pygments.lexers.templates.py Maven / Gradle / Ivy
The newest version!
# -*- coding: utf-8 -*-
"""
pygments.lexers.templates
~~~~~~~~~~~~~~~~~~~~~~~~~
Lexers for various template engines' markup.
:copyright: Copyright 2006-2019 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
from pygments.lexers.html import HtmlLexer, XmlLexer
from pygments.lexers.javascript import JavascriptLexer, LassoLexer
from pygments.lexers.css import CssLexer
from pygments.lexers.php import PhpLexer
from pygments.lexers.python import PythonLexer
from pygments.lexers.perl import PerlLexer
from pygments.lexers.jvm import JavaLexer, TeaLangLexer
from pygments.lexers.data import YamlLexer
from pygments.lexer import Lexer, DelegatingLexer, RegexLexer, bygroups, \
include, using, this, default, combined
from pygments.token import Error, Punctuation, Whitespace, \
Text, Comment, Operator, Keyword, Name, String, Number, Other, Token
from pygments.util import html_doctype_matches, looks_like_xml
__all__ = ['HtmlPhpLexer', 'XmlPhpLexer', 'CssPhpLexer',
'JavascriptPhpLexer', 'ErbLexer', 'RhtmlLexer',
'XmlErbLexer', 'CssErbLexer', 'JavascriptErbLexer',
'SmartyLexer', 'HtmlSmartyLexer', 'XmlSmartyLexer',
'CssSmartyLexer', 'JavascriptSmartyLexer', 'DjangoLexer',
'HtmlDjangoLexer', 'CssDjangoLexer', 'XmlDjangoLexer',
'JavascriptDjangoLexer', 'GenshiLexer', 'HtmlGenshiLexer',
'GenshiTextLexer', 'CssGenshiLexer', 'JavascriptGenshiLexer',
'MyghtyLexer', 'MyghtyHtmlLexer', 'MyghtyXmlLexer',
'MyghtyCssLexer', 'MyghtyJavascriptLexer', 'MasonLexer', 'MakoLexer',
'MakoHtmlLexer', 'MakoXmlLexer', 'MakoJavascriptLexer',
'MakoCssLexer', 'JspLexer', 'CheetahLexer', 'CheetahHtmlLexer',
'CheetahXmlLexer', 'CheetahJavascriptLexer', 'EvoqueLexer',
'EvoqueHtmlLexer', 'EvoqueXmlLexer', 'ColdfusionLexer',
'ColdfusionHtmlLexer', 'ColdfusionCFCLexer', 'VelocityLexer',
'VelocityHtmlLexer', 'VelocityXmlLexer', 'SspLexer',
'TeaTemplateLexer', 'LassoHtmlLexer', 'LassoXmlLexer',
'LassoCssLexer', 'LassoJavascriptLexer', 'HandlebarsLexer',
'HandlebarsHtmlLexer', 'YamlJinjaLexer', 'LiquidLexer',
'TwigLexer', 'TwigHtmlLexer', 'Angular2Lexer', 'Angular2HtmlLexer']
class ErbLexer(Lexer):
"""
Generic `ERB `_ (Ruby Templating)
lexer.
Just highlights ruby code between the preprocessor directives, other data
is left untouched by the lexer.
All options are also forwarded to the `RubyLexer`.
"""
name = 'ERB'
aliases = ['erb']
mimetypes = ['application/x-ruby-templating']
_block_re = re.compile(r'(<%%|%%>|<%=|<%#|<%-|<%|-%>|%>|^%[^%].*?$)', re.M)
def __init__(self, **options):
from pygments.lexers.ruby import RubyLexer
self.ruby_lexer = RubyLexer(**options)
Lexer.__init__(self, **options)
def get_tokens_unprocessed(self, text):
"""
Since ERB doesn't allow "<%" and other tags inside of ruby
blocks we have to use a split approach here that fails for
that too.
