Many resources are needed to download a project. Please understand that we have to compensate our server costs. Thank you in advance.
Project price only 1 $
You can buy this project and download/modify it how often you want.
pygments.lexers.text.py Maven / Gradle / Ivy
# -*- coding: utf-8 -*-
"""
pygments.lexers.text
~~~~~~~~~~~~~~~~~~~~
Lexers for non-source code file types.
:copyright: Copyright 2006-2012 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
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, ClassNotFound
from pygments.lexers.other import BashLexer
__all__ = ['IniLexer', 'PropertiesLexer', 'SourcesListLexer', 'BaseMakefileLexer',
'MakefileLexer', 'DiffLexer', 'IrcLogsLexer', 'TexLexer',
'GroffLexer', 'ApacheConfLexer', 'BBCodeLexer', 'MoinWikiLexer',
'RstLexer', 'VimLexer', 'GettextLexer', 'SquidConfLexer',
'DebianControlLexer', 'DarcsPatchLexer', 'YamlLexer',
'LighttpdConfLexer', 'NginxConfLexer', 'CMakeLexer', 'HttpLexer',
'PyPyLogLexer']
class IniLexer(RegexLexer):
"""
Lexer for configuration files in INI style.
"""
name = 'INI'
aliases = ['ini', 'cfg']
filenames = ['*.ini', '*.cfg']
mimetypes = ['text/x-ini']
tokens = {
'root': [
(r'\s+', Text),
(r'[;#].*?$', Comment),
(r'\[.*?\]$', Keyword),
(r'(.*?)([ \t]*)(=)([ \t]*)(.*(?:\n[ \t].+)*)',
bygroups(Name.Attribute, Text, Operator, Text, String))
]
}
def analyse_text(text):
npos = text.find('\n')
if npos < 3:
return False
return text[0] == '[' and text[npos-1] == ']'
class PropertiesLexer(RegexLexer):
"""
Lexer for configuration files in Java's properties format.
*New in Pygments 1.4.*
"""
name = 'Properties'
aliases = ['properties']
filenames = ['*.properties']
mimetypes = ['text/x-java-properties']
tokens = {
'root': [
(r'\s+', Text),
(r'(?:[;#]|//).*$', Comment),
(r'(.*?)([ \t]*)([=:])([ \t]*)(.*(?:(?<=\\)\n.*)*)',
bygroups(Name.Attribute, Text, Operator, Text, String)),
],
}
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.*', 'GNUmakefile']
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 = 'Base 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'(?s)"(\\\\|\\.|[^"\\])*"', String.Double),
(r"(?s)'(\\\\|\\.|[^'\\])*'", 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', 'udiff']
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'([Ii]ndex|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
DPATCH_KEYWORDS = ['hunk', 'addfile', 'adddir', 'rmfile', 'rmdir', 'move',
'replace']
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),
(r'}', Operator),
(r'(\[)((?:TAG )?)(.*)(\n)(.*)(\*\*)(\d+)(\s?)(\])',
bygroups(Operator, Keyword, Name, Text, Name, Operator,
Literal.Date, Text, Operator)),
(r'(\[)((?:TAG )?)(.*)(\n)(.*)(\*\*)(\d+)(\s?)',
bygroups(Operator, Keyword, Name, Text, Name, Operator,
Literal.Date, Text), 'comment'),
(r'New patches:', Generic.Heading),
(r'Context:', Generic.Heading),
(r'Patch bundle hash:', Generic.Heading),
(r'(\s*)(%s)(.*\n)' % '|'.join(DPATCH_KEYWORDS),
bygroups(Text, Keyword, Text)),
(r'\+', Generic.Inserted, "insert"),
(r'-', Generic.Deleted, "delete"),
(r'.*\n', Text),
],
'comment': [
(r'[^\]].*\n', Comment),
(r'\]', Operator, "#pop"),
],
'specialText': [ # darcs add [_CODE_] special operators for clarity
(r'\n', Text, "#pop"), # line-based
(r'\[_[^_]*_]', Operator),
],
'insert': [
include('specialText'),
(r'\[', Generic.Inserted),
(r'[^\n\[]+', Generic.Inserted),
],
'delete': [
include('specialText'),
(r'\[', Generic.Deleted),
(r'[^\n\[]+', Generic.Deleted),
],
}
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}|?)\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'[^[]+', Text),
# tag/end tag begin
(r'\[/?\w+', Keyword, 'tag'),
# stray bracket
(r'\[', Text),
],
'tag': [
(r'\s+', Text),
# attribute with value
(r'(\w+)(=)("?[^\s"\]]+"?)',
bygroups(Name.Attribute, Operator, String)),
# tag argument (a la [color=green])
(r'(=)("?[^\s"\]]+"?)',
bygroups(Operator, String)),
# tag end
(r'\]', Keyword, '#pop'),
],
}
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'(\.)(\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'\\\(.{2}', 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[:1] != '.':
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 `_ 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", "text/prs.fallenstein.rst"]
flags = re.MULTILINE
def _handle_sourcecode(self, match):
from pygments.lexers import get_lexer_by_name
# 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
# from docutils.parsers.rst.states
closers = u'\'")]}>\u2019\u201d\xbb!?'
