/console/app/pygments/lexers/text.py
https://bitbucket.org/alex_muscar/myspace-competition-radar · Python · 1482 lines · 1074 code · 131 blank · 277 comment · 67 complexity · cda584df89622b4651aa4d746e4a6823 MD5 · raw file
- # -*- coding: utf-8 -*-
- """
- pygments.lexers.text
- ~~~~~~~~~~~~~~~~~~~~
- Lexers for non-source code file types.
- :copyright: 2006-2008 by Armin Ronacher, Georg Brandl,
- Tim Hatch <tim@timhatch.com>,
- Ronny Pfannschmidt,
- Dennis Kaarsemaker,
- Kumar Appaiah <akumar@ee.iitm.ac.in>,
- Varun Hiremath <varunhiremath@gmail.com>,
- Jeremy Thurgood,
- Max Battcher,
- Kirill Simonov <xi@resolvent.net>.
- :license: BSD, see LICENSE for more details.
- """
- import re
- try:
- set
- except NameError:
- from sets import Set as set
- from bisect import bisect
- from pygments.lexer import Lexer, LexerContext, RegexLexer, ExtendedRegexLexer, \
- bygroups, include, using, this, do_insertions
- from pygments.token import Punctuation, Text, Comment, Keyword, Name, String, \
- Generic, Operator, Number, Whitespace, Literal
- from pygments.util import get_bool_opt
- from pygments.lexers.other import BashLexer
- __all__ = ['IniLexer', 'SourcesListLexer', 'BaseMakefileLexer',
- 'MakefileLexer', 'DiffLexer', 'IrcLogsLexer', 'TexLexer',
- 'GroffLexer', 'ApacheConfLexer', 'BBCodeLexer', 'MoinWikiLexer',
- 'RstLexer', 'VimLexer', 'GettextLexer', 'SquidConfLexer',
- 'DebianControlLexer', 'DarcsPatchLexer', 'YamlLexer',
- 'LighttpdConfLexer', 'NginxConfLexer']
- class IniLexer(RegexLexer):
- """
- Lexer for configuration files in INI style.
- """
- name = 'INI'
- aliases = ['ini', 'cfg']
- filenames = ['*.ini', '*.cfg', '*.properties']
- mimetypes = ['text/x-ini']
- tokens = {
- 'root': [
- (r'\s+', Text),
- (r'[;#].*?$', Comment),
- (r'\[.*?\]$', Keyword),
- (r'(.*?)(\s*)(=)(\s*)(.*?)$',
- bygroups(Name.Attribute, Text, Operator, Text, String))
- ]
- }
- def analyse_text(text):
- npos = text.find('\n')
- if npos < 3:
- return False
- return text[0] == '[' and text[npos-1] == ']'
- class SourcesListLexer(RegexLexer):
- """
- Lexer that highlights debian sources.list files.
- *New in Pygments 0.7.*
- """
- name = 'Debian Sourcelist'
- aliases = ['sourceslist', 'sources.list']
- filenames = ['sources.list']
- mimetype = ['application/x-debian-sourceslist']
- tokens = {
- 'root': [
- (r'\s+', Text),
- (r'#.*?$', Comment),
- (r'^(deb(?:-src)?)(\s+)',
- bygroups(Keyword, Text), 'distribution')
- ],
- 'distribution': [
- (r'#.*?$', Comment, '#pop'),
- (r'\$\(ARCH\)', Name.Variable),
- (r'[^\s$[]+', String),
- (r'\[', String.Other, 'escaped-distribution'),
- (r'\$', String),
- (r'\s+', Text, 'components')
- ],
- 'escaped-distribution': [
- (r'\]', String.Other, '#pop'),
- (r'\$\(ARCH\)', Name.Variable),
- (r'[^\]$]+', String.Other),
- (r'\$', String.Other)
- ],
- 'components': [
- (r'#.*?$', Comment, '#pop:2'),
- (r'$', Text, '#pop:2'),
- (r'\s+', Text),
- (r'\S+', Keyword.Pseudo),
- ]
- }
- def analyse_text(text):
- for line in text.split('\n'):
- line = line.strip()
- if not (line.startswith('#') or line.startswith('deb ') or
- line.startswith('deb-src ') or not line):
- return False
- return True
- class MakefileLexer(Lexer):
- """
- Lexer for BSD and GNU make extensions (lenient enough to handle both in
- the same file even).
- *Rewritten in Pygments 0.10.*
- """
- name = 'Makefile'
- aliases = ['make', 'makefile', 'mf', 'bsdmake']
- filenames = ['*.mak', 'Makefile', 'makefile', 'Makefile.*']
- mimetypes = ['text/x-makefile']
- r_special = re.compile(r'^(?:'
- # BSD Make
- r'\.\s*(include|undef|error|warning|if|else|elif|endif|for|endfor)|'
- # GNU Make
- r'\s*(ifeq|ifneq|ifdef|ifndef|else|endif|-?include|define|endef|:))(?=\s)')
- r_comment = re.compile(r'^\s*@?#')
- def get_tokens_unprocessed(self, text):
- ins = []
- lines = text.splitlines(True)
- done = ''
- lex = BaseMakefileLexer(**self.options)
- backslashflag = False
- for line in lines:
- if self.r_special.match(line) or backslashflag:
- ins.append((len(done), [(0, Comment.Preproc, line)]))
- backslashflag = line.strip().endswith('\\')
- elif self.r_comment.match(line):
- ins.append((len(done), [(0, Comment, line)]))
- else:
- done += line
- for item in do_insertions(ins, lex.get_tokens_unprocessed(done)):
- yield item
- class BaseMakefileLexer(RegexLexer):
- """
- Lexer for simple Makefiles (no preprocessing).
- *New in Pygments 0.10.*
- """
- name = 'Makefile'
- aliases = ['basemake']
- filenames = []
- mimetypes = []
- tokens = {
- 'root': [
- (r'^(?:[\t ]+.*\n|\n)+', using(BashLexer)),
- (r'\$\((?:.*\\\n|.*\n)+', using(BashLexer)),
- (r'\s+', Text),
- (r'#.*?\n', Comment),
- (r'(export)(\s+)(?=[a-zA-Z0-9_${}\t -]+\n)',
- bygroups(Keyword, Text), 'export'),
- (r'export\s+', Keyword),
- # assignment
- (r'([a-zA-Z0-9_${}.-]+)(\s*)([!?:+]?=)([ \t]*)((?:.*\\\n|.*\n)+)',
- bygroups(Name.Variable, Text, Operator, Text, using(BashLexer))),
- # strings
- (r'"(\\\\|\\"|[^"])*"', String.Double),
- (r"'(\\\\|\\'|[^'])*'", String.Single),
- # targets
- (r'([^\n:]+)(:+)([ \t]*)', bygroups(Name.Function, Operator, Text),
- 'block-header'),
- #TODO: add paren handling (grr)
- ],
- 'export': [
- (r'[a-zA-Z0-9_${}-]+', Name.Variable),
- (r'\n', Text, '#pop'),
- (r'\s+', Text),
- ],
- 'block-header': [
- (r'[^,\\\n#]+', Number),
- (r',', Punctuation),
- (r'#.*?\n', Comment),
- (r'\\\n', Text), # line continuation
- (r'\\.', Text),
- (r'(?:[\t ]+.*\n|\n)+', using(BashLexer), '#pop'),
- ],
- }
- class DiffLexer(RegexLexer):
- """
- Lexer for unified or context-style diffs or patches.