"""
tokens = self._block_re.split(text)
tokens.reverse()
state = idx = 0
try:
while True:
# text
if state == 0:
val = tokens.pop()
yield idx, Other, val
idx += len(val)
state = 1
# block starts
elif state == 1:
tag = tokens.pop()
# literals
if tag in ('<%%', '%%>'):
yield idx, Other, tag
idx += 3
state = 0
# comment
elif tag == '<%#':
yield idx, Comment.Preproc, tag
val = tokens.pop()
yield idx + 3, Comment, val
idx += 3 + len(val)
state = 2
# blocks or output
elif tag in ('<%', '<%=', '<%-'):
yield idx, Comment.Preproc, tag
idx += len(tag)
data = tokens.pop()
r_idx = 0
for r_idx, r_token, r_value in \
self.ruby_lexer.get_tokens_unprocessed(data):
yield r_idx + idx, r_token, r_value
idx += len(data)
state = 2
elif tag in ('%>', '-%>'):
yield idx, Error, tag
idx += len(tag)
state = 0
# % raw ruby statements
else:
yield idx, Comment.Preproc, tag[0]
r_idx = 0
for r_idx, r_token, r_value in \
self.ruby_lexer.get_tokens_unprocessed(tag[1:]):
yield idx + 1 + r_idx, r_token, r_value
idx += len(tag)
state = 0
# block ends
elif state == 2:
tag = tokens.pop()
if tag not in ('%>', '-%>'):
yield idx, Other, tag
else:
yield idx, Comment.Preproc, tag
idx += len(tag)
state = 0
except IndexError:
return
def analyse_text(text):
if '<%' in text and '%>' in text:
return 0.4
class SmartyLexer(RegexLexer):
"""
Generic `Smarty ', Name.Builtin, 'cfoutput'),
(r'(?s)()(.+?)( )',
bygroups(Name.Builtin, using(ColdfusionLexer), Name.Builtin)),
# negative lookbehind is for strings with embedded >
(r'(?s)()',
bygroups(Name.Builtin, using(ColdfusionLexer), Name.Builtin)),
],
'cfoutput': [
(r'[^#<]+', Other),
(r'(#)(.*?)(#)', bygroups(Punctuation, using(ColdfusionLexer),
Punctuation)),
# (r'', Name.Builtin, '#push'),
(r' ', Name.Builtin, '#pop'),
include('tags'),
(r'(?s)<[^<>]*', Other),
(r'#', Other),
],
'cfcomment': [
(r'', Comment.Multiline, '#pop'),
(r'([^<-]|<(?!!---)|-(?!-->))+', Comment.Multiline),
],
}
class ColdfusionHtmlLexer(DelegatingLexer):
"""
Coldfusion markup in html
"""
name = 'Coldfusion HTML'
aliases = ['cfm']
filenames = ['*.cfm', '*.cfml']
mimetypes = ['application/x-coldfusion']
def __init__(self, **options):
super(ColdfusionHtmlLexer, self).__init__(HtmlLexer, ColdfusionMarkupLexer,
**options)
class ColdfusionCFCLexer(DelegatingLexer):
"""
Coldfusion markup/script components
.. versionadded:: 2.0
"""
name = 'Coldfusion CFC'
aliases = ['cfc']
filenames = ['*.cfc']
mimetypes = []
def __init__(self, **options):
super(ColdfusionCFCLexer, self).__init__(ColdfusionHtmlLexer, ColdfusionLexer,
**options)
class SspLexer(DelegatingLexer):
"""
Lexer for Scalate Server Pages.
.. versionadded:: 1.4
"""
name = 'Scalate Server Page'
aliases = ['ssp']
filenames = ['*.ssp']
mimetypes = ['application/x-ssp']
def __init__(self, **options):
super(SspLexer, self).__init__(XmlLexer, JspRootLexer, **options)
def analyse_text(text):
rv = 0.0
if re.search(r'val \w+\s*:', text):
rv += 0.6
if looks_like_xml(text):
rv += 0.2
if '<%' in text and '%>' in text:
rv += 0.1
return rv
class TeaTemplateRootLexer(RegexLexer):
"""
Base for the `TeaTemplateLexer`. Yields `Token.Other` for area outside of
code blocks.
.. versionadded:: 1.5
"""
tokens = {
'root': [
(r'<%\S?', Keyword, 'sec'),
(r'[^<]+', Other),
(r'<', Other),
],
'sec': [
(r'%>', Keyword, '#pop'),
# note: '\w\W' != '.' without DOTALL.
(r'[\w\W]+?(?=%>|\Z)', using(TeaLangLexer)),
],
}
class TeaTemplateLexer(DelegatingLexer):
"""
Lexer for `Tea Templates `_.
