Andrew Rabert
5 years ago
committed by
GitHub
commit
c7f648f86a
@ -1,371 +0,0 @@
|
||||
using System;
|
||||
using System.Collections.Generic;
|
||||
using System.IO;
|
||||
using System.Linq;
|
||||
using System.Text;
|
||||
using System.Text.RegularExpressions;
|
||||
using NLangDetect.Core.Extensions;
|
||||
using NLangDetect.Core.Utils;
|
||||
|
||||
namespace NLangDetect.Core
|
||||
{
|
||||
public class Detector
|
||||
{
|
||||
private const double _AlphaDefault = 0.5;
|
||||
private const double _AlphaWidth = 0.05;
|
||||
|
||||
private const int _IterationLimit = 1000;
|
||||
private const double _ProbThreshold = 0.1;
|
||||
private const double _ConvThreshold = 0.99999;
|
||||
private const int _BaseFreq = 10000;
|
||||
|
||||
private static readonly Regex _UrlRegex = new Regex("https?://[-_.?&~;+=/#0-9A-Za-z]+", RegexOptions.Compiled);
|
||||
private static readonly Regex _MailRegex = new Regex("[-_.0-9A-Za-z]+@[-_0-9A-Za-z]+[-_.0-9A-Za-z]+", RegexOptions.Compiled);
|
||||
|
||||
private readonly Dictionary<string, ProbVector> _wordLangProbMap;
|
||||
private readonly List<string> _langlist;
|
||||
|
||||
private StringBuilder _text;
|
||||
private double[] _langprob;
|
||||
|
||||
private double _alpha = _AlphaDefault;
|
||||
private const int _trialsCount = 7;
|
||||
private int _maxTextLength = 10000;
|
||||
private double[] _priorMap;
|
||||
private int? _seed;
|
||||
|
||||
#region Constructor(s)
|
||||
|
||||
public Detector(DetectorFactory factory)
|
||||
{
|
||||
_wordLangProbMap = factory.WordLangProbMap;
|
||||
_langlist = factory.Langlist;
|
||||
_text = new StringBuilder();
|
||||
_seed = factory.Seed;
|
||||
}
|
||||
|
||||
#endregion
|
||||
|
||||
#region Public methods
|
||||
|
||||
public void SetAlpha(double alpha)
|
||||
{
|
||||
_alpha = alpha;
|
||||
}
|
||||
|
||||
public void SetPriorMap(Dictionary<string, double> priorMap)
|
||||
{
|
||||
_priorMap = new double[_langlist.Count];
|
||||
|
||||
double sump = 0;
|
||||
|
||||
for (int i = 0; i < _priorMap.Length; i++)
|
||||
{
|
||||
string lang = _langlist[i];
|
||||
|
||||
if (priorMap.ContainsKey(lang))
|
||||
{
|
||||
double p = priorMap[lang];
|
||||
|
||||
if (p < 0)
|
||||
{
|
||||
throw new NLangDetectException("Prior probability must be non-negative.", ErrorCode.InitParamError);
|
||||
}
|
||||
|
||||
_priorMap[i] = p;
|
||||
sump += p;
|
||||
}
|
||||
}
|
||||
|
||||
if (sump <= 0)
|
||||
{
|
||||
throw new NLangDetectException("More one of prior probability must be non-zero.", ErrorCode.InitParamError);
|
||||
}
|
||||
|
||||
for (int i = 0; i < _priorMap.Length; i++)
|
||||
{
|
||||
_priorMap[i] /= sump;
|
||||
}
|
||||
}
|
||||
|
||||
public void SetMaxTextLength(int max_text_length)
|
||||
{
|
||||
_maxTextLength = max_text_length;
|
||||
}
|
||||
|
||||
// TODO IMM HI: TextReader?
|
||||
public void Append(StreamReader streamReader)
|
||||
{
|
||||
var buf = new char[_maxTextLength / 2];
|
||||
|
||||
while (_text.Length < _maxTextLength && !streamReader.EndOfStream)
|
||||
{
|
||||
int length = streamReader.Read(buf, 0, buf.Length);
|
||||
|
||||
Append(new string(buf, 0, length));
|
||||
}
|
||||
}
|
||||
|
||||
public void Append(string text)
|
||||
{
|
||||
text = _UrlRegex.Replace(text, " ");
|
||||
text = _MailRegex.Replace(text, " ");
|
||||
|
||||
char pre = '\0';
|
||||
|
||||
for (int i = 0; i < text.Length && i < _maxTextLength; i++)
|
||||
{
|
||||
char c = NGram.Normalize(text[i]);
|
||||
|
||||
if (c != ' ' || pre != ' ')
|
||||
{
|
||||
_text.Append(c);
|
||||
}
|
||||
|
||||
pre = c;
|
||||
}
|
||||
}
|
||||
|
||||
private void CleanText()
|
||||
{
|
||||
int latinCount = 0, nonLatinCount = 0;
|
||||
|
||||
for (int i = 0; i < _text.Length; i++)
|
||||
{
|
||||
char c = _text[i];
|
||||
|
||||
if (c <= 'z' && c >= 'A')
|
||||
{
|
||||
latinCount++;
|
||||
}
|
||||
else if (c >= '\u0300' && c.GetUnicodeBlock() != UnicodeBlock.LatinExtendedAdditional)
|
||||
{
|
||||
nonLatinCount++;
|
||||
}
|
||||
}
|
||||
|
||||
if (latinCount * 2 < nonLatinCount)
|
||||
{
|
||||
var textWithoutLatin = new StringBuilder();
|
||||
|
||||
for (int i = 0; i < _text.Length; i++)
|
||||
{
|
||||
char c = _text[i];
|
||||
|
||||
if (c > 'z' || c < 'A')
|
||||
{
|
||||
textWithoutLatin.Append(c);
|
||||
}
|
||||
}
|
||||
|
||||
_text = textWithoutLatin;
|
||||
}
|
||||
}
|
||||
|
||||
public string Detect()
|
||||
{
|
||||
