class VbNetLexer(RegexLexer):
"""
For
`Visual Basic.NET <http://msdn2.microsoft.com/en-us/vbasic/default.aspx>`_
source code.
"""
name = 'VB.net'
aliases = ['vb.net', 'vbnet']
filenames = ['*.vb', '*.bas']
mimetypes = ['text/x-vbnet', 'text/x-vba'] # (?)
uni_name = '[_' + uni.combine('Ll', 'Lt', 'Lm', 'Nl') + ']' + \
'[' + uni.combine('Ll', 'Lt', 'Lm', 'Nl', 'Nd', 'Pc',
'Cf', 'Mn', 'Mc') + ']*'
flags = re.MULTILINE | re.IGNORECASE
tokens = {
'root': [
(r'^\s*<.*?>', Name.Attribute),
(r'\s+', Text),
(r'\n', Text),
(r'rem\b.*?\n', Comment),
(r"'.*?\n", Comment),
(r'#If\s.*?\sThen|#ElseIf\s.*?\sThen|#Else|#End\s+If|#Const|'
r'#ExternalSource.*?\n|#End\s+ExternalSource|'
r'#Region.*?\n|#End\s+Region|#ExternalChecksum', Comment.Preproc),
(r'[(){}!#,.:]', Punctuation),
(r'Option\s+(Strict|Explicit|Compare)\s+'
r'(On|Off|Binary|Text)', Keyword.Declaration),
(words(
('AddHandler', 'Alias', 'ByRef', 'ByVal', 'Call', 'Case',
'Catch', 'CBool', 'CByte', 'CChar', 'CDate', 'CDec', 'CDbl',
'CInt', 'CLng', 'CObj', 'Continue', 'CSByte', 'CShort',
'CSng', 'CStr', 'CType', 'CUInt', 'CULng', 'CUShort',
'Declare', 'Default', 'Delegate', 'DirectCast', 'Do', 'Each',
'Else', 'ElseIf', 'EndIf', 'Erase', 'Error', 'Event', 'Exit',
'False', 'Finally', 'For', 'Friend', 'Get', 'Global', 'GoSub',
'GoTo', 'Handles', 'If', 'Implements', 'Inherits',
'Interface', 'Let', 'Lib', 'Loop', 'Me', 'MustInherit',
'MustOverride', 'MyBase', 'MyClass', 'Narrowing', 'New',
'Next', 'Not', 'Nothing', 'NotInheritable', 'NotOverridable',
'Of', 'On', 'Operator', 'Option', 'Optional', 'Overloads',
'Overridable', 'Overrides', 'ParamArray', 'Partial',
'Private', 'Protected', 'Public', 'RaiseEvent', 'ReadOnly',
'ReDim', 'RemoveHandler', 'Resume', 'Return', 'Select', 'Set',
'Shadows', 'Shared', 'Single', 'Static', 'Step', 'Stop',
'SyncLock', 'Then', 'Throw', 'To', 'True', 'Try', 'TryCast',
'Wend', 'Using', 'When', 'While', 'Widening', 'With',
'WithEvents', 'WriteOnly'),
prefix='(?<!\.)',
suffix=r'\b'), Keyword),
(r'(?<!\.)End\b', Keyword, 'end'),
(r'(?<!\.)(Dim|Const)\b', Keyword, 'dim'),
(r'(?<!\.)(Function|Sub|Property)(\s+)', bygroups(Keyword, Text),
'funcname'),
(r'(?<!\.)(Class|Structure|Enum)(\s+)', bygroups(Keyword, Text),
'classname'),
(r'(?<!\.)(Module|Namespace|Imports)(\s+)',
bygroups(Keyword, Text), 'namespace'),
(r'(?<!\.)(Boolean|Byte|Char|Date|Decimal|Double|Integer|Long|'
r'Object|SByte|Short|Single|String|Variant|UInteger|ULong|'
r'UShort)\b', Keyword.Type),
(r'(?<!\.)(AddressOf|And|AndAlso|As|GetType|In|Is|IsNot|Like|Mod|'
r'Or|OrElse|TypeOf|Xor)\b', Operator.Word),
(r'&=|[*]=|/=|\\=|\^=|\+=|-=|<<=|>>=|<<|>>|:=|'
r'<=|>=|<>|[-&*/\\^+=<>\[\]]', Operator),
('"', String, 'string'),
(r'_\n', Text), # Line continuation (must be before Name)
(uni_name + '[%&@!#$]?', Name),
('#.*?#', Literal.Date),
(r'(\d+\.\d*|\d*\.\d+)(F[+-]?[0-9]+)?', Number.Float),
(r'\d+([SILDFR]|US|UI|UL)?', Number.Integer),
(r'&H[0-9a-f]+([SILDFR]|US|UI|UL)?', Number.Integer),
(r'&O[0-7]+([SILDFR]|US|UI|UL)?', Number.Integer),
],
'string': [
(r'""', String),
(r'"C?', String, '#pop'),
(r'[^"]+', String),
],
'dim': [
(uni_name, Name.Variable, '#pop'),
default('#pop'), # any other syntax
],
'funcname': [
(uni_name, Name.Function, '#pop'),
],
'classname': [
(uni_name, Name.Class, '#pop'),
],
'namespace': [
(uni_name, Name.Namespace),
(r'\.', Name.Namespace),
default('#pop'),
],
'end': [
(r'\s+', Text),
(r'(Function|Sub|Property|Class|Structure|Enum|Module|Namespace)\b',
Keyword, '#pop'),
default('#pop'),
]
}
def analyse_text(text):
if re.search(r'^\s*(#If|Module|Namespace)', text, re.MULTILINE):
return 0.5
class NemerleLexer(RegexLexer):
"""
For `Nemerle <http://nemerle.org>`_ source code.
