open-source-mirrors
/
DiscordChatExporter
mirror of https://github.com/Tyrrrz/DiscordChatExporter
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Rename `TitleLinkNodeMatcher` to `MaskedLinkNodeMatcher` to align with Discord's own terminology

Browse Source
pull/1032/head
Tyrrrz 1 year ago
parent a9fc439cc5
commit ab933a7240
1 changed files with 58 additions and 60 deletions
Show Stats Download Patch File Download Diff File

118
DiscordChatExporter.Core/Markdown/Parsing/MarkdownParser.cs
Unescape View File

@ -24,41 +24,41 @@ internal static partial class MarkdownParser
/* Formatting */
private static readonly IMatcher<MarkdownNode> BoldFormattingNodeMatcher = new RegexMatcher<MarkdownNode>(
// Capture any character until the earliest double asterisk not followed by an asterisk
// Capture any character until the earliest double asterisk not followed by an asterisk.
new Regex(@"\*\*(.+?)\*\*(?!\*)", DefaultRegexOptions | RegexOptions.Singleline),
(s, m) => new FormattingNode(FormattingKind.Bold, Parse(s.Relocate(m.Groups[1])))
);
private static readonly IMatcher<MarkdownNode> ItalicFormattingNodeMatcher = new RegexMatcher<MarkdownNode>(
// Capture any character until the earliest single asterisk not preceded or followed by an asterisk
// Opening asterisk must not be followed by whitespace
// Closing asterisk must not be preceded by whitespace
// Capture any character until the earliest single asterisk not preceded or followed by an asterisk.
// Opening asterisk must not be followed by whitespace.
// Closing asterisk must not be preceded by whitespace.
new Regex(@"\*(?!\s)(.+?)(?<!\s|\*)\*(?!\*)", DefaultRegexOptions | RegexOptions.Singleline),
(s, m) => new FormattingNode(FormattingKind.Italic, Parse(s.Relocate(m.Groups[1])))
);
private static readonly IMatcher<MarkdownNode> ItalicBoldFormattingNodeMatcher = new RegexMatcher<MarkdownNode>(
// Capture any character until the earliest triple asterisk not followed by an asterisk
// Capture any character until the earliest triple asterisk not followed by an asterisk.
new Regex(@"\*(\*\*.+?\*\*)\*(?!\*)", DefaultRegexOptions | RegexOptions.Singleline),
(s, m) => new FormattingNode(FormattingKind.Italic, Parse(s.Relocate(m.Groups[1]), BoldFormattingNodeMatcher))
);
private static readonly IMatcher<MarkdownNode> ItalicAltFormattingNodeMatcher = new RegexMatcher<MarkdownNode>(
// Capture any character except underscore until an underscore
// Closing underscore must not be followed by a word character
// Capture any character except underscore until an underscore.
// Closing underscore must not be followed by a word character.
new Regex(@"_([^_]+)_(?!\w)", DefaultRegexOptions | RegexOptions.Singleline),
(s, m) => new FormattingNode(FormattingKind.Italic, Parse(s.Relocate(m.Groups[1])))
);
private static readonly IMatcher<MarkdownNode> UnderlineFormattingNodeMatcher = new RegexMatcher<MarkdownNode>(
// Capture any character until the earliest double underscore not followed by an underscore
// Capture any character until the earliest double underscore not followed by an underscore.
new Regex(@"__(.+?)__(?!_)", DefaultRegexOptions | RegexOptions.Singleline),
(s, m) => new FormattingNode(FormattingKind.Underline, Parse(s.Relocate(m.Groups[1])))
);
private static readonly IMatcher<MarkdownNode> ItalicUnderlineFormattingNodeMatcher =
new RegexMatcher<MarkdownNode>(
// Capture any character until the earliest triple underscore not followed by an underscore
// Capture any character until the earliest triple underscore not followed by an underscore.
new Regex(@"_(__.+?__)_(?!_)", DefaultRegexOptions | RegexOptions.Singleline),
(s, m) => new FormattingNode(
FormattingKind.Italic,
@ -66,44 +66,42 @@ internal static partial class MarkdownParser
)
);
private static readonly IMatcher<MarkdownNode> StrikethroughFormattingNodeMatcher =
new RegexMatcher<MarkdownNode>(
// Capture any character until the earliest double tilde
new Regex(@"~~(.+?)~~", DefaultRegexOptions | RegexOptions.Singleline),
(s, m) => new FormattingNode(FormattingKind.Strikethrough, Parse(s.Relocate(m.Groups[1])))
);
private static readonly IMatcher<MarkdownNode> StrikethroughFormattingNodeMatcher = new RegexMatcher<MarkdownNode>(
// Capture any character until the earliest double tilde.