List<Language> probabilities = GetProbabilities();
|
||||
|
||||
return
|
||||
probabilities.Count > 0
|
||||
? probabilities[0].Name
|
||||
: null;
|
||||
}
|
||||
|
||||
public List<Language> GetProbabilities()
|
||||
{
|
||||
if (_langprob == null)
|
||||
{
|
||||
DetectBlock();
|
||||
}
|
||||
|
||||
var list = SortProbability(_langprob);
|
||||
|
||||
return list;
|
||||
}
|
||||
|
||||
#endregion
|
||||
|
||||
#region Private helper methods
|
||||
|
||||
private static double NormalizeProb(double[] probs)
|
||||
{
|
||||
double maxp = 0, sump = 0;
|
||||
|
||||
sump += probs.Sum();
|
||||
|
||||
for (int i = 0; i < probs.Length; i++)
|
||||
{
|
||||
double p = probs[i] / sump;
|
||||
|
||||
if (maxp < p)
|
||||
{
|
||||
maxp = p;
|
||||
}
|
||||
|
||||
probs[i] = p;
|
||||
}
|
||||
|
||||
return maxp;
|
||||
}
|
||||
|
||||
private static string UnicodeEncode(string word)
|
||||
{
|
||||
var resultSb = new StringBuilder();
|
||||
|
||||
foreach (char ch in word)
|
||||
{
|
||||
if (ch >= '\u0080')
|
||||
{
|
||||
string st = string.Format("{0:x}", 0x10000 + ch);
|
||||
|
||||
while (st.Length < 4)
|
||||
{
|
||||
st = "0" + st;
|
||||
}
|
||||
|
||||
resultSb
|
||||
.Append("\\u")
|
||||
.Append(st.SubSequence(1, 5));
|
||||
}
|
||||
else
|
||||
{
|
||||
resultSb.Append(ch);
|
||||
}
|
||||
}
|
||||
|
||||
return resultSb.ToString();
|
||||
}
|
||||
|
||||
private void DetectBlock()
|
||||
{
|
||||
CleanText();
|
||||
|
||||
List<string> ngrams = ExtractNGrams();
|
||||
|
||||
if (ngrams.Count == 0)
|
||||
{
|
||||
throw new NLangDetectException("no features in text", ErrorCode.CantDetectError);
|
||||
}
|
||||
|
||||
_langprob = new double[_langlist.Count];
|
||||
|
||||
var rand = (_seed.HasValue ? new Random(_seed.Value) : new Random());
|
||||
|
||||
for (int t = 0; t < _trialsCount; t++)
|
||||
{
|
||||
double[] prob = InitProbability();
|
||||
|
||||
// TODO IMM HI: verify it works
|
||||
double alpha = _alpha + rand.NextGaussian() * _AlphaWidth;
|
||||
|
||||
for (int i = 0; ; i++)
|
||||
{
|
||||
int r = rand.Next(ngrams.Count);
|
||||
|
||||
UpdateLangProb(prob, ngrams[r], alpha);
|
||||
|
||||
if (i % 5 == 0)
|
||||
{
|
||||
if (NormalizeProb(prob) > _ConvThreshold || i >= _IterationLimit)
|
||||
{
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
for (int j = 0; j < _langprob.Length; j++)
|
||||
{
|
||||
_langprob[j] += prob[j] / _trialsCount;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private double[] InitProbability()
|
||||
{
|
||||
var prob = new double[_langlist.Count];
|
||||
|
||||
if (_priorMap != null)
|
||||
{
|
||||
for (int i = 0; i < prob.Length; i++)
|
||||
{
|
||||
prob[i] = _priorMap[i];
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
for (int i = 0; i < prob.Length; i++)
|
||||
{
|
||||
prob[i] = 1.0 / _langlist.Count;
|
||||
}
|
||||
}
|
||||
return prob;
|
||||
}
|
||||
|
||||
private List<string> ExtractNGrams()
|
||||
{
|
||||
var list = new List<string>();
|
||||
var ngram = new NGram();
|
||||
|
||||
for (int i = 0; i < _text.Length; i++)
|
||||
{
|
||||
ngram.AddChar(_text[i]);
|
||||
|
||||
for (int n = 1; n <= NGram.GramsCount; n++)
|
||||
{
|
||||
string w = ngram.Get(n);
|
||||
|
||||
if (w != null && _wordLangProbMap.ContainsKey(w))
|
||||
{
|
||||
list.Add(w);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return list;
|
||||
}
|
||||
|
||||
private void UpdateLangProb(double[] prob, string word, double alpha)
|
||||
{
|
||||
if (word == null || !_wordLangProbMap.ContainsKey(word))
|
||||
{
|
||||
return;
|
||||
}
|
||||
|
||||
ProbVector langProbMap = _wordLangProbMap[word];
|
||||
double weight = alpha / _BaseFreq;
|
||||
|
||||
for (int i = 0; i < prob.Length; i++)
|
||||
{
|
||||
prob[i] *= weight + langProbMap[i];
|
||||
}
|
||||
}
|
||||
|
||||
private List<Language> SortProbability(double[] prob)
|
||||
{
|
||||
var list = new List<Language>();
|
||||
|
||||
for (int j = 0; j < prob.Length; j++)
|
||||
{
|
||||
double p = prob[j];
|
||||
|
||||
if (p > _ProbThreshold)
|
||||
{
|
||||
for (int i = 0; i <= list.Count; i++)
|
||||
{
|
||||
if (i == list.Count || list[i].Probability < p)
|
||||
{
|
||||
list.Insert(i, new Language(_langlist[j], p));
|
||||
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return list;
|
||||
}
|
||||
|
||||
#endregion
|
||||
}
|
||||
}
|
||||
@ -1,125 +0,0 @@
|
||||
using System;
|
||||
using System.Collections.Generic;
|
||||
using System.Linq;
