Mercurial Repositories > eric / file comparison
comparison: ThirdParty/Pygments/pygments/lexers/markup.py
ThirdParty/Pygments/pygments/lexers/markup.py
- changeset 5713
- 6762afd9f963
- parent 4697
- c2e9bf425554
- child 6651
- e8f3b5568b21
equal
deleted
inserted
replaced
| 5712:f0d08bdeacf4 | 5713:6762afd9f963 |
|---|---|
| 3 pygments.lexers.markup | 3 pygments.lexers.markup |
| 4 ~~~~~~~~~~~~~~~~~~~~~~ | 4 ~~~~~~~~~~~~~~~~~~~~~~ |
| 5 | 5 |
| 6 Lexers for non-HTML markup languages. | 6 Lexers for non-HTML markup languages. |
| 7 | 7 |
| 8 :copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS. | 8 :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS. |
| 9 :license: BSD, see LICENSE for details. | 9 :license: BSD, see LICENSE for details. |
| 10 """ | 10 """ |
| 11 | 11 |
| 12 import re | 12 import re |
| 13 | 13 |
| 22 from pygments.util import get_bool_opt, ClassNotFound | 22 from pygments.util import get_bool_opt, ClassNotFound |
| 23 | 23 |
| 24 __all__ = ['BBCodeLexer', 'MoinWikiLexer', 'RstLexer', 'TexLexer', 'GroffLexer', | 24 __all__ = ['BBCodeLexer', 'MoinWikiLexer', 'RstLexer', 'TexLexer', 'GroffLexer', |
| 25 'MozPreprocHashLexer', 'MozPreprocPercentLexer', | 25 'MozPreprocHashLexer', 'MozPreprocPercentLexer', |
| 26 'MozPreprocXulLexer', 'MozPreprocJavascriptLexer', | 26 'MozPreprocXulLexer', 'MozPreprocJavascriptLexer', |
| 27 'MozPreprocCssLexer'] | 27 'MozPreprocCssLexer', 'MarkdownLexer'] |
| 28 | 28 |
| 29 | 29 |
| 30 class BBCodeLexer(RegexLexer): | 30 class BBCodeLexer(RegexLexer): |
| 31 """ | 31 """ |
| 32 A lexer that highlights BBCode(-like) syntax. | 32 A lexer that highlights BBCode(-like) syntax. |
| 498 | 498 |
| 499 def __init__(self, **options): | 499 def __init__(self, **options): |
| 500 super(MozPreprocCssLexer, self).__init__( | 500 super(MozPreprocCssLexer, self).__init__( |
| 501 CssLexer, MozPreprocPercentLexer, **options) | 501 CssLexer, MozPreprocPercentLexer, **options) |
| 502 | 502 |
| 503 | |
| 504 class MarkdownLexer(RegexLexer): | |
| 505 """ | |
| 506 For `Markdown <https://help.github.com/categories/writing-on-github/>`_ markup. | |
| 507 | |
| 508 .. versionadded:: 2.2 | |
| 509 """ | |
| 510 name = 'markdown' | |
| 511 aliases = ['md'] | |
| 512 filenames = ['*.md'] | |
| 513 mimetypes = ["text/x-markdown"] | |
| 514 flags = re.MULTILINE | |
| 515 | |
| 516 def _handle_codeblock(self, match): | |
| 517 """ | |
| 518 match args: 1:backticks, 2:lang_name, 3:newline, 4:code, 5:backticks | |
| 519 """ | |
| 520 from pygments.lexers import get_lexer_by_name | |
| 521 | |
| 522 # section header | |
| 523 yield match.start(1), String , match.group(1) | |
| 524 yield match.start(2), String , match.group(2) | |
| 525 yield match.start(3), Text , match.group(3) | |
| 526 | |
| 527 # lookup lexer if wanted and existing | |
| 528 lexer = None | |
| 529 if self.handlecodeblocks: | |
| 530 try: | |
| 531 lexer = get_lexer_by_name( match.group(2).strip() ) | |
| 532 except ClassNotFound: | |
| 533 pass | |
| 534 code = match.group(4) | |
| 535 | |
| 536 # no lexer for this language. handle it like it was a code block | |
| 537 if lexer is None: | |
| 538 yield match.start(4), String, code | |
| 539 return | |
| 540 | |
| 541 for item in do_insertions([], lexer.get_tokens_unprocessed(code)): | |
| 542 yield item | |
| 543 | |
| 544 yield match.start(5), String , match.group(5) | |
| 545 | |
| 546 tokens = { | |
| 547 'root': [ | |
| 548 # heading with pound prefix | |
| 549 (r'^(#)([^#].+\n)', bygroups(Generic.Heading, Text)), | |
| 550 (r'^(#{2,6})(.+\n)', bygroups(Generic.Subheading, Text)), | |
| 551 # task list | |
| 552 (r'^(\s*)([*-] )(\[[ xX]\])( .+\n)', | |
| 553 bygroups(Text, Keyword, Keyword, using(this, state='inline'))), | |
| 554 # bulleted lists | |
| 555 (r'^(\s*)([*-])(\s)(.+\n)', | |
| 556 bygroups(Text, Keyword, Text, using(this, state='inline'))), | |
| 557 # numbered lists | |
| 558 (r'^(\s*)([0-9]+\.)( .+\n)', | |
| 559 bygroups(Text, Keyword, using(this, state='inline'))), | |
| 560 # quote | |
| 561 (r'^(\s*>\s)(.+\n)', bygroups(Keyword, Generic.Emph)), | |
| 562 # text block | |
| 563 (r'^(```\n)([\w\W]*?)(^```$)', bygroups(String, Text, String)), | |
| 564 # code block with language | |
| 565 (r'^(```)(\w+)(\n)([\w\W]*?)(^```$)', _handle_codeblock), | |
| 566 | |
| 567 include('inline'), | |
| 568 ], | |
| 569 'inline': [ | |
| 570 # escape | |
| 571 (r'\\.', Text), | |
| 572 # italics | |
| 573 (r'(\s)([*_][^*_]+[*_])(\W|\n)', bygroups(Text, Generic.Emph, Text)), | |
| 574 # bold | |
| 575 # warning: the following rule eats internal tags. eg. **foo _bar_ baz** bar is not italics | |
| 576 (r'(\s)((\*\*|__).*\3)((?=\W|\n))', bygroups(Text, Generic.Strong, None, Text)), | |
| 577 # "proper way" (r'(\s)([*_]{2}[^*_]+[*_]{2})((?=\W|\n))', bygroups(Text, Generic.Strong, Text)), | |
| 578 # strikethrough | |
| 579 (r'(\s)(~~[^~]+~~)((?=\W|\n))', bygroups(Text, Generic.Deleted, Text)), | |
| 580 # inline code | |
| 581 (r'`[^`]+`', String.Backtick), | |
| 582 # mentions and topics (twitter and github stuff) | |
| 583 (r'[@#][\w/:]+', Name.Entity), | |
| 584 # (image?) links eg:  | |
| 585 (r'(!?\[)([^]]+)(\])(\()([^)]+)(\))', bygroups(Text, Name.Tag, Text, Text, Name.Attribute, Text)), | |
| 586 | |
| 587 # general text, must come last! | |
| 588 (r'[^\\\s]+', Text), | |
| 589 (r'.', Text), | |
| 590 ], | |
| 591 } | |
| 592 | |
| 593 def __init__(self, **options): | |
| 594 self.handlecodeblocks = get_bool_opt(options, 'handlecodeblocks', True) | |
| 595 RegexLexer.__init__(self, **options) |
