default_error_creator = DefaultErrorCreator()
def insert_errors(
el,
errors,
form_id=None,
form_index=None,
error_class="error",
error_creator=default_error_creator,
):
el = _find_form(el, form_id=form_id, form_index=form_index)
for name, error in errors.items():
if error is None:
continue
for error_el, message in _find_elements_for_name(el, name, error):
assert isinstance(message, (basestring, type(None), ElementBase)), (
"Bad message: %r" % message)
_insert_error(error_el, message, error_class, error_creator)
def insert_errors_html(html, values, **kw):
result_type = type(html)
if isinstance(html, basestring):
doc = fromstring(html)
else:
doc = copy.deepcopy(html)
insert_errors(doc, values, **kw)
return _transform_result(result_type, doc)
def _insert_error(el, error, error_class, error_creator):
if _nons(el.tag) in defs.empty_tags or _nons(el.tag) == 'textarea':
is_block = False
else:
is_block = True
if _nons(el.tag) != 'form' and error_class:
_add_class(el, error_class)
if el.get('id'):
labels = _label_for_xpath(el, for_id=el.get('id'))
if labels:
for label in labels:
_add_class(label, error_class)
error_creator(el, is_block, error)
def _add_class(el, class_name):
if el.get('class'):
el.set('class', el.get('class')+' '+class_name)
else:
el.set('class', class_name)
def _find_elements_for_name(form, name, error):
if name is None:
# An error for the entire form
yield form, error
return
if name.startswith('#'):
# By id
el = form.get_element_by_id(name[1:])
if el is not None:
yield el, error
return
els = _name_xpath(form, name=name)
if not els:
# FIXME: should this raise an exception?
return
if not isinstance(error, (list, tuple)):
yield els[0], error
return
# FIXME: if error is longer than els, should it raise an error?
for el, err in zip(els, error):
if err is None:
continue
yield el, err

@ -0,0 +1,260 @@
"""
An interface to html5lib that mimics the lxml.html interface.
"""
import sys
import string
from html5lib import HTMLParser as _HTMLParser
from html5lib.treebuilders.etree_lxml import TreeBuilder
from lxml import etree
from lxml.html import Element, XHTML_NAMESPACE, _contains_block_level_tag
# python3 compatibility
try:
_strings = basestring
except NameError:
_strings = (bytes, str)
try:
from urllib2 import urlopen
except ImportError:
from urllib.request import urlopen
try:
from urlparse import urlparse
except ImportError:
from urllib.parse import urlparse
class HTMLParser(_HTMLParser):
"""An html5lib HTML parser with lxml as tree."""
def __init__(self, strict=False, **kwargs):
_HTMLParser.__init__(self, strict=strict, tree=TreeBuilder, **kwargs)
try:
from html5lib import XHTMLParser as _XHTMLParser
except ImportError:
pass
else:
class XHTMLParser(_XHTMLParser):
"""An html5lib XHTML Parser with lxml as tree."""
def __init__(self, strict=False, **kwargs):
_XHTMLParser.__init__(self, strict=strict, tree=TreeBuilder, **kwargs)
xhtml_parser = XHTMLParser()
def _find_tag(tree, tag):
elem = tree.find(tag)
if elem is not None:
return elem
return tree.find('{%s}%s' % (XHTML_NAMESPACE, tag))
def document_fromstring(html, guess_charset=None, parser=None):
"""
Parse a whole document into a string.
If `guess_charset` is true, or if the input is not Unicode but a
byte string, the `chardet` library will perform charset guessing
on the string.
"""
if not isinstance(html, _strings):
raise TypeError('string required')
if parser is None:
parser = html_parser
options = {}
if guess_charset is None and isinstance(html, bytes):
# html5lib does not accept useChardet as an argument, if it
# detected the html argument would produce unicode objects.
guess_charset = True
if guess_charset is not None:
options['useChardet'] = guess_charset
return parser.parse(html, **options).getroot()
def fragments_fromstring(html, no_leading_text=False,
guess_charset=None, parser=None):
"""Parses several HTML elements, returning a list of elements.
The first item in the list may be a string. If no_leading_text is true,
then it will be an error if there is leading text, and it will always be
a list of only elements.
If `guess_charset` is true, the `chardet` library will perform charset
guessing on the string.
"""
if not isinstance(html, _strings):
raise TypeError('string required')
if parser is None:
parser = html_parser
options = {}
if guess_charset is None and isinstance(html, bytes):
# html5lib does not accept useChardet as an argument, if it
# detected the html argument would produce unicode objects.
guess_charset = False
if guess_charset is not None:
options['useChardet'] = guess_charset
children = parser.parseFragment(html, 'div', **options)
if children and isinstance(children[0], _strings):
if no_leading_text:
if children[0].strip():
raise etree.ParserError('There is leading text: %r' %
children[0])
del children[0]
return children
def fragment_fromstring(html, create_parent=False,
guess_charset=None, parser=None):
"""Parses a single HTML element; it is an error if there is more than
one element, or if anything but whitespace precedes or follows the
element.
If 'create_parent' is true (or is a tag name) then a parent node
will be created to encapsulate the HTML in a single element. In
this case, leading or trailing text is allowed.
If `guess_charset` is true, the `chardet` library will perform charset
guessing on the string.
"""
if not isinstance(html, _strings):
raise TypeError('string required')
accept_leading_text = bool(create_parent)
elements = fragments_fromstring(
html, guess_charset=guess_charset, parser=parser,
no_leading_text=not accept_leading_text)
if create_parent:
if not isinstance(create_parent, _strings):
create_parent = 'div'
new_root = Element(create_parent)
if elements:
if isinstance(elements[0], _strings):
new_root.text = elements[0]
del elements[0]
new_root.extend(elements)
return new_root
if not elements:
raise etree.ParserError('No elements found')
if len(elements) > 1:
raise etree.ParserError('Multiple elements found')
result = elements[0]
if result.tail and result.tail.strip():
raise etree.ParserError('Element followed by text: %r' % result.tail)
result.tail = None
return result
def fromstring(html, guess_charset=None, parser=None):
"""Parse the html, returning a single element/document.
This tries to minimally parse the chunk of text, without knowing if it
is a fragment or a document.
'base_url' will set the document's base_url attribute (and the tree's
docinfo.URL)
If `guess_charset` is true, or if the input is not Unicode but a
byte string, the `chardet` library will perform charset guessing
on the string.
"""
if not isinstance(html, _strings):
raise TypeError('string required')
doc = document_fromstring(html, parser=parser,
guess_charset=guess_charset)
# document starts with doctype or <html>, full document!
start = html[:50]
if isinstance(start, bytes):
# Allow text comparison in python3.
# Decode as ascii, that also covers latin-1 and utf-8 for the
# characters we need.
start = start.decode('ascii', 'replace')
start = start.lstrip().lower()
if start.startswith('<html') or start.startswith('<!doctype'):
return doc
head = _find_tag(doc, 'head')
# if the head is not empty we have a full document
if len(head):
return doc
body = _find_tag(doc, 'body')
# The body has just one element, so it was probably a single
# element passed in
if (len(body) == 1 and (not body.text or not body.text.strip())
and (not body[-1].tail or not body[-1].tail.strip())):
return body[0]
# Now we have a body which represents a bunch of tags which have the
# content that was passed in. We will create a fake container, which
# is the body tag, except <body> implies too much structure.
if _contains_block_level_tag(body):
body.tag = 'div'
else:
body.tag = 'span'
return body
def parse(filename_url_or_file, guess_charset=None, parser=None):
"""Parse a filename, URL, or file-like object into an HTML document
tree. Note: this returns a tree, not an element. Use
``parse(...).getroot()`` to get the document root.
If ``guess_charset`` is true, the ``useChardet`` option is passed into
html5lib to enable character detection. This option is on by default
when parsing from URLs, off by default when parsing from file(-like)
objects (which tend to return Unicode more often than not), and on by
default when parsing from a file path (which is read in binary mode).
"""
if parser is None:
parser = html_parser
if not isinstance(filename_url_or_file, _strings):
fp = filename_url_or_file
if guess_charset is None:
# assume that file-like objects return Unicode more often than bytes
guess_charset = False
elif _looks_like_url(filename_url_or_file):
fp = urlopen(filename_url_or_file)
if guess_charset is None:
# assume that URLs return bytes
guess_charset = True
else:
fp = open(filename_url_or_file, 'rb')
if guess_charset is None:
guess_charset = True
options = {}
# html5lib does not accept useChardet as an argument, if it
# detected the html argument would produce unicode objects.
if guess_charset:
options['useChardet'] = guess_charset
return parser.parse(fp, **options)
def _looks_like_url(str):
scheme = urlparse(str)[0]
if not scheme:
return False
elif (sys.platform == 'win32' and
scheme in string.ascii_letters
and len(scheme) == 1):
# looks like a 'normal' absolute path
return False
else:
return True
html_parser = HTMLParser()

@ -0,0 +1,314 @@
"""External interface to the BeautifulSoup HTML parser.
"""
__all__ = ["fromstring", "parse", "convert_tree"]
import re
from lxml import etree, html
try:
from bs4 import (
BeautifulSoup, Tag, Comment, ProcessingInstruction, NavigableString,
Declaration, Doctype)
_DECLARATION_OR_DOCTYPE = (Declaration, Doctype)
except ImportError:
from BeautifulSoup import (
BeautifulSoup, Tag, Comment, ProcessingInstruction, NavigableString,
Declaration)
_DECLARATION_OR_DOCTYPE = Declaration
def fromstring(data, beautifulsoup=None, makeelement=None, **bsargs):
"""Parse a string of HTML data into an Element tree using the
BeautifulSoup parser.
Returns the root ``<html>`` Element of the tree.
You can pass a different BeautifulSoup parser through the
`beautifulsoup` keyword, and a diffent Element factory function
through the `makeelement` keyword. By default, the standard
``BeautifulSoup`` class and the default factory of `lxml.html` are
used.
"""
return _parse(data, beautifulsoup, makeelement, **bsargs)
def parse(file, beautifulsoup=None, makeelement=None, **bsargs):
"""Parse a file into an ElemenTree using the BeautifulSoup parser.
You can pass a different BeautifulSoup parser through the
`beautifulsoup` keyword, and a diffent Element factory function
through the `makeelement` keyword. By default, the standard
``BeautifulSoup`` class and the default factory of `lxml.html` are
used.
"""
if not hasattr(file, 'read'):
file = open(file)
root = _parse(file, beautifulsoup, makeelement, **bsargs)
return etree.ElementTree(root)
def convert_tree(beautiful_soup_tree, makeelement=None):
"""Convert a BeautifulSoup tree to a list of Element trees.
Returns a list instead of a single root Element to support
HTML-like soup with more than one root element.
You can pass a different Element factory through the `makeelement`
keyword.
"""
root = _convert_tree(beautiful_soup_tree, makeelement)
children = root.getchildren()
for child in children:
root.remove(child)
return children
# helpers
def _parse(source, beautifulsoup, makeelement, **bsargs):
if beautifulsoup is None:
beautifulsoup = BeautifulSoup
if hasattr(beautifulsoup, "HTML_ENTITIES"): # bs3
if 'convertEntities' not in bsargs:
bsargs['convertEntities'] = 'html'
if hasattr(beautifulsoup, "DEFAULT_BUILDER_FEATURES"): # bs4
if 'features' not in bsargs:
bsargs['features'] = 'html.parser' # use Python html parser
tree = beautifulsoup(source, **bsargs)
root = _convert_tree(tree, makeelement)
# from ET: wrap the document in a html root element, if necessary
if len(root) == 1 and root[0].tag == "html":
return root[0]
root.tag = "html"
return root
_parse_doctype_declaration = re.compile(
r'(?:\s|[<!])*DOCTYPE\s*HTML'
r'(?:\s+PUBLIC)?(?:\s+(\'[^\']*\'|"[^"]*"))?'
r'(?:\s+(\'[^\']*\'|"[^"]*"))?',
re.IGNORECASE).match
class _PseudoTag:
# Minimal imitation of BeautifulSoup.Tag
def __init__(self, contents):
self.name = 'html'
self.attrs = []
self.contents = contents
def __iter__(self):
return self.contents.__iter__()
def _convert_tree(beautiful_soup_tree, makeelement):
if makeelement is None:
makeelement = html.html_parser.makeelement
# Split the tree into three parts:
# i) everything before the root element: document type
# declaration, comments, processing instructions, whitespace
# ii) the root(s),
# iii) everything after the root: comments, processing
# instructions, whitespace
first_element_idx = last_element_idx = None
html_root = declaration = None
for i, e in enumerate(beautiful_soup_tree):
if isinstance(e, Tag):
if first_element_idx is None:
first_element_idx = i
last_element_idx = i
if html_root is None and e.name and e.name.lower() == 'html':
html_root = e
elif declaration is None and isinstance(e, _DECLARATION_OR_DOCTYPE):
declaration = e
# For a nice, well-formatted document, the variable roots below is
# a list consisting of a single <html> element. However, the document
# may be a soup like '<meta><head><title>Hello</head><body>Hi
# all<\p>'. In this example roots is a list containing meta, head
# and body elements.
if first_element_idx is None:
pre_root = post_root = []
roots = beautiful_soup_tree.contents
else:
pre_root = beautiful_soup_tree.contents[:first_element_idx]
roots = beautiful_soup_tree.contents[first_element_idx:last_element_idx+1]
post_root = beautiful_soup_tree.contents[last_element_idx+1:]
# Reorganize so that there is one <html> root...
if html_root is not None:
# ... use existing one if possible, ...
i = roots.index(html_root)
html_root.contents = roots[:i] + html_root.contents + roots[i+1:]
else:
# ... otherwise create a new one.
html_root = _PseudoTag(roots)
convert_node = _init_node_converters(makeelement)
# Process pre_root
res_root = convert_node(html_root)
prev = res_root
for e in reversed(pre_root):
converted = convert_node(e)
if converted is not None:
prev.addprevious(converted)
prev = converted
# ditto for post_root
prev = res_root
for e in post_root:
converted = convert_node(e)
if converted is not None:
prev.addnext(converted)
prev = converted
if declaration is not None:
try:
# bs4 provides full Doctype string
doctype_string = declaration.output_ready()
except AttributeError:
doctype_string = declaration.string
match = _parse_doctype_declaration(doctype_string)
if not match:
# Something is wrong if we end up in here. Since soupparser should
# tolerate errors, do not raise Exception, just let it pass.
pass
else:
external_id, sys_uri = match.groups()
docinfo = res_root.getroottree().docinfo
# strip quotes and update DOCTYPE values (any of None, '', '...')
docinfo.public_id = external_id and external_id[1:-1]
docinfo.system_url = sys_uri and sys_uri[1:-1]
return res_root
def _init_node_converters(makeelement):
converters = {}
ordered_node_types = []
def converter(*types):
def add(handler):
for t in types:
converters[t] = handler
ordered_node_types.append(t)
return handler
return add
def find_best_converter(node):
for t in ordered_node_types:
if isinstance(node, t):
return converters[t]
return None
def convert_node(bs_node, parent=None):
# duplicated in convert_tag() below
try:
handler = converters[type(bs_node)]
except KeyError:
handler = converters[type(bs_node)] = find_best_converter(bs_node)
if handler is None:
return None
return handler(bs_node, parent)
def map_attrs(bs_attrs):
if isinstance(bs_attrs, dict): # bs4
attribs = {}
for k, v in bs_attrs.items():
if isinstance(v, list):
v = " ".join(v)
attribs[k] = unescape(v)
else:
attribs = dict((k, unescape(v)) for k, v in bs_attrs)
return attribs
def append_text(parent, text):
if len(parent) == 0:
parent.text = (parent.text or '') + text
else:
parent[-1].tail = (parent[-1].tail or '') + text
# converters are tried in order of their definition
@converter(Tag, _PseudoTag)
def convert_tag(bs_node, parent):
attrs = bs_node.attrs
if parent is not None:
attribs = map_attrs(attrs) if attrs else None
res = etree.SubElement(parent, bs_node.name, attrib=attribs)
else:
attribs = map_attrs(attrs) if attrs else {}
res = makeelement(bs_node.name, attrib=attribs)
for child in bs_node:
# avoid double recursion by inlining convert_node(), see above
try:
handler = converters[type(child)]
except KeyError:
pass
else:
if handler is not None:
handler(child, res)
continue
convert_node(child, res)
return res
@converter(Comment)
def convert_comment(bs_node, parent):
res = html.HtmlComment(bs_node)
if parent is not None:
parent.append(res)
return res
@converter(ProcessingInstruction)
def convert_pi(bs_node, parent):
if bs_node.endswith('?'):
# The PI is of XML style (<?as df?>) but BeautifulSoup
# interpreted it as being SGML style (<?as df>). Fix.
bs_node = bs_node[:-1]
res = etree.ProcessingInstruction(*bs_node.split(' ', 1))
if parent is not None:
parent.append(res)
return res
@converter(NavigableString)
def convert_text(bs_node, parent):
if parent is not None:
append_text(parent, unescape(bs_node))
return None
return convert_node
# copied from ET's ElementSoup
try:
from html.entities import name2codepoint # Python 3
except ImportError:
from htmlentitydefs import name2codepoint
handle_entities = re.compile(r"&(\w+);").sub
try:
unichr
except NameError:
# Python 3
unichr = chr
def unescape(string):
if not string:
return ''
# work around oddities in BeautifulSoup's entity handling
def unescape_entity(m):
try:
return unichr(name2codepoint[m.group(1)])
except KeyError:
return m.group(0) # use as is
return handle_entities(unescape_entity, string)

@ -0,0 +1,13 @@
"""Doctest module for HTML comparison.
Usage::
>>> import lxml.html.usedoctest
>>> # now do your HTML doctests ...
See `lxml.doctestcompare`.
"""
from lxml import doctestcompare
doctestcompare.temp_install(html=True, del_module=__name__)

@ -0,0 +1,26 @@
from lxml.includes.tree cimport xmlDoc, xmlOutputBuffer, xmlChar
from lxml.includes.xpath cimport xmlNodeSet
cdef extern from "libxml/c14n.h":
cdef int xmlC14NDocDumpMemory(xmlDoc* doc,
xmlNodeSet* nodes,
int exclusive,
xmlChar** inclusive_ns_prefixes,
int with_comments,
xmlChar** doc_txt_ptr) nogil
cdef int xmlC14NDocSave(xmlDoc* doc,
xmlNodeSet* nodes,
int exclusive,
xmlChar** inclusive_ns_prefixes,
int with_comments,
char* filename,
int compression) nogil
cdef int xmlC14NDocSaveTo(xmlDoc* doc,
xmlNodeSet* nodes,
int exclusive,
xmlChar** inclusive_ns_prefixes,
int with_comments,
xmlOutputBuffer* buffer) nogil

@ -0,0 +1,3 @@
cdef extern from "etree_defs.h":
cdef bint ENABLE_THREADING
cdef bint ENABLE_SCHEMATRON

@ -0,0 +1,18 @@
from lxml.includes cimport tree
from lxml.includes.tree cimport xmlDoc, xmlDtd
cdef extern from "libxml/valid.h" nogil:
ctypedef void (*xmlValidityErrorFunc)(void * ctx, const char * msg, ...)
ctypedef void (*xmlValidityWarningFunc)(void * ctx, const char * msg, ...)
ctypedef struct xmlValidCtxt:
void *userData
xmlValidityErrorFunc error
xmlValidityWarningFunc warning
cdef xmlValidCtxt* xmlNewValidCtxt()
cdef void xmlFreeValidCtxt(xmlValidCtxt* cur)
cdef int xmlValidateDtd(xmlValidCtxt* ctxt, xmlDoc* doc, xmlDtd* dtd)
cdef tree.xmlElement* xmlGetDtdElementDesc(
xmlDtd* dtd, tree.const_xmlChar* name)

@ -0,0 +1,418 @@
#ifndef HAS_ETREE_DEFS_H
#define HAS_ETREE_DEFS_H
/* quick check for Python/libxml2/libxslt devel setup */
#include "Python.h"
#ifndef PY_VERSION_HEX
# error the development package of Python (header files etc.) is not installed correctly
#else
# if PY_VERSION_HEX < 0x02070000 || PY_MAJOR_VERSION >= 3 && PY_VERSION_HEX < 0x03030000
# error this version of lxml requires Python 2.7, 3.3 or later
# endif
#endif
#include "libxml/xmlversion.h"
#ifndef LIBXML_VERSION
# error the development package of libxml2 (header files etc.) is not installed correctly
#else
#if LIBXML_VERSION < 20700
# error minimum required version of libxml2 is 2.7.0
#endif
#endif
#include "libxslt/xsltconfig.h"
#ifndef LIBXSLT_VERSION
# error the development package of libxslt (header files etc.) is not installed correctly
#else
#if LIBXSLT_VERSION < 10123
# error minimum required version of libxslt is 1.1.23
#endif
#endif
/* v_arg functions */
#define va_int(ap) va_arg(ap, int)
#define va_charptr(ap) va_arg(ap, char *)
#ifdef PYPY_VERSION
# define IS_PYPY 1
#else
# define IS_PYPY 0
#endif
#if PY_MAJOR_VERSION >= 3
# define IS_PYTHON2 0 /* prefer for special casing Python 2.x */
# define IS_PYTHON3 1 /* avoid */
#else
# define IS_PYTHON2 1
# define IS_PYTHON3 0
#endif
#if IS_PYTHON2
#ifndef LXML_UNICODE_STRINGS
#define LXML_UNICODE_STRINGS 0
#endif
#else
#undef LXML_UNICODE_STRINGS
#define LXML_UNICODE_STRINGS 1
#endif
#if !IS_PYPY
# define PyWeakref_LockObject(obj) (NULL)
#endif
/* Threading is not currently supported by PyPy */
#if IS_PYPY
# ifndef WITHOUT_THREADING
# define WITHOUT_THREADING
# endif
#endif
#if IS_PYPY
# undef PyFile_AsFile
# define PyFile_AsFile(o) (NULL)
# undef PyByteArray_Check
# define PyByteArray_Check(o) (0)
#elif !IS_PYTHON2
/* Python 3+ doesn't have PyFile_*() anymore */
# define PyFile_AsFile(o) (NULL)
#endif
#if PY_VERSION_HEX <= 0x03030000 && !(defined(CYTHON_PEP393_ENABLED) && CYTHON_PEP393_ENABLED)
#define PyUnicode_IS_READY(op) (0)
#define PyUnicode_GET_LENGTH(u) PyUnicode_GET_SIZE(u)
#define PyUnicode_KIND(u) (sizeof(Py_UNICODE))
#define PyUnicode_DATA(u) ((void*)PyUnicode_AS_UNICODE(u))
#endif
#if IS_PYPY
# ifndef PyUnicode_FromFormat
# define PyUnicode_FromFormat PyString_FromFormat
# endif
# if !IS_PYTHON2 && !defined(PyBytes_FromFormat)
# ifdef PyString_FromFormat
# define PyBytes_FromFormat PyString_FromFormat
# else
#include <stdarg.h>
static PyObject* PyBytes_FromFormat(const char* format, ...) {
PyObject *string;
va_list vargs;
#ifdef HAVE_STDARG_PROTOTYPES
va_start(vargs, format);
#else
va_start(vargs);
#endif
string = PyUnicode_FromFormatV(format, vargs);
va_end(vargs);
if (string && PyUnicode_Check(string)) {
PyObject *bstring = PyUnicode_AsUTF8String(string);
Py_DECREF(string);
string = bstring;
}
if (string && !PyBytes_CheckExact(string)) {
Py_DECREF(string);
string = NULL;
PyErr_SetString(PyExc_TypeError, "String formatting and encoding failed to return bytes object");
}
return string;
}
# endif
# endif
#endif
/* PySlice_GetIndicesEx() has wrong signature in Py<=3.1 */
#if PY_VERSION_HEX >= 0x03020000
# define _lx_PySlice_GetIndicesEx(o, l, b, e, s, sl) PySlice_GetIndicesEx(o, l, b, e, s, sl)
#else
# define _lx_PySlice_GetIndicesEx(o, l, b, e, s, sl) PySlice_GetIndicesEx(((PySliceObject*)o), l, b, e, s, sl)
#endif
#ifdef WITHOUT_THREADING
# undef PyEval_SaveThread
# define PyEval_SaveThread() (NULL)
# undef PyEval_RestoreThread
# define PyEval_RestoreThread(state) if (state); else {}
# undef PyGILState_Ensure
# define PyGILState_Ensure() (PyGILState_UNLOCKED)
# undef PyGILState_Release
# define PyGILState_Release(state) if (state); else {}
# undef Py_UNBLOCK_THREADS
# define Py_UNBLOCK_THREADS _save = NULL;
# undef Py_BLOCK_THREADS
# define Py_BLOCK_THREADS if (_save); else {}
#endif
#ifdef WITHOUT_THREADING
# define ENABLE_THREADING 0
#else
# define ENABLE_THREADING 1
#endif
#if LIBXML_VERSION < 20704
/* FIXME: hack to make new error reporting compile in old libxml2 versions */
# define xmlStructuredErrorContext NULL
# define xmlXIncludeProcessTreeFlagsData(n,o,d) xmlXIncludeProcessTreeFlags(n,o)
#endif
/* schematron was added in libxml2 2.6.21 */
#ifdef LIBXML_SCHEMATRON_ENABLED
# define ENABLE_SCHEMATRON 1
#else
# define ENABLE_SCHEMATRON 0
# define XML_SCHEMATRON_OUT_QUIET 0
# define XML_SCHEMATRON_OUT_XML 0
# define XML_SCHEMATRON_OUT_ERROR 0
typedef void xmlSchematron;
typedef void xmlSchematronParserCtxt;
typedef void xmlSchematronValidCtxt;
# define xmlSchematronNewDocParserCtxt(doc) NULL
# define xmlSchematronNewParserCtxt(file) NULL
# define xmlSchematronParse(ctxt) NULL
# define xmlSchematronFreeParserCtxt(ctxt)
# define xmlSchematronFree(schema)
# define xmlSchematronNewValidCtxt(schema, options) NULL
# define xmlSchematronValidateDoc(ctxt, doc) 0
# define xmlSchematronFreeValidCtxt(ctxt)
# define xmlSchematronSetValidStructuredErrors(ctxt, errorfunc, data)
#endif
#if LIBXML_VERSION < 20708
# define HTML_PARSE_NODEFDTD 4
#endif
#if LIBXML_VERSION < 20900
# define XML_PARSE_BIG_LINES 4194304
#endif
#include "libxml/tree.h"
#ifndef LIBXML2_NEW_BUFFER
typedef xmlBuffer xmlBuf;
# define xmlBufContent(buf) xmlBufferContent(buf)
# define xmlBufUse(buf) xmlBufferLength(buf)
#endif
/* libexslt 1.1.25+ support EXSLT functions in XPath */
#if LIBXSLT_VERSION < 10125
#define exsltDateXpathCtxtRegister(ctxt, prefix)
#define exsltSetsXpathCtxtRegister(ctxt, prefix)
#define exsltMathXpathCtxtRegister(ctxt, prefix)
#define exsltStrXpathCtxtRegister(ctxt, prefix)
#endif
#define LXML_GET_XSLT_ENCODING(result_var, style) XSLT_GET_IMPORT_PTR(result_var, style, encoding)
/* work around MSDEV 6.0 */
#if (_MSC_VER == 1200) && (WINVER < 0x0500)
long _ftol( double ); //defined by VC6 C libs
long _ftol2( double dblSource ) { return _ftol( dblSource ); }
#endif
#ifdef __GNUC__
/* Test for GCC > 2.95 */
#if __GNUC__ > 2 || (__GNUC__ == 2 && (__GNUC_MINOR__ > 95))
#define unlikely_condition(x) __builtin_expect((x), 0)
#else /* __GNUC__ > 2 ... */
#define unlikely_condition(x) (x)
#endif /* __GNUC__ > 2 ... */
#else /* __GNUC__ */
#define unlikely_condition(x) (x)
#endif /* __GNUC__ */
#ifndef Py_TYPE
#define Py_TYPE(ob) (((PyObject*)(ob))->ob_type)
#endif
#define PY_NEW(T) \
(((PyTypeObject*)(T))->tp_new( \
(PyTypeObject*)(T), __pyx_empty_tuple, NULL))
#define _fqtypename(o) ((Py_TYPE(o))->tp_name)
#define lxml_malloc(count, item_size) \
(unlikely_condition((size_t)(count) > (size_t) (PY_SSIZE_T_MAX / item_size)) ? NULL : \
(PyMem_Malloc((count) * item_size)))
#define lxml_realloc(mem, count, item_size) \
(unlikely_condition((size_t)(count) > (size_t) (PY_SSIZE_T_MAX / item_size)) ? NULL : \
(PyMem_Realloc(mem, (count) * item_size)))
#define lxml_free(mem) PyMem_Free(mem)
#if PY_MAJOR_VERSION < 3
#define _isString(obj) (PyString_CheckExact(obj) || \
PyUnicode_CheckExact(obj) || \
PyType_IsSubtype(Py_TYPE(obj), &PyBaseString_Type))
#else
/* builtin subtype type checks are almost as fast as exact checks in Py2.7+
* and Unicode is more common in Py3 */
#define _isString(obj) (PyUnicode_Check(obj) || PyBytes_Check(obj))
#endif
#define _isElement(c_node) \
(((c_node)->type == XML_ELEMENT_NODE) || \
((c_node)->type == XML_COMMENT_NODE) || \
((c_node)->type == XML_ENTITY_REF_NODE) || \
((c_node)->type == XML_PI_NODE))
#define _isElementOrXInclude(c_node) \
(_isElement(c_node) || \
((c_node)->type == XML_XINCLUDE_START) || \
((c_node)->type == XML_XINCLUDE_END))
#define _getNs(c_node) \
(((c_node)->ns == 0) ? 0 : ((c_node)->ns->href))
#include "string.h"
static void* lxml_unpack_xmldoc_capsule(PyObject* capsule, int* is_owned) {
xmlDoc *c_doc;
void *context;
*is_owned = 0;
if (unlikely_condition(!PyCapsule_IsValid(capsule, (const char*)"libxml2:xmlDoc"))) {
PyErr_SetString(
PyExc_TypeError,
"Not a valid capsule. The capsule argument must be a capsule object with name libxml2:xmlDoc");
return NULL;
}
c_doc = (xmlDoc*) PyCapsule_GetPointer(capsule, (const char*)"libxml2:xmlDoc");
if (unlikely_condition(!c_doc)) return NULL;
if (unlikely_condition(c_doc->type != XML_DOCUMENT_NODE && c_doc->type != XML_HTML_DOCUMENT_NODE)) {
PyErr_Format(
PyExc_ValueError,
"Illegal document provided: expected XML or HTML, found %d", (int)c_doc->type);
return NULL;
}
context = PyCapsule_GetContext(capsule);
if (unlikely_condition(!context && PyErr_Occurred())) return NULL;
if (context && strcmp((const char*) context, "destructor:xmlFreeDoc") == 0) {
/* take ownership by setting destructor to NULL */
if (PyCapsule_SetDestructor(capsule, NULL) == 0) {
/* ownership transferred => invalidate capsule by clearing its name */
if (unlikely_condition(PyCapsule_SetName(capsule, NULL))) {
/* this should never happen since everything above succeeded */
xmlFreeDoc(c_doc);
return NULL;
}
*is_owned = 1;
}
}
return c_doc;
}
/* Macro pair implementation of a depth first tree walker
*
* Calls the code block between the BEGIN and END macros for all elements
* below c_tree_top (exclusively), starting at c_node (inclusively iff
* 'inclusive' is 1). The _ELEMENT_ variants will only stop on nodes
* that match _isElement(), the normal variant will stop on every node
* except text nodes.
*
* To traverse the node and all of its children and siblings in Pyrex, call
* cdef xmlNode* some_node
* BEGIN_FOR_EACH_ELEMENT_FROM(some_node.parent, some_node, 1)
* # do something with some_node
* END_FOR_EACH_ELEMENT_FROM(some_node)
*
* To traverse only the children and siblings of a node, call
* cdef xmlNode* some_node
* BEGIN_FOR_EACH_ELEMENT_FROM(some_node.parent, some_node, 0)
* # do something with some_node
* END_FOR_EACH_ELEMENT_FROM(some_node)
*
* To traverse only the children, do:
* cdef xmlNode* some_node
* some_node = parent_node.children
* BEGIN_FOR_EACH_ELEMENT_FROM(parent_node, some_node, 1)
* # do something with some_node
* END_FOR_EACH_ELEMENT_FROM(some_node)
*
* NOTE: 'some_node' MUST be a plain 'xmlNode*' !
*
* NOTE: parent modification during the walk can divert the iterator, but
* should not segfault !
*/
#define _LX__ELEMENT_MATCH(c_node, only_elements) \
((only_elements) ? (_isElement(c_node)) : 1)
#define _LX__ADVANCE_TO_NEXT(c_node, only_elements) \
while ((c_node != 0) && (!_LX__ELEMENT_MATCH(c_node, only_elements))) \
c_node = c_node->next;
#define _LX__TRAVERSE_TO_NEXT(c_stop_node, c_node, only_elements) \
{ \
/* walk through children first */ \
xmlNode* _lx__next = c_node->children; \
if (_lx__next != 0) { \
if (c_node->type == XML_ENTITY_REF_NODE || c_node->type == XML_DTD_NODE) { \
_lx__next = 0; \
} else { \
_LX__ADVANCE_TO_NEXT(_lx__next, only_elements) \
} \
} \
if ((_lx__next == 0) && (c_node != c_stop_node)) { \
/* try siblings */ \
_lx__next = c_node->next; \
_LX__ADVANCE_TO_NEXT(_lx__next, only_elements) \
/* back off through parents */ \
while (_lx__next == 0) { \
c_node = c_node->parent; \
if (c_node == 0) \
break; \
if (c_node == c_stop_node) \
break; \
if ((only_elements) && !_isElement(c_node)) \
break; \
/* we already traversed the parents -> siblings */ \
_lx__next = c_node->next; \
_LX__ADVANCE_TO_NEXT(_lx__next, only_elements) \
} \
} \
c_node = _lx__next; \
}
#define _LX__BEGIN_FOR_EACH_FROM(c_tree_top, c_node, inclusive, only_elements) \
{ \
if (c_node != 0) { \
const xmlNode* _lx__tree_top = (c_tree_top); \
const int _lx__only_elements = (only_elements); \
/* make sure we start at an element */ \
if (!_LX__ELEMENT_MATCH(c_node, _lx__only_elements)) { \
/* we skip the node, so 'inclusive' is irrelevant */ \
if (c_node == _lx__tree_top) \
c_node = 0; /* nothing to traverse */ \
else { \
c_node = c_node->next; \
_LX__ADVANCE_TO_NEXT(c_node, _lx__only_elements) \
} \
} else if (! (inclusive)) { \
/* skip the first node */ \
_LX__TRAVERSE_TO_NEXT(_lx__tree_top, c_node, _lx__only_elements) \
} \
\
/* now run the user code on the elements we find */ \
while (c_node != 0) { \
/* here goes the code to be run for each element */
#define _LX__END_FOR_EACH_FROM(c_node) \
_LX__TRAVERSE_TO_NEXT(_lx__tree_top, c_node, _lx__only_elements) \
} \
} \
}
#define BEGIN_FOR_EACH_ELEMENT_FROM(c_tree_top, c_node, inclusive) \
_LX__BEGIN_FOR_EACH_FROM(c_tree_top, c_node, inclusive, 1)
#define END_FOR_EACH_ELEMENT_FROM(c_node) \
_LX__END_FOR_EACH_FROM(c_node)
#define BEGIN_FOR_EACH_FROM(c_tree_top, c_node, inclusive) \
_LX__BEGIN_FOR_EACH_FROM(c_tree_top, c_node, inclusive, 0)
#define END_FOR_EACH_FROM(c_node) \
_LX__END_FOR_EACH_FROM(c_node)
#endif /* HAS_ETREE_DEFS_H */

@ -0,0 +1,237 @@
# public Cython/C interface to lxml.etree
from lxml.includes cimport tree
from lxml.includes.tree cimport const_xmlChar
cdef extern from "lxml-version.h":
cdef char* LXML_VERSION_STRING
cdef extern from "etree_defs.h":
# test if c_node is considered an Element (i.e. Element, Comment, etc.)
cdef bint _isElement(tree.xmlNode* c_node) nogil
# return the namespace URI of the node or NULL
cdef const_xmlChar* _getNs(tree.xmlNode* node) nogil
# pair of macros for tree traversal
cdef void BEGIN_FOR_EACH_ELEMENT_FROM(tree.xmlNode* tree_top,
tree.xmlNode* start_node,
int start_node_inclusive) nogil
cdef void END_FOR_EACH_ELEMENT_FROM(tree.xmlNode* start_node) nogil
cdef extern from "etree_api.h":
# first function to call!
cdef int import_lxml__etree() except -1
##########################################################################
# public ElementTree API classes
cdef class lxml.etree._Document [ object LxmlDocument ]:
cdef tree.xmlDoc* _c_doc
cdef class lxml.etree._Element [ object LxmlElement ]:
cdef _Document _doc
cdef tree.xmlNode* _c_node
cdef class lxml.etree.ElementBase(_Element) [ object LxmlElementBase ]:
pass
cdef class lxml.etree._ElementTree [ object LxmlElementTree ]:
cdef _Document _doc
cdef _Element _context_node
cdef class lxml.etree.ElementClassLookup [ object LxmlElementClassLookup ]:
cdef object (*_lookup_function)(object, _Document, tree.xmlNode*)
cdef class lxml.etree.FallbackElementClassLookup(ElementClassLookup) \
[ object LxmlFallbackElementClassLookup ]:
cdef ElementClassLookup fallback
cdef object (*_fallback_function)(object, _Document, tree.xmlNode*)
##########################################################################
# creating Element objects
# create an Element for a C-node in the Document
cdef _Element elementFactory(_Document doc, tree.xmlNode* c_node)
# create an ElementTree for an Element
cdef _ElementTree elementTreeFactory(_Element context_node)
# create an ElementTree subclass for an Element
cdef _ElementTree newElementTree(_Element context_node, object subclass)
# create an ElementTree from an external document
cdef _ElementTree adoptExternalDocument(tree.xmlDoc* c_doc, parser, bint is_owned)
# create a new Element for an existing or new document (doc = None)
# builds Python object after setting text, tail, namespaces and attributes
cdef _Element makeElement(tag, _Document doc, parser,
text, tail, attrib, nsmap)
# create a new SubElement for an existing parent
# builds Python object after setting text, tail, namespaces and attributes
cdef _Element makeSubElement(_Element parent, tag, text, tail,
attrib, nsmap)
# deep copy a node to include it in the Document
cdef _Element deepcopyNodeToDocument(_Document doc, tree.xmlNode* c_root)
# set the internal lookup function for Element/Comment/PI classes
# use setElementClassLookupFunction(NULL, None) to reset it
# note that the lookup function *must always* return an _Element subclass!
cdef void setElementClassLookupFunction(
object (*function)(object, _Document, tree.xmlNode*), object state)
# lookup function that always returns the default Element class
# note that the first argument is expected to be None!
cdef object lookupDefaultElementClass(_1, _Document _2,
tree.xmlNode* c_node)
# lookup function for namespace/tag specific Element classes
# note that the first argument is expected to be None!
cdef object lookupNamespaceElementClass(_1, _Document _2,
tree.xmlNode* c_node)
# call the fallback lookup function of a FallbackElementClassLookup
cdef object callLookupFallback(FallbackElementClassLookup lookup,
_Document doc, tree.xmlNode* c_node)
##########################################################################
# XML attribute access
# return an attribute value for a C attribute on a C element node
cdef object attributeValue(tree.xmlNode* c_element,
tree.xmlAttr* c_attrib_node)
# return the value of the attribute with 'ns' and 'name' (or None)
cdef object attributeValueFromNsName(tree.xmlNode* c_element,
const_xmlChar* c_ns, const_xmlChar* c_name)
# return the value of attribute "{ns}name", or the default value
cdef object getAttributeValue(_Element element, key, default)
# return an iterator over attribute names (1), values (2) or items (3)
# attributes must not be removed during iteration!
cdef object iterattributes(_Element element, int keysvalues)
# return the list of all attribute names (1), values (2) or items (3)
cdef list collectAttributes(tree.xmlNode* c_element, int keysvalues)
# set an attribute value on an element
# on failure, sets an exception and returns -1
cdef int setAttributeValue(_Element element, key, value) except -1
# delete an attribute
# on failure, sets an exception and returns -1
cdef int delAttribute(_Element element, key) except -1
# delete an attribute based on name and namespace URI
# returns -1 if the attribute was not found (no exception)
cdef int delAttributeFromNsName(tree.xmlNode* c_element,
const_xmlChar* c_href, const_xmlChar* c_name)
##########################################################################
# XML node helper functions
# check if the element has at least one child
cdef bint hasChild(tree.xmlNode* c_node) nogil
# find child element number 'index' (supports negative indexes)
cdef tree.xmlNode* findChild(tree.xmlNode* c_node,
Py_ssize_t index) nogil
# find child element number 'index' starting at first one
cdef tree.xmlNode* findChildForwards(tree.xmlNode* c_node,
Py_ssize_t index) nogil
# find child element number 'index' starting at last one
cdef tree.xmlNode* findChildBackwards(tree.xmlNode* c_node,
Py_ssize_t index) nogil
# return next/previous sibling element of the node
cdef tree.xmlNode* nextElement(tree.xmlNode* c_node) nogil
cdef tree.xmlNode* previousElement(tree.xmlNode* c_node) nogil
##########################################################################
# iterators (DEPRECATED API, don't use in new code!)
cdef class lxml.etree._ElementTagMatcher [ object LxmlElementTagMatcher ]:
cdef char* _href
cdef char* _name
# store "{ns}tag" (or None) filter for this matcher or element iterator
# ** unless _href *and* _name are set up 'by hand', this function *must*
# ** be called when subclassing the iterator below!
cdef void initTagMatch(_ElementTagMatcher matcher, tag)
cdef class lxml.etree._ElementIterator(_ElementTagMatcher) [
object LxmlElementIterator ]:
cdef _Element _node
cdef tree.xmlNode* (*_next_element)(tree.xmlNode*)
# store the initial node of the iterator if it matches the required tag
# or its next matching sibling if not
cdef void iteratorStoreNext(_ElementIterator iterator, _Element node)
##########################################################################
# other helper functions
# check if a C node matches a tag name and namespace
# (NULL allowed for each => always matches)
cdef int tagMatches(tree.xmlNode* c_node, const_xmlChar* c_href, const_xmlChar* c_name)
# convert a UTF-8 char* to a Python string or unicode string
cdef object pyunicode(const_xmlChar* s)
# convert the string to UTF-8 using the normal lxml.etree semantics
cdef bytes utf8(object s)
# split a tag into a (URI, name) tuple, return None as URI for '{}tag'
cdef tuple getNsTag(object tag)
# split a tag into a (URI, name) tuple, return b'' as URI for '{}tag'
cdef tuple getNsTagWithEmptyNs(object tag)
# get the "{ns}tag" string for a C node
cdef object namespacedName(tree.xmlNode* c_node)
# get the "{ns}tag" string for a href/tagname pair (c_ns may be NULL)
cdef object namespacedNameFromNsName(const_xmlChar* c_ns, const_xmlChar* c_tag)
# check if the node has a text value (which may be '')
cdef bint hasText(tree.xmlNode* c_node) nogil
# check if the node has a tail value (which may be '')
cdef bint hasTail(tree.xmlNode* c_node) nogil
# get the text content of an element (or None)
cdef object textOf(tree.xmlNode* c_node)
# get the tail content of an element (or None)
cdef object tailOf(tree.xmlNode* c_node)
# set the text value of an element
cdef int setNodeText(tree.xmlNode* c_node, text) except -1
# set the tail text value of an element
cdef int setTailText(tree.xmlNode* c_node, text) except -1
# append an element to the children of a parent element
# deprecated: don't use, does not propagate exceptions!
# use appendChildToElement() instead
cdef void appendChild(_Element parent, _Element child)
# added in lxml 3.3 as a safe replacement for appendChild()
# return -1 for exception, 0 for ok
cdef int appendChildToElement(_Element parent, _Element child) except -1
# recursively lookup a namespace in element or ancestors, or create it
cdef tree.xmlNs* findOrBuildNodeNsPrefix(
_Document doc, tree.xmlNode* c_node, const_xmlChar* href, const_xmlChar* prefix)
# find the Document of an Element, ElementTree or Document (itself!)
cdef _Document documentOrRaise(object input)
# find the root Element of an Element (itself!), ElementTree or Document
cdef _Element rootNodeOrRaise(object input)

@ -0,0 +1,56 @@
from libc.string cimport const_char
from lxml.includes.tree cimport xmlDoc
from lxml.includes.tree cimport xmlInputReadCallback, xmlInputCloseCallback
from lxml.includes.xmlparser cimport xmlParserCtxt, xmlSAXHandler, xmlSAXHandlerV1
cdef extern from "libxml/HTMLparser.h":
ctypedef enum htmlParserOption:
HTML_PARSE_NOERROR # suppress error reports
HTML_PARSE_NOWARNING # suppress warning reports
HTML_PARSE_PEDANTIC # pedantic error reporting
HTML_PARSE_NOBLANKS # remove blank nodes
HTML_PARSE_NONET # Forbid network access
# libxml2 2.6.21+ only:
HTML_PARSE_RECOVER # Relaxed parsing
HTML_PARSE_COMPACT # compact small text nodes
# libxml2 2.7.7+ only:
HTML_PARSE_NOIMPLIED # Do not add implied html/body... elements
# libxml2 2.7.8+ only:
HTML_PARSE_NODEFDTD # do not default a doctype if not found
# libxml2 2.8.0+ only:
XML_PARSE_IGNORE_ENC # ignore internal document encoding hint
xmlSAXHandlerV1 htmlDefaultSAXHandler
cdef xmlParserCtxt* htmlCreateMemoryParserCtxt(
char* buffer, int size) nogil
cdef xmlParserCtxt* htmlCreateFileParserCtxt(
char* filename, char* encoding) nogil
cdef xmlParserCtxt* htmlCreatePushParserCtxt(xmlSAXHandler* sax,
void* user_data,
char* chunk, int size,
char* filename, int enc) nogil
cdef void htmlFreeParserCtxt(xmlParserCtxt* ctxt) nogil
cdef void htmlCtxtReset(xmlParserCtxt* ctxt) nogil
cdef int htmlCtxtUseOptions(xmlParserCtxt* ctxt, int options) nogil
cdef int htmlParseDocument(xmlParserCtxt* ctxt) nogil
cdef int htmlParseChunk(xmlParserCtxt* ctxt,
char* chunk, int size, int terminate) nogil
cdef xmlDoc* htmlCtxtReadFile(xmlParserCtxt* ctxt,
char* filename, const_char* encoding,
int options) nogil
cdef xmlDoc* htmlCtxtReadDoc(xmlParserCtxt* ctxt,
char* buffer, char* URL, const_char* encoding,
int options) nogil
cdef xmlDoc* htmlCtxtReadIO(xmlParserCtxt* ctxt,
xmlInputReadCallback ioread,
xmlInputCloseCallback ioclose,
void* ioctx,
char* URL, const_char* encoding,
int options) nogil
cdef xmlDoc* htmlCtxtReadMemory(xmlParserCtxt* ctxt,
char* buffer, int size,
char* filename, const_char* encoding,
int options) nogil

@ -0,0 +1,102 @@
#ifndef __EXSLT_H__
#define __EXSLT_H__
#include <libxml/tree.h>
#include <libxml/xpath.h>
#include "exsltexports.h"
#include <libexslt/exsltconfig.h>
#ifdef __cplusplus
extern "C" {
#endif
EXSLTPUBVAR const char *exsltLibraryVersion;
EXSLTPUBVAR const int exsltLibexsltVersion;
EXSLTPUBVAR const int exsltLibxsltVersion;
EXSLTPUBVAR const int exsltLibxmlVersion;
/**
* EXSLT_COMMON_NAMESPACE:
*
* Namespace for EXSLT common functions
*/
#define EXSLT_COMMON_NAMESPACE ((const xmlChar *) "http://exslt.org/common")
/**
* EXSLT_CRYPTO_NAMESPACE:
*
* Namespace for EXSLT crypto functions
*/
#define EXSLT_CRYPTO_NAMESPACE ((const xmlChar *) "http://exslt.org/crypto")
/**
* EXSLT_MATH_NAMESPACE:
*
* Namespace for EXSLT math functions
*/
#define EXSLT_MATH_NAMESPACE ((const xmlChar *) "http://exslt.org/math")
/**
* EXSLT_SETS_NAMESPACE:
*
* Namespace for EXSLT set functions
*/
#define EXSLT_SETS_NAMESPACE ((const xmlChar *) "http://exslt.org/sets")
/**
* EXSLT_FUNCTIONS_NAMESPACE:
*
* Namespace for EXSLT functions extension functions
*/
#define EXSLT_FUNCTIONS_NAMESPACE ((const xmlChar *) "http://exslt.org/functions")
/**
* EXSLT_STRINGS_NAMESPACE:
*
* Namespace for EXSLT strings functions
*/
#define EXSLT_STRINGS_NAMESPACE ((const xmlChar *) "http://exslt.org/strings")
/**
* EXSLT_DATE_NAMESPACE:
*
* Namespace for EXSLT date functions
*/
#define EXSLT_DATE_NAMESPACE ((const xmlChar *) "http://exslt.org/dates-and-times")
/**
* EXSLT_DYNAMIC_NAMESPACE:
*
* Namespace for EXSLT dynamic functions
*/
#define EXSLT_DYNAMIC_NAMESPACE ((const xmlChar *) "http://exslt.org/dynamic")
/**
* SAXON_NAMESPACE:
*
* Namespace for SAXON extensions functions
*/
#define SAXON_NAMESPACE ((const xmlChar *) "http://icl.com/saxon")
EXSLTPUBFUN void EXSLTCALL exsltCommonRegister (void);
#ifdef EXSLT_CRYPTO_ENABLED
EXSLTPUBFUN void EXSLTCALL exsltCryptoRegister (void);
#endif
EXSLTPUBFUN void EXSLTCALL exsltMathRegister (void);
EXSLTPUBFUN void EXSLTCALL exsltSetsRegister (void);
EXSLTPUBFUN void EXSLTCALL exsltFuncRegister (void);
EXSLTPUBFUN void EXSLTCALL exsltStrRegister (void);
EXSLTPUBFUN void EXSLTCALL exsltDateRegister (void);
EXSLTPUBFUN void EXSLTCALL exsltSaxonRegister (void);
EXSLTPUBFUN void EXSLTCALL exsltDynRegister(void);
EXSLTPUBFUN void EXSLTCALL exsltRegisterAll (void);
EXSLTPUBFUN int EXSLTCALL exsltDateXpathCtxtRegister (xmlXPathContextPtr ctxt,
const xmlChar *prefix);
EXSLTPUBFUN int EXSLTCALL exsltMathXpathCtxtRegister (xmlXPathContextPtr ctxt,
const xmlChar *prefix);
EXSLTPUBFUN int EXSLTCALL exsltSetsXpathCtxtRegister (xmlXPathContextPtr ctxt,
const xmlChar *prefix);
EXSLTPUBFUN int EXSLTCALL exsltStrXpathCtxtRegister (xmlXPathContextPtr ctxt,
const xmlChar *prefix);
#ifdef __cplusplus
}
#endif
#endif /* __EXSLT_H__ */

@ -0,0 +1,73 @@
/*
* exsltconfig.h: compile-time version informations for the EXSLT library
*
* See Copyright for the status of this software.
*
* daniel@veillard.com
*/
#ifndef __XML_EXSLTCONFIG_H__
#define __XML_EXSLTCONFIG_H__
#ifdef __cplusplus
extern "C" {
#endif
/**
* LIBEXSLT_DOTTED_VERSION:
*
* the version string like "1.2.3"
*/
#define LIBEXSLT_DOTTED_VERSION "0.8.18"
/**
* LIBEXSLT_VERSION:
*
* the version number: 1.2.3 value is 10203
*/
#define LIBEXSLT_VERSION 818
/**
* LIBEXSLT_VERSION_STRING:
*
* the version number string, 1.2.3 value is "10203"
*/
#define LIBEXSLT_VERSION_STRING "818"
/**
* LIBEXSLT_VERSION_EXTRA:
*
* extra version information, used to show a CVS compilation
*/
#define LIBEXSLT_VERSION_EXTRA ""
/**
* WITH_CRYPTO:
*
* Whether crypto support is configured into exslt
*/
#if 1
#define EXSLT_CRYPTO_ENABLED
#endif
/**
* ATTRIBUTE_UNUSED:
*
* This macro is used to flag unused function parameters to GCC
*/
#ifdef __GNUC__
#ifdef HAVE_ANSIDECL_H
#include <ansidecl.h>
#endif
#ifndef ATTRIBUTE_UNUSED
#define ATTRIBUTE_UNUSED __attribute__((unused))
#endif
#else
#define ATTRIBUTE_UNUSED
#endif
#ifdef __cplusplus
}
#endif
#endif /* __XML_EXSLTCONFIG_H__ */

@ -0,0 +1,140 @@
/*
* exsltexports.h : macros for marking symbols as exportable/importable.
*
* See Copyright for the status of this software.
*
* igor@zlatkovic.com
*/
#ifndef __EXSLT_EXPORTS_H__
#define __EXSLT_EXPORTS_H__
/**
* EXSLTPUBFUN, EXSLTPUBVAR, EXSLTCALL
*
* Macros which declare an exportable function, an exportable variable and
* the calling convention used for functions.
*
* Please use an extra block for every platform/compiler combination when
* modifying this, rather than overlong #ifdef lines. This helps
* readability as well as the fact that different compilers on the same
* platform might need different definitions.
*/
/**
* EXSLTPUBFUN:
*
* Macros which declare an exportable function
*/
#define EXSLTPUBFUN
/**
* EXSLTPUBVAR:
*
* Macros which declare an exportable variable
*/
#define EXSLTPUBVAR extern
/**
* EXSLTCALL:
*
* Macros which declare the called convention for exported functions
*/
#define EXSLTCALL
/** DOC_DISABLE */
/* Windows platform with MS compiler */
#if defined(_WIN32) && defined(_MSC_VER)
#undef EXSLTPUBFUN
#undef EXSLTPUBVAR
#undef EXSLTCALL
#if defined(IN_LIBEXSLT) && !defined(LIBEXSLT_STATIC)
#define EXSLTPUBFUN __declspec(dllexport)
#define EXSLTPUBVAR __declspec(dllexport)
#else
#define EXSLTPUBFUN
#if !defined(LIBEXSLT_STATIC)
#define EXSLTPUBVAR __declspec(dllimport) extern
#else
#define EXSLTPUBVAR extern
#endif
#endif
#define EXSLTCALL __cdecl
#if !defined _REENTRANT
#define _REENTRANT
#endif
#endif
/* Windows platform with Borland compiler */
#if defined(_WIN32) && defined(__BORLANDC__)
#undef EXSLTPUBFUN
#undef EXSLTPUBVAR
#undef EXSLTCALL
#if defined(IN_LIBEXSLT) && !defined(LIBEXSLT_STATIC)
#define EXSLTPUBFUN __declspec(dllexport)
#define EXSLTPUBVAR __declspec(dllexport) extern
#else
#define EXSLTPUBFUN
#if !defined(LIBEXSLT_STATIC)
#define EXSLTPUBVAR __declspec(dllimport) extern
#else
#define EXSLTPUBVAR extern
#endif
#endif
#define EXSLTCALL __cdecl
#if !defined _REENTRANT
#define _REENTRANT
#endif
#endif
/* Windows platform with GNU compiler (Mingw) */
#if defined(_WIN32) && defined(__MINGW32__)
#undef EXSLTPUBFUN
#undef EXSLTPUBVAR
#undef EXSLTCALL
/*
#if defined(IN_LIBEXSLT) && !defined(LIBEXSLT_STATIC)
*/
#if !defined(LIBEXSLT_STATIC)
#define EXSLTPUBFUN __declspec(dllexport)
#define EXSLTPUBVAR __declspec(dllexport) extern
#else
#define EXSLTPUBFUN
#if !defined(LIBEXSLT_STATIC)
#define EXSLTPUBVAR __declspec(dllimport) extern
#else
#define EXSLTPUBVAR extern
#endif
#endif
#define EXSLTCALL __cdecl
#if !defined _REENTRANT
#define _REENTRANT
#endif
#endif
/* Cygwin platform, GNU compiler */
#if defined(_WIN32) && defined(__CYGWIN__)
#undef EXSLTPUBFUN
#undef EXSLTPUBVAR
#undef EXSLTCALL
#if defined(IN_LIBEXSLT) && !defined(LIBEXSLT_STATIC)
#define EXSLTPUBFUN __declspec(dllexport)
#define EXSLTPUBVAR __declspec(dllexport)
#else
#define EXSLTPUBFUN
#if !defined(LIBEXSLT_STATIC)
#define EXSLTPUBVAR __declspec(dllimport) extern
#else
#define EXSLTPUBVAR
#endif
#endif
#define EXSLTCALL __cdecl
#endif
/* Compatibility */
#if !defined(LIBEXSLT_PUBLIC)
#define LIBEXSLT_PUBLIC EXSLTPUBVAR
#endif
#endif /* __EXSLT_EXPORTS_H__ */

@ -0,0 +1,29 @@
/*
* libexslt.h: internal header only used during the compilation of libexslt
*
* See COPYRIGHT for the status of this software
*
* Author: daniel@veillard.com
*/
#ifndef __XSLT_LIBEXSLT_H__
#define __XSLT_LIBEXSLT_H__
#if defined(WIN32) && !defined (__CYGWIN__) && !defined (__MINGW32__)
#include <win32config.h>
#else
#include "config.h"
#endif
#include <libxslt/xsltconfig.h>
#include <libxml/xmlversion.h>
#if !defined LIBEXSLT_PUBLIC
#if (defined (__CYGWIN__) || defined _MSC_VER) && !defined IN_LIBEXSLT && !defined LIBEXSLT_STATIC
#define LIBEXSLT_PUBLIC __declspec(dllimport)
#else
#define LIBEXSLT_PUBLIC
#endif
#endif
#endif /* ! __XSLT_LIBEXSLT_H__ */

@ -0,0 +1,96 @@
/*
* Summary: old DocBook SGML parser
* Description: interface for a DocBook SGML non-verifying parser
* This code is DEPRECATED, and should not be used anymore.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __DOCB_PARSER_H__
#define __DOCB_PARSER_H__
#include <libxml/xmlversion.h>
#ifdef LIBXML_DOCB_ENABLED
#include <libxml/parser.h>
#include <libxml/parserInternals.h>
#ifndef IN_LIBXML
#ifdef __GNUC__
#warning "The DOCBparser module has been deprecated in libxml2-2.6.0"
#endif
#endif
#ifdef __cplusplus
extern "C" {
#endif
/*
* Most of the back-end structures from XML and SGML are shared.
*/
typedef xmlParserCtxt docbParserCtxt;
typedef xmlParserCtxtPtr docbParserCtxtPtr;
typedef xmlSAXHandler docbSAXHandler;
typedef xmlSAXHandlerPtr docbSAXHandlerPtr;
typedef xmlParserInput docbParserInput;
typedef xmlParserInputPtr docbParserInputPtr;
typedef xmlDocPtr docbDocPtr;
/*
* There is only few public functions.
*/
XMLPUBFUN int XMLCALL
docbEncodeEntities(unsigned char *out,
int *outlen,
const unsigned char *in,
int *inlen, int quoteChar);
XMLPUBFUN docbDocPtr XMLCALL
docbSAXParseDoc (xmlChar *cur,
const char *encoding,
docbSAXHandlerPtr sax,
void *userData);
XMLPUBFUN docbDocPtr XMLCALL
docbParseDoc (xmlChar *cur,
const char *encoding);
XMLPUBFUN docbDocPtr XMLCALL
docbSAXParseFile (const char *filename,
const char *encoding,
docbSAXHandlerPtr sax,
void *userData);
XMLPUBFUN docbDocPtr XMLCALL
docbParseFile (const char *filename,
const char *encoding);
/**
* Interfaces for the Push mode.
*/
XMLPUBFUN void XMLCALL
docbFreeParserCtxt (docbParserCtxtPtr ctxt);
XMLPUBFUN docbParserCtxtPtr XMLCALL
docbCreatePushParserCtxt(docbSAXHandlerPtr sax,
void *user_data,
const char *chunk,
int size,
const char *filename,
xmlCharEncoding enc);
XMLPUBFUN int XMLCALL
docbParseChunk (docbParserCtxtPtr ctxt,
const char *chunk,
int size,
int terminate);
XMLPUBFUN docbParserCtxtPtr XMLCALL
docbCreateFileParserCtxt(const char *filename,
const char *encoding);
XMLPUBFUN int XMLCALL
docbParseDocument (docbParserCtxtPtr ctxt);
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_DOCB_ENABLED */
#endif /* __DOCB_PARSER_H__ */