|
||||
using MediaBrowser.Model.Serialization;
|
||||
using NLangDetect.Core.Utils;
|
||||
|
||||
namespace NLangDetect.Core
|
||||
{
|
||||
public class DetectorFactory
|
||||
{
|
||||
public Dictionary<string, ProbVector> WordLangProbMap;
|
||||
public List<string> Langlist;
|
||||
|
||||
private static readonly DetectorFactory _instance = new DetectorFactory();
|
||||
|
||||
#region Constructor(s)
|
||||
|
||||
private DetectorFactory()
|
||||
{
|
||||
WordLangProbMap = new Dictionary<string, ProbVector>();
|
||||
Langlist = new List<string>();
|
||||
}
|
||||
|
||||
#endregion
|
||||
|
||||
#region Public methods
|
||||
|
||||
public static void LoadProfiles(IJsonSerializer json)
|
||||
{
|
||||
var assembly = typeof(DetectorFactory).Assembly;
|
||||
var names = assembly.GetManifestResourceNames()
|
||||
.Where(i => i.IndexOf("NLangDetect.Profiles", StringComparison.Ordinal) != -1)
|
||||
.ToList();
|
||||
|
||||
var index = 0;
|
||||
|
||||
foreach (var name in names)
|
||||
{
|
||||
using (var stream = assembly.GetManifestResourceStream(name))
|
||||
{
|
||||
var langProfile = (LangProfile)json.DeserializeFromStream(stream, typeof(LangProfile));
|
||||
|
||||
AddProfile(langProfile, index);
|
||||
}
|
||||
|
||||
index++;
|
||||
}
|
||||
}
|
||||
|
||||
public static Detector Create()
|
||||
{
|
||||
return CreateDetector();
|
||||
}
|
||||
|
||||
public static Detector Create(double alpha)
|
||||
{
|
||||
var detector = CreateDetector();
|
||||
|
||||
detector.SetAlpha(alpha);
|
||||
|
||||
return detector;
|
||||
}
|
||||
|
||||
public static void SetSeed(int? seed)
|
||||
{
|
||||
_instance.Seed = seed;
|
||||
}
|
||||
|
||||
#endregion
|
||||
|
||||
#region Internal methods
|
||||
|
||||
internal static void AddProfile(LangProfile profile, int index)
|
||||
{
|
||||
var lang = profile.name;
|
||||
|
||||
if (_instance.Langlist.Contains(lang))
|
||||
{
|
||||
throw new NLangDetectException("duplicate the same language profile", ErrorCode.DuplicateLangError);
|
||||
}
|
||||
|
||||
_instance.Langlist.Add(lang);
|
||||
|
||||
foreach (string word in profile.freq.Keys)
|
||||
{
|
||||
if (!_instance.WordLangProbMap.ContainsKey(word))
|
||||
{
|
||||
_instance.WordLangProbMap.Add(word, new ProbVector());
|
||||
}
|
||||
|
||||
double prob = (double)profile.freq[word] / profile.n_words[word.Length - 1];
|
||||
|
||||
_instance.WordLangProbMap[word][index] = prob;
|
||||
}
|
||||
}
|
||||
|
||||
internal static void Clear()
|
||||
{
|
||||
_instance.Langlist.Clear();
|
||||
_instance.WordLangProbMap.Clear();
|
||||
}
|
||||
|
||||
#endregion
|
||||
|
||||
#region Private helper methods
|
||||
|
||||
private static Detector CreateDetector()
|
||||
{
|
||||
if (_instance.Langlist.Count == 0)
|
||||
{
|
||||
throw new NLangDetectException("need to load profiles", ErrorCode.NeedLoadProfileError);
|
||||
}
|
||||
|
||||
return new Detector(_instance);
|
||||
}
|
||||
|
||||
#endregion
|
||||
|
||||
#region Properties
|
||||
|
||||
public int? Seed { get; private set; }
|
||||
|
||||
#endregion
|
||||
}
|
||||
}
|
||||
@ -1,15 +0,0 @@
|
||||
namespace NLangDetect.Core
|
||||
{
|
||||
public enum ErrorCode
|
||||
{
|
||||
NoTextError,
|
||||
FormatError,
|
||||
FileLoadError,
|
||||
DuplicateLangError,
|
||||
NeedLoadProfileError,
|
||||
CantDetectError,
|
||||
CantOpenTrainData,
|
||||
TrainDataFormatError,
|
||||
InitParamError,
|
||||
}
|
||||
}
|
||||
@ -1,374 +0,0 @@
|
||||
using System;
|
||||
|
||||
namespace NLangDetect.Core.Extensions
|
||||
{
|
||||
public static class CharExtensions
|
||||
{
|
||||
private const int MIN_CODE_POINT = 0x000000;
|
||||
private const int MAX_CODE_POINT = 0x10ffff;
|
||||
|
||||
private static readonly int[] _unicodeBlockStarts =
|
||||
{
|
||||
#region Unicode block starts
|
||||
|
||||
0x0000, // Basic Latin
|
||||
0x0080, // Latin-1 Supplement
|
||||
0x0100, // Latin Extended-A
|
||||
0x0180, // Latin Extended-B
|
||||
0x0250, // IPA Extensions
|
||||
0x02B0, // Spacing Modifier Letters
|
||||
0x0300, // Combining Diacritical Marks
|
||||
0x0370, // Greek and Coptic
|
||||
0x0400, // Cyrillic
|
||||
0x0500, // Cyrillic Supplementary
|
||||
0x0530, // Armenian
|
||||
0x0590, // Hebrew
|
||||
0x0600, // Arabic
|
||||
0x0700, // Syriac
|
||||
0x0750, // unassigned
|
||||
0x0780, // Thaana
|
||||
0x07C0, // unassigned
|
||||
0x0900, // Devanagari
|
||||
0x0980, // Bengali
|
||||
0x0A00, // Gurmukhi
