kr.motd.maven.sphinx.dist.pygments.lexers.html.py Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of sphinx-maven-plugin Show documentation
Show all versions of sphinx-maven-plugin Show documentation
Maven plugin that creates the site with Sphinx
# -*- coding: utf-8 -*-
"""
pygments.lexers.html
~~~~~~~~~~~~~~~~~~~~
Lexers for HTML, XML and related markup.
:copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
from pygments.lexer import RegexLexer, ExtendedRegexLexer, include, bygroups, \
default, using
from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
Punctuation
from pygments.util import looks_like_xml, html_doctype_matches
from pygments.lexers.javascript import JavascriptLexer
from pygments.lexers.jvm import ScalaLexer
from pygments.lexers.css import CssLexer, _indentation, _starts_block
from pygments.lexers.ruby import RubyLexer
__all__ = ['HtmlLexer', 'DtdLexer', 'XmlLexer', 'XsltLexer', 'HamlLexer',
'ScamlLexer', 'JadeLexer']
class HtmlLexer(RegexLexer):
"""
For HTML 4 and XHTML 1 markup. Nested JavaScript and CSS is highlighted
by the appropriate lexer.
"""
name = 'HTML'
aliases = ['html']
filenames = ['*.html', '*.htm', '*.xhtml', '*.xslt']
mimetypes = ['text/html', 'application/xhtml+xml']
flags = re.IGNORECASE | re.DOTALL
tokens = {
'root': [
('[^<&]+', Text),
(r'&\S*?;', Name.Entity),
(r'\<\!\[CDATA\[.*?\]\]\>', Comment.Preproc),
('', Comment, '#pop'),
('-', Comment),
],
'tag': [
(r'\s+', Text),
(r'([\w:-]+\s*)(=)(\s*)', bygroups(Name.Attribute, Operator, Text),
'attr'),
(r'[\w:-]+', Name.Attribute),
(r'(/?)(\s*)(>)', bygroups(Punctuation, Text, Punctuation), '#pop'),
],
'script-content': [
(r'(<)(\s*)(/)(\s*)(script)(\s*)(>)',
bygroups(Punctuation, Text, Punctuation, Text, Name.Tag, Text,
Punctuation), '#pop'),
(r'.+?(?=<\s*/\s*script\s*>)', using(JavascriptLexer)),
],
'style-content': [
(r'(<)(\s*)(/)(\s*)(style)(\s*)(>)',
bygroups(Punctuation, Text, Punctuation, Text, Name.Tag, Text,
Punctuation),'#pop'),
(r'.+?(?=<\s*/\s*style\s*>)', using(CssLexer)),
],
'attr': [
('".*?"', String, '#pop'),
("'.*?'", String, '#pop'),
(r'[^\s>]+', String, '#pop'),
],
}
def analyse_text(text):
if html_doctype_matches(text):
return 0.5
class DtdLexer(RegexLexer):
"""
A lexer for DTDs (Document Type Definitions).