unicode_delimiters = u'\u2010\u2011\u2012\u2013\u2014\u00a0'
end_string_suffix = (r'((?=$)|(?=[-/:.,; \n\x00%s%s]))'
% (re.escape(unicode_delimiters),
re.escape(closers)))
tokens = {
'root': [
# Heading with overline
(r'^(=+|-+|`+|:+|\.+|\'+|"+|~+|\^+|_+|\*+|\++|#+)([ \t]*\n)'
r'(.+)(\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'))),
# Line blocks
(r'^(\s*)(\|)( .+\n(?:\| .+\n)*)',
bygroups(Text, Operator, 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,
using(this, state='inline'))),
# A reference target
(r'^( *\.\.)(\s*)(_(?:[^:\\]|\\.)+:)(.*?)$',
bygroups(Punctuation, Text, Name.Tag, using(this, state='inline'))),
# A footnote/citation target
(r'^( *\.\.)(\s*)(\[.+\])(.*?)$',
bygroups(Punctuation, Text, Name.Tag, using(this, state='inline'))),
# A substitution def
(r'^( *\.\.)(\s*)(\|.+\|)(\s*)([\w:-]+?)(::)(?:([ \t]*)(.*))',
bygroups(Punctuation, Text, Name.Tag, Text, Operator.Word,
Punctuation, Text, using(this, state='inline'))),
# Comments
(r'^ *\.\..*(\n( +.*\n|\n)+)?', Comment.Preproc),
# Field list
(r'^( *)(:[a-zA-Z-]+:)(\s*)$', bygroups(Text, Name.Class, Text)),
(r'^( *)(:.*?:)([ \t]+)(.*?)$',
bygroups(Text, Name.Class, Text, Name.Function)),
# Definition list
(r'^([^ ].*(?)(`__?)', # reference with inline target
bygroups(String, String.Interpol, String)),
(r'`.+?`__?', String), # reference
(r'(`.+?`)(:[a-zA-Z0-9:-]+?:)?',
bygroups(Name.Variable, Name.Attribute)), # role
(r'(:[a-zA-Z0-9:-]+?:)(`.+?`)',
bygroups(Name.Attribute, Name.Variable)), # role (content first)
(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'``' + end_string_suffix, 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', '.exrc', '.gvimrc',
'_vimrc', '_exrc', '_gvimrc', 'vimrc', 'gvimrc']
mimetypes = ['text/x-vim']
flags = re.MULTILINE
tokens = {
'root': [
(r'^\s*".*', Comment),
(r'[ \t]+', Text),
# TODO: regexes can have other delims
(r'/(\\\\|\\/|[^\n/])*/', String.Regex),
(r'"(\\\\|\\"|[^\n"])*"', String.Double),
(r"'(\\\\|\\'|[^\n'])*'", String.Single),
# Who decided that doublequote was a good comment character??
(r'(?<=\s)"[^\-:.%#=*].*', Comment),
(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'^(")([A-Za-z-]+:)(.*")$',
bygroups(String, Name.Property, String)),
(r'^".*"$', 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 `_ files.