@ -0,0 +1,306 @@
/*
* Summary: interface for an HTML 4.0 non-verifying parser
* Description: this module implements an HTML 4.0 non-verifying parser
* with API compatible with the XML parser ones. It should
* be able to parse "real world" HTML, even if severely
* broken from a specification point of view.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __HTML_PARSER_H__
#define __HTML_PARSER_H__
#include <libxml/xmlversion.h>
#include <libxml/parser.h>
#ifdef LIBXML_HTML_ENABLED
#ifdef __cplusplus
extern "C" {
#endif
/*
* Most of the back-end structures from XML and HTML are shared.
*/
typedef xmlParserCtxt htmlParserCtxt;
typedef xmlParserCtxtPtr htmlParserCtxtPtr;
typedef xmlParserNodeInfo htmlParserNodeInfo;
typedef xmlSAXHandler htmlSAXHandler;
typedef xmlSAXHandlerPtr htmlSAXHandlerPtr;
typedef xmlParserInput htmlParserInput;
typedef xmlParserInputPtr htmlParserInputPtr;
typedef xmlDocPtr htmlDocPtr;
typedef xmlNodePtr htmlNodePtr;
/*
* Internal description of an HTML element, representing HTML 4.01
* and XHTML 1.0 (which share the same structure).
*/
typedef struct _htmlElemDesc htmlElemDesc;
typedef htmlElemDesc *htmlElemDescPtr;
struct _htmlElemDesc {
const char *name; /* The tag name */
char startTag; /* Whether the start tag can be implied */
char endTag; /* Whether the end tag can be implied */
char saveEndTag; /* Whether the end tag should be saved */
char empty; /* Is this an empty element ? */
char depr; /* Is this a deprecated element ? */
char dtd; /* 1: only in Loose DTD, 2: only Frameset one */
char isinline; /* is this a block 0 or inline 1 element */
const char *desc; /* the description */
/* NRK Jan.2003
* New fields encapsulating HTML structure
*
* Bugs:
* This is a very limited representation. It fails to tell us when
* an element *requires* subelements (we only have whether they're
* allowed or not), and it doesn't tell us where CDATA and PCDATA
* are allowed. Some element relationships are not fully represented:
* these are flagged with the word MODIFIER
*/
const char** subelts; /* allowed sub-elements of this element */
const char* defaultsubelt; /* subelement for suggested auto-repair
if necessary or NULL */
const char** attrs_opt; /* Optional Attributes */
const char** attrs_depr; /* Additional deprecated attributes */
const char** attrs_req; /* Required attributes */
};
/*
* Internal description of an HTML entity.
*/
typedef struct _htmlEntityDesc htmlEntityDesc;
typedef htmlEntityDesc *htmlEntityDescPtr;
struct _htmlEntityDesc {
unsigned int value; /* the UNICODE value for the character */
const char *name; /* The entity name */
const char *desc; /* the description */
};
/*
* There is only few public functions.
*/
XMLPUBFUN const htmlElemDesc * XMLCALL
htmlTagLookup (const xmlChar *tag);
XMLPUBFUN const htmlEntityDesc * XMLCALL
htmlEntityLookup(const xmlChar *name);
XMLPUBFUN const htmlEntityDesc * XMLCALL
htmlEntityValueLookup(unsigned int value);
XMLPUBFUN int XMLCALL
htmlIsAutoClosed(htmlDocPtr doc,
htmlNodePtr elem);
XMLPUBFUN int XMLCALL
htmlAutoCloseTag(htmlDocPtr doc,
const xmlChar *name,
htmlNodePtr elem);
XMLPUBFUN const htmlEntityDesc * XMLCALL
htmlParseEntityRef(htmlParserCtxtPtr ctxt,
const xmlChar **str);
XMLPUBFUN int XMLCALL
htmlParseCharRef(htmlParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
htmlParseElement(htmlParserCtxtPtr ctxt);
XMLPUBFUN htmlParserCtxtPtr XMLCALL
htmlNewParserCtxt(void);
XMLPUBFUN htmlParserCtxtPtr XMLCALL
htmlCreateMemoryParserCtxt(const char *buffer,
int size);
XMLPUBFUN int XMLCALL
htmlParseDocument(htmlParserCtxtPtr ctxt);
XMLPUBFUN htmlDocPtr XMLCALL
htmlSAXParseDoc (const xmlChar *cur,
const char *encoding,
htmlSAXHandlerPtr sax,
void *userData);
XMLPUBFUN htmlDocPtr XMLCALL
htmlParseDoc (const xmlChar *cur,
const char *encoding);
XMLPUBFUN htmlDocPtr XMLCALL
htmlSAXParseFile(const char *filename,
const char *encoding,
htmlSAXHandlerPtr sax,
void *userData);
XMLPUBFUN htmlDocPtr XMLCALL
htmlParseFile (const char *filename,
const char *encoding);
XMLPUBFUN int XMLCALL
UTF8ToHtml (unsigned char *out,
int *outlen,
const unsigned char *in,
int *inlen);
XMLPUBFUN int XMLCALL
htmlEncodeEntities(unsigned char *out,
int *outlen,
const unsigned char *in,
int *inlen, int quoteChar);
XMLPUBFUN int XMLCALL
htmlIsScriptAttribute(const xmlChar *name);
XMLPUBFUN int XMLCALL
htmlHandleOmittedElem(int val);
#ifdef LIBXML_PUSH_ENABLED
/**
* Interfaces for the Push mode.
*/
XMLPUBFUN htmlParserCtxtPtr XMLCALL
htmlCreatePushParserCtxt(htmlSAXHandlerPtr sax,
void *user_data,
const char *chunk,
int size,
const char *filename,
xmlCharEncoding enc);
XMLPUBFUN int XMLCALL
htmlParseChunk (htmlParserCtxtPtr ctxt,
const char *chunk,
int size,
int terminate);
#endif /* LIBXML_PUSH_ENABLED */
XMLPUBFUN void XMLCALL
htmlFreeParserCtxt (htmlParserCtxtPtr ctxt);
/*
* New set of simpler/more flexible APIs
*/
/**
* xmlParserOption:
*
* This is the set of XML parser options that can be passed down
* to the xmlReadDoc() and similar calls.
*/
typedef enum {
HTML_PARSE_RECOVER = 1<<0, /* Relaxed parsing */
HTML_PARSE_NODEFDTD = 1<<2, /* do not default a doctype if not found */
HTML_PARSE_NOERROR = 1<<5, /* suppress error reports */
HTML_PARSE_NOWARNING= 1<<6, /* suppress warning reports */
HTML_PARSE_PEDANTIC = 1<<7, /* pedantic error reporting */
HTML_PARSE_NOBLANKS = 1<<8, /* remove blank nodes */
HTML_PARSE_NONET = 1<<11,/* Forbid network access */
HTML_PARSE_NOIMPLIED= 1<<13,/* Do not add implied html/body... elements */
HTML_PARSE_COMPACT = 1<<16,/* compact small text nodes */
HTML_PARSE_IGNORE_ENC=1<<21 /* ignore internal document encoding hint */
} htmlParserOption;
XMLPUBFUN void XMLCALL
htmlCtxtReset (htmlParserCtxtPtr ctxt);
XMLPUBFUN int XMLCALL
htmlCtxtUseOptions (htmlParserCtxtPtr ctxt,
int options);
XMLPUBFUN htmlDocPtr XMLCALL
htmlReadDoc (const xmlChar *cur,
const char *URL,
const char *encoding,
int options);
XMLPUBFUN htmlDocPtr XMLCALL
htmlReadFile (const char *URL,
const char *encoding,
int options);
XMLPUBFUN htmlDocPtr XMLCALL
htmlReadMemory (const char *buffer,
int size,
const char *URL,
const char *encoding,
int options);
XMLPUBFUN htmlDocPtr XMLCALL
htmlReadFd (int fd,
const char *URL,
const char *encoding,
int options);
XMLPUBFUN htmlDocPtr XMLCALL
htmlReadIO (xmlInputReadCallback ioread,
xmlInputCloseCallback ioclose,
void *ioctx,
const char *URL,
const char *encoding,
int options);
XMLPUBFUN htmlDocPtr XMLCALL
htmlCtxtReadDoc (xmlParserCtxtPtr ctxt,
const xmlChar *cur,
const char *URL,
const char *encoding,
int options);
XMLPUBFUN htmlDocPtr XMLCALL
htmlCtxtReadFile (xmlParserCtxtPtr ctxt,
const char *filename,
const char *encoding,
int options);
XMLPUBFUN htmlDocPtr XMLCALL
htmlCtxtReadMemory (xmlParserCtxtPtr ctxt,
const char *buffer,
int size,
const char *URL,
const char *encoding,
int options);
XMLPUBFUN htmlDocPtr XMLCALL
htmlCtxtReadFd (xmlParserCtxtPtr ctxt,
int fd,
const char *URL,
const char *encoding,
int options);
XMLPUBFUN htmlDocPtr XMLCALL
htmlCtxtReadIO (xmlParserCtxtPtr ctxt,
xmlInputReadCallback ioread,
xmlInputCloseCallback ioclose,
void *ioctx,
const char *URL,
const char *encoding,
int options);
/* NRK/Jan2003: further knowledge of HTML structure
*/
typedef enum {
HTML_NA = 0 , /* something we don't check at all */
HTML_INVALID = 0x1 ,
HTML_DEPRECATED = 0x2 ,
HTML_VALID = 0x4 ,
HTML_REQUIRED = 0xc /* VALID bit set so ( & HTML_VALID ) is TRUE */
} htmlStatus ;
/* Using htmlElemDesc rather than name here, to emphasise the fact
that otherwise there's a lookup overhead
*/
XMLPUBFUN htmlStatus XMLCALL htmlAttrAllowed(const htmlElemDesc*, const xmlChar*, int) ;
XMLPUBFUN int XMLCALL htmlElementAllowedHere(const htmlElemDesc*, const xmlChar*) ;
XMLPUBFUN htmlStatus XMLCALL htmlElementStatusHere(const htmlElemDesc*, const htmlElemDesc*) ;
XMLPUBFUN htmlStatus XMLCALL htmlNodeStatus(const htmlNodePtr, int) ;
/**
* htmlDefaultSubelement:
* @elt: HTML element
*
* Returns the default subelement for this element
*/
#define htmlDefaultSubelement(elt) elt->defaultsubelt
/**
* htmlElementAllowedHereDesc:
* @parent: HTML parent element
* @elt: HTML element
*
* Checks whether an HTML element description may be a
* direct child of the specified element.
*
* Returns 1 if allowed; 0 otherwise.
*/
#define htmlElementAllowedHereDesc(parent,elt) \
htmlElementAllowedHere((parent), (elt)->name)
/**
* htmlRequiredAttrs:
* @elt: HTML element
*
* Returns the attributes required for the specified element.
*/
#define htmlRequiredAttrs(elt) (elt)->attrs_req
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_HTML_ENABLED */
#endif /* __HTML_PARSER_H__ */

@ -0,0 +1,147 @@
/*
* Summary: specific APIs to process HTML tree, especially serialization
* Description: this module implements a few function needed to process
* tree in an HTML specific way.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __HTML_TREE_H__
#define __HTML_TREE_H__
#include <stdio.h>
#include <libxml/xmlversion.h>
#include <libxml/tree.h>
#include <libxml/HTMLparser.h>
#ifdef LIBXML_HTML_ENABLED
#ifdef __cplusplus
extern "C" {
#endif
/**
* HTML_TEXT_NODE:
*
* Macro. A text node in a HTML document is really implemented
* the same way as a text node in an XML document.
*/
#define HTML_TEXT_NODE XML_TEXT_NODE
/**
* HTML_ENTITY_REF_NODE:
*
* Macro. An entity reference in a HTML document is really implemented
* the same way as an entity reference in an XML document.
*/
#define HTML_ENTITY_REF_NODE XML_ENTITY_REF_NODE
/**
* HTML_COMMENT_NODE:
*
* Macro. A comment in a HTML document is really implemented
* the same way as a comment in an XML document.
*/
#define HTML_COMMENT_NODE XML_COMMENT_NODE
/**
* HTML_PRESERVE_NODE:
*
* Macro. A preserved node in a HTML document is really implemented
* the same way as a CDATA section in an XML document.
*/
#define HTML_PRESERVE_NODE XML_CDATA_SECTION_NODE
/**
* HTML_PI_NODE:
*
* Macro. A processing instruction in a HTML document is really implemented
* the same way as a processing instruction in an XML document.
*/
#define HTML_PI_NODE XML_PI_NODE
XMLPUBFUN htmlDocPtr XMLCALL
htmlNewDoc (const xmlChar *URI,
const xmlChar *ExternalID);
XMLPUBFUN htmlDocPtr XMLCALL
htmlNewDocNoDtD (const xmlChar *URI,
const xmlChar *ExternalID);
XMLPUBFUN const xmlChar * XMLCALL
htmlGetMetaEncoding (htmlDocPtr doc);
XMLPUBFUN int XMLCALL
htmlSetMetaEncoding (htmlDocPtr doc,
const xmlChar *encoding);
#ifdef LIBXML_OUTPUT_ENABLED
XMLPUBFUN void XMLCALL
htmlDocDumpMemory (xmlDocPtr cur,
xmlChar **mem,
int *size);
XMLPUBFUN void XMLCALL
htmlDocDumpMemoryFormat (xmlDocPtr cur,
xmlChar **mem,
int *size,
int format);
XMLPUBFUN int XMLCALL
htmlDocDump (FILE *f,
xmlDocPtr cur);
XMLPUBFUN int XMLCALL
htmlSaveFile (const char *filename,
xmlDocPtr cur);
XMLPUBFUN int XMLCALL
htmlNodeDump (xmlBufferPtr buf,
xmlDocPtr doc,
xmlNodePtr cur);
XMLPUBFUN void XMLCALL
htmlNodeDumpFile (FILE *out,
xmlDocPtr doc,
xmlNodePtr cur);
XMLPUBFUN int XMLCALL
htmlNodeDumpFileFormat (FILE *out,
xmlDocPtr doc,
xmlNodePtr cur,
const char *encoding,
int format);
XMLPUBFUN int XMLCALL
htmlSaveFileEnc (const char *filename,
xmlDocPtr cur,
const char *encoding);
XMLPUBFUN int XMLCALL
htmlSaveFileFormat (const char *filename,
xmlDocPtr cur,
const char *encoding,
int format);
XMLPUBFUN void XMLCALL
htmlNodeDumpFormatOutput(xmlOutputBufferPtr buf,
xmlDocPtr doc,
xmlNodePtr cur,
const char *encoding,
int format);
XMLPUBFUN void XMLCALL
htmlDocContentDumpOutput(xmlOutputBufferPtr buf,
xmlDocPtr cur,
const char *encoding);
XMLPUBFUN void XMLCALL
htmlDocContentDumpFormatOutput(xmlOutputBufferPtr buf,
xmlDocPtr cur,
const char *encoding,
int format);
XMLPUBFUN void XMLCALL
htmlNodeDumpOutput (xmlOutputBufferPtr buf,
xmlDocPtr doc,
xmlNodePtr cur,
const char *encoding);
#endif /* LIBXML_OUTPUT_ENABLED */
XMLPUBFUN int XMLCALL
htmlIsBooleanAttr (const xmlChar *name);
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_HTML_ENABLED */
#endif /* __HTML_TREE_H__ */

@ -0,0 +1,173 @@
/*
* Summary: Old SAX version 1 handler, deprecated
* Description: DEPRECATED set of SAX version 1 interfaces used to
* build the DOM tree.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_SAX_H__
#define __XML_SAX_H__
#include <stdio.h>
#include <stdlib.h>
#include <libxml/xmlversion.h>
#include <libxml/parser.h>
#include <libxml/xlink.h>
#ifdef LIBXML_LEGACY_ENABLED
#ifdef __cplusplus
extern "C" {
#endif
XMLPUBFUN const xmlChar * XMLCALL
getPublicId (void *ctx);
XMLPUBFUN const xmlChar * XMLCALL
getSystemId (void *ctx);
XMLPUBFUN void XMLCALL
setDocumentLocator (void *ctx,
xmlSAXLocatorPtr loc);
XMLPUBFUN int XMLCALL
getLineNumber (void *ctx);
XMLPUBFUN int XMLCALL
getColumnNumber (void *ctx);
XMLPUBFUN int XMLCALL
isStandalone (void *ctx);
XMLPUBFUN int XMLCALL
hasInternalSubset (void *ctx);
XMLPUBFUN int XMLCALL
hasExternalSubset (void *ctx);
XMLPUBFUN void XMLCALL
internalSubset (void *ctx,
const xmlChar *name,
const xmlChar *ExternalID,
const xmlChar *SystemID);
XMLPUBFUN void XMLCALL
externalSubset (void *ctx,
const xmlChar *name,
const xmlChar *ExternalID,
const xmlChar *SystemID);
XMLPUBFUN xmlEntityPtr XMLCALL
getEntity (void *ctx,
const xmlChar *name);
XMLPUBFUN xmlEntityPtr XMLCALL
getParameterEntity (void *ctx,
const xmlChar *name);
XMLPUBFUN xmlParserInputPtr XMLCALL
resolveEntity (void *ctx,
const xmlChar *publicId,
const xmlChar *systemId);
XMLPUBFUN void XMLCALL
entityDecl (void *ctx,
const xmlChar *name,
int type,
const xmlChar *publicId,
const xmlChar *systemId,
xmlChar *content);
XMLPUBFUN void XMLCALL
attributeDecl (void *ctx,
const xmlChar *elem,
const xmlChar *fullname,
int type,
int def,
const xmlChar *defaultValue,
xmlEnumerationPtr tree);
XMLPUBFUN void XMLCALL
elementDecl (void *ctx,
const xmlChar *name,
int type,
xmlElementContentPtr content);
XMLPUBFUN void XMLCALL
notationDecl (void *ctx,
const xmlChar *name,
const xmlChar *publicId,
const xmlChar *systemId);
XMLPUBFUN void XMLCALL
unparsedEntityDecl (void *ctx,
const xmlChar *name,
const xmlChar *publicId,
const xmlChar *systemId,
const xmlChar *notationName);
XMLPUBFUN void XMLCALL
startDocument (void *ctx);
XMLPUBFUN void XMLCALL
endDocument (void *ctx);
XMLPUBFUN void XMLCALL
attribute (void *ctx,
const xmlChar *fullname,
const xmlChar *value);
XMLPUBFUN void XMLCALL
startElement (void *ctx,
const xmlChar *fullname,
const xmlChar **atts);
XMLPUBFUN void XMLCALL
endElement (void *ctx,
const xmlChar *name);
XMLPUBFUN void XMLCALL
reference (void *ctx,
const xmlChar *name);
XMLPUBFUN void XMLCALL
characters (void *ctx,
const xmlChar *ch,
int len);
XMLPUBFUN void XMLCALL
ignorableWhitespace (void *ctx,
const xmlChar *ch,
int len);
XMLPUBFUN void XMLCALL
processingInstruction (void *ctx,
const xmlChar *target,
const xmlChar *data);
XMLPUBFUN void XMLCALL
globalNamespace (void *ctx,
const xmlChar *href,
const xmlChar *prefix);
XMLPUBFUN void XMLCALL
setNamespace (void *ctx,
const xmlChar *name);
XMLPUBFUN xmlNsPtr XMLCALL
getNamespace (void *ctx);
XMLPUBFUN int XMLCALL
checkNamespace (void *ctx,
xmlChar *nameSpace);
XMLPUBFUN void XMLCALL
namespaceDecl (void *ctx,
const xmlChar *href,
const xmlChar *prefix);
XMLPUBFUN void XMLCALL
comment (void *ctx,
const xmlChar *value);
XMLPUBFUN void XMLCALL
cdataBlock (void *ctx,
const xmlChar *value,
int len);
#ifdef LIBXML_SAX1_ENABLED
XMLPUBFUN void XMLCALL
initxmlDefaultSAXHandler (xmlSAXHandlerV1 *hdlr,
int warning);
#ifdef LIBXML_HTML_ENABLED
XMLPUBFUN void XMLCALL
inithtmlDefaultSAXHandler (xmlSAXHandlerV1 *hdlr);
#endif
#ifdef LIBXML_DOCB_ENABLED
XMLPUBFUN void XMLCALL
initdocbDefaultSAXHandler (xmlSAXHandlerV1 *hdlr);
#endif
#endif /* LIBXML_SAX1_ENABLED */
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_LEGACY_ENABLED */
#endif /* __XML_SAX_H__ */

@ -0,0 +1,178 @@
/*
* Summary: SAX2 parser interface used to build the DOM tree
* Description: those are the default SAX2 interfaces used by
* the library when building DOM tree.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_SAX2_H__
#define __XML_SAX2_H__
#include <stdio.h>
#include <stdlib.h>
#include <libxml/xmlversion.h>
#include <libxml/parser.h>
#include <libxml/xlink.h>
#ifdef __cplusplus
extern "C" {
#endif
XMLPUBFUN const xmlChar * XMLCALL
xmlSAX2GetPublicId (void *ctx);
XMLPUBFUN const xmlChar * XMLCALL
xmlSAX2GetSystemId (void *ctx);
XMLPUBFUN void XMLCALL
xmlSAX2SetDocumentLocator (void *ctx,
xmlSAXLocatorPtr loc);
XMLPUBFUN int XMLCALL
xmlSAX2GetLineNumber (void *ctx);
XMLPUBFUN int XMLCALL
xmlSAX2GetColumnNumber (void *ctx);
XMLPUBFUN int XMLCALL
xmlSAX2IsStandalone (void *ctx);
XMLPUBFUN int XMLCALL
xmlSAX2HasInternalSubset (void *ctx);
XMLPUBFUN int XMLCALL
xmlSAX2HasExternalSubset (void *ctx);
XMLPUBFUN void XMLCALL
xmlSAX2InternalSubset (void *ctx,
const xmlChar *name,
const xmlChar *ExternalID,
const xmlChar *SystemID);
XMLPUBFUN void XMLCALL
xmlSAX2ExternalSubset (void *ctx,
const xmlChar *name,
const xmlChar *ExternalID,
const xmlChar *SystemID);
XMLPUBFUN xmlEntityPtr XMLCALL
xmlSAX2GetEntity (void *ctx,
const xmlChar *name);
XMLPUBFUN xmlEntityPtr XMLCALL
xmlSAX2GetParameterEntity (void *ctx,
const xmlChar *name);
XMLPUBFUN xmlParserInputPtr XMLCALL
xmlSAX2ResolveEntity (void *ctx,
const xmlChar *publicId,
const xmlChar *systemId);
XMLPUBFUN void XMLCALL
xmlSAX2EntityDecl (void *ctx,
const xmlChar *name,
int type,
const xmlChar *publicId,
const xmlChar *systemId,
xmlChar *content);
XMLPUBFUN void XMLCALL
xmlSAX2AttributeDecl (void *ctx,
const xmlChar *elem,
const xmlChar *fullname,
int type,
int def,
const xmlChar *defaultValue,
xmlEnumerationPtr tree);
XMLPUBFUN void XMLCALL
xmlSAX2ElementDecl (void *ctx,
const xmlChar *name,
int type,
xmlElementContentPtr content);
XMLPUBFUN void XMLCALL
xmlSAX2NotationDecl (void *ctx,
const xmlChar *name,
const xmlChar *publicId,
const xmlChar *systemId);
XMLPUBFUN void XMLCALL
xmlSAX2UnparsedEntityDecl (void *ctx,
const xmlChar *name,
const xmlChar *publicId,
const xmlChar *systemId,
const xmlChar *notationName);
XMLPUBFUN void XMLCALL
xmlSAX2StartDocument (void *ctx);
XMLPUBFUN void XMLCALL
xmlSAX2EndDocument (void *ctx);
#if defined(LIBXML_SAX1_ENABLED) || defined(LIBXML_HTML_ENABLED) || \
defined(LIBXML_WRITER_ENABLED) || defined(LIBXML_DOCB_ENABLED) || \
defined(LIBXML_LEGACY_ENABLED)
XMLPUBFUN void XMLCALL
xmlSAX2StartElement (void *ctx,
const xmlChar *fullname,
const xmlChar **atts);
XMLPUBFUN void XMLCALL
xmlSAX2EndElement (void *ctx,
const xmlChar *name);
#endif /* LIBXML_SAX1_ENABLED or LIBXML_HTML_ENABLED or LIBXML_LEGACY_ENABLED */
XMLPUBFUN void XMLCALL
xmlSAX2StartElementNs (void *ctx,
const xmlChar *localname,
const xmlChar *prefix,
const xmlChar *URI,
int nb_namespaces,
const xmlChar **namespaces,
int nb_attributes,
int nb_defaulted,
const xmlChar **attributes);
XMLPUBFUN void XMLCALL
xmlSAX2EndElementNs (void *ctx,
const xmlChar *localname,
const xmlChar *prefix,
const xmlChar *URI);
XMLPUBFUN void XMLCALL
xmlSAX2Reference (void *ctx,
const xmlChar *name);
XMLPUBFUN void XMLCALL
xmlSAX2Characters (void *ctx,
const xmlChar *ch,
int len);
XMLPUBFUN void XMLCALL
xmlSAX2IgnorableWhitespace (void *ctx,
const xmlChar *ch,
int len);
XMLPUBFUN void XMLCALL
xmlSAX2ProcessingInstruction (void *ctx,
const xmlChar *target,
const xmlChar *data);
XMLPUBFUN void XMLCALL
xmlSAX2Comment (void *ctx,
const xmlChar *value);
XMLPUBFUN void XMLCALL
xmlSAX2CDataBlock (void *ctx,
const xmlChar *value,
int len);
#ifdef LIBXML_SAX1_ENABLED
XMLPUBFUN int XMLCALL
xmlSAXDefaultVersion (int version);
#endif /* LIBXML_SAX1_ENABLED */
XMLPUBFUN int XMLCALL
xmlSAXVersion (xmlSAXHandler *hdlr,
int version);
XMLPUBFUN void XMLCALL
xmlSAX2InitDefaultSAXHandler (xmlSAXHandler *hdlr,
int warning);
#ifdef LIBXML_HTML_ENABLED
XMLPUBFUN void XMLCALL
xmlSAX2InitHtmlDefaultSAXHandler(xmlSAXHandler *hdlr);
XMLPUBFUN void XMLCALL
htmlDefaultSAXHandlerInit (void);
#endif
#ifdef LIBXML_DOCB_ENABLED
XMLPUBFUN void XMLCALL
xmlSAX2InitDocbDefaultSAXHandler(xmlSAXHandler *hdlr);
XMLPUBFUN void XMLCALL
docbDefaultSAXHandlerInit (void);
#endif
XMLPUBFUN void XMLCALL
xmlDefaultSAXHandlerInit (void);
#ifdef __cplusplus
}
#endif
#endif /* __XML_SAX2_H__ */

@ -0,0 +1,126 @@
/*
* Summary: Provide Canonical XML and Exclusive XML Canonicalization
* Description: the c14n modules provides a
*
* "Canonical XML" implementation
* http://www.w3.org/TR/xml-c14n
*
* and an
*
* "Exclusive XML Canonicalization" implementation
* http://www.w3.org/TR/xml-exc-c14n
* Copy: See Copyright for the status of this software.
*
* Author: Aleksey Sanin <aleksey@aleksey.com>
*/
#ifndef __XML_C14N_H__
#define __XML_C14N_H__
#ifdef LIBXML_C14N_ENABLED
#ifdef LIBXML_OUTPUT_ENABLED
#ifdef __cplusplus
extern "C" {
#endif /* __cplusplus */
#include <libxml/xmlversion.h>
#include <libxml/tree.h>
#include <libxml/xpath.h>
/*
* XML Canonicazation
* http://www.w3.org/TR/xml-c14n
*
* Exclusive XML Canonicazation
* http://www.w3.org/TR/xml-exc-c14n
*
* Canonical form of an XML document could be created if and only if
* a) default attributes (if any) are added to all nodes
* b) all character and parsed entity references are resolved
* In order to achive this in libxml2 the document MUST be loaded with
* following global setings:
*
* xmlLoadExtDtdDefaultValue = XML_DETECT_IDS | XML_COMPLETE_ATTRS;
* xmlSubstituteEntitiesDefault(1);
*
* or corresponding parser context setting:
* xmlParserCtxtPtr ctxt;
*
* ...
* ctxt->loadsubset = XML_DETECT_IDS | XML_COMPLETE_ATTRS;
* ctxt->replaceEntities = 1;
* ...
*/
/*
* xmlC14NMode:
*
* Predefined values for C14N modes
*
*/
typedef enum {
XML_C14N_1_0 = 0, /* Origianal C14N 1.0 spec */
XML_C14N_EXCLUSIVE_1_0 = 1, /* Exclusive C14N 1.0 spec */
XML_C14N_1_1 = 2 /* C14N 1.1 spec */
} xmlC14NMode;
XMLPUBFUN int XMLCALL
xmlC14NDocSaveTo (xmlDocPtr doc,
xmlNodeSetPtr nodes,
int mode, /* a xmlC14NMode */
xmlChar **inclusive_ns_prefixes,
int with_comments,
xmlOutputBufferPtr buf);
XMLPUBFUN int XMLCALL
xmlC14NDocDumpMemory (xmlDocPtr doc,
xmlNodeSetPtr nodes,
int mode, /* a xmlC14NMode */
xmlChar **inclusive_ns_prefixes,
int with_comments,
xmlChar **doc_txt_ptr);
XMLPUBFUN int XMLCALL
xmlC14NDocSave (xmlDocPtr doc,
xmlNodeSetPtr nodes,
int mode, /* a xmlC14NMode */
xmlChar **inclusive_ns_prefixes,
int with_comments,
const char* filename,
int compression);
/**
* This is the core C14N function
*/
/**
* xmlC14NIsVisibleCallback:
* @user_data: user data
* @node: the curent node
* @parent: the parent node
*
* Signature for a C14N callback on visible nodes
*
* Returns 1 if the node should be included
*/
typedef int (*xmlC14NIsVisibleCallback) (void* user_data,
xmlNodePtr node,
xmlNodePtr parent);
XMLPUBFUN int XMLCALL
xmlC14NExecute (xmlDocPtr doc,
xmlC14NIsVisibleCallback is_visible_callback,
void* user_data,
int mode, /* a xmlC14NMode */
xmlChar **inclusive_ns_prefixes,
int with_comments,
xmlOutputBufferPtr buf);
#ifdef __cplusplus
}
#endif /* __cplusplus */
#endif /* LIBXML_OUTPUT_ENABLED */
#endif /* LIBXML_C14N_ENABLED */
#endif /* __XML_C14N_H__ */

@ -0,0 +1,182 @@
/**
* Summary: interfaces to the Catalog handling system
* Description: the catalog module implements the support for
* XML Catalogs and SGML catalogs
*
* SGML Open Technical Resolution TR9401:1997.
* http://www.jclark.com/sp/catalog.htm
*
* XML Catalogs Working Draft 06 August 2001
* http://www.oasis-open.org/committees/entity/spec-2001-08-06.html
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_CATALOG_H__
#define __XML_CATALOG_H__
#include <stdio.h>
#include <libxml/xmlversion.h>
#include <libxml/xmlstring.h>
#include <libxml/tree.h>
#ifdef LIBXML_CATALOG_ENABLED
#ifdef __cplusplus
extern "C" {
#endif
/**
* XML_CATALOGS_NAMESPACE:
*
* The namespace for the XML Catalogs elements.
*/
#define XML_CATALOGS_NAMESPACE \
(const xmlChar *) "urn:oasis:names:tc:entity:xmlns:xml:catalog"
/**
* XML_CATALOG_PI:
*
* The specific XML Catalog Processing Instuction name.
*/
#define XML_CATALOG_PI \
(const xmlChar *) "oasis-xml-catalog"
/*
* The API is voluntarily limited to general cataloging.
*/
typedef enum {
XML_CATA_PREFER_NONE = 0,
XML_CATA_PREFER_PUBLIC = 1,
XML_CATA_PREFER_SYSTEM
} xmlCatalogPrefer;
typedef enum {
XML_CATA_ALLOW_NONE = 0,
XML_CATA_ALLOW_GLOBAL = 1,
XML_CATA_ALLOW_DOCUMENT = 2,
XML_CATA_ALLOW_ALL = 3
} xmlCatalogAllow;
typedef struct _xmlCatalog xmlCatalog;
typedef xmlCatalog *xmlCatalogPtr;
/*
* Operations on a given catalog.
*/
XMLPUBFUN xmlCatalogPtr XMLCALL
xmlNewCatalog (int sgml);
XMLPUBFUN xmlCatalogPtr XMLCALL
xmlLoadACatalog (const char *filename);
XMLPUBFUN xmlCatalogPtr XMLCALL
xmlLoadSGMLSuperCatalog (const char *filename);
XMLPUBFUN int XMLCALL
xmlConvertSGMLCatalog (xmlCatalogPtr catal);
XMLPUBFUN int XMLCALL
xmlACatalogAdd (xmlCatalogPtr catal,
const xmlChar *type,
const xmlChar *orig,
const xmlChar *replace);
XMLPUBFUN int XMLCALL
xmlACatalogRemove (xmlCatalogPtr catal,
const xmlChar *value);
XMLPUBFUN xmlChar * XMLCALL
xmlACatalogResolve (xmlCatalogPtr catal,
const xmlChar *pubID,
const xmlChar *sysID);
XMLPUBFUN xmlChar * XMLCALL
xmlACatalogResolveSystem(xmlCatalogPtr catal,
const xmlChar *sysID);
XMLPUBFUN xmlChar * XMLCALL
xmlACatalogResolvePublic(xmlCatalogPtr catal,
const xmlChar *pubID);
XMLPUBFUN xmlChar * XMLCALL
xmlACatalogResolveURI (xmlCatalogPtr catal,
const xmlChar *URI);
#ifdef LIBXML_OUTPUT_ENABLED
XMLPUBFUN void XMLCALL
xmlACatalogDump (xmlCatalogPtr catal,
FILE *out);
#endif /* LIBXML_OUTPUT_ENABLED */
XMLPUBFUN void XMLCALL
xmlFreeCatalog (xmlCatalogPtr catal);
XMLPUBFUN int XMLCALL
xmlCatalogIsEmpty (xmlCatalogPtr catal);
/*
* Global operations.
*/
XMLPUBFUN void XMLCALL
xmlInitializeCatalog (void);
XMLPUBFUN int XMLCALL
xmlLoadCatalog (const char *filename);
XMLPUBFUN void XMLCALL
xmlLoadCatalogs (const char *paths);
XMLPUBFUN void XMLCALL
xmlCatalogCleanup (void);
#ifdef LIBXML_OUTPUT_ENABLED
XMLPUBFUN void XMLCALL
xmlCatalogDump (FILE *out);
#endif /* LIBXML_OUTPUT_ENABLED */
XMLPUBFUN xmlChar * XMLCALL
xmlCatalogResolve (const xmlChar *pubID,
const xmlChar *sysID);
XMLPUBFUN xmlChar * XMLCALL
xmlCatalogResolveSystem (const xmlChar *sysID);
XMLPUBFUN xmlChar * XMLCALL
xmlCatalogResolvePublic (const xmlChar *pubID);
XMLPUBFUN xmlChar * XMLCALL
xmlCatalogResolveURI (const xmlChar *URI);
XMLPUBFUN int XMLCALL
xmlCatalogAdd (const xmlChar *type,
const xmlChar *orig,
const xmlChar *replace);
XMLPUBFUN int XMLCALL
xmlCatalogRemove (const xmlChar *value);
XMLPUBFUN xmlDocPtr XMLCALL
xmlParseCatalogFile (const char *filename);
XMLPUBFUN int XMLCALL
xmlCatalogConvert (void);
/*
* Strictly minimal interfaces for per-document catalogs used
* by the parser.
*/
XMLPUBFUN void XMLCALL
xmlCatalogFreeLocal (void *catalogs);
XMLPUBFUN void * XMLCALL
xmlCatalogAddLocal (void *catalogs,
const xmlChar *URL);
XMLPUBFUN xmlChar * XMLCALL
xmlCatalogLocalResolve (void *catalogs,
const xmlChar *pubID,
const xmlChar *sysID);
XMLPUBFUN xmlChar * XMLCALL
xmlCatalogLocalResolveURI(void *catalogs,
const xmlChar *URI);
/*
* Preference settings.
*/
XMLPUBFUN int XMLCALL
xmlCatalogSetDebug (int level);
XMLPUBFUN xmlCatalogPrefer XMLCALL
xmlCatalogSetDefaultPrefer(xmlCatalogPrefer prefer);
XMLPUBFUN void XMLCALL
xmlCatalogSetDefaults (xmlCatalogAllow allow);
XMLPUBFUN xmlCatalogAllow XMLCALL
xmlCatalogGetDefaults (void);
/* DEPRECATED interfaces */
XMLPUBFUN const xmlChar * XMLCALL
xmlCatalogGetSystem (const xmlChar *sysID);
XMLPUBFUN const xmlChar * XMLCALL
xmlCatalogGetPublic (const xmlChar *pubID);
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_CATALOG_ENABLED */
#endif /* __XML_CATALOG_H__ */

@ -0,0 +1,230 @@
/*
* Summary: Unicode character range checking
* Description: this module exports interfaces for the character
* range validation APIs
*
* This file is automatically generated from the cvs source
* definition files using the genChRanges.py Python script
*
* Generation date: Mon Mar 27 11:09:48 2006
* Sources: chvalid.def
* Author: William Brack <wbrack@mmm.com.hk>
*/
#ifndef __XML_CHVALID_H__
#define __XML_CHVALID_H__
#include <libxml/xmlversion.h>
#include <libxml/xmlstring.h>
#ifdef __cplusplus
extern "C" {
#endif
/*
* Define our typedefs and structures
*
*/
typedef struct _xmlChSRange xmlChSRange;
typedef xmlChSRange *xmlChSRangePtr;
struct _xmlChSRange {
unsigned short low;
unsigned short high;
};
typedef struct _xmlChLRange xmlChLRange;
typedef xmlChLRange *xmlChLRangePtr;
struct _xmlChLRange {
unsigned int low;
unsigned int high;
};
typedef struct _xmlChRangeGroup xmlChRangeGroup;
typedef xmlChRangeGroup *xmlChRangeGroupPtr;
struct _xmlChRangeGroup {
int nbShortRange;
int nbLongRange;
const xmlChSRange *shortRange; /* points to an array of ranges */
const xmlChLRange *longRange;
};
/**
* Range checking routine
*/
XMLPUBFUN int XMLCALL
xmlCharInRange(unsigned int val, const xmlChRangeGroup *group);
/**
* xmlIsBaseChar_ch:
* @c: char to validate
*
* Automatically generated by genChRanges.py
*/
#define xmlIsBaseChar_ch(c) (((0x41 <= (c)) && ((c) <= 0x5a)) || \
((0x61 <= (c)) && ((c) <= 0x7a)) || \
((0xc0 <= (c)) && ((c) <= 0xd6)) || \
((0xd8 <= (c)) && ((c) <= 0xf6)) || \
(0xf8 <= (c)))
/**
* xmlIsBaseCharQ:
* @c: char to validate
*
* Automatically generated by genChRanges.py
*/
#define xmlIsBaseCharQ(c) (((c) < 0x100) ? \
xmlIsBaseChar_ch((c)) : \
xmlCharInRange((c), &xmlIsBaseCharGroup))
XMLPUBVAR const xmlChRangeGroup xmlIsBaseCharGroup;
/**
* xmlIsBlank_ch:
* @c: char to validate
*
* Automatically generated by genChRanges.py
*/
#define xmlIsBlank_ch(c) (((c) == 0x20) || \
((0x9 <= (c)) && ((c) <= 0xa)) || \
((c) == 0xd))
/**
* xmlIsBlankQ:
* @c: char to validate
*
* Automatically generated by genChRanges.py
*/
#define xmlIsBlankQ(c) (((c) < 0x100) ? \
xmlIsBlank_ch((c)) : 0)
/**
* xmlIsChar_ch:
* @c: char to validate
*
* Automatically generated by genChRanges.py
*/
#define xmlIsChar_ch(c) (((0x9 <= (c)) && ((c) <= 0xa)) || \
((c) == 0xd) || \
(0x20 <= (c)))
/**
* xmlIsCharQ:
* @c: char to validate
*
* Automatically generated by genChRanges.py
*/
#define xmlIsCharQ(c) (((c) < 0x100) ? \
xmlIsChar_ch((c)) :\
(((0x100 <= (c)) && ((c) <= 0xd7ff)) || \
((0xe000 <= (c)) && ((c) <= 0xfffd)) || \
((0x10000 <= (c)) && ((c) <= 0x10ffff))))
XMLPUBVAR const xmlChRangeGroup xmlIsCharGroup;
/**
* xmlIsCombiningQ:
* @c: char to validate
*
* Automatically generated by genChRanges.py
*/
#define xmlIsCombiningQ(c) (((c) < 0x100) ? \
0 : \
xmlCharInRange((c), &xmlIsCombiningGroup))
XMLPUBVAR const xmlChRangeGroup xmlIsCombiningGroup;
/**
* xmlIsDigit_ch:
* @c: char to validate
*
* Automatically generated by genChRanges.py
*/
#define xmlIsDigit_ch(c) (((0x30 <= (c)) && ((c) <= 0x39)))
/**
* xmlIsDigitQ:
* @c: char to validate
*
* Automatically generated by genChRanges.py
*/
#define xmlIsDigitQ(c) (((c) < 0x100) ? \
xmlIsDigit_ch((c)) : \
xmlCharInRange((c), &xmlIsDigitGroup))
XMLPUBVAR const xmlChRangeGroup xmlIsDigitGroup;
/**
* xmlIsExtender_ch:
* @c: char to validate
*
* Automatically generated by genChRanges.py
*/
#define xmlIsExtender_ch(c) (((c) == 0xb7))
/**
* xmlIsExtenderQ:
* @c: char to validate
*
* Automatically generated by genChRanges.py
*/
#define xmlIsExtenderQ(c) (((c) < 0x100) ? \
xmlIsExtender_ch((c)) : \
xmlCharInRange((c), &xmlIsExtenderGroup))
XMLPUBVAR const xmlChRangeGroup xmlIsExtenderGroup;
/**
* xmlIsIdeographicQ:
* @c: char to validate
*
* Automatically generated by genChRanges.py
*/
#define xmlIsIdeographicQ(c) (((c) < 0x100) ? \
0 :\
(((0x4e00 <= (c)) && ((c) <= 0x9fa5)) || \
((c) == 0x3007) || \
((0x3021 <= (c)) && ((c) <= 0x3029))))
XMLPUBVAR const xmlChRangeGroup xmlIsIdeographicGroup;
XMLPUBVAR const unsigned char xmlIsPubidChar_tab[256];
/**
* xmlIsPubidChar_ch:
* @c: char to validate
*
* Automatically generated by genChRanges.py
*/
#define xmlIsPubidChar_ch(c) (xmlIsPubidChar_tab[(c)])
/**
* xmlIsPubidCharQ:
* @c: char to validate
*
* Automatically generated by genChRanges.py
*/
#define xmlIsPubidCharQ(c) (((c) < 0x100) ? \
xmlIsPubidChar_ch((c)) : 0)
XMLPUBFUN int XMLCALL
xmlIsBaseChar(unsigned int ch);
XMLPUBFUN int XMLCALL
xmlIsBlank(unsigned int ch);
XMLPUBFUN int XMLCALL
xmlIsChar(unsigned int ch);
XMLPUBFUN int XMLCALL
xmlIsCombining(unsigned int ch);
XMLPUBFUN int XMLCALL
xmlIsDigit(unsigned int ch);
XMLPUBFUN int XMLCALL
xmlIsExtender(unsigned int ch);
XMLPUBFUN int XMLCALL
xmlIsIdeographic(unsigned int ch);
XMLPUBFUN int XMLCALL
xmlIsPubidChar(unsigned int ch);
#ifdef __cplusplus
}
#endif
#endif /* __XML_CHVALID_H__ */

@ -0,0 +1,217 @@
/*
* Summary: Tree debugging APIs
* Description: Interfaces to a set of routines used for debugging the tree
* produced by the XML parser.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __DEBUG_XML__
#define __DEBUG_XML__
#include <stdio.h>
#include <libxml/xmlversion.h>
#include <libxml/tree.h>
#ifdef LIBXML_DEBUG_ENABLED
#include <libxml/xpath.h>
#ifdef __cplusplus
extern "C" {
#endif
/*
* The standard Dump routines.
*/
XMLPUBFUN void XMLCALL
xmlDebugDumpString (FILE *output,
const xmlChar *str);
XMLPUBFUN void XMLCALL
xmlDebugDumpAttr (FILE *output,
xmlAttrPtr attr,
int depth);
XMLPUBFUN void XMLCALL
xmlDebugDumpAttrList (FILE *output,
xmlAttrPtr attr,
int depth);
XMLPUBFUN void XMLCALL
xmlDebugDumpOneNode (FILE *output,
xmlNodePtr node,
int depth);
XMLPUBFUN void XMLCALL
xmlDebugDumpNode (FILE *output,
xmlNodePtr node,
int depth);
XMLPUBFUN void XMLCALL
xmlDebugDumpNodeList (FILE *output,
xmlNodePtr node,
int depth);
XMLPUBFUN void XMLCALL
xmlDebugDumpDocumentHead(FILE *output,
xmlDocPtr doc);
XMLPUBFUN void XMLCALL
xmlDebugDumpDocument (FILE *output,
xmlDocPtr doc);
XMLPUBFUN void XMLCALL
xmlDebugDumpDTD (FILE *output,
xmlDtdPtr dtd);
XMLPUBFUN void XMLCALL
xmlDebugDumpEntities (FILE *output,
xmlDocPtr doc);
/****************************************************************
* *
* Checking routines *
* *
****************************************************************/
XMLPUBFUN int XMLCALL
xmlDebugCheckDocument (FILE * output,
xmlDocPtr doc);
/****************************************************************
* *
* XML shell helpers *
* *
****************************************************************/
XMLPUBFUN void XMLCALL
xmlLsOneNode (FILE *output, xmlNodePtr node);
XMLPUBFUN int XMLCALL
xmlLsCountNode (xmlNodePtr node);
XMLPUBFUN const char * XMLCALL
xmlBoolToText (int boolval);
/****************************************************************
* *
* The XML shell related structures and functions *
* *
****************************************************************/
#ifdef LIBXML_XPATH_ENABLED
/**
* xmlShellReadlineFunc:
* @prompt: a string prompt
*
* This is a generic signature for the XML shell input function.
*
* Returns a string which will be freed by the Shell.
*/
typedef char * (* xmlShellReadlineFunc)(char *prompt);
/**
* xmlShellCtxt:
*
* A debugging shell context.
* TODO: add the defined function tables.
*/
typedef struct _xmlShellCtxt xmlShellCtxt;
typedef xmlShellCtxt *xmlShellCtxtPtr;
struct _xmlShellCtxt {
char *filename;
xmlDocPtr doc;
xmlNodePtr node;
xmlXPathContextPtr pctxt;
int loaded;
FILE *output;
xmlShellReadlineFunc input;
};
/**
* xmlShellCmd:
* @ctxt: a shell context
* @arg: a string argument
* @node: a first node
* @node2: a second node
*
* This is a generic signature for the XML shell functions.
*
* Returns an int, negative returns indicating errors.
*/
typedef int (* xmlShellCmd) (xmlShellCtxtPtr ctxt,
char *arg,
xmlNodePtr node,
xmlNodePtr node2);
XMLPUBFUN void XMLCALL
xmlShellPrintXPathError (int errorType,
const char *arg);
XMLPUBFUN void XMLCALL
xmlShellPrintXPathResult(xmlXPathObjectPtr list);
XMLPUBFUN int XMLCALL
xmlShellList (xmlShellCtxtPtr ctxt,
char *arg,
xmlNodePtr node,
xmlNodePtr node2);
XMLPUBFUN int XMLCALL
xmlShellBase (xmlShellCtxtPtr ctxt,
char *arg,
xmlNodePtr node,
xmlNodePtr node2);
XMLPUBFUN int XMLCALL
xmlShellDir (xmlShellCtxtPtr ctxt,
char *arg,
xmlNodePtr node,
xmlNodePtr node2);
XMLPUBFUN int XMLCALL
xmlShellLoad (xmlShellCtxtPtr ctxt,
char *filename,
xmlNodePtr node,
xmlNodePtr node2);
#ifdef LIBXML_OUTPUT_ENABLED
XMLPUBFUN void XMLCALL
xmlShellPrintNode (xmlNodePtr node);
XMLPUBFUN int XMLCALL
xmlShellCat (xmlShellCtxtPtr ctxt,
char *arg,
xmlNodePtr node,
xmlNodePtr node2);
XMLPUBFUN int XMLCALL
xmlShellWrite (xmlShellCtxtPtr ctxt,
char *filename,
xmlNodePtr node,
xmlNodePtr node2);
XMLPUBFUN int XMLCALL
xmlShellSave (xmlShellCtxtPtr ctxt,
char *filename,
xmlNodePtr node,
xmlNodePtr node2);
#endif /* LIBXML_OUTPUT_ENABLED */
#ifdef LIBXML_VALID_ENABLED
XMLPUBFUN int XMLCALL
xmlShellValidate (xmlShellCtxtPtr ctxt,
char *dtd,
xmlNodePtr node,
xmlNodePtr node2);
#endif /* LIBXML_VALID_ENABLED */
XMLPUBFUN int XMLCALL
xmlShellDu (xmlShellCtxtPtr ctxt,
char *arg,
xmlNodePtr tree,
xmlNodePtr node2);
XMLPUBFUN int XMLCALL
xmlShellPwd (xmlShellCtxtPtr ctxt,
char *buffer,
xmlNodePtr node,
xmlNodePtr node2);
/*
* The Shell interface.
*/
XMLPUBFUN void XMLCALL
xmlShell (xmlDocPtr doc,
char *filename,
xmlShellReadlineFunc input,
FILE *output);
#endif /* LIBXML_XPATH_ENABLED */
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_DEBUG_ENABLED */
#endif /* __DEBUG_XML__ */

@ -0,0 +1,86 @@
/*
* Summary: string dictionary
* Description: dictionary of reusable strings, just used to avoid allocation
* and freeing operations.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_DICT_H__
#define __XML_DICT_H__
#ifdef __cplusplus
#define __XML_EXTERNC extern "C"
#else
#define __XML_EXTERNC
#endif
/*
* The dictionary.
*/
__XML_EXTERNC typedef struct _xmlDict xmlDict;
__XML_EXTERNC typedef xmlDict *xmlDictPtr;
#include <limits.h>
#include <libxml/xmlversion.h>
#include <libxml/tree.h>
#ifdef __cplusplus
extern "C" {
#endif
/*
* Initializer
*/
XMLPUBFUN int XMLCALL xmlInitializeDict(void);
/*
* Constructor and destructor.
*/
XMLPUBFUN xmlDictPtr XMLCALL
xmlDictCreate (void);
XMLPUBFUN size_t XMLCALL
xmlDictSetLimit (xmlDictPtr dict,
size_t limit);
XMLPUBFUN size_t XMLCALL
xmlDictGetUsage (xmlDictPtr dict);
XMLPUBFUN xmlDictPtr XMLCALL
xmlDictCreateSub(xmlDictPtr sub);
XMLPUBFUN int XMLCALL
xmlDictReference(xmlDictPtr dict);
XMLPUBFUN void XMLCALL
xmlDictFree (xmlDictPtr dict);
/*
* Lookup of entry in the dictionary.
*/
XMLPUBFUN const xmlChar * XMLCALL
xmlDictLookup (xmlDictPtr dict,
const xmlChar *name,
int len);
XMLPUBFUN const xmlChar * XMLCALL
xmlDictExists (xmlDictPtr dict,
const xmlChar *name,
int len);
XMLPUBFUN const xmlChar * XMLCALL
xmlDictQLookup (xmlDictPtr dict,
const xmlChar *prefix,
const xmlChar *name);
XMLPUBFUN int XMLCALL
xmlDictOwns (xmlDictPtr dict,
const xmlChar *str);
XMLPUBFUN int XMLCALL
xmlDictSize (xmlDictPtr dict);
/*
* Cleanup function
*/
XMLPUBFUN void XMLCALL
xmlDictCleanup (void);
#ifdef __cplusplus
}
#endif
#endif /* ! __XML_DICT_H__ */

@ -0,0 +1,240 @@
/*
* Summary: interface for the encoding conversion functions
* Description: interface for the encoding conversion functions needed for
* XML basic encoding and iconv() support.
*
* Related specs are
* rfc2044 (UTF-8 and UTF-16) F. Yergeau Alis Technologies
* [ISO-10646] UTF-8 and UTF-16 in Annexes
* [ISO-8859-1] ISO Latin-1 characters codes.
* [UNICODE] The Unicode Consortium, "The Unicode Standard --
* Worldwide Character Encoding -- Version 1.0", Addison-
* Wesley, Volume 1, 1991, Volume 2, 1992. UTF-8 is
* described in Unicode Technical Report #4.
* [US-ASCII] Coded Character Set--7-bit American Standard Code for
* Information Interchange, ANSI X3.4-1986.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_CHAR_ENCODING_H__
#define __XML_CHAR_ENCODING_H__
#include <libxml/xmlversion.h>
#ifdef LIBXML_ICONV_ENABLED
#include <iconv.h>
#endif
#ifdef LIBXML_ICU_ENABLED
#include <unicode/ucnv.h>
#endif
#ifdef __cplusplus
extern "C" {
#endif
/*
* xmlCharEncoding:
*
* Predefined values for some standard encodings.
* Libxml does not do beforehand translation on UTF8 and ISOLatinX.
* It also supports ASCII, ISO-8859-1, and UTF16 (LE and BE) by default.
*
* Anything else would have to be translated to UTF8 before being
* given to the parser itself. The BOM for UTF16 and the encoding
* declaration are looked at and a converter is looked for at that
* point. If not found the parser stops here as asked by the XML REC. A
* converter can be registered by the user using xmlRegisterCharEncodingHandler
* but the current form doesn't allow stateful transcoding (a serious
* problem agreed !). If iconv has been found it will be used
* automatically and allow stateful transcoding, the simplest is then
* to be sure to enable iconv and to provide iconv libs for the encoding
* support needed.
*
* Note that the generic "UTF-16" is not a predefined value. Instead, only
* the specific UTF-16LE and UTF-16BE are present.
*/
typedef enum {
XML_CHAR_ENCODING_ERROR= -1, /* No char encoding detected */
XML_CHAR_ENCODING_NONE= 0, /* No char encoding detected */
XML_CHAR_ENCODING_UTF8= 1, /* UTF-8 */
XML_CHAR_ENCODING_UTF16LE= 2, /* UTF-16 little endian */
XML_CHAR_ENCODING_UTF16BE= 3, /* UTF-16 big endian */
XML_CHAR_ENCODING_UCS4LE= 4, /* UCS-4 little endian */
XML_CHAR_ENCODING_UCS4BE= 5, /* UCS-4 big endian */
XML_CHAR_ENCODING_EBCDIC= 6, /* EBCDIC uh! */
XML_CHAR_ENCODING_UCS4_2143=7, /* UCS-4 unusual ordering */
XML_CHAR_ENCODING_UCS4_3412=8, /* UCS-4 unusual ordering */
XML_CHAR_ENCODING_UCS2= 9, /* UCS-2 */
XML_CHAR_ENCODING_8859_1= 10,/* ISO-8859-1 ISO Latin 1 */
XML_CHAR_ENCODING_8859_2= 11,/* ISO-8859-2 ISO Latin 2 */
XML_CHAR_ENCODING_8859_3= 12,/* ISO-8859-3 */
XML_CHAR_ENCODING_8859_4= 13,/* ISO-8859-4 */
XML_CHAR_ENCODING_8859_5= 14,/* ISO-8859-5 */
XML_CHAR_ENCODING_8859_6= 15,/* ISO-8859-6 */
XML_CHAR_ENCODING_8859_7= 16,/* ISO-8859-7 */
XML_CHAR_ENCODING_8859_8= 17,/* ISO-8859-8 */
XML_CHAR_ENCODING_8859_9= 18,/* ISO-8859-9 */
XML_CHAR_ENCODING_2022_JP= 19,/* ISO-2022-JP */
XML_CHAR_ENCODING_SHIFT_JIS=20,/* Shift_JIS */
XML_CHAR_ENCODING_EUC_JP= 21,/* EUC-JP */
XML_CHAR_ENCODING_ASCII= 22 /* pure ASCII */
} xmlCharEncoding;
/**
* xmlCharEncodingInputFunc:
* @out: a pointer to an array of bytes to store the UTF-8 result
* @outlen: the length of @out
* @in: a pointer to an array of chars in the original encoding
* @inlen: the length of @in
*
* Take a block of chars in the original encoding and try to convert
* it to an UTF-8 block of chars out.
*
* Returns the number of bytes written, -1 if lack of space, or -2
* if the transcoding failed.
* The value of @inlen after return is the number of octets consumed
* if the return value is positive, else unpredictiable.
* The value of @outlen after return is the number of octets consumed.
*/
typedef int (* xmlCharEncodingInputFunc)(unsigned char *out, int *outlen,
const unsigned char *in, int *inlen);
/**
* xmlCharEncodingOutputFunc:
* @out: a pointer to an array of bytes to store the result
* @outlen: the length of @out
* @in: a pointer to an array of UTF-8 chars
* @inlen: the length of @in
*
* Take a block of UTF-8 chars in and try to convert it to another
* encoding.
* Note: a first call designed to produce heading info is called with
* in = NULL. If stateful this should also initialize the encoder state.
*
* Returns the number of bytes written, -1 if lack of space, or -2
* if the transcoding failed.
* The value of @inlen after return is the number of octets consumed
* if the return value is positive, else unpredictiable.
* The value of @outlen after return is the number of octets produced.
*/
typedef int (* xmlCharEncodingOutputFunc)(unsigned char *out, int *outlen,
const unsigned char *in, int *inlen);
/*
* Block defining the handlers for non UTF-8 encodings.
* If iconv is supported, there are two extra fields.
*/
#ifdef LIBXML_ICU_ENABLED
struct _uconv_t {
UConverter *uconv; /* for conversion between an encoding and UTF-16 */
UConverter *utf8; /* for conversion between UTF-8 and UTF-16 */
};
typedef struct _uconv_t uconv_t;
#endif
typedef struct _xmlCharEncodingHandler xmlCharEncodingHandler;
typedef xmlCharEncodingHandler *xmlCharEncodingHandlerPtr;
struct _xmlCharEncodingHandler {
char *name;
xmlCharEncodingInputFunc input;
xmlCharEncodingOutputFunc output;
#ifdef LIBXML_ICONV_ENABLED
iconv_t iconv_in;
iconv_t iconv_out;
#endif /* LIBXML_ICONV_ENABLED */
#ifdef LIBXML_ICU_ENABLED
uconv_t *uconv_in;
uconv_t *uconv_out;
#endif /* LIBXML_ICU_ENABLED */
};
#ifdef __cplusplus
}
#endif
#include <libxml/tree.h>
#ifdef __cplusplus
extern "C" {
#endif
/*
* Interfaces for encoding handlers.
*/
XMLPUBFUN void XMLCALL
xmlInitCharEncodingHandlers (void);
XMLPUBFUN void XMLCALL
xmlCleanupCharEncodingHandlers (void);
XMLPUBFUN void XMLCALL
xmlRegisterCharEncodingHandler (xmlCharEncodingHandlerPtr handler);
XMLPUBFUN xmlCharEncodingHandlerPtr XMLCALL
xmlGetCharEncodingHandler (xmlCharEncoding enc);
XMLPUBFUN xmlCharEncodingHandlerPtr XMLCALL
xmlFindCharEncodingHandler (const char *name);
XMLPUBFUN xmlCharEncodingHandlerPtr XMLCALL
xmlNewCharEncodingHandler (const char *name,
xmlCharEncodingInputFunc input,
xmlCharEncodingOutputFunc output);
/*
* Interfaces for encoding names and aliases.
*/
XMLPUBFUN int XMLCALL
xmlAddEncodingAlias (const char *name,
const char *alias);
XMLPUBFUN int XMLCALL
xmlDelEncodingAlias (const char *alias);
XMLPUBFUN const char * XMLCALL
xmlGetEncodingAlias (const char *alias);
XMLPUBFUN void XMLCALL
xmlCleanupEncodingAliases (void);
XMLPUBFUN xmlCharEncoding XMLCALL
xmlParseCharEncoding (const char *name);
XMLPUBFUN const char * XMLCALL
xmlGetCharEncodingName (xmlCharEncoding enc);
/*
* Interfaces directly used by the parsers.
*/
XMLPUBFUN xmlCharEncoding XMLCALL
xmlDetectCharEncoding (const unsigned char *in,
int len);
XMLPUBFUN int XMLCALL
xmlCharEncOutFunc (xmlCharEncodingHandler *handler,
xmlBufferPtr out,
xmlBufferPtr in);
XMLPUBFUN int XMLCALL
xmlCharEncInFunc (xmlCharEncodingHandler *handler,
xmlBufferPtr out,
xmlBufferPtr in);
XMLPUBFUN int XMLCALL
xmlCharEncFirstLine (xmlCharEncodingHandler *handler,
xmlBufferPtr out,
xmlBufferPtr in);
XMLPUBFUN int XMLCALL
xmlCharEncCloseFunc (xmlCharEncodingHandler *handler);
/*
* Export a few useful functions
*/
#ifdef LIBXML_OUTPUT_ENABLED
XMLPUBFUN int XMLCALL
UTF8Toisolat1 (unsigned char *out,
int *outlen,
const unsigned char *in,
int *inlen);
#endif /* LIBXML_OUTPUT_ENABLED */
XMLPUBFUN int XMLCALL
isolat1ToUTF8 (unsigned char *out,
int *outlen,
const unsigned char *in,
int *inlen);
#ifdef __cplusplus
}
#endif
#endif /* __XML_CHAR_ENCODING_H__ */

@ -0,0 +1,151 @@
/*
* Summary: interface for the XML entities handling
* Description: this module provides some of the entity API needed
* for the parser and applications.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_ENTITIES_H__
#define __XML_ENTITIES_H__
#include <libxml/xmlversion.h>
#include <libxml/tree.h>
#ifdef __cplusplus
extern "C" {
#endif
/*
* The different valid entity types.
*/
typedef enum {
XML_INTERNAL_GENERAL_ENTITY = 1,
XML_EXTERNAL_GENERAL_PARSED_ENTITY = 2,
XML_EXTERNAL_GENERAL_UNPARSED_ENTITY = 3,
XML_INTERNAL_PARAMETER_ENTITY = 4,
XML_EXTERNAL_PARAMETER_ENTITY = 5,
XML_INTERNAL_PREDEFINED_ENTITY = 6
} xmlEntityType;
/*
* An unit of storage for an entity, contains the string, the value
* and the linkind data needed for the linking in the hash table.
*/
struct _xmlEntity {
void *_private; /* application data */
xmlElementType type; /* XML_ENTITY_DECL, must be second ! */
const xmlChar *name; /* Entity name */
struct _xmlNode *children; /* First child link */
struct _xmlNode *last; /* Last child link */
struct _xmlDtd *parent; /* -> DTD */
struct _xmlNode *next; /* next sibling link */
struct _xmlNode *prev; /* previous sibling link */
struct _xmlDoc *doc; /* the containing document */
xmlChar *orig; /* content without ref substitution */
xmlChar *content; /* content or ndata if unparsed */
int length; /* the content length */
xmlEntityType etype; /* The entity type */
const xmlChar *ExternalID; /* External identifier for PUBLIC */
const xmlChar *SystemID; /* URI for a SYSTEM or PUBLIC Entity */
struct _xmlEntity *nexte; /* unused */
const xmlChar *URI; /* the full URI as computed */
int owner; /* does the entity own the childrens */
int checked; /* was the entity content checked */
/* this is also used to count entities
* references done from that entity
* and if it contains '<' */
};
/*
* All entities are stored in an hash table.
* There is 2 separate hash tables for global and parameter entities.
*/
typedef struct _xmlHashTable xmlEntitiesTable;
typedef xmlEntitiesTable *xmlEntitiesTablePtr;
/*
* External functions:
*/
#ifdef LIBXML_LEGACY_ENABLED
XMLPUBFUN void XMLCALL
xmlInitializePredefinedEntities (void);
#endif /* LIBXML_LEGACY_ENABLED */
XMLPUBFUN xmlEntityPtr XMLCALL
xmlNewEntity (xmlDocPtr doc,
const xmlChar *name,
int type,
const xmlChar *ExternalID,
const xmlChar *SystemID,
const xmlChar *content);
XMLPUBFUN xmlEntityPtr XMLCALL
xmlAddDocEntity (xmlDocPtr doc,
const xmlChar *name,
int type,
const xmlChar *ExternalID,
const xmlChar *SystemID,
const xmlChar *content);
XMLPUBFUN xmlEntityPtr XMLCALL
xmlAddDtdEntity (xmlDocPtr doc,
const xmlChar *name,
int type,
const xmlChar *ExternalID,
const xmlChar *SystemID,
const xmlChar *content);
XMLPUBFUN xmlEntityPtr XMLCALL
xmlGetPredefinedEntity (const xmlChar *name);
XMLPUBFUN xmlEntityPtr XMLCALL
xmlGetDocEntity (const xmlDoc *doc,
const xmlChar *name);
XMLPUBFUN xmlEntityPtr XMLCALL
xmlGetDtdEntity (xmlDocPtr doc,
const xmlChar *name);
XMLPUBFUN xmlEntityPtr XMLCALL
xmlGetParameterEntity (xmlDocPtr doc,
const xmlChar *name);
#ifdef LIBXML_LEGACY_ENABLED
XMLPUBFUN const xmlChar * XMLCALL
xmlEncodeEntities (xmlDocPtr doc,
const xmlChar *input);
#endif /* LIBXML_LEGACY_ENABLED */
XMLPUBFUN xmlChar * XMLCALL
xmlEncodeEntitiesReentrant(xmlDocPtr doc,
const xmlChar *input);
XMLPUBFUN xmlChar * XMLCALL
xmlEncodeSpecialChars (const xmlDoc *doc,
const xmlChar *input);
XMLPUBFUN xmlEntitiesTablePtr XMLCALL
xmlCreateEntitiesTable (void);
#ifdef LIBXML_TREE_ENABLED
XMLPUBFUN xmlEntitiesTablePtr XMLCALL
xmlCopyEntitiesTable (xmlEntitiesTablePtr table);
#endif /* LIBXML_TREE_ENABLED */
XMLPUBFUN void XMLCALL
xmlFreeEntitiesTable (xmlEntitiesTablePtr table);
#ifdef LIBXML_OUTPUT_ENABLED
XMLPUBFUN void XMLCALL
xmlDumpEntitiesTable (xmlBufferPtr buf,
xmlEntitiesTablePtr table);
XMLPUBFUN void XMLCALL
xmlDumpEntityDecl (xmlBufferPtr buf,
xmlEntityPtr ent);
#endif /* LIBXML_OUTPUT_ENABLED */
#ifdef LIBXML_LEGACY_ENABLED
XMLPUBFUN void XMLCALL
xmlCleanupPredefinedEntities(void);
#endif /* LIBXML_LEGACY_ENABLED */
#ifdef __cplusplus
}
#endif
# endif /* __XML_ENTITIES_H__ */

