# -*- coding: utf-8 -*-
"""
pygments.lexers.web
~~~~~~~~~~~~~~~~~~~
Lexers for web-related languages and markup.
:copyright: Copyright 2006-2009 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
try:
set
except NameError:
from sets import Set as set
from pygments.lexer import RegexLexer, bygroups, using, include, this
from pygments.token import \
Text, Comment, Operator, Keyword, Name, String, Number, Other, Punctuation
from pygments.util import get_bool_opt, get_list_opt, looks_like_xml, \
html_doctype_matches
__all__ = ['HtmlLexer', 'XmlLexer', 'JavascriptLexer', 'CssLexer',
'PhpLexer', 'ActionScriptLexer', 'XsltLexer', 'ActionScript3Lexer',
'MxmlLexer']
class JavascriptLexer(RegexLexer):
"""
For JavaScript source code.
"""
name = 'JavaScript'
aliases = ['js', 'javascript']
filenames = ['*.js']
mimetypes = ['application/x-javascript', 'text/x-javascript', 'text/javascript']
flags = re.DOTALL
tokens = {
'commentsandwhitespace': [
(r'\s+', Text),
(r'', Comment, '#pop'),
('-', Comment),
],
'tag': [
(r'\s+', Text),
(r'[a-zA-Z0-9_:-]+\s*=', Name.Attribute, 'attr'),
(r'[a-zA-Z0-9_:-]+', Name.Attribute),
(r'/?\s*>', Name.Tag, '#pop'),
],
'script-content': [
(r'<\s*/\s*script\s*>', Name.Tag, '#pop'),
(r'.+?(?=<\s*/\s*script\s*>)', using(JavascriptLexer)),
],
'style-content': [
(r'<\s*/\s*style\s*>', Name.Tag, '#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 PhpLexer(RegexLexer):
"""
For `PHP `_ source code.
For PHP embedded in HTML, use the `HtmlPhpLexer`.
Additional options accepted:
`startinline`
If given and ``True`` the lexer starts highlighting with
php code (i.e.: no starting ``>> from pygments.lexers._phpbuiltins import MODULES
>>> MODULES.keys()
['PHP Options/Info', 'Zip', 'dba', ...]
In fact the names of those modules match the module names from
the php documentation.
"""
name = 'PHP'
aliases = ['php', 'php3', 'php4', 'php5']
filenames = ['*.php', '*.php[345]']
mimetypes = ['text/x-php']
flags = re.IGNORECASE | re.DOTALL | re.MULTILINE
tokens = {
'root': [
(r'<\?(php)?', Comment.Preproc, 'php'),
(r'[^<]+', Other),
(r'<', Other)
],
'php': [
(r'\?>', Comment.Preproc, '#pop'),
(r'<<<([a-zA-Z_][a-zA-Z0-9_]*)\n.*?\n\1\;?\n', String),
(r'\s+', Text),
(r'#.*?\n', Comment.Single),
(r'//.*?\n', Comment.Single),
# put the empty comment here, it is otherwise seen as
# the start of a docstring
(r'/\*\*/', Comment.Multiline),
(r'/\*\*.*?\*/', String.Doc),
(r'/\*.*?\*/', Comment.Multiline),
(r'(->|::)(\s*)([a-zA-Z_][a-zA-Z0-9_]*)',
bygroups(Operator, Text, Name.Attribute)),
(r'[~!%^&*+=|:.<>/?@-]+', Operator),
(r'[\[\]{}();,]+', Punctuation),
(r'(class)(\s+)', bygroups(Keyword, Text), 'classname'),
(r'(function)(\s+)(&?)(\s*)',
bygroups(Keyword, Text, Operator, Text), 'functionname'),
(r'(const)(\s+)([a-zA-Z_][a-zA-Z0-9_]*)',
bygroups(Keyword, Text, Name.Constant)),
(r'(and|E_PARSE|old_function|E_ERROR|or|as|E_WARNING|parent|'
r'eval|PHP_OS|break|exit|case|extends|PHP_VERSION|cfunction|'
r'FALSE|print|for|require|continue|foreach|require_once|'
r'declare|return|default|static|do|switch|die|stdClass|'
r'echo|else|TRUE|elseif|var|empty|if|xor|enddeclare|include|'
r'virtual|endfor|include_once|while|endforeach|global|__FILE__|'
r'endif|list|__LINE__|endswitch|new|__sleep|endwhile|not|'
r'array|__wakeup|E_ALL|NULL|final|php_user_filter|interface|'
r'implements|public|private|protected|abstract|clone|try|'
r'catch|throw|this)\b', Keyword),
('(true|false|null)\b', Keyword.Constant),
(r'\$\{\$+[a-zA-Z_][a-zA-Z0-9_]*\}', Name.Variable),