*New in Pygments 1.2.*
"""
name = 'CMake'
aliases = ['cmake']
filenames = ['*.cmake', 'CMakeLists.txt']
mimetypes = ['text/x-cmake']
tokens = {
'root': [
#(r'(ADD_CUSTOM_COMMAND|ADD_CUSTOM_TARGET|ADD_DEFINITIONS|'
# r'ADD_DEPENDENCIES|ADD_EXECUTABLE|ADD_LIBRARY|ADD_SUBDIRECTORY|'
# r'ADD_TEST|AUX_SOURCE_DIRECTORY|BUILD_COMMAND|BUILD_NAME|'
# r'CMAKE_MINIMUM_REQUIRED|CONFIGURE_FILE|CREATE_TEST_SOURCELIST|'
# r'ELSE|ELSEIF|ENABLE_LANGUAGE|ENABLE_TESTING|ENDFOREACH|'
# r'ENDFUNCTION|ENDIF|ENDMACRO|ENDWHILE|EXEC_PROGRAM|'
# r'EXECUTE_PROCESS|EXPORT_LIBRARY_DEPENDENCIES|FILE|FIND_FILE|'
# r'FIND_LIBRARY|FIND_PACKAGE|FIND_PATH|FIND_PROGRAM|FLTK_WRAP_UI|'
# r'FOREACH|FUNCTION|GET_CMAKE_PROPERTY|GET_DIRECTORY_PROPERTY|'
# r'GET_FILENAME_COMPONENT|GET_SOURCE_FILE_PROPERTY|'
# r'GET_TARGET_PROPERTY|GET_TEST_PROPERTY|IF|INCLUDE|'
# r'INCLUDE_DIRECTORIES|INCLUDE_EXTERNAL_MSPROJECT|'
# r'INCLUDE_REGULAR_EXPRESSION|INSTALL|INSTALL_FILES|'
# r'INSTALL_PROGRAMS|INSTALL_TARGETS|LINK_DIRECTORIES|'
# r'LINK_LIBRARIES|LIST|LOAD_CACHE|LOAD_COMMAND|MACRO|'
# r'MAKE_DIRECTORY|MARK_AS_ADVANCED|MATH|MESSAGE|OPTION|'
# r'OUTPUT_REQUIRED_FILES|PROJECT|QT_WRAP_CPP|QT_WRAP_UI|REMOVE|'
# r'REMOVE_DEFINITIONS|SEPARATE_ARGUMENTS|SET|'
# r'SET_DIRECTORY_PROPERTIES|SET_SOURCE_FILES_PROPERTIES|'
# r'SET_TARGET_PROPERTIES|SET_TESTS_PROPERTIES|SITE_NAME|'
# r'SOURCE_GROUP|STRING|SUBDIR_DEPENDS|SUBDIRS|'
# r'TARGET_LINK_LIBRARIES|TRY_COMPILE|TRY_RUN|UNSET|'
# r'USE_MANGLED_MESA|UTILITY_SOURCE|VARIABLE_REQUIRES|'
# r'VTK_MAKE_INSTANTIATOR|VTK_WRAP_JAVA|VTK_WRAP_PYTHON|'
# r'VTK_WRAP_TCL|WHILE|WRITE_FILE|'
# r'COUNTARGS)\b', Name.Builtin, 'args'),
(r'\b([A-Za-z_]+)([ \t]*)(\()', bygroups(Name.Builtin, Text,
Punctuation), 'args'),
include('keywords'),
include('ws')
],
'args': [
(r'\(', Punctuation, '#push'),
(r'\)', Punctuation, '#pop'),
(r'(\${)(.+?)(})', bygroups(Operator, Name.Variable, Operator)),
(r'(?s)".*?"', String.Double),
(r'\\\S+', String),
(r'[^\)$"# \t\n]+', String),
(r'\n', Text), # explicitly legal
include('keywords'),
include('ws')
],
'string': [
],
'keywords': [
(r'\b(WIN32|UNIX|APPLE|CYGWIN|BORLAND|MINGW|MSVC|MSVC_IDE|MSVC60|'
r'MSVC70|MSVC71|MSVC80|MSVC90)\b', Keyword),
],
'ws': [
(r'[ \t]+', Text),
(r'#.+\n', Comment),
]
}
class HttpLexer(RegexLexer):
"""
Lexer for HTTP sessions.