@ -0,0 +1,509 @@
/*
* Summary: interface for all global variables of the library
* Description: all the global variables and thread handling for
* those variables is handled by this module.
*
* The bottom of this file is automatically generated by build_glob.py
* based on the description file global.data
*
* Copy: See Copyright for the status of this software.
*
* Author: Gary Pennington <Gary.Pennington@uk.sun.com>, Daniel Veillard
*/
#ifndef __XML_GLOBALS_H
#define __XML_GLOBALS_H
#include <libxml/xmlversion.h>
#include <libxml/parser.h>
#include <libxml/xmlerror.h>
#include <libxml/SAX.h>
#include <libxml/SAX2.h>
#include <libxml/xmlmemory.h>
#ifdef __cplusplus
extern "C" {
#endif
XMLPUBFUN void XMLCALL xmlInitGlobals(void);
XMLPUBFUN void XMLCALL xmlCleanupGlobals(void);
/**
* xmlParserInputBufferCreateFilenameFunc:
* @URI: the URI to read from
* @enc: the requested source encoding
*
* Signature for the function doing the lookup for a suitable input method
* corresponding to an URI.
*
* Returns the new xmlParserInputBufferPtr in case of success or NULL if no
* method was found.
*/
typedef xmlParserInputBufferPtr (*xmlParserInputBufferCreateFilenameFunc) (const char *URI,
xmlCharEncoding enc);
/**
* xmlOutputBufferCreateFilenameFunc:
* @URI: the URI to write to
* @enc: the requested target encoding
*
* Signature for the function doing the lookup for a suitable output method
* corresponding to an URI.
*
* Returns the new xmlOutputBufferPtr in case of success or NULL if no
* method was found.
*/
typedef xmlOutputBufferPtr (*xmlOutputBufferCreateFilenameFunc) (const char *URI,
xmlCharEncodingHandlerPtr encoder,
int compression);
XMLPUBFUN xmlParserInputBufferCreateFilenameFunc
XMLCALL xmlParserInputBufferCreateFilenameDefault (xmlParserInputBufferCreateFilenameFunc func);
XMLPUBFUN xmlOutputBufferCreateFilenameFunc
XMLCALL xmlOutputBufferCreateFilenameDefault (xmlOutputBufferCreateFilenameFunc func);
/*
* Externally global symbols which need to be protected for backwards
* compatibility support.
*/
#undef docbDefaultSAXHandler
#undef htmlDefaultSAXHandler
#undef oldXMLWDcompatibility
#undef xmlBufferAllocScheme
#undef xmlDefaultBufferSize
#undef xmlDefaultSAXHandler
#undef xmlDefaultSAXLocator
#undef xmlDoValidityCheckingDefaultValue
#undef xmlFree
#undef xmlGenericError
#undef xmlStructuredError
#undef xmlGenericErrorContext
#undef xmlStructuredErrorContext
#undef xmlGetWarningsDefaultValue
#undef xmlIndentTreeOutput
#undef xmlTreeIndentString
#undef xmlKeepBlanksDefaultValue
#undef xmlLineNumbersDefaultValue
#undef xmlLoadExtDtdDefaultValue
#undef xmlMalloc
#undef xmlMallocAtomic
#undef xmlMemStrdup
#undef xmlParserDebugEntities
#undef xmlParserVersion
#undef xmlPedanticParserDefaultValue
#undef xmlRealloc
#undef xmlSaveNoEmptyTags
#undef xmlSubstituteEntitiesDefaultValue
#undef xmlRegisterNodeDefaultValue
#undef xmlDeregisterNodeDefaultValue
#undef xmlLastError
#undef xmlParserInputBufferCreateFilenameValue
#undef xmlOutputBufferCreateFilenameValue
/**
* xmlRegisterNodeFunc:
* @node: the current node
*
* Signature for the registration callback of a created node
*/
typedef void (*xmlRegisterNodeFunc) (xmlNodePtr node);
/**
* xmlDeregisterNodeFunc:
* @node: the current node
*
* Signature for the deregistration callback of a discarded node
*/
typedef void (*xmlDeregisterNodeFunc) (xmlNodePtr node);
typedef struct _xmlGlobalState xmlGlobalState;
typedef xmlGlobalState *xmlGlobalStatePtr;
struct _xmlGlobalState
{
const char *xmlParserVersion;
xmlSAXLocator xmlDefaultSAXLocator;
xmlSAXHandlerV1 xmlDefaultSAXHandler;
xmlSAXHandlerV1 docbDefaultSAXHandler;
xmlSAXHandlerV1 htmlDefaultSAXHandler;
xmlFreeFunc xmlFree;
xmlMallocFunc xmlMalloc;
xmlStrdupFunc xmlMemStrdup;
xmlReallocFunc xmlRealloc;
xmlGenericErrorFunc xmlGenericError;
xmlStructuredErrorFunc xmlStructuredError;
void *xmlGenericErrorContext;
int oldXMLWDcompatibility;
xmlBufferAllocationScheme xmlBufferAllocScheme;
int xmlDefaultBufferSize;
int xmlSubstituteEntitiesDefaultValue;
int xmlDoValidityCheckingDefaultValue;
int xmlGetWarningsDefaultValue;
int xmlKeepBlanksDefaultValue;
int xmlLineNumbersDefaultValue;
int xmlLoadExtDtdDefaultValue;
int xmlParserDebugEntities;
int xmlPedanticParserDefaultValue;
int xmlSaveNoEmptyTags;
int xmlIndentTreeOutput;
const char *xmlTreeIndentString;
xmlRegisterNodeFunc xmlRegisterNodeDefaultValue;
xmlDeregisterNodeFunc xmlDeregisterNodeDefaultValue;
xmlMallocFunc xmlMallocAtomic;
xmlError xmlLastError;
xmlParserInputBufferCreateFilenameFunc xmlParserInputBufferCreateFilenameValue;
xmlOutputBufferCreateFilenameFunc xmlOutputBufferCreateFilenameValue;
void *xmlStructuredErrorContext;
};
#ifdef __cplusplus
}
#endif
#include <libxml/threads.h>
#ifdef __cplusplus
extern "C" {
#endif
XMLPUBFUN void XMLCALL xmlInitializeGlobalState(xmlGlobalStatePtr gs);
XMLPUBFUN void XMLCALL xmlThrDefSetGenericErrorFunc(void *ctx, xmlGenericErrorFunc handler);
XMLPUBFUN void XMLCALL xmlThrDefSetStructuredErrorFunc(void *ctx, xmlStructuredErrorFunc handler);
XMLPUBFUN xmlRegisterNodeFunc XMLCALL xmlRegisterNodeDefault(xmlRegisterNodeFunc func);
XMLPUBFUN xmlRegisterNodeFunc XMLCALL xmlThrDefRegisterNodeDefault(xmlRegisterNodeFunc func);
XMLPUBFUN xmlDeregisterNodeFunc XMLCALL xmlDeregisterNodeDefault(xmlDeregisterNodeFunc func);
XMLPUBFUN xmlDeregisterNodeFunc XMLCALL xmlThrDefDeregisterNodeDefault(xmlDeregisterNodeFunc func);
XMLPUBFUN xmlOutputBufferCreateFilenameFunc XMLCALL
xmlThrDefOutputBufferCreateFilenameDefault(xmlOutputBufferCreateFilenameFunc func);
XMLPUBFUN xmlParserInputBufferCreateFilenameFunc XMLCALL
xmlThrDefParserInputBufferCreateFilenameDefault(
xmlParserInputBufferCreateFilenameFunc func);
/** DOC_DISABLE */
/*
* In general the memory allocation entry points are not kept
* thread specific but this can be overridden by LIBXML_THREAD_ALLOC_ENABLED
* - xmlMalloc
* - xmlMallocAtomic
* - xmlRealloc
* - xmlMemStrdup
* - xmlFree
*/
#ifdef LIBXML_THREAD_ALLOC_ENABLED
#ifdef LIBXML_THREAD_ENABLED
XMLPUBFUN xmlMallocFunc * XMLCALL __xmlMalloc(void);
#define xmlMalloc \
(*(__xmlMalloc()))
#else
XMLPUBVAR xmlMallocFunc xmlMalloc;
#endif
#ifdef LIBXML_THREAD_ENABLED
XMLPUBFUN xmlMallocFunc * XMLCALL __xmlMallocAtomic(void);
#define xmlMallocAtomic \
(*(__xmlMallocAtomic()))
#else
XMLPUBVAR xmlMallocFunc xmlMallocAtomic;
#endif
#ifdef LIBXML_THREAD_ENABLED
XMLPUBFUN xmlReallocFunc * XMLCALL __xmlRealloc(void);
#define xmlRealloc \
(*(__xmlRealloc()))
#else
XMLPUBVAR xmlReallocFunc xmlRealloc;
#endif
#ifdef LIBXML_THREAD_ENABLED
XMLPUBFUN xmlFreeFunc * XMLCALL __xmlFree(void);
#define xmlFree \
(*(__xmlFree()))
#else
XMLPUBVAR xmlFreeFunc xmlFree;
#endif
#ifdef LIBXML_THREAD_ENABLED
XMLPUBFUN xmlStrdupFunc * XMLCALL __xmlMemStrdup(void);
#define xmlMemStrdup \
(*(__xmlMemStrdup()))
#else
XMLPUBVAR xmlStrdupFunc xmlMemStrdup;
#endif
#else /* !LIBXML_THREAD_ALLOC_ENABLED */
XMLPUBVAR xmlMallocFunc xmlMalloc;
XMLPUBVAR xmlMallocFunc xmlMallocAtomic;
XMLPUBVAR xmlReallocFunc xmlRealloc;
XMLPUBVAR xmlFreeFunc xmlFree;
XMLPUBVAR xmlStrdupFunc xmlMemStrdup;
#endif /* LIBXML_THREAD_ALLOC_ENABLED */
#ifdef LIBXML_DOCB_ENABLED
XMLPUBFUN xmlSAXHandlerV1 * XMLCALL __docbDefaultSAXHandler(void);
#ifdef LIBXML_THREAD_ENABLED
#define docbDefaultSAXHandler \
(*(__docbDefaultSAXHandler()))
#else
XMLPUBVAR xmlSAXHandlerV1 docbDefaultSAXHandler;
#endif
#endif
#ifdef LIBXML_HTML_ENABLED
XMLPUBFUN xmlSAXHandlerV1 * XMLCALL __htmlDefaultSAXHandler(void);
#ifdef LIBXML_THREAD_ENABLED
#define htmlDefaultSAXHandler \
(*(__htmlDefaultSAXHandler()))
#else
XMLPUBVAR xmlSAXHandlerV1 htmlDefaultSAXHandler;
#endif
#endif
XMLPUBFUN xmlError * XMLCALL __xmlLastError(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlLastError \
(*(__xmlLastError()))
#else
XMLPUBVAR xmlError xmlLastError;
#endif
/*
* Everything starting from the line below is
* Automatically generated by build_glob.py.
* Do not modify the previous line.
*/
XMLPUBFUN int * XMLCALL __oldXMLWDcompatibility(void);
#ifdef LIBXML_THREAD_ENABLED
#define oldXMLWDcompatibility \
(*(__oldXMLWDcompatibility()))
#else
XMLPUBVAR int oldXMLWDcompatibility;
#endif
XMLPUBFUN xmlBufferAllocationScheme * XMLCALL __xmlBufferAllocScheme(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlBufferAllocScheme \
(*(__xmlBufferAllocScheme()))
#else
XMLPUBVAR xmlBufferAllocationScheme xmlBufferAllocScheme;
#endif
XMLPUBFUN xmlBufferAllocationScheme XMLCALL
xmlThrDefBufferAllocScheme(xmlBufferAllocationScheme v);
XMLPUBFUN int * XMLCALL __xmlDefaultBufferSize(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlDefaultBufferSize \
(*(__xmlDefaultBufferSize()))
#else
XMLPUBVAR int xmlDefaultBufferSize;
#endif
XMLPUBFUN int XMLCALL xmlThrDefDefaultBufferSize(int v);
XMLPUBFUN xmlSAXHandlerV1 * XMLCALL __xmlDefaultSAXHandler(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlDefaultSAXHandler \
(*(__xmlDefaultSAXHandler()))
#else
XMLPUBVAR xmlSAXHandlerV1 xmlDefaultSAXHandler;
#endif
XMLPUBFUN xmlSAXLocator * XMLCALL __xmlDefaultSAXLocator(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlDefaultSAXLocator \
(*(__xmlDefaultSAXLocator()))
#else
XMLPUBVAR xmlSAXLocator xmlDefaultSAXLocator;
#endif
XMLPUBFUN int * XMLCALL __xmlDoValidityCheckingDefaultValue(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlDoValidityCheckingDefaultValue \
(*(__xmlDoValidityCheckingDefaultValue()))
#else
XMLPUBVAR int xmlDoValidityCheckingDefaultValue;
#endif
XMLPUBFUN int XMLCALL xmlThrDefDoValidityCheckingDefaultValue(int v);
XMLPUBFUN xmlGenericErrorFunc * XMLCALL __xmlGenericError(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlGenericError \
(*(__xmlGenericError()))
#else
XMLPUBVAR xmlGenericErrorFunc xmlGenericError;
#endif
XMLPUBFUN xmlStructuredErrorFunc * XMLCALL __xmlStructuredError(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlStructuredError \
(*(__xmlStructuredError()))
#else
XMLPUBVAR xmlStructuredErrorFunc xmlStructuredError;
#endif
XMLPUBFUN void * * XMLCALL __xmlGenericErrorContext(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlGenericErrorContext \
(*(__xmlGenericErrorContext()))
#else
XMLPUBVAR void * xmlGenericErrorContext;
#endif
XMLPUBFUN void * * XMLCALL __xmlStructuredErrorContext(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlStructuredErrorContext \
(*(__xmlStructuredErrorContext()))
#else
XMLPUBVAR void * xmlStructuredErrorContext;
#endif
XMLPUBFUN int * XMLCALL __xmlGetWarningsDefaultValue(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlGetWarningsDefaultValue \
(*(__xmlGetWarningsDefaultValue()))
#else
XMLPUBVAR int xmlGetWarningsDefaultValue;
#endif
XMLPUBFUN int XMLCALL xmlThrDefGetWarningsDefaultValue(int v);
XMLPUBFUN int * XMLCALL __xmlIndentTreeOutput(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlIndentTreeOutput \
(*(__xmlIndentTreeOutput()))
#else
XMLPUBVAR int xmlIndentTreeOutput;
#endif
XMLPUBFUN int XMLCALL xmlThrDefIndentTreeOutput(int v);
XMLPUBFUN const char * * XMLCALL __xmlTreeIndentString(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlTreeIndentString \
(*(__xmlTreeIndentString()))
#else
XMLPUBVAR const char * xmlTreeIndentString;
#endif
XMLPUBFUN const char * XMLCALL xmlThrDefTreeIndentString(const char * v);
XMLPUBFUN int * XMLCALL __xmlKeepBlanksDefaultValue(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlKeepBlanksDefaultValue \
(*(__xmlKeepBlanksDefaultValue()))
#else
XMLPUBVAR int xmlKeepBlanksDefaultValue;
#endif
XMLPUBFUN int XMLCALL xmlThrDefKeepBlanksDefaultValue(int v);
XMLPUBFUN int * XMLCALL __xmlLineNumbersDefaultValue(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlLineNumbersDefaultValue \
(*(__xmlLineNumbersDefaultValue()))
#else
XMLPUBVAR int xmlLineNumbersDefaultValue;
#endif
XMLPUBFUN int XMLCALL xmlThrDefLineNumbersDefaultValue(int v);
XMLPUBFUN int * XMLCALL __xmlLoadExtDtdDefaultValue(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlLoadExtDtdDefaultValue \
(*(__xmlLoadExtDtdDefaultValue()))
#else
XMLPUBVAR int xmlLoadExtDtdDefaultValue;
#endif
XMLPUBFUN int XMLCALL xmlThrDefLoadExtDtdDefaultValue(int v);
XMLPUBFUN int * XMLCALL __xmlParserDebugEntities(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlParserDebugEntities \
(*(__xmlParserDebugEntities()))
#else
XMLPUBVAR int xmlParserDebugEntities;
#endif
XMLPUBFUN int XMLCALL xmlThrDefParserDebugEntities(int v);
XMLPUBFUN const char * * XMLCALL __xmlParserVersion(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlParserVersion \
(*(__xmlParserVersion()))
#else
XMLPUBVAR const char * xmlParserVersion;
#endif
XMLPUBFUN int * XMLCALL __xmlPedanticParserDefaultValue(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlPedanticParserDefaultValue \
(*(__xmlPedanticParserDefaultValue()))
#else
XMLPUBVAR int xmlPedanticParserDefaultValue;
#endif
XMLPUBFUN int XMLCALL xmlThrDefPedanticParserDefaultValue(int v);
XMLPUBFUN int * XMLCALL __xmlSaveNoEmptyTags(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlSaveNoEmptyTags \
(*(__xmlSaveNoEmptyTags()))
#else
XMLPUBVAR int xmlSaveNoEmptyTags;
#endif
XMLPUBFUN int XMLCALL xmlThrDefSaveNoEmptyTags(int v);
XMLPUBFUN int * XMLCALL __xmlSubstituteEntitiesDefaultValue(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlSubstituteEntitiesDefaultValue \
(*(__xmlSubstituteEntitiesDefaultValue()))
#else
XMLPUBVAR int xmlSubstituteEntitiesDefaultValue;
#endif
XMLPUBFUN int XMLCALL xmlThrDefSubstituteEntitiesDefaultValue(int v);
XMLPUBFUN xmlRegisterNodeFunc * XMLCALL __xmlRegisterNodeDefaultValue(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlRegisterNodeDefaultValue \
(*(__xmlRegisterNodeDefaultValue()))
#else
XMLPUBVAR xmlRegisterNodeFunc xmlRegisterNodeDefaultValue;
#endif
XMLPUBFUN xmlDeregisterNodeFunc * XMLCALL __xmlDeregisterNodeDefaultValue(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlDeregisterNodeDefaultValue \
(*(__xmlDeregisterNodeDefaultValue()))
#else
XMLPUBVAR xmlDeregisterNodeFunc xmlDeregisterNodeDefaultValue;
#endif
XMLPUBFUN xmlParserInputBufferCreateFilenameFunc * XMLCALL \
__xmlParserInputBufferCreateFilenameValue(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlParserInputBufferCreateFilenameValue \
(*(__xmlParserInputBufferCreateFilenameValue()))
#else
XMLPUBVAR xmlParserInputBufferCreateFilenameFunc xmlParserInputBufferCreateFilenameValue;
#endif
XMLPUBFUN xmlOutputBufferCreateFilenameFunc * XMLCALL __xmlOutputBufferCreateFilenameValue(void);
#ifdef LIBXML_THREAD_ENABLED
#define xmlOutputBufferCreateFilenameValue \
(*(__xmlOutputBufferCreateFilenameValue()))
#else
XMLPUBVAR xmlOutputBufferCreateFilenameFunc xmlOutputBufferCreateFilenameValue;
#endif
#ifdef __cplusplus
}
#endif
#endif /* __XML_GLOBALS_H */

@ -0,0 +1,233 @@
/*
* Summary: Chained hash tables
* Description: This module implements the hash table support used in
* various places in the library.
*
* Copy: See Copyright for the status of this software.
*
* Author: Bjorn Reese <bjorn.reese@systematic.dk>
*/
#ifndef __XML_HASH_H__
#define __XML_HASH_H__
#ifdef __cplusplus
extern "C" {
#endif
/*
* The hash table.
*/
typedef struct _xmlHashTable xmlHashTable;
typedef xmlHashTable *xmlHashTablePtr;
#ifdef __cplusplus
}
#endif
#include <libxml/xmlversion.h>
#include <libxml/parser.h>
#include <libxml/dict.h>
#ifdef __cplusplus
extern "C" {
#endif
/*
* Recent version of gcc produce a warning when a function pointer is assigned
* to an object pointer, or vice versa. The following macro is a dirty hack
* to allow suppression of the warning. If your architecture has function
* pointers which are a different size than a void pointer, there may be some
* serious trouble within the library.
*/
/**
* XML_CAST_FPTR:
* @fptr: pointer to a function
*
* Macro to do a casting from an object pointer to a
* function pointer without encountering a warning from
* gcc
*
* #define XML_CAST_FPTR(fptr) (*(void **)(&fptr))
* This macro violated ISO C aliasing rules (gcc4 on s390 broke)
* so it is disabled now
*/
#define XML_CAST_FPTR(fptr) fptr
/*
* function types:
*/
/**
* xmlHashDeallocator:
* @payload: the data in the hash
* @name: the name associated
*
* Callback to free data from a hash.
*/
typedef void (*xmlHashDeallocator)(void *payload, xmlChar *name);
/**
* xmlHashCopier:
* @payload: the data in the hash
* @name: the name associated
*
* Callback to copy data from a hash.
*
* Returns a copy of the data or NULL in case of error.
*/
typedef void *(*xmlHashCopier)(void *payload, xmlChar *name);
/**
* xmlHashScanner:
* @payload: the data in the hash
* @data: extra scannner data
* @name: the name associated
*
* Callback when scanning data in a hash with the simple scanner.
*/
typedef void (*xmlHashScanner)(void *payload, void *data, xmlChar *name);
/**
* xmlHashScannerFull:
* @payload: the data in the hash
* @data: extra scannner data
* @name: the name associated
* @name2: the second name associated
* @name3: the third name associated
*
* Callback when scanning data in a hash with the full scanner.
*/
typedef void (*xmlHashScannerFull)(void *payload, void *data,
const xmlChar *name, const xmlChar *name2,
const xmlChar *name3);
/*
* Constructor and destructor.
*/
XMLPUBFUN xmlHashTablePtr XMLCALL
xmlHashCreate (int size);
XMLPUBFUN xmlHashTablePtr XMLCALL
xmlHashCreateDict(int size,
xmlDictPtr dict);
XMLPUBFUN void XMLCALL
xmlHashFree (xmlHashTablePtr table,
xmlHashDeallocator f);
/*
* Add a new entry to the hash table.
*/
XMLPUBFUN int XMLCALL
xmlHashAddEntry (xmlHashTablePtr table,
const xmlChar *name,
void *userdata);
XMLPUBFUN int XMLCALL
xmlHashUpdateEntry(xmlHashTablePtr table,
const xmlChar *name,
void *userdata,
xmlHashDeallocator f);
XMLPUBFUN int XMLCALL
xmlHashAddEntry2(xmlHashTablePtr table,
const xmlChar *name,
const xmlChar *name2,
void *userdata);
XMLPUBFUN int XMLCALL
xmlHashUpdateEntry2(xmlHashTablePtr table,
const xmlChar *name,
const xmlChar *name2,
void *userdata,
xmlHashDeallocator f);
XMLPUBFUN int XMLCALL
xmlHashAddEntry3(xmlHashTablePtr table,
const xmlChar *name,
const xmlChar *name2,
const xmlChar *name3,
void *userdata);
XMLPUBFUN int XMLCALL
xmlHashUpdateEntry3(xmlHashTablePtr table,
const xmlChar *name,
const xmlChar *name2,
const xmlChar *name3,
void *userdata,
xmlHashDeallocator f);
/*
* Remove an entry from the hash table.
*/
XMLPUBFUN int XMLCALL
xmlHashRemoveEntry(xmlHashTablePtr table, const xmlChar *name,
xmlHashDeallocator f);
XMLPUBFUN int XMLCALL
xmlHashRemoveEntry2(xmlHashTablePtr table, const xmlChar *name,
const xmlChar *name2, xmlHashDeallocator f);
XMLPUBFUN int XMLCALL
xmlHashRemoveEntry3(xmlHashTablePtr table, const xmlChar *name,
const xmlChar *name2, const xmlChar *name3,
xmlHashDeallocator f);
/*
* Retrieve the userdata.
*/
XMLPUBFUN void * XMLCALL
xmlHashLookup (xmlHashTablePtr table,
const xmlChar *name);
XMLPUBFUN void * XMLCALL
xmlHashLookup2 (xmlHashTablePtr table,
const xmlChar *name,
const xmlChar *name2);
XMLPUBFUN void * XMLCALL
xmlHashLookup3 (xmlHashTablePtr table,
const xmlChar *name,
const xmlChar *name2,
const xmlChar *name3);
XMLPUBFUN void * XMLCALL
xmlHashQLookup (xmlHashTablePtr table,
const xmlChar *name,
const xmlChar *prefix);
XMLPUBFUN void * XMLCALL
xmlHashQLookup2 (xmlHashTablePtr table,
const xmlChar *name,
const xmlChar *prefix,
const xmlChar *name2,
const xmlChar *prefix2);
XMLPUBFUN void * XMLCALL
xmlHashQLookup3 (xmlHashTablePtr table,
const xmlChar *name,
const xmlChar *prefix,
const xmlChar *name2,
const xmlChar *prefix2,
const xmlChar *name3,
const xmlChar *prefix3);
/*
* Helpers.
*/
XMLPUBFUN xmlHashTablePtr XMLCALL
xmlHashCopy (xmlHashTablePtr table,
xmlHashCopier f);
XMLPUBFUN int XMLCALL
xmlHashSize (xmlHashTablePtr table);
XMLPUBFUN void XMLCALL
xmlHashScan (xmlHashTablePtr table,
xmlHashScanner f,
void *data);
XMLPUBFUN void XMLCALL
xmlHashScan3 (xmlHashTablePtr table,
const xmlChar *name,
const xmlChar *name2,
const xmlChar *name3,
xmlHashScanner f,
void *data);
XMLPUBFUN void XMLCALL
xmlHashScanFull (xmlHashTablePtr table,
xmlHashScannerFull f,
void *data);
XMLPUBFUN void XMLCALL
xmlHashScanFull3(xmlHashTablePtr table,
const xmlChar *name,
const xmlChar *name2,
const xmlChar *name3,
xmlHashScannerFull f,
void *data);
#ifdef __cplusplus
}
#endif
#endif /* ! __XML_HASH_H__ */

@ -0,0 +1,137 @@
/*
* Summary: lists interfaces
* Description: this module implement the list support used in
* various place in the library.
*
* Copy: See Copyright for the status of this software.
*
* Author: Gary Pennington <Gary.Pennington@uk.sun.com>
*/
#ifndef __XML_LINK_INCLUDE__
#define __XML_LINK_INCLUDE__
#include <libxml/xmlversion.h>
#ifdef __cplusplus
extern "C" {
#endif
typedef struct _xmlLink xmlLink;
typedef xmlLink *xmlLinkPtr;
typedef struct _xmlList xmlList;
typedef xmlList *xmlListPtr;
/**
* xmlListDeallocator:
* @lk: the data to deallocate
*
* Callback function used to free data from a list.
*/
typedef void (*xmlListDeallocator) (xmlLinkPtr lk);
/**
* xmlListDataCompare:
* @data0: the first data
* @data1: the second data
*
* Callback function used to compare 2 data.
*
* Returns 0 is equality, -1 or 1 otherwise depending on the ordering.
*/
typedef int (*xmlListDataCompare) (const void *data0, const void *data1);
/**
* xmlListWalker:
* @data: the data found in the list
* @user: extra user provided data to the walker
*
* Callback function used when walking a list with xmlListWalk().
*
* Returns 0 to stop walking the list, 1 otherwise.
*/
typedef int (*xmlListWalker) (const void *data, const void *user);
/* Creation/Deletion */
XMLPUBFUN xmlListPtr XMLCALL
xmlListCreate (xmlListDeallocator deallocator,
xmlListDataCompare compare);
XMLPUBFUN void XMLCALL
xmlListDelete (xmlListPtr l);
/* Basic Operators */
XMLPUBFUN void * XMLCALL
xmlListSearch (xmlListPtr l,
void *data);
XMLPUBFUN void * XMLCALL
xmlListReverseSearch (xmlListPtr l,
void *data);
XMLPUBFUN int XMLCALL
xmlListInsert (xmlListPtr l,
void *data) ;
XMLPUBFUN int XMLCALL
xmlListAppend (xmlListPtr l,
void *data) ;
XMLPUBFUN int XMLCALL
xmlListRemoveFirst (xmlListPtr l,
void *data);
XMLPUBFUN int XMLCALL
xmlListRemoveLast (xmlListPtr l,
void *data);
XMLPUBFUN int XMLCALL
xmlListRemoveAll (xmlListPtr l,
void *data);
XMLPUBFUN void XMLCALL
xmlListClear (xmlListPtr l);
XMLPUBFUN int XMLCALL
xmlListEmpty (xmlListPtr l);
XMLPUBFUN xmlLinkPtr XMLCALL
xmlListFront (xmlListPtr l);
XMLPUBFUN xmlLinkPtr XMLCALL
xmlListEnd (xmlListPtr l);
XMLPUBFUN int XMLCALL
xmlListSize (xmlListPtr l);
XMLPUBFUN void XMLCALL
xmlListPopFront (xmlListPtr l);
XMLPUBFUN void XMLCALL
xmlListPopBack (xmlListPtr l);
XMLPUBFUN int XMLCALL
xmlListPushFront (xmlListPtr l,
void *data);
XMLPUBFUN int XMLCALL
xmlListPushBack (xmlListPtr l,
void *data);
/* Advanced Operators */
XMLPUBFUN void XMLCALL
xmlListReverse (xmlListPtr l);
XMLPUBFUN void XMLCALL
xmlListSort (xmlListPtr l);
XMLPUBFUN void XMLCALL
xmlListWalk (xmlListPtr l,
xmlListWalker walker,
const void *user);
XMLPUBFUN void XMLCALL
xmlListReverseWalk (xmlListPtr l,
xmlListWalker walker,
const void *user);
XMLPUBFUN void XMLCALL
xmlListMerge (xmlListPtr l1,
xmlListPtr l2);
XMLPUBFUN xmlListPtr XMLCALL
xmlListDup (const xmlListPtr old);
XMLPUBFUN int XMLCALL
xmlListCopy (xmlListPtr cur,
const xmlListPtr old);
/* Link operators */
XMLPUBFUN void * XMLCALL
xmlLinkGetData (xmlLinkPtr lk);
/* xmlListUnique() */
/* xmlListSwap */
#ifdef __cplusplus
}
#endif
#endif /* __XML_LINK_INCLUDE__ */

@ -0,0 +1,163 @@
/*
* Summary: minimal FTP implementation
* Description: minimal FTP implementation allowing to fetch resources
* like external subset.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __NANO_FTP_H__
#define __NANO_FTP_H__
#include <libxml/xmlversion.h>
#ifdef LIBXML_FTP_ENABLED
/* Needed for portability to Windows 64 bits */
#if defined(__MINGW32__) || defined(_WIN32_WCE)
#include <winsock2.h>
#else
/**
* SOCKET:
*
* macro used to provide portability of code to windows sockets
*/
#define SOCKET int
/**
* INVALID_SOCKET:
*
* macro used to provide portability of code to windows sockets
* the value to be used when the socket is not valid
*/
#undef INVALID_SOCKET
#define INVALID_SOCKET (-1)
#endif
#ifdef __cplusplus
extern "C" {
#endif
/**
* ftpListCallback:
* @userData: user provided data for the callback
* @filename: the file name (including "->" when links are shown)
* @attrib: the attribute string
* @owner: the owner string
* @group: the group string
* @size: the file size
* @links: the link count
* @year: the year
* @month: the month
* @day: the day
* @hour: the hour
* @minute: the minute
*
* A callback for the xmlNanoFTPList command.
* Note that only one of year and day:minute are specified.
*/
typedef void (*ftpListCallback) (void *userData,
const char *filename, const char *attrib,
const char *owner, const char *group,
unsigned long size, int links, int year,
const char *month, int day, int hour,
int minute);
/**
* ftpDataCallback:
* @userData: the user provided context
* @data: the data received
* @len: its size in bytes
*
* A callback for the xmlNanoFTPGet command.
*/
typedef void (*ftpDataCallback) (void *userData,
const char *data,
int len);
/*
* Init
*/
XMLPUBFUN void XMLCALL
xmlNanoFTPInit (void);
XMLPUBFUN void XMLCALL
xmlNanoFTPCleanup (void);
/*
* Creating/freeing contexts.
*/
XMLPUBFUN void * XMLCALL
xmlNanoFTPNewCtxt (const char *URL);
XMLPUBFUN void XMLCALL
xmlNanoFTPFreeCtxt (void * ctx);
XMLPUBFUN void * XMLCALL
xmlNanoFTPConnectTo (const char *server,
int port);
/*
* Opening/closing session connections.
*/
XMLPUBFUN void * XMLCALL
xmlNanoFTPOpen (const char *URL);
XMLPUBFUN int XMLCALL
xmlNanoFTPConnect (void *ctx);
XMLPUBFUN int XMLCALL
xmlNanoFTPClose (void *ctx);
XMLPUBFUN int XMLCALL
xmlNanoFTPQuit (void *ctx);
XMLPUBFUN void XMLCALL
xmlNanoFTPScanProxy (const char *URL);
XMLPUBFUN void XMLCALL
xmlNanoFTPProxy (const char *host,
int port,
const char *user,
const char *passwd,
int type);
XMLPUBFUN int XMLCALL
xmlNanoFTPUpdateURL (void *ctx,
const char *URL);
/*
* Rather internal commands.
*/
XMLPUBFUN int XMLCALL
xmlNanoFTPGetResponse (void *ctx);
XMLPUBFUN int XMLCALL
xmlNanoFTPCheckResponse (void *ctx);
/*
* CD/DIR/GET handlers.
*/
XMLPUBFUN int XMLCALL
xmlNanoFTPCwd (void *ctx,
const char *directory);
XMLPUBFUN int XMLCALL
xmlNanoFTPDele (void *ctx,
const char *file);
XMLPUBFUN SOCKET XMLCALL
xmlNanoFTPGetConnection (void *ctx);
XMLPUBFUN int XMLCALL
xmlNanoFTPCloseConnection(void *ctx);
XMLPUBFUN int XMLCALL
xmlNanoFTPList (void *ctx,
ftpListCallback callback,
void *userData,
const char *filename);
XMLPUBFUN SOCKET XMLCALL
xmlNanoFTPGetSocket (void *ctx,
const char *filename);
XMLPUBFUN int XMLCALL
xmlNanoFTPGet (void *ctx,
ftpDataCallback callback,
void *userData,
const char *filename);
XMLPUBFUN int XMLCALL
xmlNanoFTPRead (void *ctx,
void *dest,
int len);
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_FTP_ENABLED */
#endif /* __NANO_FTP_H__ */

@ -0,0 +1,81 @@
/*
* Summary: minimal HTTP implementation
* Description: minimal HTTP implementation allowing to fetch resources
* like external subset.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __NANO_HTTP_H__
#define __NANO_HTTP_H__
#include <libxml/xmlversion.h>
#ifdef LIBXML_HTTP_ENABLED
#ifdef __cplusplus
extern "C" {
#endif
XMLPUBFUN void XMLCALL
xmlNanoHTTPInit (void);
XMLPUBFUN void XMLCALL
xmlNanoHTTPCleanup (void);
XMLPUBFUN void XMLCALL
xmlNanoHTTPScanProxy (const char *URL);
XMLPUBFUN int XMLCALL
xmlNanoHTTPFetch (const char *URL,
const char *filename,
char **contentType);
XMLPUBFUN void * XMLCALL
xmlNanoHTTPMethod (const char *URL,
const char *method,
const char *input,
char **contentType,
const char *headers,
int ilen);
XMLPUBFUN void * XMLCALL
xmlNanoHTTPMethodRedir (const char *URL,
const char *method,
const char *input,
char **contentType,
char **redir,
const char *headers,
int ilen);
XMLPUBFUN void * XMLCALL
xmlNanoHTTPOpen (const char *URL,
char **contentType);
XMLPUBFUN void * XMLCALL
xmlNanoHTTPOpenRedir (const char *URL,
char **contentType,
char **redir);
XMLPUBFUN int XMLCALL
xmlNanoHTTPReturnCode (void *ctx);
XMLPUBFUN const char * XMLCALL
xmlNanoHTTPAuthHeader (void *ctx);
XMLPUBFUN const char * XMLCALL
xmlNanoHTTPRedir (void *ctx);
XMLPUBFUN int XMLCALL
xmlNanoHTTPContentLength( void * ctx );
XMLPUBFUN const char * XMLCALL
xmlNanoHTTPEncoding (void *ctx);
XMLPUBFUN const char * XMLCALL
xmlNanoHTTPMimeType (void *ctx);
XMLPUBFUN int XMLCALL
xmlNanoHTTPRead (void *ctx,
void *dest,
int len);
#ifdef LIBXML_OUTPUT_ENABLED
XMLPUBFUN int XMLCALL
xmlNanoHTTPSave (void *ctxt,
const char *filename);
#endif /* LIBXML_OUTPUT_ENABLED */
XMLPUBFUN void XMLCALL
xmlNanoHTTPClose (void *ctx);
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_HTTP_ENABLED */
#endif /* __NANO_HTTP_H__ */

File diff suppressed because it is too large Load Diff

@ -0,0 +1,644 @@
/*
* Summary: internals routines and limits exported by the parser.
* Description: this module exports a number of internal parsing routines
* they are not really all intended for applications but
* can prove useful doing low level processing.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_PARSER_INTERNALS_H__
#define __XML_PARSER_INTERNALS_H__
#include <libxml/xmlversion.h>
#include <libxml/parser.h>
#include <libxml/HTMLparser.h>
#include <libxml/chvalid.h>
#ifdef __cplusplus
extern "C" {
#endif
/**
* xmlParserMaxDepth:
*
* arbitrary depth limit for the XML documents that we allow to
* process. This is not a limitation of the parser but a safety
* boundary feature, use XML_PARSE_HUGE option to override it.
*/
XMLPUBVAR unsigned int xmlParserMaxDepth;
/**
* XML_MAX_TEXT_LENGTH:
*
* Maximum size allowed for a single text node when building a tree.
* This is not a limitation of the parser but a safety boundary feature,
* use XML_PARSE_HUGE option to override it.
* Introduced in 2.9.0
*/
#define XML_MAX_TEXT_LENGTH 10000000
/**
* XML_MAX_NAME_LENGTH:
*
* Maximum size allowed for a markup identitier
* This is not a limitation of the parser but a safety boundary feature,
* use XML_PARSE_HUGE option to override it.
* Note that with the use of parsing dictionaries overriding the limit
* may result in more runtime memory usage in face of "unfriendly' content
* Introduced in 2.9.0
*/
#define XML_MAX_NAME_LENGTH 50000
/**
* XML_MAX_DICTIONARY_LIMIT:
*
* Maximum size allowed by the parser for a dictionary by default
* This is not a limitation of the parser but a safety boundary feature,
* use XML_PARSE_HUGE option to override it.
* Introduced in 2.9.0
*/
#define XML_MAX_DICTIONARY_LIMIT 10000000
/**
* XML_MAX_LOOKUP_LIMIT:
*
* Maximum size allowed by the parser for ahead lookup
* This is an upper boundary enforced by the parser to avoid bad
* behaviour on "unfriendly' content
* Introduced in 2.9.0
*/
#define XML_MAX_LOOKUP_LIMIT 10000000
/**
* XML_MAX_NAMELEN:
*
* Identifiers can be longer, but this will be more costly
* at runtime.
*/
#define XML_MAX_NAMELEN 100
/**
* INPUT_CHUNK:
*
* The parser tries to always have that amount of input ready.
* One of the point is providing context when reporting errors.
*/
#define INPUT_CHUNK 250
/************************************************************************
* *
* UNICODE version of the macros. *
* *
************************************************************************/
/**
* IS_BYTE_CHAR:
* @c: an byte value (int)
*
* Macro to check the following production in the XML spec:
*
* [2] Char ::= #x9 | #xA | #xD | [#x20...]
* any byte character in the accepted range
*/
#define IS_BYTE_CHAR(c) xmlIsChar_ch(c)
/**
* IS_CHAR:
* @c: an UNICODE value (int)
*
* Macro to check the following production in the XML spec:
*
* [2] Char ::= #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD]
* | [#x10000-#x10FFFF]
* any Unicode character, excluding the surrogate blocks, FFFE, and FFFF.
*/
#define IS_CHAR(c) xmlIsCharQ(c)
/**
* IS_CHAR_CH:
* @c: an xmlChar (usually an unsigned char)
*
* Behaves like IS_CHAR on single-byte value
*/
#define IS_CHAR_CH(c) xmlIsChar_ch(c)
/**
* IS_BLANK:
* @c: an UNICODE value (int)
*
* Macro to check the following production in the XML spec:
*
* [3] S ::= (#x20 | #x9 | #xD | #xA)+
*/
#define IS_BLANK(c) xmlIsBlankQ(c)
/**
* IS_BLANK_CH:
* @c: an xmlChar value (normally unsigned char)
*
* Behaviour same as IS_BLANK
*/
#define IS_BLANK_CH(c) xmlIsBlank_ch(c)
/**
* IS_BASECHAR:
* @c: an UNICODE value (int)
*
* Macro to check the following production in the XML spec:
*
* [85] BaseChar ::= ... long list see REC ...
*/
#define IS_BASECHAR(c) xmlIsBaseCharQ(c)
/**
* IS_DIGIT:
* @c: an UNICODE value (int)
*
* Macro to check the following production in the XML spec:
*
* [88] Digit ::= ... long list see REC ...
*/
#define IS_DIGIT(c) xmlIsDigitQ(c)
/**
* IS_DIGIT_CH:
* @c: an xmlChar value (usually an unsigned char)
*
* Behaves like IS_DIGIT but with a single byte argument
*/
#define IS_DIGIT_CH(c) xmlIsDigit_ch(c)
/**
* IS_COMBINING:
* @c: an UNICODE value (int)
*
* Macro to check the following production in the XML spec:
*
* [87] CombiningChar ::= ... long list see REC ...
*/
#define IS_COMBINING(c) xmlIsCombiningQ(c)
/**
* IS_COMBINING_CH:
* @c: an xmlChar (usually an unsigned char)
*
* Always false (all combining chars > 0xff)
*/
#define IS_COMBINING_CH(c) 0
/**
* IS_EXTENDER:
* @c: an UNICODE value (int)
*
* Macro to check the following production in the XML spec:
*
*
* [89] Extender ::= #x00B7 | #x02D0 | #x02D1 | #x0387 | #x0640 |
* #x0E46 | #x0EC6 | #x3005 | [#x3031-#x3035] |
* [#x309D-#x309E] | [#x30FC-#x30FE]
*/
#define IS_EXTENDER(c) xmlIsExtenderQ(c)
/**
* IS_EXTENDER_CH:
* @c: an xmlChar value (usually an unsigned char)
*
* Behaves like IS_EXTENDER but with a single-byte argument
*/
#define IS_EXTENDER_CH(c) xmlIsExtender_ch(c)
/**
* IS_IDEOGRAPHIC:
* @c: an UNICODE value (int)
*
* Macro to check the following production in the XML spec:
*
*
* [86] Ideographic ::= [#x4E00-#x9FA5] | #x3007 | [#x3021-#x3029]
*/
#define IS_IDEOGRAPHIC(c) xmlIsIdeographicQ(c)
/**
* IS_LETTER:
* @c: an UNICODE value (int)
*
* Macro to check the following production in the XML spec:
*
*
* [84] Letter ::= BaseChar | Ideographic
*/
#define IS_LETTER(c) (IS_BASECHAR(c) || IS_IDEOGRAPHIC(c))
/**
* IS_LETTER_CH:
* @c: an xmlChar value (normally unsigned char)
*
* Macro behaves like IS_LETTER, but only check base chars
*
*/
#define IS_LETTER_CH(c) xmlIsBaseChar_ch(c)
/**
* IS_ASCII_LETTER:
* @c: an xmlChar value
*
* Macro to check [a-zA-Z]
*
*/
#define IS_ASCII_LETTER(c) (((0x41 <= (c)) && ((c) <= 0x5a)) || \
((0x61 <= (c)) && ((c) <= 0x7a)))
/**
* IS_ASCII_DIGIT:
* @c: an xmlChar value
*
* Macro to check [0-9]
*
*/
#define IS_ASCII_DIGIT(c) ((0x30 <= (c)) && ((c) <= 0x39))
/**
* IS_PUBIDCHAR:
* @c: an UNICODE value (int)
*
* Macro to check the following production in the XML spec:
*
*
* [13] PubidChar ::= #x20 | #xD | #xA | [a-zA-Z0-9] | [-'()+,./:=?;!*#@$_%]
*/
#define IS_PUBIDCHAR(c) xmlIsPubidCharQ(c)
/**
* IS_PUBIDCHAR_CH:
* @c: an xmlChar value (normally unsigned char)
*
* Same as IS_PUBIDCHAR but for single-byte value
*/
#define IS_PUBIDCHAR_CH(c) xmlIsPubidChar_ch(c)
/**
* SKIP_EOL:
* @p: and UTF8 string pointer
*
* Skips the end of line chars.
*/
#define SKIP_EOL(p) \
if (*(p) == 0x13) { p++ ; if (*(p) == 0x10) p++; } \
if (*(p) == 0x10) { p++ ; if (*(p) == 0x13) p++; }
/**
* MOVETO_ENDTAG:
* @p: and UTF8 string pointer
*
* Skips to the next '>' char.
*/
#define MOVETO_ENDTAG(p) \
while ((*p) && (*(p) != '>')) (p)++
/**
* MOVETO_STARTTAG:
* @p: and UTF8 string pointer
*
* Skips to the next '<' char.
*/
#define MOVETO_STARTTAG(p) \
while ((*p) && (*(p) != '<')) (p)++
/**
* Global variables used for predefined strings.
*/
XMLPUBVAR const xmlChar xmlStringText[];
XMLPUBVAR const xmlChar xmlStringTextNoenc[];
XMLPUBVAR const xmlChar xmlStringComment[];
/*
* Function to finish the work of the macros where needed.
*/
XMLPUBFUN int XMLCALL xmlIsLetter (int c);
/**
* Parser context.
*/
XMLPUBFUN xmlParserCtxtPtr XMLCALL
xmlCreateFileParserCtxt (const char *filename);
XMLPUBFUN xmlParserCtxtPtr XMLCALL
xmlCreateURLParserCtxt (const char *filename,
int options);
XMLPUBFUN xmlParserCtxtPtr XMLCALL
xmlCreateMemoryParserCtxt(const char *buffer,
int size);
XMLPUBFUN xmlParserCtxtPtr XMLCALL
xmlCreateEntityParserCtxt(const xmlChar *URL,
const xmlChar *ID,
const xmlChar *base);
XMLPUBFUN int XMLCALL
xmlSwitchEncoding (xmlParserCtxtPtr ctxt,
xmlCharEncoding enc);
XMLPUBFUN int XMLCALL
xmlSwitchToEncoding (xmlParserCtxtPtr ctxt,
xmlCharEncodingHandlerPtr handler);
XMLPUBFUN int XMLCALL
xmlSwitchInputEncoding (xmlParserCtxtPtr ctxt,
xmlParserInputPtr input,
xmlCharEncodingHandlerPtr handler);
#ifdef IN_LIBXML
/* internal error reporting */
XMLPUBFUN void XMLCALL
__xmlErrEncoding (xmlParserCtxtPtr ctxt,
xmlParserErrors xmlerr,
const char *msg,
const xmlChar * str1,
const xmlChar * str2) LIBXML_ATTR_FORMAT(3,0);
#endif
/**
* Input Streams.
*/
XMLPUBFUN xmlParserInputPtr XMLCALL
xmlNewStringInputStream (xmlParserCtxtPtr ctxt,
const xmlChar *buffer);
XMLPUBFUN xmlParserInputPtr XMLCALL
xmlNewEntityInputStream (xmlParserCtxtPtr ctxt,
xmlEntityPtr entity);
XMLPUBFUN int XMLCALL
xmlPushInput (xmlParserCtxtPtr ctxt,
xmlParserInputPtr input);
XMLPUBFUN xmlChar XMLCALL
xmlPopInput (xmlParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlFreeInputStream (xmlParserInputPtr input);
XMLPUBFUN xmlParserInputPtr XMLCALL
xmlNewInputFromFile (xmlParserCtxtPtr ctxt,
const char *filename);
XMLPUBFUN xmlParserInputPtr XMLCALL
xmlNewInputStream (xmlParserCtxtPtr ctxt);
/**
* Namespaces.
*/
XMLPUBFUN xmlChar * XMLCALL
xmlSplitQName (xmlParserCtxtPtr ctxt,
const xmlChar *name,
xmlChar **prefix);
/**
* Generic production rules.
*/
XMLPUBFUN const xmlChar * XMLCALL
xmlParseName (xmlParserCtxtPtr ctxt);
XMLPUBFUN xmlChar * XMLCALL
xmlParseNmtoken (xmlParserCtxtPtr ctxt);
XMLPUBFUN xmlChar * XMLCALL
xmlParseEntityValue (xmlParserCtxtPtr ctxt,
xmlChar **orig);
XMLPUBFUN xmlChar * XMLCALL
xmlParseAttValue (xmlParserCtxtPtr ctxt);
XMLPUBFUN xmlChar * XMLCALL
xmlParseSystemLiteral (xmlParserCtxtPtr ctxt);
XMLPUBFUN xmlChar * XMLCALL
xmlParsePubidLiteral (xmlParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlParseCharData (xmlParserCtxtPtr ctxt,
int cdata);
XMLPUBFUN xmlChar * XMLCALL
xmlParseExternalID (xmlParserCtxtPtr ctxt,
xmlChar **publicID,
int strict);
XMLPUBFUN void XMLCALL
xmlParseComment (xmlParserCtxtPtr ctxt);
XMLPUBFUN const xmlChar * XMLCALL
xmlParsePITarget (xmlParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlParsePI (xmlParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlParseNotationDecl (xmlParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlParseEntityDecl (xmlParserCtxtPtr ctxt);
XMLPUBFUN int XMLCALL
xmlParseDefaultDecl (xmlParserCtxtPtr ctxt,
xmlChar **value);
XMLPUBFUN xmlEnumerationPtr XMLCALL
xmlParseNotationType (xmlParserCtxtPtr ctxt);
XMLPUBFUN xmlEnumerationPtr XMLCALL
xmlParseEnumerationType (xmlParserCtxtPtr ctxt);
XMLPUBFUN int XMLCALL
xmlParseEnumeratedType (xmlParserCtxtPtr ctxt,
xmlEnumerationPtr *tree);
XMLPUBFUN int XMLCALL
xmlParseAttributeType (xmlParserCtxtPtr ctxt,
xmlEnumerationPtr *tree);
XMLPUBFUN void XMLCALL
xmlParseAttributeListDecl(xmlParserCtxtPtr ctxt);
XMLPUBFUN xmlElementContentPtr XMLCALL
xmlParseElementMixedContentDecl
(xmlParserCtxtPtr ctxt,
int inputchk);
XMLPUBFUN xmlElementContentPtr XMLCALL
xmlParseElementChildrenContentDecl
(xmlParserCtxtPtr ctxt,
int inputchk);
XMLPUBFUN int XMLCALL
xmlParseElementContentDecl(xmlParserCtxtPtr ctxt,
const xmlChar *name,
xmlElementContentPtr *result);
XMLPUBFUN int XMLCALL
xmlParseElementDecl (xmlParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlParseMarkupDecl (xmlParserCtxtPtr ctxt);
XMLPUBFUN int XMLCALL
xmlParseCharRef (xmlParserCtxtPtr ctxt);
XMLPUBFUN xmlEntityPtr XMLCALL
xmlParseEntityRef (xmlParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlParseReference (xmlParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlParsePEReference (xmlParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlParseDocTypeDecl (xmlParserCtxtPtr ctxt);
#ifdef LIBXML_SAX1_ENABLED
XMLPUBFUN const xmlChar * XMLCALL
xmlParseAttribute (xmlParserCtxtPtr ctxt,
xmlChar **value);
XMLPUBFUN const xmlChar * XMLCALL
xmlParseStartTag (xmlParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlParseEndTag (xmlParserCtxtPtr ctxt);
#endif /* LIBXML_SAX1_ENABLED */
XMLPUBFUN void XMLCALL
xmlParseCDSect (xmlParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlParseContent (xmlParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlParseElement (xmlParserCtxtPtr ctxt);
XMLPUBFUN xmlChar * XMLCALL
xmlParseVersionNum (xmlParserCtxtPtr ctxt);
XMLPUBFUN xmlChar * XMLCALL
xmlParseVersionInfo (xmlParserCtxtPtr ctxt);
XMLPUBFUN xmlChar * XMLCALL
xmlParseEncName (xmlParserCtxtPtr ctxt);
XMLPUBFUN const xmlChar * XMLCALL
xmlParseEncodingDecl (xmlParserCtxtPtr ctxt);
XMLPUBFUN int XMLCALL
xmlParseSDDecl (xmlParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlParseXMLDecl (xmlParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlParseTextDecl (xmlParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlParseMisc (xmlParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlParseExternalSubset (xmlParserCtxtPtr ctxt,
const xmlChar *ExternalID,
const xmlChar *SystemID);
/**
* XML_SUBSTITUTE_NONE:
*
* If no entities need to be substituted.
*/
#define XML_SUBSTITUTE_NONE 0
/**
* XML_SUBSTITUTE_REF:
*
* Whether general entities need to be substituted.
*/
#define XML_SUBSTITUTE_REF 1
/**
* XML_SUBSTITUTE_PEREF:
*
* Whether parameter entities need to be substituted.
*/
#define XML_SUBSTITUTE_PEREF 2
/**
* XML_SUBSTITUTE_BOTH:
*
* Both general and parameter entities need to be substituted.
*/
#define XML_SUBSTITUTE_BOTH 3
XMLPUBFUN xmlChar * XMLCALL
xmlStringDecodeEntities (xmlParserCtxtPtr ctxt,
const xmlChar *str,
int what,
xmlChar end,
xmlChar end2,
xmlChar end3);
XMLPUBFUN xmlChar * XMLCALL
xmlStringLenDecodeEntities (xmlParserCtxtPtr ctxt,
const xmlChar *str,
int len,
int what,
xmlChar end,
xmlChar end2,
xmlChar end3);
/*
* Generated by MACROS on top of parser.c c.f. PUSH_AND_POP.
*/
XMLPUBFUN int XMLCALL nodePush (xmlParserCtxtPtr ctxt,
xmlNodePtr value);
XMLPUBFUN xmlNodePtr XMLCALL nodePop (xmlParserCtxtPtr ctxt);
XMLPUBFUN int XMLCALL inputPush (xmlParserCtxtPtr ctxt,
xmlParserInputPtr value);
XMLPUBFUN xmlParserInputPtr XMLCALL inputPop (xmlParserCtxtPtr ctxt);
XMLPUBFUN const xmlChar * XMLCALL namePop (xmlParserCtxtPtr ctxt);
XMLPUBFUN int XMLCALL namePush (xmlParserCtxtPtr ctxt,
const xmlChar *value);
/*
* other commodities shared between parser.c and parserInternals.
*/
XMLPUBFUN int XMLCALL xmlSkipBlankChars (xmlParserCtxtPtr ctxt);
XMLPUBFUN int XMLCALL xmlStringCurrentChar (xmlParserCtxtPtr ctxt,
const xmlChar *cur,
int *len);
XMLPUBFUN void XMLCALL xmlParserHandlePEReference(xmlParserCtxtPtr ctxt);
XMLPUBFUN int XMLCALL xmlCheckLanguageID (const xmlChar *lang);
/*
* Really core function shared with HTML parser.
*/
XMLPUBFUN int XMLCALL xmlCurrentChar (xmlParserCtxtPtr ctxt,
int *len);
XMLPUBFUN int XMLCALL xmlCopyCharMultiByte (xmlChar *out,
int val);
XMLPUBFUN int XMLCALL xmlCopyChar (int len,
xmlChar *out,
int val);
XMLPUBFUN void XMLCALL xmlNextChar (xmlParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL xmlParserInputShrink (xmlParserInputPtr in);
#ifdef LIBXML_HTML_ENABLED
/*
* Actually comes from the HTML parser but launched from the init stuff.
*/
XMLPUBFUN void XMLCALL htmlInitAutoClose (void);
XMLPUBFUN htmlParserCtxtPtr XMLCALL htmlCreateFileParserCtxt(const char *filename,
const char *encoding);
#endif
/*
* Specific function to keep track of entities references
* and used by the XSLT debugger.
*/
#ifdef LIBXML_LEGACY_ENABLED
/**
* xmlEntityReferenceFunc:
* @ent: the entity
* @firstNode: the fist node in the chunk
* @lastNode: the last nod in the chunk
*
* Callback function used when one needs to be able to track back the
* provenance of a chunk of nodes inherited from an entity replacement.
*/
typedef void (*xmlEntityReferenceFunc) (xmlEntityPtr ent,
xmlNodePtr firstNode,
xmlNodePtr lastNode);
XMLPUBFUN void XMLCALL xmlSetEntityReferenceFunc (xmlEntityReferenceFunc func);
XMLPUBFUN xmlChar * XMLCALL
xmlParseQuotedString (xmlParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlParseNamespace (xmlParserCtxtPtr ctxt);
XMLPUBFUN xmlChar * XMLCALL
xmlNamespaceParseNSDef (xmlParserCtxtPtr ctxt);
XMLPUBFUN xmlChar * XMLCALL
xmlScanName (xmlParserCtxtPtr ctxt);
XMLPUBFUN xmlChar * XMLCALL
xmlNamespaceParseNCName (xmlParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL xmlParserHandleReference(xmlParserCtxtPtr ctxt);
XMLPUBFUN xmlChar * XMLCALL
xmlNamespaceParseQName (xmlParserCtxtPtr ctxt,
xmlChar **prefix);
/**
* Entities
*/
XMLPUBFUN xmlChar * XMLCALL
xmlDecodeEntities (xmlParserCtxtPtr ctxt,
int len,
int what,
xmlChar end,
xmlChar end2,
xmlChar end3);
XMLPUBFUN void XMLCALL
xmlHandleEntity (xmlParserCtxtPtr ctxt,
xmlEntityPtr entity);
#endif /* LIBXML_LEGACY_ENABLED */
#ifdef IN_LIBXML
/*
* internal only
*/
XMLPUBFUN void XMLCALL
xmlErrMemory (xmlParserCtxtPtr ctxt,
const char *extra);
#endif
#ifdef __cplusplus
}
#endif
#endif /* __XML_PARSER_INTERNALS_H__ */

@ -0,0 +1,100 @@
/*
* Summary: pattern expression handling
* Description: allows to compile and test pattern expressions for nodes
* either in a tree or based on a parser state.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_PATTERN_H__
#define __XML_PATTERN_H__
#include <libxml/xmlversion.h>
#include <libxml/tree.h>
#include <libxml/dict.h>
#ifdef LIBXML_PATTERN_ENABLED
#ifdef __cplusplus
extern "C" {
#endif
/**
* xmlPattern:
*
* A compiled (XPath based) pattern to select nodes
*/
typedef struct _xmlPattern xmlPattern;
typedef xmlPattern *xmlPatternPtr;
/**
* xmlPatternFlags:
*
* This is the set of options affecting the behaviour of pattern
* matching with this module
*
*/
typedef enum {
XML_PATTERN_DEFAULT = 0, /* simple pattern match */
XML_PATTERN_XPATH = 1<<0, /* standard XPath pattern */
XML_PATTERN_XSSEL = 1<<1, /* XPath subset for schema selector */
XML_PATTERN_XSFIELD = 1<<2 /* XPath subset for schema field */
} xmlPatternFlags;
XMLPUBFUN void XMLCALL
xmlFreePattern (xmlPatternPtr comp);
XMLPUBFUN void XMLCALL
xmlFreePatternList (xmlPatternPtr comp);
XMLPUBFUN xmlPatternPtr XMLCALL
xmlPatterncompile (const xmlChar *pattern,
xmlDict *dict,
int flags,
const xmlChar **namespaces);
XMLPUBFUN int XMLCALL
xmlPatternMatch (xmlPatternPtr comp,
xmlNodePtr node);
/* streaming interfaces */
typedef struct _xmlStreamCtxt xmlStreamCtxt;
typedef xmlStreamCtxt *xmlStreamCtxtPtr;
XMLPUBFUN int XMLCALL
xmlPatternStreamable (xmlPatternPtr comp);
XMLPUBFUN int XMLCALL
xmlPatternMaxDepth (xmlPatternPtr comp);
XMLPUBFUN int XMLCALL
xmlPatternMinDepth (xmlPatternPtr comp);
XMLPUBFUN int XMLCALL
xmlPatternFromRoot (xmlPatternPtr comp);
XMLPUBFUN xmlStreamCtxtPtr XMLCALL
xmlPatternGetStreamCtxt (xmlPatternPtr comp);
XMLPUBFUN void XMLCALL
xmlFreeStreamCtxt (xmlStreamCtxtPtr stream);
XMLPUBFUN int XMLCALL
xmlStreamPushNode (xmlStreamCtxtPtr stream,
const xmlChar *name,
const xmlChar *ns,
int nodeType);
XMLPUBFUN int XMLCALL
xmlStreamPush (xmlStreamCtxtPtr stream,
const xmlChar *name,
const xmlChar *ns);
XMLPUBFUN int XMLCALL
xmlStreamPushAttr (xmlStreamCtxtPtr stream,
const xmlChar *name,
const xmlChar *ns);
XMLPUBFUN int XMLCALL
xmlStreamPop (xmlStreamCtxtPtr stream);
XMLPUBFUN int XMLCALL
xmlStreamWantsAnyNode (xmlStreamCtxtPtr stream);
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_PATTERN_ENABLED */
#endif /* __XML_PATTERN_H__ */

@ -0,0 +1,217 @@
/*
* Summary: implementation of the Relax-NG validation
* Description: implementation of the Relax-NG validation
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_RELAX_NG__
#define __XML_RELAX_NG__
#include <libxml/xmlversion.h>
#include <libxml/hash.h>
#include <libxml/xmlstring.h>
#ifdef LIBXML_SCHEMAS_ENABLED
#ifdef __cplusplus
extern "C" {
#endif
typedef struct _xmlRelaxNG xmlRelaxNG;
typedef xmlRelaxNG *xmlRelaxNGPtr;
/**
* xmlRelaxNGValidityErrorFunc:
* @ctx: the validation context
* @msg: the message
* @...: extra arguments
*
* Signature of an error callback from a Relax-NG validation
*/
typedef void (XMLCDECL *xmlRelaxNGValidityErrorFunc) (void *ctx,
const char *msg,
...) LIBXML_ATTR_FORMAT(2,3);
/**
* xmlRelaxNGValidityWarningFunc:
* @ctx: the validation context
* @msg: the message
* @...: extra arguments
*
* Signature of a warning callback from a Relax-NG validation
*/
typedef void (XMLCDECL *xmlRelaxNGValidityWarningFunc) (void *ctx,
const char *msg,
...) LIBXML_ATTR_FORMAT(2,3);
/**
* A schemas validation context
*/
typedef struct _xmlRelaxNGParserCtxt xmlRelaxNGParserCtxt;
typedef xmlRelaxNGParserCtxt *xmlRelaxNGParserCtxtPtr;
typedef struct _xmlRelaxNGValidCtxt xmlRelaxNGValidCtxt;
typedef xmlRelaxNGValidCtxt *xmlRelaxNGValidCtxtPtr;
/*
* xmlRelaxNGValidErr:
*
* List of possible Relax NG validation errors
*/
typedef enum {
XML_RELAXNG_OK = 0,
XML_RELAXNG_ERR_MEMORY,
XML_RELAXNG_ERR_TYPE,
XML_RELAXNG_ERR_TYPEVAL,
XML_RELAXNG_ERR_DUPID,
XML_RELAXNG_ERR_TYPECMP,
XML_RELAXNG_ERR_NOSTATE,
XML_RELAXNG_ERR_NODEFINE,
XML_RELAXNG_ERR_LISTEXTRA,
XML_RELAXNG_ERR_LISTEMPTY,
XML_RELAXNG_ERR_INTERNODATA,
XML_RELAXNG_ERR_INTERSEQ,
XML_RELAXNG_ERR_INTEREXTRA,
XML_RELAXNG_ERR_ELEMNAME,
XML_RELAXNG_ERR_ATTRNAME,
XML_RELAXNG_ERR_ELEMNONS,
XML_RELAXNG_ERR_ATTRNONS,
XML_RELAXNG_ERR_ELEMWRONGNS,
XML_RELAXNG_ERR_ATTRWRONGNS,
XML_RELAXNG_ERR_ELEMEXTRANS,
XML_RELAXNG_ERR_ATTREXTRANS,
XML_RELAXNG_ERR_ELEMNOTEMPTY,
XML_RELAXNG_ERR_NOELEM,
XML_RELAXNG_ERR_NOTELEM,
XML_RELAXNG_ERR_ATTRVALID,
XML_RELAXNG_ERR_CONTENTVALID,
XML_RELAXNG_ERR_EXTRACONTENT,
XML_RELAXNG_ERR_INVALIDATTR,
XML_RELAXNG_ERR_DATAELEM,
XML_RELAXNG_ERR_VALELEM,
XML_RELAXNG_ERR_LISTELEM,
XML_RELAXNG_ERR_DATATYPE,
XML_RELAXNG_ERR_VALUE,
XML_RELAXNG_ERR_LIST,
XML_RELAXNG_ERR_NOGRAMMAR,
XML_RELAXNG_ERR_EXTRADATA,
XML_RELAXNG_ERR_LACKDATA,
XML_RELAXNG_ERR_INTERNAL,
XML_RELAXNG_ERR_ELEMWRONG,
XML_RELAXNG_ERR_TEXTWRONG
} xmlRelaxNGValidErr;
/*
* xmlRelaxNGParserFlags:
*
* List of possible Relax NG Parser flags
*/
typedef enum {
XML_RELAXNGP_NONE = 0,
XML_RELAXNGP_FREE_DOC = 1,
XML_RELAXNGP_CRNG = 2
} xmlRelaxNGParserFlag;
XMLPUBFUN int XMLCALL
xmlRelaxNGInitTypes (void);
XMLPUBFUN void XMLCALL
xmlRelaxNGCleanupTypes (void);
/*
* Interfaces for parsing.
*/
XMLPUBFUN xmlRelaxNGParserCtxtPtr XMLCALL
xmlRelaxNGNewParserCtxt (const char *URL);
XMLPUBFUN xmlRelaxNGParserCtxtPtr XMLCALL
xmlRelaxNGNewMemParserCtxt (const char *buffer,
int size);
XMLPUBFUN xmlRelaxNGParserCtxtPtr XMLCALL
xmlRelaxNGNewDocParserCtxt (xmlDocPtr doc);
XMLPUBFUN int XMLCALL
xmlRelaxParserSetFlag (xmlRelaxNGParserCtxtPtr ctxt,
int flag);
XMLPUBFUN void XMLCALL
xmlRelaxNGFreeParserCtxt (xmlRelaxNGParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlRelaxNGSetParserErrors(xmlRelaxNGParserCtxtPtr ctxt,
xmlRelaxNGValidityErrorFunc err,
xmlRelaxNGValidityWarningFunc warn,
void *ctx);
XMLPUBFUN int XMLCALL
xmlRelaxNGGetParserErrors(xmlRelaxNGParserCtxtPtr ctxt,
xmlRelaxNGValidityErrorFunc *err,
xmlRelaxNGValidityWarningFunc *warn,
void **ctx);
XMLPUBFUN void XMLCALL
xmlRelaxNGSetParserStructuredErrors(
xmlRelaxNGParserCtxtPtr ctxt,
xmlStructuredErrorFunc serror,
void *ctx);
XMLPUBFUN xmlRelaxNGPtr XMLCALL
xmlRelaxNGParse (xmlRelaxNGParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlRelaxNGFree (xmlRelaxNGPtr schema);
#ifdef LIBXML_OUTPUT_ENABLED
XMLPUBFUN void XMLCALL
xmlRelaxNGDump (FILE *output,
xmlRelaxNGPtr schema);
XMLPUBFUN void XMLCALL
xmlRelaxNGDumpTree (FILE * output,
xmlRelaxNGPtr schema);
#endif /* LIBXML_OUTPUT_ENABLED */
/*
* Interfaces for validating
*/
XMLPUBFUN void XMLCALL
xmlRelaxNGSetValidErrors(xmlRelaxNGValidCtxtPtr ctxt,
xmlRelaxNGValidityErrorFunc err,
xmlRelaxNGValidityWarningFunc warn,
void *ctx);
XMLPUBFUN int XMLCALL
xmlRelaxNGGetValidErrors(xmlRelaxNGValidCtxtPtr ctxt,
xmlRelaxNGValidityErrorFunc *err,
xmlRelaxNGValidityWarningFunc *warn,
void **ctx);
XMLPUBFUN void XMLCALL
xmlRelaxNGSetValidStructuredErrors(xmlRelaxNGValidCtxtPtr ctxt,
xmlStructuredErrorFunc serror, void *ctx);
XMLPUBFUN xmlRelaxNGValidCtxtPtr XMLCALL
xmlRelaxNGNewValidCtxt (xmlRelaxNGPtr schema);
XMLPUBFUN void XMLCALL
xmlRelaxNGFreeValidCtxt (xmlRelaxNGValidCtxtPtr ctxt);
XMLPUBFUN int XMLCALL
xmlRelaxNGValidateDoc (xmlRelaxNGValidCtxtPtr ctxt,
xmlDocPtr doc);
/*
* Interfaces for progressive validation when possible
*/
XMLPUBFUN int XMLCALL
xmlRelaxNGValidatePushElement (xmlRelaxNGValidCtxtPtr ctxt,
xmlDocPtr doc,
xmlNodePtr elem);
XMLPUBFUN int XMLCALL
xmlRelaxNGValidatePushCData (xmlRelaxNGValidCtxtPtr ctxt,
const xmlChar *data,
int len);
XMLPUBFUN int XMLCALL
xmlRelaxNGValidatePopElement (xmlRelaxNGValidCtxtPtr ctxt,
xmlDocPtr doc,
xmlNodePtr elem);
XMLPUBFUN int XMLCALL
xmlRelaxNGValidateFullElement (xmlRelaxNGValidCtxtPtr ctxt,
xmlDocPtr doc,
xmlNodePtr elem);
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_SCHEMAS_ENABLED */
#endif /* __XML_RELAX_NG__ */