- """
- name = 'Diff'
- aliases = ['diff']
- filenames = ['*.diff', '*.patch']
- mimetypes = ['text/x-diff', 'text/x-patch']
- tokens = {
- 'root': [
- (r' .*\n', Text),
- (r'\+.*\n', Generic.Inserted),
- (r'-.*\n', Generic.Deleted),
- (r'!.*\n', Generic.Strong),
- (r'@.*\n', Generic.Subheading),
- (r'(Index|diff).*\n', Generic.Heading),
- (r'=.*\n', Generic.Heading),
- (r'.*\n', Text),
- ]
- }
- def analyse_text(text):
- if text[:7] == 'Index: ':
- return True
- if text[:5] == 'diff ':
- return True
- if text[:4] == '--- ':
- return 0.9
- class DarcsPatchLexer(RegexLexer):
- """
- DarcsPatchLexer is a lexer for the various versions of the darcs patch
- format. Examples of this format are derived by commands such as
- ``darcs annotate --patch`` and ``darcs send``.
- *New in Pygments 0.10.*
- """
- name = 'Darcs Patch'
- aliases = ['dpatch']
- filenames = ['*.dpatch', '*.darcspatch']
- tokens = {
- 'root': [
- (r'<', Operator),
- (r'>', Operator),
- (r'{', Operator, 'patch'),
- (r'(\[)((?:TAG )?)(.*)(\n)(.*)(\*\*)(\d+)(\s?)',
- bygroups(Operator, Keyword, Name, Text, Name, Operator,
- Literal.Date, Text), 'comment'),
- (r'New patches:', Generic.Heading),
- (r'Context:', Generic.Heading),
- (r'Patch bundle hash:', Generic.Heading),
- (r'\s+|\w+', Text),
- ],
- 'comment': [
- (r' .*\n', Comment),
- (r'\]', Operator, "#pop"),
- ],
- 'patch': [
- (r'}', Operator, "#pop"),
- (r'(\w+)(.*\n)', bygroups(Keyword, Text)),
- (r'\+.*\n', Generic.Inserted),
- (r'-.*\n', Generic.Deleted),
- (r'.*\n', Text),
- ],
- }
- class IrcLogsLexer(RegexLexer):
- """
- Lexer for IRC logs in *irssi*, *xchat* or *weechat* style.
- """
- name = 'IRC logs'
- aliases = ['irc']
- filenames = ['*.weechatlog']
- mimetypes = ['text/x-irclog']
- flags = re.VERBOSE | re.MULTILINE
- timestamp = r"""
- (
- # irssi / xchat and others
- (?: \[|\()? # Opening bracket or paren for the timestamp
- (?: # Timestamp
- (?: (?:\d{1,4} [-/]?)+ # Date as - or /-separated groups of digits
- [T ])? # Date/time separator: T or space
- (?: \d?\d [:.]?)+ # Time as :/.-separated groups of 1 or 2 digits
- )
- (?: \]|\))?\s+ # Closing bracket or paren for the timestamp
- |
- # weechat
- \d{4}\s\w{3}\s\d{2}\s # Date
- \d{2}:\d{2}:\d{2}\s+ # Time + Whitespace
- |
- # xchat
- \w{3}\s\d{2}\s # Date
- \d{2}:\d{2}:\d{2}\s+ # Time + Whitespace
- )?
- """
- tokens = {
- 'root': [
- # log start/end
- (r'^\*\*\*\*(.*)\*\*\*\*$', Comment),
- # hack
- ("^" + timestamp + r'(\s*<[^>]*>\s*)$', bygroups(Comment.Preproc, Name.Tag)),
- # normal msgs
- ("^" + timestamp + r"""
- (\s*<.*?>\s*) # Nick """,
- bygroups(Comment.Preproc, Name.Tag), 'msg'),
- # /me msgs
- ("^" + timestamp + r"""
- (\s*[*]\s+) # Star
- ([^\s]+\s+.*?\n) # Nick + rest of message """,
- bygroups(Comment.Preproc, Keyword, Generic.Inserted)),
- # join/part msgs
- ("^" + timestamp + r"""
- (\s*(?:\*{3}|<?-[!@=P]?->?)\s*) # Star(s) or symbols
- ([^\s]+\s+) # Nick + Space
- (.*?\n) # Rest of message """,
- bygroups(Comment.Preproc, Keyword, String, Comment)),
- (r"^.*?\n", Text),
- ],
- 'msg': [
- (r"[^\s]+:(?!//)", Name.Attribute), # Prefix
- (r".*\n", Text, '#pop'),
- ],
- }
- class BBCodeLexer(RegexLexer):
- """
- A lexer that highlights BBCode(-like) syntax.
- *New in Pygments 0.6.*
- """
- name = 'BBCode'
- aliases = ['bbcode']
- mimetypes = ['text/x-bbcode']
- tokens = {
- 'root' : [
- (r'[\s\w]+', Text),
- (r'(\[)(/?[^\]\n\r=]+)(\])',
- bygroups(Keyword, Keyword.Pseudo, Keyword)),
- (r'(\[)([^\]\n\r=]+)(=)([^\]\n\r]+)(\])',
- bygroups(Keyword, Keyword.Pseudo, Operator, String, Keyword)),
- ],
- }
- class TexLexer(RegexLexer):
- """
- Lexer for the TeX and LaTeX typesetting languages.
- """
- name = 'TeX'
- aliases = ['tex', 'latex']
- filenames = ['*.tex', '*.aux', '*.toc']
- mimetypes = ['text/x-tex', 'text/x-latex']
- tokens = {
- 'general': [
- (r'%.*?\n', Comment),
- (r'[{}]', Name.Builtin),
- (r'[&_^]', Name.Builtin),
- ],
- 'root': [
- (r'\\\[', String.Backtick, 'displaymath'),
- (r'\\\(', String, 'inlinemath'),
- (r'\$\$', String.Backtick, 'displaymath'),
- (r'\$', String, 'inlinemath'),
- (r'\\([a-zA-Z]+|.)', Keyword, 'command'),
- include('general'),
- (r'[^\\$%&_^{}]+', Text),
- ],
- 'math': [
- (r'\\([a-zA-Z]+|.)', Name.Variable),
- include('general'),
- (r'[0-9]+', Number),
- (r'[-=!+*/()\[\]]', Operator),
- (r'[^=!+*/()\[\]\\$%&_^{}0-9-]+', Name.Builtin),
- ],
- 'inlinemath': [
- (r'\\\)', String, '#pop'),
- (r'\$', String, '#pop'),
- include('math'),
- ],
- 'displaymath': [
- (r'\\\]', String, '#pop'),
- (r'\$\$', String, '#pop'),
- (r'\$', Name.Builtin),
- include('math'),
- ],
- 'command': [
- (r'\[.*?\]', Name.Attribute),
- (r'\*', Keyword),
- (r'', Text, '#pop'),
- ],
- }
- def analyse_text(text):
- for start in ("\\documentclass", "\\input", "\\documentstyle",
- "\\relax"):
- if text[:len(start)] == start:
- return True
- class GroffLexer(RegexLexer):
- """
- Lexer for the (g)roff typesetting language, supporting groff
- extensions. Mainly useful for highlighting manpage sources.