new Regex(@"~~(.+?)~~", DefaultRegexOptions | RegexOptions.Singleline),
(s, m) => new FormattingNode(FormattingKind.Strikethrough, Parse(s.Relocate(m.Groups[1])))
);
private static readonly IMatcher<MarkdownNode> SpoilerFormattingNodeMatcher = new RegexMatcher<MarkdownNode>(
// Capture any character until the earliest double pipe
// Capture any character until the earliest double pipe.
new Regex(@"\|\|(.+?)\|\|", DefaultRegexOptions | RegexOptions.Singleline),
(s, m) => new FormattingNode(FormattingKind.Spoiler, Parse(s.Relocate(m.Groups[1])))
);
private static readonly IMatcher<MarkdownNode> SingleLineQuoteNodeMatcher = new RegexMatcher<MarkdownNode>(
// Capture any character until the end of the line
// Opening 'greater than' character must be followed by whitespace
// Text content is optional
// Capture any character until the end of the line.
// Opening 'greater than' character must be followed by whitespace.
// Text content is optional.
new Regex(@"^>\s(.*\n?)", DefaultRegexOptions),
(s, m) => new FormattingNode(FormattingKind.Quote, Parse(s.Relocate(m.Groups[1])))
);
private static readonly IMatcher<MarkdownNode> RepeatedSingleLineQuoteNodeMatcher =
new RegexMatcher<MarkdownNode>(
// Repeatedly capture any character until the end of the line
// This one is tricky as it ends up producing multiple separate captures which need to be joined
new Regex(@"(?:^>\s(.*\n?)){2,}", DefaultRegexOptions),
(_, m) => new FormattingNode(
FormattingKind.Quote,
Parse(
// Combine all captures into a single string
string.Concat(m.Groups[1].Captures.Select(c => c.Value))
)
private static readonly IMatcher<MarkdownNode> RepeatedSingleLineQuoteNodeMatcher = new RegexMatcher<MarkdownNode>(
// Repeatedly capture any character until the end of the line.
// This one is tricky as it ends up producing multiple separate captures which need to be joined.
new Regex(@"(?:^>\s(.*\n?)){2,}", DefaultRegexOptions),
(_, m) => new FormattingNode(
FormattingKind.Quote,
Parse(
// Combine all captures into a single string
string.Concat(m.Groups[1].Captures.Select(c => c.Value))
)
);
)
);
private static readonly IMatcher<MarkdownNode> MultiLineQuoteNodeMatcher = new RegexMatcher<MarkdownNode>(
// Capture any character until the end of the input
// Opening 'greater than' characters must be followed by whitespace
// Capture any character until the end of the input.
// Opening 'greater than' characters must be followed by whitespace.
new Regex(@"^>>>\s(.+)", DefaultRegexOptions | RegexOptions.Singleline),
(s, m) => new FormattingNode(FormattingKind.Quote, Parse(s.Relocate(m.Groups[1])))
);
@ -111,17 +109,17 @@ internal static partial class MarkdownParser
/* Code blocks */
private static readonly IMatcher<MarkdownNode> InlineCodeBlockNodeMatcher = new RegexMatcher<MarkdownNode>(
// Capture any character except backtick until a backtick
// Blank lines at the beginning and end of content are trimmed
// There can be either one or two backticks, but equal number on both sides
// Capture any character except backtick until a backtick.
// Blank lines at the beginning and at the end of content are trimmed.
// There can be either one or two backticks, but equal number on both sides.
new Regex(@"(`{1,2})([^`]+)\1", DefaultRegexOptions | RegexOptions.Singleline),
(_, m) => new InlineCodeBlockNode(m.Groups[2].Value.Trim('\r', '\n'))
);
private static readonly IMatcher<MarkdownNode> MultiLineCodeBlockNodeMatcher = new RegexMatcher<MarkdownNode>(
// Capture language identifier and then any character until the earliest triple backtick
// Language identifier is one word immediately after opening backticks, followed immediately by newline
// Blank lines at the beginning and end of content are trimmed
// Capture language identifier and then any character until the earliest triple backtick.
// Language identifier is one word immediately after opening backticks, followed immediately by newline.
// Blank lines at the beginning and at the end of content are trimmed.