@ -0,0 +1,958 @@
/*
* Summary: internal interfaces for XML Schemas
* Description: internal interfaces for the XML Schemas handling
* and schema validity checking
* The Schemas development is a Work In Progress.
* Some of those interfaces are not guaranteed to be API or ABI stable !
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_SCHEMA_INTERNALS_H__
#define __XML_SCHEMA_INTERNALS_H__
#include <libxml/xmlversion.h>
#ifdef LIBXML_SCHEMAS_ENABLED
#include <libxml/xmlregexp.h>
#include <libxml/hash.h>
#include <libxml/dict.h>
#ifdef __cplusplus
extern "C" {
#endif
typedef enum {
XML_SCHEMAS_UNKNOWN = 0,
XML_SCHEMAS_STRING = 1,
XML_SCHEMAS_NORMSTRING = 2,
XML_SCHEMAS_DECIMAL = 3,
XML_SCHEMAS_TIME = 4,
XML_SCHEMAS_GDAY = 5,
XML_SCHEMAS_GMONTH = 6,
XML_SCHEMAS_GMONTHDAY = 7,
XML_SCHEMAS_GYEAR = 8,
XML_SCHEMAS_GYEARMONTH = 9,
XML_SCHEMAS_DATE = 10,
XML_SCHEMAS_DATETIME = 11,
XML_SCHEMAS_DURATION = 12,
XML_SCHEMAS_FLOAT = 13,
XML_SCHEMAS_DOUBLE = 14,
XML_SCHEMAS_BOOLEAN = 15,
XML_SCHEMAS_TOKEN = 16,
XML_SCHEMAS_LANGUAGE = 17,
XML_SCHEMAS_NMTOKEN = 18,
XML_SCHEMAS_NMTOKENS = 19,
XML_SCHEMAS_NAME = 20,
XML_SCHEMAS_QNAME = 21,
XML_SCHEMAS_NCNAME = 22,
XML_SCHEMAS_ID = 23,
XML_SCHEMAS_IDREF = 24,
XML_SCHEMAS_IDREFS = 25,
XML_SCHEMAS_ENTITY = 26,
XML_SCHEMAS_ENTITIES = 27,
XML_SCHEMAS_NOTATION = 28,
XML_SCHEMAS_ANYURI = 29,
XML_SCHEMAS_INTEGER = 30,
XML_SCHEMAS_NPINTEGER = 31,
XML_SCHEMAS_NINTEGER = 32,
XML_SCHEMAS_NNINTEGER = 33,
XML_SCHEMAS_PINTEGER = 34,
XML_SCHEMAS_INT = 35,
XML_SCHEMAS_UINT = 36,
XML_SCHEMAS_LONG = 37,
XML_SCHEMAS_ULONG = 38,
XML_SCHEMAS_SHORT = 39,
XML_SCHEMAS_USHORT = 40,
XML_SCHEMAS_BYTE = 41,
XML_SCHEMAS_UBYTE = 42,
XML_SCHEMAS_HEXBINARY = 43,
XML_SCHEMAS_BASE64BINARY = 44,
XML_SCHEMAS_ANYTYPE = 45,
XML_SCHEMAS_ANYSIMPLETYPE = 46
} xmlSchemaValType;
/*
* XML Schemas defines multiple type of types.
*/
typedef enum {
XML_SCHEMA_TYPE_BASIC = 1, /* A built-in datatype */
XML_SCHEMA_TYPE_ANY,
XML_SCHEMA_TYPE_FACET,
XML_SCHEMA_TYPE_SIMPLE,
XML_SCHEMA_TYPE_COMPLEX,
XML_SCHEMA_TYPE_SEQUENCE = 6,
XML_SCHEMA_TYPE_CHOICE,
XML_SCHEMA_TYPE_ALL,
XML_SCHEMA_TYPE_SIMPLE_CONTENT,
XML_SCHEMA_TYPE_COMPLEX_CONTENT,
XML_SCHEMA_TYPE_UR,
XML_SCHEMA_TYPE_RESTRICTION,
XML_SCHEMA_TYPE_EXTENSION,
XML_SCHEMA_TYPE_ELEMENT,
XML_SCHEMA_TYPE_ATTRIBUTE,
XML_SCHEMA_TYPE_ATTRIBUTEGROUP,
XML_SCHEMA_TYPE_GROUP,
XML_SCHEMA_TYPE_NOTATION,
XML_SCHEMA_TYPE_LIST,
XML_SCHEMA_TYPE_UNION,
XML_SCHEMA_TYPE_ANY_ATTRIBUTE,
XML_SCHEMA_TYPE_IDC_UNIQUE,
XML_SCHEMA_TYPE_IDC_KEY,
XML_SCHEMA_TYPE_IDC_KEYREF,
XML_SCHEMA_TYPE_PARTICLE = 25,
XML_SCHEMA_TYPE_ATTRIBUTE_USE,
XML_SCHEMA_FACET_MININCLUSIVE = 1000,
XML_SCHEMA_FACET_MINEXCLUSIVE,
XML_SCHEMA_FACET_MAXINCLUSIVE,
XML_SCHEMA_FACET_MAXEXCLUSIVE,
XML_SCHEMA_FACET_TOTALDIGITS,
XML_SCHEMA_FACET_FRACTIONDIGITS,
XML_SCHEMA_FACET_PATTERN,
XML_SCHEMA_FACET_ENUMERATION,
XML_SCHEMA_FACET_WHITESPACE,
XML_SCHEMA_FACET_LENGTH,
XML_SCHEMA_FACET_MAXLENGTH,
XML_SCHEMA_FACET_MINLENGTH,
XML_SCHEMA_EXTRA_QNAMEREF = 2000,
XML_SCHEMA_EXTRA_ATTR_USE_PROHIB
} xmlSchemaTypeType;
typedef enum {
XML_SCHEMA_CONTENT_UNKNOWN = 0,
XML_SCHEMA_CONTENT_EMPTY = 1,
XML_SCHEMA_CONTENT_ELEMENTS,
XML_SCHEMA_CONTENT_MIXED,
XML_SCHEMA_CONTENT_SIMPLE,
XML_SCHEMA_CONTENT_MIXED_OR_ELEMENTS, /* Obsolete */
XML_SCHEMA_CONTENT_BASIC,
XML_SCHEMA_CONTENT_ANY
} xmlSchemaContentType;
typedef struct _xmlSchemaVal xmlSchemaVal;
typedef xmlSchemaVal *xmlSchemaValPtr;
typedef struct _xmlSchemaType xmlSchemaType;
typedef xmlSchemaType *xmlSchemaTypePtr;
typedef struct _xmlSchemaFacet xmlSchemaFacet;
typedef xmlSchemaFacet *xmlSchemaFacetPtr;
/**
* Annotation
*/
typedef struct _xmlSchemaAnnot xmlSchemaAnnot;
typedef xmlSchemaAnnot *xmlSchemaAnnotPtr;
struct _xmlSchemaAnnot {
struct _xmlSchemaAnnot *next;
xmlNodePtr content; /* the annotation */
};
/**
* XML_SCHEMAS_ANYATTR_SKIP:
*
* Skip unknown attribute from validation
* Obsolete, not used anymore.
*/
#define XML_SCHEMAS_ANYATTR_SKIP 1
/**
* XML_SCHEMAS_ANYATTR_LAX:
*
* Ignore validation non definition on attributes
* Obsolete, not used anymore.
*/
#define XML_SCHEMAS_ANYATTR_LAX 2
/**
* XML_SCHEMAS_ANYATTR_STRICT:
*
* Apply strict validation rules on attributes
* Obsolete, not used anymore.
*/
#define XML_SCHEMAS_ANYATTR_STRICT 3
/**
* XML_SCHEMAS_ANY_SKIP:
*
* Skip unknown attribute from validation
*/
#define XML_SCHEMAS_ANY_SKIP 1
/**
* XML_SCHEMAS_ANY_LAX:
*
* Used by wildcards.
* Validate if type found, don't worry if not found
*/
#define XML_SCHEMAS_ANY_LAX 2
/**
* XML_SCHEMAS_ANY_STRICT:
*
* Used by wildcards.
* Apply strict validation rules
*/
#define XML_SCHEMAS_ANY_STRICT 3
/**
* XML_SCHEMAS_ATTR_USE_PROHIBITED:
*
* Used by wildcards.
* The attribute is prohibited.
*/
#define XML_SCHEMAS_ATTR_USE_PROHIBITED 0
/**
* XML_SCHEMAS_ATTR_USE_REQUIRED:
*
* The attribute is required.
*/
#define XML_SCHEMAS_ATTR_USE_REQUIRED 1
/**
* XML_SCHEMAS_ATTR_USE_OPTIONAL:
*
* The attribute is optional.
*/
#define XML_SCHEMAS_ATTR_USE_OPTIONAL 2
/**
* XML_SCHEMAS_ATTR_GLOBAL:
*
* allow elements in no namespace
*/
#define XML_SCHEMAS_ATTR_GLOBAL 1 << 0
/**
* XML_SCHEMAS_ATTR_NSDEFAULT:
*
* allow elements in no namespace
*/
#define XML_SCHEMAS_ATTR_NSDEFAULT 1 << 7
/**
* XML_SCHEMAS_ATTR_INTERNAL_RESOLVED:
*
* this is set when the "type" and "ref" references
* have been resolved.
*/
#define XML_SCHEMAS_ATTR_INTERNAL_RESOLVED 1 << 8
/**
* XML_SCHEMAS_ATTR_FIXED:
*
* the attribute has a fixed value
*/
#define XML_SCHEMAS_ATTR_FIXED 1 << 9
/**
* xmlSchemaAttribute:
* An attribute definition.
*/
typedef struct _xmlSchemaAttribute xmlSchemaAttribute;
typedef xmlSchemaAttribute *xmlSchemaAttributePtr;
struct _xmlSchemaAttribute {
xmlSchemaTypeType type;
struct _xmlSchemaAttribute *next; /* the next attribute (not used?) */
const xmlChar *name; /* the name of the declaration */
const xmlChar *id; /* Deprecated; not used */
const xmlChar *ref; /* Deprecated; not used */
const xmlChar *refNs; /* Deprecated; not used */
const xmlChar *typeName; /* the local name of the type definition */
const xmlChar *typeNs; /* the ns URI of the type definition */
xmlSchemaAnnotPtr annot;
xmlSchemaTypePtr base; /* Deprecated; not used */
int occurs; /* Deprecated; not used */
const xmlChar *defValue; /* The initial value of the value constraint */
xmlSchemaTypePtr subtypes; /* the type definition */
xmlNodePtr node;
const xmlChar *targetNamespace;
int flags;
const xmlChar *refPrefix; /* Deprecated; not used */
xmlSchemaValPtr defVal; /* The compiled value constraint */
xmlSchemaAttributePtr refDecl; /* Deprecated; not used */
};
/**
* xmlSchemaAttributeLink:
* Used to build a list of attribute uses on complexType definitions.
* WARNING: Deprecated; not used.
*/
typedef struct _xmlSchemaAttributeLink xmlSchemaAttributeLink;
typedef xmlSchemaAttributeLink *xmlSchemaAttributeLinkPtr;
struct _xmlSchemaAttributeLink {
struct _xmlSchemaAttributeLink *next;/* the next attribute link ... */
struct _xmlSchemaAttribute *attr;/* the linked attribute */
};
/**
* XML_SCHEMAS_WILDCARD_COMPLETE:
*
* If the wildcard is complete.
*/
#define XML_SCHEMAS_WILDCARD_COMPLETE 1 << 0
/**
* xmlSchemaCharValueLink:
* Used to build a list of namespaces on wildcards.
*/
typedef struct _xmlSchemaWildcardNs xmlSchemaWildcardNs;
typedef xmlSchemaWildcardNs *xmlSchemaWildcardNsPtr;
struct _xmlSchemaWildcardNs {
struct _xmlSchemaWildcardNs *next;/* the next constraint link ... */
const xmlChar *value;/* the value */
};
/**
* xmlSchemaWildcard.
* A wildcard.
*/
typedef struct _xmlSchemaWildcard xmlSchemaWildcard;
typedef xmlSchemaWildcard *xmlSchemaWildcardPtr;
struct _xmlSchemaWildcard {
xmlSchemaTypeType type; /* The kind of type */
const xmlChar *id; /* Deprecated; not used */
xmlSchemaAnnotPtr annot;
xmlNodePtr node;
int minOccurs; /* Deprecated; not used */
int maxOccurs; /* Deprecated; not used */
int processContents;
int any; /* Indicates if the ns constraint is of ##any */
xmlSchemaWildcardNsPtr nsSet; /* The list of allowed namespaces */
xmlSchemaWildcardNsPtr negNsSet; /* The negated namespace */
int flags;
};
/**
* XML_SCHEMAS_ATTRGROUP_WILDCARD_BUILDED:
*
* The attribute wildcard has been already builded.
*/
#define XML_SCHEMAS_ATTRGROUP_WILDCARD_BUILDED 1 << 0
/**
* XML_SCHEMAS_ATTRGROUP_GLOBAL:
*
* The attribute wildcard has been already builded.
*/
#define XML_SCHEMAS_ATTRGROUP_GLOBAL 1 << 1
/**
* XML_SCHEMAS_ATTRGROUP_MARKED:
*
* Marks the attr group as marked; used for circular checks.
*/
#define XML_SCHEMAS_ATTRGROUP_MARKED 1 << 2
/**
* XML_SCHEMAS_ATTRGROUP_REDEFINED:
*
* The attr group was redefined.
*/
#define XML_SCHEMAS_ATTRGROUP_REDEFINED 1 << 3
/**
* XML_SCHEMAS_ATTRGROUP_HAS_REFS:
*
* Whether this attr. group contains attr. group references.
*/
#define XML_SCHEMAS_ATTRGROUP_HAS_REFS 1 << 4
/**
* An attribute group definition.
*
* xmlSchemaAttribute and xmlSchemaAttributeGroup start of structures
* must be kept similar
*/
typedef struct _xmlSchemaAttributeGroup xmlSchemaAttributeGroup;
typedef xmlSchemaAttributeGroup *xmlSchemaAttributeGroupPtr;
struct _xmlSchemaAttributeGroup {
xmlSchemaTypeType type; /* The kind of type */
struct _xmlSchemaAttribute *next;/* the next attribute if in a group ... */
const xmlChar *name;
const xmlChar *id;
const xmlChar *ref; /* Deprecated; not used */
const xmlChar *refNs; /* Deprecated; not used */
xmlSchemaAnnotPtr annot;
xmlSchemaAttributePtr attributes; /* Deprecated; not used */
xmlNodePtr node;
int flags;
xmlSchemaWildcardPtr attributeWildcard;
const xmlChar *refPrefix; /* Deprecated; not used */
xmlSchemaAttributeGroupPtr refItem; /* Deprecated; not used */
const xmlChar *targetNamespace;
void *attrUses;
};
/**
* xmlSchemaTypeLink:
* Used to build a list of types (e.g. member types of
* simpleType with variety "union").
*/
typedef struct _xmlSchemaTypeLink xmlSchemaTypeLink;
typedef xmlSchemaTypeLink *xmlSchemaTypeLinkPtr;
struct _xmlSchemaTypeLink {
struct _xmlSchemaTypeLink *next;/* the next type link ... */
xmlSchemaTypePtr type;/* the linked type */
};
/**
* xmlSchemaFacetLink:
* Used to build a list of facets.
*/
typedef struct _xmlSchemaFacetLink xmlSchemaFacetLink;
typedef xmlSchemaFacetLink *xmlSchemaFacetLinkPtr;
struct _xmlSchemaFacetLink {
struct _xmlSchemaFacetLink *next;/* the next facet link ... */
xmlSchemaFacetPtr facet;/* the linked facet */
};
/**
* XML_SCHEMAS_TYPE_MIXED:
*
* the element content type is mixed
*/
#define XML_SCHEMAS_TYPE_MIXED 1 << 0
/**
* XML_SCHEMAS_TYPE_DERIVATION_METHOD_EXTENSION:
*
* the simple or complex type has a derivation method of "extension".
*/
#define XML_SCHEMAS_TYPE_DERIVATION_METHOD_EXTENSION 1 << 1
/**
* XML_SCHEMAS_TYPE_DERIVATION_METHOD_RESTRICTION:
*
* the simple or complex type has a derivation method of "restriction".
*/
#define XML_SCHEMAS_TYPE_DERIVATION_METHOD_RESTRICTION 1 << 2
/**
* XML_SCHEMAS_TYPE_GLOBAL:
*
* the type is global
*/
#define XML_SCHEMAS_TYPE_GLOBAL 1 << 3
/**
* XML_SCHEMAS_TYPE_OWNED_ATTR_WILDCARD:
*
* the complexType owns an attribute wildcard, i.e.
* it can be freed by the complexType
*/
#define XML_SCHEMAS_TYPE_OWNED_ATTR_WILDCARD 1 << 4 /* Obsolete. */
/**
* XML_SCHEMAS_TYPE_VARIETY_ABSENT:
*
* the simpleType has a variety of "absent".
* TODO: Actually not necessary :-/, since if
* none of the variety flags occur then it's
* automatically absent.
*/
#define XML_SCHEMAS_TYPE_VARIETY_ABSENT 1 << 5
/**
* XML_SCHEMAS_TYPE_VARIETY_LIST:
*
* the simpleType has a variety of "list".
*/
#define XML_SCHEMAS_TYPE_VARIETY_LIST 1 << 6
/**
* XML_SCHEMAS_TYPE_VARIETY_UNION:
*
* the simpleType has a variety of "union".
*/
#define XML_SCHEMAS_TYPE_VARIETY_UNION 1 << 7
/**
* XML_SCHEMAS_TYPE_VARIETY_ATOMIC:
*
* the simpleType has a variety of "union".
*/
#define XML_SCHEMAS_TYPE_VARIETY_ATOMIC 1 << 8
/**
* XML_SCHEMAS_TYPE_FINAL_EXTENSION:
*
* the complexType has a final of "extension".
*/
#define XML_SCHEMAS_TYPE_FINAL_EXTENSION 1 << 9
/**
* XML_SCHEMAS_TYPE_FINAL_RESTRICTION:
*
* the simpleType/complexType has a final of "restriction".
*/
#define XML_SCHEMAS_TYPE_FINAL_RESTRICTION 1 << 10
/**
* XML_SCHEMAS_TYPE_FINAL_LIST:
*
* the simpleType has a final of "list".
*/
#define XML_SCHEMAS_TYPE_FINAL_LIST 1 << 11
/**
* XML_SCHEMAS_TYPE_FINAL_UNION:
*
* the simpleType has a final of "union".
*/
#define XML_SCHEMAS_TYPE_FINAL_UNION 1 << 12
/**
* XML_SCHEMAS_TYPE_FINAL_DEFAULT:
*
* the simpleType has a final of "default".
*/
#define XML_SCHEMAS_TYPE_FINAL_DEFAULT 1 << 13
/**
* XML_SCHEMAS_TYPE_BUILTIN_PRIMITIVE:
*
* Marks the item as a builtin primitive.
*/
#define XML_SCHEMAS_TYPE_BUILTIN_PRIMITIVE 1 << 14
/**
* XML_SCHEMAS_TYPE_MARKED:
*
* Marks the item as marked; used for circular checks.
*/
#define XML_SCHEMAS_TYPE_MARKED 1 << 16
/**
* XML_SCHEMAS_TYPE_BLOCK_DEFAULT:
*
* the complexType did not specify 'block' so use the default of the
* <schema> item.
*/
#define XML_SCHEMAS_TYPE_BLOCK_DEFAULT 1 << 17
/**
* XML_SCHEMAS_TYPE_BLOCK_EXTENSION:
*
* the complexType has a 'block' of "extension".
*/
#define XML_SCHEMAS_TYPE_BLOCK_EXTENSION 1 << 18
/**
* XML_SCHEMAS_TYPE_BLOCK_RESTRICTION:
*
* the complexType has a 'block' of "restriction".
*/
#define XML_SCHEMAS_TYPE_BLOCK_RESTRICTION 1 << 19
/**
* XML_SCHEMAS_TYPE_ABSTRACT:
*
* the simple/complexType is abstract.
*/
#define XML_SCHEMAS_TYPE_ABSTRACT 1 << 20
/**
* XML_SCHEMAS_TYPE_FACETSNEEDVALUE:
*
* indicates if the facets need a computed value
*/
#define XML_SCHEMAS_TYPE_FACETSNEEDVALUE 1 << 21
/**
* XML_SCHEMAS_TYPE_INTERNAL_RESOLVED:
*
* indicates that the type was typefixed
*/
#define XML_SCHEMAS_TYPE_INTERNAL_RESOLVED 1 << 22
/**
* XML_SCHEMAS_TYPE_INTERNAL_INVALID:
*
* indicates that the type is invalid
*/
#define XML_SCHEMAS_TYPE_INTERNAL_INVALID 1 << 23
/**
* XML_SCHEMAS_TYPE_WHITESPACE_PRESERVE:
*
* a whitespace-facet value of "preserve"
*/
#define XML_SCHEMAS_TYPE_WHITESPACE_PRESERVE 1 << 24
/**
* XML_SCHEMAS_TYPE_WHITESPACE_REPLACE:
*
* a whitespace-facet value of "replace"
*/
#define XML_SCHEMAS_TYPE_WHITESPACE_REPLACE 1 << 25
/**
* XML_SCHEMAS_TYPE_WHITESPACE_COLLAPSE:
*
* a whitespace-facet value of "collapse"
*/
#define XML_SCHEMAS_TYPE_WHITESPACE_COLLAPSE 1 << 26
/**
* XML_SCHEMAS_TYPE_HAS_FACETS:
*
* has facets
*/
#define XML_SCHEMAS_TYPE_HAS_FACETS 1 << 27
/**
* XML_SCHEMAS_TYPE_NORMVALUENEEDED:
*
* indicates if the facets (pattern) need a normalized value
*/
#define XML_SCHEMAS_TYPE_NORMVALUENEEDED 1 << 28
/**
* XML_SCHEMAS_TYPE_FIXUP_1:
*
* First stage of fixup was done.
*/
#define XML_SCHEMAS_TYPE_FIXUP_1 1 << 29
/**
* XML_SCHEMAS_TYPE_REDEFINED:
*
* The type was redefined.
*/
#define XML_SCHEMAS_TYPE_REDEFINED 1 << 30
/**
* XML_SCHEMAS_TYPE_REDEFINING:
*
* The type redefines an other type.
*/
/* #define XML_SCHEMAS_TYPE_REDEFINING 1 << 31 */
/**
* _xmlSchemaType:
*
* Schemas type definition.
*/
struct _xmlSchemaType {
xmlSchemaTypeType type; /* The kind of type */
struct _xmlSchemaType *next; /* the next type if in a sequence ... */
const xmlChar *name;
const xmlChar *id ; /* Deprecated; not used */
const xmlChar *ref; /* Deprecated; not used */
const xmlChar *refNs; /* Deprecated; not used */
xmlSchemaAnnotPtr annot;
xmlSchemaTypePtr subtypes;
xmlSchemaAttributePtr attributes; /* Deprecated; not used */
xmlNodePtr node;
int minOccurs; /* Deprecated; not used */
int maxOccurs; /* Deprecated; not used */
int flags;
xmlSchemaContentType contentType;
const xmlChar *base; /* Base type's local name */
const xmlChar *baseNs; /* Base type's target namespace */
xmlSchemaTypePtr baseType; /* The base type component */
xmlSchemaFacetPtr facets; /* Local facets */
struct _xmlSchemaType *redef; /* Deprecated; not used */
int recurse; /* Obsolete */
xmlSchemaAttributeLinkPtr *attributeUses; /* Deprecated; not used */
xmlSchemaWildcardPtr attributeWildcard;
int builtInType; /* Type of built-in types. */
xmlSchemaTypeLinkPtr memberTypes; /* member-types if a union type. */
xmlSchemaFacetLinkPtr facetSet; /* All facets (incl. inherited) */
const xmlChar *refPrefix; /* Deprecated; not used */
xmlSchemaTypePtr contentTypeDef; /* Used for the simple content of complex types.
Could we use @subtypes for this? */
xmlRegexpPtr contModel; /* Holds the automaton of the content model */
const xmlChar *targetNamespace;
void *attrUses;
};
/*
* xmlSchemaElement:
* An element definition.
*
* xmlSchemaType, xmlSchemaFacet and xmlSchemaElement start of
* structures must be kept similar
*/
/**
* XML_SCHEMAS_ELEM_NILLABLE:
*
* the element is nillable
*/
#define XML_SCHEMAS_ELEM_NILLABLE 1 << 0
/**
* XML_SCHEMAS_ELEM_GLOBAL:
*
* the element is global
*/
#define XML_SCHEMAS_ELEM_GLOBAL 1 << 1
/**
* XML_SCHEMAS_ELEM_DEFAULT:
*
* the element has a default value
*/
#define XML_SCHEMAS_ELEM_DEFAULT 1 << 2
/**
* XML_SCHEMAS_ELEM_FIXED:
*
* the element has a fixed value
*/
#define XML_SCHEMAS_ELEM_FIXED 1 << 3
/**
* XML_SCHEMAS_ELEM_ABSTRACT:
*
* the element is abstract
*/
#define XML_SCHEMAS_ELEM_ABSTRACT 1 << 4
/**
* XML_SCHEMAS_ELEM_TOPLEVEL:
*
* the element is top level
* obsolete: use XML_SCHEMAS_ELEM_GLOBAL instead
*/
#define XML_SCHEMAS_ELEM_TOPLEVEL 1 << 5
/**
* XML_SCHEMAS_ELEM_REF:
*
* the element is a reference to a type
*/
#define XML_SCHEMAS_ELEM_REF 1 << 6
/**
* XML_SCHEMAS_ELEM_NSDEFAULT:
*
* allow elements in no namespace
* Obsolete, not used anymore.
*/
#define XML_SCHEMAS_ELEM_NSDEFAULT 1 << 7
/**
* XML_SCHEMAS_ELEM_INTERNAL_RESOLVED:
*
* this is set when "type", "ref", "substitutionGroup"
* references have been resolved.
*/
#define XML_SCHEMAS_ELEM_INTERNAL_RESOLVED 1 << 8
/**
* XML_SCHEMAS_ELEM_CIRCULAR:
*
* a helper flag for the search of circular references.
*/
#define XML_SCHEMAS_ELEM_CIRCULAR 1 << 9
/**
* XML_SCHEMAS_ELEM_BLOCK_ABSENT:
*
* the "block" attribute is absent
*/
#define XML_SCHEMAS_ELEM_BLOCK_ABSENT 1 << 10
/**
* XML_SCHEMAS_ELEM_BLOCK_EXTENSION:
*
* disallowed substitutions are absent
*/
#define XML_SCHEMAS_ELEM_BLOCK_EXTENSION 1 << 11
/**
* XML_SCHEMAS_ELEM_BLOCK_RESTRICTION:
*
* disallowed substitutions: "restriction"
*/
#define XML_SCHEMAS_ELEM_BLOCK_RESTRICTION 1 << 12
/**
* XML_SCHEMAS_ELEM_BLOCK_SUBSTITUTION:
*
* disallowed substitutions: "substituion"
*/
#define XML_SCHEMAS_ELEM_BLOCK_SUBSTITUTION 1 << 13
/**
* XML_SCHEMAS_ELEM_FINAL_ABSENT:
*
* substitution group exclusions are absent
*/
#define XML_SCHEMAS_ELEM_FINAL_ABSENT 1 << 14
/**
* XML_SCHEMAS_ELEM_FINAL_EXTENSION:
*
* substitution group exclusions: "extension"
*/
#define XML_SCHEMAS_ELEM_FINAL_EXTENSION 1 << 15
/**
* XML_SCHEMAS_ELEM_FINAL_RESTRICTION:
*
* substitution group exclusions: "restriction"
*/
#define XML_SCHEMAS_ELEM_FINAL_RESTRICTION 1 << 16
/**
* XML_SCHEMAS_ELEM_SUBST_GROUP_HEAD:
*
* the declaration is a substitution group head
*/
#define XML_SCHEMAS_ELEM_SUBST_GROUP_HEAD 1 << 17
/**
* XML_SCHEMAS_ELEM_INTERNAL_CHECKED:
*
* this is set when the elem decl has been checked against
* all constraints
*/
#define XML_SCHEMAS_ELEM_INTERNAL_CHECKED 1 << 18
typedef struct _xmlSchemaElement xmlSchemaElement;
typedef xmlSchemaElement *xmlSchemaElementPtr;
struct _xmlSchemaElement {
xmlSchemaTypeType type; /* The kind of type */
struct _xmlSchemaType *next; /* Not used? */
const xmlChar *name;
const xmlChar *id; /* Deprecated; not used */
const xmlChar *ref; /* Deprecated; not used */
const xmlChar *refNs; /* Deprecated; not used */
xmlSchemaAnnotPtr annot;
xmlSchemaTypePtr subtypes; /* the type definition */
xmlSchemaAttributePtr attributes;
xmlNodePtr node;
int minOccurs; /* Deprecated; not used */
int maxOccurs; /* Deprecated; not used */
int flags;
const xmlChar *targetNamespace;
const xmlChar *namedType;
const xmlChar *namedTypeNs;
const xmlChar *substGroup;
const xmlChar *substGroupNs;
const xmlChar *scope;
const xmlChar *value; /* The original value of the value constraint. */
struct _xmlSchemaElement *refDecl; /* This will now be used for the
substitution group affiliation */
xmlRegexpPtr contModel; /* Obsolete for WXS, maybe used for RelaxNG */
xmlSchemaContentType contentType;
const xmlChar *refPrefix; /* Deprecated; not used */
xmlSchemaValPtr defVal; /* The compiled value contraint. */
void *idcs; /* The identity-constraint defs */
};
/*
* XML_SCHEMAS_FACET_UNKNOWN:
*
* unknown facet handling
*/
#define XML_SCHEMAS_FACET_UNKNOWN 0
/*
* XML_SCHEMAS_FACET_PRESERVE:
*
* preserve the type of the facet
*/
#define XML_SCHEMAS_FACET_PRESERVE 1
/*
* XML_SCHEMAS_FACET_REPLACE:
*
* replace the type of the facet
*/
#define XML_SCHEMAS_FACET_REPLACE 2
/*
* XML_SCHEMAS_FACET_COLLAPSE:
*
* collapse the types of the facet
*/
#define XML_SCHEMAS_FACET_COLLAPSE 3
/**
* A facet definition.
*/
struct _xmlSchemaFacet {
xmlSchemaTypeType type; /* The kind of type */
struct _xmlSchemaFacet *next;/* the next type if in a sequence ... */
const xmlChar *value; /* The original value */
const xmlChar *id; /* Obsolete */
xmlSchemaAnnotPtr annot;
xmlNodePtr node;
int fixed; /* XML_SCHEMAS_FACET_PRESERVE, etc. */
int whitespace;
xmlSchemaValPtr val; /* The compiled value */
xmlRegexpPtr regexp; /* The regex for patterns */
};
/**
* A notation definition.
*/
typedef struct _xmlSchemaNotation xmlSchemaNotation;
typedef xmlSchemaNotation *xmlSchemaNotationPtr;
struct _xmlSchemaNotation {
xmlSchemaTypeType type; /* The kind of type */
const xmlChar *name;
xmlSchemaAnnotPtr annot;
const xmlChar *identifier;
const xmlChar *targetNamespace;
};
/*
* TODO: Actually all those flags used for the schema should sit
* on the schema parser context, since they are used only
* during parsing an XML schema document, and not available
* on the component level as per spec.
*/
/**
* XML_SCHEMAS_QUALIF_ELEM:
*
* Reflects elementFormDefault == qualified in
* an XML schema document.
*/
#define XML_SCHEMAS_QUALIF_ELEM 1 << 0
/**
* XML_SCHEMAS_QUALIF_ATTR:
*
* Reflects attributeFormDefault == qualified in
* an XML schema document.
*/
#define XML_SCHEMAS_QUALIF_ATTR 1 << 1
/**
* XML_SCHEMAS_FINAL_DEFAULT_EXTENSION:
*
* the schema has "extension" in the set of finalDefault.
*/
#define XML_SCHEMAS_FINAL_DEFAULT_EXTENSION 1 << 2
/**
* XML_SCHEMAS_FINAL_DEFAULT_RESTRICTION:
*
* the schema has "restriction" in the set of finalDefault.
*/
#define XML_SCHEMAS_FINAL_DEFAULT_RESTRICTION 1 << 3
/**
* XML_SCHEMAS_FINAL_DEFAULT_LIST:
*
* the cshema has "list" in the set of finalDefault.
*/
#define XML_SCHEMAS_FINAL_DEFAULT_LIST 1 << 4
/**
* XML_SCHEMAS_FINAL_DEFAULT_UNION:
*
* the schema has "union" in the set of finalDefault.
*/
#define XML_SCHEMAS_FINAL_DEFAULT_UNION 1 << 5
/**
* XML_SCHEMAS_BLOCK_DEFAULT_EXTENSION:
*
* the schema has "extension" in the set of blockDefault.
*/
#define XML_SCHEMAS_BLOCK_DEFAULT_EXTENSION 1 << 6
/**
* XML_SCHEMAS_BLOCK_DEFAULT_RESTRICTION:
*
* the schema has "restriction" in the set of blockDefault.
*/
#define XML_SCHEMAS_BLOCK_DEFAULT_RESTRICTION 1 << 7
/**
* XML_SCHEMAS_BLOCK_DEFAULT_SUBSTITUTION:
*
* the schema has "substitution" in the set of blockDefault.
*/
#define XML_SCHEMAS_BLOCK_DEFAULT_SUBSTITUTION 1 << 8
/**
* XML_SCHEMAS_INCLUDING_CONVERT_NS:
*
* the schema is currently including an other schema with
* no target namespace.
*/
#define XML_SCHEMAS_INCLUDING_CONVERT_NS 1 << 9
/**
* _xmlSchema:
*
* A Schemas definition
*/
struct _xmlSchema {
const xmlChar *name; /* schema name */
const xmlChar *targetNamespace; /* the target namespace */
const xmlChar *version;
const xmlChar *id; /* Obsolete */
xmlDocPtr doc;
xmlSchemaAnnotPtr annot;
int flags;
xmlHashTablePtr typeDecl;
xmlHashTablePtr attrDecl;
xmlHashTablePtr attrgrpDecl;
xmlHashTablePtr elemDecl;
xmlHashTablePtr notaDecl;
xmlHashTablePtr schemasImports;
void *_private; /* unused by the library for users or bindings */
xmlHashTablePtr groupDecl;
xmlDictPtr dict;
void *includes; /* the includes, this is opaque for now */
int preserve; /* whether to free the document */
int counter; /* used to give ononymous components unique names */
xmlHashTablePtr idcDef; /* All identity-constraint defs. */
void *volatiles; /* Obsolete */
};
XMLPUBFUN void XMLCALL xmlSchemaFreeType (xmlSchemaTypePtr type);
XMLPUBFUN void XMLCALL xmlSchemaFreeWildcard(xmlSchemaWildcardPtr wildcard);
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_SCHEMAS_ENABLED */
#endif /* __XML_SCHEMA_INTERNALS_H__ */

@ -0,0 +1,142 @@
/*
* Summary: XML Schemastron implementation
* Description: interface to the XML Schematron validity checking.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_SCHEMATRON_H__
#define __XML_SCHEMATRON_H__
#include <libxml/xmlversion.h>
#ifdef LIBXML_SCHEMATRON_ENABLED
#include <libxml/tree.h>
#ifdef __cplusplus
extern "C" {
#endif
typedef enum {
XML_SCHEMATRON_OUT_QUIET = 1 << 0, /* quiet no report */
XML_SCHEMATRON_OUT_TEXT = 1 << 1, /* build a textual report */
XML_SCHEMATRON_OUT_XML = 1 << 2, /* output SVRL */
XML_SCHEMATRON_OUT_ERROR = 1 << 3, /* output via xmlStructuredErrorFunc */
XML_SCHEMATRON_OUT_FILE = 1 << 8, /* output to a file descriptor */
XML_SCHEMATRON_OUT_BUFFER = 1 << 9, /* output to a buffer */
XML_SCHEMATRON_OUT_IO = 1 << 10 /* output to I/O mechanism */
} xmlSchematronValidOptions;
/**
* The schemas related types are kept internal
*/
typedef struct _xmlSchematron xmlSchematron;
typedef xmlSchematron *xmlSchematronPtr;
/**
* xmlSchematronValidityErrorFunc:
* @ctx: the validation context
* @msg: the message
* @...: extra arguments
*
* Signature of an error callback from a Schematron validation
*/
typedef void (*xmlSchematronValidityErrorFunc) (void *ctx, const char *msg, ...);
/**
* xmlSchematronValidityWarningFunc:
* @ctx: the validation context
* @msg: the message
* @...: extra arguments
*
* Signature of a warning callback from a Schematron validation
*/
typedef void (*xmlSchematronValidityWarningFunc) (void *ctx, const char *msg, ...);
/**
* A schemas validation context
*/
typedef struct _xmlSchematronParserCtxt xmlSchematronParserCtxt;
typedef xmlSchematronParserCtxt *xmlSchematronParserCtxtPtr;
typedef struct _xmlSchematronValidCtxt xmlSchematronValidCtxt;
typedef xmlSchematronValidCtxt *xmlSchematronValidCtxtPtr;
/*
* Interfaces for parsing.
*/
XMLPUBFUN xmlSchematronParserCtxtPtr XMLCALL
xmlSchematronNewParserCtxt (const char *URL);
XMLPUBFUN xmlSchematronParserCtxtPtr XMLCALL
xmlSchematronNewMemParserCtxt(const char *buffer,
int size);
XMLPUBFUN xmlSchematronParserCtxtPtr XMLCALL
xmlSchematronNewDocParserCtxt(xmlDocPtr doc);
XMLPUBFUN void XMLCALL
xmlSchematronFreeParserCtxt (xmlSchematronParserCtxtPtr ctxt);
/*****
XMLPUBFUN void XMLCALL
xmlSchematronSetParserErrors(xmlSchematronParserCtxtPtr ctxt,
xmlSchematronValidityErrorFunc err,
xmlSchematronValidityWarningFunc warn,
void *ctx);
XMLPUBFUN int XMLCALL
xmlSchematronGetParserErrors(xmlSchematronParserCtxtPtr ctxt,
xmlSchematronValidityErrorFunc * err,
xmlSchematronValidityWarningFunc * warn,
void **ctx);
XMLPUBFUN int XMLCALL
xmlSchematronIsValid (xmlSchematronValidCtxtPtr ctxt);
*****/
XMLPUBFUN xmlSchematronPtr XMLCALL
xmlSchematronParse (xmlSchematronParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlSchematronFree (xmlSchematronPtr schema);
/*
* Interfaces for validating
*/
XMLPUBFUN void XMLCALL
xmlSchematronSetValidStructuredErrors(
xmlSchematronValidCtxtPtr ctxt,
xmlStructuredErrorFunc serror,
void *ctx);
/******
XMLPUBFUN void XMLCALL
xmlSchematronSetValidErrors (xmlSchematronValidCtxtPtr ctxt,
xmlSchematronValidityErrorFunc err,
xmlSchematronValidityWarningFunc warn,
void *ctx);
XMLPUBFUN int XMLCALL
xmlSchematronGetValidErrors (xmlSchematronValidCtxtPtr ctxt,
xmlSchematronValidityErrorFunc *err,
xmlSchematronValidityWarningFunc *warn,
void **ctx);
XMLPUBFUN int XMLCALL
xmlSchematronSetValidOptions(xmlSchematronValidCtxtPtr ctxt,
int options);
XMLPUBFUN int XMLCALL
xmlSchematronValidCtxtGetOptions(xmlSchematronValidCtxtPtr ctxt);
XMLPUBFUN int XMLCALL
xmlSchematronValidateOneElement (xmlSchematronValidCtxtPtr ctxt,
xmlNodePtr elem);
*******/
XMLPUBFUN xmlSchematronValidCtxtPtr XMLCALL
xmlSchematronNewValidCtxt (xmlSchematronPtr schema,
int options);
XMLPUBFUN void XMLCALL
xmlSchematronFreeValidCtxt (xmlSchematronValidCtxtPtr ctxt);
XMLPUBFUN int XMLCALL
xmlSchematronValidateDoc (xmlSchematronValidCtxtPtr ctxt,
xmlDocPtr instance);
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_SCHEMATRON_ENABLED */
#endif /* __XML_SCHEMATRON_H__ */

@ -0,0 +1,84 @@
/**
* Summary: interfaces for thread handling
* Description: set of generic threading related routines
* should work with pthreads, Windows native or TLS threads
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_THREADS_H__
#define __XML_THREADS_H__
#include <libxml/xmlversion.h>
#ifdef __cplusplus
extern "C" {
#endif
/*
* xmlMutex are a simple mutual exception locks.
*/
typedef struct _xmlMutex xmlMutex;
typedef xmlMutex *xmlMutexPtr;
/*
* xmlRMutex are reentrant mutual exception locks.
*/
typedef struct _xmlRMutex xmlRMutex;
typedef xmlRMutex *xmlRMutexPtr;
#ifdef __cplusplus
}
#endif
#include <libxml/globals.h>
#ifdef __cplusplus
extern "C" {
#endif
XMLPUBFUN xmlMutexPtr XMLCALL
xmlNewMutex (void);
XMLPUBFUN void XMLCALL
xmlMutexLock (xmlMutexPtr tok);
XMLPUBFUN void XMLCALL
xmlMutexUnlock (xmlMutexPtr tok);
XMLPUBFUN void XMLCALL
xmlFreeMutex (xmlMutexPtr tok);
XMLPUBFUN xmlRMutexPtr XMLCALL
xmlNewRMutex (void);
XMLPUBFUN void XMLCALL
xmlRMutexLock (xmlRMutexPtr tok);
XMLPUBFUN void XMLCALL
xmlRMutexUnlock (xmlRMutexPtr tok);
XMLPUBFUN void XMLCALL
xmlFreeRMutex (xmlRMutexPtr tok);
/*
* Library wide APIs.
*/
XMLPUBFUN void XMLCALL
xmlInitThreads (void);
XMLPUBFUN void XMLCALL
xmlLockLibrary (void);
XMLPUBFUN void XMLCALL
xmlUnlockLibrary(void);
XMLPUBFUN int XMLCALL
xmlGetThreadId (void);
XMLPUBFUN int XMLCALL
xmlIsMainThread (void);
XMLPUBFUN void XMLCALL
xmlCleanupThreads(void);
XMLPUBFUN xmlGlobalStatePtr XMLCALL
xmlGetGlobalState(void);
#if defined(HAVE_WIN32_THREADS) && !defined(HAVE_COMPILER_TLS) && defined(LIBXML_STATIC_FOR_DLL)
int XMLCALL xmlDllMain(void *hinstDLL, unsigned long fdwReason, void *lpvReserved);
#endif
#ifdef __cplusplus
}
#endif
#endif /* __XML_THREADS_H__ */

File diff suppressed because it is too large Load Diff

@ -0,0 +1,94 @@
/**
* Summary: library of generic URI related routines
* Description: library of generic URI related routines
* Implements RFC 2396
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_URI_H__
#define __XML_URI_H__
#include <libxml/xmlversion.h>
#include <libxml/tree.h>
#ifdef __cplusplus
extern "C" {
#endif
/**
* xmlURI:
*
* A parsed URI reference. This is a struct containing the various fields
* as described in RFC 2396 but separated for further processing.
*
* Note: query is a deprecated field which is incorrectly unescaped.
* query_raw takes precedence over query if the former is set.
* See: http://mail.gnome.org/archives/xml/2007-April/thread.html#00127
*/
typedef struct _xmlURI xmlURI;
typedef xmlURI *xmlURIPtr;
struct _xmlURI {
char *scheme; /* the URI scheme */
char *opaque; /* opaque part */
char *authority; /* the authority part */
char *server; /* the server part */
char *user; /* the user part */
int port; /* the port number */
char *path; /* the path string */
char *query; /* the query string (deprecated - use with caution) */
char *fragment; /* the fragment identifier */
int cleanup; /* parsing potentially unclean URI */
char *query_raw; /* the query string (as it appears in the URI) */
};
/*
* This function is in tree.h:
* xmlChar * xmlNodeGetBase (xmlDocPtr doc,
* xmlNodePtr cur);
*/
XMLPUBFUN xmlURIPtr XMLCALL
xmlCreateURI (void);
XMLPUBFUN xmlChar * XMLCALL
xmlBuildURI (const xmlChar *URI,
const xmlChar *base);
XMLPUBFUN xmlChar * XMLCALL
xmlBuildRelativeURI (const xmlChar *URI,
const xmlChar *base);
XMLPUBFUN xmlURIPtr XMLCALL
xmlParseURI (const char *str);
XMLPUBFUN xmlURIPtr XMLCALL
xmlParseURIRaw (const char *str,
int raw);
XMLPUBFUN int XMLCALL
xmlParseURIReference (xmlURIPtr uri,
const char *str);
XMLPUBFUN xmlChar * XMLCALL
xmlSaveUri (xmlURIPtr uri);
XMLPUBFUN void XMLCALL
xmlPrintURI (FILE *stream,
xmlURIPtr uri);
XMLPUBFUN xmlChar * XMLCALL
xmlURIEscapeStr (const xmlChar *str,
const xmlChar *list);
XMLPUBFUN char * XMLCALL
xmlURIUnescapeString (const char *str,
int len,
char *target);
XMLPUBFUN int XMLCALL
xmlNormalizeURIPath (char *path);
XMLPUBFUN xmlChar * XMLCALL
xmlURIEscape (const xmlChar *str);
XMLPUBFUN void XMLCALL
xmlFreeURI (xmlURIPtr uri);
XMLPUBFUN xmlChar* XMLCALL
xmlCanonicPath (const xmlChar *path);
XMLPUBFUN xmlChar* XMLCALL
xmlPathToURI (const xmlChar *path);
#ifdef __cplusplus
}
#endif
#endif /* __XML_URI_H__ */

@ -0,0 +1,458 @@
/*
* Summary: The DTD validation
* Description: API for the DTD handling and the validity checking
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_VALID_H__
#define __XML_VALID_H__
#include <libxml/xmlversion.h>
#include <libxml/xmlerror.h>
#include <libxml/tree.h>
#include <libxml/list.h>
#include <libxml/xmlautomata.h>
#include <libxml/xmlregexp.h>
#ifdef __cplusplus
extern "C" {
#endif
/*
* Validation state added for non-determinist content model.
*/
typedef struct _xmlValidState xmlValidState;
typedef xmlValidState *xmlValidStatePtr;
/**
* xmlValidityErrorFunc:
* @ctx: usually an xmlValidCtxtPtr to a validity error context,
* but comes from ctxt->userData (which normally contains such
* a pointer); ctxt->userData can be changed by the user.
* @msg: the string to format *printf like vararg
* @...: remaining arguments to the format
*
* Callback called when a validity error is found. This is a message
* oriented function similar to an *printf function.
*/
typedef void (XMLCDECL *xmlValidityErrorFunc) (void *ctx,
const char *msg,
...) LIBXML_ATTR_FORMAT(2,3);
/**
* xmlValidityWarningFunc:
* @ctx: usually an xmlValidCtxtPtr to a validity error context,
* but comes from ctxt->userData (which normally contains such
* a pointer); ctxt->userData can be changed by the user.
* @msg: the string to format *printf like vararg
* @...: remaining arguments to the format
*
* Callback called when a validity warning is found. This is a message
* oriented function similar to an *printf function.
*/
typedef void (XMLCDECL *xmlValidityWarningFunc) (void *ctx,
const char *msg,
...) LIBXML_ATTR_FORMAT(2,3);
#ifdef IN_LIBXML
/**
* XML_CTXT_FINISH_DTD_0:
*
* Special value for finishDtd field when embedded in an xmlParserCtxt
*/
#define XML_CTXT_FINISH_DTD_0 0xabcd1234
/**
* XML_CTXT_FINISH_DTD_1:
*
* Special value for finishDtd field when embedded in an xmlParserCtxt
*/
#define XML_CTXT_FINISH_DTD_1 0xabcd1235
#endif
/*
* xmlValidCtxt:
* An xmlValidCtxt is used for error reporting when validating.
*/
typedef struct _xmlValidCtxt xmlValidCtxt;
typedef xmlValidCtxt *xmlValidCtxtPtr;
struct _xmlValidCtxt {
void *userData; /* user specific data block */
xmlValidityErrorFunc error; /* the callback in case of errors */
xmlValidityWarningFunc warning; /* the callback in case of warning */
/* Node analysis stack used when validating within entities */
xmlNodePtr node; /* Current parsed Node */
int nodeNr; /* Depth of the parsing stack */
int nodeMax; /* Max depth of the parsing stack */
xmlNodePtr *nodeTab; /* array of nodes */
unsigned int finishDtd; /* finished validating the Dtd ? */
xmlDocPtr doc; /* the document */
int valid; /* temporary validity check result */
/* state state used for non-determinist content validation */
xmlValidState *vstate; /* current state */
int vstateNr; /* Depth of the validation stack */
int vstateMax; /* Max depth of the validation stack */
xmlValidState *vstateTab; /* array of validation states */
#ifdef LIBXML_REGEXP_ENABLED
xmlAutomataPtr am; /* the automata */
xmlAutomataStatePtr state; /* used to build the automata */
#else
void *am;
void *state;
#endif
};
/*
* ALL notation declarations are stored in a table.
* There is one table per DTD.
*/
typedef struct _xmlHashTable xmlNotationTable;
typedef xmlNotationTable *xmlNotationTablePtr;
/*
* ALL element declarations are stored in a table.
* There is one table per DTD.
*/
typedef struct _xmlHashTable xmlElementTable;
typedef xmlElementTable *xmlElementTablePtr;
/*
* ALL attribute declarations are stored in a table.
* There is one table per DTD.
*/
typedef struct _xmlHashTable xmlAttributeTable;
typedef xmlAttributeTable *xmlAttributeTablePtr;
/*
* ALL IDs attributes are stored in a table.
* There is one table per document.
*/
typedef struct _xmlHashTable xmlIDTable;
typedef xmlIDTable *xmlIDTablePtr;
/*
* ALL Refs attributes are stored in a table.
* There is one table per document.
*/
typedef struct _xmlHashTable xmlRefTable;
typedef xmlRefTable *xmlRefTablePtr;
/* Notation */
XMLPUBFUN xmlNotationPtr XMLCALL
xmlAddNotationDecl (xmlValidCtxtPtr ctxt,
xmlDtdPtr dtd,
const xmlChar *name,
const xmlChar *PublicID,
const xmlChar *SystemID);
#ifdef LIBXML_TREE_ENABLED
XMLPUBFUN xmlNotationTablePtr XMLCALL
xmlCopyNotationTable (xmlNotationTablePtr table);
#endif /* LIBXML_TREE_ENABLED */
XMLPUBFUN void XMLCALL
xmlFreeNotationTable (xmlNotationTablePtr table);
#ifdef LIBXML_OUTPUT_ENABLED
XMLPUBFUN void XMLCALL
xmlDumpNotationDecl (xmlBufferPtr buf,
xmlNotationPtr nota);
XMLPUBFUN void XMLCALL
xmlDumpNotationTable (xmlBufferPtr buf,
xmlNotationTablePtr table);
#endif /* LIBXML_OUTPUT_ENABLED */
/* Element Content */
/* the non Doc version are being deprecated */
XMLPUBFUN xmlElementContentPtr XMLCALL
xmlNewElementContent (const xmlChar *name,
xmlElementContentType type);
XMLPUBFUN xmlElementContentPtr XMLCALL
xmlCopyElementContent (xmlElementContentPtr content);
XMLPUBFUN void XMLCALL
xmlFreeElementContent (xmlElementContentPtr cur);
/* the new versions with doc argument */
XMLPUBFUN xmlElementContentPtr XMLCALL
xmlNewDocElementContent (xmlDocPtr doc,
const xmlChar *name,
xmlElementContentType type);
XMLPUBFUN xmlElementContentPtr XMLCALL
xmlCopyDocElementContent(xmlDocPtr doc,
xmlElementContentPtr content);
XMLPUBFUN void XMLCALL
xmlFreeDocElementContent(xmlDocPtr doc,
xmlElementContentPtr cur);
XMLPUBFUN void XMLCALL
xmlSnprintfElementContent(char *buf,
int size,
xmlElementContentPtr content,
int englob);
#ifdef LIBXML_OUTPUT_ENABLED
/* DEPRECATED */
XMLPUBFUN void XMLCALL
xmlSprintfElementContent(char *buf,
xmlElementContentPtr content,
int englob);
#endif /* LIBXML_OUTPUT_ENABLED */
/* DEPRECATED */
/* Element */
XMLPUBFUN xmlElementPtr XMLCALL
xmlAddElementDecl (xmlValidCtxtPtr ctxt,
xmlDtdPtr dtd,
const xmlChar *name,
xmlElementTypeVal type,
xmlElementContentPtr content);
#ifdef LIBXML_TREE_ENABLED
XMLPUBFUN xmlElementTablePtr XMLCALL
xmlCopyElementTable (xmlElementTablePtr table);
#endif /* LIBXML_TREE_ENABLED */
XMLPUBFUN void XMLCALL
xmlFreeElementTable (xmlElementTablePtr table);
#ifdef LIBXML_OUTPUT_ENABLED
XMLPUBFUN void XMLCALL
xmlDumpElementTable (xmlBufferPtr buf,
xmlElementTablePtr table);
XMLPUBFUN void XMLCALL
xmlDumpElementDecl (xmlBufferPtr buf,
xmlElementPtr elem);
#endif /* LIBXML_OUTPUT_ENABLED */
/* Enumeration */
XMLPUBFUN xmlEnumerationPtr XMLCALL
xmlCreateEnumeration (const xmlChar *name);
XMLPUBFUN void XMLCALL
xmlFreeEnumeration (xmlEnumerationPtr cur);
#ifdef LIBXML_TREE_ENABLED
XMLPUBFUN xmlEnumerationPtr XMLCALL
xmlCopyEnumeration (xmlEnumerationPtr cur);
#endif /* LIBXML_TREE_ENABLED */
/* Attribute */
XMLPUBFUN xmlAttributePtr XMLCALL
xmlAddAttributeDecl (xmlValidCtxtPtr ctxt,
xmlDtdPtr dtd,
const xmlChar *elem,
const xmlChar *name,
const xmlChar *ns,
xmlAttributeType type,
xmlAttributeDefault def,
const xmlChar *defaultValue,
xmlEnumerationPtr tree);
#ifdef LIBXML_TREE_ENABLED
XMLPUBFUN xmlAttributeTablePtr XMLCALL
xmlCopyAttributeTable (xmlAttributeTablePtr table);
#endif /* LIBXML_TREE_ENABLED */
XMLPUBFUN void XMLCALL
xmlFreeAttributeTable (xmlAttributeTablePtr table);
#ifdef LIBXML_OUTPUT_ENABLED
XMLPUBFUN void XMLCALL
xmlDumpAttributeTable (xmlBufferPtr buf,
xmlAttributeTablePtr table);
XMLPUBFUN void XMLCALL
xmlDumpAttributeDecl (xmlBufferPtr buf,
xmlAttributePtr attr);
#endif /* LIBXML_OUTPUT_ENABLED */
/* IDs */
XMLPUBFUN xmlIDPtr XMLCALL
xmlAddID (xmlValidCtxtPtr ctxt,
xmlDocPtr doc,
const xmlChar *value,
xmlAttrPtr attr);
XMLPUBFUN void XMLCALL
xmlFreeIDTable (xmlIDTablePtr table);
XMLPUBFUN xmlAttrPtr XMLCALL
xmlGetID (xmlDocPtr doc,
const xmlChar *ID);
XMLPUBFUN int XMLCALL
xmlIsID (xmlDocPtr doc,
xmlNodePtr elem,
xmlAttrPtr attr);
XMLPUBFUN int XMLCALL
xmlRemoveID (xmlDocPtr doc,
xmlAttrPtr attr);
/* IDREFs */
XMLPUBFUN xmlRefPtr XMLCALL
xmlAddRef (xmlValidCtxtPtr ctxt,
xmlDocPtr doc,
const xmlChar *value,
xmlAttrPtr attr);
XMLPUBFUN void XMLCALL
xmlFreeRefTable (xmlRefTablePtr table);
XMLPUBFUN int XMLCALL
xmlIsRef (xmlDocPtr doc,
xmlNodePtr elem,
xmlAttrPtr attr);
XMLPUBFUN int XMLCALL
xmlRemoveRef (xmlDocPtr doc,
xmlAttrPtr attr);
XMLPUBFUN xmlListPtr XMLCALL
xmlGetRefs (xmlDocPtr doc,
const xmlChar *ID);
/**
* The public function calls related to validity checking.
*/
#ifdef LIBXML_VALID_ENABLED
/* Allocate/Release Validation Contexts */
XMLPUBFUN xmlValidCtxtPtr XMLCALL
xmlNewValidCtxt(void);
XMLPUBFUN void XMLCALL
xmlFreeValidCtxt(xmlValidCtxtPtr);
XMLPUBFUN int XMLCALL
xmlValidateRoot (xmlValidCtxtPtr ctxt,
xmlDocPtr doc);
XMLPUBFUN int XMLCALL
xmlValidateElementDecl (xmlValidCtxtPtr ctxt,
xmlDocPtr doc,
xmlElementPtr elem);
XMLPUBFUN xmlChar * XMLCALL
xmlValidNormalizeAttributeValue(xmlDocPtr doc,
xmlNodePtr elem,
const xmlChar *name,
const xmlChar *value);
XMLPUBFUN xmlChar * XMLCALL
xmlValidCtxtNormalizeAttributeValue(xmlValidCtxtPtr ctxt,
xmlDocPtr doc,
xmlNodePtr elem,
const xmlChar *name,
const xmlChar *value);
XMLPUBFUN int XMLCALL
xmlValidateAttributeDecl(xmlValidCtxtPtr ctxt,
xmlDocPtr doc,
xmlAttributePtr attr);
XMLPUBFUN int XMLCALL
xmlValidateAttributeValue(xmlAttributeType type,
const xmlChar *value);
XMLPUBFUN int XMLCALL
xmlValidateNotationDecl (xmlValidCtxtPtr ctxt,
xmlDocPtr doc,
xmlNotationPtr nota);
XMLPUBFUN int XMLCALL
xmlValidateDtd (xmlValidCtxtPtr ctxt,
xmlDocPtr doc,
xmlDtdPtr dtd);
XMLPUBFUN int XMLCALL
xmlValidateDtdFinal (xmlValidCtxtPtr ctxt,
xmlDocPtr doc);
XMLPUBFUN int XMLCALL
xmlValidateDocument (xmlValidCtxtPtr ctxt,
xmlDocPtr doc);
XMLPUBFUN int XMLCALL
xmlValidateElement (xmlValidCtxtPtr ctxt,
xmlDocPtr doc,
xmlNodePtr elem);
XMLPUBFUN int XMLCALL
xmlValidateOneElement (xmlValidCtxtPtr ctxt,
xmlDocPtr doc,
xmlNodePtr elem);
XMLPUBFUN int XMLCALL
xmlValidateOneAttribute (xmlValidCtxtPtr ctxt,
xmlDocPtr doc,
xmlNodePtr elem,
xmlAttrPtr attr,
const xmlChar *value);
XMLPUBFUN int XMLCALL
xmlValidateOneNamespace (xmlValidCtxtPtr ctxt,
xmlDocPtr doc,
xmlNodePtr elem,
const xmlChar *prefix,
xmlNsPtr ns,
const xmlChar *value);
XMLPUBFUN int XMLCALL
xmlValidateDocumentFinal(xmlValidCtxtPtr ctxt,
xmlDocPtr doc);
#endif /* LIBXML_VALID_ENABLED */
#if defined(LIBXML_VALID_ENABLED) || defined(LIBXML_SCHEMAS_ENABLED)
XMLPUBFUN int XMLCALL
xmlValidateNotationUse (xmlValidCtxtPtr ctxt,
xmlDocPtr doc,
const xmlChar *notationName);
#endif /* LIBXML_VALID_ENABLED or LIBXML_SCHEMAS_ENABLED */
XMLPUBFUN int XMLCALL
xmlIsMixedElement (xmlDocPtr doc,
const xmlChar *name);
XMLPUBFUN xmlAttributePtr XMLCALL
xmlGetDtdAttrDesc (xmlDtdPtr dtd,
const xmlChar *elem,
const xmlChar *name);
XMLPUBFUN xmlAttributePtr XMLCALL
xmlGetDtdQAttrDesc (xmlDtdPtr dtd,
const xmlChar *elem,
const xmlChar *name,
const xmlChar *prefix);
XMLPUBFUN xmlNotationPtr XMLCALL
xmlGetDtdNotationDesc (xmlDtdPtr dtd,
const xmlChar *name);
XMLPUBFUN xmlElementPtr XMLCALL
xmlGetDtdQElementDesc (xmlDtdPtr dtd,
const xmlChar *name,
const xmlChar *prefix);
XMLPUBFUN xmlElementPtr XMLCALL
xmlGetDtdElementDesc (xmlDtdPtr dtd,
const xmlChar *name);
#ifdef LIBXML_VALID_ENABLED
XMLPUBFUN int XMLCALL
xmlValidGetPotentialChildren(xmlElementContent *ctree,
const xmlChar **names,
int *len,
int max);
XMLPUBFUN int XMLCALL
xmlValidGetValidElements(xmlNode *prev,
xmlNode *next,
const xmlChar **names,
int max);
XMLPUBFUN int XMLCALL
xmlValidateNameValue (const xmlChar *value);
XMLPUBFUN int XMLCALL
xmlValidateNamesValue (const xmlChar *value);
XMLPUBFUN int XMLCALL
xmlValidateNmtokenValue (const xmlChar *value);
XMLPUBFUN int XMLCALL
xmlValidateNmtokensValue(const xmlChar *value);
#ifdef LIBXML_REGEXP_ENABLED
/*
* Validation based on the regexp support
*/
XMLPUBFUN int XMLCALL
xmlValidBuildContentModel(xmlValidCtxtPtr ctxt,
xmlElementPtr elem);
XMLPUBFUN int XMLCALL
xmlValidatePushElement (xmlValidCtxtPtr ctxt,
xmlDocPtr doc,
xmlNodePtr elem,
const xmlChar *qname);
XMLPUBFUN int XMLCALL
xmlValidatePushCData (xmlValidCtxtPtr ctxt,
const xmlChar *data,
int len);
XMLPUBFUN int XMLCALL
xmlValidatePopElement (xmlValidCtxtPtr ctxt,
xmlDocPtr doc,
xmlNodePtr elem,
const xmlChar *qname);
#endif /* LIBXML_REGEXP_ENABLED */
#endif /* LIBXML_VALID_ENABLED */
#ifdef __cplusplus
}
#endif
#endif /* __XML_VALID_H__ */

@ -0,0 +1,129 @@
/*
* Summary: implementation of XInclude
* Description: API to handle XInclude processing,
* implements the
* World Wide Web Consortium Last Call Working Draft 10 November 2003
* http://www.w3.org/TR/2003/WD-xinclude-20031110
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_XINCLUDE_H__
#define __XML_XINCLUDE_H__
#include <libxml/xmlversion.h>
#include <libxml/tree.h>
#ifdef LIBXML_XINCLUDE_ENABLED
#ifdef __cplusplus
extern "C" {
#endif
/**
* XINCLUDE_NS:
*
* Macro defining the Xinclude namespace: http://www.w3.org/2003/XInclude
*/
#define XINCLUDE_NS (const xmlChar *) "http://www.w3.org/2003/XInclude"
/**
* XINCLUDE_OLD_NS:
*
* Macro defining the draft Xinclude namespace: http://www.w3.org/2001/XInclude
*/
#define XINCLUDE_OLD_NS (const xmlChar *) "http://www.w3.org/2001/XInclude"
/**
* XINCLUDE_NODE:
*
* Macro defining "include"
*/
#define XINCLUDE_NODE (const xmlChar *) "include"
/**
* XINCLUDE_FALLBACK:
*
* Macro defining "fallback"
*/
#define XINCLUDE_FALLBACK (const xmlChar *) "fallback"
/**
* XINCLUDE_HREF:
*
* Macro defining "href"
*/
#define XINCLUDE_HREF (const xmlChar *) "href"
/**
* XINCLUDE_PARSE:
*
* Macro defining "parse"
*/
#define XINCLUDE_PARSE (const xmlChar *) "parse"
/**
* XINCLUDE_PARSE_XML:
*
* Macro defining "xml"
*/
#define XINCLUDE_PARSE_XML (const xmlChar *) "xml"
/**
* XINCLUDE_PARSE_TEXT:
*
* Macro defining "text"
*/
#define XINCLUDE_PARSE_TEXT (const xmlChar *) "text"
/**
* XINCLUDE_PARSE_ENCODING:
*
* Macro defining "encoding"
*/
#define XINCLUDE_PARSE_ENCODING (const xmlChar *) "encoding"
/**
* XINCLUDE_PARSE_XPOINTER:
*
* Macro defining "xpointer"
*/
#define XINCLUDE_PARSE_XPOINTER (const xmlChar *) "xpointer"
typedef struct _xmlXIncludeCtxt xmlXIncludeCtxt;
typedef xmlXIncludeCtxt *xmlXIncludeCtxtPtr;
/*
* standalone processing
*/
XMLPUBFUN int XMLCALL
xmlXIncludeProcess (xmlDocPtr doc);
XMLPUBFUN int XMLCALL
xmlXIncludeProcessFlags (xmlDocPtr doc,
int flags);
XMLPUBFUN int XMLCALL
xmlXIncludeProcessFlagsData(xmlDocPtr doc,
int flags,
void *data);
XMLPUBFUN int XMLCALL
xmlXIncludeProcessTreeFlagsData(xmlNodePtr tree,
int flags,
void *data);
XMLPUBFUN int XMLCALL
xmlXIncludeProcessTree (xmlNodePtr tree);
XMLPUBFUN int XMLCALL
xmlXIncludeProcessTreeFlags(xmlNodePtr tree,
int flags);
/*
* contextual processing
*/
XMLPUBFUN xmlXIncludeCtxtPtr XMLCALL
xmlXIncludeNewContext (xmlDocPtr doc);
XMLPUBFUN int XMLCALL
xmlXIncludeSetFlags (xmlXIncludeCtxtPtr ctxt,
int flags);
XMLPUBFUN void XMLCALL
xmlXIncludeFreeContext (xmlXIncludeCtxtPtr ctxt);
XMLPUBFUN int XMLCALL
xmlXIncludeProcessNode (xmlXIncludeCtxtPtr ctxt,
xmlNodePtr tree);
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_XINCLUDE_ENABLED */
#endif /* __XML_XINCLUDE_H__ */