Additional options accepted:
`unicodelevel`
Determines which Unicode characters this lexer allows for identifiers.
The possible values are:
* ``none`` -- only the ASCII letters and numbers are allowed. This
is the fastest selection.
* ``basic`` -- all Unicode characters from the specification except
category ``Lo`` are allowed.
* ``full`` -- all Unicode characters as specified in the C# specs
are allowed. Note that this means a considerable slowdown since the
``Lo`` category has more than 40,000 characters in it!
The default value is ``basic``.
.. versionadded:: 1.5
"""
name = 'Nemerle'
aliases = ['nemerle']
filenames = ['*.n']
mimetypes = ['text/x-nemerle'] # inferred
flags = re.MULTILINE | re.DOTALL | re.UNICODE
# for the range of allowed unicode characters in identifiers, see
# http://www.ecma-international.org/publications/files/ECMA-ST/Ecma-334.pdf
levels = {
'none':
'@?[_a-zA-Z]\w*',
'basic': ('@?[_' + uni.combine('Lu', 'Ll', 'Lt', 'Lm', 'Nl') + ']' +
'[' + uni.combine('Lu', 'Ll', 'Lt', 'Lm', 'Nl', 'Nd', 'Pc',
'Cf', 'Mn', 'Mc') + ']*'),
'full':
('@?(?:_|[^' + uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl') +
'])' + '[^' + uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl', 'Nd',
'Pc', 'Cf', 'Mn', 'Mc') + ']*'),
}
tokens = {}
token_variants = True
for levelname, cs_ident in iteritems(levels):
tokens[levelname] = {
'root': [
# method names
(
r'^([ \t]*(?:' + cs_ident +
r'(?:\[\])?\s+)+?)' # return type
r'(' + cs_ident + ')' # method name
r'(\s*)(\()', # signature start
bygroups(using(this), Name.Function, Text, Punctuation)),
(r'^\s*\[.*?\]', Name.Attribute),
(r'[^\S\n]+', Text),
(r'\\\n', Text), # line continuation
(r'//.*?\n', Comment.Single),
(r'/[*].*?[*]/', Comment.Multiline),
(r'\n', Text),
(r'\$\s*"', String, 'splice-string'),
(r'\$\s*<#', String, 'splice-string2'),
(r'<#', String, 'recursive-string'),
(r'(<\[)\s*(' + cs_ident + ':)?', Keyword),
(r'\]\>', Keyword),
# quasiquotation only
(r'\$' + cs_ident, Name),
(r'(\$)(\()', bygroups(Name,
Punctuation), 'splice-string-content'),
(r'[~!%^&*()+=|\[\]:;,.<>/?-]', Punctuation),
(r'[{}]', Punctuation),
(r'@"(""|[^"])*"', String),
(r'"(\\\\|\\"|[^"\n])*["\n]', String),
(r"'\\.'|'[^\\]'", String.Char),
(r"0[xX][0-9a-fA-F]+[Ll]?", Number),
(r"[0-9](\.[0-9]*)?([eE][+-][0-9]+)?[flFLdD]?", Number),
(r'#[ \t]*(if|endif|else|elif|define|undef|'
r'line|error|warning|region|endregion|pragma)\b.*?\n',
Comment.Preproc),
(r'\b(extern)(\s+)(alias)\b', bygroups(Keyword, Text,
Keyword)),
(r'(abstract|and|as|base|catch|def|delegate|'
r'enum|event|extern|false|finally|'
r'fun|implements|interface|internal|'
r'is|macro|match|matches|module|mutable|new|'
r'null|out|override|params|partial|private|'
r'protected|public|ref|sealed|static|'
r'syntax|this|throw|true|try|type|typeof|'
r'virtual|volatile|when|where|with|'
r'assert|assert2|async|break|checked|continue|do|else|'
r'ensures|for|foreach|if|late|lock|new|nolate|'
r'otherwise|regexp|repeat|requires|return|surroundwith|'
r'unchecked|unless|using|while|yield)\b', Keyword),
(r'(global)(::)', bygroups(Keyword, Punctuation)),
(r'(bool|byte|char|decimal|double|float|int|long|object|sbyte|'
r'short|string|uint|ulong|ushort|void|array|list)\b\??',
Keyword.Type),
(r'(:>?)\s*(' + cs_ident + r'\??)',
bygroups(Punctuation, Keyword.Type)),
(r'(class|struct|variant|module)(\s+)',