- *New in Pygments 0.6.*
- """
- name = 'Groff'
- aliases = ['groff', 'nroff', 'man']
- filenames = ['*.[1234567]', '*.man']
- mimetypes = ['application/x-troff', 'text/troff']
- tokens = {
- 'root': [
- (r'(?i)(\.)(\w+)', bygroups(Text, Keyword), 'request'),
- (r'\.', Punctuation, 'request'),
- # Regular characters, slurp till we find a backslash or newline
- (r'[^\\\n]*', Text, 'textline'),
- ],
- 'textline': [
- include('escapes'),
- (r'[^\\\n]+', Text),
- (r'\n', Text, '#pop'),
- ],
- 'escapes': [
- # groff has many ways to write escapes.
- (r'\\"[^\n]*', Comment),
- (r'\\[fn]\w', String.Escape),
- (r'\\\(..', String.Escape),
- (r'\\.\[.*\]', String.Escape),
- (r'\\.', String.Escape),
- (r'\\\n', Text, 'request'),
- ],
- 'request': [
- (r'\n', Text, '#pop'),
- include('escapes'),
- (r'"[^\n"]+"', String.Double),
- (r'\d+', Number),
- (r'\S+', String),
- (r'\s+', Text),
- ],
- }
- def analyse_text(text):
- if text[0] != '.':
- return False
- if text[:3] == '.\\"':
- return True
- if text[:4] == '.TH ':
- return True
- if text[1:3].isalnum() and text[3].isspace():
- return 0.9
- class ApacheConfLexer(RegexLexer):
- """
- Lexer for configuration files following the Apache config file
- format.
- *New in Pygments 0.6.*
- """
- name = 'ApacheConf'
- aliases = ['apacheconf', 'aconf', 'apache']
- filenames = ['.htaccess', 'apache.conf', 'apache2.conf']
- mimetypes = ['text/x-apacheconf']
- flags = re.MULTILINE | re.IGNORECASE
- tokens = {
- 'root': [
- (r'\s+', Text),
- (r'(#.*?)$', Comment),
- (r'(<[^\s>]+)(?:(\s+)(.*?))?(>)',
- bygroups(Name.Tag, Text, String, Name.Tag)),
- (r'([a-zA-Z][a-zA-Z0-9]*)(\s+)',
- bygroups(Name.Builtin, Text), 'value'),
- (r'\.+', Text),
- ],
- 'value': [
- (r'$', Text, '#pop'),
- (r'[^\S\n]+', Text),
- (r'\d+\.\d+\.\d+\.\d+(?:/\d+)?', Number),
- (r'\d+', Number),
- (r'/([a-zA-Z0-9][a-zA-Z0-9_./-]+)', String.Other),
- (r'(on|off|none|any|all|double|email|dns|min|minimal|'
- r'os|productonly|full|emerg|alert|crit|error|warn|'
- r'notice|info|debug|registry|script|inetd|standalone|'
- r'user|group)\b', Keyword),
- (r'"([^"\\]*(?:\\.[^"\\]*)*)"', String.Double),
- (r'[^\s"]+', Text)
- ]
- }
- class MoinWikiLexer(RegexLexer):
- """
- For MoinMoin (and Trac) Wiki markup.
- *New in Pygments 0.7.*
- """
- name = 'MoinMoin/Trac Wiki markup'
- aliases = ['trac-wiki', 'moin']
- filenames = []
- mimetypes = ['text/x-trac-wiki']
- flags = re.MULTILINE | re.IGNORECASE
- tokens = {
- 'root': [
- (r'^#.*$', Comment),
- (r'(!)(\S+)', bygroups(Keyword, Text)), # Ignore-next
- # Titles
- (r'^(=+)([^=]+)(=+)(\s*#.+)?$',
- bygroups(Generic.Heading, using(this), Generic.Heading, String)),
- # Literal code blocks, with optional shebang
- (r'({{{)(\n#!.+)?', bygroups(Name.Builtin, Name.Namespace), 'codeblock'),
- (r'(\'\'\'?|\|\||`|__|~~|\^|,,|::)', Comment), # Formatting
- # Lists
- (r'^( +)([.*-])( )', bygroups(Text, Name.Builtin, Text)),
- (r'^( +)([a-zivx]{1,5}\.)( )', bygroups(Text, Name.Builtin, Text)),
- # Other Formatting
- (r'\[\[\w+.*?\]\]', Keyword), # Macro
- (r'(\[[^\s\]]+)(\s+[^\]]+?)?(\])',
- bygroups(Keyword, String, Keyword)), # Link
- (r'^----+$', Keyword), # Horizontal rules
- (r'[^\n\'\[{!_~^,|]+', Text),
- (r'\n', Text),
- (r'.', Text),
- ],
- 'codeblock': [
- (r'}}}', Name.Builtin, '#pop'),
- # these blocks are allowed to be nested in Trac, but not MoinMoin
- (r'{{{', Text, '#push'),
- (r'[^{}]+', Comment.Preproc), # slurp boring text
- (r'.', Comment.Preproc), # allow loose { or }
- ],
- }
- class RstLexer(RegexLexer):
- """
- For `reStructuredText <http://docutils.sf.net/rst.html>`_ markup.
- *New in Pygments 0.7.*
- Additional options accepted:
- `handlecodeblocks`
- Highlight the contents of ``.. sourcecode:: langauge`` and
- ``.. code:: language`` directives with a lexer for the given
- language (default: ``True``). *New in Pygments 0.8.*
- """
- name = 'reStructuredText'
- aliases = ['rst', 'rest', 'restructuredtext']
- filenames = ['*.rst', '*.rest']
- mimetypes = ["text/x-rst"]
- flags = re.MULTILINE
- def _handle_sourcecode(self, match):
- from pygments.lexers import get_lexer_by_name
- from pygments.util import ClassNotFound
- # section header
- yield match.start(1), Punctuation, match.group(1)
- yield match.start(2), Text, match.group(2)
- yield match.start(3), Operator.Word, match.group(3)
- yield match.start(4), Punctuation, match.group(4)
- yield match.start(5), Text, match.group(5)
- yield match.start(6), Keyword, match.group(6)
- yield match.start(7), Text, match.group(7)
- # lookup lexer if wanted and existing
- lexer = None
- if self.handlecodeblocks:
- try:
- lexer = get_lexer_by_name(match.group(6).strip())
- except ClassNotFound:
- pass
- indention = match.group(8)
- indention_size = len(indention)
- code = (indention + match.group(9) + match.group(10) + match.group(11))
- # no lexer for this language. handle it like it was a code block
- if lexer is None:
- yield match.start(8), String, code
- return
- # highlight the lines with the lexer.