@ -0,0 +1,189 @@
/*
* Summary: unfinished XLink detection module
* Description: unfinished XLink detection module
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_XLINK_H__
#define __XML_XLINK_H__
#include <libxml/xmlversion.h>
#include <libxml/tree.h>
#ifdef LIBXML_XPTR_ENABLED
#ifdef __cplusplus
extern "C" {
#endif
/**
* Various defines for the various Link properties.
*
* NOTE: the link detection layer will try to resolve QName expansion
* of namespaces. If "foo" is the prefix for "http://foo.com/"
* then the link detection layer will expand role="foo:myrole"
* to "http://foo.com/:myrole".
* NOTE: the link detection layer will expand URI-Refences found on
* href attributes by using the base mechanism if found.
*/
typedef xmlChar *xlinkHRef;
typedef xmlChar *xlinkRole;
typedef xmlChar *xlinkTitle;
typedef enum {
XLINK_TYPE_NONE = 0,
XLINK_TYPE_SIMPLE,
XLINK_TYPE_EXTENDED,
XLINK_TYPE_EXTENDED_SET
} xlinkType;
typedef enum {
XLINK_SHOW_NONE = 0,
XLINK_SHOW_NEW,
XLINK_SHOW_EMBED,
XLINK_SHOW_REPLACE
} xlinkShow;
typedef enum {
XLINK_ACTUATE_NONE = 0,
XLINK_ACTUATE_AUTO,
XLINK_ACTUATE_ONREQUEST
} xlinkActuate;
/**
* xlinkNodeDetectFunc:
* @ctx: user data pointer
* @node: the node to check
*
* This is the prototype for the link detection routine.
* It calls the default link detection callbacks upon link detection.
*/
typedef void (*xlinkNodeDetectFunc) (void *ctx, xmlNodePtr node);
/*
* The link detection module interact with the upper layers using
* a set of callback registered at parsing time.
*/
/**
* xlinkSimpleLinkFunk:
* @ctx: user data pointer
* @node: the node carrying the link
* @href: the target of the link
* @role: the role string
* @title: the link title
*
* This is the prototype for a simple link detection callback.
*/
typedef void
(*xlinkSimpleLinkFunk) (void *ctx,
xmlNodePtr node,
const xlinkHRef href,
const xlinkRole role,
const xlinkTitle title);
/**
* xlinkExtendedLinkFunk:
* @ctx: user data pointer
* @node: the node carrying the link
* @nbLocators: the number of locators detected on the link
* @hrefs: pointer to the array of locator hrefs
* @roles: pointer to the array of locator roles
* @nbArcs: the number of arcs detected on the link
* @from: pointer to the array of source roles found on the arcs
* @to: pointer to the array of target roles found on the arcs
* @show: array of values for the show attributes found on the arcs
* @actuate: array of values for the actuate attributes found on the arcs
* @nbTitles: the number of titles detected on the link
* @title: array of titles detected on the link
* @langs: array of xml:lang values for the titles
*
* This is the prototype for a extended link detection callback.
*/
typedef void
(*xlinkExtendedLinkFunk)(void *ctx,
xmlNodePtr node,
int nbLocators,
const xlinkHRef *hrefs,
const xlinkRole *roles,
int nbArcs,
const xlinkRole *from,
const xlinkRole *to,
xlinkShow *show,
xlinkActuate *actuate,
int nbTitles,
const xlinkTitle *titles,
const xmlChar **langs);
/**
* xlinkExtendedLinkSetFunk:
* @ctx: user data pointer
* @node: the node carrying the link
* @nbLocators: the number of locators detected on the link
* @hrefs: pointer to the array of locator hrefs
* @roles: pointer to the array of locator roles
* @nbTitles: the number of titles detected on the link
* @title: array of titles detected on the link
* @langs: array of xml:lang values for the titles
*
* This is the prototype for a extended link set detection callback.
*/
typedef void
(*xlinkExtendedLinkSetFunk) (void *ctx,
xmlNodePtr node,
int nbLocators,
const xlinkHRef *hrefs,
const xlinkRole *roles,
int nbTitles,
const xlinkTitle *titles,
const xmlChar **langs);
/**
* This is the structure containing a set of Links detection callbacks.
*
* There is no default xlink callbacks, if one want to get link
* recognition activated, those call backs must be provided before parsing.
*/
typedef struct _xlinkHandler xlinkHandler;
typedef xlinkHandler *xlinkHandlerPtr;
struct _xlinkHandler {
xlinkSimpleLinkFunk simple;
xlinkExtendedLinkFunk extended;
xlinkExtendedLinkSetFunk set;
};
/*
* The default detection routine, can be overridden, they call the default
* detection callbacks.
*/
XMLPUBFUN xlinkNodeDetectFunc XMLCALL
xlinkGetDefaultDetect (void);
XMLPUBFUN void XMLCALL
xlinkSetDefaultDetect (xlinkNodeDetectFunc func);
/*
* Routines to set/get the default handlers.
*/
XMLPUBFUN xlinkHandlerPtr XMLCALL
xlinkGetDefaultHandler (void);
XMLPUBFUN void XMLCALL
xlinkSetDefaultHandler (xlinkHandlerPtr handler);
/*
* Link detection module itself.
*/
XMLPUBFUN xlinkType XMLCALL
xlinkIsLink (xmlDocPtr doc,
xmlNodePtr node);
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_XPTR_ENABLED */
#endif /* __XML_XLINK_H__ */

@ -0,0 +1,366 @@
/*
* Summary: interface for the I/O interfaces used by the parser
* Description: interface for the I/O interfaces used by the parser
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_IO_H__
#define __XML_IO_H__
#include <stdio.h>
#include <libxml/xmlversion.h>
#ifdef __cplusplus
extern "C" {
#endif
/*
* Those are the functions and datatypes for the parser input
* I/O structures.
*/
/**
* xmlInputMatchCallback:
* @filename: the filename or URI
*
* Callback used in the I/O Input API to detect if the current handler
* can provide input fonctionnalities for this resource.
*
* Returns 1 if yes and 0 if another Input module should be used
*/
typedef int (XMLCALL *xmlInputMatchCallback) (char const *filename);
/**
* xmlInputOpenCallback:
* @filename: the filename or URI
*
* Callback used in the I/O Input API to open the resource
*
* Returns an Input context or NULL in case or error
*/
typedef void * (XMLCALL *xmlInputOpenCallback) (char const *filename);
/**
* xmlInputReadCallback:
* @context: an Input context
* @buffer: the buffer to store data read
* @len: the length of the buffer in bytes
*
* Callback used in the I/O Input API to read the resource
*
* Returns the number of bytes read or -1 in case of error
*/
typedef int (XMLCALL *xmlInputReadCallback) (void * context, char * buffer, int len);
/**
* xmlInputCloseCallback:
* @context: an Input context
*
* Callback used in the I/O Input API to close the resource
*
* Returns 0 or -1 in case of error
*/
typedef int (XMLCALL *xmlInputCloseCallback) (void * context);
#ifdef LIBXML_OUTPUT_ENABLED
/*
* Those are the functions and datatypes for the library output
* I/O structures.
*/
/**
* xmlOutputMatchCallback:
* @filename: the filename or URI
*
* Callback used in the I/O Output API to detect if the current handler
* can provide output fonctionnalities for this resource.
*
* Returns 1 if yes and 0 if another Output module should be used
*/
typedef int (XMLCALL *xmlOutputMatchCallback) (char const *filename);
/**
* xmlOutputOpenCallback:
* @filename: the filename or URI
*
* Callback used in the I/O Output API to open the resource
*
* Returns an Output context or NULL in case or error
*/
typedef void * (XMLCALL *xmlOutputOpenCallback) (char const *filename);
/**
* xmlOutputWriteCallback:
* @context: an Output context
* @buffer: the buffer of data to write
* @len: the length of the buffer in bytes
*
* Callback used in the I/O Output API to write to the resource
*
* Returns the number of bytes written or -1 in case of error
*/
typedef int (XMLCALL *xmlOutputWriteCallback) (void * context, const char * buffer,
int len);
/**
* xmlOutputCloseCallback:
* @context: an Output context
*
* Callback used in the I/O Output API to close the resource
*
* Returns 0 or -1 in case of error
*/
typedef int (XMLCALL *xmlOutputCloseCallback) (void * context);
#endif /* LIBXML_OUTPUT_ENABLED */
#ifdef __cplusplus
}
#endif
#include <libxml/globals.h>
#include <libxml/tree.h>
#include <libxml/parser.h>
#include <libxml/encoding.h>
#ifdef __cplusplus
extern "C" {
#endif
struct _xmlParserInputBuffer {
void* context;
xmlInputReadCallback readcallback;
xmlInputCloseCallback closecallback;
xmlCharEncodingHandlerPtr encoder; /* I18N conversions to UTF-8 */
xmlBufPtr buffer; /* Local buffer encoded in UTF-8 */
xmlBufPtr raw; /* if encoder != NULL buffer for raw input */
int compressed; /* -1=unknown, 0=not compressed, 1=compressed */
int error;
unsigned long rawconsumed;/* amount consumed from raw */
};
#ifdef LIBXML_OUTPUT_ENABLED
struct _xmlOutputBuffer {
void* context;
xmlOutputWriteCallback writecallback;
xmlOutputCloseCallback closecallback;
xmlCharEncodingHandlerPtr encoder; /* I18N conversions to UTF-8 */
xmlBufPtr buffer; /* Local buffer encoded in UTF-8 or ISOLatin */
xmlBufPtr conv; /* if encoder != NULL buffer for output */
int written; /* total number of byte written */
int error;
};
#endif /* LIBXML_OUTPUT_ENABLED */
/*
* Interfaces for input
*/
XMLPUBFUN void XMLCALL
xmlCleanupInputCallbacks (void);
XMLPUBFUN int XMLCALL
xmlPopInputCallbacks (void);
XMLPUBFUN void XMLCALL
xmlRegisterDefaultInputCallbacks (void);
XMLPUBFUN xmlParserInputBufferPtr XMLCALL
xmlAllocParserInputBuffer (xmlCharEncoding enc);
XMLPUBFUN xmlParserInputBufferPtr XMLCALL
xmlParserInputBufferCreateFilename (const char *URI,
xmlCharEncoding enc);
XMLPUBFUN xmlParserInputBufferPtr XMLCALL
xmlParserInputBufferCreateFile (FILE *file,
xmlCharEncoding enc);
XMLPUBFUN xmlParserInputBufferPtr XMLCALL
xmlParserInputBufferCreateFd (int fd,
xmlCharEncoding enc);
XMLPUBFUN xmlParserInputBufferPtr XMLCALL
xmlParserInputBufferCreateMem (const char *mem, int size,
xmlCharEncoding enc);
XMLPUBFUN xmlParserInputBufferPtr XMLCALL
xmlParserInputBufferCreateStatic (const char *mem, int size,
xmlCharEncoding enc);
XMLPUBFUN xmlParserInputBufferPtr XMLCALL
xmlParserInputBufferCreateIO (xmlInputReadCallback ioread,
xmlInputCloseCallback ioclose,
void *ioctx,
xmlCharEncoding enc);
XMLPUBFUN int XMLCALL
xmlParserInputBufferRead (xmlParserInputBufferPtr in,
int len);
XMLPUBFUN int XMLCALL
xmlParserInputBufferGrow (xmlParserInputBufferPtr in,
int len);
XMLPUBFUN int XMLCALL
xmlParserInputBufferPush (xmlParserInputBufferPtr in,
int len,
const char *buf);
XMLPUBFUN void XMLCALL
xmlFreeParserInputBuffer (xmlParserInputBufferPtr in);
XMLPUBFUN char * XMLCALL
xmlParserGetDirectory (const char *filename);
XMLPUBFUN int XMLCALL
xmlRegisterInputCallbacks (xmlInputMatchCallback matchFunc,
xmlInputOpenCallback openFunc,
xmlInputReadCallback readFunc,
xmlInputCloseCallback closeFunc);
xmlParserInputBufferPtr
__xmlParserInputBufferCreateFilename(const char *URI,
xmlCharEncoding enc);
#ifdef LIBXML_OUTPUT_ENABLED
/*
* Interfaces for output
*/
XMLPUBFUN void XMLCALL
xmlCleanupOutputCallbacks (void);
XMLPUBFUN void XMLCALL
xmlRegisterDefaultOutputCallbacks(void);
XMLPUBFUN xmlOutputBufferPtr XMLCALL
xmlAllocOutputBuffer (xmlCharEncodingHandlerPtr encoder);
XMLPUBFUN xmlOutputBufferPtr XMLCALL
xmlOutputBufferCreateFilename (const char *URI,
xmlCharEncodingHandlerPtr encoder,
int compression);
XMLPUBFUN xmlOutputBufferPtr XMLCALL
xmlOutputBufferCreateFile (FILE *file,
xmlCharEncodingHandlerPtr encoder);
XMLPUBFUN xmlOutputBufferPtr XMLCALL
xmlOutputBufferCreateBuffer (xmlBufferPtr buffer,
xmlCharEncodingHandlerPtr encoder);
XMLPUBFUN xmlOutputBufferPtr XMLCALL
xmlOutputBufferCreateFd (int fd,
xmlCharEncodingHandlerPtr encoder);
XMLPUBFUN xmlOutputBufferPtr XMLCALL
xmlOutputBufferCreateIO (xmlOutputWriteCallback iowrite,
xmlOutputCloseCallback ioclose,
void *ioctx,
xmlCharEncodingHandlerPtr encoder);
/* Couple of APIs to get the output without digging into the buffers */
XMLPUBFUN const xmlChar * XMLCALL
xmlOutputBufferGetContent (xmlOutputBufferPtr out);
XMLPUBFUN size_t XMLCALL
xmlOutputBufferGetSize (xmlOutputBufferPtr out);
XMLPUBFUN int XMLCALL
xmlOutputBufferWrite (xmlOutputBufferPtr out,
int len,
const char *buf);
XMLPUBFUN int XMLCALL
xmlOutputBufferWriteString (xmlOutputBufferPtr out,
const char *str);
XMLPUBFUN int XMLCALL
xmlOutputBufferWriteEscape (xmlOutputBufferPtr out,
const xmlChar *str,
xmlCharEncodingOutputFunc escaping);
XMLPUBFUN int XMLCALL
xmlOutputBufferFlush (xmlOutputBufferPtr out);
XMLPUBFUN int XMLCALL
xmlOutputBufferClose (xmlOutputBufferPtr out);
XMLPUBFUN int XMLCALL
xmlRegisterOutputCallbacks (xmlOutputMatchCallback matchFunc,
xmlOutputOpenCallback openFunc,
xmlOutputWriteCallback writeFunc,
xmlOutputCloseCallback closeFunc);
xmlOutputBufferPtr
__xmlOutputBufferCreateFilename(const char *URI,
xmlCharEncodingHandlerPtr encoder,
int compression);
#ifdef LIBXML_HTTP_ENABLED
/* This function only exists if HTTP support built into the library */
XMLPUBFUN void XMLCALL
xmlRegisterHTTPPostCallbacks (void );
#endif /* LIBXML_HTTP_ENABLED */
#endif /* LIBXML_OUTPUT_ENABLED */
XMLPUBFUN xmlParserInputPtr XMLCALL
xmlCheckHTTPInput (xmlParserCtxtPtr ctxt,
xmlParserInputPtr ret);
/*
* A predefined entity loader disabling network accesses
*/
XMLPUBFUN xmlParserInputPtr XMLCALL
xmlNoNetExternalEntityLoader (const char *URL,
const char *ID,
xmlParserCtxtPtr ctxt);
/*
* xmlNormalizeWindowsPath is obsolete, don't use it.
* Check xmlCanonicPath in uri.h for a better alternative.
*/
XMLPUBFUN xmlChar * XMLCALL
xmlNormalizeWindowsPath (const xmlChar *path);
XMLPUBFUN int XMLCALL
xmlCheckFilename (const char *path);
/**
* Default 'file://' protocol callbacks
*/
XMLPUBFUN int XMLCALL
xmlFileMatch (const char *filename);
XMLPUBFUN void * XMLCALL
xmlFileOpen (const char *filename);
XMLPUBFUN int XMLCALL
xmlFileRead (void * context,
char * buffer,
int len);
XMLPUBFUN int XMLCALL
xmlFileClose (void * context);
/**
* Default 'http://' protocol callbacks
*/
#ifdef LIBXML_HTTP_ENABLED
XMLPUBFUN int XMLCALL
xmlIOHTTPMatch (const char *filename);
XMLPUBFUN void * XMLCALL
xmlIOHTTPOpen (const char *filename);
#ifdef LIBXML_OUTPUT_ENABLED
XMLPUBFUN void * XMLCALL
xmlIOHTTPOpenW (const char * post_uri,
int compression );
#endif /* LIBXML_OUTPUT_ENABLED */
XMLPUBFUN int XMLCALL
xmlIOHTTPRead (void * context,
char * buffer,
int len);
XMLPUBFUN int XMLCALL
xmlIOHTTPClose (void * context);
#endif /* LIBXML_HTTP_ENABLED */
/**
* Default 'ftp://' protocol callbacks
*/
#ifdef LIBXML_FTP_ENABLED
XMLPUBFUN int XMLCALL
xmlIOFTPMatch (const char *filename);
XMLPUBFUN void * XMLCALL
xmlIOFTPOpen (const char *filename);
XMLPUBFUN int XMLCALL
xmlIOFTPRead (void * context,
char * buffer,
int len);
XMLPUBFUN int XMLCALL
xmlIOFTPClose (void * context);
#endif /* LIBXML_FTP_ENABLED */
#ifdef __cplusplus
}
#endif
#endif /* __XML_IO_H__ */

@ -0,0 +1,146 @@
/*
* Summary: API to build regexp automata
* Description: the API to build regexp automata
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_AUTOMATA_H__
#define __XML_AUTOMATA_H__
#include <libxml/xmlversion.h>
#include <libxml/tree.h>
#ifdef LIBXML_REGEXP_ENABLED
#ifdef LIBXML_AUTOMATA_ENABLED
#include <libxml/xmlregexp.h>
#ifdef __cplusplus
extern "C" {
#endif
/**
* xmlAutomataPtr:
*
* A libxml automata description, It can be compiled into a regexp
*/
typedef struct _xmlAutomata xmlAutomata;
typedef xmlAutomata *xmlAutomataPtr;
/**
* xmlAutomataStatePtr:
*
* A state int the automata description,
*/
typedef struct _xmlAutomataState xmlAutomataState;
typedef xmlAutomataState *xmlAutomataStatePtr;
/*
* Building API
*/
XMLPUBFUN xmlAutomataPtr XMLCALL
xmlNewAutomata (void);
XMLPUBFUN void XMLCALL
xmlFreeAutomata (xmlAutomataPtr am);
XMLPUBFUN xmlAutomataStatePtr XMLCALL
xmlAutomataGetInitState (xmlAutomataPtr am);
XMLPUBFUN int XMLCALL
xmlAutomataSetFinalState (xmlAutomataPtr am,
xmlAutomataStatePtr state);
XMLPUBFUN xmlAutomataStatePtr XMLCALL
xmlAutomataNewState (xmlAutomataPtr am);
XMLPUBFUN xmlAutomataStatePtr XMLCALL
xmlAutomataNewTransition (xmlAutomataPtr am,
xmlAutomataStatePtr from,
xmlAutomataStatePtr to,
const xmlChar *token,
void *data);
XMLPUBFUN xmlAutomataStatePtr XMLCALL
xmlAutomataNewTransition2 (xmlAutomataPtr am,
xmlAutomataStatePtr from,
xmlAutomataStatePtr to,
const xmlChar *token,
const xmlChar *token2,
void *data);
XMLPUBFUN xmlAutomataStatePtr XMLCALL
xmlAutomataNewNegTrans (xmlAutomataPtr am,
xmlAutomataStatePtr from,
xmlAutomataStatePtr to,
const xmlChar *token,
const xmlChar *token2,
void *data);
XMLPUBFUN xmlAutomataStatePtr XMLCALL
xmlAutomataNewCountTrans (xmlAutomataPtr am,
xmlAutomataStatePtr from,
xmlAutomataStatePtr to,
const xmlChar *token,
int min,
int max,
void *data);
XMLPUBFUN xmlAutomataStatePtr XMLCALL
xmlAutomataNewCountTrans2 (xmlAutomataPtr am,
xmlAutomataStatePtr from,
xmlAutomataStatePtr to,
const xmlChar *token,
const xmlChar *token2,
int min,
int max,
void *data);
XMLPUBFUN xmlAutomataStatePtr XMLCALL
xmlAutomataNewOnceTrans (xmlAutomataPtr am,
xmlAutomataStatePtr from,
xmlAutomataStatePtr to,
const xmlChar *token,
int min,
int max,
void *data);
XMLPUBFUN xmlAutomataStatePtr XMLCALL
xmlAutomataNewOnceTrans2 (xmlAutomataPtr am,
xmlAutomataStatePtr from,
xmlAutomataStatePtr to,
const xmlChar *token,
const xmlChar *token2,
int min,
int max,
void *data);
XMLPUBFUN xmlAutomataStatePtr XMLCALL
xmlAutomataNewAllTrans (xmlAutomataPtr am,
xmlAutomataStatePtr from,
xmlAutomataStatePtr to,
int lax);
XMLPUBFUN xmlAutomataStatePtr XMLCALL
xmlAutomataNewEpsilon (xmlAutomataPtr am,
xmlAutomataStatePtr from,
xmlAutomataStatePtr to);
XMLPUBFUN xmlAutomataStatePtr XMLCALL
xmlAutomataNewCountedTrans (xmlAutomataPtr am,
xmlAutomataStatePtr from,
xmlAutomataStatePtr to,
int counter);
XMLPUBFUN xmlAutomataStatePtr XMLCALL
xmlAutomataNewCounterTrans (xmlAutomataPtr am,
xmlAutomataStatePtr from,
xmlAutomataStatePtr to,
int counter);
XMLPUBFUN int XMLCALL
xmlAutomataNewCounter (xmlAutomataPtr am,
int min,
int max);
XMLPUBFUN xmlRegexpPtr XMLCALL
xmlAutomataCompile (xmlAutomataPtr am);
XMLPUBFUN int XMLCALL
xmlAutomataIsDeterminist (xmlAutomataPtr am);
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_AUTOMATA_ENABLED */
#endif /* LIBXML_REGEXP_ENABLED */
#endif /* __XML_AUTOMATA_H__ */

@ -0,0 +1,945 @@
/*
* Summary: error handling
* Description: the API used to report errors
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#include <libxml/parser.h>
#ifndef __XML_ERROR_H__
#define __XML_ERROR_H__
#ifdef __cplusplus
extern "C" {
#endif
/**
* xmlErrorLevel:
*
* Indicates the level of an error
*/
typedef enum {
XML_ERR_NONE = 0,
XML_ERR_WARNING = 1, /* A simple warning */
XML_ERR_ERROR = 2, /* A recoverable error */
XML_ERR_FATAL = 3 /* A fatal error */
} xmlErrorLevel;
/**
* xmlErrorDomain:
*
* Indicates where an error may have come from
*/
typedef enum {
XML_FROM_NONE = 0,
XML_FROM_PARSER, /* The XML parser */
XML_FROM_TREE, /* The tree module */
XML_FROM_NAMESPACE, /* The XML Namespace module */
XML_FROM_DTD, /* The XML DTD validation with parser context*/
XML_FROM_HTML, /* The HTML parser */
XML_FROM_MEMORY, /* The memory allocator */
XML_FROM_OUTPUT, /* The serialization code */
XML_FROM_IO, /* The Input/Output stack */
XML_FROM_FTP, /* The FTP module */
XML_FROM_HTTP, /* The HTTP module */
XML_FROM_XINCLUDE, /* The XInclude processing */
XML_FROM_XPATH, /* The XPath module */
XML_FROM_XPOINTER, /* The XPointer module */
XML_FROM_REGEXP, /* The regular expressions module */
XML_FROM_DATATYPE, /* The W3C XML Schemas Datatype module */
XML_FROM_SCHEMASP, /* The W3C XML Schemas parser module */
XML_FROM_SCHEMASV, /* The W3C XML Schemas validation module */
XML_FROM_RELAXNGP, /* The Relax-NG parser module */
XML_FROM_RELAXNGV, /* The Relax-NG validator module */
XML_FROM_CATALOG, /* The Catalog module */
XML_FROM_C14N, /* The Canonicalization module */
XML_FROM_XSLT, /* The XSLT engine from libxslt */
XML_FROM_VALID, /* The XML DTD validation with valid context */
XML_FROM_CHECK, /* The error checking module */
XML_FROM_WRITER, /* The xmlwriter module */
XML_FROM_MODULE, /* The dynamically loaded module module*/
XML_FROM_I18N, /* The module handling character conversion */
XML_FROM_SCHEMATRONV,/* The Schematron validator module */
XML_FROM_BUFFER, /* The buffers module */
XML_FROM_URI /* The URI module */
} xmlErrorDomain;
/**
* xmlError:
*
* An XML Error instance.
*/
typedef struct _xmlError xmlError;
typedef xmlError *xmlErrorPtr;
struct _xmlError {
int domain; /* What part of the library raised this error */
int code; /* The error code, e.g. an xmlParserError */
char *message;/* human-readable informative error message */
xmlErrorLevel level;/* how consequent is the error */
char *file; /* the filename */
int line; /* the line number if available */
char *str1; /* extra string information */
char *str2; /* extra string information */
char *str3; /* extra string information */
int int1; /* extra number information */
int int2; /* error column # or 0 if N/A (todo: rename field when we would brk ABI) */
void *ctxt; /* the parser context if available */
void *node; /* the node in the tree */
};
/**
* xmlParserError:
*
* This is an error that the XML (or HTML) parser can generate
*/
typedef enum {
XML_ERR_OK = 0,
XML_ERR_INTERNAL_ERROR, /* 1 */
XML_ERR_NO_MEMORY, /* 2 */
XML_ERR_DOCUMENT_START, /* 3 */
XML_ERR_DOCUMENT_EMPTY, /* 4 */
XML_ERR_DOCUMENT_END, /* 5 */
XML_ERR_INVALID_HEX_CHARREF, /* 6 */
XML_ERR_INVALID_DEC_CHARREF, /* 7 */
XML_ERR_INVALID_CHARREF, /* 8 */
XML_ERR_INVALID_CHAR, /* 9 */
XML_ERR_CHARREF_AT_EOF, /* 10 */
XML_ERR_CHARREF_IN_PROLOG, /* 11 */
XML_ERR_CHARREF_IN_EPILOG, /* 12 */
XML_ERR_CHARREF_IN_DTD, /* 13 */
XML_ERR_ENTITYREF_AT_EOF, /* 14 */
XML_ERR_ENTITYREF_IN_PROLOG, /* 15 */
XML_ERR_ENTITYREF_IN_EPILOG, /* 16 */
XML_ERR_ENTITYREF_IN_DTD, /* 17 */
XML_ERR_PEREF_AT_EOF, /* 18 */
XML_ERR_PEREF_IN_PROLOG, /* 19 */
XML_ERR_PEREF_IN_EPILOG, /* 20 */
XML_ERR_PEREF_IN_INT_SUBSET, /* 21 */
XML_ERR_ENTITYREF_NO_NAME, /* 22 */
XML_ERR_ENTITYREF_SEMICOL_MISSING, /* 23 */
XML_ERR_PEREF_NO_NAME, /* 24 */
XML_ERR_PEREF_SEMICOL_MISSING, /* 25 */
XML_ERR_UNDECLARED_ENTITY, /* 26 */
XML_WAR_UNDECLARED_ENTITY, /* 27 */
XML_ERR_UNPARSED_ENTITY, /* 28 */
XML_ERR_ENTITY_IS_EXTERNAL, /* 29 */
XML_ERR_ENTITY_IS_PARAMETER, /* 30 */
XML_ERR_UNKNOWN_ENCODING, /* 31 */
XML_ERR_UNSUPPORTED_ENCODING, /* 32 */
XML_ERR_STRING_NOT_STARTED, /* 33 */
XML_ERR_STRING_NOT_CLOSED, /* 34 */
XML_ERR_NS_DECL_ERROR, /* 35 */
XML_ERR_ENTITY_NOT_STARTED, /* 36 */
XML_ERR_ENTITY_NOT_FINISHED, /* 37 */
XML_ERR_LT_IN_ATTRIBUTE, /* 38 */
XML_ERR_ATTRIBUTE_NOT_STARTED, /* 39 */
XML_ERR_ATTRIBUTE_NOT_FINISHED, /* 40 */
XML_ERR_ATTRIBUTE_WITHOUT_VALUE, /* 41 */
XML_ERR_ATTRIBUTE_REDEFINED, /* 42 */
XML_ERR_LITERAL_NOT_STARTED, /* 43 */
XML_ERR_LITERAL_NOT_FINISHED, /* 44 */
XML_ERR_COMMENT_NOT_FINISHED, /* 45 */
XML_ERR_PI_NOT_STARTED, /* 46 */
XML_ERR_PI_NOT_FINISHED, /* 47 */
XML_ERR_NOTATION_NOT_STARTED, /* 48 */
XML_ERR_NOTATION_NOT_FINISHED, /* 49 */
XML_ERR_ATTLIST_NOT_STARTED, /* 50 */
XML_ERR_ATTLIST_NOT_FINISHED, /* 51 */
XML_ERR_MIXED_NOT_STARTED, /* 52 */
XML_ERR_MIXED_NOT_FINISHED, /* 53 */
XML_ERR_ELEMCONTENT_NOT_STARTED, /* 54 */
XML_ERR_ELEMCONTENT_NOT_FINISHED, /* 55 */
XML_ERR_XMLDECL_NOT_STARTED, /* 56 */
XML_ERR_XMLDECL_NOT_FINISHED, /* 57 */
XML_ERR_CONDSEC_NOT_STARTED, /* 58 */
XML_ERR_CONDSEC_NOT_FINISHED, /* 59 */
XML_ERR_EXT_SUBSET_NOT_FINISHED, /* 60 */
XML_ERR_DOCTYPE_NOT_FINISHED, /* 61 */
XML_ERR_MISPLACED_CDATA_END, /* 62 */
XML_ERR_CDATA_NOT_FINISHED, /* 63 */
XML_ERR_RESERVED_XML_NAME, /* 64 */
XML_ERR_SPACE_REQUIRED, /* 65 */
XML_ERR_SEPARATOR_REQUIRED, /* 66 */
XML_ERR_NMTOKEN_REQUIRED, /* 67 */
XML_ERR_NAME_REQUIRED, /* 68 */
XML_ERR_PCDATA_REQUIRED, /* 69 */
XML_ERR_URI_REQUIRED, /* 70 */
XML_ERR_PUBID_REQUIRED, /* 71 */
XML_ERR_LT_REQUIRED, /* 72 */
XML_ERR_GT_REQUIRED, /* 73 */
XML_ERR_LTSLASH_REQUIRED, /* 74 */
XML_ERR_EQUAL_REQUIRED, /* 75 */
XML_ERR_TAG_NAME_MISMATCH, /* 76 */
XML_ERR_TAG_NOT_FINISHED, /* 77 */
XML_ERR_STANDALONE_VALUE, /* 78 */
XML_ERR_ENCODING_NAME, /* 79 */
XML_ERR_HYPHEN_IN_COMMENT, /* 80 */
XML_ERR_INVALID_ENCODING, /* 81 */
XML_ERR_EXT_ENTITY_STANDALONE, /* 82 */
XML_ERR_CONDSEC_INVALID, /* 83 */
XML_ERR_VALUE_REQUIRED, /* 84 */
XML_ERR_NOT_WELL_BALANCED, /* 85 */
XML_ERR_EXTRA_CONTENT, /* 86 */
XML_ERR_ENTITY_CHAR_ERROR, /* 87 */
XML_ERR_ENTITY_PE_INTERNAL, /* 88 */
XML_ERR_ENTITY_LOOP, /* 89 */
XML_ERR_ENTITY_BOUNDARY, /* 90 */
XML_ERR_INVALID_URI, /* 91 */
XML_ERR_URI_FRAGMENT, /* 92 */
XML_WAR_CATALOG_PI, /* 93 */
XML_ERR_NO_DTD, /* 94 */
XML_ERR_CONDSEC_INVALID_KEYWORD, /* 95 */
XML_ERR_VERSION_MISSING, /* 96 */
XML_WAR_UNKNOWN_VERSION, /* 97 */
XML_WAR_LANG_VALUE, /* 98 */
XML_WAR_NS_URI, /* 99 */
XML_WAR_NS_URI_RELATIVE, /* 100 */
XML_ERR_MISSING_ENCODING, /* 101 */
XML_WAR_SPACE_VALUE, /* 102 */
XML_ERR_NOT_STANDALONE, /* 103 */
XML_ERR_ENTITY_PROCESSING, /* 104 */
XML_ERR_NOTATION_PROCESSING, /* 105 */
XML_WAR_NS_COLUMN, /* 106 */
XML_WAR_ENTITY_REDEFINED, /* 107 */
XML_ERR_UNKNOWN_VERSION, /* 108 */
XML_ERR_VERSION_MISMATCH, /* 109 */
XML_ERR_NAME_TOO_LONG, /* 110 */
XML_ERR_USER_STOP, /* 111 */
XML_NS_ERR_XML_NAMESPACE = 200,
XML_NS_ERR_UNDEFINED_NAMESPACE, /* 201 */
XML_NS_ERR_QNAME, /* 202 */
XML_NS_ERR_ATTRIBUTE_REDEFINED, /* 203 */
XML_NS_ERR_EMPTY, /* 204 */
XML_NS_ERR_COLON, /* 205 */
XML_DTD_ATTRIBUTE_DEFAULT = 500,
XML_DTD_ATTRIBUTE_REDEFINED, /* 501 */
XML_DTD_ATTRIBUTE_VALUE, /* 502 */
XML_DTD_CONTENT_ERROR, /* 503 */
XML_DTD_CONTENT_MODEL, /* 504 */
XML_DTD_CONTENT_NOT_DETERMINIST, /* 505 */
XML_DTD_DIFFERENT_PREFIX, /* 506 */
XML_DTD_ELEM_DEFAULT_NAMESPACE, /* 507 */
XML_DTD_ELEM_NAMESPACE, /* 508 */
XML_DTD_ELEM_REDEFINED, /* 509 */
XML_DTD_EMPTY_NOTATION, /* 510 */
XML_DTD_ENTITY_TYPE, /* 511 */
XML_DTD_ID_FIXED, /* 512 */
XML_DTD_ID_REDEFINED, /* 513 */
XML_DTD_ID_SUBSET, /* 514 */
XML_DTD_INVALID_CHILD, /* 515 */
XML_DTD_INVALID_DEFAULT, /* 516 */
XML_DTD_LOAD_ERROR, /* 517 */
XML_DTD_MISSING_ATTRIBUTE, /* 518 */
XML_DTD_MIXED_CORRUPT, /* 519 */
XML_DTD_MULTIPLE_ID, /* 520 */
XML_DTD_NO_DOC, /* 521 */
XML_DTD_NO_DTD, /* 522 */
XML_DTD_NO_ELEM_NAME, /* 523 */
XML_DTD_NO_PREFIX, /* 524 */
XML_DTD_NO_ROOT, /* 525 */
XML_DTD_NOTATION_REDEFINED, /* 526 */
XML_DTD_NOTATION_VALUE, /* 527 */
XML_DTD_NOT_EMPTY, /* 528 */
XML_DTD_NOT_PCDATA, /* 529 */
XML_DTD_NOT_STANDALONE, /* 530 */
XML_DTD_ROOT_NAME, /* 531 */
XML_DTD_STANDALONE_WHITE_SPACE, /* 532 */
XML_DTD_UNKNOWN_ATTRIBUTE, /* 533 */
XML_DTD_UNKNOWN_ELEM, /* 534 */
XML_DTD_UNKNOWN_ENTITY, /* 535 */
XML_DTD_UNKNOWN_ID, /* 536 */
XML_DTD_UNKNOWN_NOTATION, /* 537 */
XML_DTD_STANDALONE_DEFAULTED, /* 538 */
XML_DTD_XMLID_VALUE, /* 539 */
XML_DTD_XMLID_TYPE, /* 540 */
XML_DTD_DUP_TOKEN, /* 541 */
XML_HTML_STRUCURE_ERROR = 800,
XML_HTML_UNKNOWN_TAG, /* 801 */
XML_RNGP_ANYNAME_ATTR_ANCESTOR = 1000,
XML_RNGP_ATTR_CONFLICT, /* 1001 */
XML_RNGP_ATTRIBUTE_CHILDREN, /* 1002 */
XML_RNGP_ATTRIBUTE_CONTENT, /* 1003 */
XML_RNGP_ATTRIBUTE_EMPTY, /* 1004 */
XML_RNGP_ATTRIBUTE_NOOP, /* 1005 */
XML_RNGP_CHOICE_CONTENT, /* 1006 */
XML_RNGP_CHOICE_EMPTY, /* 1007 */
XML_RNGP_CREATE_FAILURE, /* 1008 */
XML_RNGP_DATA_CONTENT, /* 1009 */
XML_RNGP_DEF_CHOICE_AND_INTERLEAVE, /* 1010 */
XML_RNGP_DEFINE_CREATE_FAILED, /* 1011 */
XML_RNGP_DEFINE_EMPTY, /* 1012 */
XML_RNGP_DEFINE_MISSING, /* 1013 */
XML_RNGP_DEFINE_NAME_MISSING, /* 1014 */
XML_RNGP_ELEM_CONTENT_EMPTY, /* 1015 */
XML_RNGP_ELEM_CONTENT_ERROR, /* 1016 */
XML_RNGP_ELEMENT_EMPTY, /* 1017 */
XML_RNGP_ELEMENT_CONTENT, /* 1018 */
XML_RNGP_ELEMENT_NAME, /* 1019 */
XML_RNGP_ELEMENT_NO_CONTENT, /* 1020 */
XML_RNGP_ELEM_TEXT_CONFLICT, /* 1021 */
XML_RNGP_EMPTY, /* 1022 */
XML_RNGP_EMPTY_CONSTRUCT, /* 1023 */
XML_RNGP_EMPTY_CONTENT, /* 1024 */
XML_RNGP_EMPTY_NOT_EMPTY, /* 1025 */
XML_RNGP_ERROR_TYPE_LIB, /* 1026 */
XML_RNGP_EXCEPT_EMPTY, /* 1027 */
XML_RNGP_EXCEPT_MISSING, /* 1028 */
XML_RNGP_EXCEPT_MULTIPLE, /* 1029 */
XML_RNGP_EXCEPT_NO_CONTENT, /* 1030 */
XML_RNGP_EXTERNALREF_EMTPY, /* 1031 */
XML_RNGP_EXTERNAL_REF_FAILURE, /* 1032 */
XML_RNGP_EXTERNALREF_RECURSE, /* 1033 */
XML_RNGP_FORBIDDEN_ATTRIBUTE, /* 1034 */
XML_RNGP_FOREIGN_ELEMENT, /* 1035 */
XML_RNGP_GRAMMAR_CONTENT, /* 1036 */
XML_RNGP_GRAMMAR_EMPTY, /* 1037 */
XML_RNGP_GRAMMAR_MISSING, /* 1038 */
XML_RNGP_GRAMMAR_NO_START, /* 1039 */
XML_RNGP_GROUP_ATTR_CONFLICT, /* 1040 */
XML_RNGP_HREF_ERROR, /* 1041 */
XML_RNGP_INCLUDE_EMPTY, /* 1042 */
XML_RNGP_INCLUDE_FAILURE, /* 1043 */
XML_RNGP_INCLUDE_RECURSE, /* 1044 */
XML_RNGP_INTERLEAVE_ADD, /* 1045 */
XML_RNGP_INTERLEAVE_CREATE_FAILED, /* 1046 */
XML_RNGP_INTERLEAVE_EMPTY, /* 1047 */
XML_RNGP_INTERLEAVE_NO_CONTENT, /* 1048 */
XML_RNGP_INVALID_DEFINE_NAME, /* 1049 */
XML_RNGP_INVALID_URI, /* 1050 */
XML_RNGP_INVALID_VALUE, /* 1051 */
XML_RNGP_MISSING_HREF, /* 1052 */
XML_RNGP_NAME_MISSING, /* 1053 */
XML_RNGP_NEED_COMBINE, /* 1054 */
XML_RNGP_NOTALLOWED_NOT_EMPTY, /* 1055 */
XML_RNGP_NSNAME_ATTR_ANCESTOR, /* 1056 */
XML_RNGP_NSNAME_NO_NS, /* 1057 */
XML_RNGP_PARAM_FORBIDDEN, /* 1058 */
XML_RNGP_PARAM_NAME_MISSING, /* 1059 */
XML_RNGP_PARENTREF_CREATE_FAILED, /* 1060 */
XML_RNGP_PARENTREF_NAME_INVALID, /* 1061 */
XML_RNGP_PARENTREF_NO_NAME, /* 1062 */
XML_RNGP_PARENTREF_NO_PARENT, /* 1063 */
XML_RNGP_PARENTREF_NOT_EMPTY, /* 1064 */
XML_RNGP_PARSE_ERROR, /* 1065 */
XML_RNGP_PAT_ANYNAME_EXCEPT_ANYNAME, /* 1066 */
XML_RNGP_PAT_ATTR_ATTR, /* 1067 */
XML_RNGP_PAT_ATTR_ELEM, /* 1068 */
XML_RNGP_PAT_DATA_EXCEPT_ATTR, /* 1069 */
XML_RNGP_PAT_DATA_EXCEPT_ELEM, /* 1070 */
XML_RNGP_PAT_DATA_EXCEPT_EMPTY, /* 1071 */
XML_RNGP_PAT_DATA_EXCEPT_GROUP, /* 1072 */
XML_RNGP_PAT_DATA_EXCEPT_INTERLEAVE, /* 1073 */
XML_RNGP_PAT_DATA_EXCEPT_LIST, /* 1074 */
XML_RNGP_PAT_DATA_EXCEPT_ONEMORE, /* 1075 */
XML_RNGP_PAT_DATA_EXCEPT_REF, /* 1076 */
XML_RNGP_PAT_DATA_EXCEPT_TEXT, /* 1077 */
XML_RNGP_PAT_LIST_ATTR, /* 1078 */
XML_RNGP_PAT_LIST_ELEM, /* 1079 */
XML_RNGP_PAT_LIST_INTERLEAVE, /* 1080 */
XML_RNGP_PAT_LIST_LIST, /* 1081 */
XML_RNGP_PAT_LIST_REF, /* 1082 */
XML_RNGP_PAT_LIST_TEXT, /* 1083 */
XML_RNGP_PAT_NSNAME_EXCEPT_ANYNAME, /* 1084 */
XML_RNGP_PAT_NSNAME_EXCEPT_NSNAME, /* 1085 */
XML_RNGP_PAT_ONEMORE_GROUP_ATTR, /* 1086 */
XML_RNGP_PAT_ONEMORE_INTERLEAVE_ATTR, /* 1087 */
XML_RNGP_PAT_START_ATTR, /* 1088 */
XML_RNGP_PAT_START_DATA, /* 1089 */
XML_RNGP_PAT_START_EMPTY, /* 1090 */
XML_RNGP_PAT_START_GROUP, /* 1091 */
XML_RNGP_PAT_START_INTERLEAVE, /* 1092 */
XML_RNGP_PAT_START_LIST, /* 1093 */
XML_RNGP_PAT_START_ONEMORE, /* 1094 */
XML_RNGP_PAT_START_TEXT, /* 1095 */
XML_RNGP_PAT_START_VALUE, /* 1096 */
XML_RNGP_PREFIX_UNDEFINED, /* 1097 */
XML_RNGP_REF_CREATE_FAILED, /* 1098 */
XML_RNGP_REF_CYCLE, /* 1099 */
XML_RNGP_REF_NAME_INVALID, /* 1100 */
XML_RNGP_REF_NO_DEF, /* 1101 */
XML_RNGP_REF_NO_NAME, /* 1102 */
XML_RNGP_REF_NOT_EMPTY, /* 1103 */
XML_RNGP_START_CHOICE_AND_INTERLEAVE, /* 1104 */
XML_RNGP_START_CONTENT, /* 1105 */
XML_RNGP_START_EMPTY, /* 1106 */
XML_RNGP_START_MISSING, /* 1107 */
XML_RNGP_TEXT_EXPECTED, /* 1108 */
XML_RNGP_TEXT_HAS_CHILD, /* 1109 */
XML_RNGP_TYPE_MISSING, /* 1110 */
XML_RNGP_TYPE_NOT_FOUND, /* 1111 */
XML_RNGP_TYPE_VALUE, /* 1112 */
XML_RNGP_UNKNOWN_ATTRIBUTE, /* 1113 */
XML_RNGP_UNKNOWN_COMBINE, /* 1114 */
XML_RNGP_UNKNOWN_CONSTRUCT, /* 1115 */
XML_RNGP_UNKNOWN_TYPE_LIB, /* 1116 */
XML_RNGP_URI_FRAGMENT, /* 1117 */
XML_RNGP_URI_NOT_ABSOLUTE, /* 1118 */
XML_RNGP_VALUE_EMPTY, /* 1119 */
XML_RNGP_VALUE_NO_CONTENT, /* 1120 */
XML_RNGP_XMLNS_NAME, /* 1121 */
XML_RNGP_XML_NS, /* 1122 */
XML_XPATH_EXPRESSION_OK = 1200,
XML_XPATH_NUMBER_ERROR, /* 1201 */
XML_XPATH_UNFINISHED_LITERAL_ERROR, /* 1202 */
XML_XPATH_START_LITERAL_ERROR, /* 1203 */
XML_XPATH_VARIABLE_REF_ERROR, /* 1204 */
XML_XPATH_UNDEF_VARIABLE_ERROR, /* 1205 */
XML_XPATH_INVALID_PREDICATE_ERROR, /* 1206 */
XML_XPATH_EXPR_ERROR, /* 1207 */
XML_XPATH_UNCLOSED_ERROR, /* 1208 */
XML_XPATH_UNKNOWN_FUNC_ERROR, /* 1209 */
XML_XPATH_INVALID_OPERAND, /* 1210 */
XML_XPATH_INVALID_TYPE, /* 1211 */
XML_XPATH_INVALID_ARITY, /* 1212 */
XML_XPATH_INVALID_CTXT_SIZE, /* 1213 */
XML_XPATH_INVALID_CTXT_POSITION, /* 1214 */
XML_XPATH_MEMORY_ERROR, /* 1215 */
XML_XPTR_SYNTAX_ERROR, /* 1216 */
XML_XPTR_RESOURCE_ERROR, /* 1217 */
XML_XPTR_SUB_RESOURCE_ERROR, /* 1218 */
XML_XPATH_UNDEF_PREFIX_ERROR, /* 1219 */
XML_XPATH_ENCODING_ERROR, /* 1220 */
XML_XPATH_INVALID_CHAR_ERROR, /* 1221 */
XML_TREE_INVALID_HEX = 1300,
XML_TREE_INVALID_DEC, /* 1301 */
XML_TREE_UNTERMINATED_ENTITY, /* 1302 */
XML_TREE_NOT_UTF8, /* 1303 */
XML_SAVE_NOT_UTF8 = 1400,
XML_SAVE_CHAR_INVALID, /* 1401 */
XML_SAVE_NO_DOCTYPE, /* 1402 */
XML_SAVE_UNKNOWN_ENCODING, /* 1403 */
XML_REGEXP_COMPILE_ERROR = 1450,
XML_IO_UNKNOWN = 1500,
XML_IO_EACCES, /* 1501 */
XML_IO_EAGAIN, /* 1502 */
XML_IO_EBADF, /* 1503 */
XML_IO_EBADMSG, /* 1504 */
XML_IO_EBUSY, /* 1505 */
XML_IO_ECANCELED, /* 1506 */
XML_IO_ECHILD, /* 1507 */
XML_IO_EDEADLK, /* 1508 */
XML_IO_EDOM, /* 1509 */
XML_IO_EEXIST, /* 1510 */
XML_IO_EFAULT, /* 1511 */
XML_IO_EFBIG, /* 1512 */
XML_IO_EINPROGRESS, /* 1513 */
XML_IO_EINTR, /* 1514 */
XML_IO_EINVAL, /* 1515 */
XML_IO_EIO, /* 1516 */
XML_IO_EISDIR, /* 1517 */
XML_IO_EMFILE, /* 1518 */
XML_IO_EMLINK, /* 1519 */
XML_IO_EMSGSIZE, /* 1520 */
XML_IO_ENAMETOOLONG, /* 1521 */
XML_IO_ENFILE, /* 1522 */
XML_IO_ENODEV, /* 1523 */
XML_IO_ENOENT, /* 1524 */
XML_IO_ENOEXEC, /* 1525 */
XML_IO_ENOLCK, /* 1526 */
XML_IO_ENOMEM, /* 1527 */
XML_IO_ENOSPC, /* 1528 */
XML_IO_ENOSYS, /* 1529 */
XML_IO_ENOTDIR, /* 1530 */
XML_IO_ENOTEMPTY, /* 1531 */
XML_IO_ENOTSUP, /* 1532 */
XML_IO_ENOTTY, /* 1533 */
XML_IO_ENXIO, /* 1534 */
XML_IO_EPERM, /* 1535 */
XML_IO_EPIPE, /* 1536 */
XML_IO_ERANGE, /* 1537 */
XML_IO_EROFS, /* 1538 */
XML_IO_ESPIPE, /* 1539 */
XML_IO_ESRCH, /* 1540 */
XML_IO_ETIMEDOUT, /* 1541 */
XML_IO_EXDEV, /* 1542 */
XML_IO_NETWORK_ATTEMPT, /* 1543 */
XML_IO_ENCODER, /* 1544 */
XML_IO_FLUSH, /* 1545 */
XML_IO_WRITE, /* 1546 */
XML_IO_NO_INPUT, /* 1547 */
XML_IO_BUFFER_FULL, /* 1548 */
XML_IO_LOAD_ERROR, /* 1549 */
XML_IO_ENOTSOCK, /* 1550 */
XML_IO_EISCONN, /* 1551 */
XML_IO_ECONNREFUSED, /* 1552 */
XML_IO_ENETUNREACH, /* 1553 */
XML_IO_EADDRINUSE, /* 1554 */
XML_IO_EALREADY, /* 1555 */
XML_IO_EAFNOSUPPORT, /* 1556 */
XML_XINCLUDE_RECURSION=1600,
XML_XINCLUDE_PARSE_VALUE, /* 1601 */
XML_XINCLUDE_ENTITY_DEF_MISMATCH, /* 1602 */
XML_XINCLUDE_NO_HREF, /* 1603 */
XML_XINCLUDE_NO_FALLBACK, /* 1604 */
XML_XINCLUDE_HREF_URI, /* 1605 */
XML_XINCLUDE_TEXT_FRAGMENT, /* 1606 */
XML_XINCLUDE_TEXT_DOCUMENT, /* 1607 */
XML_XINCLUDE_INVALID_CHAR, /* 1608 */
XML_XINCLUDE_BUILD_FAILED, /* 1609 */
XML_XINCLUDE_UNKNOWN_ENCODING, /* 1610 */
XML_XINCLUDE_MULTIPLE_ROOT, /* 1611 */
XML_XINCLUDE_XPTR_FAILED, /* 1612 */
XML_XINCLUDE_XPTR_RESULT, /* 1613 */
XML_XINCLUDE_INCLUDE_IN_INCLUDE, /* 1614 */
XML_XINCLUDE_FALLBACKS_IN_INCLUDE, /* 1615 */
XML_XINCLUDE_FALLBACK_NOT_IN_INCLUDE, /* 1616 */
XML_XINCLUDE_DEPRECATED_NS, /* 1617 */
XML_XINCLUDE_FRAGMENT_ID, /* 1618 */
XML_CATALOG_MISSING_ATTR = 1650,
XML_CATALOG_ENTRY_BROKEN, /* 1651 */
XML_CATALOG_PREFER_VALUE, /* 1652 */
XML_CATALOG_NOT_CATALOG, /* 1653 */
XML_CATALOG_RECURSION, /* 1654 */
XML_SCHEMAP_PREFIX_UNDEFINED = 1700,
XML_SCHEMAP_ATTRFORMDEFAULT_VALUE, /* 1701 */
XML_SCHEMAP_ATTRGRP_NONAME_NOREF, /* 1702 */
XML_SCHEMAP_ATTR_NONAME_NOREF, /* 1703 */
XML_SCHEMAP_COMPLEXTYPE_NONAME_NOREF, /* 1704 */
XML_SCHEMAP_ELEMFORMDEFAULT_VALUE, /* 1705 */
XML_SCHEMAP_ELEM_NONAME_NOREF, /* 1706 */
XML_SCHEMAP_EXTENSION_NO_BASE, /* 1707 */
XML_SCHEMAP_FACET_NO_VALUE, /* 1708 */
XML_SCHEMAP_FAILED_BUILD_IMPORT, /* 1709 */
XML_SCHEMAP_GROUP_NONAME_NOREF, /* 1710 */
XML_SCHEMAP_IMPORT_NAMESPACE_NOT_URI, /* 1711 */
XML_SCHEMAP_IMPORT_REDEFINE_NSNAME, /* 1712 */
XML_SCHEMAP_IMPORT_SCHEMA_NOT_URI, /* 1713 */
XML_SCHEMAP_INVALID_BOOLEAN, /* 1714 */
XML_SCHEMAP_INVALID_ENUM, /* 1715 */
XML_SCHEMAP_INVALID_FACET, /* 1716 */
XML_SCHEMAP_INVALID_FACET_VALUE, /* 1717 */
XML_SCHEMAP_INVALID_MAXOCCURS, /* 1718 */
XML_SCHEMAP_INVALID_MINOCCURS, /* 1719 */
XML_SCHEMAP_INVALID_REF_AND_SUBTYPE, /* 1720 */
XML_SCHEMAP_INVALID_WHITE_SPACE, /* 1721 */
XML_SCHEMAP_NOATTR_NOREF, /* 1722 */
XML_SCHEMAP_NOTATION_NO_NAME, /* 1723 */
XML_SCHEMAP_NOTYPE_NOREF, /* 1724 */
XML_SCHEMAP_REF_AND_SUBTYPE, /* 1725 */
XML_SCHEMAP_RESTRICTION_NONAME_NOREF, /* 1726 */
XML_SCHEMAP_SIMPLETYPE_NONAME, /* 1727 */
XML_SCHEMAP_TYPE_AND_SUBTYPE, /* 1728 */
XML_SCHEMAP_UNKNOWN_ALL_CHILD, /* 1729 */
XML_SCHEMAP_UNKNOWN_ANYATTRIBUTE_CHILD, /* 1730 */
XML_SCHEMAP_UNKNOWN_ATTR_CHILD, /* 1731 */
XML_SCHEMAP_UNKNOWN_ATTRGRP_CHILD, /* 1732 */
XML_SCHEMAP_UNKNOWN_ATTRIBUTE_GROUP, /* 1733 */
XML_SCHEMAP_UNKNOWN_BASE_TYPE, /* 1734 */
XML_SCHEMAP_UNKNOWN_CHOICE_CHILD, /* 1735 */
XML_SCHEMAP_UNKNOWN_COMPLEXCONTENT_CHILD, /* 1736 */
XML_SCHEMAP_UNKNOWN_COMPLEXTYPE_CHILD, /* 1737 */
XML_SCHEMAP_UNKNOWN_ELEM_CHILD, /* 1738 */
XML_SCHEMAP_UNKNOWN_EXTENSION_CHILD, /* 1739 */
XML_SCHEMAP_UNKNOWN_FACET_CHILD, /* 1740 */
XML_SCHEMAP_UNKNOWN_FACET_TYPE, /* 1741 */
XML_SCHEMAP_UNKNOWN_GROUP_CHILD, /* 1742 */
XML_SCHEMAP_UNKNOWN_IMPORT_CHILD, /* 1743 */
XML_SCHEMAP_UNKNOWN_LIST_CHILD, /* 1744 */
XML_SCHEMAP_UNKNOWN_NOTATION_CHILD, /* 1745 */
XML_SCHEMAP_UNKNOWN_PROCESSCONTENT_CHILD, /* 1746 */
XML_SCHEMAP_UNKNOWN_REF, /* 1747 */
XML_SCHEMAP_UNKNOWN_RESTRICTION_CHILD, /* 1748 */
XML_SCHEMAP_UNKNOWN_SCHEMAS_CHILD, /* 1749 */
XML_SCHEMAP_UNKNOWN_SEQUENCE_CHILD, /* 1750 */
XML_SCHEMAP_UNKNOWN_SIMPLECONTENT_CHILD, /* 1751 */
XML_SCHEMAP_UNKNOWN_SIMPLETYPE_CHILD, /* 1752 */
XML_SCHEMAP_UNKNOWN_TYPE, /* 1753 */
XML_SCHEMAP_UNKNOWN_UNION_CHILD, /* 1754 */
XML_SCHEMAP_ELEM_DEFAULT_FIXED, /* 1755 */
XML_SCHEMAP_REGEXP_INVALID, /* 1756 */
XML_SCHEMAP_FAILED_LOAD, /* 1757 */
XML_SCHEMAP_NOTHING_TO_PARSE, /* 1758 */
XML_SCHEMAP_NOROOT, /* 1759 */
XML_SCHEMAP_REDEFINED_GROUP, /* 1760 */
XML_SCHEMAP_REDEFINED_TYPE, /* 1761 */
XML_SCHEMAP_REDEFINED_ELEMENT, /* 1762 */
XML_SCHEMAP_REDEFINED_ATTRGROUP, /* 1763 */
XML_SCHEMAP_REDEFINED_ATTR, /* 1764 */
XML_SCHEMAP_REDEFINED_NOTATION, /* 1765 */
XML_SCHEMAP_FAILED_PARSE, /* 1766 */
XML_SCHEMAP_UNKNOWN_PREFIX, /* 1767 */
XML_SCHEMAP_DEF_AND_PREFIX, /* 1768 */
XML_SCHEMAP_UNKNOWN_INCLUDE_CHILD, /* 1769 */
XML_SCHEMAP_INCLUDE_SCHEMA_NOT_URI, /* 1770 */
XML_SCHEMAP_INCLUDE_SCHEMA_NO_URI, /* 1771 */
XML_SCHEMAP_NOT_SCHEMA, /* 1772 */
XML_SCHEMAP_UNKNOWN_MEMBER_TYPE, /* 1773 */
XML_SCHEMAP_INVALID_ATTR_USE, /* 1774 */
XML_SCHEMAP_RECURSIVE, /* 1775 */
XML_SCHEMAP_SUPERNUMEROUS_LIST_ITEM_TYPE, /* 1776 */
XML_SCHEMAP_INVALID_ATTR_COMBINATION, /* 1777 */
XML_SCHEMAP_INVALID_ATTR_INLINE_COMBINATION, /* 1778 */
XML_SCHEMAP_MISSING_SIMPLETYPE_CHILD, /* 1779 */
XML_SCHEMAP_INVALID_ATTR_NAME, /* 1780 */
XML_SCHEMAP_REF_AND_CONTENT, /* 1781 */
XML_SCHEMAP_CT_PROPS_CORRECT_1, /* 1782 */
XML_SCHEMAP_CT_PROPS_CORRECT_2, /* 1783 */
XML_SCHEMAP_CT_PROPS_CORRECT_3, /* 1784 */
XML_SCHEMAP_CT_PROPS_CORRECT_4, /* 1785 */
XML_SCHEMAP_CT_PROPS_CORRECT_5, /* 1786 */
XML_SCHEMAP_DERIVATION_OK_RESTRICTION_1, /* 1787 */
XML_SCHEMAP_DERIVATION_OK_RESTRICTION_2_1_1, /* 1788 */
XML_SCHEMAP_DERIVATION_OK_RESTRICTION_2_1_2, /* 1789 */
XML_SCHEMAP_DERIVATION_OK_RESTRICTION_2_2, /* 1790 */
XML_SCHEMAP_DERIVATION_OK_RESTRICTION_3, /* 1791 */
XML_SCHEMAP_WILDCARD_INVALID_NS_MEMBER, /* 1792 */
XML_SCHEMAP_INTERSECTION_NOT_EXPRESSIBLE, /* 1793 */
XML_SCHEMAP_UNION_NOT_EXPRESSIBLE, /* 1794 */
XML_SCHEMAP_SRC_IMPORT_3_1, /* 1795 */
XML_SCHEMAP_SRC_IMPORT_3_2, /* 1796 */
XML_SCHEMAP_DERIVATION_OK_RESTRICTION_4_1, /* 1797 */
XML_SCHEMAP_DERIVATION_OK_RESTRICTION_4_2, /* 1798 */
XML_SCHEMAP_DERIVATION_OK_RESTRICTION_4_3, /* 1799 */
XML_SCHEMAP_COS_CT_EXTENDS_1_3, /* 1800 */
XML_SCHEMAV_NOROOT = 1801,
XML_SCHEMAV_UNDECLAREDELEM, /* 1802 */
XML_SCHEMAV_NOTTOPLEVEL, /* 1803 */
XML_SCHEMAV_MISSING, /* 1804 */
XML_SCHEMAV_WRONGELEM, /* 1805 */
XML_SCHEMAV_NOTYPE, /* 1806 */
XML_SCHEMAV_NOROLLBACK, /* 1807 */
XML_SCHEMAV_ISABSTRACT, /* 1808 */
XML_SCHEMAV_NOTEMPTY, /* 1809 */
XML_SCHEMAV_ELEMCONT, /* 1810 */
XML_SCHEMAV_HAVEDEFAULT, /* 1811 */
XML_SCHEMAV_NOTNILLABLE, /* 1812 */
XML_SCHEMAV_EXTRACONTENT, /* 1813 */
XML_SCHEMAV_INVALIDATTR, /* 1814 */
XML_SCHEMAV_INVALIDELEM, /* 1815 */
XML_SCHEMAV_NOTDETERMINIST, /* 1816 */
XML_SCHEMAV_CONSTRUCT, /* 1817 */
XML_SCHEMAV_INTERNAL, /* 1818 */
XML_SCHEMAV_NOTSIMPLE, /* 1819 */
XML_SCHEMAV_ATTRUNKNOWN, /* 1820 */
XML_SCHEMAV_ATTRINVALID, /* 1821 */
XML_SCHEMAV_VALUE, /* 1822 */
XML_SCHEMAV_FACET, /* 1823 */
XML_SCHEMAV_CVC_DATATYPE_VALID_1_2_1, /* 1824 */
XML_SCHEMAV_CVC_DATATYPE_VALID_1_2_2, /* 1825 */
XML_SCHEMAV_CVC_DATATYPE_VALID_1_2_3, /* 1826 */
XML_SCHEMAV_CVC_TYPE_3_1_1, /* 1827 */
XML_SCHEMAV_CVC_TYPE_3_1_2, /* 1828 */
XML_SCHEMAV_CVC_FACET_VALID, /* 1829 */
XML_SCHEMAV_CVC_LENGTH_VALID, /* 1830 */
XML_SCHEMAV_CVC_MINLENGTH_VALID, /* 1831 */
XML_SCHEMAV_CVC_MAXLENGTH_VALID, /* 1832 */
XML_SCHEMAV_CVC_MININCLUSIVE_VALID, /* 1833 */
XML_SCHEMAV_CVC_MAXINCLUSIVE_VALID, /* 1834 */
XML_SCHEMAV_CVC_MINEXCLUSIVE_VALID, /* 1835 */
XML_SCHEMAV_CVC_MAXEXCLUSIVE_VALID, /* 1836 */
XML_SCHEMAV_CVC_TOTALDIGITS_VALID, /* 1837 */
XML_SCHEMAV_CVC_FRACTIONDIGITS_VALID, /* 1838 */
XML_SCHEMAV_CVC_PATTERN_VALID, /* 1839 */
XML_SCHEMAV_CVC_ENUMERATION_VALID, /* 1840 */
XML_SCHEMAV_CVC_COMPLEX_TYPE_2_1, /* 1841 */
XML_SCHEMAV_CVC_COMPLEX_TYPE_2_2, /* 1842 */
XML_SCHEMAV_CVC_COMPLEX_TYPE_2_3, /* 1843 */
XML_SCHEMAV_CVC_COMPLEX_TYPE_2_4, /* 1844 */
XML_SCHEMAV_CVC_ELT_1, /* 1845 */
XML_SCHEMAV_CVC_ELT_2, /* 1846 */
XML_SCHEMAV_CVC_ELT_3_1, /* 1847 */
XML_SCHEMAV_CVC_ELT_3_2_1, /* 1848 */
XML_SCHEMAV_CVC_ELT_3_2_2, /* 1849 */
XML_SCHEMAV_CVC_ELT_4_1, /* 1850 */
XML_SCHEMAV_CVC_ELT_4_2, /* 1851 */
XML_SCHEMAV_CVC_ELT_4_3, /* 1852 */
XML_SCHEMAV_CVC_ELT_5_1_1, /* 1853 */
XML_SCHEMAV_CVC_ELT_5_1_2, /* 1854 */
XML_SCHEMAV_CVC_ELT_5_2_1, /* 1855 */
XML_SCHEMAV_CVC_ELT_5_2_2_1, /* 1856 */
XML_SCHEMAV_CVC_ELT_5_2_2_2_1, /* 1857 */
XML_SCHEMAV_CVC_ELT_5_2_2_2_2, /* 1858 */
XML_SCHEMAV_CVC_ELT_6, /* 1859 */
XML_SCHEMAV_CVC_ELT_7, /* 1860 */
XML_SCHEMAV_CVC_ATTRIBUTE_1, /* 1861 */
XML_SCHEMAV_CVC_ATTRIBUTE_2, /* 1862 */
XML_SCHEMAV_CVC_ATTRIBUTE_3, /* 1863 */
XML_SCHEMAV_CVC_ATTRIBUTE_4, /* 1864 */
XML_SCHEMAV_CVC_COMPLEX_TYPE_3_1, /* 1865 */
XML_SCHEMAV_CVC_COMPLEX_TYPE_3_2_1, /* 1866 */
XML_SCHEMAV_CVC_COMPLEX_TYPE_3_2_2, /* 1867 */
XML_SCHEMAV_CVC_COMPLEX_TYPE_4, /* 1868 */
XML_SCHEMAV_CVC_COMPLEX_TYPE_5_1, /* 1869 */
XML_SCHEMAV_CVC_COMPLEX_TYPE_5_2, /* 1870 */
XML_SCHEMAV_ELEMENT_CONTENT, /* 1871 */
XML_SCHEMAV_DOCUMENT_ELEMENT_MISSING, /* 1872 */
XML_SCHEMAV_CVC_COMPLEX_TYPE_1, /* 1873 */
XML_SCHEMAV_CVC_AU, /* 1874 */
XML_SCHEMAV_CVC_TYPE_1, /* 1875 */
XML_SCHEMAV_CVC_TYPE_2, /* 1876 */
XML_SCHEMAV_CVC_IDC, /* 1877 */
XML_SCHEMAV_CVC_WILDCARD, /* 1878 */
XML_SCHEMAV_MISC, /* 1879 */
XML_XPTR_UNKNOWN_SCHEME = 1900,
XML_XPTR_CHILDSEQ_START, /* 1901 */
XML_XPTR_EVAL_FAILED, /* 1902 */
XML_XPTR_EXTRA_OBJECTS, /* 1903 */
XML_C14N_CREATE_CTXT = 1950,
XML_C14N_REQUIRES_UTF8, /* 1951 */
XML_C14N_CREATE_STACK, /* 1952 */
XML_C14N_INVALID_NODE, /* 1953 */
XML_C14N_UNKNOW_NODE, /* 1954 */
XML_C14N_RELATIVE_NAMESPACE, /* 1955 */
XML_FTP_PASV_ANSWER = 2000,
XML_FTP_EPSV_ANSWER, /* 2001 */
XML_FTP_ACCNT, /* 2002 */
XML_FTP_URL_SYNTAX, /* 2003 */
XML_HTTP_URL_SYNTAX = 2020,
XML_HTTP_USE_IP, /* 2021 */
XML_HTTP_UNKNOWN_HOST, /* 2022 */
XML_SCHEMAP_SRC_SIMPLE_TYPE_1 = 3000,
XML_SCHEMAP_SRC_SIMPLE_TYPE_2, /* 3001 */
XML_SCHEMAP_SRC_SIMPLE_TYPE_3, /* 3002 */
XML_SCHEMAP_SRC_SIMPLE_TYPE_4, /* 3003 */
XML_SCHEMAP_SRC_RESOLVE, /* 3004 */
XML_SCHEMAP_SRC_RESTRICTION_BASE_OR_SIMPLETYPE, /* 3005 */
XML_SCHEMAP_SRC_LIST_ITEMTYPE_OR_SIMPLETYPE, /* 3006 */
XML_SCHEMAP_SRC_UNION_MEMBERTYPES_OR_SIMPLETYPES, /* 3007 */
XML_SCHEMAP_ST_PROPS_CORRECT_1, /* 3008 */
XML_SCHEMAP_ST_PROPS_CORRECT_2, /* 3009 */
XML_SCHEMAP_ST_PROPS_CORRECT_3, /* 3010 */
XML_SCHEMAP_COS_ST_RESTRICTS_1_1, /* 3011 */
XML_SCHEMAP_COS_ST_RESTRICTS_1_2, /* 3012 */
XML_SCHEMAP_COS_ST_RESTRICTS_1_3_1, /* 3013 */
XML_SCHEMAP_COS_ST_RESTRICTS_1_3_2, /* 3014 */
XML_SCHEMAP_COS_ST_RESTRICTS_2_1, /* 3015 */
XML_SCHEMAP_COS_ST_RESTRICTS_2_3_1_1, /* 3016 */
XML_SCHEMAP_COS_ST_RESTRICTS_2_3_1_2, /* 3017 */
XML_SCHEMAP_COS_ST_RESTRICTS_2_3_2_1, /* 3018 */
XML_SCHEMAP_COS_ST_RESTRICTS_2_3_2_2, /* 3019 */
XML_SCHEMAP_COS_ST_RESTRICTS_2_3_2_3, /* 3020 */
XML_SCHEMAP_COS_ST_RESTRICTS_2_3_2_4, /* 3021 */
XML_SCHEMAP_COS_ST_RESTRICTS_2_3_2_5, /* 3022 */
XML_SCHEMAP_COS_ST_RESTRICTS_3_1, /* 3023 */
XML_SCHEMAP_COS_ST_RESTRICTS_3_3_1, /* 3024 */
XML_SCHEMAP_COS_ST_RESTRICTS_3_3_1_2, /* 3025 */
XML_SCHEMAP_COS_ST_RESTRICTS_3_3_2_2, /* 3026 */
XML_SCHEMAP_COS_ST_RESTRICTS_3_3_2_1, /* 3027 */
XML_SCHEMAP_COS_ST_RESTRICTS_3_3_2_3, /* 3028 */
XML_SCHEMAP_COS_ST_RESTRICTS_3_3_2_4, /* 3029 */
XML_SCHEMAP_COS_ST_RESTRICTS_3_3_2_5, /* 3030 */
XML_SCHEMAP_COS_ST_DERIVED_OK_2_1, /* 3031 */
XML_SCHEMAP_COS_ST_DERIVED_OK_2_2, /* 3032 */
XML_SCHEMAP_S4S_ELEM_NOT_ALLOWED, /* 3033 */
XML_SCHEMAP_S4S_ELEM_MISSING, /* 3034 */
XML_SCHEMAP_S4S_ATTR_NOT_ALLOWED, /* 3035 */
XML_SCHEMAP_S4S_ATTR_MISSING, /* 3036 */
XML_SCHEMAP_S4S_ATTR_INVALID_VALUE, /* 3037 */
XML_SCHEMAP_SRC_ELEMENT_1, /* 3038 */
XML_SCHEMAP_SRC_ELEMENT_2_1, /* 3039 */
XML_SCHEMAP_SRC_ELEMENT_2_2, /* 3040 */
XML_SCHEMAP_SRC_ELEMENT_3, /* 3041 */
XML_SCHEMAP_P_PROPS_CORRECT_1, /* 3042 */
XML_SCHEMAP_P_PROPS_CORRECT_2_1, /* 3043 */
XML_SCHEMAP_P_PROPS_CORRECT_2_2, /* 3044 */
XML_SCHEMAP_E_PROPS_CORRECT_2, /* 3045 */
XML_SCHEMAP_E_PROPS_CORRECT_3, /* 3046 */
XML_SCHEMAP_E_PROPS_CORRECT_4, /* 3047 */
XML_SCHEMAP_E_PROPS_CORRECT_5, /* 3048 */
XML_SCHEMAP_E_PROPS_CORRECT_6, /* 3049 */
XML_SCHEMAP_SRC_INCLUDE, /* 3050 */
XML_SCHEMAP_SRC_ATTRIBUTE_1, /* 3051 */
XML_SCHEMAP_SRC_ATTRIBUTE_2, /* 3052 */
XML_SCHEMAP_SRC_ATTRIBUTE_3_1, /* 3053 */
XML_SCHEMAP_SRC_ATTRIBUTE_3_2, /* 3054 */
XML_SCHEMAP_SRC_ATTRIBUTE_4, /* 3055 */
XML_SCHEMAP_NO_XMLNS, /* 3056 */
XML_SCHEMAP_NO_XSI, /* 3057 */
XML_SCHEMAP_COS_VALID_DEFAULT_1, /* 3058 */
XML_SCHEMAP_COS_VALID_DEFAULT_2_1, /* 3059 */
XML_SCHEMAP_COS_VALID_DEFAULT_2_2_1, /* 3060 */
XML_SCHEMAP_COS_VALID_DEFAULT_2_2_2, /* 3061 */
XML_SCHEMAP_CVC_SIMPLE_TYPE, /* 3062 */
XML_SCHEMAP_COS_CT_EXTENDS_1_1, /* 3063 */
XML_SCHEMAP_SRC_IMPORT_1_1, /* 3064 */
XML_SCHEMAP_SRC_IMPORT_1_2, /* 3065 */
XML_SCHEMAP_SRC_IMPORT_2, /* 3066 */
XML_SCHEMAP_SRC_IMPORT_2_1, /* 3067 */
XML_SCHEMAP_SRC_IMPORT_2_2, /* 3068 */
XML_SCHEMAP_INTERNAL, /* 3069 non-W3C */
XML_SCHEMAP_NOT_DETERMINISTIC, /* 3070 non-W3C */
XML_SCHEMAP_SRC_ATTRIBUTE_GROUP_1, /* 3071 */
XML_SCHEMAP_SRC_ATTRIBUTE_GROUP_2, /* 3072 */
XML_SCHEMAP_SRC_ATTRIBUTE_GROUP_3, /* 3073 */
XML_SCHEMAP_MG_PROPS_CORRECT_1, /* 3074 */
XML_SCHEMAP_MG_PROPS_CORRECT_2, /* 3075 */
XML_SCHEMAP_SRC_CT_1, /* 3076 */
XML_SCHEMAP_DERIVATION_OK_RESTRICTION_2_1_3, /* 3077 */
XML_SCHEMAP_AU_PROPS_CORRECT_2, /* 3078 */
XML_SCHEMAP_A_PROPS_CORRECT_2, /* 3079 */
XML_SCHEMAP_C_PROPS_CORRECT, /* 3080 */
XML_SCHEMAP_SRC_REDEFINE, /* 3081 */
XML_SCHEMAP_SRC_IMPORT, /* 3082 */
XML_SCHEMAP_WARN_SKIP_SCHEMA, /* 3083 */
XML_SCHEMAP_WARN_UNLOCATED_SCHEMA, /* 3084 */
XML_SCHEMAP_WARN_ATTR_REDECL_PROH, /* 3085 */
XML_SCHEMAP_WARN_ATTR_POINTLESS_PROH, /* 3085 */
XML_SCHEMAP_AG_PROPS_CORRECT, /* 3086 */
XML_SCHEMAP_COS_CT_EXTENDS_1_2, /* 3087 */
XML_SCHEMAP_AU_PROPS_CORRECT, /* 3088 */
XML_SCHEMAP_A_PROPS_CORRECT_3, /* 3089 */
XML_SCHEMAP_COS_ALL_LIMITED, /* 3090 */
XML_SCHEMATRONV_ASSERT = 4000, /* 4000 */
XML_SCHEMATRONV_REPORT,
XML_MODULE_OPEN = 4900, /* 4900 */
XML_MODULE_CLOSE, /* 4901 */
XML_CHECK_FOUND_ELEMENT = 5000,
XML_CHECK_FOUND_ATTRIBUTE, /* 5001 */
XML_CHECK_FOUND_TEXT, /* 5002 */
XML_CHECK_FOUND_CDATA, /* 5003 */
XML_CHECK_FOUND_ENTITYREF, /* 5004 */
XML_CHECK_FOUND_ENTITY, /* 5005 */
XML_CHECK_FOUND_PI, /* 5006 */
XML_CHECK_FOUND_COMMENT, /* 5007 */
XML_CHECK_FOUND_DOCTYPE, /* 5008 */
XML_CHECK_FOUND_FRAGMENT, /* 5009 */
XML_CHECK_FOUND_NOTATION, /* 5010 */
XML_CHECK_UNKNOWN_NODE, /* 5011 */
XML_CHECK_ENTITY_TYPE, /* 5012 */
XML_CHECK_NO_PARENT, /* 5013 */
XML_CHECK_NO_DOC, /* 5014 */
XML_CHECK_NO_NAME, /* 5015 */
XML_CHECK_NO_ELEM, /* 5016 */
XML_CHECK_WRONG_DOC, /* 5017 */
XML_CHECK_NO_PREV, /* 5018 */
XML_CHECK_WRONG_PREV, /* 5019 */
XML_CHECK_NO_NEXT, /* 5020 */
XML_CHECK_WRONG_NEXT, /* 5021 */
XML_CHECK_NOT_DTD, /* 5022 */
XML_CHECK_NOT_ATTR, /* 5023 */
XML_CHECK_NOT_ATTR_DECL, /* 5024 */
XML_CHECK_NOT_ELEM_DECL, /* 5025 */
XML_CHECK_NOT_ENTITY_DECL, /* 5026 */
XML_CHECK_NOT_NS_DECL, /* 5027 */
XML_CHECK_NO_HREF, /* 5028 */
XML_CHECK_WRONG_PARENT,/* 5029 */
XML_CHECK_NS_SCOPE, /* 5030 */
XML_CHECK_NS_ANCESTOR, /* 5031 */
XML_CHECK_NOT_UTF8, /* 5032 */
XML_CHECK_NO_DICT, /* 5033 */
XML_CHECK_NOT_NCNAME, /* 5034 */
XML_CHECK_OUTSIDE_DICT, /* 5035 */
XML_CHECK_WRONG_NAME, /* 5036 */
XML_CHECK_NAME_NOT_NULL, /* 5037 */
XML_I18N_NO_NAME = 6000,
XML_I18N_NO_HANDLER, /* 6001 */
XML_I18N_EXCESS_HANDLER, /* 6002 */
XML_I18N_CONV_FAILED, /* 6003 */
XML_I18N_NO_OUTPUT, /* 6004 */
XML_BUF_OVERFLOW = 7000
} xmlParserErrors;
/**
* xmlGenericErrorFunc:
* @ctx: a parsing context
* @msg: the message
* @...: the extra arguments of the varags to format the message
*
* Signature of the function to use when there is an error and
* no parsing or validity context available .
*/
typedef void (XMLCDECL *xmlGenericErrorFunc) (void *ctx,
const char *msg,
...) LIBXML_ATTR_FORMAT(2,3);
/**
* xmlStructuredErrorFunc:
* @userData: user provided data for the error callback
* @error: the error being raised.
*
* Signature of the function to use when there is an error and
* the module handles the new error reporting mechanism.
*/
typedef void (XMLCALL *xmlStructuredErrorFunc) (void *userData, xmlErrorPtr error);
/*
* Use the following function to reset the two global variables
* xmlGenericError and xmlGenericErrorContext.
*/
XMLPUBFUN void XMLCALL
xmlSetGenericErrorFunc (void *ctx,
xmlGenericErrorFunc handler);
XMLPUBFUN void XMLCALL
initGenericErrorDefaultFunc (xmlGenericErrorFunc *handler);
XMLPUBFUN void XMLCALL
xmlSetStructuredErrorFunc (void *ctx,
xmlStructuredErrorFunc handler);
/*
* Default message routines used by SAX and Valid context for error
* and warning reporting.
*/
XMLPUBFUN void XMLCDECL
xmlParserError (void *ctx,
const char *msg,
...) LIBXML_ATTR_FORMAT(2,3);
XMLPUBFUN void XMLCDECL
xmlParserWarning (void *ctx,
const char *msg,
...) LIBXML_ATTR_FORMAT(2,3);
XMLPUBFUN void XMLCDECL
xmlParserValidityError (void *ctx,
const char *msg,
...) LIBXML_ATTR_FORMAT(2,3);
XMLPUBFUN void XMLCDECL
xmlParserValidityWarning (void *ctx,
const char *msg,
...) LIBXML_ATTR_FORMAT(2,3);
XMLPUBFUN void XMLCALL
xmlParserPrintFileInfo (xmlParserInputPtr input);
XMLPUBFUN void XMLCALL
xmlParserPrintFileContext (xmlParserInputPtr input);
/*
* Extended error information routines
*/
XMLPUBFUN xmlErrorPtr XMLCALL
xmlGetLastError (void);
XMLPUBFUN void XMLCALL
xmlResetLastError (void);
XMLPUBFUN xmlErrorPtr XMLCALL
xmlCtxtGetLastError (void *ctx);
XMLPUBFUN void XMLCALL
xmlCtxtResetLastError (void *ctx);
XMLPUBFUN void XMLCALL
xmlResetError (xmlErrorPtr err);
XMLPUBFUN int XMLCALL
xmlCopyError (xmlErrorPtr from,
xmlErrorPtr to);
#ifdef IN_LIBXML
/*
* Internal callback reporting routine
*/
XMLPUBFUN void XMLCALL
__xmlRaiseError (xmlStructuredErrorFunc schannel,
xmlGenericErrorFunc channel,
void *data,
void *ctx,
void *node,
int domain,
int code,
xmlErrorLevel level,
const char *file,
int line,
const char *str1,
const char *str2,
const char *str3,
int int1,
int col,
const char *msg,
...) LIBXML_ATTR_FORMAT(16,17);
XMLPUBFUN void XMLCALL
__xmlSimpleError (int domain,
int code,
xmlNodePtr node,
const char *msg,
const char *extra) LIBXML_ATTR_FORMAT(4,0);
#endif
#ifdef __cplusplus
}
#endif
#endif /* __XML_ERROR_H__ */