.. versionadded:: 1.5
"""
flags = re.MULTILINE | re.DOTALL
name = 'DTD'
aliases = ['dtd']
filenames = ['*.dtd']
mimetypes = ['application/xml-dtd']
tokens = {
'root': [
include('common'),
(r'(\s]+)',
bygroups(Keyword, Text, Name.Tag)),
(r'PUBLIC|SYSTEM', Keyword.Constant),
(r'[\[\]>]', Keyword),
],
'common': [
(r'\s+', Text),
(r'(%|&)[^;]*;', Name.Entity),
('', Comment, '#pop'),
('-', Comment),
],
'element': [
include('common'),
(r'EMPTY|ANY|#PCDATA', Keyword.Constant),
(r'[^>\s|()?+*,]+', Name.Tag),
(r'>', Keyword, '#pop'),
],
'attlist': [
include('common'),
(r'CDATA|IDREFS|IDREF|ID|NMTOKENS|NMTOKEN|ENTITIES|ENTITY|NOTATION',
Keyword.Constant),
(r'#REQUIRED|#IMPLIED|#FIXED', Keyword.Constant),
(r'xml:space|xml:lang', Keyword.Reserved),
(r'[^>\s|()?+*,]+', Name.Attribute),
(r'>', Keyword, '#pop'),
],
'entity': [
include('common'),
(r'SYSTEM|PUBLIC|NDATA', Keyword.Constant),
(r'[^>\s|()?+*,]+', Name.Entity),
(r'>', Keyword, '#pop'),
],
'notation': [
include('common'),
(r'SYSTEM|PUBLIC', Keyword.Constant),
(r'[^>\s|()?+*,]+', Name.Attribute),
(r'>', Keyword, '#pop'),
],
}
def analyse_text(text):
if not looks_like_xml(text) and \
('', Comment.Preproc),
('', Comment, '#pop'),
('-', Comment),
],
'tag': [
(r'\s+', Text),
(r'[\w.:-]+\s*=', Name.Attribute, 'attr'),
(r'/?\s*>', Name.Tag, '#pop'),
],
'attr': [
('\s+', Text),
('".*?"', String, '#pop'),
("'.*?'", String, '#pop'),
(r'[^\s>]+', String, '#pop'),
],
}
def analyse_text(text):
if looks_like_xml(text):
return 0.45 # less than HTML
class XsltLexer(XmlLexer):
"""
A lexer for XSLT.
.. versionadded:: 0.10
"""
name = 'XSLT'
aliases = ['xslt']
filenames = ['*.xsl', '*.xslt', '*.xpl'] # xpl is XProc
mimetypes = ['application/xsl+xml', 'application/xslt+xml']
EXTRA_KEYWORDS = set((
'apply-imports', 'apply-templates', 'attribute',
'attribute-set', 'call-template', 'choose', 'comment',
'copy', 'copy-of', 'decimal-format', 'element', 'fallback',
'for-each', 'if', 'import', 'include', 'key', 'message',
'namespace-alias', 'number', 'otherwise', 'output', 'param',
'preserve-space', 'processing-instruction', 'sort',
'strip-space', 'stylesheet', 'template', 'text', 'transform',
'value-of', 'variable', 'when', 'with-param'
))
def get_tokens_unprocessed(self, text):
for index, token, value in XmlLexer.get_tokens_unprocessed(self, text):
m = re.match(']*)/?>?', value)
if token is Name.Tag and m and m.group(1) in self.EXTRA_KEYWORDS:
yield index, Keyword, value
else:
yield index, token, value
def analyse_text(text):
if looks_like_xml(text) and ']{1,2}(?=[ \t=])', Punctuation),
include('eval-or-plain'),
],
'plain': [
(r'([^#\n]|#[^{\n]|(\\\\)*\\#\{)+', Text),
(r'(#\{)(' + _dot + '*?)(\})',
bygroups(String.Interpol, using(RubyLexer), String.Interpol)),
(r'\n', Text, 'root'),
],
'html-attributes': [
(r'\s+', Text),
(r'[\w:-]+[ \t]*=', Name.Attribute, 'html-attribute-value'),
(r'[\w:-]+', Name.Attribute),
(r'\)', Text, '#pop'),
],
'html-attribute-value': [
(r'[ \t]+', Text),
(r'\w+', Name.Variable, '#pop'),
(r'@\w+', Name.Variable.Instance, '#pop'),
(r'\$\w+', Name.Variable.Global, '#pop'),
(r"'(\\\\|\\'|[^'\n])*'", String, '#pop'),
(r'"(\\\\|\\"|[^"\n])*"', String, '#pop'),
],
'html-comment-block': [
(_dot + '+', Comment),
(r'\n', Text, 'root'),
],
'haml-comment-block': [
(_dot + '+', Comment.Preproc),
(r'\n', Text, 'root'),
],
'filter-block': [
(r'([^#\n]|#[^{\n]|(\\\\)*\\#\{)+', Name.Decorator),
(r'(#\{)(' + _dot + '*?)(\})',
bygroups(String.Interpol, using(RubyLexer), String.Interpol)),
(r'\n', Text, 'root'),
],
}
class ScamlLexer(ExtendedRegexLexer):
"""
For `Scaml markup