|
||||
0x0A80, // Gujarati
|
||||
0x0B00, // Oriya
|
||||
0x0B80, // Tamil
|
||||
0x0C00, // Telugu
|
||||
0x0C80, // Kannada
|
||||
0x0D00, // Malayalam
|
||||
0x0D80, // Sinhala
|
||||
0x0E00, // Thai
|
||||
0x0E80, // Lao
|
||||
0x0F00, // Tibetan
|
||||
0x1000, // Myanmar
|
||||
0x10A0, // Georgian
|
||||
0x1100, // Hangul Jamo
|
||||
0x1200, // Ethiopic
|
||||
0x1380, // unassigned
|
||||
0x13A0, // Cherokee
|
||||
0x1400, // Unified Canadian Aboriginal Syllabics
|
||||
0x1680, // Ogham
|
||||
0x16A0, // Runic
|
||||
0x1700, // Tagalog
|
||||
0x1720, // Hanunoo
|
||||
0x1740, // Buhid
|
||||
0x1760, // Tagbanwa
|
||||
0x1780, // Khmer
|
||||
0x1800, // Mongolian
|
||||
0x18B0, // unassigned
|
||||
0x1900, // Limbu
|
||||
0x1950, // Tai Le
|
||||
0x1980, // unassigned
|
||||
0x19E0, // Khmer Symbols
|
||||
0x1A00, // unassigned
|
||||
0x1D00, // Phonetic Extensions
|
||||
0x1D80, // unassigned
|
||||
0x1E00, // Latin Extended Additional
|
||||
0x1F00, // Greek Extended
|
||||
0x2000, // General Punctuation
|
||||
0x2070, // Superscripts and Subscripts
|
||||
0x20A0, // Currency Symbols
|
||||
0x20D0, // Combining Diacritical Marks for Symbols
|
||||
0x2100, // Letterlike Symbols
|
||||
0x2150, // Number Forms
|
||||
0x2190, // Arrows
|
||||
0x2200, // Mathematical Operators
|
||||
0x2300, // Miscellaneous Technical
|
||||
0x2400, // Control Pictures
|
||||
0x2440, // Optical Character Recognition
|
||||
0x2460, // Enclosed Alphanumerics
|
||||
0x2500, // Box Drawing
|
||||
0x2580, // Block Elements
|
||||
0x25A0, // Geometric Shapes
|
||||
0x2600, // Miscellaneous Symbols
|
||||
0x2700, // Dingbats
|
||||
0x27C0, // Miscellaneous Mathematical Symbols-A
|
||||
0x27F0, // Supplemental Arrows-A
|
||||
0x2800, // Braille Patterns
|
||||
0x2900, // Supplemental Arrows-B
|
||||
0x2980, // Miscellaneous Mathematical Symbols-B
|
||||
0x2A00, // Supplemental Mathematical Operators
|
||||
0x2B00, // Miscellaneous Symbols and Arrows
|
||||
0x2C00, // unassigned
|
||||
0x2E80, // CJK Radicals Supplement
|
||||
0x2F00, // Kangxi Radicals
|
||||
0x2FE0, // unassigned
|
||||
0x2FF0, // Ideographic Description Characters
|
||||
0x3000, // CJK Symbols and Punctuation
|
||||
0x3040, // Hiragana
|
||||
0x30A0, // Katakana
|
||||
0x3100, // Bopomofo
|
||||
0x3130, // Hangul Compatibility Jamo
|
||||
0x3190, // Kanbun
|
||||
0x31A0, // Bopomofo Extended
|
||||
0x31C0, // unassigned
|
||||
0x31F0, // Katakana Phonetic Extensions
|
||||
0x3200, // Enclosed CJK Letters and Months
|
||||
0x3300, // CJK Compatibility
|
||||
0x3400, // CJK Unified Ideographs Extension A
|
||||
0x4DC0, // Yijing Hexagram Symbols
|
||||
0x4E00, // CJK Unified Ideographs
|
||||
0xA000, // Yi Syllables
|
||||
0xA490, // Yi Radicals
|
||||
0xA4D0, // unassigned
|
||||
0xAC00, // Hangul Syllables
|
||||
0xD7B0, // unassigned
|
||||
0xD800, // High Surrogates
|
||||
0xDB80, // High Private Use Surrogates
|
||||
0xDC00, // Low Surrogates
|
||||
0xE000, // Private Use
|
||||
0xF900, // CJK Compatibility Ideographs
|
||||
0xFB00, // Alphabetic Presentation Forms
|
||||
0xFB50, // Arabic Presentation Forms-A
|
||||
0xFE00, // Variation Selectors
|
||||
0xFE10, // unassigned
|
||||
0xFE20, // Combining Half Marks
|
||||
0xFE30, // CJK Compatibility Forms
|
||||
0xFE50, // Small Form Variants
|
||||
0xFE70, // Arabic Presentation Forms-B
|
||||
0xFF00, // Halfwidth and Fullwidth Forms
|
||||
0xFFF0, // Specials
|
||||
0x10000, // Linear B Syllabary
|
||||
0x10080, // Linear B Ideograms
|
||||
0x10100, // Aegean Numbers
|
||||
0x10140, // unassigned
|
||||
0x10300, // Old Italic
|
||||
0x10330, // Gothic
|
||||
0x10350, // unassigned
|
||||
0x10380, // Ugaritic
|
||||
0x103A0, // unassigned
|
||||
0x10400, // Deseret
|
||||
0x10450, // Shavian
|
||||
0x10480, // Osmanya
|
||||
0x104B0, // unassigned
|
||||
0x10800, // Cypriot Syllabary
|
||||
0x10840, // unassigned
|
||||
0x1D000, // Byzantine Musical Symbols
|
||||
0x1D100, // Musical Symbols
|
||||
0x1D200, // unassigned
|
||||
0x1D300, // Tai Xuan Jing Symbols
|
||||
0x1D360, // unassigned
|
||||
0x1D400, // Mathematical Alphanumeric Symbols
|
||||
0x1D800, // unassigned
|
||||
0x20000, // CJK Unified Ideographs Extension B
|
||||
0x2A6E0, // unassigned
|
||||
0x2F800, // CJK Compatibility Ideographs Supplement
|
||||
0x2FA20, // unassigned
|
||||
0xE0000, // Tags
|
||||
0xE0080, // unassigned
|
||||
0xE0100, // Variation Selectors Supplement