@ -0,0 +1,162 @@
/*
* Summary: macros for marking symbols as exportable/importable.
* Description: macros for marking symbols as exportable/importable.
*
* Copy: See Copyright for the status of this software.
*
* Author: Igor Zlatovic <igor@zlatkovic.com>
*/
#ifndef __XML_EXPORTS_H__
#define __XML_EXPORTS_H__
/**
* XMLPUBFUN, XMLPUBVAR, XMLCALL
*
* Macros which declare an exportable function, an exportable variable and
* the calling convention used for functions.
*
* Please use an extra block for every platform/compiler combination when
* modifying this, rather than overlong #ifdef lines. This helps
* readability as well as the fact that different compilers on the same
* platform might need different definitions.
*/
/**
* XMLPUBFUN:
*
* Macros which declare an exportable function
*/
#define XMLPUBFUN
/**
* XMLPUBVAR:
*
* Macros which declare an exportable variable
*/
#define XMLPUBVAR extern
/**
* XMLCALL:
*
* Macros which declare the called convention for exported functions
*/
#define XMLCALL
/**
* XMLCDECL:
*
* Macro which declares the calling convention for exported functions that
* use '...'.
*/
#define XMLCDECL
/** DOC_DISABLE */
/* Windows platform with MS compiler */
#if defined(_WIN32) && defined(_MSC_VER)
#undef XMLPUBFUN
#undef XMLPUBVAR
#undef XMLCALL
#undef XMLCDECL
#if defined(IN_LIBXML) && !defined(LIBXML_STATIC)
#define XMLPUBFUN __declspec(dllexport)
#define XMLPUBVAR __declspec(dllexport)
#else
#define XMLPUBFUN
#if !defined(LIBXML_STATIC)
#define XMLPUBVAR __declspec(dllimport) extern
#else
#define XMLPUBVAR extern
#endif
#endif
#if defined(LIBXML_FASTCALL)
#define XMLCALL __fastcall
#else
#define XMLCALL __cdecl
#endif
#define XMLCDECL __cdecl
#if !defined _REENTRANT
#define _REENTRANT
#endif
#endif
/* Windows platform with Borland compiler */
#if defined(_WIN32) && defined(__BORLANDC__)
#undef XMLPUBFUN
#undef XMLPUBVAR
#undef XMLCALL
#undef XMLCDECL
#if defined(IN_LIBXML) && !defined(LIBXML_STATIC)
#define XMLPUBFUN __declspec(dllexport)
#define XMLPUBVAR __declspec(dllexport) extern
#else
#define XMLPUBFUN
#if !defined(LIBXML_STATIC)
#define XMLPUBVAR __declspec(dllimport) extern
#else
#define XMLPUBVAR extern
#endif
#endif
#define XMLCALL __cdecl
#define XMLCDECL __cdecl
#if !defined _REENTRANT
#define _REENTRANT
#endif
#endif
/* Windows platform with GNU compiler (Mingw) */
#if defined(_WIN32) && defined(__MINGW32__)
#undef XMLPUBFUN
#undef XMLPUBVAR
#undef XMLCALL
#undef XMLCDECL
/*
* if defined(IN_LIBXML) this raises problems on mingw with msys
* _imp__xmlFree listed as missing. Try to workaround the problem
* by also making that declaration when compiling client code.
*/
#if defined(IN_LIBXML) && !defined(LIBXML_STATIC)
#define XMLPUBFUN __declspec(dllexport)
#define XMLPUBVAR __declspec(dllexport) extern
#else
#define XMLPUBFUN
#if !defined(LIBXML_STATIC)
#define XMLPUBVAR __declspec(dllimport) extern
#else
#define XMLPUBVAR extern
#endif
#endif
#define XMLCALL __cdecl
#define XMLCDECL __cdecl
#if !defined _REENTRANT
#define _REENTRANT
#endif
#endif
/* Cygwin platform, GNU compiler */
#if defined(_WIN32) && defined(__CYGWIN__)
#undef XMLPUBFUN
#undef XMLPUBVAR
#undef XMLCALL
#undef XMLCDECL
#if defined(IN_LIBXML) && !defined(LIBXML_STATIC)
#define XMLPUBFUN __declspec(dllexport)
#define XMLPUBVAR __declspec(dllexport)
#else
#define XMLPUBFUN
#if !defined(LIBXML_STATIC)
#define XMLPUBVAR __declspec(dllimport) extern
#else
#define XMLPUBVAR
#endif
#endif
#define XMLCALL __cdecl
#define XMLCDECL __cdecl
#endif
/* Compatibility */
#if !defined(LIBXML_DLL_IMPORT)
#define LIBXML_DLL_IMPORT XMLPUBVAR
#endif
#endif /* __XML_EXPORTS_H__ */

@ -0,0 +1,224 @@
/*
* Summary: interface for the memory allocator
* Description: provides interfaces for the memory allocator,
* including debugging capabilities.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __DEBUG_MEMORY_ALLOC__
#define __DEBUG_MEMORY_ALLOC__
#include <stdio.h>
#include <libxml/xmlversion.h>
/**
* DEBUG_MEMORY:
*
* DEBUG_MEMORY replaces the allocator with a collect and debug
* shell to the libc allocator.
* DEBUG_MEMORY should only be activated when debugging
* libxml i.e. if libxml has been configured with --with-debug-mem too.
*/
/* #define DEBUG_MEMORY_FREED */
/* #define DEBUG_MEMORY_LOCATION */
#ifdef DEBUG
#ifndef DEBUG_MEMORY
#define DEBUG_MEMORY
#endif
#endif
/**
* DEBUG_MEMORY_LOCATION:
*
* DEBUG_MEMORY_LOCATION should be activated only when debugging
* libxml i.e. if libxml has been configured with --with-debug-mem too.
*/
#ifdef DEBUG_MEMORY_LOCATION
#endif
#ifdef __cplusplus
extern "C" {
#endif
/*
* The XML memory wrapper support 4 basic overloadable functions.
*/
/**
* xmlFreeFunc:
* @mem: an already allocated block of memory
*
* Signature for a free() implementation.
*/
typedef void (XMLCALL *xmlFreeFunc)(void *mem);
/**
* xmlMallocFunc:
* @size: the size requested in bytes
*
* Signature for a malloc() implementation.
*
* Returns a pointer to the newly allocated block or NULL in case of error.
*/
typedef void *(LIBXML_ATTR_ALLOC_SIZE(1) XMLCALL *xmlMallocFunc)(size_t size);
/**
* xmlReallocFunc:
* @mem: an already allocated block of memory
* @size: the new size requested in bytes
*
* Signature for a realloc() implementation.
*
* Returns a pointer to the newly reallocated block or NULL in case of error.
*/
typedef void *(XMLCALL *xmlReallocFunc)(void *mem, size_t size);
/**
* xmlStrdupFunc:
* @str: a zero terminated string
*
* Signature for an strdup() implementation.
*
* Returns the copy of the string or NULL in case of error.
*/
typedef char *(XMLCALL *xmlStrdupFunc)(const char *str);
/*
* The 4 interfaces used for all memory handling within libxml.
LIBXML_DLL_IMPORT xmlFreeFunc xmlFree;
LIBXML_DLL_IMPORT xmlMallocFunc xmlMalloc;
LIBXML_DLL_IMPORT xmlMallocFunc xmlMallocAtomic;
LIBXML_DLL_IMPORT xmlReallocFunc xmlRealloc;
LIBXML_DLL_IMPORT xmlStrdupFunc xmlMemStrdup;
*/
/*
* The way to overload the existing functions.
* The xmlGc function have an extra entry for atomic block
* allocations useful for garbage collected memory allocators
*/
XMLPUBFUN int XMLCALL
xmlMemSetup (xmlFreeFunc freeFunc,
xmlMallocFunc mallocFunc,
xmlReallocFunc reallocFunc,
xmlStrdupFunc strdupFunc);
XMLPUBFUN int XMLCALL
xmlMemGet (xmlFreeFunc *freeFunc,
xmlMallocFunc *mallocFunc,
xmlReallocFunc *reallocFunc,
xmlStrdupFunc *strdupFunc);
XMLPUBFUN int XMLCALL
xmlGcMemSetup (xmlFreeFunc freeFunc,
xmlMallocFunc mallocFunc,
xmlMallocFunc mallocAtomicFunc,
xmlReallocFunc reallocFunc,
xmlStrdupFunc strdupFunc);
XMLPUBFUN int XMLCALL
xmlGcMemGet (xmlFreeFunc *freeFunc,
xmlMallocFunc *mallocFunc,
xmlMallocFunc *mallocAtomicFunc,
xmlReallocFunc *reallocFunc,
xmlStrdupFunc *strdupFunc);
/*
* Initialization of the memory layer.
*/
XMLPUBFUN int XMLCALL
xmlInitMemory (void);
/*
* Cleanup of the memory layer.
*/
XMLPUBFUN void XMLCALL
xmlCleanupMemory (void);
/*
* These are specific to the XML debug memory wrapper.
*/
XMLPUBFUN int XMLCALL
xmlMemUsed (void);
XMLPUBFUN int XMLCALL
xmlMemBlocks (void);
XMLPUBFUN void XMLCALL
xmlMemDisplay (FILE *fp);
XMLPUBFUN void XMLCALL
xmlMemDisplayLast(FILE *fp, long nbBytes);
XMLPUBFUN void XMLCALL
xmlMemShow (FILE *fp, int nr);
XMLPUBFUN void XMLCALL
xmlMemoryDump (void);
XMLPUBFUN void * XMLCALL
xmlMemMalloc (size_t size) LIBXML_ATTR_ALLOC_SIZE(1);
XMLPUBFUN void * XMLCALL
xmlMemRealloc (void *ptr,size_t size);
XMLPUBFUN void XMLCALL
xmlMemFree (void *ptr);
XMLPUBFUN char * XMLCALL
xmlMemoryStrdup (const char *str);
XMLPUBFUN void * XMLCALL
xmlMallocLoc (size_t size, const char *file, int line) LIBXML_ATTR_ALLOC_SIZE(1);
XMLPUBFUN void * XMLCALL
xmlReallocLoc (void *ptr, size_t size, const char *file, int line);
XMLPUBFUN void * XMLCALL
xmlMallocAtomicLoc (size_t size, const char *file, int line) LIBXML_ATTR_ALLOC_SIZE(1);
XMLPUBFUN char * XMLCALL
xmlMemStrdupLoc (const char *str, const char *file, int line);
#ifdef DEBUG_MEMORY_LOCATION
/**
* xmlMalloc:
* @size: number of bytes to allocate
*
* Wrapper for the malloc() function used in the XML library.
*
* Returns the pointer to the allocated area or NULL in case of error.
*/
#define xmlMalloc(size) xmlMallocLoc((size), __FILE__, __LINE__)
/**
* xmlMallocAtomic:
* @size: number of bytes to allocate
*
* Wrapper for the malloc() function used in the XML library for allocation
* of block not containing pointers to other areas.
*
* Returns the pointer to the allocated area or NULL in case of error.
*/
#define xmlMallocAtomic(size) xmlMallocAtomicLoc((size), __FILE__, __LINE__)
/**
* xmlRealloc:
* @ptr: pointer to the existing allocated area
* @size: number of bytes to allocate
*
* Wrapper for the realloc() function used in the XML library.
*
* Returns the pointer to the allocated area or NULL in case of error.
*/
#define xmlRealloc(ptr, size) xmlReallocLoc((ptr), (size), __FILE__, __LINE__)
/**
* xmlMemStrdup:
* @str: pointer to the existing string
*
* Wrapper for the strdup() function, xmlStrdup() is usually preferred.
*
* Returns the pointer to the allocated area or NULL in case of error.
*/
#define xmlMemStrdup(str) xmlMemStrdupLoc((str), __FILE__, __LINE__)
#endif /* DEBUG_MEMORY_LOCATION */
#ifdef __cplusplus
}
#endif /* __cplusplus */
#ifndef __XML_GLOBALS_H
#ifndef __XML_THREADS_H__
#include <libxml/threads.h>
#include <libxml/globals.h>
#endif
#endif
#endif /* __DEBUG_MEMORY_ALLOC__ */

@ -0,0 +1,57 @@
/*
* Summary: dynamic module loading
* Description: basic API for dynamic module loading, used by
* libexslt added in 2.6.17
*
* Copy: See Copyright for the status of this software.
*
* Author: Joel W. Reed
*/
#ifndef __XML_MODULE_H__
#define __XML_MODULE_H__
#include <libxml/xmlversion.h>
#ifdef LIBXML_MODULES_ENABLED
#ifdef __cplusplus
extern "C" {
#endif
/**
* xmlModulePtr:
*
* A handle to a dynamically loaded module
*/
typedef struct _xmlModule xmlModule;
typedef xmlModule *xmlModulePtr;
/**
* xmlModuleOption:
*
* enumeration of options that can be passed down to xmlModuleOpen()
*/
typedef enum {
XML_MODULE_LAZY = 1, /* lazy binding */
XML_MODULE_LOCAL= 2 /* local binding */
} xmlModuleOption;
XMLPUBFUN xmlModulePtr XMLCALL xmlModuleOpen (const char *filename,
int options);
XMLPUBFUN int XMLCALL xmlModuleSymbol (xmlModulePtr module,
const char* name,
void **result);
XMLPUBFUN int XMLCALL xmlModuleClose (xmlModulePtr module);
XMLPUBFUN int XMLCALL xmlModuleFree (xmlModulePtr module);
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_MODULES_ENABLED */
#endif /*__XML_MODULE_H__ */

@ -0,0 +1,428 @@
/*
* Summary: the XMLReader implementation
* Description: API of the XML streaming API based on C# interfaces.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_XMLREADER_H__
#define __XML_XMLREADER_H__
#include <libxml/xmlversion.h>
#include <libxml/tree.h>
#include <libxml/xmlIO.h>
#ifdef LIBXML_SCHEMAS_ENABLED
#include <libxml/relaxng.h>
#include <libxml/xmlschemas.h>
#endif
#ifdef __cplusplus
extern "C" {
#endif
/**
* xmlParserSeverities:
*
* How severe an error callback is when the per-reader error callback API
* is used.
*/
typedef enum {
XML_PARSER_SEVERITY_VALIDITY_WARNING = 1,
XML_PARSER_SEVERITY_VALIDITY_ERROR = 2,
XML_PARSER_SEVERITY_WARNING = 3,
XML_PARSER_SEVERITY_ERROR = 4
} xmlParserSeverities;
#ifdef LIBXML_READER_ENABLED
/**
* xmlTextReaderMode:
*
* Internal state values for the reader.
*/
typedef enum {
XML_TEXTREADER_MODE_INITIAL = 0,
XML_TEXTREADER_MODE_INTERACTIVE = 1,
XML_TEXTREADER_MODE_ERROR = 2,
XML_TEXTREADER_MODE_EOF =3,
XML_TEXTREADER_MODE_CLOSED = 4,
XML_TEXTREADER_MODE_READING = 5
} xmlTextReaderMode;
/**
* xmlParserProperties:
*
* Some common options to use with xmlTextReaderSetParserProp, but it
* is better to use xmlParserOption and the xmlReaderNewxxx and
* xmlReaderForxxx APIs now.
*/
typedef enum {
XML_PARSER_LOADDTD = 1,
XML_PARSER_DEFAULTATTRS = 2,
XML_PARSER_VALIDATE = 3,
XML_PARSER_SUBST_ENTITIES = 4
} xmlParserProperties;
/**
* xmlReaderTypes:
*
* Predefined constants for the different types of nodes.
*/
typedef enum {
XML_READER_TYPE_NONE = 0,
XML_READER_TYPE_ELEMENT = 1,
XML_READER_TYPE_ATTRIBUTE = 2,
XML_READER_TYPE_TEXT = 3,
XML_READER_TYPE_CDATA = 4,
XML_READER_TYPE_ENTITY_REFERENCE = 5,
XML_READER_TYPE_ENTITY = 6,
XML_READER_TYPE_PROCESSING_INSTRUCTION = 7,
XML_READER_TYPE_COMMENT = 8,
XML_READER_TYPE_DOCUMENT = 9,
XML_READER_TYPE_DOCUMENT_TYPE = 10,
XML_READER_TYPE_DOCUMENT_FRAGMENT = 11,
XML_READER_TYPE_NOTATION = 12,
XML_READER_TYPE_WHITESPACE = 13,
XML_READER_TYPE_SIGNIFICANT_WHITESPACE = 14,
XML_READER_TYPE_END_ELEMENT = 15,
XML_READER_TYPE_END_ENTITY = 16,
XML_READER_TYPE_XML_DECLARATION = 17
} xmlReaderTypes;
/**
* xmlTextReader:
*
* Structure for an xmlReader context.
*/
typedef struct _xmlTextReader xmlTextReader;
/**
* xmlTextReaderPtr:
*
* Pointer to an xmlReader context.
*/
typedef xmlTextReader *xmlTextReaderPtr;
/*
* Constructors & Destructor
*/
XMLPUBFUN xmlTextReaderPtr XMLCALL
xmlNewTextReader (xmlParserInputBufferPtr input,
const char *URI);
XMLPUBFUN xmlTextReaderPtr XMLCALL
xmlNewTextReaderFilename(const char *URI);
XMLPUBFUN void XMLCALL
xmlFreeTextReader (xmlTextReaderPtr reader);
XMLPUBFUN int XMLCALL
xmlTextReaderSetup(xmlTextReaderPtr reader,
xmlParserInputBufferPtr input, const char *URL,
const char *encoding, int options);
/*
* Iterators
*/
XMLPUBFUN int XMLCALL
xmlTextReaderRead (xmlTextReaderPtr reader);
#ifdef LIBXML_WRITER_ENABLED
XMLPUBFUN xmlChar * XMLCALL
xmlTextReaderReadInnerXml(xmlTextReaderPtr reader);
XMLPUBFUN xmlChar * XMLCALL
xmlTextReaderReadOuterXml(xmlTextReaderPtr reader);
#endif
XMLPUBFUN xmlChar * XMLCALL
xmlTextReaderReadString (xmlTextReaderPtr reader);
XMLPUBFUN int XMLCALL
xmlTextReaderReadAttributeValue(xmlTextReaderPtr reader);
/*
* Attributes of the node
*/
XMLPUBFUN int XMLCALL
xmlTextReaderAttributeCount(xmlTextReaderPtr reader);
XMLPUBFUN int XMLCALL
xmlTextReaderDepth (xmlTextReaderPtr reader);
XMLPUBFUN int XMLCALL
xmlTextReaderHasAttributes(xmlTextReaderPtr reader);
XMLPUBFUN int XMLCALL
xmlTextReaderHasValue(xmlTextReaderPtr reader);
XMLPUBFUN int XMLCALL
xmlTextReaderIsDefault (xmlTextReaderPtr reader);
XMLPUBFUN int XMLCALL
xmlTextReaderIsEmptyElement(xmlTextReaderPtr reader);
XMLPUBFUN int XMLCALL
xmlTextReaderNodeType (xmlTextReaderPtr reader);
XMLPUBFUN int XMLCALL
xmlTextReaderQuoteChar (xmlTextReaderPtr reader);
XMLPUBFUN int XMLCALL
xmlTextReaderReadState (xmlTextReaderPtr reader);
XMLPUBFUN int XMLCALL
xmlTextReaderIsNamespaceDecl(xmlTextReaderPtr reader);
XMLPUBFUN const xmlChar * XMLCALL
xmlTextReaderConstBaseUri (xmlTextReaderPtr reader);
XMLPUBFUN const xmlChar * XMLCALL
xmlTextReaderConstLocalName (xmlTextReaderPtr reader);
XMLPUBFUN const xmlChar * XMLCALL
xmlTextReaderConstName (xmlTextReaderPtr reader);
XMLPUBFUN const xmlChar * XMLCALL
xmlTextReaderConstNamespaceUri(xmlTextReaderPtr reader);
XMLPUBFUN const xmlChar * XMLCALL
xmlTextReaderConstPrefix (xmlTextReaderPtr reader);
XMLPUBFUN const xmlChar * XMLCALL
xmlTextReaderConstXmlLang (xmlTextReaderPtr reader);
XMLPUBFUN const xmlChar * XMLCALL
xmlTextReaderConstString (xmlTextReaderPtr reader,
const xmlChar *str);
XMLPUBFUN const xmlChar * XMLCALL
xmlTextReaderConstValue (xmlTextReaderPtr reader);
/*
* use the Const version of the routine for
* better performance and simpler code
*/
XMLPUBFUN xmlChar * XMLCALL
xmlTextReaderBaseUri (xmlTextReaderPtr reader);
XMLPUBFUN xmlChar * XMLCALL
xmlTextReaderLocalName (xmlTextReaderPtr reader);
XMLPUBFUN xmlChar * XMLCALL
xmlTextReaderName (xmlTextReaderPtr reader);
XMLPUBFUN xmlChar * XMLCALL
xmlTextReaderNamespaceUri(xmlTextReaderPtr reader);
XMLPUBFUN xmlChar * XMLCALL
xmlTextReaderPrefix (xmlTextReaderPtr reader);
XMLPUBFUN xmlChar * XMLCALL
xmlTextReaderXmlLang (xmlTextReaderPtr reader);
XMLPUBFUN xmlChar * XMLCALL
xmlTextReaderValue (xmlTextReaderPtr reader);
/*
* Methods of the XmlTextReader
*/
XMLPUBFUN int XMLCALL
xmlTextReaderClose (xmlTextReaderPtr reader);
XMLPUBFUN xmlChar * XMLCALL
xmlTextReaderGetAttributeNo (xmlTextReaderPtr reader,
int no);
XMLPUBFUN xmlChar * XMLCALL
xmlTextReaderGetAttribute (xmlTextReaderPtr reader,
const xmlChar *name);
XMLPUBFUN xmlChar * XMLCALL
xmlTextReaderGetAttributeNs (xmlTextReaderPtr reader,
const xmlChar *localName,
const xmlChar *namespaceURI);
XMLPUBFUN xmlParserInputBufferPtr XMLCALL
xmlTextReaderGetRemainder (xmlTextReaderPtr reader);
XMLPUBFUN xmlChar * XMLCALL
xmlTextReaderLookupNamespace(xmlTextReaderPtr reader,
const xmlChar *prefix);
XMLPUBFUN int XMLCALL
xmlTextReaderMoveToAttributeNo(xmlTextReaderPtr reader,
int no);
XMLPUBFUN int XMLCALL
xmlTextReaderMoveToAttribute(xmlTextReaderPtr reader,
const xmlChar *name);
XMLPUBFUN int XMLCALL
xmlTextReaderMoveToAttributeNs(xmlTextReaderPtr reader,
const xmlChar *localName,
const xmlChar *namespaceURI);
XMLPUBFUN int XMLCALL
xmlTextReaderMoveToFirstAttribute(xmlTextReaderPtr reader);
XMLPUBFUN int XMLCALL
xmlTextReaderMoveToNextAttribute(xmlTextReaderPtr reader);
XMLPUBFUN int XMLCALL
xmlTextReaderMoveToElement (xmlTextReaderPtr reader);
XMLPUBFUN int XMLCALL
xmlTextReaderNormalization (xmlTextReaderPtr reader);
XMLPUBFUN const xmlChar * XMLCALL
xmlTextReaderConstEncoding (xmlTextReaderPtr reader);
/*
* Extensions
*/
XMLPUBFUN int XMLCALL
xmlTextReaderSetParserProp (xmlTextReaderPtr reader,
int prop,
int value);
XMLPUBFUN int XMLCALL
xmlTextReaderGetParserProp (xmlTextReaderPtr reader,
int prop);
XMLPUBFUN xmlNodePtr XMLCALL
xmlTextReaderCurrentNode (xmlTextReaderPtr reader);
XMLPUBFUN int XMLCALL
xmlTextReaderGetParserLineNumber(xmlTextReaderPtr reader);
XMLPUBFUN int XMLCALL
xmlTextReaderGetParserColumnNumber(xmlTextReaderPtr reader);
XMLPUBFUN xmlNodePtr XMLCALL
xmlTextReaderPreserve (xmlTextReaderPtr reader);
#ifdef LIBXML_PATTERN_ENABLED
XMLPUBFUN int XMLCALL
xmlTextReaderPreservePattern(xmlTextReaderPtr reader,
const xmlChar *pattern,
const xmlChar **namespaces);
#endif /* LIBXML_PATTERN_ENABLED */
XMLPUBFUN xmlDocPtr XMLCALL
xmlTextReaderCurrentDoc (xmlTextReaderPtr reader);
XMLPUBFUN xmlNodePtr XMLCALL
xmlTextReaderExpand (xmlTextReaderPtr reader);
XMLPUBFUN int XMLCALL
xmlTextReaderNext (xmlTextReaderPtr reader);
XMLPUBFUN int XMLCALL
xmlTextReaderNextSibling (xmlTextReaderPtr reader);
XMLPUBFUN int XMLCALL
xmlTextReaderIsValid (xmlTextReaderPtr reader);
#ifdef LIBXML_SCHEMAS_ENABLED
XMLPUBFUN int XMLCALL
xmlTextReaderRelaxNGValidate(xmlTextReaderPtr reader,
const char *rng);
XMLPUBFUN int XMLCALL
xmlTextReaderRelaxNGValidateCtxt(xmlTextReaderPtr reader,
xmlRelaxNGValidCtxtPtr ctxt,
int options);
XMLPUBFUN int XMLCALL
xmlTextReaderRelaxNGSetSchema(xmlTextReaderPtr reader,
xmlRelaxNGPtr schema);
XMLPUBFUN int XMLCALL
xmlTextReaderSchemaValidate (xmlTextReaderPtr reader,
const char *xsd);
XMLPUBFUN int XMLCALL
xmlTextReaderSchemaValidateCtxt(xmlTextReaderPtr reader,
xmlSchemaValidCtxtPtr ctxt,
int options);
XMLPUBFUN int XMLCALL
xmlTextReaderSetSchema (xmlTextReaderPtr reader,
xmlSchemaPtr schema);
#endif
XMLPUBFUN const xmlChar * XMLCALL
xmlTextReaderConstXmlVersion(xmlTextReaderPtr reader);
XMLPUBFUN int XMLCALL
xmlTextReaderStandalone (xmlTextReaderPtr reader);
/*
* Index lookup
*/
XMLPUBFUN long XMLCALL
xmlTextReaderByteConsumed (xmlTextReaderPtr reader);
/*
* New more complete APIs for simpler creation and reuse of readers
*/
XMLPUBFUN xmlTextReaderPtr XMLCALL
xmlReaderWalker (xmlDocPtr doc);
XMLPUBFUN xmlTextReaderPtr XMLCALL
xmlReaderForDoc (const xmlChar * cur,
const char *URL,
const char *encoding,
int options);
XMLPUBFUN xmlTextReaderPtr XMLCALL
xmlReaderForFile (const char *filename,
const char *encoding,
int options);
XMLPUBFUN xmlTextReaderPtr XMLCALL
xmlReaderForMemory (const char *buffer,
int size,
const char *URL,
const char *encoding,
int options);
XMLPUBFUN xmlTextReaderPtr XMLCALL
xmlReaderForFd (int fd,
const char *URL,
const char *encoding,
int options);
XMLPUBFUN xmlTextReaderPtr XMLCALL
xmlReaderForIO (xmlInputReadCallback ioread,
xmlInputCloseCallback ioclose,
void *ioctx,
const char *URL,
const char *encoding,
int options);
XMLPUBFUN int XMLCALL
xmlReaderNewWalker (xmlTextReaderPtr reader,
xmlDocPtr doc);
XMLPUBFUN int XMLCALL
xmlReaderNewDoc (xmlTextReaderPtr reader,
const xmlChar * cur,
const char *URL,
const char *encoding,
int options);
XMLPUBFUN int XMLCALL
xmlReaderNewFile (xmlTextReaderPtr reader,
const char *filename,
const char *encoding,
int options);
XMLPUBFUN int XMLCALL
xmlReaderNewMemory (xmlTextReaderPtr reader,
const char *buffer,
int size,
const char *URL,
const char *encoding,
int options);
XMLPUBFUN int XMLCALL
xmlReaderNewFd (xmlTextReaderPtr reader,
int fd,
const char *URL,
const char *encoding,
int options);
XMLPUBFUN int XMLCALL
xmlReaderNewIO (xmlTextReaderPtr reader,
xmlInputReadCallback ioread,
xmlInputCloseCallback ioclose,
void *ioctx,
const char *URL,
const char *encoding,
int options);
/*
* Error handling extensions
*/
typedef void * xmlTextReaderLocatorPtr;
/**
* xmlTextReaderErrorFunc:
* @arg: the user argument
* @msg: the message
* @severity: the severity of the error
* @locator: a locator indicating where the error occurred
*
* Signature of an error callback from a reader parser
*/
typedef void (XMLCALL *xmlTextReaderErrorFunc)(void *arg,
const char *msg,
xmlParserSeverities severity,
xmlTextReaderLocatorPtr locator);
XMLPUBFUN int XMLCALL
xmlTextReaderLocatorLineNumber(xmlTextReaderLocatorPtr locator);
XMLPUBFUN xmlChar * XMLCALL
xmlTextReaderLocatorBaseURI (xmlTextReaderLocatorPtr locator);
XMLPUBFUN void XMLCALL
xmlTextReaderSetErrorHandler(xmlTextReaderPtr reader,
xmlTextReaderErrorFunc f,
void *arg);
XMLPUBFUN void XMLCALL
xmlTextReaderSetStructuredErrorHandler(xmlTextReaderPtr reader,
xmlStructuredErrorFunc f,
void *arg);
XMLPUBFUN void XMLCALL
xmlTextReaderGetErrorHandler(xmlTextReaderPtr reader,
xmlTextReaderErrorFunc *f,
void **arg);
#endif /* LIBXML_READER_ENABLED */
#ifdef __cplusplus
}
#endif
#endif /* __XML_XMLREADER_H__ */

@ -0,0 +1,222 @@
/*
* Summary: regular expressions handling
* Description: basic API for libxml regular expressions handling used
* for XML Schemas and validation.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_REGEXP_H__
#define __XML_REGEXP_H__
#include <libxml/xmlversion.h>
#ifdef LIBXML_REGEXP_ENABLED
#ifdef __cplusplus
extern "C" {
#endif
/**
* xmlRegexpPtr:
*
* A libxml regular expression, they can actually be far more complex
* thank the POSIX regex expressions.
*/
typedef struct _xmlRegexp xmlRegexp;
typedef xmlRegexp *xmlRegexpPtr;
/**
* xmlRegExecCtxtPtr:
*
* A libxml progressive regular expression evaluation context
*/
typedef struct _xmlRegExecCtxt xmlRegExecCtxt;
typedef xmlRegExecCtxt *xmlRegExecCtxtPtr;
#ifdef __cplusplus
}
#endif
#include <libxml/tree.h>
#include <libxml/dict.h>
#ifdef __cplusplus
extern "C" {
#endif
/*
* The POSIX like API
*/
XMLPUBFUN xmlRegexpPtr XMLCALL
xmlRegexpCompile (const xmlChar *regexp);
XMLPUBFUN void XMLCALL xmlRegFreeRegexp(xmlRegexpPtr regexp);
XMLPUBFUN int XMLCALL
xmlRegexpExec (xmlRegexpPtr comp,
const xmlChar *value);
XMLPUBFUN void XMLCALL
xmlRegexpPrint (FILE *output,
xmlRegexpPtr regexp);
XMLPUBFUN int XMLCALL
xmlRegexpIsDeterminist(xmlRegexpPtr comp);
/**
* xmlRegExecCallbacks:
* @exec: the regular expression context
* @token: the current token string
* @transdata: transition data
* @inputdata: input data
*
* Callback function when doing a transition in the automata
*/
typedef void (*xmlRegExecCallbacks) (xmlRegExecCtxtPtr exec,
const xmlChar *token,
void *transdata,
void *inputdata);
/*
* The progressive API
*/
XMLPUBFUN xmlRegExecCtxtPtr XMLCALL
xmlRegNewExecCtxt (xmlRegexpPtr comp,
xmlRegExecCallbacks callback,
void *data);
XMLPUBFUN void XMLCALL
xmlRegFreeExecCtxt (xmlRegExecCtxtPtr exec);
XMLPUBFUN int XMLCALL
xmlRegExecPushString(xmlRegExecCtxtPtr exec,
const xmlChar *value,
void *data);
XMLPUBFUN int XMLCALL
xmlRegExecPushString2(xmlRegExecCtxtPtr exec,
const xmlChar *value,
const xmlChar *value2,
void *data);
XMLPUBFUN int XMLCALL
xmlRegExecNextValues(xmlRegExecCtxtPtr exec,
int *nbval,
int *nbneg,
xmlChar **values,
int *terminal);
XMLPUBFUN int XMLCALL
xmlRegExecErrInfo (xmlRegExecCtxtPtr exec,
const xmlChar **string,
int *nbval,
int *nbneg,
xmlChar **values,
int *terminal);
#ifdef LIBXML_EXPR_ENABLED
/*
* Formal regular expression handling
* Its goal is to do some formal work on content models
*/
/* expressions are used within a context */
typedef struct _xmlExpCtxt xmlExpCtxt;
typedef xmlExpCtxt *xmlExpCtxtPtr;
XMLPUBFUN void XMLCALL
xmlExpFreeCtxt (xmlExpCtxtPtr ctxt);
XMLPUBFUN xmlExpCtxtPtr XMLCALL
xmlExpNewCtxt (int maxNodes,
xmlDictPtr dict);
XMLPUBFUN int XMLCALL
xmlExpCtxtNbNodes(xmlExpCtxtPtr ctxt);
XMLPUBFUN int XMLCALL
xmlExpCtxtNbCons(xmlExpCtxtPtr ctxt);
/* Expressions are trees but the tree is opaque */
typedef struct _xmlExpNode xmlExpNode;
typedef xmlExpNode *xmlExpNodePtr;
typedef enum {
XML_EXP_EMPTY = 0,
XML_EXP_FORBID = 1,
XML_EXP_ATOM = 2,
XML_EXP_SEQ = 3,
XML_EXP_OR = 4,
XML_EXP_COUNT = 5
} xmlExpNodeType;
/*
* 2 core expressions shared by all for the empty language set
* and for the set with just the empty token
*/
XMLPUBVAR xmlExpNodePtr forbiddenExp;
XMLPUBVAR xmlExpNodePtr emptyExp;
/*
* Expressions are reference counted internally
*/
XMLPUBFUN void XMLCALL
xmlExpFree (xmlExpCtxtPtr ctxt,
xmlExpNodePtr expr);
XMLPUBFUN void XMLCALL
xmlExpRef (xmlExpNodePtr expr);
/*
* constructors can be either manual or from a string
*/
XMLPUBFUN xmlExpNodePtr XMLCALL
xmlExpParse (xmlExpCtxtPtr ctxt,
const char *expr);
XMLPUBFUN xmlExpNodePtr XMLCALL
xmlExpNewAtom (xmlExpCtxtPtr ctxt,
const xmlChar *name,
int len);
XMLPUBFUN xmlExpNodePtr XMLCALL
xmlExpNewOr (xmlExpCtxtPtr ctxt,
xmlExpNodePtr left,
xmlExpNodePtr right);
XMLPUBFUN xmlExpNodePtr XMLCALL
xmlExpNewSeq (xmlExpCtxtPtr ctxt,
xmlExpNodePtr left,
xmlExpNodePtr right);
XMLPUBFUN xmlExpNodePtr XMLCALL
xmlExpNewRange (xmlExpCtxtPtr ctxt,
xmlExpNodePtr subset,
int min,
int max);
/*
* The really interesting APIs
*/
XMLPUBFUN int XMLCALL
xmlExpIsNillable(xmlExpNodePtr expr);
XMLPUBFUN int XMLCALL
xmlExpMaxToken (xmlExpNodePtr expr);
XMLPUBFUN int XMLCALL
xmlExpGetLanguage(xmlExpCtxtPtr ctxt,
xmlExpNodePtr expr,
const xmlChar**langList,
int len);
XMLPUBFUN int XMLCALL
xmlExpGetStart (xmlExpCtxtPtr ctxt,
xmlExpNodePtr expr,
const xmlChar**tokList,
int len);
XMLPUBFUN xmlExpNodePtr XMLCALL
xmlExpStringDerive(xmlExpCtxtPtr ctxt,
xmlExpNodePtr expr,
const xmlChar *str,
int len);
XMLPUBFUN xmlExpNodePtr XMLCALL
xmlExpExpDerive (xmlExpCtxtPtr ctxt,
xmlExpNodePtr expr,
xmlExpNodePtr sub);
XMLPUBFUN int XMLCALL
xmlExpSubsume (xmlExpCtxtPtr ctxt,
xmlExpNodePtr expr,
xmlExpNodePtr sub);
XMLPUBFUN void XMLCALL
xmlExpDump (xmlBufferPtr buf,
xmlExpNodePtr expr);
#endif /* LIBXML_EXPR_ENABLED */
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_REGEXP_ENABLED */
#endif /*__XML_REGEXP_H__ */

@ -0,0 +1,88 @@
/*
* Summary: the XML document serializer
* Description: API to save document or subtree of document
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_XMLSAVE_H__
#define __XML_XMLSAVE_H__
#include <libxml/xmlversion.h>
#include <libxml/tree.h>
#include <libxml/encoding.h>
#include <libxml/xmlIO.h>
#ifdef LIBXML_OUTPUT_ENABLED
#ifdef __cplusplus
extern "C" {
#endif
/**
* xmlSaveOption:
*
* This is the set of XML save options that can be passed down
* to the xmlSaveToFd() and similar calls.
*/
typedef enum {
XML_SAVE_FORMAT = 1<<0, /* format save output */
XML_SAVE_NO_DECL = 1<<1, /* drop the xml declaration */
XML_SAVE_NO_EMPTY = 1<<2, /* no empty tags */
XML_SAVE_NO_XHTML = 1<<3, /* disable XHTML1 specific rules */
XML_SAVE_XHTML = 1<<4, /* force XHTML1 specific rules */
XML_SAVE_AS_XML = 1<<5, /* force XML serialization on HTML doc */
XML_SAVE_AS_HTML = 1<<6, /* force HTML serialization on XML doc */
XML_SAVE_WSNONSIG = 1<<7 /* format with non-significant whitespace */
} xmlSaveOption;
typedef struct _xmlSaveCtxt xmlSaveCtxt;
typedef xmlSaveCtxt *xmlSaveCtxtPtr;
XMLPUBFUN xmlSaveCtxtPtr XMLCALL
xmlSaveToFd (int fd,
const char *encoding,
int options);
XMLPUBFUN xmlSaveCtxtPtr XMLCALL
xmlSaveToFilename (const char *filename,
const char *encoding,
int options);
XMLPUBFUN xmlSaveCtxtPtr XMLCALL
xmlSaveToBuffer (xmlBufferPtr buffer,
const char *encoding,
int options);
XMLPUBFUN xmlSaveCtxtPtr XMLCALL
xmlSaveToIO (xmlOutputWriteCallback iowrite,
xmlOutputCloseCallback ioclose,
void *ioctx,
const char *encoding,
int options);
XMLPUBFUN long XMLCALL
xmlSaveDoc (xmlSaveCtxtPtr ctxt,
xmlDocPtr doc);
XMLPUBFUN long XMLCALL
xmlSaveTree (xmlSaveCtxtPtr ctxt,
xmlNodePtr node);
XMLPUBFUN int XMLCALL
xmlSaveFlush (xmlSaveCtxtPtr ctxt);
XMLPUBFUN int XMLCALL
xmlSaveClose (xmlSaveCtxtPtr ctxt);
XMLPUBFUN int XMLCALL
xmlSaveSetEscape (xmlSaveCtxtPtr ctxt,
xmlCharEncodingOutputFunc escape);
XMLPUBFUN int XMLCALL
xmlSaveSetAttrEscape (xmlSaveCtxtPtr ctxt,
xmlCharEncodingOutputFunc escape);
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_OUTPUT_ENABLED */
#endif /* __XML_XMLSAVE_H__ */

@ -0,0 +1,246 @@
/*
* Summary: incomplete XML Schemas structure implementation
* Description: interface to the XML Schemas handling and schema validity
* checking, it is incomplete right now.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_SCHEMA_H__
#define __XML_SCHEMA_H__
#include <libxml/xmlversion.h>
#ifdef LIBXML_SCHEMAS_ENABLED
#include <libxml/tree.h>
#ifdef __cplusplus
extern "C" {
#endif
/**
* This error codes are obsolete; not used any more.
*/
typedef enum {
XML_SCHEMAS_ERR_OK = 0,
XML_SCHEMAS_ERR_NOROOT = 1,
XML_SCHEMAS_ERR_UNDECLAREDELEM,
XML_SCHEMAS_ERR_NOTTOPLEVEL,
XML_SCHEMAS_ERR_MISSING,
XML_SCHEMAS_ERR_WRONGELEM,
XML_SCHEMAS_ERR_NOTYPE,
XML_SCHEMAS_ERR_NOROLLBACK,
XML_SCHEMAS_ERR_ISABSTRACT,
XML_SCHEMAS_ERR_NOTEMPTY,
XML_SCHEMAS_ERR_ELEMCONT,
XML_SCHEMAS_ERR_HAVEDEFAULT,
XML_SCHEMAS_ERR_NOTNILLABLE,
XML_SCHEMAS_ERR_EXTRACONTENT,
XML_SCHEMAS_ERR_INVALIDATTR,
XML_SCHEMAS_ERR_INVALIDELEM,
XML_SCHEMAS_ERR_NOTDETERMINIST,
XML_SCHEMAS_ERR_CONSTRUCT,
XML_SCHEMAS_ERR_INTERNAL,
XML_SCHEMAS_ERR_NOTSIMPLE,
XML_SCHEMAS_ERR_ATTRUNKNOWN,
XML_SCHEMAS_ERR_ATTRINVALID,
XML_SCHEMAS_ERR_VALUE,
XML_SCHEMAS_ERR_FACET,
XML_SCHEMAS_ERR_,
XML_SCHEMAS_ERR_XXX
} xmlSchemaValidError;
/*
* ATTENTION: Change xmlSchemaSetValidOptions's check
* for invalid values, if adding to the validation
* options below.
*/
/**
* xmlSchemaValidOption:
*
* This is the set of XML Schema validation options.
*/
typedef enum {
XML_SCHEMA_VAL_VC_I_CREATE = 1<<0
/* Default/fixed: create an attribute node
* or an element's text node on the instance.
*/
} xmlSchemaValidOption;
/*
XML_SCHEMA_VAL_XSI_ASSEMBLE = 1<<1,
* assemble schemata using
* xsi:schemaLocation and
* xsi:noNamespaceSchemaLocation
*/
/**
* The schemas related types are kept internal
*/
typedef struct _xmlSchema xmlSchema;
typedef xmlSchema *xmlSchemaPtr;
/**
* xmlSchemaValidityErrorFunc:
* @ctx: the validation context
* @msg: the message
* @...: extra arguments
*
* Signature of an error callback from an XSD validation
*/
typedef void (XMLCDECL *xmlSchemaValidityErrorFunc)
(void *ctx, const char *msg, ...) LIBXML_ATTR_FORMAT(2,3);
/**
* xmlSchemaValidityWarningFunc:
* @ctx: the validation context
* @msg: the message
* @...: extra arguments
*
* Signature of a warning callback from an XSD validation
*/
typedef void (XMLCDECL *xmlSchemaValidityWarningFunc)
(void *ctx, const char *msg, ...) LIBXML_ATTR_FORMAT(2,3);
/**
* A schemas validation context
*/
typedef struct _xmlSchemaParserCtxt xmlSchemaParserCtxt;
typedef xmlSchemaParserCtxt *xmlSchemaParserCtxtPtr;
typedef struct _xmlSchemaValidCtxt xmlSchemaValidCtxt;
typedef xmlSchemaValidCtxt *xmlSchemaValidCtxtPtr;
/**
* xmlSchemaValidityLocatorFunc:
* @ctx: user provided context
* @file: returned file information
* @line: returned line information
*
* A schemas validation locator, a callback called by the validator.
* This is used when file or node informations are not available
* to find out what file and line number are affected
*
* Returns: 0 in case of success and -1 in case of error
*/
typedef int (XMLCDECL *xmlSchemaValidityLocatorFunc) (void *ctx,
const char **file, unsigned long *line);
/*
* Interfaces for parsing.
*/
XMLPUBFUN xmlSchemaParserCtxtPtr XMLCALL
xmlSchemaNewParserCtxt (const char *URL);
XMLPUBFUN xmlSchemaParserCtxtPtr XMLCALL
xmlSchemaNewMemParserCtxt (const char *buffer,
int size);
XMLPUBFUN xmlSchemaParserCtxtPtr XMLCALL
xmlSchemaNewDocParserCtxt (xmlDocPtr doc);
XMLPUBFUN void XMLCALL
xmlSchemaFreeParserCtxt (xmlSchemaParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlSchemaSetParserErrors (xmlSchemaParserCtxtPtr ctxt,
xmlSchemaValidityErrorFunc err,
xmlSchemaValidityWarningFunc warn,
void *ctx);
XMLPUBFUN void XMLCALL
xmlSchemaSetParserStructuredErrors(xmlSchemaParserCtxtPtr ctxt,
xmlStructuredErrorFunc serror,
void *ctx);
XMLPUBFUN int XMLCALL
xmlSchemaGetParserErrors(xmlSchemaParserCtxtPtr ctxt,
xmlSchemaValidityErrorFunc * err,
xmlSchemaValidityWarningFunc * warn,
void **ctx);
XMLPUBFUN int XMLCALL
xmlSchemaIsValid (xmlSchemaValidCtxtPtr ctxt);
XMLPUBFUN xmlSchemaPtr XMLCALL
xmlSchemaParse (xmlSchemaParserCtxtPtr ctxt);
XMLPUBFUN void XMLCALL
xmlSchemaFree (xmlSchemaPtr schema);
#ifdef LIBXML_OUTPUT_ENABLED
XMLPUBFUN void XMLCALL
xmlSchemaDump (FILE *output,
xmlSchemaPtr schema);
#endif /* LIBXML_OUTPUT_ENABLED */
/*
* Interfaces for validating
*/
XMLPUBFUN void XMLCALL
xmlSchemaSetValidErrors (xmlSchemaValidCtxtPtr ctxt,
xmlSchemaValidityErrorFunc err,
xmlSchemaValidityWarningFunc warn,
void *ctx);
XMLPUBFUN void XMLCALL
xmlSchemaSetValidStructuredErrors(xmlSchemaValidCtxtPtr ctxt,
xmlStructuredErrorFunc serror,
void *ctx);
XMLPUBFUN int XMLCALL
xmlSchemaGetValidErrors (xmlSchemaValidCtxtPtr ctxt,
xmlSchemaValidityErrorFunc *err,
xmlSchemaValidityWarningFunc *warn,
void **ctx);
XMLPUBFUN int XMLCALL
xmlSchemaSetValidOptions (xmlSchemaValidCtxtPtr ctxt,
int options);
XMLPUBFUN void XMLCALL
xmlSchemaValidateSetFilename(xmlSchemaValidCtxtPtr vctxt,
const char *filename);
XMLPUBFUN int XMLCALL
xmlSchemaValidCtxtGetOptions(xmlSchemaValidCtxtPtr ctxt);
XMLPUBFUN xmlSchemaValidCtxtPtr XMLCALL
xmlSchemaNewValidCtxt (xmlSchemaPtr schema);
XMLPUBFUN void XMLCALL
xmlSchemaFreeValidCtxt (xmlSchemaValidCtxtPtr ctxt);
XMLPUBFUN int XMLCALL
xmlSchemaValidateDoc (xmlSchemaValidCtxtPtr ctxt,
xmlDocPtr instance);
XMLPUBFUN int XMLCALL
xmlSchemaValidateOneElement (xmlSchemaValidCtxtPtr ctxt,
xmlNodePtr elem);
XMLPUBFUN int XMLCALL
xmlSchemaValidateStream (xmlSchemaValidCtxtPtr ctxt,
xmlParserInputBufferPtr input,
xmlCharEncoding enc,
xmlSAXHandlerPtr sax,
void *user_data);
XMLPUBFUN int XMLCALL
xmlSchemaValidateFile (xmlSchemaValidCtxtPtr ctxt,
const char * filename,
int options);
XMLPUBFUN xmlParserCtxtPtr XMLCALL
xmlSchemaValidCtxtGetParserCtxt(xmlSchemaValidCtxtPtr ctxt);
/*
* Interface to insert Schemas SAX validation in a SAX stream
*/
typedef struct _xmlSchemaSAXPlug xmlSchemaSAXPlugStruct;
typedef xmlSchemaSAXPlugStruct *xmlSchemaSAXPlugPtr;
XMLPUBFUN xmlSchemaSAXPlugPtr XMLCALL
xmlSchemaSAXPlug (xmlSchemaValidCtxtPtr ctxt,
xmlSAXHandlerPtr *sax,
void **user_data);
XMLPUBFUN int XMLCALL
xmlSchemaSAXUnplug (xmlSchemaSAXPlugPtr plug);
XMLPUBFUN void XMLCALL
xmlSchemaValidateSetLocator (xmlSchemaValidCtxtPtr vctxt,
xmlSchemaValidityLocatorFunc f,
void *ctxt);
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_SCHEMAS_ENABLED */
#endif /* __XML_SCHEMA_H__ */

