diff options
Diffstat (limited to 'pygments/lexers/markup.py')
| -rw-r--r-- | pygments/lexers/markup.py | 50 |
1 files changed, 27 insertions, 23 deletions
diff --git a/pygments/lexers/markup.py b/pygments/lexers/markup.py index 6f7da3fc..5e6b6635 100644 --- a/pygments/lexers/markup.py +++ b/pygments/lexers/markup.py @@ -204,7 +204,7 @@ class RstLexer(RegexLexer): bygroups(Text, Operator, using(this, state='inline'))), # Sourcecode directives (r'^( *\.\.)(\s*)((?:source)?code(?:-block)?)(::)([ \t]*)([^\n]+)' - r'(\n[ \t]*\n)([ \t]+)(.*)(\n)((?:(?:\8.*|)\n)+)', + r'(\n[ \t]*\n)([ \t]+)(.*)(\n)((?:(?:\8.*)?\n)+)', _handle_sourcecode), # A directive (r'^( *\.\.)(\s*)([\w:-]+?)(::)(?:([ \t]*)(.*))', @@ -229,7 +229,7 @@ class RstLexer(RegexLexer): (r'^(\S.*(?<!::)\n)((?:(?: +.*)\n)+)', bygroups(using(this, state='inline'), using(this, state='inline'))), # Code blocks - (r'(::)(\n[ \t]*\n)([ \t]+)(.*)(\n)((?:(?:\3.*|)\n)+)', + (r'(::)(\n[ \t]*\n)([ \t]+)(.*)(\n)((?:(?:\3.*)?\n)+)', bygroups(String.Escape, Text, String, String, Text, String)), include('inline'), ], @@ -579,24 +579,27 @@ class MarkdownLexer(RegexLexer): # warning: the following rules eat outer tags. # eg. **foo _bar_ baz** => foo and baz are not recognized as bold # bold fenced by '**' - (r'(\*\*[^\*\n\ ][^\*\n]*\*\*)', bygroups(Generic.Strong)), + (r'(\*\*[^* \n][^*\n]*\*\*)', bygroups(Generic.Strong)), # # bold fenced by '__' - (r'(\_\_[^\_\n\ ][^\_\n]*\_\_)', bygroups(Generic.Strong)), + (r'(\_\_[^_ \n][^_\n]*\_\_)', bygroups(Generic.Strong)), # italics fenced by '*' - (r'(\*[^\*\n\ ][^\*\n]*\*)', bygroups(Generic.Emph)), + (r'(\*[^* \n][^*\n]*\*)', bygroups(Generic.Emph)), # italics fenced by '_' - (r'(\_[^\_\n\ ][^\_\n]*\_)', bygroups(Generic.Emph)), + (r'(\_[^_ \n][^_\n]*\_)', bygroups(Generic.Emph)), # strikethrough (r'([^~]*)(~~[^~]+~~)', bygroups(Text, Generic.Deleted)), # mentions and topics (twitter and github stuff) (r'[@#][\w/:]+', Name.Entity), # (image?) links eg:  - (r'(!?\[)([^]]+)(\])(\()([^)]+)(\))', bygroups(Text, Name.Tag, Text, Text, Name.Attribute, Text)), + (r'(!?\[)([^]]+)(\])(\()([^)]+)(\))', + bygroups(Text, Name.Tag, Text, Text, Name.Attribute, Text)), # reference-style links, e.g.: # [an example][id] # [id]: http://example.com/ - (r'(\[)([^]]+)(\])(\[)([^]]*)(\])', bygroups(Text, Name.Tag, Text, Text, Name.Label, Text)), - (r'^(\s*\[)([^]]*)(\]:\s*)(.+)', bygroups(Text, Name.Label, Text, Name.Attribute)), + (r'(\[)([^]]+)(\])(\[)([^]]*)(\])', + bygroups(Text, Name.Tag, Text, Text, Name.Label, Text)), + (r'^(\s*\[)([^]]*)(\]:\s*)(.+)', + bygroups(Text, Name.Label, Text, Name.Attribute)), # general text, must come last! (r'[^\\\s]+', Text), @@ -608,6 +611,7 @@ class MarkdownLexer(RegexLexer): self.handlecodeblocks = get_bool_opt(options, 'handlecodeblocks', True) RegexLexer.