.. versionadded:: 2.0
"""
name = 'liquid'
aliases = ['liquid']
filenames = ['*.liquid']
tokens = {
'root': [
(r'[^{]+', Text),
# tags and block tags
(r'(\{%)(\s*)', bygroups(Punctuation, Whitespace), 'tag-or-block'),
# output tags
(r'(\{\{)(\s*)([^\s}]+)',
bygroups(Punctuation, Whitespace, using(this, state = 'generic')),
'output'),
(r'\{', Text)
],
'tag-or-block': [
# builtin logic blocks
(r'(if|unless|elsif|case)(?=\s+)', Keyword.Reserved, 'condition'),
(r'(when)(\s+)', bygroups(Keyword.Reserved, Whitespace),
combined('end-of-block', 'whitespace', 'generic')),
(r'(else)(\s*)(%\})',
bygroups(Keyword.Reserved, Whitespace, Punctuation), '#pop'),
# other builtin blocks
(r'(capture)(\s+)([^\s%]+)(\s*)(%\})',
bygroups(Name.Tag, Whitespace, using(this, state = 'variable'),
Whitespace, Punctuation), '#pop'),
(r'(comment)(\s*)(%\})',
bygroups(Name.Tag, Whitespace, Punctuation), 'comment'),
(r'(raw)(\s*)(%\})',
bygroups(Name.Tag, Whitespace, Punctuation), 'raw'),
# end of block
(r'(end(case|unless|if))(\s*)(%\})',
bygroups(Keyword.Reserved, None, Whitespace, Punctuation), '#pop'),
(r'(end([^\s%]+))(\s*)(%\})',
bygroups(Name.Tag, None, Whitespace, Punctuation), '#pop'),
# builtin tags (assign and include are handled together with usual tags)
(r'(cycle)(\s+)(?:([^\s:]*)(:))?(\s*)',
bygroups(Name.Tag, Whitespace,
using(this, state='generic'), Punctuation, Whitespace),
'variable-tag-markup'),
# other tags or blocks
(r'([^\s%]+)(\s*)', bygroups(Name.Tag, Whitespace), 'tag-markup')
],
'output': [
include('whitespace'),
(r'\}\}', Punctuation, '#pop'), # end of output
(r'\|', Punctuation, 'filters')
],
'filters': [
include('whitespace'),
(r'\}\}', Punctuation, ('#pop', '#pop')), # end of filters and output
(r'([^\s|:]+)(:?)(\s*)',
bygroups(Name.Function, Punctuation, Whitespace), 'filter-markup')
],
'filter-markup': [
(r'\|', Punctuation, '#pop'),
include('end-of-tag'),
include('default-param-markup')
],
'condition': [
include('end-of-block'),
include('whitespace'),
(r'([^\s=!><]+)(\s*)([=!><]=?)(\s*)(\S+)(\s*)(%\})',
bygroups(using(this, state = 'generic'), Whitespace, Operator,
Whitespace, using(this, state = 'generic'), Whitespace,
Punctuation)),
(r'\b!', Operator),
(r'\bnot\b', Operator.Word),
(r'([\w.\'"]+)(\s+)(contains)(\s+)([\w.\'"]+)',
bygroups(using(this, state = 'generic'), Whitespace, Operator.Word,
Whitespace, using(this, state = 'generic'))),
include('generic'),
include('whitespace')
],
'generic-value': [
include('generic'),
include('end-at-whitespace')
],
'operator': [
(r'(\s*)((=|!|>|<)=?)(\s*)',
bygroups(Whitespace, Operator, None, Whitespace), '#pop'),
(r'(\s*)(\bcontains\b)(\s*)',
bygroups(Whitespace, Operator.Word, Whitespace), '#pop'),
],
'end-of-tag': [
(r'\}\}', Punctuation, '#pop')
],
'end-of-block': [
(r'%\}', Punctuation, ('#pop', '#pop'))
],
'end-at-whitespace': [
(r'\s+', Whitespace, '#pop')
],
# states for unknown markup
'param-markup': [
include('whitespace'),
# params with colons or equals
(r'([^\s=:]+)(\s*)(=|:)',
bygroups(Name.Attribute, Whitespace, Operator)),
# explicit variables
(r'(\{\{)(\s*)([^\s}])(\s*)(\}\})',
bygroups(Punctuation, Whitespace, using(this, state = 'variable'),
Whitespace, Punctuation)),
include('string'),
include('number'),
include('keyword'),
(r',', Punctuation)
],
'default-param-markup': [
include('param-markup'),
(r'.', Text) # fallback for switches / variables / un-quoted strings / ...