bygroups(Keyword, Text), 'class'),
(r'(namespace|using)(\s+)', bygroups(Keyword,
Text), 'namespace'),
(cs_ident, Name),
],
'class': [(cs_ident, Name.Class, '#pop')],
'namespace': [
(r'(?=\()', Text, '#pop'), # using (resource)
('(' + cs_ident + r'|\.)+', Name.Namespace, '#pop')
],
'splice-string':
[(r'[^"$]', String), (r'\$' + cs_ident, Name),
(r'(\$)(\()', bygroups(Name,
Punctuation), 'splice-string-content'),
(r'\\"', String), (r'"', String, '#pop')],
'splice-string2':
[(r'[^#<>$]', String), (r'\$' + cs_ident, Name),
(r'(\$)(\()', bygroups(Name,
Punctuation), 'splice-string-content'),
(r'<#', String, '#push'), (r'#>', String, '#pop')],
'recursive-string': [(r'[^#<>]', String), (r'<#', String, '#push'),
(r'#>', String, '#pop')],
'splice-string-content':
[(r'if|match', Keyword),
(r'[~!%^&*+=|\[\]:;,.<>/?-\\"$ ]', Punctuation), (cs_ident, Name),
(r'\d+', Number), (r'\(', Punctuation, '#push'),
(r'\)', Punctuation, '#pop')]
}
def __init__(self, **options):
level = get_choice_opt(options, 'unicodelevel', list(self.tokens),
'basic')
if level not in self._all_tokens:
# compile the regexes now
self._tokens = self.__class__.process_tokendef(level)
else:
self._tokens = self._all_tokens[level]
RegexLexer.__init__(self, **options)
class CSharpLexer(RegexLexer):
"""
For `C# <http://msdn2.microsoft.com/en-us/vcsharp/default.aspx>`_
source code.
Additional options accepted:
`unicodelevel`
Determines which Unicode characters this lexer allows for identifiers.
The possible values are:
* ``none`` -- only the ASCII letters and numbers are allowed. This
is the fastest selection.
* ``basic`` -- all Unicode characters from the specification except
category ``Lo`` are allowed.
* ``full`` -- all Unicode characters as specified in the C# specs
are allowed. Note that this means a considerable slowdown since the
``Lo`` category has more than 40,000 characters in it!
The default value is ``basic``.
.. versionadded:: 0.8
"""
name = 'C#'
aliases = ['csharp', 'c#']
filenames = ['*.cs']
mimetypes = ['text/x-csharp'] # inferred
flags = re.MULTILINE | re.DOTALL | re.UNICODE
# for the range of allowed unicode characters in identifiers, see
# http://www.ecma-international.org/publications/files/ECMA-ST/Ecma-334.pdf
levels = {
'none':
'@?[_a-zA-Z]\w*',
'basic': ('@?[_' + uni.combine('Lu', 'Ll', 'Lt', 'Lm', 'Nl') + ']' +
'[' + uni.combine('Lu', 'Ll', 'Lt', 'Lm', 'Nl', 'Nd', 'Pc',
'Cf', 'Mn', 'Mc') + ']*'),
'full':
('@?(?:_|[^' + uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl') +
'])' + '[^' + uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl', 'Nd',
'Pc', 'Cf', 'Mn', 'Mc') + ']*'),
}
tokens = {}
token_variants = True
for levelname, cs_ident in iteritems(levels):
tokens[levelname] = {
'root': [
# method names
(
r'^([ \t]*(?:' + cs_ident +
r'(?:\[\])?\s+)+?)' # return type
r'(' + cs_ident + ')' # method name
r'(\s*)(\()', # signature start
bygroups(using(this), Name.Function, Text, Punctuation)),
(r'^\s*\[.*?\]', Name.Attribute),
(r'[^\S\n]+', Text),
(r'\\\n', Text), # line continuation
(r'//.*?\n', Comment.Single),
(r'/[*].*?[*]/', Comment.Multiline),
(r'\n', Text),
(r'[~!%^&*()+=|\[\]:;,.<>/?-]', Punctuation),
(r'[{}]', Punctuation),
(r'@"(""|[^"])*"', String),
(r'"(\\\\|\\"|[^"\n])*["\n]', String),
(r"'\\.'|'[^\\]'", String.Char),
(r"[0-9](\.[0-9]*)?([eE][+-][0-9]+)?"