new Regex(@"```(?:(\w*)\n)?(.+?)```", DefaultRegexOptions | RegexOptions.Singleline),
(_, m) => new MultiLineCodeBlockNode(m.Groups[1].Value, m.Groups[2].Value.Trim('\r', '\n'))
);
@ -224,12 +222,6 @@ internal static partial class MarkdownParser
/* Links */
private static readonly IMatcher<MarkdownNode> TitledLinkNodeMatcher = new RegexMatcher<MarkdownNode>(
// Capture [title](link)
new Regex(@"\[(.+?)\]\((.+?)\)", DefaultRegexOptions),
(s, m) => new LinkNode(m.Groups[2].Value, Parse(s.Relocate(m.Groups[1])))
);
private static readonly IMatcher<MarkdownNode> AutoLinkNodeMatcher = new RegexMatcher<MarkdownNode>(
// Capture any non-whitespace character after http:// or https://
// until the last punctuation character or whitespace
@ -243,32 +235,38 @@ internal static partial class MarkdownParser
(_, m) => new LinkNode(m.Groups[1].Value)
);
private static readonly IMatcher<MarkdownNode> MaskedLinkNodeMatcher = new RegexMatcher<MarkdownNode>(
// Capture [title](link)
new Regex(@"\[(.+?)\]\((.+?)\)", DefaultRegexOptions),
(s, m) => new LinkNode(m.Groups[2].Value, Parse(s.Relocate(m.Groups[1])))
);
/* Text */
private static readonly IMatcher<MarkdownNode> ShrugTextNodeMatcher = new StringMatcher<MarkdownNode>(
// Capture the shrug kaomoji
// This escapes it from matching for formatting
// Capture the shrug kaomoji.
// This escapes it from matching for formatting.
@"¯\_(ツ)_/¯",
s => new TextNode(s.ToString())
);
private static readonly IMatcher<MarkdownNode> IgnoredEmojiTextNodeMatcher = new RegexMatcher<MarkdownNode>(
// Capture some specific emoji that don't get rendered
// This escapes it from matching for emoji
// Capture some specific emoji that don't get rendered.
// This escapes them from matching for emoji.
new Regex(@"([\u26A7\u2640\u2642\u2695\u267E\u00A9\u00AE\u2122])", DefaultRegexOptions),
(_, m) => new TextNode(m.Groups[1].Value)
);
private static readonly IMatcher<MarkdownNode> EscapedSymbolTextNodeMatcher = new RegexMatcher<MarkdownNode>(
// Capture any "symbol/other" character or surrogate pair preceded by a backslash
// This escapes it from matching for emoji
// Capture any "symbol/other" character or surrogate pair preceded by a backslash.
// This escapes them from matching for emoji.
new Regex(@"\\(\p{So}|\p{Cs}{2})", DefaultRegexOptions),
(_, m) => new TextNode(m.Groups[1].Value)
);
private static readonly IMatcher<MarkdownNode> EscapedCharacterTextNodeMatcher = new RegexMatcher<MarkdownNode>(
// Capture any non-whitespace, non latin alphanumeric character preceded by a backslash
// This escapes it from matching for formatting or other tokens
// Capture any non-whitespace, non latin alphanumeric character preceded by a backslash.
// This escapes them from matching for formatting or other tokens.
new Regex(@"\\([^a-zA-Z0-9\s])", DefaultRegexOptions),
(_, m) => new TextNode(m.Groups[1].Value)
);
@ -310,9 +308,9 @@ internal static partial class MarkdownParser
}
);
// Combine all matchers into one
// Matchers that have similar patterns are ordered from most specific to least specific
private static readonly IMatcher<MarkdownNode> AggregateNodeMatcher = new AggregateMatcher<MarkdownNode>(
// Combine all matchers into one.
// Matchers that have similar patterns are ordered from most specific to least specific.
private static readonly IMatcher<MarkdownNode> NodeMatcher = new AggregateMatcher<MarkdownNode>(
// Escaped text
ShrugTextNodeMatcher,
IgnoredEmojiTextNodeMatcher,
@ -344,7 +342,7 @@ internal static partial class MarkdownParser
RoleMentionNodeMatcher,
// Links
TitledLinkNodeMatcher,
MaskedLinkNodeMatcher,
AutoLinkNodeMatcher,
HiddenLinkNodeMatcher,
@ -358,7 +356,7 @@ internal static partial class MarkdownParser
);
// Minimal set of matchers for non-multimedia formats (e.g. plain text)
private static readonly IMatcher<MarkdownNode> MinimalAggregateNodeMatcher = new AggregateMatcher<MarkdownNode>(
private static readonly IMatcher<MarkdownNode> MinimalNodeMatcher = new AggregateMatcher<MarkdownNode>(
// Mentions
EveryoneMentionNodeMatcher,
HereMentionNodeMatcher,
@ -383,13 +381,13 @@ internal static partial class MarkdownParser
internal static partial class MarkdownParser
{
private static IReadOnlyList<MarkdownNode> Parse(StringSegment segment) =>
Parse(segment, AggregateNodeMatcher);
Parse(segment, NodeMatcher);
public static IReadOnlyList<MarkdownNode> Parse(string markdown) =>
Parse(new StringSegment(markdown));
private static IReadOnlyList<MarkdownNode> ParseMinimal(StringSegment segment) =>
Parse(segment, MinimalAggregateNodeMatcher);
Parse(segment, MinimalNodeMatcher);
public static IReadOnlyList<MarkdownNode> ParseMinimal(string markdown) =>
ParseMinimal(new StringSegment(markdown));

Write Preview
Loading…
Cancel
Save