__init__(self, **options) + class TiddlyWiki5Lexer(RegexLexer): """ For `TiddlyWiki5 <https://tiddlywiki.com/#TiddlerFiles>`_ markup. @@ -627,15 +631,15 @@ class TiddlyWiki5Lexer(RegexLexer): from pygments.lexers import get_lexer_by_name # section header - yield match.start(1), String , match.group(1) - yield match.start(2), String , match.group(2) - yield match.start(3), Text , match.group(3) + yield match.start(1), String, match.group(1) + yield match.start(2), String, match.group(2) + yield match.start(3), Text, match.group(3) # lookup lexer if wanted and existing lexer = None if self.handlecodeblocks: try: - lexer = get_lexer_by_name( match.group(2).strip() ) + lexer = get_lexer_by_name(match.group(2).strip()) except ClassNotFound: pass code = match.group(4) @@ -648,7 +652,7 @@ class TiddlyWiki5Lexer(RegexLexer): for item in do_insertions([], lexer.get_tokens_unprocessed(code)): yield item - yield match.start(5), String , match.group(5) + yield match.start(5), String, match.group(5) def _handle_cssblock(self, match): """ @@ -657,13 +661,13 @@ class TiddlyWiki5Lexer(RegexLexer): from pygments.lexers import get_lexer_by_name # section header - yield match.start(1), String , match.group(1) - yield match.start(2), String , match.group(2) + yield match.start(1), String, match.group(1) + yield match.start(2), String, match.group(2) lexer = None if self.handlecodeblocks: try: - lexer = get_lexer_by_name( 'css' ) + lexer = get_lexer_by_name('css') except ClassNotFound: pass code = match.group(3) @@ -676,7 +680,7 @@ class TiddlyWiki5Lexer(RegexLexer): for item in do_insertions([], lexer.get_tokens_unprocessed(code)): yield item - yield match.start(4), String , match.group(4) + yield match.start(4), String, match.group(4) tokens = { 'root': [ @@ -688,7 +692,7 @@ class TiddlyWiki5Lexer(RegexLexer): # bulleted or numbered lists or single-line block quotes # (can be mixed) (r'^(\s*)([*#>]+)(\s*)(.+\n)', - bygroups(Text, Keyword, Text, using(this, state='inline'))), + bygroups(Text, Keyword, Text, using(this, state='inline'))), # multi-line block quotes (r'^(<<<.*\n)([\w\W]*?)(^<<<.*$)', bygroups(String, Text, String)), # table header @@ -722,7 +726,7 @@ class TiddlyWiki5Lexer(RegexLexer): (r'\d{17}', Number.Integer), # italics (r'(\s)(//[^/]+//)((?=\W|\n))', - bygroups(Text, Generic.Emph, Text)), + bygroups(Text, Generic.Emph, Text)), # superscript (r'(\s)(\^\^[^\^]+\^\^)', bygroups(Text, Generic.Emph)), # subscript @@ -731,13 +735,13 @@ class TiddlyWiki5Lexer(RegexLexer): (r'(\s)(__[^_]+__)', bygroups(Text, Generic.Strong)), # bold (r"(\s)(''[^']+'')((?=\W|\n))", - bygroups(Text, Generic.Strong, Text)), + bygroups(Text, Generic.Strong, Text)), # strikethrough (r'(\s)(~~[^~]+~~)((?=\W|\n))', - bygroups(Text, Generic.Deleted, Text)), + bygroups(Text, Generic.Deleted, Text)), # TiddlyWiki variables (r'<<[^>]+>>', Name.Tag), - (r'\$\$[^\$]+\$\$', Name.Tag), + (r'\$\$[^$]+\$\$', Name.Tag), (r'\$\([^)]+\)\$', Name.Tag), # TiddlyWiki style or class (r'^@@.*$', Name.Tag), |