],
'variable-param-markup': [
include('param-markup'),
include('variable'),
(r'.', Text) # fallback
],
'tag-markup': [
(r'%\}', Punctuation, ('#pop', '#pop')), # end of tag
include('default-param-markup')
],
'variable-tag-markup': [
(r'%\}', Punctuation, ('#pop', '#pop')), # end of tag
include('variable-param-markup')
],
# states for different values types
'keyword': [
(r'\b(false|true)\b', Keyword.Constant)
],
'variable': [
(r'[a-zA-Z_]\w*', Name.Variable),
(r'(?<=\w)\.(?=\w)', Punctuation)
],
'string': [
(r"'[^']*'", String.Single),
(r'"[^"]*"', String.Double)
],
'number': [
(r'\d+\.\d+', Number.Float),
(r'\d+', Number.Integer)
],
'generic': [ # decides for variable, string, keyword or number
include('keyword'),
include('string'),
include('number'),
include('variable')
],
'whitespace': [
(r'[ \t]+', Whitespace)
],
# states for builtin blocks
'comment': [
(r'(\{%)(\s*)(endcomment)(\s*)(%\})',
bygroups(Punctuation, Whitespace, Name.Tag, Whitespace,
Punctuation), ('#pop', '#pop')),
(r'.', Comment)
],
'raw': [
(r'[^{]+', Text),
(r'(\{%)(\s*)(endraw)(\s*)(%\})',
bygroups(Punctuation, Whitespace, Name.Tag, Whitespace,
Punctuation), '#pop'),
(r'\{', Text)
],
}
class TwigLexer(RegexLexer):
"""
`Twig `_
template lexer.
Highlights only the Angular template tags (stuff between `{{` and `}}` and
special attributes: '(event)=', '[property]=', '[(twoWayBinding)]=').
Everything else is left for a delegating lexer.
.. versionadded:: 2.1
"""
name = "Angular2"
aliases = ['ng2']
tokens = {
'root': [
(r'[^{([*#]+', Other),
# {{meal.name}}
(r'(\{\{)(\s*)', bygroups(Comment.Preproc, Text), 'ngExpression'),
# (click)="deleteOrder()"; [value]="test"; [(twoWayTest)]="foo.bar"
(r'([([]+)([\w:.-]+)([\])]+)(\s*)(=)(\s*)',
bygroups(Punctuation, Name.Attribute, Punctuation, Text, Operator, Text),
'attr'),
(r'([([]+)([\w:.-]+)([\])]+)(\s*)',
bygroups(Punctuation, Name.Attribute, Punctuation, Text)),
# *ngIf="..."; #f="ngForm"
(r'([*#])([\w:.-]+)(\s*)(=)(\s*)',
bygroups(Punctuation, Name.Attribute, Punctuation, Operator), 'attr'),
(r'([*#])([\w:.-]+)(\s*)',
bygroups(Punctuation, Name.Attribute, Punctuation)),
],
'ngExpression': [
(r'\s+(\|\s+)?', Text),
(r'\}\}', Comment.Preproc, '#pop'),
# Literals
(r':?(true|false)', String.Boolean),
(r':?"(\\\\|\\"|[^"])*"', String.Double),
(r":?'(\\\\|\\'|[^'])*'", String.Single),
(r"[0-9](\.[0-9]*)?(eE[+-][0-9])?[flFLdD]?|"
r"0[xX][0-9a-fA-F]+[Ll]?", Number),
# Variabletext
(r'[a-zA-Z][\w-]*(\(.*\))?', Name.Variable),
(r'\.[\w-]+(\(.*\))?', Name.Variable),
# inline If
(r'(\?)(\s*)([^}\s]+)(\s*)(:)(\s*)([^}\s]+)(\s*)',
bygroups(Operator, Text, String, Text, Operator, Text, String, Text)),
],
'attr': [
('".*?"', String, '#pop'),
("'.*?'", String, '#pop'),
(r'[^\s>]+', String, '#pop'),
],
}
class Angular2HtmlLexer(DelegatingLexer):
"""
Subclass of the `Angular2Lexer` that highlights unlexed data with the
`HtmlLexer`.
.. versionadded:: 2.0
"""
name = "HTML + Angular2"
aliases = ["html+ng2"]
filenames = ['*.ng2']
def __init__(self, **options):
super(Angular2HtmlLexer, self).__init__(HtmlLexer, Angular2Lexer, **options)