*New in Pygments 1.5.*
"""
name = 'HTTP'
aliases = ['http']
flags = re.DOTALL
def header_callback(self, match):
if match.group(1).lower() == 'content-type':
content_type = match.group(5).strip()
if ';' in content_type:
content_type = content_type[:content_type.find(';')].strip()
self.content_type = content_type
yield match.start(1), Name.Attribute, match.group(1)
yield match.start(2), Text, match.group(2)
yield match.start(3), Operator, match.group(3)
yield match.start(4), Text, match.group(4)
yield match.start(5), Literal, match.group(5)
yield match.start(6), Text, match.group(6)
def continuous_header_callback(self, match):
yield match.start(1), Text, match.group(1)
yield match.start(2), Literal, match.group(2)
yield match.start(3), Text, match.group(3)
def content_callback(self, match):
content_type = getattr(self, 'content_type', None)
content = match.group()
offset = match.start()
if content_type:
from pygments.lexers import get_lexer_for_mimetype
try:
lexer = get_lexer_for_mimetype(content_type)
except ClassNotFound:
pass
else:
for idx, token, value in lexer.get_tokens_unprocessed(content):
yield offset + idx, token, value
return
yield offset, Text, content
tokens = {
'root': [
(r'(GET|POST|PUT|DELETE|HEAD|OPTIONS|TRACE)( +)([^ ]+)( +)'
r'(HTTPS?)(/)(1\.[01])(\r?\n|$)',
bygroups(Name.Function, Text, Name.Namespace, Text,
Keyword.Reserved, Operator, Number, Text),
'headers'),
(r'(HTTPS?)(/)(1\.[01])( +)(\d{3})( +)([^\r\n]+)(\r?\n|$)',
bygroups(Keyword.Reserved, Operator, Number, Text, Number,
Text, Name.Exception, Text),
'headers'),
],
'headers': [
(r'([^\s:]+)( *)(:)( *)([^\r\n]+)(\r?\n|$)', header_callback),
(r'([\t ]+)([^\r\n]+)(\r?\n|$)', continuous_header_callback),
(r'\r?\n', Text, 'content')
],
'content': [
(r'.+', content_callback)
]
}
class PyPyLogLexer(RegexLexer):
"""
Lexer for PyPy log files.
*New in Pygments 1.5.*
"""
name = "PyPy Log"
aliases = ["pypylog", "pypy"]
filenames = ["*.pypylog"]
mimetypes = ['application/x-pypylog']
tokens = {
"root": [
(r"\[\w+\] {jit-log-.*?$", Keyword, "jit-log"),
(r"\[\w+\] {jit-backend-counts$", Keyword, "jit-backend-counts"),
include("extra-stuff"),
],
"jit-log": [
(r"\[\w+\] jit-log-.*?}$", Keyword, "#pop"),
(r"^\+\d+: ", Comment),
(r"[ifp]\d+", Name),
(r"ptr\d+", Name),
(r"(\()(\w+(?:\.\w+)?)(\))",
bygroups(Punctuation, Name.Builtin, Punctuation)),
(r"[\[\]=,()]", Punctuation),
(r"(\d+\.\d+|inf|-inf)", Number.Float),
(r"-?\d+", Number.Integer),
(r"'.*'", String),
(r"(None|descr|ConstClass|ConstPtr|TargetToken)", Name),
(r"<.*?>", Name.Builtin),
(r"(label|debug_merge_point|jump|finish)", Name.Class),
(r"(int_add_ovf|int_add|int_sub_ovf|int_sub|int_mul_ovf|int_mul|"
r"int_floordiv|int_mod|int_lshift|int_rshift|int_and|int_or|"
r"int_xor|int_eq|int_ne|int_ge|int_gt|int_le|int_lt|int_is_zero|"
r"int_is_true|"
r"uint_floordiv|uint_ge|uint_lt|"
r"float_add|float_sub|float_mul|float_truediv|float_neg|"
r"float_eq|float_ne|float_ge|float_gt|float_le|float_lt|float_abs|"
r"ptr_eq|ptr_ne|instance_ptr_eq|instance_ptr_ne|"
r"cast_int_to_float|cast_float_to_int|"
r"force_token|quasiimmut_field|same_as|virtual_ref_finish|"
r"virtual_ref|mark_opaque_ptr|"
r"call_may_force|call_assembler|call_loopinvariant|"
r"call_release_gil|call_pure|call|"
r"new_with_vtable|new_array|newstr|newunicode|new|"
r"arraylen_gc|"
r"getarrayitem_gc_pure|getarrayitem_gc|setarrayitem_gc|"
r"getarrayitem_raw|setarrayitem_raw|getfield_gc_pure|"
r"getfield_gc|getinteriorfield_gc|setinteriorfield_gc|"
r"getfield_raw|setfield_gc|setfield_raw|"
r"strgetitem|strsetitem|strlen|copystrcontent|"
r"unicodegetitem|unicodesetitem|unicodelen|"
r"guard_true|guard_false|guard_value|guard_isnull|"
r"guard_nonnull_class|guard_nonnull|guard_class|guard_no_overflow|"
r"guard_not_forced|guard_no_exception|guard_not_invalidated)",
Name.Builtin),
include("extra-stuff"),
],
"jit-backend-counts": [
(r"\[\w+\] jit-backend-counts}$", Keyword, "#pop"),
(r":", Punctuation),
(r"\d+", Number),
include("extra-stuff"),
],
"extra-stuff": [
(r"\s+", Text),
(r"#.*?$", Comment),
],
}