- ins = []
- codelines = code.splitlines(True)
- code = ''
- for line in codelines:
- if len(line) > indention_size:
- ins.append((len(code), [(0, Text, line[:indention_size])]))
- code += line[indention_size:]
- else:
- code += line
- for item in do_insertions(ins, lexer.get_tokens_unprocessed(code)):
- yield item
- tokens = {
- 'root': [
- # Heading with overline
- (r'^(=+|-+|`+|:+|\.+|\'+|"+|~+|\^+|_+|\*+|\++|#+)([ \t]*\n)(.+)(\n)(\1)(\n)',
- bygroups(Generic.Heading, Text, Generic.Heading,
- Text, Generic.Heading, Text)),
- # Plain heading
- (r'^(\S.*)(\n)(={3,}|-{3,}|`{3,}|:{3,}|\.{3,}|\'{3,}|"{3,}|'
- r'~{3,}|\^{3,}|_{3,}|\*{3,}|\+{3,}|#{3,})(\n)',
- bygroups(Generic.Heading, Text, Generic.Heading, Text)),
- # Bulleted lists
- (r'^(\s*)([-*+])( .+\n(?:\1 .+\n)*)',
- bygroups(Text, Number, using(this, state='inline'))),
- # Numbered lists
- (r'^(\s*)([0-9#ivxlcmIVXLCM]+\.)( .+\n(?:\1 .+\n)*)',
- bygroups(Text, Number, using(this, state='inline'))),
- (r'^(\s*)(\(?[0-9#ivxlcmIVXLCM]+\))( .+\n(?:\1 .+\n)*)',
- bygroups(Text, Number, using(this, state='inline'))),
- # Numbered, but keep words at BOL from becoming lists
- (r'^(\s*)([A-Z]+\.)( .+\n(?:\1 .+\n)+)',
- bygroups(Text, Number, using(this, state='inline'))),
- (r'^(\s*)(\(?[A-Za-z]+\))( .+\n(?:\1 .+\n)+)',
- bygroups(Text, Number, using(this, state='inline'))),
- # Sourcecode directives
- (r'^( *\.\.)(\s*)((?:source)?code)(::)([ \t]*)([^\n]+)'
- r'(\n[ \t]*\n)([ \t]+)(.*)(\n)((?:(?:\8.*|)\n)+)',
- _handle_sourcecode),
- # A directive
- (r'^( *\.\.)(\s*)([\w-]+)(::)(?:([ \t]*)(.+))?',
- bygroups(Punctuation, Text, Operator.Word, Punctuation, Text, Keyword)),
- # A reference target
- (r'^( *\.\.)(\s*)([\w\t ]+:)(.*?)$',
- bygroups(Punctuation, Text, Name.Tag, using(this, state='inline'))),
- # A footnote target
- (r'^( *\.\.)(\s*)(\[.+\])(.*?)$',
- bygroups(Punctuation, Text, Name.Tag, using(this, state='inline'))),
- # Comments
- (r'^ *\.\..*(\n( +.*\n|\n)+)?', Comment.Preproc),
- # Field list
- (r'^( *)(:.*?:)([ \t]+)(.*?)$', bygroups(Text, Name.Class, Text,
- Name.Function)),
- # Definition list
- (r'^([^ ].*(?<!::)\n)((?:(?: +.*)\n)+)',
- bygroups(using(this, state='inline'), using(this, state='inline'))),
- # Code blocks
- (r'(::)(\n[ \t]*\n)([ \t]+)(.*)(\n)((?:(?:\3.*|)\n)+)',
- bygroups(String.Escape, Text, String, String, Text, String)),
- include('inline'),
- ],
- 'inline': [
- (r'\\.', Text), # escape
- (r'``', String, 'literal'), # code
- (r'(`)(.+?)(`__?)',
- bygroups(Punctuation, using(this), Punctuation)), # reference
- (r'(`.+?`)(:[a-zA-Z0-9-]+?:)?',
- bygroups(Name.Variable, Name.Attribute)), # role
- (r'(:[a-zA-Z0-9-]+?:)(`.+?`)',
- bygroups(Name.Attribute, Name.Variable)), # user-defined role
- (r'\*\*.+?\*\*', Generic.Strong), # Strong emphasis
- (r'\*.+?\*', Generic.Emph), # Emphasis
- (r'\[.*?\]_', String), # Footnote or citation
- (r'<.+?>', Name.Tag), # Hyperlink
- (r'[^\\\n\[*`:]+', Text),
- (r'.', Text),
- ],
- 'literal': [
- (r'[^`\\]+', String),
- (r'\\.', String),
- (r'``', String, '#pop'),
- (r'[`\\]', String),
- ]
- }
- def __init__(self, **options):
- self.handlecodeblocks = get_bool_opt(options, 'handlecodeblocks', True)
- RegexLexer.__init__(self, **options)
- def analyse_text(text):
- if text[:2] == '..' and text[2:3] != '.':
- return 0.3
- p1 = text.find("\n")
- p2 = text.find("\n", p1 + 1)
- if (p2 > -1 and # has two lines
- p1 * 2 + 1 == p2 and # they are the same length
- text[p1+1] in '-=' and # the next line both starts and ends with
- text[p1+1] == text[p2-1]): # ...a sufficiently high header
- return 0.5
- class VimLexer(RegexLexer):
- """
- Lexer for VimL script files.
- *New in Pygments 0.8.*
- """
- name = 'VimL'
- aliases = ['vim']
- filenames = ['*.vim', '.vimrc']
- mimetypes = ['text/x-vim']
- flags = re.MULTILINE
- tokens = {
- 'root': [
- # Who decided that doublequote was a good comment character??
- (r'^\s*".*', Comment),
- (r'(?<=\s)"[^\-:.%#=*].*', Comment),
- (r'[ \t]+', Text),
- # TODO: regexes can have other delims
- (r'/(\\\\|\\/|[^\n/])*/', String.Regex),
- (r'"(\\\\|\\"|[^\n"])*"', String.Double),
- (r"'(\\\\|\\'|[^\n'])*'", String.Single),
- (r'-?\d+', Number),
- (r'#[0-9a-f]{6}', Number.Hex),
- (r'^:', Punctuation),
- (r'[()<>+=!|,~-]', Punctuation), # Inexact list. Looks decent.