|
||||
0xE01F0, // unassigned
|
||||
0xF0000, // Supplementary Private Use Area-A
|
||||
0x100000, // Supplementary Private Use Area-B
|
||||
|
||||
#endregion
|
||||
};
|
||||
|
||||
private static readonly UnicodeBlock?[] _unicodeBlocks =
|
||||
{
|
||||
#region Unicode blocks
|
||||
UnicodeBlock.BasicLatin,
|
||||
UnicodeBlock.Latin1Supplement,
|
||||
UnicodeBlock.LatinExtendedA,
|
||||
UnicodeBlock.LatinExtendedB,
|
||||
UnicodeBlock.IpaExtensions,
|
||||
UnicodeBlock.SpacingModifierLetters,
|
||||
UnicodeBlock.CombiningDiacriticalMarks,
|
||||
UnicodeBlock.Greek,
|
||||
UnicodeBlock.Cyrillic,
|
||||
UnicodeBlock.CyrillicSupplementary,
|
||||
UnicodeBlock.Armenian,
|
||||
UnicodeBlock.Hebrew,
|
||||
UnicodeBlock.Arabic,
|
||||
UnicodeBlock.Syriac,
|
||||
null,
|
||||
UnicodeBlock.Thaana,
|
||||
null,
|
||||
UnicodeBlock.Devanagari,
|
||||
UnicodeBlock.Bengali,
|
||||
UnicodeBlock.Gurmukhi,
|
||||
UnicodeBlock.Gujarati,
|
||||
UnicodeBlock.Oriya,
|
||||
UnicodeBlock.Tamil,
|
||||
UnicodeBlock.Telugu,
|
||||
UnicodeBlock.Kannada,
|
||||
UnicodeBlock.Malayalam,
|
||||
UnicodeBlock.Sinhala,
|
||||
UnicodeBlock.Thai,
|
||||
UnicodeBlock.Lao,
|
||||
UnicodeBlock.Tibetan,
|
||||
UnicodeBlock.Myanmar,
|
||||
UnicodeBlock.Georgian,
|
||||
UnicodeBlock.HangulJamo,
|
||||
UnicodeBlock.Ethiopic,
|
||||
null,
|
||||
UnicodeBlock.Cherokee,
|
||||
UnicodeBlock.UnifiedCanadianAboriginalSyllabics,
|
||||
UnicodeBlock.Ogham,
|
||||
UnicodeBlock.Runic,
|
||||
UnicodeBlock.Tagalog,
|
||||
UnicodeBlock.Hanunoo,
|
||||
UnicodeBlock.Buhid,
|
||||
UnicodeBlock.Tagbanwa,
|
||||
UnicodeBlock.Khmer,
|
||||
UnicodeBlock.Mongolian,
|
||||
null,
|
||||
UnicodeBlock.Limbu,
|
||||
UnicodeBlock.TaiLe,
|
||||
null,
|
||||
UnicodeBlock.KhmerSymbols,
|
||||
null,
|
||||
UnicodeBlock.PhoneticExtensions,
|
||||
null,
|
||||
UnicodeBlock.LatinExtendedAdditional,
|
||||
UnicodeBlock.GreekExtended,
|
||||
UnicodeBlock.GeneralPunctuation,
|
||||
UnicodeBlock.SuperscriptsAndSubscripts,
|
||||
UnicodeBlock.CurrencySymbols,
|
||||
UnicodeBlock.CombiningMarksForSymbols,
|
||||
UnicodeBlock.LetterlikeSymbols,
|
||||
UnicodeBlock.NumberForms,
|
||||
UnicodeBlock.Arrows,
|
||||
UnicodeBlock.MathematicalOperators,
|
||||
UnicodeBlock.MiscellaneousTechnical,
|
||||
UnicodeBlock.ControlPictures,
|
||||
UnicodeBlock.OpticalCharacterRecognition,
|
||||
UnicodeBlock.EnclosedAlphanumerics,
|
||||
UnicodeBlock.BoxDrawing,
|
||||
UnicodeBlock.BlockElements,
|
||||
UnicodeBlock.GeometricShapes,
|
||||
UnicodeBlock.MiscellaneousSymbols,
|
||||
UnicodeBlock.Dingbats,
|
||||
UnicodeBlock.MiscellaneousMathematicalSymbolsA,
|
||||
UnicodeBlock.SupplementalArrowsA,
|
||||
UnicodeBlock.BraillePatterns,
|
||||
UnicodeBlock.SupplementalArrowsB,
|
||||
UnicodeBlock.MiscellaneousMathematicalSymbolsB,
|
||||
UnicodeBlock.SupplementalMathematicalOperators,
|
||||
UnicodeBlock.MiscellaneousSymbolsAndArrows,
|
||||
null,
|
||||
UnicodeBlock.CjkRadicalsSupplement,
|
||||
UnicodeBlock.KangxiRadicals,
|
||||
null,
|
||||
UnicodeBlock.IdeographicDescriptionCharacters,
|
||||
UnicodeBlock.CjkSymbolsAndPunctuation,
|
||||
UnicodeBlock.Hiragana,
|
||||
UnicodeBlock.Katakana,
|
||||
UnicodeBlock.Bopomofo,
|
||||
UnicodeBlock.HangulCompatibilityJamo,
|
||||
UnicodeBlock.Kanbun,
|
||||
UnicodeBlock.BopomofoExtended,
|
||||
null,
|
||||
UnicodeBlock.KatakanaPhoneticExtensions,
|
||||
UnicodeBlock.EnclosedCjkLettersAndMonths,
|
||||
UnicodeBlock.CjkCompatibility,
|
||||
UnicodeBlock.CjkUnifiedIdeographsExtensionA,
|
||||
UnicodeBlock.YijingHexagramSymbols,
|
||||
UnicodeBlock.CjkUnifiedIdeographs,
|
||||
UnicodeBlock.YiSyllables,
|
||||
UnicodeBlock.YiRadicals,
|
||||
null,
|
||||
UnicodeBlock.HangulSyllables,
|
||||
null,
|
||||
UnicodeBlock.HighSurrogates,
|
||||
UnicodeBlock.HighPrivateUseSurrogates,
|
||||
UnicodeBlock.LowSurrogates,
|
||||
UnicodeBlock.PrivateUseArea,
|
||||
UnicodeBlock.CjkCompatibilityIdeographs,
|
||||
UnicodeBlock.AlphabeticPresentationForms,
|
||||
UnicodeBlock.ArabicPresentationFormsA,
|
||||
UnicodeBlock.VariationSelectors,
|
||||
null,
|
||||
UnicodeBlock.CombiningHalfMarks,
|
||||
UnicodeBlock.CjkCompatibilityForms,
|
||||
UnicodeBlock.SmallFormVariants,
|
||||
UnicodeBlock.ArabicPresentationFormsB,
|
||||
UnicodeBlock.HalfwidthAndFullwidthForms,
|
||||
UnicodeBlock.Specials,
|
||||
UnicodeBlock.LinearBSyllabary,
|
||||
UnicodeBlock.LinearBIdeograms,
|
||||