@ -0,0 +1,151 @@
/*
* Summary: implementation of XML Schema Datatypes
* Description: module providing the XML Schema Datatypes implementation
* both definition and validity checking
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_SCHEMA_TYPES_H__
#define __XML_SCHEMA_TYPES_H__
#include <libxml/xmlversion.h>
#ifdef LIBXML_SCHEMAS_ENABLED
#include <libxml/schemasInternals.h>
#include <libxml/xmlschemas.h>
#ifdef __cplusplus
extern "C" {
#endif
typedef enum {
XML_SCHEMA_WHITESPACE_UNKNOWN = 0,
XML_SCHEMA_WHITESPACE_PRESERVE = 1,
XML_SCHEMA_WHITESPACE_REPLACE = 2,
XML_SCHEMA_WHITESPACE_COLLAPSE = 3
} xmlSchemaWhitespaceValueType;
XMLPUBFUN void XMLCALL
xmlSchemaInitTypes (void);
XMLPUBFUN void XMLCALL
xmlSchemaCleanupTypes (void);
XMLPUBFUN xmlSchemaTypePtr XMLCALL
xmlSchemaGetPredefinedType (const xmlChar *name,
const xmlChar *ns);
XMLPUBFUN int XMLCALL
xmlSchemaValidatePredefinedType (xmlSchemaTypePtr type,
const xmlChar *value,
xmlSchemaValPtr *val);
XMLPUBFUN int XMLCALL
xmlSchemaValPredefTypeNode (xmlSchemaTypePtr type,
const xmlChar *value,
xmlSchemaValPtr *val,
xmlNodePtr node);
XMLPUBFUN int XMLCALL
xmlSchemaValidateFacet (xmlSchemaTypePtr base,
xmlSchemaFacetPtr facet,
const xmlChar *value,
xmlSchemaValPtr val);
XMLPUBFUN int XMLCALL
xmlSchemaValidateFacetWhtsp (xmlSchemaFacetPtr facet,
xmlSchemaWhitespaceValueType fws,
xmlSchemaValType valType,
const xmlChar *value,
xmlSchemaValPtr val,
xmlSchemaWhitespaceValueType ws);
XMLPUBFUN void XMLCALL
xmlSchemaFreeValue (xmlSchemaValPtr val);
XMLPUBFUN xmlSchemaFacetPtr XMLCALL
xmlSchemaNewFacet (void);
XMLPUBFUN int XMLCALL
xmlSchemaCheckFacet (xmlSchemaFacetPtr facet,
xmlSchemaTypePtr typeDecl,
xmlSchemaParserCtxtPtr ctxt,
const xmlChar *name);
XMLPUBFUN void XMLCALL
xmlSchemaFreeFacet (xmlSchemaFacetPtr facet);
XMLPUBFUN int XMLCALL
xmlSchemaCompareValues (xmlSchemaValPtr x,
xmlSchemaValPtr y);
XMLPUBFUN xmlSchemaTypePtr XMLCALL
xmlSchemaGetBuiltInListSimpleTypeItemType (xmlSchemaTypePtr type);
XMLPUBFUN int XMLCALL
xmlSchemaValidateListSimpleTypeFacet (xmlSchemaFacetPtr facet,
const xmlChar *value,
unsigned long actualLen,
unsigned long *expectedLen);
XMLPUBFUN xmlSchemaTypePtr XMLCALL
xmlSchemaGetBuiltInType (xmlSchemaValType type);
XMLPUBFUN int XMLCALL
xmlSchemaIsBuiltInTypeFacet (xmlSchemaTypePtr type,
int facetType);
XMLPUBFUN xmlChar * XMLCALL
xmlSchemaCollapseString (const xmlChar *value);
XMLPUBFUN xmlChar * XMLCALL
xmlSchemaWhiteSpaceReplace (const xmlChar *value);
XMLPUBFUN unsigned long XMLCALL
xmlSchemaGetFacetValueAsULong (xmlSchemaFacetPtr facet);
XMLPUBFUN int XMLCALL
xmlSchemaValidateLengthFacet (xmlSchemaTypePtr type,
xmlSchemaFacetPtr facet,
const xmlChar *value,
xmlSchemaValPtr val,
unsigned long *length);
XMLPUBFUN int XMLCALL
xmlSchemaValidateLengthFacetWhtsp(xmlSchemaFacetPtr facet,
xmlSchemaValType valType,
const xmlChar *value,
xmlSchemaValPtr val,
unsigned long *length,
xmlSchemaWhitespaceValueType ws);
XMLPUBFUN int XMLCALL
xmlSchemaValPredefTypeNodeNoNorm(xmlSchemaTypePtr type,
const xmlChar *value,
xmlSchemaValPtr *val,
xmlNodePtr node);
XMLPUBFUN int XMLCALL
xmlSchemaGetCanonValue (xmlSchemaValPtr val,
const xmlChar **retValue);
XMLPUBFUN int XMLCALL
xmlSchemaGetCanonValueWhtsp (xmlSchemaValPtr val,
const xmlChar **retValue,
xmlSchemaWhitespaceValueType ws);
XMLPUBFUN int XMLCALL
xmlSchemaValueAppend (xmlSchemaValPtr prev,
xmlSchemaValPtr cur);
XMLPUBFUN xmlSchemaValPtr XMLCALL
xmlSchemaValueGetNext (xmlSchemaValPtr cur);
XMLPUBFUN const xmlChar * XMLCALL
xmlSchemaValueGetAsString (xmlSchemaValPtr val);
XMLPUBFUN int XMLCALL
xmlSchemaValueGetAsBoolean (xmlSchemaValPtr val);
XMLPUBFUN xmlSchemaValPtr XMLCALL
xmlSchemaNewStringValue (xmlSchemaValType type,
const xmlChar *value);
XMLPUBFUN xmlSchemaValPtr XMLCALL
xmlSchemaNewNOTATIONValue (const xmlChar *name,
const xmlChar *ns);
XMLPUBFUN xmlSchemaValPtr XMLCALL
xmlSchemaNewQNameValue (const xmlChar *namespaceName,
const xmlChar *localName);
XMLPUBFUN int XMLCALL
xmlSchemaCompareValuesWhtsp (xmlSchemaValPtr x,
xmlSchemaWhitespaceValueType xws,
xmlSchemaValPtr y,
xmlSchemaWhitespaceValueType yws);
XMLPUBFUN xmlSchemaValPtr XMLCALL
xmlSchemaCopyValue (xmlSchemaValPtr val);
XMLPUBFUN xmlSchemaValType XMLCALL
xmlSchemaGetValType (xmlSchemaValPtr val);
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_SCHEMAS_ENABLED */
#endif /* __XML_SCHEMA_TYPES_H__ */

@ -0,0 +1,140 @@
/*
* Summary: set of routines to process strings
* Description: type and interfaces needed for the internal string handling
* of the library, especially UTF8 processing.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_STRING_H__
#define __XML_STRING_H__
#include <stdarg.h>
#include <libxml/xmlversion.h>
#ifdef __cplusplus
extern "C" {
#endif
/**
* xmlChar:
*
* This is a basic byte in an UTF-8 encoded string.
* It's unsigned allowing to pinpoint case where char * are assigned
* to xmlChar * (possibly making serialization back impossible).
*/
typedef unsigned char xmlChar;
/**
* BAD_CAST:
*
* Macro to cast a string to an xmlChar * when one know its safe.
*/
#define BAD_CAST (xmlChar *)
/*
* xmlChar handling
*/
XMLPUBFUN xmlChar * XMLCALL
xmlStrdup (const xmlChar *cur);
XMLPUBFUN xmlChar * XMLCALL
xmlStrndup (const xmlChar *cur,
int len);
XMLPUBFUN xmlChar * XMLCALL
xmlCharStrndup (const char *cur,
int len);
XMLPUBFUN xmlChar * XMLCALL
xmlCharStrdup (const char *cur);
XMLPUBFUN xmlChar * XMLCALL
xmlStrsub (const xmlChar *str,
int start,
int len);
XMLPUBFUN const xmlChar * XMLCALL
xmlStrchr (const xmlChar *str,
xmlChar val);
XMLPUBFUN const xmlChar * XMLCALL
xmlStrstr (const xmlChar *str,
const xmlChar *val);
XMLPUBFUN const xmlChar * XMLCALL
xmlStrcasestr (const xmlChar *str,
const xmlChar *val);
XMLPUBFUN int XMLCALL
xmlStrcmp (const xmlChar *str1,
const xmlChar *str2);
XMLPUBFUN int XMLCALL
xmlStrncmp (const xmlChar *str1,
const xmlChar *str2,
int len);
XMLPUBFUN int XMLCALL
xmlStrcasecmp (const xmlChar *str1,
const xmlChar *str2);
XMLPUBFUN int XMLCALL
xmlStrncasecmp (const xmlChar *str1,
const xmlChar *str2,
int len);
XMLPUBFUN int XMLCALL
xmlStrEqual (const xmlChar *str1,
const xmlChar *str2);
XMLPUBFUN int XMLCALL
xmlStrQEqual (const xmlChar *pref,
const xmlChar *name,
const xmlChar *str);
XMLPUBFUN int XMLCALL
xmlStrlen (const xmlChar *str);
XMLPUBFUN xmlChar * XMLCALL
xmlStrcat (xmlChar *cur,
const xmlChar *add);
XMLPUBFUN xmlChar * XMLCALL
xmlStrncat (xmlChar *cur,
const xmlChar *add,
int len);
XMLPUBFUN xmlChar * XMLCALL
xmlStrncatNew (const xmlChar *str1,
const xmlChar *str2,
int len);
XMLPUBFUN int XMLCALL
xmlStrPrintf (xmlChar *buf,
int len,
const char *msg,
...) LIBXML_ATTR_FORMAT(3,4);
XMLPUBFUN int XMLCALL
xmlStrVPrintf (xmlChar *buf,
int len,
const char *msg,
va_list ap) LIBXML_ATTR_FORMAT(3,0);
XMLPUBFUN int XMLCALL
xmlGetUTF8Char (const unsigned char *utf,
int *len);
XMLPUBFUN int XMLCALL
xmlCheckUTF8 (const unsigned char *utf);
XMLPUBFUN int XMLCALL
xmlUTF8Strsize (const xmlChar *utf,
int len);
XMLPUBFUN xmlChar * XMLCALL
xmlUTF8Strndup (const xmlChar *utf,
int len);
XMLPUBFUN const xmlChar * XMLCALL
xmlUTF8Strpos (const xmlChar *utf,
int pos);
XMLPUBFUN int XMLCALL
xmlUTF8Strloc (const xmlChar *utf,
const xmlChar *utfchar);
XMLPUBFUN xmlChar * XMLCALL
xmlUTF8Strsub (const xmlChar *utf,
int start,
int len);
XMLPUBFUN int XMLCALL
xmlUTF8Strlen (const xmlChar *utf);
XMLPUBFUN int XMLCALL
xmlUTF8Size (const xmlChar *utf);
XMLPUBFUN int XMLCALL
xmlUTF8Charcmp (const xmlChar *utf1,
const xmlChar *utf2);
#ifdef __cplusplus
}
#endif
#endif /* __XML_STRING_H__ */

@ -0,0 +1,202 @@
/*
* Summary: Unicode character APIs
* Description: API for the Unicode character APIs
*
* This file is automatically generated from the
* UCS description files of the Unicode Character Database
* http://www.unicode.org/Public/4.0-Update1/UCD-4.0.1.html
* using the genUnicode.py Python script.
*
* Generation date: Mon Mar 27 11:09:52 2006
* Sources: Blocks-4.0.1.txt UnicodeData-4.0.1.txt
* Author: Daniel Veillard
*/
#ifndef __XML_UNICODE_H__
#define __XML_UNICODE_H__
#include <libxml/xmlversion.h>
#ifdef LIBXML_UNICODE_ENABLED
#ifdef __cplusplus
extern "C" {
#endif
XMLPUBFUN int XMLCALL xmlUCSIsAegeanNumbers (int code);
XMLPUBFUN int XMLCALL xmlUCSIsAlphabeticPresentationForms (int code);
XMLPUBFUN int XMLCALL xmlUCSIsArabic (int code);
XMLPUBFUN int XMLCALL xmlUCSIsArabicPresentationFormsA (int code);
XMLPUBFUN int XMLCALL xmlUCSIsArabicPresentationFormsB (int code);
XMLPUBFUN int XMLCALL xmlUCSIsArmenian (int code);
XMLPUBFUN int XMLCALL xmlUCSIsArrows (int code);
XMLPUBFUN int XMLCALL xmlUCSIsBasicLatin (int code);
XMLPUBFUN int XMLCALL xmlUCSIsBengali (int code);
XMLPUBFUN int XMLCALL xmlUCSIsBlockElements (int code);
XMLPUBFUN int XMLCALL xmlUCSIsBopomofo (int code);
XMLPUBFUN int XMLCALL xmlUCSIsBopomofoExtended (int code);
XMLPUBFUN int XMLCALL xmlUCSIsBoxDrawing (int code);
XMLPUBFUN int XMLCALL xmlUCSIsBraillePatterns (int code);
XMLPUBFUN int XMLCALL xmlUCSIsBuhid (int code);
XMLPUBFUN int XMLCALL xmlUCSIsByzantineMusicalSymbols (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCJKCompatibility (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCJKCompatibilityForms (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCJKCompatibilityIdeographs (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCJKCompatibilityIdeographsSupplement (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCJKRadicalsSupplement (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCJKSymbolsandPunctuation (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCJKUnifiedIdeographs (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCJKUnifiedIdeographsExtensionA (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCJKUnifiedIdeographsExtensionB (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCherokee (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCombiningDiacriticalMarks (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCombiningDiacriticalMarksforSymbols (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCombiningHalfMarks (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCombiningMarksforSymbols (int code);
XMLPUBFUN int XMLCALL xmlUCSIsControlPictures (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCurrencySymbols (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCypriotSyllabary (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCyrillic (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCyrillicSupplement (int code);
XMLPUBFUN int XMLCALL xmlUCSIsDeseret (int code);
XMLPUBFUN int XMLCALL xmlUCSIsDevanagari (int code);
XMLPUBFUN int XMLCALL xmlUCSIsDingbats (int code);
XMLPUBFUN int XMLCALL xmlUCSIsEnclosedAlphanumerics (int code);
XMLPUBFUN int XMLCALL xmlUCSIsEnclosedCJKLettersandMonths (int code);
XMLPUBFUN int XMLCALL xmlUCSIsEthiopic (int code);
XMLPUBFUN int XMLCALL xmlUCSIsGeneralPunctuation (int code);
XMLPUBFUN int XMLCALL xmlUCSIsGeometricShapes (int code);
XMLPUBFUN int XMLCALL xmlUCSIsGeorgian (int code);
XMLPUBFUN int XMLCALL xmlUCSIsGothic (int code);
XMLPUBFUN int XMLCALL xmlUCSIsGreek (int code);
XMLPUBFUN int XMLCALL xmlUCSIsGreekExtended (int code);
XMLPUBFUN int XMLCALL xmlUCSIsGreekandCoptic (int code);
XMLPUBFUN int XMLCALL xmlUCSIsGujarati (int code);
XMLPUBFUN int XMLCALL xmlUCSIsGurmukhi (int code);
XMLPUBFUN int XMLCALL xmlUCSIsHalfwidthandFullwidthForms (int code);
XMLPUBFUN int XMLCALL xmlUCSIsHangulCompatibilityJamo (int code);
XMLPUBFUN int XMLCALL xmlUCSIsHangulJamo (int code);
XMLPUBFUN int XMLCALL xmlUCSIsHangulSyllables (int code);
XMLPUBFUN int XMLCALL xmlUCSIsHanunoo (int code);
XMLPUBFUN int XMLCALL xmlUCSIsHebrew (int code);
XMLPUBFUN int XMLCALL xmlUCSIsHighPrivateUseSurrogates (int code);
XMLPUBFUN int XMLCALL xmlUCSIsHighSurrogates (int code);
XMLPUBFUN int XMLCALL xmlUCSIsHiragana (int code);
XMLPUBFUN int XMLCALL xmlUCSIsIPAExtensions (int code);
XMLPUBFUN int XMLCALL xmlUCSIsIdeographicDescriptionCharacters (int code);
XMLPUBFUN int XMLCALL xmlUCSIsKanbun (int code);
XMLPUBFUN int XMLCALL xmlUCSIsKangxiRadicals (int code);
XMLPUBFUN int XMLCALL xmlUCSIsKannada (int code);
XMLPUBFUN int XMLCALL xmlUCSIsKatakana (int code);
XMLPUBFUN int XMLCALL xmlUCSIsKatakanaPhoneticExtensions (int code);
XMLPUBFUN int XMLCALL xmlUCSIsKhmer (int code);
XMLPUBFUN int XMLCALL xmlUCSIsKhmerSymbols (int code);
XMLPUBFUN int XMLCALL xmlUCSIsLao (int code);
XMLPUBFUN int XMLCALL xmlUCSIsLatin1Supplement (int code);
XMLPUBFUN int XMLCALL xmlUCSIsLatinExtendedA (int code);
XMLPUBFUN int XMLCALL xmlUCSIsLatinExtendedB (int code);
XMLPUBFUN int XMLCALL xmlUCSIsLatinExtendedAdditional (int code);
XMLPUBFUN int XMLCALL xmlUCSIsLetterlikeSymbols (int code);
XMLPUBFUN int XMLCALL xmlUCSIsLimbu (int code);
XMLPUBFUN int XMLCALL xmlUCSIsLinearBIdeograms (int code);
XMLPUBFUN int XMLCALL xmlUCSIsLinearBSyllabary (int code);
XMLPUBFUN int XMLCALL xmlUCSIsLowSurrogates (int code);
XMLPUBFUN int XMLCALL xmlUCSIsMalayalam (int code);
XMLPUBFUN int XMLCALL xmlUCSIsMathematicalAlphanumericSymbols (int code);
XMLPUBFUN int XMLCALL xmlUCSIsMathematicalOperators (int code);
XMLPUBFUN int XMLCALL xmlUCSIsMiscellaneousMathematicalSymbolsA (int code);
XMLPUBFUN int XMLCALL xmlUCSIsMiscellaneousMathematicalSymbolsB (int code);
XMLPUBFUN int XMLCALL xmlUCSIsMiscellaneousSymbols (int code);
XMLPUBFUN int XMLCALL xmlUCSIsMiscellaneousSymbolsandArrows (int code);
XMLPUBFUN int XMLCALL xmlUCSIsMiscellaneousTechnical (int code);
XMLPUBFUN int XMLCALL xmlUCSIsMongolian (int code);
XMLPUBFUN int XMLCALL xmlUCSIsMusicalSymbols (int code);
XMLPUBFUN int XMLCALL xmlUCSIsMyanmar (int code);
XMLPUBFUN int XMLCALL xmlUCSIsNumberForms (int code);
XMLPUBFUN int XMLCALL xmlUCSIsOgham (int code);
XMLPUBFUN int XMLCALL xmlUCSIsOldItalic (int code);
XMLPUBFUN int XMLCALL xmlUCSIsOpticalCharacterRecognition (int code);
XMLPUBFUN int XMLCALL xmlUCSIsOriya (int code);
XMLPUBFUN int XMLCALL xmlUCSIsOsmanya (int code);
XMLPUBFUN int XMLCALL xmlUCSIsPhoneticExtensions (int code);
XMLPUBFUN int XMLCALL xmlUCSIsPrivateUse (int code);
XMLPUBFUN int XMLCALL xmlUCSIsPrivateUseArea (int code);
XMLPUBFUN int XMLCALL xmlUCSIsRunic (int code);
XMLPUBFUN int XMLCALL xmlUCSIsShavian (int code);
XMLPUBFUN int XMLCALL xmlUCSIsSinhala (int code);
XMLPUBFUN int XMLCALL xmlUCSIsSmallFormVariants (int code);
XMLPUBFUN int XMLCALL xmlUCSIsSpacingModifierLetters (int code);
XMLPUBFUN int XMLCALL xmlUCSIsSpecials (int code);
XMLPUBFUN int XMLCALL xmlUCSIsSuperscriptsandSubscripts (int code);
XMLPUBFUN int XMLCALL xmlUCSIsSupplementalArrowsA (int code);
XMLPUBFUN int XMLCALL xmlUCSIsSupplementalArrowsB (int code);
XMLPUBFUN int XMLCALL xmlUCSIsSupplementalMathematicalOperators (int code);
XMLPUBFUN int XMLCALL xmlUCSIsSupplementaryPrivateUseAreaA (int code);
XMLPUBFUN int XMLCALL xmlUCSIsSupplementaryPrivateUseAreaB (int code);
XMLPUBFUN int XMLCALL xmlUCSIsSyriac (int code);
XMLPUBFUN int XMLCALL xmlUCSIsTagalog (int code);
XMLPUBFUN int XMLCALL xmlUCSIsTagbanwa (int code);
XMLPUBFUN int XMLCALL xmlUCSIsTags (int code);
XMLPUBFUN int XMLCALL xmlUCSIsTaiLe (int code);
XMLPUBFUN int XMLCALL xmlUCSIsTaiXuanJingSymbols (int code);
XMLPUBFUN int XMLCALL xmlUCSIsTamil (int code);
XMLPUBFUN int XMLCALL xmlUCSIsTelugu (int code);
XMLPUBFUN int XMLCALL xmlUCSIsThaana (int code);
XMLPUBFUN int XMLCALL xmlUCSIsThai (int code);
XMLPUBFUN int XMLCALL xmlUCSIsTibetan (int code);
XMLPUBFUN int XMLCALL xmlUCSIsUgaritic (int code);
XMLPUBFUN int XMLCALL xmlUCSIsUnifiedCanadianAboriginalSyllabics (int code);
XMLPUBFUN int XMLCALL xmlUCSIsVariationSelectors (int code);
XMLPUBFUN int XMLCALL xmlUCSIsVariationSelectorsSupplement (int code);
XMLPUBFUN int XMLCALL xmlUCSIsYiRadicals (int code);
XMLPUBFUN int XMLCALL xmlUCSIsYiSyllables (int code);
XMLPUBFUN int XMLCALL xmlUCSIsYijingHexagramSymbols (int code);
XMLPUBFUN int XMLCALL xmlUCSIsBlock (int code, const char *block);
XMLPUBFUN int XMLCALL xmlUCSIsCatC (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatCc (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatCf (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatCo (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatCs (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatL (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatLl (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatLm (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatLo (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatLt (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatLu (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatM (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatMc (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatMe (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatMn (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatN (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatNd (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatNl (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatNo (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatP (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatPc (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatPd (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatPe (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatPf (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatPi (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatPo (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatPs (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatS (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatSc (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatSk (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatSm (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatSo (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatZ (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatZl (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatZp (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCatZs (int code);
XMLPUBFUN int XMLCALL xmlUCSIsCat (int code, const char *cat);
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_UNICODE_ENABLED */
#endif /* __XML_UNICODE_H__ */

@ -0,0 +1,489 @@
/*
* Summary: compile-time version informations
* Description: compile-time version informations for the XML library
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_VERSION_H__
#define __XML_VERSION_H__
#include <libxml/xmlexports.h>
#ifdef __cplusplus
extern "C" {
#endif
/*
* use those to be sure nothing nasty will happen if
* your library and includes mismatch
*/
#ifndef LIBXML2_COMPILING_MSCCDEF
XMLPUBFUN void XMLCALL xmlCheckVersion(int version);
#endif /* LIBXML2_COMPILING_MSCCDEF */
/**
* LIBXML_DOTTED_VERSION:
*
* the version string like "1.2.3"
*/
#define LIBXML_DOTTED_VERSION "2.9.5"
/**
* LIBXML_VERSION:
*
* the version number: 1.2.3 value is 10203
*/
#define LIBXML_VERSION 20905
/**
* LIBXML_VERSION_STRING:
*
* the version number string, 1.2.3 value is "10203"
*/
#define LIBXML_VERSION_STRING "20905"
/**
* LIBXML_VERSION_EXTRA:
*
* extra version information, used to show a CVS compilation
*/
#define LIBXML_VERSION_EXTRA ""
/**
* LIBXML_TEST_VERSION:
*
* Macro to check that the libxml version in use is compatible with
* the version the software has been compiled against
*/
#define LIBXML_TEST_VERSION xmlCheckVersion(20905);
#ifndef VMS
#if 0
/**
* WITH_TRIO:
*
* defined if the trio support need to be configured in
*/
#define WITH_TRIO
#else
/**
* WITHOUT_TRIO:
*
* defined if the trio support should not be configured in
*/
#define WITHOUT_TRIO
#endif
#else /* VMS */
/**
* WITH_TRIO:
*
* defined if the trio support need to be configured in
*/
#define WITH_TRIO 1
#endif /* VMS */
/**
* LIBXML_THREAD_ENABLED:
*
* Whether the thread support is configured in
*/
#if 1
#if defined(_REENTRANT) || defined(__MT__) || \
(defined(_POSIX_C_SOURCE) && (_POSIX_C_SOURCE - 0 >= 199506L))
#define LIBXML_THREAD_ENABLED
#endif
#endif
/**
* LIBXML_THREAD_ALLOC_ENABLED:
*
* Whether the allocation hooks are per-thread
*/
#if 0
#define LIBXML_THREAD_ALLOC_ENABLED
#endif
/**
* LIBXML_TREE_ENABLED:
*
* Whether the DOM like tree manipulation API support is configured in
*/
#if 1
#define LIBXML_TREE_ENABLED
#endif
/**
* LIBXML_OUTPUT_ENABLED:
*
* Whether the serialization/saving support is configured in
*/
#if 1
#define LIBXML_OUTPUT_ENABLED
#endif
/**
* LIBXML_PUSH_ENABLED:
*
* Whether the push parsing interfaces are configured in
*/
#if 1
#define LIBXML_PUSH_ENABLED
#endif
/**
* LIBXML_READER_ENABLED:
*
* Whether the xmlReader parsing interface is configured in
*/
#if 1
#define LIBXML_READER_ENABLED
#endif
/**
* LIBXML_PATTERN_ENABLED:
*
* Whether the xmlPattern node selection interface is configured in
*/
#if 1
#define LIBXML_PATTERN_ENABLED
#endif
/**
* LIBXML_WRITER_ENABLED:
*
* Whether the xmlWriter saving interface is configured in
*/
#if 1
#define LIBXML_WRITER_ENABLED
#endif
/**
* LIBXML_SAX1_ENABLED:
*
* Whether the older SAX1 interface is configured in
*/
#if 1
#define LIBXML_SAX1_ENABLED
#endif
/**
* LIBXML_FTP_ENABLED:
*
* Whether the FTP support is configured in
*/
#if 1
#define LIBXML_FTP_ENABLED
#endif
/**
* LIBXML_HTTP_ENABLED:
*
* Whether the HTTP support is configured in
*/
#if 1
#define LIBXML_HTTP_ENABLED
#endif
/**
* LIBXML_VALID_ENABLED:
*
* Whether the DTD validation support is configured in
*/
#if 1
#define LIBXML_VALID_ENABLED
#endif
/**
* LIBXML_HTML_ENABLED:
*
* Whether the HTML support is configured in
*/
#if 1
#define LIBXML_HTML_ENABLED
#endif
/**
* LIBXML_LEGACY_ENABLED:
*
* Whether the deprecated APIs are compiled in for compatibility
*/
#if 1
#define LIBXML_LEGACY_ENABLED
#endif
/**
* LIBXML_C14N_ENABLED:
*
* Whether the Canonicalization support is configured in
*/
#if 1
#define LIBXML_C14N_ENABLED
#endif
/**
* LIBXML_CATALOG_ENABLED:
*
* Whether the Catalog support is configured in
*/
#if 1
#define LIBXML_CATALOG_ENABLED
#endif
/**
* LIBXML_DOCB_ENABLED:
*
* Whether the SGML Docbook support is configured in
*/
#if 1
#define LIBXML_DOCB_ENABLED
#endif
/**
* LIBXML_XPATH_ENABLED:
*
* Whether XPath is configured in
*/
#if 1
#define LIBXML_XPATH_ENABLED
#endif
/**
* LIBXML_XPTR_ENABLED:
*
* Whether XPointer is configured in
*/
#if 1
#define LIBXML_XPTR_ENABLED
#endif
/**
* LIBXML_XINCLUDE_ENABLED:
*
* Whether XInclude is configured in
*/
#if 1
#define LIBXML_XINCLUDE_ENABLED
#endif
/**
* LIBXML_ICONV_ENABLED:
*
* Whether iconv support is available
*/
#if 1
#define LIBXML_ICONV_ENABLED
#endif
/**
* LIBXML_ICU_ENABLED:
*
* Whether icu support is available
*/
#if 0
#define LIBXML_ICU_ENABLED
#endif
/**
* LIBXML_ISO8859X_ENABLED:
*
* Whether ISO-8859-* support is made available in case iconv is not
*/
#if 0
#define LIBXML_ISO8859X_ENABLED
#endif
/**
* LIBXML_DEBUG_ENABLED:
*
* Whether Debugging module is configured in
*/
#if 1
#define LIBXML_DEBUG_ENABLED
#endif
/**
* DEBUG_MEMORY_LOCATION:
*
* Whether the memory debugging is configured in
*/
#if 0
#define DEBUG_MEMORY_LOCATION
#endif
/**
* LIBXML_DEBUG_RUNTIME:
*
* Whether the runtime debugging is configured in
*/
#if 0
#define LIBXML_DEBUG_RUNTIME
#endif
/**
* LIBXML_UNICODE_ENABLED:
*
* Whether the Unicode related interfaces are compiled in
*/
#if 1
#define LIBXML_UNICODE_ENABLED
#endif
/**
* LIBXML_REGEXP_ENABLED:
*
* Whether the regular expressions interfaces are compiled in
*/
#if 1
#define LIBXML_REGEXP_ENABLED
#endif
/**
* LIBXML_AUTOMATA_ENABLED:
*
* Whether the automata interfaces are compiled in
*/
#if 1
#define LIBXML_AUTOMATA_ENABLED
#endif
/**
* LIBXML_EXPR_ENABLED:
*
* Whether the formal expressions interfaces are compiled in
*/
#if 1
#define LIBXML_EXPR_ENABLED
#endif
/**
* LIBXML_SCHEMAS_ENABLED:
*
* Whether the Schemas validation interfaces are compiled in
*/
#if 1
#define LIBXML_SCHEMAS_ENABLED
#endif
/**
* LIBXML_SCHEMATRON_ENABLED:
*
* Whether the Schematron validation interfaces are compiled in
*/
#if 1
#define LIBXML_SCHEMATRON_ENABLED
#endif
/**
* LIBXML_MODULES_ENABLED:
*
* Whether the module interfaces are compiled in
*/
#if 1
#define LIBXML_MODULES_ENABLED
/**
* LIBXML_MODULE_EXTENSION:
*
* the string suffix used by dynamic modules (usually shared libraries)
*/
#define LIBXML_MODULE_EXTENSION ".dll"
#endif
/**
* LIBXML_ZLIB_ENABLED:
*
* Whether the Zlib support is compiled in
*/
#if 1
#define LIBXML_ZLIB_ENABLED
#endif
/**
* LIBXML_LZMA_ENABLED:
*
* Whether the Lzma support is compiled in
*/
#if 0
#define LIBXML_LZMA_ENABLED
#endif
#ifdef __GNUC__
#ifdef HAVE_ANSIDECL_H
#include <ansidecl.h>
#endif
/**
* ATTRIBUTE_UNUSED:
*
* Macro used to signal to GCC unused function parameters
*/
#ifndef ATTRIBUTE_UNUSED
# if ((__GNUC__ > 2) || ((__GNUC__ == 2) && (__GNUC_MINOR__ >= 7)))
# define ATTRIBUTE_UNUSED __attribute__((unused))
# else
# define ATTRIBUTE_UNUSED
# endif
#endif
/**
* LIBXML_ATTR_ALLOC_SIZE:
*
* Macro used to indicate to GCC this is an allocator function
*/
#ifndef LIBXML_ATTR_ALLOC_SIZE
# if (!defined(__clang__) && ((__GNUC__ > 4) || ((__GNUC__ == 4) && (__GNUC_MINOR__ >= 3))))
# define LIBXML_ATTR_ALLOC_SIZE(x) __attribute__((alloc_size(x)))
# else
# define LIBXML_ATTR_ALLOC_SIZE(x)
# endif
#else
# define LIBXML_ATTR_ALLOC_SIZE(x)
#endif
/**
* LIBXML_ATTR_FORMAT:
*
* Macro used to indicate to GCC the parameter are printf like
*/
#ifndef LIBXML_ATTR_FORMAT
# if ((__GNUC__ > 3) || ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 3)))
# define LIBXML_ATTR_FORMAT(fmt,args) __attribute__((__format__(__printf__,fmt,args)))
# else
# define LIBXML_ATTR_FORMAT(fmt,args)
# endif
#else
# define LIBXML_ATTR_FORMAT(fmt,args)
#endif
#else /* ! __GNUC__ */
/**
* ATTRIBUTE_UNUSED:
*
* Macro used to signal to GCC unused function parameters
*/
#define ATTRIBUTE_UNUSED
/**
* LIBXML_ATTR_ALLOC_SIZE:
*
* Macro used to indicate to GCC this is an allocator function
*/
#define LIBXML_ATTR_ALLOC_SIZE(x)
/**
* LIBXML_ATTR_FORMAT:
*
* Macro used to indicate to GCC the parameter are printf like
*/
#define LIBXML_ATTR_FORMAT(fmt,args)
#endif /* __GNUC__ */
#ifdef __cplusplus
}
#endif /* __cplusplus */
#endif

@ -0,0 +1,488 @@
/*
* Summary: text writing API for XML
* Description: text writing API for XML
*
* Copy: See Copyright for the status of this software.
*
* Author: Alfred Mickautsch <alfred@mickautsch.de>
*/
#ifndef __XML_XMLWRITER_H__
#define __XML_XMLWRITER_H__
#include <libxml/xmlversion.h>
#ifdef LIBXML_WRITER_ENABLED
#include <stdarg.h>
#include <libxml/xmlIO.h>
#include <libxml/list.h>
#include <libxml/xmlstring.h>
#ifdef __cplusplus
extern "C" {
#endif
typedef struct _xmlTextWriter xmlTextWriter;
typedef xmlTextWriter *xmlTextWriterPtr;
/*
* Constructors & Destructor
*/
XMLPUBFUN xmlTextWriterPtr XMLCALL
xmlNewTextWriter(xmlOutputBufferPtr out);
XMLPUBFUN xmlTextWriterPtr XMLCALL
xmlNewTextWriterFilename(const char *uri, int compression);
XMLPUBFUN xmlTextWriterPtr XMLCALL
xmlNewTextWriterMemory(xmlBufferPtr buf, int compression);
XMLPUBFUN xmlTextWriterPtr XMLCALL
xmlNewTextWriterPushParser(xmlParserCtxtPtr ctxt, int compression);
XMLPUBFUN xmlTextWriterPtr XMLCALL
xmlNewTextWriterDoc(xmlDocPtr * doc, int compression);
XMLPUBFUN xmlTextWriterPtr XMLCALL
xmlNewTextWriterTree(xmlDocPtr doc, xmlNodePtr node,
int compression);
XMLPUBFUN void XMLCALL xmlFreeTextWriter(xmlTextWriterPtr writer);
/*
* Functions
*/
/*
* Document
*/
XMLPUBFUN int XMLCALL
xmlTextWriterStartDocument(xmlTextWriterPtr writer,
const char *version,
const char *encoding,
const char *standalone);
XMLPUBFUN int XMLCALL xmlTextWriterEndDocument(xmlTextWriterPtr
writer);
/*
* Comments
*/
XMLPUBFUN int XMLCALL xmlTextWriterStartComment(xmlTextWriterPtr
writer);
XMLPUBFUN int XMLCALL xmlTextWriterEndComment(xmlTextWriterPtr writer);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteFormatComment(xmlTextWriterPtr writer,
const char *format, ...)
LIBXML_ATTR_FORMAT(2,3);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteVFormatComment(xmlTextWriterPtr writer,
const char *format,
va_list argptr)
LIBXML_ATTR_FORMAT(2,0);
XMLPUBFUN int XMLCALL xmlTextWriterWriteComment(xmlTextWriterPtr
writer,
const xmlChar *
content);
/*
* Elements
*/
XMLPUBFUN int XMLCALL
xmlTextWriterStartElement(xmlTextWriterPtr writer,
const xmlChar * name);
XMLPUBFUN int XMLCALL xmlTextWriterStartElementNS(xmlTextWriterPtr
writer,
const xmlChar *
prefix,
const xmlChar * name,
const xmlChar *
namespaceURI);
XMLPUBFUN int XMLCALL xmlTextWriterEndElement(xmlTextWriterPtr writer);
XMLPUBFUN int XMLCALL xmlTextWriterFullEndElement(xmlTextWriterPtr
writer);
/*
* Elements conveniency functions
*/
XMLPUBFUN int XMLCALL
xmlTextWriterWriteFormatElement(xmlTextWriterPtr writer,
const xmlChar * name,
const char *format, ...)
LIBXML_ATTR_FORMAT(3,4);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteVFormatElement(xmlTextWriterPtr writer,
const xmlChar * name,
const char *format,
va_list argptr)
LIBXML_ATTR_FORMAT(3,0);
XMLPUBFUN int XMLCALL xmlTextWriterWriteElement(xmlTextWriterPtr
writer,
const xmlChar * name,
const xmlChar *
content);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteFormatElementNS(xmlTextWriterPtr writer,
const xmlChar * prefix,
const xmlChar * name,
const xmlChar * namespaceURI,
const char *format, ...)
LIBXML_ATTR_FORMAT(5,6);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteVFormatElementNS(xmlTextWriterPtr writer,
const xmlChar * prefix,
const xmlChar * name,
const xmlChar * namespaceURI,
const char *format,
va_list argptr)
LIBXML_ATTR_FORMAT(5,0);
XMLPUBFUN int XMLCALL xmlTextWriterWriteElementNS(xmlTextWriterPtr
writer,
const xmlChar *
prefix,
const xmlChar * name,
const xmlChar *
namespaceURI,
const xmlChar *
content);
/*
* Text
*/
XMLPUBFUN int XMLCALL
xmlTextWriterWriteFormatRaw(xmlTextWriterPtr writer,
const char *format, ...)
LIBXML_ATTR_FORMAT(2,3);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteVFormatRaw(xmlTextWriterPtr writer,
const char *format, va_list argptr)
LIBXML_ATTR_FORMAT(2,0);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteRawLen(xmlTextWriterPtr writer,
const xmlChar * content, int len);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteRaw(xmlTextWriterPtr writer,
const xmlChar * content);
XMLPUBFUN int XMLCALL xmlTextWriterWriteFormatString(xmlTextWriterPtr
writer,
const char
*format, ...)
LIBXML_ATTR_FORMAT(2,3);
XMLPUBFUN int XMLCALL xmlTextWriterWriteVFormatString(xmlTextWriterPtr
writer,
const char
*format,
va_list argptr)
LIBXML_ATTR_FORMAT(2,0);
XMLPUBFUN int XMLCALL xmlTextWriterWriteString(xmlTextWriterPtr writer,
const xmlChar *
content);
XMLPUBFUN int XMLCALL xmlTextWriterWriteBase64(xmlTextWriterPtr writer,
const char *data,
int start, int len);
XMLPUBFUN int XMLCALL xmlTextWriterWriteBinHex(xmlTextWriterPtr writer,
const char *data,
int start, int len);
/*
* Attributes
*/
XMLPUBFUN int XMLCALL
xmlTextWriterStartAttribute(xmlTextWriterPtr writer,
const xmlChar * name);
XMLPUBFUN int XMLCALL xmlTextWriterStartAttributeNS(xmlTextWriterPtr
writer,
const xmlChar *
prefix,
const xmlChar *
name,
const xmlChar *
namespaceURI);
XMLPUBFUN int XMLCALL xmlTextWriterEndAttribute(xmlTextWriterPtr
writer);
/*
* Attributes conveniency functions
*/
XMLPUBFUN int XMLCALL
xmlTextWriterWriteFormatAttribute(xmlTextWriterPtr writer,
const xmlChar * name,
const char *format, ...)
LIBXML_ATTR_FORMAT(3,4);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteVFormatAttribute(xmlTextWriterPtr writer,
const xmlChar * name,
const char *format,
va_list argptr)
LIBXML_ATTR_FORMAT(3,0);
XMLPUBFUN int XMLCALL xmlTextWriterWriteAttribute(xmlTextWriterPtr
writer,
const xmlChar * name,
const xmlChar *
content);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteFormatAttributeNS(xmlTextWriterPtr writer,
const xmlChar * prefix,
const xmlChar * name,
const xmlChar * namespaceURI,
const char *format, ...)
LIBXML_ATTR_FORMAT(5,6);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteVFormatAttributeNS(xmlTextWriterPtr writer,
const xmlChar * prefix,
const xmlChar * name,
const xmlChar * namespaceURI,
const char *format,
va_list argptr)
LIBXML_ATTR_FORMAT(5,0);
XMLPUBFUN int XMLCALL xmlTextWriterWriteAttributeNS(xmlTextWriterPtr
writer,
const xmlChar *
prefix,
const xmlChar *
name,
const xmlChar *
namespaceURI,
const xmlChar *
content);
/*
* PI's
*/
XMLPUBFUN int XMLCALL
xmlTextWriterStartPI(xmlTextWriterPtr writer,
const xmlChar * target);
XMLPUBFUN int XMLCALL xmlTextWriterEndPI(xmlTextWriterPtr writer);
/*
* PI conveniency functions
*/
XMLPUBFUN int XMLCALL
xmlTextWriterWriteFormatPI(xmlTextWriterPtr writer,
const xmlChar * target,
const char *format, ...)
LIBXML_ATTR_FORMAT(3,4);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteVFormatPI(xmlTextWriterPtr writer,
const xmlChar * target,
const char *format, va_list argptr)
LIBXML_ATTR_FORMAT(3,0);
XMLPUBFUN int XMLCALL
xmlTextWriterWritePI(xmlTextWriterPtr writer,
const xmlChar * target,
const xmlChar * content);
/**
* xmlTextWriterWriteProcessingInstruction:
*
* This macro maps to xmlTextWriterWritePI
*/
#define xmlTextWriterWriteProcessingInstruction xmlTextWriterWritePI
/*
* CDATA
*/
XMLPUBFUN int XMLCALL xmlTextWriterStartCDATA(xmlTextWriterPtr writer);
XMLPUBFUN int XMLCALL xmlTextWriterEndCDATA(xmlTextWriterPtr writer);
/*
* CDATA conveniency functions
*/
XMLPUBFUN int XMLCALL
xmlTextWriterWriteFormatCDATA(xmlTextWriterPtr writer,
const char *format, ...)
LIBXML_ATTR_FORMAT(2,3);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteVFormatCDATA(xmlTextWriterPtr writer,
const char *format, va_list argptr)
LIBXML_ATTR_FORMAT(2,0);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteCDATA(xmlTextWriterPtr writer,
const xmlChar * content);
/*
* DTD
*/
XMLPUBFUN int XMLCALL
xmlTextWriterStartDTD(xmlTextWriterPtr writer,
const xmlChar * name,
const xmlChar * pubid,
const xmlChar * sysid);
XMLPUBFUN int XMLCALL xmlTextWriterEndDTD(xmlTextWriterPtr writer);
/*
* DTD conveniency functions
*/
XMLPUBFUN int XMLCALL
xmlTextWriterWriteFormatDTD(xmlTextWriterPtr writer,
const xmlChar * name,
const xmlChar * pubid,
const xmlChar * sysid,
const char *format, ...)
LIBXML_ATTR_FORMAT(5,6);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteVFormatDTD(xmlTextWriterPtr writer,
const xmlChar * name,
const xmlChar * pubid,
const xmlChar * sysid,
const char *format, va_list argptr)
LIBXML_ATTR_FORMAT(5,0);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteDTD(xmlTextWriterPtr writer,
const xmlChar * name,
const xmlChar * pubid,
const xmlChar * sysid,
const xmlChar * subset);
/**
* xmlTextWriterWriteDocType:
*
* this macro maps to xmlTextWriterWriteDTD
*/
#define xmlTextWriterWriteDocType xmlTextWriterWriteDTD
/*
* DTD element definition
*/
XMLPUBFUN int XMLCALL
xmlTextWriterStartDTDElement(xmlTextWriterPtr writer,
const xmlChar * name);
XMLPUBFUN int XMLCALL xmlTextWriterEndDTDElement(xmlTextWriterPtr
writer);
/*
* DTD element definition conveniency functions
*/
XMLPUBFUN int XMLCALL
xmlTextWriterWriteFormatDTDElement(xmlTextWriterPtr writer,
const xmlChar * name,
const char *format, ...)
LIBXML_ATTR_FORMAT(3,4);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteVFormatDTDElement(xmlTextWriterPtr writer,
const xmlChar * name,
const char *format,
va_list argptr)
LIBXML_ATTR_FORMAT(3,0);
XMLPUBFUN int XMLCALL xmlTextWriterWriteDTDElement(xmlTextWriterPtr
writer,
const xmlChar *
name,
const xmlChar *
content);
/*
* DTD attribute list definition
*/
XMLPUBFUN int XMLCALL
xmlTextWriterStartDTDAttlist(xmlTextWriterPtr writer,
const xmlChar * name);
XMLPUBFUN int XMLCALL xmlTextWriterEndDTDAttlist(xmlTextWriterPtr
writer);
/*
* DTD attribute list definition conveniency functions
*/
XMLPUBFUN int XMLCALL
xmlTextWriterWriteFormatDTDAttlist(xmlTextWriterPtr writer,
const xmlChar * name,
const char *format, ...)
LIBXML_ATTR_FORMAT(3,4);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteVFormatDTDAttlist(xmlTextWriterPtr writer,
const xmlChar * name,
const char *format,
va_list argptr)
LIBXML_ATTR_FORMAT(3,0);
XMLPUBFUN int XMLCALL xmlTextWriterWriteDTDAttlist(xmlTextWriterPtr
writer,
const xmlChar *
name,
const xmlChar *
content);
/*
* DTD entity definition
*/
XMLPUBFUN int XMLCALL
xmlTextWriterStartDTDEntity(xmlTextWriterPtr writer,
int pe, const xmlChar * name);
XMLPUBFUN int XMLCALL xmlTextWriterEndDTDEntity(xmlTextWriterPtr
writer);
/*
* DTD entity definition conveniency functions
*/
XMLPUBFUN int XMLCALL
xmlTextWriterWriteFormatDTDInternalEntity(xmlTextWriterPtr writer,
int pe,
const xmlChar * name,
const char *format, ...)
LIBXML_ATTR_FORMAT(4,5);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteVFormatDTDInternalEntity(xmlTextWriterPtr writer,
int pe,
const xmlChar * name,
const char *format,
va_list argptr)
LIBXML_ATTR_FORMAT(4,0);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteDTDInternalEntity(xmlTextWriterPtr writer,
int pe,
const xmlChar * name,
const xmlChar * content);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteDTDExternalEntity(xmlTextWriterPtr writer,
int pe,
const xmlChar * name,
const xmlChar * pubid,
const xmlChar * sysid,
const xmlChar * ndataid);
XMLPUBFUN int XMLCALL
xmlTextWriterWriteDTDExternalEntityContents(xmlTextWriterPtr
writer,
const xmlChar * pubid,
const xmlChar * sysid,
const xmlChar *
ndataid);
XMLPUBFUN int XMLCALL xmlTextWriterWriteDTDEntity(xmlTextWriterPtr
writer, int pe,
const xmlChar * name,
const xmlChar *
pubid,
const xmlChar *
sysid,
const xmlChar *
ndataid,
const xmlChar *
content);
/*
* DTD notation definition
*/
XMLPUBFUN int XMLCALL
xmlTextWriterWriteDTDNotation(xmlTextWriterPtr writer,
const xmlChar * name,
const xmlChar * pubid,
const xmlChar * sysid);
/*
* Indentation
*/
XMLPUBFUN int XMLCALL
xmlTextWriterSetIndent(xmlTextWriterPtr writer, int indent);
XMLPUBFUN int XMLCALL
xmlTextWriterSetIndentString(xmlTextWriterPtr writer,
const xmlChar * str);
XMLPUBFUN int XMLCALL
xmlTextWriterSetQuoteChar(xmlTextWriterPtr writer, xmlChar quotechar);
/*
* misc
*/
XMLPUBFUN int XMLCALL xmlTextWriterFlush(xmlTextWriterPtr writer);
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_WRITER_ENABLED */
#endif /* __XML_XMLWRITER_H__ */

@ -0,0 +1,557 @@
/*
* Summary: XML Path Language implementation
* Description: API for the XML Path Language implementation
*
* XML Path Language implementation
* XPath is a language for addressing parts of an XML document,
* designed to be used by both XSLT and XPointer
* http://www.w3.org/TR/xpath
*
* Implements
* W3C Recommendation 16 November 1999
* http://www.w3.org/TR/1999/REC-xpath-19991116
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_XPATH_H__
#define __XML_XPATH_H__
#include <libxml/xmlversion.h>
#ifdef LIBXML_XPATH_ENABLED
#include <libxml/xmlerror.h>
#include <libxml/tree.h>
#include <libxml/hash.h>
#endif /* LIBXML_XPATH_ENABLED */
#if defined(LIBXML_XPATH_ENABLED) || defined(LIBXML_SCHEMAS_ENABLED)
#ifdef __cplusplus
extern "C" {
#endif
#endif /* LIBXML_XPATH_ENABLED or LIBXML_SCHEMAS_ENABLED */
#ifdef LIBXML_XPATH_ENABLED
typedef struct _xmlXPathContext xmlXPathContext;
typedef xmlXPathContext *xmlXPathContextPtr;
typedef struct _xmlXPathParserContext xmlXPathParserContext;
typedef xmlXPathParserContext *xmlXPathParserContextPtr;
/**
* The set of XPath error codes.
*/
typedef enum {
XPATH_EXPRESSION_OK = 0,
XPATH_NUMBER_ERROR,
XPATH_UNFINISHED_LITERAL_ERROR,
XPATH_START_LITERAL_ERROR,
XPATH_VARIABLE_REF_ERROR,
XPATH_UNDEF_VARIABLE_ERROR,
XPATH_INVALID_PREDICATE_ERROR,
XPATH_EXPR_ERROR,
XPATH_UNCLOSED_ERROR,
XPATH_UNKNOWN_FUNC_ERROR,
XPATH_INVALID_OPERAND,
XPATH_INVALID_TYPE,
XPATH_INVALID_ARITY,
XPATH_INVALID_CTXT_SIZE,
XPATH_INVALID_CTXT_POSITION,
XPATH_MEMORY_ERROR,
XPTR_SYNTAX_ERROR,
XPTR_RESOURCE_ERROR,
XPTR_SUB_RESOURCE_ERROR,
XPATH_UNDEF_PREFIX_ERROR,
XPATH_ENCODING_ERROR,
XPATH_INVALID_CHAR_ERROR,
XPATH_INVALID_CTXT,
XPATH_STACK_ERROR,
XPATH_FORBID_VARIABLE_ERROR
} xmlXPathError;
/*
* A node-set (an unordered collection of nodes without duplicates).
*/
typedef struct _xmlNodeSet xmlNodeSet;
typedef xmlNodeSet *xmlNodeSetPtr;
struct _xmlNodeSet {
int nodeNr; /* number of nodes in the set */
int nodeMax; /* size of the array as allocated */
xmlNodePtr *nodeTab; /* array of nodes in no particular order */
/* @@ with_ns to check wether namespace nodes should be looked at @@ */
};
/*
* An expression is evaluated to yield an object, which
* has one of the following four basic types:
* - node-set
* - boolean
* - number
* - string
*
* @@ XPointer will add more types !
*/
typedef enum {
XPATH_UNDEFINED = 0,
XPATH_NODESET = 1,
XPATH_BOOLEAN = 2,
XPATH_NUMBER = 3,
XPATH_STRING = 4,
XPATH_POINT = 5,
XPATH_RANGE = 6,
XPATH_LOCATIONSET = 7,
XPATH_USERS = 8,
XPATH_XSLT_TREE = 9 /* An XSLT value tree, non modifiable */
} xmlXPathObjectType;
typedef struct _xmlXPathObject xmlXPathObject;
typedef xmlXPathObject *xmlXPathObjectPtr;
struct _xmlXPathObject {
xmlXPathObjectType type;
xmlNodeSetPtr nodesetval;
int boolval;
double floatval;
xmlChar *stringval;
void *user;
int index;
void *user2;
int index2;
};
/**
* xmlXPathConvertFunc:
* @obj: an XPath object
* @type: the number of the target type
*
* A conversion function is associated to a type and used to cast
* the new type to primitive values.
*
* Returns -1 in case of error, 0 otherwise
*/
typedef int (*xmlXPathConvertFunc) (xmlXPathObjectPtr obj, int type);
/*
* Extra type: a name and a conversion function.
*/
typedef struct _xmlXPathType xmlXPathType;
typedef xmlXPathType *xmlXPathTypePtr;
struct _xmlXPathType {
const xmlChar *name; /* the type name */
xmlXPathConvertFunc func; /* the conversion function */
};
/*
* Extra variable: a name and a value.
*/
typedef struct _xmlXPathVariable xmlXPathVariable;
typedef xmlXPathVariable *xmlXPathVariablePtr;
struct _xmlXPathVariable {
const xmlChar *name; /* the variable name */
xmlXPathObjectPtr value; /* the value */
};
/**
* xmlXPathEvalFunc:
* @ctxt: an XPath parser context
* @nargs: the number of arguments passed to the function
*
* An XPath evaluation function, the parameters are on the XPath context stack.
*/
typedef void (*xmlXPathEvalFunc)(xmlXPathParserContextPtr ctxt,
int nargs);
/*
* Extra function: a name and a evaluation function.
*/
typedef struct _xmlXPathFunct xmlXPathFunct;
typedef xmlXPathFunct *xmlXPathFuncPtr;
struct _xmlXPathFunct {
const xmlChar *name; /* the function name */
xmlXPathEvalFunc func; /* the evaluation function */
};
/**
* xmlXPathAxisFunc:
* @ctxt: the XPath interpreter context
* @cur: the previous node being explored on that axis
*
* An axis traversal function. To traverse an axis, the engine calls
* the first time with cur == NULL and repeat until the function returns
* NULL indicating the end of the axis traversal.
*
* Returns the next node in that axis or NULL if at the end of the axis.
*/
typedef xmlXPathObjectPtr (*xmlXPathAxisFunc) (xmlXPathParserContextPtr ctxt,
xmlXPathObjectPtr cur);
/*
* Extra axis: a name and an axis function.
*/
typedef struct _xmlXPathAxis xmlXPathAxis;
typedef xmlXPathAxis *xmlXPathAxisPtr;
struct _xmlXPathAxis {
const xmlChar *name; /* the axis name */
xmlXPathAxisFunc func; /* the search function */
};
/**
* xmlXPathFunction:
* @ctxt: the XPath interprestation context
* @nargs: the number of arguments
*
* An XPath function.
* The arguments (if any) are popped out from the context stack
* and the result is pushed on the stack.
*/
typedef void (*xmlXPathFunction) (xmlXPathParserContextPtr ctxt, int nargs);
/*
* Function and Variable Lookup.
*/
/**
* xmlXPathVariableLookupFunc:
* @ctxt: an XPath context
* @name: name of the variable
* @ns_uri: the namespace name hosting this variable
*
* Prototype for callbacks used to plug variable lookup in the XPath
* engine.
*
* Returns the XPath object value or NULL if not found.
*/
typedef xmlXPathObjectPtr (*xmlXPathVariableLookupFunc) (void *ctxt,
const xmlChar *name,
const xmlChar *ns_uri);
/**
* xmlXPathFuncLookupFunc:
* @ctxt: an XPath context
* @name: name of the function
* @ns_uri: the namespace name hosting this function
*
* Prototype for callbacks used to plug function lookup in the XPath
* engine.
*
* Returns the XPath function or NULL if not found.
*/
typedef xmlXPathFunction (*xmlXPathFuncLookupFunc) (void *ctxt,
const xmlChar *name,
const xmlChar *ns_uri);
/**
* xmlXPathFlags:
* Flags for XPath engine compilation and runtime
*/
/**
* XML_XPATH_CHECKNS:
*
* check namespaces at compilation
*/
#define XML_XPATH_CHECKNS (1<<0)
/**
* XML_XPATH_NOVAR:
*
* forbid variables in expression
*/
#define XML_XPATH_NOVAR (1<<1)
/**
* xmlXPathContext:
*
* Expression evaluation occurs with respect to a context.
* he context consists of:
* - a node (the context node)
* - a node list (the context node list)
* - a set of variable bindings
* - a function library
* - the set of namespace declarations in scope for the expression
* Following the switch to hash tables, this need to be trimmed up at
* the next binary incompatible release.
* The node may be modified when the context is passed to libxml2
* for an XPath evaluation so you may need to initialize it again
* before the next call.
*/
struct _xmlXPathContext {
xmlDocPtr doc; /* The current document */
xmlNodePtr node; /* The current node */
int nb_variables_unused; /* unused (hash table) */
int max_variables_unused; /* unused (hash table) */
xmlHashTablePtr varHash; /* Hash table of defined variables */
int nb_types; /* number of defined types */
int max_types; /* max number of types */
xmlXPathTypePtr types; /* Array of defined types */
int nb_funcs_unused; /* unused (hash table) */
int max_funcs_unused; /* unused (hash table) */
xmlHashTablePtr funcHash; /* Hash table of defined funcs */
int nb_axis; /* number of defined axis */
int max_axis; /* max number of axis */
xmlXPathAxisPtr axis; /* Array of defined axis */
/* the namespace nodes of the context node */
xmlNsPtr *namespaces; /* Array of namespaces */
int nsNr; /* number of namespace in scope */
void *user; /* function to free */
/* extra variables */
int contextSize; /* the context size */
int proximityPosition; /* the proximity position */
/* extra stuff for XPointer */
int xptr; /* is this an XPointer context? */
xmlNodePtr here; /* for here() */
xmlNodePtr origin; /* for origin() */
/* the set of namespace declarations in scope for the expression */
xmlHashTablePtr nsHash; /* The namespaces hash table */
xmlXPathVariableLookupFunc varLookupFunc;/* variable lookup func */
void *varLookupData; /* variable lookup data */
/* Possibility to link in an extra item */
void *extra; /* needed for XSLT */
/* The function name and URI when calling a function */
const xmlChar *function;
const xmlChar *functionURI;
/* function lookup function and data */
xmlXPathFuncLookupFunc funcLookupFunc;/* function lookup func */
void *funcLookupData; /* function lookup data */
/* temporary namespace lists kept for walking the namespace axis */
xmlNsPtr *tmpNsList; /* Array of namespaces */
int tmpNsNr; /* number of namespaces in scope */
/* error reporting mechanism */
void *userData; /* user specific data block */
xmlStructuredErrorFunc error; /* the callback in case of errors */
xmlError lastError; /* the last error */
xmlNodePtr debugNode; /* the source node XSLT */
/* dictionary */
xmlDictPtr dict; /* dictionary if any */
int flags; /* flags to control compilation */
/* Cache for reusal of XPath objects */
void *cache;
};
/*
* The structure of a compiled expression form is not public.
*/
typedef struct _xmlXPathCompExpr xmlXPathCompExpr;
typedef xmlXPathCompExpr *xmlXPathCompExprPtr;
/**
* xmlXPathParserContext:
*
* An XPath parser context. It contains pure parsing informations,
* an xmlXPathContext, and the stack of objects.
*/
struct _xmlXPathParserContext {
const xmlChar *cur; /* the current char being parsed */
const xmlChar *base; /* the full expression */
int error; /* error code */
xmlXPathContextPtr context; /* the evaluation context */
xmlXPathObjectPtr value; /* the current value */
int valueNr; /* number of values stacked */
int valueMax; /* max number of values stacked */
xmlXPathObjectPtr *valueTab; /* stack of values */
xmlXPathCompExprPtr comp; /* the precompiled expression */
int xptr; /* it this an XPointer expression */
xmlNodePtr ancestor; /* used for walking preceding axis */
int valueFrame; /* used to limit Pop on the stack */
};
/************************************************************************
* *
* Public API *
* *
************************************************************************/
/**
* Objects and Nodesets handling
*/
XMLPUBVAR double xmlXPathNAN;
XMLPUBVAR double xmlXPathPINF;
XMLPUBVAR double xmlXPathNINF;
/* These macros may later turn into functions */
/**
* xmlXPathNodeSetGetLength:
* @ns: a node-set
*
* Implement a functionality similar to the DOM NodeList.length.
*
* Returns the number of nodes in the node-set.
*/
#define xmlXPathNodeSetGetLength(ns) ((ns) ? (ns)->nodeNr : 0)
/**
* xmlXPathNodeSetItem:
* @ns: a node-set
* @index: index of a node in the set
*
* Implements a functionality similar to the DOM NodeList.item().
*
* Returns the xmlNodePtr at the given @index in @ns or NULL if
* @index is out of range (0 to length-1)
*/
#define xmlXPathNodeSetItem(ns, index) \
((((ns) != NULL) && \
((index) >= 0) && ((index) < (ns)->nodeNr)) ? \
(ns)->nodeTab[(index)] \
: NULL)
/**
* xmlXPathNodeSetIsEmpty:
* @ns: a node-set
*
* Checks whether @ns is empty or not.
*
* Returns %TRUE if @ns is an empty node-set.
*/
#define xmlXPathNodeSetIsEmpty(ns) \
(((ns) == NULL) || ((ns)->nodeNr == 0) || ((ns)->nodeTab == NULL))
XMLPUBFUN void XMLCALL
xmlXPathFreeObject (xmlXPathObjectPtr obj);
XMLPUBFUN xmlNodeSetPtr XMLCALL
xmlXPathNodeSetCreate (xmlNodePtr val);
XMLPUBFUN void XMLCALL
xmlXPathFreeNodeSetList (xmlXPathObjectPtr obj);
XMLPUBFUN void XMLCALL
xmlXPathFreeNodeSet (xmlNodeSetPtr obj);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPathObjectCopy (xmlXPathObjectPtr val);
XMLPUBFUN int XMLCALL
xmlXPathCmpNodes (xmlNodePtr node1,
xmlNodePtr node2);
/**
* Conversion functions to basic types.
*/
XMLPUBFUN int XMLCALL
xmlXPathCastNumberToBoolean (double val);
XMLPUBFUN int XMLCALL
xmlXPathCastStringToBoolean (const xmlChar * val);
XMLPUBFUN int XMLCALL
xmlXPathCastNodeSetToBoolean(xmlNodeSetPtr ns);
XMLPUBFUN int XMLCALL
xmlXPathCastToBoolean (xmlXPathObjectPtr val);
XMLPUBFUN double XMLCALL
xmlXPathCastBooleanToNumber (int val);
XMLPUBFUN double XMLCALL
xmlXPathCastStringToNumber (const xmlChar * val);
XMLPUBFUN double XMLCALL
xmlXPathCastNodeToNumber (xmlNodePtr node);
XMLPUBFUN double XMLCALL
xmlXPathCastNodeSetToNumber (xmlNodeSetPtr ns);
XMLPUBFUN double XMLCALL
xmlXPathCastToNumber (xmlXPathObjectPtr val);
XMLPUBFUN xmlChar * XMLCALL
xmlXPathCastBooleanToString (int val);
XMLPUBFUN xmlChar * XMLCALL
xmlXPathCastNumberToString (double val);
XMLPUBFUN xmlChar * XMLCALL
xmlXPathCastNodeToString (xmlNodePtr node);
XMLPUBFUN xmlChar * XMLCALL
xmlXPathCastNodeSetToString (xmlNodeSetPtr ns);
XMLPUBFUN xmlChar * XMLCALL
xmlXPathCastToString (xmlXPathObjectPtr val);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPathConvertBoolean (xmlXPathObjectPtr val);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPathConvertNumber (xmlXPathObjectPtr val);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPathConvertString (xmlXPathObjectPtr val);
/**
* Context handling.
*/
XMLPUBFUN xmlXPathContextPtr XMLCALL
xmlXPathNewContext (xmlDocPtr doc);
XMLPUBFUN void XMLCALL
xmlXPathFreeContext (xmlXPathContextPtr ctxt);
XMLPUBFUN int XMLCALL
xmlXPathContextSetCache(xmlXPathContextPtr ctxt,
int active,
int value,
int options);
/**
* Evaluation functions.
*/
XMLPUBFUN long XMLCALL
xmlXPathOrderDocElems (xmlDocPtr doc);
XMLPUBFUN int XMLCALL
xmlXPathSetContextNode (xmlNodePtr node,
xmlXPathContextPtr ctx);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPathNodeEval (xmlNodePtr node,
const xmlChar *str,
xmlXPathContextPtr ctx);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPathEval (const xmlChar *str,
xmlXPathContextPtr ctx);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPathEvalExpression (const xmlChar *str,
xmlXPathContextPtr ctxt);
XMLPUBFUN int XMLCALL
xmlXPathEvalPredicate (xmlXPathContextPtr ctxt,
xmlXPathObjectPtr res);
/**
* Separate compilation/evaluation entry points.
*/
XMLPUBFUN xmlXPathCompExprPtr XMLCALL
xmlXPathCompile (const xmlChar *str);
XMLPUBFUN xmlXPathCompExprPtr XMLCALL
xmlXPathCtxtCompile (xmlXPathContextPtr ctxt,
const xmlChar *str);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPathCompiledEval (xmlXPathCompExprPtr comp,
xmlXPathContextPtr ctx);
XMLPUBFUN int XMLCALL
xmlXPathCompiledEvalToBoolean(xmlXPathCompExprPtr comp,
xmlXPathContextPtr ctxt);
XMLPUBFUN void XMLCALL
xmlXPathFreeCompExpr (xmlXPathCompExprPtr comp);
#endif /* LIBXML_XPATH_ENABLED */
#if defined(LIBXML_XPATH_ENABLED) || defined(LIBXML_SCHEMAS_ENABLED)
XMLPUBFUN void XMLCALL
xmlXPathInit (void);
XMLPUBFUN int XMLCALL
xmlXPathIsNaN (double val);
XMLPUBFUN int XMLCALL
xmlXPathIsInf (double val);
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_XPATH_ENABLED or LIBXML_SCHEMAS_ENABLED*/
#endif /* ! __XML_XPATH_H__ */