- (r'\b(let|if|else|endif|elseif|fun|function|endfunction)\b',
- Keyword),
- (r'\b(NONE|bold|italic|underline|dark|light)\b', Name.Builtin),
- (r'\b\w+\b', Name.Other), # These are postprocessed below
- (r'.', Text),
- ],
- }
- def __init__(self, **options):
- from pygments.lexers._vimbuiltins import command, option, auto
- self._cmd = command
- self._opt = option
- self._aut = auto
- RegexLexer.__init__(self, **options)
- def is_in(self, w, mapping):
- r"""
- It's kind of difficult to decide if something might be a keyword
- in VimL because it allows you to abbreviate them. In fact,
- 'ab[breviate]' is a good example. :ab, :abbre, or :abbreviate are
- valid ways to call it so rather than making really awful regexps
- like::
- \bab(?:b(?:r(?:e(?:v(?:i(?:a(?:t(?:e)?)?)?)?)?)?)?)?\b
- we match `\b\w+\b` and then call is_in() on those tokens. See
- `scripts/get_vimkw.py` for how the lists are extracted.
- """
- p = bisect(mapping, (w,))
- if p > 0:
- if mapping[p-1][0] == w[:len(mapping[p-1][0])] and \
- mapping[p-1][1][:len(w)] == w: return True
- if p < len(mapping):
- return mapping[p][0] == w[:len(mapping[p][0])] and \
- mapping[p][1][:len(w)] == w
- return False
- def get_tokens_unprocessed(self, text):
- # TODO: builtins are only subsequent tokens on lines
- # and 'keywords' only happen at the beginning except
- # for :au ones
- for index, token, value in \
- RegexLexer.get_tokens_unprocessed(self, text):
- if token is Name.Other:
- if self.is_in(value, self._cmd):
- yield index, Keyword, value
- elif self.is_in(value, self._opt) or \
- self.is_in(value, self._aut):
- yield index, Name.Builtin, value
- else:
- yield index, Text, value
- else:
- yield index, token, value
- class GettextLexer(RegexLexer):
- """
- Lexer for Gettext catalog files.
- *New in Pygments 0.9.*
- """
- name = 'Gettext Catalog'
- aliases = ['pot', 'po']
- filenames = ['*.pot', '*.po']
- mimetypes = ['application/x-gettext', 'text/x-gettext', 'text/gettext']
- tokens = {
- 'root': [
- (r'^#,\s.*?$', Keyword.Type),
- (r'^#:\s.*?$', Keyword.Declaration),
- #(r'^#$', Comment),
- (r'^(#|#\.\s|#\|\s|#~\s|#\s).*$', Comment.Single),
- (r'^(")([\w-]*:)(.*")$',
- bygroups(String, Name.Property, String)),
- (r'^".*"$', String),
- (r'^(msgid|msgid_plural|msgstr)(\s+)(".*")$',
- bygroups(Name.Variable, Text, String)),
- (r'^(msgstr\[)(\d)(\])(\s+)(".*")$',
- bygroups(Name.Variable, Number.Integer, Name.Variable, Text, String)),
- ]
- }
- class SquidConfLexer(RegexLexer):
- """
- Lexer for `squid <http://www.squid-cache.org/>`_ configuration files.
- *New in Pygments 0.9.*
- """
- name = 'SquidConf'
- aliases = ['squidconf', 'squid.conf', 'squid']
- filenames = ['squid.conf']
- mimetypes = ['text/x-squidconf']
- flags = re.IGNORECASE
- keywords = [ "acl", "always_direct", "announce_host",
- "announce_period", "announce_port", "announce_to",
- "anonymize_headers", "append_domain", "as_whois_server",
- "auth_param_basic", "authenticate_children",
- "authenticate_program", "authenticate_ttl", "broken_posts",
- "buffered_logs", "cache_access_log", "cache_announce",
- "cache_dir", "cache_dns_program", "cache_effective_group",
- "cache_effective_user", "cache_host", "cache_host_acl",
- "cache_host_domain", "cache_log", "cache_mem",
- "cache_mem_high", "cache_mem_low", "cache_mgr",
- "cachemgr_passwd", "cache_peer", "cache_peer_access",
- "cahce_replacement_policy", "cache_stoplist",
- "cache_stoplist_pattern", "cache_store_log", "cache_swap",
- "cache_swap_high", "cache_swap_log", "cache_swap_low",
- "client_db", "client_lifetime", "client_netmask",
- "connect_timeout", "coredump_dir", "dead_peer_timeout",
- "debug_options", "delay_access", "delay_class",
- "delay_initial_bucket_level", "delay_parameters",
- "delay_pools", "deny_info", "dns_children", "dns_defnames",
- "dns_nameservers", "dns_testnames", "emulate_httpd_log",
- "err_html_text", "fake_user_agent", "firewall_ip",
- "forwarded_for", "forward_snmpd_port", "fqdncache_size",
- "ftpget_options", "ftpget_program", "ftp_list_width",
- "ftp_passive", "ftp_user", "half_closed_clients",
- "header_access", "header_replace", "hierarchy_stoplist",
- "high_response_time_warning", "high_page_fault_warning",
- "htcp_port", "http_access", "http_anonymizer", "httpd_accel",
- "httpd_accel_host", "httpd_accel_port",
- "httpd_accel_uses_host_header", "httpd_accel_with_proxy",
- "http_port", "http_reply_access", "icp_access",
- "icp_hit_stale", "icp_port", "icp_query_timeout",
- "ident_lookup", "ident_lookup_access", "ident_timeout",
- "incoming_http_average", "incoming_icp_average",
- "inside_firewall", "ipcache_high", "ipcache_low",
- "ipcache_size", "local_domain", "local_ip", "logfile_rotate",
- "log_fqdn", "log_icp_queries", "log_mime_hdrs",
- "maximum_object_size", "maximum_single_addr_tries",
- "mcast_groups", "mcast_icp_query_timeout", "mcast_miss_addr",
- "mcast_miss_encode_key", "mcast_miss_port", "memory_pools",
- "memory_pools_limit", "memory_replacement_policy",
- "mime_table", "min_http_poll_cnt", "min_icp_poll_cnt",
- "minimum_direct_hops", "minimum_object_size",
- "minimum_retry_timeout", "miss_access", "negative_dns_ttl",
- "negative_ttl", "neighbor_timeout", "neighbor_type_domain",
- "netdb_high", "netdb_low", "netdb_ping_period",
- "netdb_ping_rate", "never_direct", "no_cache",
- "passthrough_proxy", "pconn_timeout", "pid_filename",
- "pinger_program", "positive_dns_ttl", "prefer_direct",
- "proxy_auth", "proxy_auth_realm", "query_icmp", "quick_abort",
- "quick_abort", "quick_abort_max", "quick_abort_min",
- "quick_abort_pct", "range_offset_limit", "read_timeout",
- "redirect_children", "redirect_program",
- "redirect_rewrites_host_header", "reference_age",
- "reference_age", "refresh_pattern", "reload_into_ims",
- "request_body_max_size", "request_size", "request_timeout",
- "shutdown_lifetime", "single_parent_bypass",