UnicodeBlock.AegeanNumbers,
|
||||
null,
|
||||
UnicodeBlock.OldItalic,
|
||||
UnicodeBlock.Gothic,
|
||||
null,
|
||||
UnicodeBlock.Ugaritic,
|
||||
null,
|
||||
UnicodeBlock.Deseret,
|
||||
UnicodeBlock.Shavian,
|
||||
UnicodeBlock.Osmanya,
|
||||
null,
|
||||
UnicodeBlock.CypriotSyllabary,
|
||||
null,
|
||||
UnicodeBlock.ByzantineMusicalSymbols,
|
||||
UnicodeBlock.MusicalSymbols,
|
||||
null,
|
||||
UnicodeBlock.TaiXuanJingSymbols,
|
||||
null,
|
||||
UnicodeBlock.MathematicalAlphanumericSymbols,
|
||||
null,
|
||||
UnicodeBlock.CjkUnifiedIdeographsExtensionB,
|
||||
null,
|
||||
UnicodeBlock.CjkCompatibilityIdeographsSupplement,
|
||||
null,
|
||||
UnicodeBlock.Tags,
|
||||
null,
|
||||
UnicodeBlock.VariationSelectorsSupplement,
|
||||
null,
|
||||
UnicodeBlock.SupplementaryPrivateUseAreaA,
|
||||
UnicodeBlock.SupplementaryPrivateUseAreaB,
|
||||
|
||||
#endregion
|
||||
};
|
||||
|
||||
#region Public methods
|
||||
|
||||
/// <remarks>
|
||||
/// Taken from JDK source: http://grepcode.com/file/repository.grepcode.com/java/root/jdk/openjdk/6-b14/java/lang/Character.java#Character.UnicodeBlock.0LATIN_EXTENDED_ADDITIONAL
|
||||
/// </remarks>
|
||||
public static UnicodeBlock? GetUnicodeBlock(this char ch)
|
||||
{
|
||||
int codePoint = ch;
|
||||
|
||||
if (!IsValidCodePoint(codePoint))
|
||||
{
|
||||
throw new ArgumentException("Argument is not a valid code point.", nameof(ch));
|
||||
}
|
||||
|
||||
int top, bottom, current;
|
||||
|
||||
bottom = 0;
|
||||
top = _unicodeBlockStarts.Length;
|
||||
current = top / 2;
|
||||
|
||||
// invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom]
|
||||
while (top - bottom > 1)
|
||||
{
|
||||
if (codePoint >= _unicodeBlockStarts[current])
|
||||
{
|
||||
bottom = current;
|
||||
}
|
||||
else
|
||||
{
|
||||
top = current;
|
||||
}
|
||||
|
||||
current = (top + bottom) / 2;
|
||||
}
|
||||
|
||||
return _unicodeBlocks[current];
|
||||
}
|
||||
|
||||
#endregion
|
||||
|
||||
#region Private helper methods
|
||||
|
||||
private static bool IsValidCodePoint(int codePoint)
|
||||
{
|
||||
return codePoint >= MIN_CODE_POINT && codePoint <= MAX_CODE_POINT;
|
||||
}
|
||||
|
||||
#endregion
|
||||
}
|
||||
}
|
||||
@ -1,51 +0,0 @@
|
||||
using System;
|
||||
|
||||
namespace NLangDetect.Core.Extensions
|
||||
{
|
||||
public static class RandomExtensions
|
||||
{
|
||||
private const double _Epsilon = 2.22044604925031E-15;
|
||||
|
||||
private static readonly object _mutex = new object();
|
||||
|
||||
private static double _nextNextGaussian;
|
||||
private static bool _hasNextNextGaussian;
|
||||
|
||||
/// <summary>
|
||||
/// Returns the next pseudorandom, Gaussian ("normally") distributed double value with mean 0.0 and standard deviation 1.0 from this random number generator's sequence.
|
||||
/// The general contract of nextGaussian is that one double value, chosen from (approximately) the usual normal distribution with mean 0.0 and standard deviation 1.0, is pseudorandomly generated and returned.
|
||||
/// </summary>
|
||||
/// <remarks>
|
||||
/// Taken from: http://download.oracle.com/javase/6/docs/api/java/util/Random.html (nextGaussian())
|
||||
/// </remarks>
|
||||
public static double NextGaussian(this Random random)
|
||||
{
|
||||
lock (_mutex)
|
||||
{
|
||||
if (_hasNextNextGaussian)
|
||||
{
|
||||
_hasNextNextGaussian = false;
|
||||
|
||||
return _nextNextGaussian;
|
||||
}
|
||||
|
||||
double v1, v2, s;
|
||||
|
||||
do
|
||||
{
|
||||
v1 = 2.0 * random.NextDouble() - 1.0; // between -1.0 and 1.0
|
||||
v2 = 2.0 * random.NextDouble() - 1.0; // between -1.0 and 1.0
|
||||
s = v1 * v1 + v2 * v2;
|
||||
}
|
||||
while (s >= 1.0 || Math.Abs(s - 0.0) < _Epsilon);
|
||||
|
||||
double multiplier = Math.Sqrt(-2.0 * Math.Log(s) / s);
|
||||
|
||||
_nextNextGaussian = v2 * multiplier;
|
||||
_hasNextNextGaussian = true;
|
||||
|
||||
return v1 * multiplier;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -1,25 +0,0 @@
|
||||
using System;
|
||||
|
||||
namespace NLangDetect.Core.Extensions
|
||||
{
|
||||
public static class StringExtensions
|
||||
{
|
||||
/// <summary>
|
||||
/// Returns a new character sequence that is a subsequence of this sequence. The subsequence starts with the character at the specified index and ends with the character at index end - 1. The length of the returned sequence is end - start, so if start == end then an empty sequence is returned.