(r'\$+[a-zA-Z_][a-zA-Z0-9_]*', Name.Variable),
('[a-zA-Z_][a-zA-Z0-9_]*', Name.Other),
(r"[0-9](\.[0-9]*)?(eE[+-][0-9])?[flFLdD]?|"
r"0[xX][0-9a-fA-F]+[Ll]?", Number),
(r"'([^'\\]*(?:\\.[^'\\]*)*)'", String.Single),
(r'`([^`\\]*(?:\\.[^`\\]*)*)`', String.Backtick),
(r'"', String.Double, 'string'),
],
'classname': [
(r'[a-zA-Z_][a-zA-Z0-9_]*', Name.Class, '#pop')
],
'functionname': [
(r'[a-zA-Z_][a-zA-Z0-9_]*', Name.Function, '#pop')
],
'string': [
(r'"', String.Double, '#pop'),
(r'[^{$"\\]+', String.Double),
(r'\\([nrt\"$]|[0-7]{1,3}|x[0-9A-Fa-f]{1,2})', String.Escape),
(r'\$[a-zA-Z_][a-zA-Z0-9_]*(\[\S+\]|->[a-zA-Z_][a-zA-Z0-9_]*)?',
String.Interpol),
(r'(\{\$\{)(.*?)(\}\})',
bygroups(String.Interpol, using(this, _startinline=True),
String.Interpol)),
(r'(\{)(\$.*?)(\})',
bygroups(String.Interpol, using(this, _startinline=True),
String.Interpol)),
(r'(\$\{)(\S+)(\})',
bygroups(String.Interpol, Name.Variable, String.Interpol)),
(r'[${\\]+', String.Double)
],
}
def __init__(self, **options):
self.funcnamehighlighting = get_bool_opt(
options, 'funcnamehighlighting', True)
self.disabledmodules = get_list_opt(
options, 'disabledmodules', ['unknown'])
self.startinline = get_bool_opt(options, 'startinline', False)
# private option argument for the lexer itself
if '_startinline' in options:
self.startinline = options.pop('_startinline')
# collect activated functions in a set
self._functions = set()
if self.funcnamehighlighting:
from pygments.lexers._phpbuiltins import MODULES
for key, value in MODULES.iteritems():
if key not in self.disabledmodules:
self._functions.update(value)
RegexLexer.__init__(self, **options)
def get_tokens_unprocessed(self, text):
stack = ['root']
if self.startinline:
stack.append('php')
for index, token, value in \
RegexLexer.get_tokens_unprocessed(self, text, stack):
if token is Name.Other:
if value in self._functions:
yield index, Name.Builtin, value
continue
yield index, token, value
def analyse_text(text):
rv = 0.0
if re.search(r'<\?(?!xml)', text):
rv += 0.3
if '?>' in text:
rv += 0.1
return rv
class XmlLexer(RegexLexer):
"""
Generic lexer for XML (eXtensible Markup Language).
"""
flags = re.MULTILINE | re.DOTALL
name = 'XML'
aliases = ['xml']
filenames = ['*.xml', '*.xsl', '*.rss', '*.xslt', '*.xsd', '*.wsdl']
mimetypes = ['text/xml', 'application/xml', 'image/svg+xml',
'application/rss+xml', 'application/atom+xml',
'application/xsl+xml', 'application/xslt+xml']
tokens = {
'root': [
('[^<&]+', Text),
(r'&\S*?;', Name.Entity),
(r'\<\!\[CDATA\[.*?\]\]\>', Comment.Preproc),
('', Comment, '#pop'),
('-', Comment),
],
'tag': [
(r'\s+', Text),
(r'[a-zA-Z0-9_.:-]+\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 0.5
class XsltLexer(XmlLexer):
'''
A lexer for XSLT.
*New in Pygments 0.10.*
'''
name = 'XSLT'
aliases = ['xslt']
filenames = ['*.xsl', '*.xslt']
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 ' tags is highlighted by the appropriate lexer.
"""
flags = re.MULTILINE | re.DOTALL
name = 'MXML'
aliases = ['mxml']
filenames = ['*.mxml']
mimetimes = ['text/xml', 'application/xml']
tokens = {
'root': [
('[^<&]+', Text),
(r'&\S*?;', Name.Entity),
(r'(\<\!\[CDATA\[)(.*?)(\]\]\>)',
bygroups(String, using(ActionScript3Lexer), String)),
('', Comment, '#pop'),
('-', Comment),
],
'tag': [
(r'\s+', Text),
(r'[a-zA-Z0-9_.:-]+\s*=', Name.Attribute, 'attr'),
(r'/?\s*>', Name.Tag, '#pop'),
],
'attr': [
('\s+', Text),
('".*?"', String, '#pop'),
("'.*?'", String, '#pop'),
(r'[^\s>]+', String, '#pop'),
],
}