- "siteselect_timeout", "snmp_access", "snmp_incoming_address",
- "snmp_port", "source_ping", "ssl_proxy",
- "store_avg_object_size", "store_objects_per_bucket",
- "strip_query_terms", "swap_level1_dirs", "swap_level2_dirs",
- "tcp_incoming_address", "tcp_outgoing_address",
- "tcp_recv_bufsize", "test_reachability", "udp_hit_obj",
- "udp_hit_obj_size", "udp_incoming_address",
- "udp_outgoing_address", "unique_hostname", "unlinkd_program",
- "uri_whitespace", "useragent_log", "visible_hostname",
- "wais_relay", "wais_relay_host", "wais_relay_port",
- ]
- opts = [ "proxy-only", "weight", "ttl", "no-query", "default",
- "round-robin", "multicast-responder", "on", "off", "all",
- "deny", "allow", "via", "parent", "no-digest", "heap", "lru",
- "realm", "children", "credentialsttl", "none", "disable",
- "offline_toggle", "diskd", "q1", "q2",
- ]
- actions = [ "shutdown", "info", "parameter", "server_list",
- "client_list", r'squid\.conf',
- ]
- actions_stats = [ "objects", "vm_objects", "utilization",
- "ipcache", "fqdncache", "dns", "redirector", "io",
- "reply_headers", "filedescriptors", "netdb",
- ]
- actions_log = [ "status", "enable", "disable", "clear"]
- acls = [ "url_regex", "urlpath_regex", "referer_regex", "port",
- "proto", "req_mime_type", "rep_mime_type", "method",
- "browser", "user", "src", "dst", "time", "dstdomain", "ident",
- "snmp_community",
- ]
- ip_re = r'\b(?:\d{1,3}\.){3}\d{1,3}\b'
- def makelistre(list):
- return r'\b(?:'+'|'.join(list)+r')\b'
- tokens = {
- 'root': [
- (r'\s+', Text),
- (r'#', Comment, 'comment'),
- (makelistre(keywords), Keyword),
- (makelistre(opts), Name.Constant),
- # Actions
- (makelistre(actions), String),
- (r'stats/'+makelistre(actions), String),
- (r'log/'+makelistre(actions)+r'=', String),
- (makelistre(acls), Keyword),
- (ip_re+r'(?:/(?:'+ip_re+r')|\d+)?', Number),
- (r'\b\d+\b', Number),
- (r'\S+', Text),
- ],
- 'comment': [
- (r'\s*TAG:.*', String.Escape, '#pop'),
- (r'.*', Comment, '#pop'),
- ],
- }
- class DebianControlLexer(RegexLexer):
- """
- Lexer for Debian ``control`` files and ``apt-cache show <pkg>`` outputs.
- *New in Pygments 0.9.*
- """
- name = 'Debian Control file'
- aliases = ['control']
- filenames = ['control']
- tokens = {
- 'root': [
- (r'^(Description)', Keyword, 'description'),
- (r'^(Maintainer)(:\s*)', bygroups(Keyword, Text), 'maintainer'),
- (r'^((Build-)?Depends)', Keyword, 'depends'),
- (r'^((?:Python-)?Version)(:\s*)([^\s]+)$',
- bygroups(Keyword, Text, Number)),
- (r'^((?:Installed-)?Size)(:\s*)([^\s]+)$',
- bygroups(Keyword, Text, Number)),
- (r'^(MD5Sum|SHA1|SHA256)(:\s*)([^\s]+)$',
- bygroups(Keyword, Text, Number)),
- (r'^([a-zA-Z\-0-9\.]*?)(:\s*)(.*?)$',
- bygroups(Keyword, Whitespace, String)),
- ],
- 'maintainer': [
- (r'<[^>]+>', Generic.Strong),
- (r'<[^>]+>$', Generic.Strong, '#pop'),
- (r',\n?', Text),
- (r'.', Text),
- ],
- 'description': [
- (r'(.*)(Homepage)(: )([^\s]+)', bygroups(Text, String, Name, Name.Class)),
- (r':.*\n', Generic.Strong),
- (r' .*\n', Text),
- ('', Text, '#pop'),
- ],
- 'depends': [
- (r':\s*', Text),
- (r'(\$)(\{)(\w+\s*:\s*\w+)', bygroups(Operator, Text, Name.Entity)),
- (r'\(', Text, 'depend_vers'),
- (r',', Text),
- (r'\|', Operator),
- (r'[\s]+', Text),
- (r'[}\)]\s*$', Text, '#pop'),
- (r'[}]', Text),
- (r'[^,]$', Name.Function, '#pop'),
- (r'([\+\.a-zA-Z0-9-][\s\n]*)', Name.Function),
- ],
- 'depend_vers': [
- (r'\),', Text, '#pop'),
- (r'\)[^,]', Text, '#pop:2'),
- (r'([><=]+)(\s*)([^\)]+)', bygroups(Operator, Text, Number))
- ]
- }
- class YamlLexerContext(LexerContext):
- """Indentation context for the YAML lexer."""
- def __init__(self, *args, **kwds):
- super(YamlLexerContext, self).__init__(*args, **kwds)
- self.indent_stack = []
- self.indent = -1
- self.next_indent = 0
- self.block_scalar_indent = None
- class YamlLexer(ExtendedRegexLexer):
- """
- Lexer for `YAML <http://yaml.org/>`_, a human-friendly data serialization
- language.
- *New in Pygments 0.11.*
- """
- name = 'YAML'
- aliases = ['yaml']
- filenames = ['*.yaml', '*.yml']
- mimetypes = ['text/x-yaml']
- def something(token_class):
- """Do not produce empty tokens."""
- def callback(lexer, match, context):
- text = match.group()
- if not text:
- return
- yield match.start(), token_class, text
- context.pos = match.end()
- return callback
- def reset_indent(token_class):
- """Reset the indentation levels."""
- def callback(lexer, match, context):
- text = match.group()
- context.indent_stack = []
- context.indent = -1
- context.next_indent = 0
- context.block_scalar_indent = None
- yield match.start(), token_class, text
- context.pos = match.end()
- return callback
- def save_indent(token_class, start=False):
- """Save a possible indentation level."""
- def callback(lexer, match, context):
- text = match.group()
- extra = ''
- if start:
- context.next_indent = len(text)
- if context.next_indent < context.indent:
- while context.next_indent < context.indent:
- context.indent = context.indent_stack.pop()
- if context.next_indent > context.indent:
- extra = text[context.indent:]
- text = text[:context.indent]
- else:
- context.next_indent += len(text)
- if text:
- yield match.start(), token_class, text
- if extra:
- yield match.start()+len(text), token_class.Error, extra
- context.pos = match.end()
- return callback
- def set_indent(token_class, implicit=False):
- """Set the previously saved indentation level."""
- def callback(lexer, match, context):
- text = match.group()
- if context.indent < context.next_indent:
- context.indent_stack.append(context.indent)
- context.indent = context.next_indent
- if not implicit:
- context.next_indent += len(text)
- yield match.start(), token_class, text
- context.pos = match.end()
- return callback
- def set_block_scalar_indent(token_class):
- """Set an explicit indentation level for a block scalar."""