|
||||
/// </summary>
|
||||
/// <param name="s"></param>
|
||||
/// <param name="start">the start index, inclusive</param>
|
||||
/// <param name="end">the end index, exclusive</param>
|
||||
/// <returns>the specified subsequence</returns>
|
||||
/// <exception cref="IndexOutOfRangeException"> if start or end are negative, if end is greater than length(), or if start is greater than end</exception>
|
||||
public static string SubSequence(this string s, int start, int end)
|
||||
{
|
||||
if (start < 0) throw new ArgumentOutOfRangeException(nameof(start), "Argument must not be negative.");
|
||||
if (end < 0) throw new ArgumentOutOfRangeException(nameof(end), "Argument must not be negative.");
|
||||
if (end > s.Length) throw new ArgumentOutOfRangeException(nameof(end), "Argument must not be greater than the input string's length.");
|
||||
if (start > end) throw new ArgumentOutOfRangeException(nameof(start), "Argument must not be greater than the 'end' argument.");
|
||||
|
||||
return s.Substring(start, end - start);
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -1,131 +0,0 @@
|
||||
namespace NLangDetect.Core.Extensions
|
||||
{
|
||||
public enum UnicodeBlock
|
||||
{
|
||||
BasicLatin,
|
||||
Latin1Supplement,
|
||||
LatinExtendedA,
|
||||
LatinExtendedB,
|
||||
IpaExtensions,
|
||||
SpacingModifierLetters,
|
||||
CombiningDiacriticalMarks,
|
||||
Greek,
|
||||
Cyrillic,
|
||||
CyrillicSupplementary,
|
||||
Armenian,
|
||||
Hebrew,
|
||||
Arabic,
|
||||
Syriac,
|
||||
Thaana,
|
||||
Devanagari,
|
||||
Bengali,
|
||||
Gurmukhi,
|
||||
Gujarati,
|
||||
Oriya,
|
||||
Tamil,
|
||||
Telugu,
|
||||
Kannada,
|
||||
Malayalam,
|
||||
Sinhala,
|
||||
Thai,
|
||||
Lao,
|
||||
Tibetan,
|
||||
Myanmar,
|
||||
Georgian,
|
||||
HangulJamo,
|
||||
Ethiopic,
|
||||
Cherokee,
|
||||
UnifiedCanadianAboriginalSyllabics,
|
||||
Ogham,
|
||||
Runic,
|
||||
Tagalog,
|
||||
Hanunoo,
|
||||
Buhid,
|
||||
Tagbanwa,
|
||||
Khmer,
|
||||
Mongolian,
|
||||
Limbu,
|
||||
TaiLe,
|
||||
KhmerSymbols,
|
||||
PhoneticExtensions,
|
||||
LatinExtendedAdditional,
|
||||
GreekExtended,
|
||||
GeneralPunctuation,
|
||||
SuperscriptsAndSubscripts,
|
||||
CurrencySymbols,
|
||||
CombiningMarksForSymbols,
|
||||
LetterlikeSymbols,
|
||||
NumberForms,
|
||||
Arrows,
|
||||
MathematicalOperators,
|
||||
MiscellaneousTechnical,
|
||||
ControlPictures,
|
||||
OpticalCharacterRecognition,
|
||||
EnclosedAlphanumerics,
|
||||
BoxDrawing,
|
||||
BlockElements,
|
||||
GeometricShapes,
|
||||
MiscellaneousSymbols,
|
||||
Dingbats,
|
||||
MiscellaneousMathematicalSymbolsA,
|
||||
SupplementalArrowsA,
|
||||
BraillePatterns,
|
||||
SupplementalArrowsB,
|
||||
MiscellaneousMathematicalSymbolsB,
|
||||
SupplementalMathematicalOperators,
|
||||
MiscellaneousSymbolsAndArrows,
|
||||
CjkRadicalsSupplement,
|
||||
KangxiRadicals,
|
||||
IdeographicDescriptionCharacters,
|
||||
CjkSymbolsAndPunctuation,
|
||||
Hiragana,
|
||||
Katakana,
|
||||
Bopomofo,
|
||||
HangulCompatibilityJamo,
|
||||
Kanbun,
|
||||
BopomofoExtended,
|
||||
KatakanaPhoneticExtensions,
|
||||
EnclosedCjkLettersAndMonths,
|
||||
CjkCompatibility,
|
||||
CjkUnifiedIdeographsExtensionA,
|
||||
YijingHexagramSymbols,
|
||||
CjkUnifiedIdeographs,
|
||||
YiSyllables,
|
||||
YiRadicals,
|
||||
HangulSyllables,
|
||||
HighSurrogates,
|
||||
HighPrivateUseSurrogates,
|
||||
LowSurrogates,
|
||||
PrivateUseArea,
|
||||
CjkCompatibilityIdeographs,
|
||||
AlphabeticPresentationForms,
|
||||
ArabicPresentationFormsA,
|
||||
VariationSelectors,
|
||||
CombiningHalfMarks,
|
||||
CjkCompatibilityForms,
|
||||
SmallFormVariants,
|
||||
ArabicPresentationFormsB,
|
||||
HalfwidthAndFullwidthForms,
|
||||
Specials,
|
||||
LinearBSyllabary,
|
||||
LinearBIdeograms,
|
||||
AegeanNumbers,
|
||||
OldItalic,
|
||||
Gothic,
|
||||
Ugaritic,
|
||||
Deseret,
|
||||
Shavian,
|
||||
Osmanya,
|
||||
CypriotSyllabary,
|
||||
ByzantineMusicalSymbols,
|
||||
MusicalSymbols,
|
||||
TaiXuanJingSymbols,
|
||||
MathematicalAlphanumericSymbols,
|
||||
CjkUnifiedIdeographsExtensionB,
|
||||
CjkCompatibilityIdeographsSupplement,
|
||||
Tags,
|
||||
VariationSelectorsSupplement,
|
||||
SupplementaryPrivateUseAreaA,
|
||||
SupplementaryPrivateUseAreaB,
|
||||
}
|
||||
}
|
||||
@ -1,67 +0,0 @@
|
||||
using System;
|
||||
using System.IO;
|
||||
using System.IO.Compression;
|
||||
using System.Xml;
|
||||
using NLangDetect.Core.Utils;
|
||||
|
||||
namespace NLangDetect.Core
|
||||
{
|
||||
// TODO IMM HI: xml reader not tested
|
||||
public static class GenProfile
|
||||
{
|
||||
#region Public methods
|
||||
|
||||
public static LangProfile load(string lang, string file)
|
||||
{
|
||||
var profile = new LangProfile(lang);
|
||||