@ -0,0 +1,632 @@
/*
* Summary: internal interfaces for XML Path Language implementation
* Description: internal interfaces for XML Path Language implementation
* used to build new modules on top of XPath like XPointer and
* XSLT
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_XPATH_INTERNALS_H__
#define __XML_XPATH_INTERNALS_H__
#include <libxml/xmlversion.h>
#include <libxml/xpath.h>
#ifdef LIBXML_XPATH_ENABLED
#ifdef __cplusplus
extern "C" {
#endif
/************************************************************************
* *
* Helpers *
* *
************************************************************************/
/*
* Many of these macros may later turn into functions. They
* shouldn't be used in #ifdef's preprocessor instructions.
*/
/**
* xmlXPathSetError:
* @ctxt: an XPath parser context
* @err: an xmlXPathError code
*
* Raises an error.
*/
#define xmlXPathSetError(ctxt, err) \
{ xmlXPatherror((ctxt), __FILE__, __LINE__, (err)); \
if ((ctxt) != NULL) (ctxt)->error = (err); }
/**
* xmlXPathSetArityError:
* @ctxt: an XPath parser context
*
* Raises an XPATH_INVALID_ARITY error.
*/
#define xmlXPathSetArityError(ctxt) \
xmlXPathSetError((ctxt), XPATH_INVALID_ARITY)
/**
* xmlXPathSetTypeError:
* @ctxt: an XPath parser context
*
* Raises an XPATH_INVALID_TYPE error.
*/
#define xmlXPathSetTypeError(ctxt) \
xmlXPathSetError((ctxt), XPATH_INVALID_TYPE)
/**
* xmlXPathGetError:
* @ctxt: an XPath parser context
*
* Get the error code of an XPath context.
*
* Returns the context error.
*/
#define xmlXPathGetError(ctxt) ((ctxt)->error)
/**
* xmlXPathCheckError:
* @ctxt: an XPath parser context
*
* Check if an XPath error was raised.
*
* Returns true if an error has been raised, false otherwise.
*/
#define xmlXPathCheckError(ctxt) ((ctxt)->error != XPATH_EXPRESSION_OK)
/**
* xmlXPathGetDocument:
* @ctxt: an XPath parser context
*
* Get the document of an XPath context.
*
* Returns the context document.
*/
#define xmlXPathGetDocument(ctxt) ((ctxt)->context->doc)
/**
* xmlXPathGetContextNode:
* @ctxt: an XPath parser context
*
* Get the context node of an XPath context.
*
* Returns the context node.
*/
#define xmlXPathGetContextNode(ctxt) ((ctxt)->context->node)
XMLPUBFUN int XMLCALL
xmlXPathPopBoolean (xmlXPathParserContextPtr ctxt);
XMLPUBFUN double XMLCALL
xmlXPathPopNumber (xmlXPathParserContextPtr ctxt);
XMLPUBFUN xmlChar * XMLCALL
xmlXPathPopString (xmlXPathParserContextPtr ctxt);
XMLPUBFUN xmlNodeSetPtr XMLCALL
xmlXPathPopNodeSet (xmlXPathParserContextPtr ctxt);
XMLPUBFUN void * XMLCALL
xmlXPathPopExternal (xmlXPathParserContextPtr ctxt);
/**
* xmlXPathReturnBoolean:
* @ctxt: an XPath parser context
* @val: a boolean
*
* Pushes the boolean @val on the context stack.
*/
#define xmlXPathReturnBoolean(ctxt, val) \
valuePush((ctxt), xmlXPathNewBoolean(val))
/**
* xmlXPathReturnTrue:
* @ctxt: an XPath parser context
*
* Pushes true on the context stack.
*/
#define xmlXPathReturnTrue(ctxt) xmlXPathReturnBoolean((ctxt), 1)
/**
* xmlXPathReturnFalse:
* @ctxt: an XPath parser context
*
* Pushes false on the context stack.
*/
#define xmlXPathReturnFalse(ctxt) xmlXPathReturnBoolean((ctxt), 0)
/**
* xmlXPathReturnNumber:
* @ctxt: an XPath parser context
* @val: a double
*
* Pushes the double @val on the context stack.
*/
#define xmlXPathReturnNumber(ctxt, val) \
valuePush((ctxt), xmlXPathNewFloat(val))
/**
* xmlXPathReturnString:
* @ctxt: an XPath parser context
* @str: a string
*
* Pushes the string @str on the context stack.
*/
#define xmlXPathReturnString(ctxt, str) \
valuePush((ctxt), xmlXPathWrapString(str))
/**
* xmlXPathReturnEmptyString:
* @ctxt: an XPath parser context
*
* Pushes an empty string on the stack.
*/
#define xmlXPathReturnEmptyString(ctxt) \
valuePush((ctxt), xmlXPathNewCString(""))
/**
* xmlXPathReturnNodeSet:
* @ctxt: an XPath parser context
* @ns: a node-set
*
* Pushes the node-set @ns on the context stack.
*/
#define xmlXPathReturnNodeSet(ctxt, ns) \
valuePush((ctxt), xmlXPathWrapNodeSet(ns))
/**
* xmlXPathReturnEmptyNodeSet:
* @ctxt: an XPath parser context
*
* Pushes an empty node-set on the context stack.
*/
#define xmlXPathReturnEmptyNodeSet(ctxt) \
valuePush((ctxt), xmlXPathNewNodeSet(NULL))
/**
* xmlXPathReturnExternal:
* @ctxt: an XPath parser context
* @val: user data
*
* Pushes user data on the context stack.
*/
#define xmlXPathReturnExternal(ctxt, val) \
valuePush((ctxt), xmlXPathWrapExternal(val))
/**
* xmlXPathStackIsNodeSet:
* @ctxt: an XPath parser context
*
* Check if the current value on the XPath stack is a node set or
* an XSLT value tree.
*
* Returns true if the current object on the stack is a node-set.
*/
#define xmlXPathStackIsNodeSet(ctxt) \
(((ctxt)->value != NULL) \
&& (((ctxt)->value->type == XPATH_NODESET) \
|| ((ctxt)->value->type == XPATH_XSLT_TREE)))
/**
* xmlXPathStackIsExternal:
* @ctxt: an XPath parser context
*
* Checks if the current value on the XPath stack is an external
* object.
*
* Returns true if the current object on the stack is an external
* object.
*/
#define xmlXPathStackIsExternal(ctxt) \
((ctxt->value != NULL) && (ctxt->value->type == XPATH_USERS))
/**
* xmlXPathEmptyNodeSet:
* @ns: a node-set
*
* Empties a node-set.
*/
#define xmlXPathEmptyNodeSet(ns) \
{ while ((ns)->nodeNr > 0) (ns)->nodeTab[--(ns)->nodeNr] = NULL; }
/**
* CHECK_ERROR:
*
* Macro to return from the function if an XPath error was detected.
*/
#define CHECK_ERROR \
if (ctxt->error != XPATH_EXPRESSION_OK) return
/**
* CHECK_ERROR0:
*
* Macro to return 0 from the function if an XPath error was detected.
*/
#define CHECK_ERROR0 \
if (ctxt->error != XPATH_EXPRESSION_OK) return(0)
/**
* XP_ERROR:
* @X: the error code
*
* Macro to raise an XPath error and return.
*/
#define XP_ERROR(X) \
{ xmlXPathErr(ctxt, X); return; }
/**
* XP_ERROR0:
* @X: the error code
*
* Macro to raise an XPath error and return 0.
*/
#define XP_ERROR0(X) \
{ xmlXPathErr(ctxt, X); return(0); }
/**
* CHECK_TYPE:
* @typeval: the XPath type
*
* Macro to check that the value on top of the XPath stack is of a given
* type.
*/
#define CHECK_TYPE(typeval) \
if ((ctxt->value == NULL) || (ctxt->value->type != typeval)) \
XP_ERROR(XPATH_INVALID_TYPE)
/**
* CHECK_TYPE0:
* @typeval: the XPath type
*
* Macro to check that the value on top of the XPath stack is of a given
* type. Return(0) in case of failure
*/
#define CHECK_TYPE0(typeval) \
if ((ctxt->value == NULL) || (ctxt->value->type != typeval)) \
XP_ERROR0(XPATH_INVALID_TYPE)
/**
* CHECK_ARITY:
* @x: the number of expected args
*
* Macro to check that the number of args passed to an XPath function matches.
*/
#define CHECK_ARITY(x) \
if (ctxt == NULL) return; \
if (nargs != (x)) \
XP_ERROR(XPATH_INVALID_ARITY); \
if (ctxt->valueNr < ctxt->valueFrame + (x)) \
XP_ERROR(XPATH_STACK_ERROR);
/**
* CAST_TO_STRING:
*
* Macro to try to cast the value on the top of the XPath stack to a string.
*/
#define CAST_TO_STRING \
if ((ctxt->value != NULL) && (ctxt->value->type != XPATH_STRING)) \
xmlXPathStringFunction(ctxt, 1);
/**
* CAST_TO_NUMBER:
*
* Macro to try to cast the value on the top of the XPath stack to a number.
*/
#define CAST_TO_NUMBER \
if ((ctxt->value != NULL) && (ctxt->value->type != XPATH_NUMBER)) \
xmlXPathNumberFunction(ctxt, 1);
/**
* CAST_TO_BOOLEAN:
*
* Macro to try to cast the value on the top of the XPath stack to a boolean.
*/
#define CAST_TO_BOOLEAN \
if ((ctxt->value != NULL) && (ctxt->value->type != XPATH_BOOLEAN)) \
xmlXPathBooleanFunction(ctxt, 1);
/*
* Variable Lookup forwarding.
*/
XMLPUBFUN void XMLCALL
xmlXPathRegisterVariableLookup (xmlXPathContextPtr ctxt,
xmlXPathVariableLookupFunc f,
void *data);
/*
* Function Lookup forwarding.
*/
XMLPUBFUN void XMLCALL
xmlXPathRegisterFuncLookup (xmlXPathContextPtr ctxt,
xmlXPathFuncLookupFunc f,
void *funcCtxt);
/*
* Error reporting.
*/
XMLPUBFUN void XMLCALL
xmlXPatherror (xmlXPathParserContextPtr ctxt,
const char *file,
int line,
int no);
XMLPUBFUN void XMLCALL
xmlXPathErr (xmlXPathParserContextPtr ctxt,
int error);
#ifdef LIBXML_DEBUG_ENABLED
XMLPUBFUN void XMLCALL
xmlXPathDebugDumpObject (FILE *output,
xmlXPathObjectPtr cur,
int depth);
XMLPUBFUN void XMLCALL
xmlXPathDebugDumpCompExpr(FILE *output,
xmlXPathCompExprPtr comp,
int depth);
#endif
/**
* NodeSet handling.
*/
XMLPUBFUN int XMLCALL
xmlXPathNodeSetContains (xmlNodeSetPtr cur,
xmlNodePtr val);
XMLPUBFUN xmlNodeSetPtr XMLCALL
xmlXPathDifference (xmlNodeSetPtr nodes1,
xmlNodeSetPtr nodes2);
XMLPUBFUN xmlNodeSetPtr XMLCALL
xmlXPathIntersection (xmlNodeSetPtr nodes1,
xmlNodeSetPtr nodes2);
XMLPUBFUN xmlNodeSetPtr XMLCALL
xmlXPathDistinctSorted (xmlNodeSetPtr nodes);
XMLPUBFUN xmlNodeSetPtr XMLCALL
xmlXPathDistinct (xmlNodeSetPtr nodes);
XMLPUBFUN int XMLCALL
xmlXPathHasSameNodes (xmlNodeSetPtr nodes1,
xmlNodeSetPtr nodes2);
XMLPUBFUN xmlNodeSetPtr XMLCALL
xmlXPathNodeLeadingSorted (xmlNodeSetPtr nodes,
xmlNodePtr node);
XMLPUBFUN xmlNodeSetPtr XMLCALL
xmlXPathLeadingSorted (xmlNodeSetPtr nodes1,
xmlNodeSetPtr nodes2);
XMLPUBFUN xmlNodeSetPtr XMLCALL
xmlXPathNodeLeading (xmlNodeSetPtr nodes,
xmlNodePtr node);
XMLPUBFUN xmlNodeSetPtr XMLCALL
xmlXPathLeading (xmlNodeSetPtr nodes1,
xmlNodeSetPtr nodes2);
XMLPUBFUN xmlNodeSetPtr XMLCALL
xmlXPathNodeTrailingSorted (xmlNodeSetPtr nodes,
xmlNodePtr node);
XMLPUBFUN xmlNodeSetPtr XMLCALL
xmlXPathTrailingSorted (xmlNodeSetPtr nodes1,
xmlNodeSetPtr nodes2);
XMLPUBFUN xmlNodeSetPtr XMLCALL
xmlXPathNodeTrailing (xmlNodeSetPtr nodes,
xmlNodePtr node);
XMLPUBFUN xmlNodeSetPtr XMLCALL
xmlXPathTrailing (xmlNodeSetPtr nodes1,
xmlNodeSetPtr nodes2);
/**
* Extending a context.
*/
XMLPUBFUN int XMLCALL
xmlXPathRegisterNs (xmlXPathContextPtr ctxt,
const xmlChar *prefix,
const xmlChar *ns_uri);
XMLPUBFUN const xmlChar * XMLCALL
xmlXPathNsLookup (xmlXPathContextPtr ctxt,
const xmlChar *prefix);
XMLPUBFUN void XMLCALL
xmlXPathRegisteredNsCleanup (xmlXPathContextPtr ctxt);
XMLPUBFUN int XMLCALL
xmlXPathRegisterFunc (xmlXPathContextPtr ctxt,
const xmlChar *name,
xmlXPathFunction f);
XMLPUBFUN int XMLCALL
xmlXPathRegisterFuncNS (xmlXPathContextPtr ctxt,
const xmlChar *name,
const xmlChar *ns_uri,
xmlXPathFunction f);
XMLPUBFUN int XMLCALL
xmlXPathRegisterVariable (xmlXPathContextPtr ctxt,
const xmlChar *name,
xmlXPathObjectPtr value);
XMLPUBFUN int XMLCALL
xmlXPathRegisterVariableNS (xmlXPathContextPtr ctxt,
const xmlChar *name,
const xmlChar *ns_uri,
xmlXPathObjectPtr value);
XMLPUBFUN xmlXPathFunction XMLCALL
xmlXPathFunctionLookup (xmlXPathContextPtr ctxt,
const xmlChar *name);
XMLPUBFUN xmlXPathFunction XMLCALL
xmlXPathFunctionLookupNS (xmlXPathContextPtr ctxt,
const xmlChar *name,
const xmlChar *ns_uri);
XMLPUBFUN void XMLCALL
xmlXPathRegisteredFuncsCleanup (xmlXPathContextPtr ctxt);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPathVariableLookup (xmlXPathContextPtr ctxt,
const xmlChar *name);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPathVariableLookupNS (xmlXPathContextPtr ctxt,
const xmlChar *name,
const xmlChar *ns_uri);
XMLPUBFUN void XMLCALL
xmlXPathRegisteredVariablesCleanup(xmlXPathContextPtr ctxt);
/**
* Utilities to extend XPath.
*/
XMLPUBFUN xmlXPathParserContextPtr XMLCALL
xmlXPathNewParserContext (const xmlChar *str,
xmlXPathContextPtr ctxt);
XMLPUBFUN void XMLCALL
xmlXPathFreeParserContext (xmlXPathParserContextPtr ctxt);
/* TODO: remap to xmlXPathValuePop and Push. */
XMLPUBFUN xmlXPathObjectPtr XMLCALL
valuePop (xmlXPathParserContextPtr ctxt);
XMLPUBFUN int XMLCALL
valuePush (xmlXPathParserContextPtr ctxt,
xmlXPathObjectPtr value);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPathNewString (const xmlChar *val);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPathNewCString (const char *val);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPathWrapString (xmlChar *val);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPathWrapCString (char * val);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPathNewFloat (double val);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPathNewBoolean (int val);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPathNewNodeSet (xmlNodePtr val);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPathNewValueTree (xmlNodePtr val);
XMLPUBFUN int XMLCALL
xmlXPathNodeSetAdd (xmlNodeSetPtr cur,
xmlNodePtr val);
XMLPUBFUN int XMLCALL
xmlXPathNodeSetAddUnique (xmlNodeSetPtr cur,
xmlNodePtr val);
XMLPUBFUN int XMLCALL
xmlXPathNodeSetAddNs (xmlNodeSetPtr cur,
xmlNodePtr node,
xmlNsPtr ns);
XMLPUBFUN void XMLCALL
xmlXPathNodeSetSort (xmlNodeSetPtr set);
XMLPUBFUN void XMLCALL
xmlXPathRoot (xmlXPathParserContextPtr ctxt);
XMLPUBFUN void XMLCALL
xmlXPathEvalExpr (xmlXPathParserContextPtr ctxt);
XMLPUBFUN xmlChar * XMLCALL
xmlXPathParseName (xmlXPathParserContextPtr ctxt);
XMLPUBFUN xmlChar * XMLCALL
xmlXPathParseNCName (xmlXPathParserContextPtr ctxt);
/*
* Existing functions.
*/
XMLPUBFUN double XMLCALL
xmlXPathStringEvalNumber (const xmlChar *str);
XMLPUBFUN int XMLCALL
xmlXPathEvaluatePredicateResult (xmlXPathParserContextPtr ctxt,
xmlXPathObjectPtr res);
XMLPUBFUN void XMLCALL
xmlXPathRegisterAllFunctions (xmlXPathContextPtr ctxt);
XMLPUBFUN xmlNodeSetPtr XMLCALL
xmlXPathNodeSetMerge (xmlNodeSetPtr val1,
xmlNodeSetPtr val2);
XMLPUBFUN void XMLCALL
xmlXPathNodeSetDel (xmlNodeSetPtr cur,
xmlNodePtr val);
XMLPUBFUN void XMLCALL
xmlXPathNodeSetRemove (xmlNodeSetPtr cur,
int val);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPathNewNodeSetList (xmlNodeSetPtr val);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPathWrapNodeSet (xmlNodeSetPtr val);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPathWrapExternal (void *val);
XMLPUBFUN int XMLCALL xmlXPathEqualValues(xmlXPathParserContextPtr ctxt);
XMLPUBFUN int XMLCALL xmlXPathNotEqualValues(xmlXPathParserContextPtr ctxt);
XMLPUBFUN int XMLCALL xmlXPathCompareValues(xmlXPathParserContextPtr ctxt, int inf, int strict);
XMLPUBFUN void XMLCALL xmlXPathValueFlipSign(xmlXPathParserContextPtr ctxt);
XMLPUBFUN void XMLCALL xmlXPathAddValues(xmlXPathParserContextPtr ctxt);
XMLPUBFUN void XMLCALL xmlXPathSubValues(xmlXPathParserContextPtr ctxt);
XMLPUBFUN void XMLCALL xmlXPathMultValues(xmlXPathParserContextPtr ctxt);
XMLPUBFUN void XMLCALL xmlXPathDivValues(xmlXPathParserContextPtr ctxt);
XMLPUBFUN void XMLCALL xmlXPathModValues(xmlXPathParserContextPtr ctxt);
XMLPUBFUN int XMLCALL xmlXPathIsNodeType(const xmlChar *name);
/*
* Some of the axis navigation routines.
*/
XMLPUBFUN xmlNodePtr XMLCALL xmlXPathNextSelf(xmlXPathParserContextPtr ctxt,
xmlNodePtr cur);
XMLPUBFUN xmlNodePtr XMLCALL xmlXPathNextChild(xmlXPathParserContextPtr ctxt,
xmlNodePtr cur);
XMLPUBFUN xmlNodePtr XMLCALL xmlXPathNextDescendant(xmlXPathParserContextPtr ctxt,
xmlNodePtr cur);
XMLPUBFUN xmlNodePtr XMLCALL xmlXPathNextDescendantOrSelf(xmlXPathParserContextPtr ctxt,
xmlNodePtr cur);
XMLPUBFUN xmlNodePtr XMLCALL xmlXPathNextParent(xmlXPathParserContextPtr ctxt,
xmlNodePtr cur);
XMLPUBFUN xmlNodePtr XMLCALL xmlXPathNextAncestorOrSelf(xmlXPathParserContextPtr ctxt,
xmlNodePtr cur);
XMLPUBFUN xmlNodePtr XMLCALL xmlXPathNextFollowingSibling(xmlXPathParserContextPtr ctxt,
xmlNodePtr cur);
XMLPUBFUN xmlNodePtr XMLCALL xmlXPathNextFollowing(xmlXPathParserContextPtr ctxt,
xmlNodePtr cur);
XMLPUBFUN xmlNodePtr XMLCALL xmlXPathNextNamespace(xmlXPathParserContextPtr ctxt,
xmlNodePtr cur);
XMLPUBFUN xmlNodePtr XMLCALL xmlXPathNextAttribute(xmlXPathParserContextPtr ctxt,
xmlNodePtr cur);
XMLPUBFUN xmlNodePtr XMLCALL xmlXPathNextPreceding(xmlXPathParserContextPtr ctxt,
xmlNodePtr cur);
XMLPUBFUN xmlNodePtr XMLCALL xmlXPathNextAncestor(xmlXPathParserContextPtr ctxt,
xmlNodePtr cur);
XMLPUBFUN xmlNodePtr XMLCALL xmlXPathNextPrecedingSibling(xmlXPathParserContextPtr ctxt,
xmlNodePtr cur);
/*
* The official core of XPath functions.
*/
XMLPUBFUN void XMLCALL xmlXPathLastFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathPositionFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathCountFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathIdFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathLocalNameFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathNamespaceURIFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathStringFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathStringLengthFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathConcatFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathContainsFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathStartsWithFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathSubstringFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathSubstringBeforeFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathSubstringAfterFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathNormalizeFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathTranslateFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathNotFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathTrueFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathFalseFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathLangFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathNumberFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathSumFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathFloorFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathCeilingFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathRoundFunction(xmlXPathParserContextPtr ctxt, int nargs);
XMLPUBFUN void XMLCALL xmlXPathBooleanFunction(xmlXPathParserContextPtr ctxt, int nargs);
/**
* Really internal functions
*/
XMLPUBFUN void XMLCALL xmlXPathNodeSetFreeNs(xmlNsPtr ns);
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_XPATH_ENABLED */
#endif /* ! __XML_XPATH_INTERNALS_H__ */

@ -0,0 +1,114 @@
/*
* Summary: API to handle XML Pointers
* Description: API to handle XML Pointers
* Base implementation was made accordingly to
* W3C Candidate Recommendation 7 June 2000
* http://www.w3.org/TR/2000/CR-xptr-20000607
*
* Added support for the element() scheme described in:
* W3C Proposed Recommendation 13 November 2002
* http://www.w3.org/TR/2002/PR-xptr-element-20021113/
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_XPTR_H__
#define __XML_XPTR_H__
#include <libxml/xmlversion.h>
#ifdef LIBXML_XPTR_ENABLED
#include <libxml/tree.h>
#include <libxml/xpath.h>
#ifdef __cplusplus
extern "C" {
#endif
/*
* A Location Set
*/
typedef struct _xmlLocationSet xmlLocationSet;
typedef xmlLocationSet *xmlLocationSetPtr;
struct _xmlLocationSet {
int locNr; /* number of locations in the set */
int locMax; /* size of the array as allocated */
xmlXPathObjectPtr *locTab;/* array of locations */
};
/*
* Handling of location sets.
*/
XMLPUBFUN xmlLocationSetPtr XMLCALL
xmlXPtrLocationSetCreate (xmlXPathObjectPtr val);
XMLPUBFUN void XMLCALL
xmlXPtrFreeLocationSet (xmlLocationSetPtr obj);
XMLPUBFUN xmlLocationSetPtr XMLCALL
xmlXPtrLocationSetMerge (xmlLocationSetPtr val1,
xmlLocationSetPtr val2);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPtrNewRange (xmlNodePtr start,
int startindex,
xmlNodePtr end,
int endindex);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPtrNewRangePoints (xmlXPathObjectPtr start,
xmlXPathObjectPtr end);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPtrNewRangeNodePoint (xmlNodePtr start,
xmlXPathObjectPtr end);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPtrNewRangePointNode (xmlXPathObjectPtr start,
xmlNodePtr end);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPtrNewRangeNodes (xmlNodePtr start,
xmlNodePtr end);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPtrNewLocationSetNodes (xmlNodePtr start,
xmlNodePtr end);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPtrNewLocationSetNodeSet(xmlNodeSetPtr set);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPtrNewRangeNodeObject (xmlNodePtr start,
xmlXPathObjectPtr end);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPtrNewCollapsedRange (xmlNodePtr start);
XMLPUBFUN void XMLCALL
xmlXPtrLocationSetAdd (xmlLocationSetPtr cur,
xmlXPathObjectPtr val);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPtrWrapLocationSet (xmlLocationSetPtr val);
XMLPUBFUN void XMLCALL
xmlXPtrLocationSetDel (xmlLocationSetPtr cur,
xmlXPathObjectPtr val);
XMLPUBFUN void XMLCALL
xmlXPtrLocationSetRemove (xmlLocationSetPtr cur,
int val);
/*
* Functions.
*/
XMLPUBFUN xmlXPathContextPtr XMLCALL
xmlXPtrNewContext (xmlDocPtr doc,
xmlNodePtr here,
xmlNodePtr origin);
XMLPUBFUN xmlXPathObjectPtr XMLCALL
xmlXPtrEval (const xmlChar *str,
xmlXPathContextPtr ctx);
XMLPUBFUN void XMLCALL
xmlXPtrRangeToFunction (xmlXPathParserContextPtr ctxt,
int nargs);
XMLPUBFUN xmlNodePtr XMLCALL
xmlXPtrBuildNodeList (xmlXPathObjectPtr obj);
XMLPUBFUN void XMLCALL
xmlXPtrEvalRangePredicate (xmlXPathParserContextPtr ctxt);
#ifdef __cplusplus
}
#endif
#endif /* LIBXML_XPTR_ENABLED */
#endif /* __XML_XPTR_H__ */

@ -0,0 +1,38 @@
/*
* Summary: interface for the XSLT attribute handling
* Description: this module handles the specificities of attribute
* and attribute groups processing.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_XSLT_ATTRIBUTES_H__
#define __XML_XSLT_ATTRIBUTES_H__
#include <libxml/tree.h>
#include "xsltexports.h"
#ifdef __cplusplus
extern "C" {
#endif
XSLTPUBFUN void XSLTCALL
xsltParseStylesheetAttributeSet (xsltStylesheetPtr style,
xmlNodePtr cur);
XSLTPUBFUN void XSLTCALL
xsltFreeAttributeSetsHashes (xsltStylesheetPtr style);
XSLTPUBFUN void XSLTCALL
xsltApplyAttributeSet (xsltTransformContextPtr ctxt,
xmlNodePtr node,
xmlNodePtr inst,
const xmlChar *attributes);
XSLTPUBFUN void XSLTCALL
xsltResolveStylesheetAttributeSet(xsltStylesheetPtr style);
#ifdef __cplusplus
}
#endif
#endif /* __XML_XSLT_ATTRIBUTES_H__ */

@ -0,0 +1,93 @@
/*
* Summary: interface for the document handling
* Description: implements document loading and cache (multiple
* document() reference for the same resources must
* be equal.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_XSLT_DOCUMENTS_H__
#define __XML_XSLT_DOCUMENTS_H__
#include <libxml/tree.h>
#include "xsltexports.h"
#include "xsltInternals.h"
#ifdef __cplusplus
extern "C" {
#endif
XSLTPUBFUN xsltDocumentPtr XSLTCALL
xsltNewDocument (xsltTransformContextPtr ctxt,
xmlDocPtr doc);
XSLTPUBFUN xsltDocumentPtr XSLTCALL
xsltLoadDocument (xsltTransformContextPtr ctxt,
const xmlChar *URI);
XSLTPUBFUN xsltDocumentPtr XSLTCALL
xsltFindDocument (xsltTransformContextPtr ctxt,
xmlDocPtr doc);
XSLTPUBFUN void XSLTCALL
xsltFreeDocuments (xsltTransformContextPtr ctxt);
XSLTPUBFUN xsltDocumentPtr XSLTCALL
xsltLoadStyleDocument (xsltStylesheetPtr style,
const xmlChar *URI);
XSLTPUBFUN xsltDocumentPtr XSLTCALL
xsltNewStyleDocument (xsltStylesheetPtr style,
xmlDocPtr doc);
XSLTPUBFUN void XSLTCALL
xsltFreeStyleDocuments (xsltStylesheetPtr style);
/*
* Hooks for document loading
*/
/**
* xsltLoadType:
*
* Enum defining the kind of loader requirement.
*/
typedef enum {
XSLT_LOAD_START = 0, /* loading for a top stylesheet */
XSLT_LOAD_STYLESHEET = 1, /* loading for a stylesheet include/import */
XSLT_LOAD_DOCUMENT = 2 /* loading document at transformation time */
} xsltLoadType;
/**
* xsltDocLoaderFunc:
* @URI: the URI of the document to load
* @dict: the dictionary to use when parsing that document
* @options: parsing options, a set of xmlParserOption
* @ctxt: the context, either a stylesheet or a transformation context
* @type: the xsltLoadType indicating the kind of loading required
*
* An xsltDocLoaderFunc is a signature for a function which can be
* registered to load document not provided by the compilation or
* transformation API themselve, for example when an xsl:import,
* xsl:include is found at compilation time or when a document()
* call is made at runtime.
*
* Returns the pointer to the document (which will be modified and
* freed by the engine later), or NULL in case of error.
*/
typedef xmlDocPtr (*xsltDocLoaderFunc) (const xmlChar *URI,
xmlDictPtr dict,
int options,
void *ctxt,
xsltLoadType type);
XSLTPUBFUN void XSLTCALL
xsltSetLoaderFunc (xsltDocLoaderFunc f);
/* the loader may be needed by extension libraries so it is exported */
XSLTPUBVAR xsltDocLoaderFunc xsltDocDefaultLoader;
#ifdef __cplusplus
}
#endif
#endif /* __XML_XSLT_DOCUMENTS_H__ */

@ -0,0 +1,262 @@
/*
* Summary: interface for the extension support
* Description: This provide the API needed for simple and module
* extension support.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_XSLT_EXTENSION_H__
#define __XML_XSLT_EXTENSION_H__
#include <libxml/xpath.h>
#include "xsltexports.h"
#include "xsltInternals.h"
#ifdef __cplusplus
extern "C" {
#endif
/**
* Extension Modules API.
*/
/**
* xsltInitGlobals:
*
* Initialize the global variables for extensions
*
*/
XSLTPUBFUN void XSLTCALL
xsltInitGlobals (void);
/**
* xsltStyleExtInitFunction:
* @ctxt: an XSLT stylesheet
* @URI: the namespace URI for the extension
*
* A function called at initialization time of an XSLT extension module.
*
* Returns a pointer to the module specific data for this transformation.
*/
typedef void * (*xsltStyleExtInitFunction) (xsltStylesheetPtr style,
const xmlChar *URI);
/**
* xsltStyleExtShutdownFunction:
* @ctxt: an XSLT stylesheet
* @URI: the namespace URI for the extension
* @data: the data associated to this module
*
* A function called at shutdown time of an XSLT extension module.
*/
typedef void (*xsltStyleExtShutdownFunction) (xsltStylesheetPtr style,
const xmlChar *URI,
void *data);
/**
* xsltExtInitFunction:
* @ctxt: an XSLT transformation context
* @URI: the namespace URI for the extension
*
* A function called at initialization time of an XSLT extension module.
*
* Returns a pointer to the module specific data for this transformation.
*/
typedef void * (*xsltExtInitFunction) (xsltTransformContextPtr ctxt,
const xmlChar *URI);
/**
* xsltExtShutdownFunction:
* @ctxt: an XSLT transformation context
* @URI: the namespace URI for the extension
* @data: the data associated to this module
*
* A function called at shutdown time of an XSLT extension module.
*/
typedef void (*xsltExtShutdownFunction) (xsltTransformContextPtr ctxt,
const xmlChar *URI,
void *data);
XSLTPUBFUN int XSLTCALL
xsltRegisterExtModule (const xmlChar *URI,
xsltExtInitFunction initFunc,
xsltExtShutdownFunction shutdownFunc);
XSLTPUBFUN int XSLTCALL
xsltRegisterExtModuleFull
(const xmlChar * URI,
xsltExtInitFunction initFunc,
xsltExtShutdownFunction shutdownFunc,
xsltStyleExtInitFunction styleInitFunc,
xsltStyleExtShutdownFunction styleShutdownFunc);
XSLTPUBFUN int XSLTCALL
xsltUnregisterExtModule (const xmlChar * URI);
XSLTPUBFUN void * XSLTCALL
xsltGetExtData (xsltTransformContextPtr ctxt,
const xmlChar *URI);
XSLTPUBFUN void * XSLTCALL
xsltStyleGetExtData (xsltStylesheetPtr style,
const xmlChar *URI);
#ifdef XSLT_REFACTORED
XSLTPUBFUN void * XSLTCALL
xsltStyleStylesheetLevelGetExtData(
xsltStylesheetPtr style,
const xmlChar * URI);
#endif
XSLTPUBFUN void XSLTCALL
xsltShutdownCtxtExts (xsltTransformContextPtr ctxt);
XSLTPUBFUN void XSLTCALL
xsltShutdownExts (xsltStylesheetPtr style);
XSLTPUBFUN xsltTransformContextPtr XSLTCALL
xsltXPathGetTransformContext
(xmlXPathParserContextPtr ctxt);
/*
* extension functions
*/
XSLTPUBFUN int XSLTCALL
xsltRegisterExtModuleFunction
(const xmlChar *name,
const xmlChar *URI,
xmlXPathFunction function);
XSLTPUBFUN xmlXPathFunction XSLTCALL
xsltExtModuleFunctionLookup (const xmlChar *name,
const xmlChar *URI);
XSLTPUBFUN int XSLTCALL
xsltUnregisterExtModuleFunction
(const xmlChar *name,
const xmlChar *URI);
/*
* extension elements
*/
typedef xsltElemPreCompPtr (*xsltPreComputeFunction)
(xsltStylesheetPtr style,
xmlNodePtr inst,
xsltTransformFunction function);
XSLTPUBFUN xsltElemPreCompPtr XSLTCALL
xsltNewElemPreComp (xsltStylesheetPtr style,
xmlNodePtr inst,
xsltTransformFunction function);
XSLTPUBFUN void XSLTCALL
xsltInitElemPreComp (xsltElemPreCompPtr comp,
xsltStylesheetPtr style,
xmlNodePtr inst,
xsltTransformFunction function,
xsltElemPreCompDeallocator freeFunc);
XSLTPUBFUN int XSLTCALL
xsltRegisterExtModuleElement
(const xmlChar *name,
const xmlChar *URI,
xsltPreComputeFunction precomp,
xsltTransformFunction transform);
XSLTPUBFUN xsltTransformFunction XSLTCALL
xsltExtElementLookup (xsltTransformContextPtr ctxt,
const xmlChar *name,
const xmlChar *URI);
XSLTPUBFUN xsltTransformFunction XSLTCALL
xsltExtModuleElementLookup
(const xmlChar *name,
const xmlChar *URI);
XSLTPUBFUN xsltPreComputeFunction XSLTCALL
xsltExtModuleElementPreComputeLookup
(const xmlChar *name,
const xmlChar *URI);
XSLTPUBFUN int XSLTCALL
xsltUnregisterExtModuleElement
(const xmlChar *name,
const xmlChar *URI);
/*
* top-level elements
*/
typedef void (*xsltTopLevelFunction) (xsltStylesheetPtr style,
xmlNodePtr inst);
XSLTPUBFUN int XSLTCALL
xsltRegisterExtModuleTopLevel
(const xmlChar *name,
const xmlChar *URI,
xsltTopLevelFunction function);
XSLTPUBFUN xsltTopLevelFunction XSLTCALL
xsltExtModuleTopLevelLookup
(const xmlChar *name,
const xmlChar *URI);
XSLTPUBFUN int XSLTCALL
xsltUnregisterExtModuleTopLevel
(const xmlChar *name,
const xmlChar *URI);
/* These 2 functions are deprecated for use within modules. */
XSLTPUBFUN int XSLTCALL
xsltRegisterExtFunction (xsltTransformContextPtr ctxt,
const xmlChar *name,
const xmlChar *URI,
xmlXPathFunction function);
XSLTPUBFUN int XSLTCALL
xsltRegisterExtElement (xsltTransformContextPtr ctxt,
const xmlChar *name,
const xmlChar *URI,
xsltTransformFunction function);
/*
* Extension Prefix handling API.
* Those are used by the XSLT (pre)processor.
*/
XSLTPUBFUN int XSLTCALL
xsltRegisterExtPrefix (xsltStylesheetPtr style,
const xmlChar *prefix,
const xmlChar *URI);
XSLTPUBFUN int XSLTCALL
xsltCheckExtPrefix (xsltStylesheetPtr style,
const xmlChar *URI);
XSLTPUBFUN int XSLTCALL
xsltCheckExtURI (xsltStylesheetPtr style,
const xmlChar *URI);
XSLTPUBFUN int XSLTCALL
xsltInitCtxtExts (xsltTransformContextPtr ctxt);
XSLTPUBFUN void XSLTCALL
xsltFreeCtxtExts (xsltTransformContextPtr ctxt);
XSLTPUBFUN void XSLTCALL
xsltFreeExts (xsltStylesheetPtr style);
XSLTPUBFUN xsltElemPreCompPtr XSLTCALL
xsltPreComputeExtModuleElement
(xsltStylesheetPtr style,
xmlNodePtr inst);
/*
* Extension Infos access.
* Used by exslt initialisation
*/
XSLTPUBFUN xmlHashTablePtr XSLTCALL
xsltGetExtInfo (xsltStylesheetPtr style,
const xmlChar *URI);
/**
* Test module http://xmlsoft.org/XSLT/
*/
XSLTPUBFUN void XSLTCALL
xsltRegisterTestModule (void);
XSLTPUBFUN void XSLTCALL
xsltDebugDumpExtensions (FILE * output);
#ifdef __cplusplus
}
#endif
#endif /* __XML_XSLT_EXTENSION_H__ */

@ -0,0 +1,72 @@
/*
* Summary: interface for the non-standard features
* Description: implement some extension outside the XSLT namespace
* but not EXSLT with is in a different library.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_XSLT_EXTRA_H__
#define __XML_XSLT_EXTRA_H__
#include <libxml/xpath.h>
#include "xsltexports.h"
#include "xsltInternals.h"
#ifdef __cplusplus
extern "C" {
#endif
/**
* XSLT_LIBXSLT_NAMESPACE:
*
* This is the libxslt namespace for specific extensions.
*/
#define XSLT_LIBXSLT_NAMESPACE ((xmlChar *) "http://xmlsoft.org/XSLT/namespace")
/**
* XSLT_SAXON_NAMESPACE:
*
* This is Michael Kay's Saxon processor namespace for extensions.
*/
#define XSLT_SAXON_NAMESPACE ((xmlChar *) "http://icl.com/saxon")
/**
* XSLT_XT_NAMESPACE:
*
* This is James Clark's XT processor namespace for extensions.
*/
#define XSLT_XT_NAMESPACE ((xmlChar *) "http://www.jclark.com/xt")
/**
* XSLT_XALAN_NAMESPACE:
*
* This is the Apache project XALAN processor namespace for extensions.
*/
#define XSLT_XALAN_NAMESPACE ((xmlChar *) \
"org.apache.xalan.xslt.extensions.Redirect")
XSLTPUBFUN void XSLTCALL
xsltFunctionNodeSet (xmlXPathParserContextPtr ctxt,
int nargs);
XSLTPUBFUN void XSLTCALL
xsltDebug (xsltTransformContextPtr ctxt,
xmlNodePtr node,
xmlNodePtr inst,
xsltStylePreCompPtr comp);
XSLTPUBFUN void XSLTCALL
xsltRegisterExtras (xsltTransformContextPtr ctxt);
XSLTPUBFUN void XSLTCALL
xsltRegisterAllExtras (void);
#ifdef __cplusplus
}
#endif
#endif /* __XML_XSLT_EXTRA_H__ */

@ -0,0 +1,78 @@
/*
* Summary: interface for the XSLT functions not from XPath
* Description: a set of extra functions coming from XSLT but not in XPath
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard and Bjorn Reese <breese@users.sourceforge.net>
*/
#ifndef __XML_XSLT_FUNCTIONS_H__
#define __XML_XSLT_FUNCTIONS_H__
#include <libxml/xpath.h>
#include <libxml/xpathInternals.h>
#include "xsltexports.h"
#include "xsltInternals.h"
#ifdef __cplusplus
extern "C" {
#endif
/**
* XSLT_REGISTER_FUNCTION_LOOKUP:
*
* Registering macro, not general purpose at all but used in different modules.
*/
#define XSLT_REGISTER_FUNCTION_LOOKUP(ctxt) \
xmlXPathRegisterFuncLookup((ctxt)->xpathCtxt, \
(xmlXPathFuncLookupFunc) xsltXPathFunctionLookup, \
(void *)(ctxt->xpathCtxt));
XSLTPUBFUN xmlXPathFunction XSLTCALL
xsltXPathFunctionLookup (xmlXPathContextPtr ctxt,
const xmlChar *name,
const xmlChar *ns_uri);
/*
* Interfaces for the functions implementations.
*/
XSLTPUBFUN void XSLTCALL
xsltDocumentFunction (xmlXPathParserContextPtr ctxt,
int nargs);
XSLTPUBFUN void XSLTCALL
xsltKeyFunction (xmlXPathParserContextPtr ctxt,
int nargs);
XSLTPUBFUN void XSLTCALL
xsltUnparsedEntityURIFunction (xmlXPathParserContextPtr ctxt,
int nargs);
XSLTPUBFUN void XSLTCALL
xsltFormatNumberFunction (xmlXPathParserContextPtr ctxt,
int nargs);
XSLTPUBFUN void XSLTCALL
xsltGenerateIdFunction (xmlXPathParserContextPtr ctxt,
int nargs);
XSLTPUBFUN void XSLTCALL
xsltSystemPropertyFunction (xmlXPathParserContextPtr ctxt,
int nargs);
XSLTPUBFUN void XSLTCALL
xsltElementAvailableFunction (xmlXPathParserContextPtr ctxt,
int nargs);
XSLTPUBFUN void XSLTCALL
xsltFunctionAvailableFunction (xmlXPathParserContextPtr ctxt,
int nargs);
/*
* And the registration
*/
XSLTPUBFUN void XSLTCALL
xsltRegisterAllFunctions (xmlXPathContextPtr ctxt);
#ifdef __cplusplus
}
#endif
#endif /* __XML_XSLT_FUNCTIONS_H__ */

@ -0,0 +1,75 @@
/*
* Summary: interface for the XSLT import support
* Description: macros and fuctions needed to implement and
* access the import tree
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_XSLT_IMPORTS_H__
#define __XML_XSLT_IMPORTS_H__
#include <libxml/tree.h>
#include "xsltexports.h"
#include "xsltInternals.h"
#ifdef __cplusplus
extern "C" {
#endif
/**
* XSLT_GET_IMPORT_PTR:
*
* A macro to import pointers from the stylesheet cascading order.
*/
#define XSLT_GET_IMPORT_PTR(res, style, name) { \
xsltStylesheetPtr st = style; \
res = NULL; \
while (st != NULL) { \
if (st->name != NULL) { res = st->name; break; } \
st = xsltNextImport(st); \
}}
/**
* XSLT_GET_IMPORT_INT:
*
* A macro to import intergers from the stylesheet cascading order.
*/
#define XSLT_GET_IMPORT_INT(res, style, name) { \
xsltStylesheetPtr st = style; \
res = -1; \
while (st != NULL) { \
if (st->name != -1) { res = st->name; break; } \
st = xsltNextImport(st); \
}}
/*
* Module interfaces
*/
XSLTPUBFUN int XSLTCALL
xsltParseStylesheetImport(xsltStylesheetPtr style,
xmlNodePtr cur);
XSLTPUBFUN int XSLTCALL
xsltParseStylesheetInclude
(xsltStylesheetPtr style,
xmlNodePtr cur);
XSLTPUBFUN xsltStylesheetPtr XSLTCALL
xsltNextImport (xsltStylesheetPtr style);
XSLTPUBFUN int XSLTCALL
xsltNeedElemSpaceHandling(xsltTransformContextPtr ctxt);
XSLTPUBFUN int XSLTCALL
xsltFindElemSpaceHandling(xsltTransformContextPtr ctxt,
xmlNodePtr node);
XSLTPUBFUN xsltTemplatePtr XSLTCALL
xsltFindTemplate (xsltTransformContextPtr ctxt,
const xmlChar *name,
const xmlChar *nameURI);
#ifdef __cplusplus
}
#endif
#endif /* __XML_XSLT_IMPORTS_H__ */

@ -0,0 +1,53 @@
/*
* Summary: interface for the key matching used in key() and template matches.
* Description: implementation of the key mechanims.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_XSLT_KEY_H__
#define __XML_XSLT_KEY_H__
#include <libxml/xpath.h>
#include "xsltexports.h"
#include "xsltInternals.h"
#ifdef __cplusplus
extern "C" {
#endif
/**
* NODE_IS_KEYED:
*
* check for bit 15 set
*/
#define NODE_IS_KEYED (1 >> 15)
XSLTPUBFUN int XSLTCALL
xsltAddKey (xsltStylesheetPtr style,
const xmlChar *name,
const xmlChar *nameURI,
const xmlChar *match,
const xmlChar *use,
xmlNodePtr inst);
XSLTPUBFUN xmlNodeSetPtr XSLTCALL
xsltGetKey (xsltTransformContextPtr ctxt,
const xmlChar *name,
const xmlChar *nameURI,
const xmlChar *value);
XSLTPUBFUN void XSLTCALL
xsltInitCtxtKeys (xsltTransformContextPtr ctxt,
xsltDocumentPtr doc);
XSLTPUBFUN void XSLTCALL
xsltFreeKeys (xsltStylesheetPtr style);
XSLTPUBFUN void XSLTCALL
xsltFreeDocumentKeys (xsltDocumentPtr doc);
#ifdef __cplusplus
}
#endif
#endif /* __XML_XSLT_H__ */

@ -0,0 +1,36 @@
/*
* Summary: internal header only used during the compilation of libxslt
* Description: internal header only used during the compilation of libxslt
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XSLT_LIBXSLT_H__
#define __XSLT_LIBXSLT_H__
#if defined(WIN32) && !defined (__CYGWIN__) && !defined (__MINGW32__)
#include <win32config.h>
#else
#include "config.h"
#endif
#include <libxslt/xsltconfig.h>
#include <libxml/xmlversion.h>
#if !defined LIBXSLT_PUBLIC
#if (defined (__CYGWIN__) || defined _MSC_VER) && !defined IN_LIBXSLT && !defined LIBXSLT_STATIC
#define LIBXSLT_PUBLIC __declspec(dllimport)
#else
#define LIBXSLT_PUBLIC
#endif
#endif
#if defined(_MSC_VER) || defined(__MINGW32__)
#include <io.h>
#include <direct.h>
#define mkdir(p,m) _mkdir(p)
#endif
#endif /* ! __XSLT_LIBXSLT_H__ */

@ -0,0 +1,68 @@
/*
* Summary: interface for the XSLT namespace handling
* Description: set of function easing the processing and generation
* of namespace nodes in XSLT.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_XSLT_NAMESPACES_H__
#define __XML_XSLT_NAMESPACES_H__
#include <libxml/tree.h>
#include "xsltexports.h"
#ifdef __cplusplus
extern "C" {
#endif
/*
* Used within nsAliases hashtable when the default namespace is required
* but it's not been explicitly defined
*/
/**
* UNDEFINED_DEFAULT_NS:
*
* Special value for undefined namespace, internal
*/
#define UNDEFINED_DEFAULT_NS (const xmlChar *) -1L
XSLTPUBFUN void XSLTCALL
xsltNamespaceAlias (xsltStylesheetPtr style,
xmlNodePtr node);
XSLTPUBFUN xmlNsPtr XSLTCALL
xsltGetNamespace (xsltTransformContextPtr ctxt,
xmlNodePtr cur,
xmlNsPtr ns,
xmlNodePtr out);
XSLTPUBFUN xmlNsPtr XSLTCALL
xsltGetPlainNamespace (xsltTransformContextPtr ctxt,
xmlNodePtr cur,
xmlNsPtr ns,
xmlNodePtr out);
XSLTPUBFUN xmlNsPtr XSLTCALL
xsltGetSpecialNamespace (xsltTransformContextPtr ctxt,
xmlNodePtr cur,
const xmlChar *URI,
const xmlChar *prefix,
xmlNodePtr out);
XSLTPUBFUN xmlNsPtr XSLTCALL
xsltCopyNamespace (xsltTransformContextPtr ctxt,
xmlNodePtr elem,
xmlNsPtr ns);
XSLTPUBFUN xmlNsPtr XSLTCALL
xsltCopyNamespaceList (xsltTransformContextPtr ctxt,
xmlNodePtr node,
xmlNsPtr cur);
XSLTPUBFUN void XSLTCALL
xsltFreeNamespaceAliasHashes
(xsltStylesheetPtr style);
#ifdef __cplusplus
}
#endif
#endif /* __XML_XSLT_NAMESPACES_H__ */

@ -0,0 +1,73 @@
/*
* Summary: Implementation of the XSLT number functions
* Description: Implementation of the XSLT number functions
*
* Copy: See Copyright for the status of this software.
*
* Author: Bjorn Reese <breese@users.sourceforge.net> and Daniel Veillard
*/
#ifndef __XML_XSLT_NUMBERSINTERNALS_H__
#define __XML_XSLT_NUMBERSINTERNALS_H__
#include <libxml/tree.h>
#include "xsltexports.h"
#ifdef __cplusplus
extern "C" {
#endif
struct _xsltCompMatch;
/**
* xsltNumberData:
*
* This data structure is just a wrapper to pass xsl:number data in.
*/
typedef struct _xsltNumberData xsltNumberData;
typedef xsltNumberData *xsltNumberDataPtr;
struct _xsltNumberData {
const xmlChar *level;
const xmlChar *count;
const xmlChar *from;
const xmlChar *value;
const xmlChar *format;
int has_format;
int digitsPerGroup;
int groupingCharacter;
int groupingCharacterLen;
xmlDocPtr doc;
xmlNodePtr node;
struct _xsltCompMatch *countPat;
struct _xsltCompMatch *fromPat;
/*
* accelerators
*/
};
/**
* xsltFormatNumberInfo,:
*
* This data structure lists the various parameters needed to format numbers.
*/
typedef struct _xsltFormatNumberInfo xsltFormatNumberInfo;
typedef xsltFormatNumberInfo *xsltFormatNumberInfoPtr;
struct _xsltFormatNumberInfo {
int integer_hash; /* Number of '#' in integer part */
int integer_digits; /* Number of '0' in integer part */
int frac_digits; /* Number of '0' in fractional part */
int frac_hash; /* Number of '#' in fractional part */
int group; /* Number of chars per display 'group' */
int multiplier; /* Scaling for percent or permille */
char add_decimal; /* Flag for whether decimal point appears in pattern */
char is_multiplier_set; /* Flag to catch multiple occurences of percent/permille */
char is_negative_pattern;/* Flag for processing -ve prefix/suffix */
};
#ifdef __cplusplus
}
#endif
#endif /* __XML_XSLT_NUMBERSINTERNALS_H__ */

@ -0,0 +1,43 @@
/*
* Summary: precomputing stylesheets
* Description: this is the compilation phase, where most of the
* stylesheet is "compiled" into faster to use data.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_XSLT_PRECOMP_H__
#define __XML_XSLT_PRECOMP_H__
#include <libxml/tree.h>
#include "xsltexports.h"
#include "xsltInternals.h"
#ifdef __cplusplus
extern "C" {
#endif
/*
* Interfaces
*/
extern const xmlChar *xsltExtMarker;
XSLTPUBFUN xsltElemPreCompPtr XSLTCALL
xsltDocumentComp (xsltStylesheetPtr style,
xmlNodePtr inst,
xsltTransformFunction function);
XSLTPUBFUN void XSLTCALL
xsltStylePreCompute (xsltStylesheetPtr style,
xmlNodePtr inst);
XSLTPUBFUN void XSLTCALL
xsltFreeStylePreComps (xsltStylesheetPtr style);
#ifdef __cplusplus
}
#endif
#endif /* __XML_XSLT_PRECOMP_H__ */

@ -0,0 +1,104 @@
/*
* Summary: interface for the libxslt security framework
* Description: the libxslt security framework allow to restrict
* the access to new resources (file or URL) from
* the stylesheet at runtime.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_XSLT_SECURITY_H__
#define __XML_XSLT_SECURITY_H__
#include <libxml/tree.h>
#include "xsltexports.h"
#include "xsltInternals.h"
#ifdef __cplusplus
extern "C" {
#endif
/**
* xsltSecurityPref:
*
* structure to indicate the preferences for security in the XSLT
* transformation.
*/
typedef struct _xsltSecurityPrefs xsltSecurityPrefs;
typedef xsltSecurityPrefs *xsltSecurityPrefsPtr;
/**
* xsltSecurityOption:
*
* the set of option that can be configured
*/
typedef enum {
XSLT_SECPREF_READ_FILE = 1,
XSLT_SECPREF_WRITE_FILE,
XSLT_SECPREF_CREATE_DIRECTORY,
XSLT_SECPREF_READ_NETWORK,
XSLT_SECPREF_WRITE_NETWORK
} xsltSecurityOption;
/**
* xsltSecurityCheck:
*
* User provided function to check the value of a string like a file
* path or an URL ...
*/
typedef int (*xsltSecurityCheck) (xsltSecurityPrefsPtr sec,
xsltTransformContextPtr ctxt,
const char *value);
/*
* Module interfaces
*/
XSLTPUBFUN xsltSecurityPrefsPtr XSLTCALL
xsltNewSecurityPrefs (void);
XSLTPUBFUN void XSLTCALL
xsltFreeSecurityPrefs (xsltSecurityPrefsPtr sec);
XSLTPUBFUN int XSLTCALL
xsltSetSecurityPrefs (xsltSecurityPrefsPtr sec,
xsltSecurityOption option,
xsltSecurityCheck func);
XSLTPUBFUN xsltSecurityCheck XSLTCALL
xsltGetSecurityPrefs (xsltSecurityPrefsPtr sec,
xsltSecurityOption option);
XSLTPUBFUN void XSLTCALL
xsltSetDefaultSecurityPrefs (xsltSecurityPrefsPtr sec);
XSLTPUBFUN xsltSecurityPrefsPtr XSLTCALL
xsltGetDefaultSecurityPrefs (void);
XSLTPUBFUN int XSLTCALL
xsltSetCtxtSecurityPrefs (xsltSecurityPrefsPtr sec,
xsltTransformContextPtr ctxt);
XSLTPUBFUN int XSLTCALL
xsltSecurityAllow (xsltSecurityPrefsPtr sec,
xsltTransformContextPtr ctxt,
const char *value);
XSLTPUBFUN int XSLTCALL
xsltSecurityForbid (xsltSecurityPrefsPtr sec,
xsltTransformContextPtr ctxt,
const char *value);
/*
* internal interfaces
*/
XSLTPUBFUN int XSLTCALL
xsltCheckWrite (xsltSecurityPrefsPtr sec,
xsltTransformContextPtr ctxt,
const xmlChar *URL);
XSLTPUBFUN int XSLTCALL
xsltCheckRead (xsltSecurityPrefsPtr sec,
xsltTransformContextPtr ctxt,
const xmlChar *URL);
#ifdef __cplusplus
}
#endif
#endif /* __XML_XSLT_SECURITY_H__ */

@ -0,0 +1,77 @@
/*
* Summary: interface for the template processing
* Description: This set of routine encapsulates XPath calls
* and Attribute Value Templates evaluation.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_XSLT_TEMPLATES_H__
#define __XML_XSLT_TEMPLATES_H__
#include <libxml/xpath.h>
#include <libxml/xpathInternals.h>
#include "xsltexports.h"
#include "xsltInternals.h"
#ifdef __cplusplus
extern "C" {
#endif
XSLTPUBFUN int XSLTCALL
xsltEvalXPathPredicate (xsltTransformContextPtr ctxt,
xmlXPathCompExprPtr comp,
xmlNsPtr *nsList,
int nsNr);
XSLTPUBFUN xmlChar * XSLTCALL
xsltEvalTemplateString (xsltTransformContextPtr ctxt,
xmlNodePtr contextNode,
xmlNodePtr inst);
XSLTPUBFUN xmlChar * XSLTCALL
xsltEvalAttrValueTemplate (xsltTransformContextPtr ctxt,
xmlNodePtr node,
const xmlChar *name,
const xmlChar *ns);
XSLTPUBFUN const xmlChar * XSLTCALL
xsltEvalStaticAttrValueTemplate (xsltStylesheetPtr style,
xmlNodePtr node,
const xmlChar *name,
const xmlChar *ns,
int *found);
/* TODO: this is obviously broken ... the namespaces should be passed too ! */
XSLTPUBFUN xmlChar * XSLTCALL
xsltEvalXPathString (xsltTransformContextPtr ctxt,
xmlXPathCompExprPtr comp);
XSLTPUBFUN xmlChar * XSLTCALL
xsltEvalXPathStringNs (xsltTransformContextPtr ctxt,
xmlXPathCompExprPtr comp,
int nsNr,
xmlNsPtr *nsList);
XSLTPUBFUN xmlNodePtr * XSLTCALL
xsltTemplateProcess (xsltTransformContextPtr ctxt,
xmlNodePtr node);
XSLTPUBFUN xmlAttrPtr XSLTCALL
xsltAttrListTemplateProcess (xsltTransformContextPtr ctxt,
xmlNodePtr target,
xmlAttrPtr cur);
XSLTPUBFUN xmlAttrPtr XSLTCALL
xsltAttrTemplateProcess (xsltTransformContextPtr ctxt,
xmlNodePtr target,
xmlAttrPtr attr);
XSLTPUBFUN xmlChar * XSLTCALL
xsltAttrTemplateValueProcess (xsltTransformContextPtr ctxt,
const xmlChar* attr);
XSLTPUBFUN xmlChar * XSLTCALL
xsltAttrTemplateValueProcessNode(xsltTransformContextPtr ctxt,
const xmlChar* str,
xmlNodePtr node);
#ifdef __cplusplus
}
#endif
#endif /* __XML_XSLT_TEMPLATES_H__ */

@ -0,0 +1,207 @@
/*
* Summary: the XSLT engine transformation part.
* Description: This module implements the bulk of the actual
* transformation processing. Most of the xsl: element
* constructs are implemented in this module.
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_XSLT_TRANSFORM_H__
#define __XML_XSLT_TRANSFORM_H__
#include <libxml/parser.h>
#include <libxml/xmlIO.h>
#include "xsltexports.h"
#include <libxslt/xsltInternals.h>
#ifdef __cplusplus
extern "C" {
#endif
/**
* XInclude default processing.
*/
XSLTPUBFUN void XSLTCALL
xsltSetXIncludeDefault (int xinclude);
XSLTPUBFUN int XSLTCALL
xsltGetXIncludeDefault (void);
/**
* Export context to users.
*/
XSLTPUBFUN xsltTransformContextPtr XSLTCALL
xsltNewTransformContext (xsltStylesheetPtr style,
xmlDocPtr doc);
XSLTPUBFUN void XSLTCALL
xsltFreeTransformContext(xsltTransformContextPtr ctxt);
XSLTPUBFUN xmlDocPtr XSLTCALL
xsltApplyStylesheetUser (xsltStylesheetPtr style,
xmlDocPtr doc,
const char **params,
const char *output,
FILE * profile,
xsltTransformContextPtr userCtxt);
XSLTPUBFUN void XSLTCALL
xsltProcessOneNode (xsltTransformContextPtr ctxt,
xmlNodePtr node,
xsltStackElemPtr params);
/**
* Private Interfaces.
*/
XSLTPUBFUN void XSLTCALL
xsltApplyStripSpaces (xsltTransformContextPtr ctxt,
xmlNodePtr node);
XSLTPUBFUN xmlDocPtr XSLTCALL
xsltApplyStylesheet (xsltStylesheetPtr style,
xmlDocPtr doc,
const char **params);
XSLTPUBFUN xmlDocPtr XSLTCALL
xsltProfileStylesheet (xsltStylesheetPtr style,
xmlDocPtr doc,
const char **params,
FILE * output);
XSLTPUBFUN int XSLTCALL
xsltRunStylesheet (xsltStylesheetPtr style,
xmlDocPtr doc,
const char **params,
const char *output,
xmlSAXHandlerPtr SAX,
xmlOutputBufferPtr IObuf);
XSLTPUBFUN int XSLTCALL
xsltRunStylesheetUser (xsltStylesheetPtr style,
xmlDocPtr doc,
const char **params,
const char *output,
xmlSAXHandlerPtr SAX,
xmlOutputBufferPtr IObuf,
FILE * profile,
xsltTransformContextPtr userCtxt);
XSLTPUBFUN void XSLTCALL
xsltApplyOneTemplate (xsltTransformContextPtr ctxt,
xmlNodePtr node,
xmlNodePtr list,
xsltTemplatePtr templ,
xsltStackElemPtr params);
XSLTPUBFUN void XSLTCALL
xsltDocumentElem (xsltTransformContextPtr ctxt,
xmlNodePtr node,
xmlNodePtr inst,
xsltStylePreCompPtr comp);
XSLTPUBFUN void XSLTCALL
xsltSort (xsltTransformContextPtr ctxt,
xmlNodePtr node,
xmlNodePtr inst,
xsltStylePreCompPtr comp);
XSLTPUBFUN void XSLTCALL
xsltCopy (xsltTransformContextPtr ctxt,
xmlNodePtr node,
xmlNodePtr inst,
xsltStylePreCompPtr comp);
XSLTPUBFUN void XSLTCALL
xsltText (xsltTransformContextPtr ctxt,
xmlNodePtr node,
xmlNodePtr inst,
xsltStylePreCompPtr comp);
XSLTPUBFUN void XSLTCALL
xsltElement (xsltTransformContextPtr ctxt,
xmlNodePtr node,
xmlNodePtr inst,
xsltStylePreCompPtr comp);
XSLTPUBFUN void XSLTCALL
xsltComment (xsltTransformContextPtr ctxt,
xmlNodePtr node,
xmlNodePtr inst,
xsltStylePreCompPtr comp);
XSLTPUBFUN void XSLTCALL
xsltAttribute (xsltTransformContextPtr ctxt,
xmlNodePtr node,
xmlNodePtr inst,
xsltStylePreCompPtr comp);
XSLTPUBFUN void XSLTCALL
xsltProcessingInstruction(xsltTransformContextPtr ctxt,
xmlNodePtr node,
xmlNodePtr inst,
xsltStylePreCompPtr comp);
XSLTPUBFUN void XSLTCALL
xsltCopyOf (xsltTransformContextPtr ctxt,
xmlNodePtr node,
xmlNodePtr inst,
xsltStylePreCompPtr comp);
XSLTPUBFUN void XSLTCALL
xsltValueOf (xsltTransformContextPtr ctxt,
xmlNodePtr node,
xmlNodePtr inst,
xsltStylePreCompPtr comp);
XSLTPUBFUN void XSLTCALL
xsltNumber (xsltTransformContextPtr ctxt,
xmlNodePtr node,
xmlNodePtr inst,
xsltStylePreCompPtr comp);
XSLTPUBFUN void XSLTCALL
xsltApplyImports (xsltTransformContextPtr ctxt,
xmlNodePtr node,
xmlNodePtr inst,
xsltStylePreCompPtr comp);
XSLTPUBFUN void XSLTCALL
xsltCallTemplate (xsltTransformContextPtr ctxt,
xmlNodePtr node,
xmlNodePtr inst,
xsltStylePreCompPtr comp);
XSLTPUBFUN void XSLTCALL
xsltApplyTemplates (xsltTransformContextPtr ctxt,
xmlNodePtr node,
xmlNodePtr inst,
xsltStylePreCompPtr comp);
XSLTPUBFUN void XSLTCALL
xsltChoose (xsltTransformContextPtr ctxt,
xmlNodePtr node,
xmlNodePtr inst,
xsltStylePreCompPtr comp);
XSLTPUBFUN void XSLTCALL
xsltIf (xsltTransformContextPtr ctxt,
xmlNodePtr node,
xmlNodePtr inst,
xsltStylePreCompPtr comp);
XSLTPUBFUN void XSLTCALL
xsltForEach (xsltTransformContextPtr ctxt,
xmlNodePtr node,
xmlNodePtr inst,
xsltStylePreCompPtr comp);
XSLTPUBFUN void XSLTCALL
xsltRegisterAllElement (xsltTransformContextPtr ctxt);
XSLTPUBFUN xmlNodePtr XSLTCALL
xsltCopyTextString (xsltTransformContextPtr ctxt,
xmlNodePtr target,
const xmlChar *string,
int noescape);
/* Following 2 functions needed for libexslt/functions.c */
XSLTPUBFUN void XSLTCALL
xsltLocalVariablePop (xsltTransformContextPtr ctxt,
int limitNr,
int level);
XSLTPUBFUN int XSLTCALL
xsltLocalVariablePush (xsltTransformContextPtr ctxt,
xsltStackElemPtr variable,
int level);
/*
* Hook for the debugger if activated.
*/
XSLTPUBFUN void XSLTCALL
xslHandleDebugger (xmlNodePtr cur,
xmlNodePtr node,
xsltTemplatePtr templ,
xsltTransformContextPtr ctxt);
#ifdef __cplusplus
}
#endif
#endif /* __XML_XSLT_TRANSFORM_H__ */

Some files were not shown because too many files have changed in this diff Show More

Loading…
Cancel
Save