- def callback(lexer, match, context):
- text = match.group()
- context.block_scalar_indent = None
- if not text:
- return
- increment = match.group(1)
- if increment:
- current_indent = max(context.indent, 0)
- increment = int(increment)
- context.block_scalar_indent = current_indent + increment
- if text:
- yield match.start(), token_class, text
- context.pos = match.end()
- return callback
- def parse_block_scalar_empty_line(indent_token_class, content_token_class):
- """Process an empty line in a block scalar."""
- def callback(lexer, match, context):
- text = match.group()
- if (context.block_scalar_indent is None or
- len(text) <= context.block_scalar_indent):
- if text:
- yield match.start(), indent_token_class, text
- else:
- indentation = text[:context.block_scalar_indent]
- content = text[context.block_scalar_indent:]
- yield match.start(), indent_token_class, indentation
- yield (match.start()+context.block_scalar_indent,
- content_token_class, content)
- context.pos = match.end()
- return callback
- def parse_block_scalar_indent(token_class):
- """Process indentation spaces in a block scalar."""
- def callback(lexer, match, context):
- text = match.group()
- if context.block_scalar_indent is None:
- if len(text) <= max(context.indent, 0):
- context.stack.pop()
- context.stack.pop()
- return
- context.block_scalar_indent = len(text)
- else:
- if len(text) < context.block_scalar_indent:
- context.stack.pop()
- context.stack.pop()
- return
- if text:
- yield match.start(), token_class, text
- context.pos = match.end()
- return callback
- def parse_plain_scalar_indent(token_class):
- """Process indentation spaces in a plain scalar."""
- def callback(lexer, match, context):
- text = match.group()
- if len(text) <= context.indent:
- context.stack.pop()
- context.stack.pop()
- return
- if text:
- yield match.start(), token_class, text
- context.pos = match.end()
- return callback
- tokens = {
- # the root rules
- 'root': [
- # ignored whitespaces
- (r'[ ]+(?=#|$)', Text),
- # line breaks
- (r'\n+', Text),
- # a comment
- (r'#[^\n]*', Comment.Single),
- # the '%YAML' directive
- (r'^%YAML(?=[ ]|$)', reset_indent(Name.Tag), 'yaml-directive'),
- # the %TAG directive
- (r'^%TAG(?=[ ]|$)', reset_indent(Name.Tag), 'tag-directive'),
- # document start and document end indicators
- (r'^(?:---|\.\.\.)(?=[ ]|$)', reset_indent(Name.Namespace),
- 'block-line'),
- # indentation spaces
- (r'[ ]*(?![ \t\n\r\f\v]|$)', save_indent(Text, start=True),
- ('block-line', 'indentation')),
- ],
- # trailing whitespaces after directives or a block scalar indicator
- 'ignored-line': [
- # ignored whitespaces
- (r'[ ]+(?=#|$)', Text),
- # a comment
- (r'#[^\n]*', Comment.Single),
- # line break
- (r'\n', Text, '#pop:2'),
- ],
- # the %YAML directive
- 'yaml-directive': [
- # the version number
- (r'([ ]+)([0-9]+\.[0-9]+)',
- bygroups(Text, Number), 'ignored-line'),
- ],
- # the %YAG directive
- 'tag-directive': [
- # a tag handle and the corresponding prefix
- (r'([ ]+)(!|![0-9A-Za-z_-]*!)'
- r'([ ]+)(!|!?[0-9A-Za-z;/?:@&=+$,_.!~*\'()\[\]%-]+)',
- bygroups(Text, Keyword.Type, Text, Keyword.Type),
- 'ignored-line'),
- ],
- # block scalar indicators and indentation spaces
- 'indentation': [
- # trailing whitespaces are ignored
- (r'[ ]*$', something(Text), '#pop:2'),
- # whitespaces preceeding block collection indicators
- (r'[ ]+(?=[?:-](?:[ ]|$))', save_indent(Text)),
- # block collection indicators
- (r'[?:-](?=[ ]|$)', set_indent(Punctuation.Indicator)),
- # the beginning a block line
- (r'[ ]*', save_indent(Text), '#pop'),
- ],
- # an indented line in the block context
- 'block-line': [
- # the line end
- (r'[ ]*(?=#|$)', something(Text), '#pop'),
- # whitespaces separating tokens
- (r'[ ]+', Text),
- # tags, anchors and aliases,
- include('descriptors'),
- # block collections and scalars
- include('block-nodes'),
- # flow collections and quoted scalars
- include('flow-nodes'),
- # a plain scalar
- (r'(?=[^ \t\n\r\f\v?:,\[\]{}#&*!|>\'"%@`-]|[?:-][^ \t\n\r\f\v])',
- something(Name.Variable),
- 'plain-scalar-in-block-context'),
- ],
- # tags, anchors, aliases
- 'descriptors' : [
- # a full-form tag
- (r'!<[0-9A-Za-z;/?:@&=+$,_.!~*\'()\[\]%-]+>', Keyword.Type),
- # a tag in the form '!', '!suffix' or '!handle!suffix'
- (r'!(?:[0-9A-Za-z_-]+)?'