var tagextractor = new TagExtractor("abstract", 100);
|
||||
Stream inputStream = null;
|
||||
|
||||
try
|
||||
{
|
||||
inputStream = File.OpenRead(file);
|
||||
|
||||
string extension = Path.GetExtension(file) ?? "";
|
||||
|
||||
if (extension.ToUpper() == ".GZ")
|
||||
{
|
||||
inputStream = new GZipStream(inputStream, CompressionMode.Decompress);
|
||||
}
|
||||
|
||||
using (var xmlReader = XmlReader.Create(inputStream))
|
||||
{
|
||||
while (xmlReader.Read())
|
||||
{
|
||||
switch (xmlReader.NodeType)
|
||||
{
|
||||
case XmlNodeType.Element:
|
||||
tagextractor.SetTag(xmlReader.Name);
|
||||
break;
|
||||
|
||||
case XmlNodeType.Text:
|
||||
tagextractor.Add(xmlReader.Value);
|
||||
break;
|
||||
|
||||
case XmlNodeType.EndElement:
|
||||
tagextractor.CloseTag(profile);
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
finally
|
||||
{
|
||||
if (inputStream != null)
|
||||
{
|
||||
inputStream.Close();
|
||||
}
|
||||
}
|
||||
|
||||
Console.WriteLine(lang + ": " + tagextractor.Count);
|
||||
|
||||
return profile;
|
||||
}
|
||||
|
||||
#endregion
|
||||
}
|
||||
}
|
||||
@ -1,22 +0,0 @@
|
||||
using System;
|
||||
|
||||
namespace NLangDetect.Core
|
||||
{
|
||||
[Serializable]
|
||||
public class InternalException : Exception
|
||||
{
|
||||
#region Constructor(s)
|
||||
|
||||
public InternalException(string message, Exception innerException)
|
||||
: base(message, innerException)
|
||||
{
|
||||
}
|
||||
|
||||
public InternalException(string message)
|
||||
: this(message, null)
|
||||
{
|
||||
}
|
||||
|
||||
#endregion
|
||||
}
|
||||
}
|
||||
@ -1,45 +0,0 @@
|
||||
using System.Globalization;
|
||||
|
||||
namespace NLangDetect.Core
|
||||
{
|
||||
// TODO IMM HI: name??
|
||||
public class Language
|
||||
{
|
||||
#region Constructor(s)
|
||||
|
||||
public Language(string name, double probability)
|
||||
{
|
||||
Name = name;
|
||||
Probability = probability;
|
||||
}
|
||||
|
||||
#endregion
|
||||
|
||||
#region Object overrides
|
||||
|
||||
public override string ToString()
|
||||
{
|
||||
if (Name == null)
|
||||
{
|
||||
return "";
|
||||
}
|
||||
|
||||
return
|
||||
string.Format(
|
||||
CultureInfo.InvariantCulture.NumberFormat,
|
||||
"{0}:{1:0.000000}",
|
||||
Name,
|
||||
Probability);
|
||||
}
|
||||
|
||||
#endregion
|
||||
|
||||
#region Properties
|
||||
|
||||
public string Name { get; set; }
|
||||
|
||||
public double Probability { get; set; }
|
||||
|
||||
#endregion
|
||||
}
|
||||
}
|
||||
@ -1,37 +0,0 @@
|
||||
using System;
|
||||
using MediaBrowser.Model.Serialization;
|
||||
|
||||
namespace NLangDetect.Core
|
||||
{
|
||||
// TODO IMM HI: change to non-static class
|
||||
// TODO IMM HI: hide other, unnecassary classes via internal?
|
||||
public static class LanguageDetector
|
||||
{
|
||||
private const double _DefaultAlpha = 0.5;
|
||||
|
||||
#region Public methods
|
||||
|
||||
public static void Initialize(IJsonSerializer json)
|
||||
{
|
||||
DetectorFactory.LoadProfiles(json);
|
||||
}
|
||||
|
||||
public static void Release()
|
||||
{
|
||||
DetectorFactory.Clear();
|
||||
}
|
||||
|
||||
public static string DetectLanguage(string plainText)
|
||||
{
|
||||
if (string.IsNullOrEmpty(plainText)) { throw new ArgumentException("Argument can't be null nor empty.", nameof(plainText)); }
|
||||
|
||||
var detector = DetectorFactory.Create(_DefaultAlpha);
|
||||
|
||||
detector.Append(plainText);
|
||||
|
||||
return detector.Detect();
|
||||
}
|
||||
|
||||
#endregion
|
||||
}
|
||||
}
|
||||
@ -1,23 +0,0 @@
|
||||
using System;
|
||||
|
||||
namespace NLangDetect.Core
|
||||
{
|
||||
public class NLangDetectException : Exception
|
||||
{
|
||||
#region Constructor(s)
|
||||
|
||||
public NLangDetectException(string message, ErrorCode errorCode)
|
||||
: base(message)
|
||||
{
|
||||
ErrorCode = errorCode;
|
||||
}
|
||||
|
||||
#endregion
|
||||
|
||||
#region Properties
|
||||
|
||||
public ErrorCode ErrorCode { get; private set; }
|
||||
|
||||
#endregion
|
||||
}
|
||||
}
|
||||
@ -1,33 +0,0 @@
|
||||
using System;
|
||||
using System.Collections.Generic;
|
||||
|
||||
namespace NLangDetect.Core
|
||||
{
|
||||
public class ProbVector
|
||||
{
|
||||
private readonly Dictionary<int, double> _dict = new Dictionary<int, double>();
|
||||
|
||||
public double this[int key]
|
||||
{
|
||||
get
|
||||
{
|
||||
return _dict.TryGetValue(key, out var value) ? value : 0.0;
|
||||
}
|
||||
|
||||
set
|
||||
{
|
||||
if (Math.Abs(value) < double.Epsilon)
|
||||
{
|
||||
if (_dict.ContainsKey(key))
|
||||
{
|
||||
_dict.Remove(key);
|
||||
}
|
||||
|
||||
return;
|
||||
}
|
||||
|
||||
_dict[key] = value;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in new issue