- r'(?:![0-9A-Za-z;/?:@&=+$,_.!~*\'()\[\]%-]+)?', Keyword.Type),
- # an anchor
- (r'&[0-9A-Za-z_-]+', Name.Label),
- # an alias
- (r'\*[0-9A-Za-z_-]+', Name.Variable),
- ],
- # block collections and scalars
- 'block-nodes': [
- # implicit key
- (r':(?=[ ]|$)', set_indent(Punctuation.Indicator, implicit=True)),
- # literal and folded scalars
- (r'[|>]', Punctuation.Indicator,
- ('block-scalar-content', 'block-scalar-header')),
- ],
- # flow collections and quoted scalars
- 'flow-nodes': [
- # a flow sequence
- (r'\[', Punctuation.Indicator, 'flow-sequence'),
- # a flow mapping
- (r'\{', Punctuation.Indicator, 'flow-mapping'),
- # a single-quoted scalar
- (r'\'', String, 'single-quoted-scalar'),
- # a double-quoted scalar
- (r'\"', String, 'double-quoted-scalar'),
- ],
- # the content of a flow collection
- 'flow-collection': [
- # whitespaces
- (r'[ ]+', Text),
- # line breaks
- (r'\n+', Text),
- # a comment
- (r'#[^\n]*', Comment.Single),
- # simple indicators
- (r'[?:,]', Punctuation.Indicator),
- # tags, anchors and aliases
- include('descriptors'),
- # nested collections and quoted scalars
- include('flow-nodes'),
- # a plain scalar
- (r'(?=[^ \t\n\r\f\v?:,\[\]{}#&*!|>\'"%@`])',
- something(Name.Variable),
- 'plain-scalar-in-flow-context'),
- ],
- # a flow sequence indicated by '[' and ']'
- 'flow-sequence': [
- # include flow collection rules
- include('flow-collection'),
- # the closing indicator
- (r'\]', Punctuation.Indicator, '#pop'),
- ],
- # a flow mapping indicated by '{' and '}'
- 'flow-mapping': [
- # include flow collection rules
- include('flow-collection'),
- # the closing indicator
- (r'\}', Punctuation.Indicator, '#pop'),
- ],
- # block scalar lines
- 'block-scalar-content': [
- # line break
- (r'\n', Text),
- # empty line
- (r'^[ ]+$',
- parse_block_scalar_empty_line(Text, Name.Constant)),
- # indentation spaces (we may leave the state here)
- (r'^[ ]*', parse_block_scalar_indent(Text)),
- # line content
- (r'[^\n\r\f\v]+', Name.Constant),
- ],
- # the content of a literal or folded scalar
- 'block-scalar-header': [
- # indentation indicator followed by chomping flag
- (r'([1-9])?[+-]?(?=[ ]|$)',
- set_block_scalar_indent(Punctuation.Indicator),
- 'ignored-line'),
- # chomping flag followed by indentation indicator
- (r'[+-]?([1-9])?(?=[ ]|$)',
- set_block_scalar_indent(Punctuation.Indicator),
- 'ignored-line'),
- ],
- # ignored and regular whitespaces in quoted scalars
- 'quoted-scalar-whitespaces': [
- # leading and trailing whitespaces are ignored
- (r'^[ ]+|[ ]+$', Text),
- # line breaks are ignored
- (r'\n+', Text),
- # other whitespaces are a part of the value
- (r'[ ]+', Name.Variable),
- ],
- # single-quoted scalars
- 'single-quoted-scalar': [
- # include whitespace and line break rules
- include('quoted-scalar-whitespaces'),
- # escaping of the quote character
- (r'\'\'', String.Escape),
- # regular non-whitespace characters
- (r'[^ \t\n\r\f\v\']+', String),
- # the closing quote
- (r'\'', String, '#pop'),
- ],
- # double-quoted scalars
- 'double-quoted-scalar': [
- # include whitespace and line break rules
- include('quoted-scalar-whitespaces'),
- # escaping of special characters
- (r'\\[0abt\tn\nvfre "\\N_LP]', String),
- # escape codes
- (r'\\(?:x[0-9A-Fa-f]{2}|u[0-9A-Fa-f]{4}|U[0-9A-Fa-f]{8})',
- String.Escape),
- # regular non-whitespace characters
- (r'[^ \t\n\r\f\v\"\\]+', String),
- # the closing quote
- (r'"', String, '#pop'),
- ],
- # the beginning of a new line while scanning a plain scalar
- 'plain-scalar-in-block-context-new-line': [
- # empty lines
- (r'^[ ]+$', Text),
- # line breaks
- (r'\n+', Text),
- # document start and document end indicators
- (r'^(?=---|\.\.\.)', something(Name.Namespace), '#pop:3'),
- # indentation spaces (we may leave the block line state here)
- (r'^[ ]*', parse_plain_scalar_indent(Text), '#pop'),
- ],
- # a plain scalar in the block context
- 'plain-scalar-in-block-context': [
- # the scalar ends with the ':' indicator
- (r'[ ]*(?=:[ ]|:$)', something(Text), '#pop'),
- # the scalar ends with whitespaces followed by a comment
- (r'[ ]+(?=#)', Text, '#pop'),
- # trailing whitespaces are ignored
- (r'[ ]+$', Text),
- # line breaks are ignored
- (r'\n+', Text, 'plain-scalar-in-block-context-new-line'),
- # other whitespaces are a part of the value
- (r'[ ]+', Literal.Scalar.Plain),
- # regular non-whitespace characters
- (r'(?::(?![ \t\n\r\f\v])|[^ \t\n\r\f\v:])+', Literal.Scalar.Plain),
- ],
- # a plain scalar is the flow context
- 'plain-scalar-in-flow-context': [
- # the scalar ends with an indicator character
- (r'[ ]*(?=[,:?\[\]{}])', something(Text), '#pop'),
- # the scalar ends with a comment
- (r'[ ]+(?=#)', Text, '#pop'),
- # leading and trailing whitespaces are ignored
- (r'^[ ]+|[ ]+$', Text),
- # line breaks are ignored
- (r'\n+', Text),
- # other whitespaces are a part of the value
- (r'[ ]+', Name.Variable),
- # regular non-whitespace characters
- (r'[^ \t\n\r\f\v,:?\[\]{}]+', Name.Variable),
- ],
- }
- def get_tokens_unprocessed(self, text=None, context=None):
- if context is None:
- context = YamlLexerContext(text, 0)
- return super(YamlLexer, self).get_tokens_unprocessed(text, context)
- class LighttpdConfLexer(RegexLexer):
- """
- Lexer for `Lighttpd <http://lighttpd.net/>`_ configuration files.
- *New in Pygments 0.11.*
- """
- name = 'Lighttpd configuration file'
- aliases = ['lighty', 'lighttpd']
- filenames = []
- mimetypes = ['text/x-lighttpd-conf']
- tokens = {
- 'root': [
- (r'#.*\n', Comment.Single),
- (r'/\S*', Name), # pathname
- (r'[a-zA-Z._-]+', Keyword),
- (r'\d+\.\d+\.\d+\.\d+(?:/\d+)?', Number),
- (r'[0-9]+', Number),
- (r'=>|=~|\+=|==|=|\+', Operator),
- (r'\$[A-Z]+', Name.Builtin),
- (r'[(){}\[\],]', Punctuation),
- (r'"([^"\\]*(?:\\.[^"\\]*)*)"', String.Double),
- (r'\s+', Text),
- ],
- }
- class NginxConfLexer(RegexLexer):
- """
- Lexer for `Nginx <http://nginx.net/>`_ configuration files.
- *New in Pygments 0.11.*
- """
- name = 'Nginx configuration file'
- aliases = ['nginx']
- filenames = []
- mimetypes = ['text/x-nginx-conf']
- tokens = {
- 'root': [
- (r'(include)(\s+)([^\s;]+)', bygroups(Keyword, Text, Name)),
- (r'[^\s;#]+', Keyword, 'stmt'),
- include('base'),
- ],
- 'block': [
- (r'}', Punctuation, '#pop:2'),
- (r'[^\s;#]+', Keyword.Namespace, 'stmt'),
- include('base'),
- ],
- 'stmt': [
- (r'{', Punctuation, 'block'),
- (r';', Punctuation, '#pop'),
- include('base'),
- ],
- 'base': [
- (r'#.*\n', Comment.Single),
- (r'on|off', Name.Constant),
- (r'\$[^\s;#]+', Name.Variable),
- (r'([a-z0-9.-]+)(:)([0-9]+)',
- bygroups(Name, Punctuation, Number.Integer)),
- (r'[a-z-]+/[a-z-]+', Name), # mimetype
- #(r'[a-zA-Z._-]+', Keyword),
- (r'[0-9]+[km]?\b', Number.Integer),
- (r'(~)(\s*)([^\s{]+)', bygroups(Punctuation, Text, String.Regex)),
- (r'[:=~]', Punctuation),
- (r'[^\s;#{}$]+', String), # catch all
- (r'/[^\s;#]*', Name), # pathname
- (r'\s+', Text),
- ],
- }