r"[flFLdD]?|0[xX][0-9a-fA-F]+[Ll]?", Number),
(r'#[ \t]*(if|endif|else|elif|define|undef|'
r'line|error|warning|region|endregion|pragma)\b.*?\n',
Comment.Preproc),
(r'\b(extern)(\s+)(alias)\b', bygroups(Keyword, Text,
Keyword)),
(r'(abstract|as|async|await|base|break|by|case|catch|'
r'checked|const|continue|default|delegate|'
r'do|else|enum|event|explicit|extern|false|finally|'
r'fixed|for|foreach|goto|if|implicit|in|interface|'
r'internal|is|let|lock|new|null|on|operator|'
r'out|override|params|private|protected|public|readonly|'
r'ref|return|sealed|sizeof|stackalloc|static|'
r'switch|this|throw|true|try|typeof|'
r'unchecked|unsafe|virtual|void|while|'
r'get|set|new|partial|yield|add|remove|value|alias|ascending|'
r'descending|from|group|into|orderby|select|thenby|where|'
r'join|equals)\b', Keyword),
(r'(global)(::)', bygroups(Keyword, Punctuation)),
(r'(bool|byte|char|decimal|double|dynamic|float|int|long|object|'
r'sbyte|short|string|uint|ulong|ushort|var)\b\??',
Keyword.Type),
(r'(class|struct)(\s+)', bygroups(Keyword, Text), 'class'),
(r'(namespace|using)(\s+)', bygroups(Keyword,
Text), 'namespace'),
(cs_ident, Name),
],
'class': [
(cs_ident, Name.Class, '#pop'),
default('#pop'),
],
'namespace': [
(r'(?=\()', Text, '#pop'), # using (resource)
('(' + cs_ident + r'|\.)+', Name.Namespace, '#pop'),
]
}
def __init__(self, **options):
level = get_choice_opt(options, 'unicodelevel', list(self.tokens),
'basic')
if level not in self._all_tokens:
# compile the regexes now
self._tokens = self.__class__.process_tokendef(level)
else:
self._tokens = self._all_tokens[level]
RegexLexer.__init__(self, **options)
"""
pygments.lexers.javascript
~~~~~~~~~~~~~~~~~~~~~~~~~~
Lexers for JavaScript and related languages.
:copyright: Copyright 2006-2019 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
from pygments.lexer import RegexLexer, include, bygroups, default, using, \
this, words, combined
from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
Number, Punctuation, Other
from pygments.util import get_bool_opt
import pygments.unistring as uni
__all__ = ['TypeScriptLexer']
JS_IDENT_START = ('(?:[$_' + uni.combine('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl') +
']|\\\\u[a-fA-F0-9]{4})')
JS_IDENT_PART = (
'(?:[$' +
uni.combine('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl', 'Mn', 'Mc', 'Nd', 'Pc') +
u'\u200c\u200d]|\\\\u[a-fA-F0-9]{4})')
JS_IDENT = JS_IDENT_START + '(?:' + JS_IDENT_PART + ')*'
class TypeScriptLexer(RegexLexer):
"""
For `TypeScript <http://typescriptlang.org/>`_ source code.
.. versionadded:: 1.6
"""
name = 'TypeScript'
aliases = ['ts', 'typescript']
:license: BSD, see LICENSE for details.
"""
import re
from pygments.lexer import RegexLexer, include, bygroups, default, using, this
from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
Number, Punctuation, Other
from pygments.util import get_bool_opt, iteritems
import pygments.unistring as uni
__all__ = ['JavascriptLexer', 'KalLexer', 'LiveScriptLexer', 'DartLexer',
'TypeScriptLexer', 'LassoLexer', 'ObjectiveJLexer',
'CoffeeScriptLexer', 'MaskLexer']
JS_IDENT_START = ('(?:[$_' + uni.combine('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl') +
']|\\\\u[a-fA-F0-9]{4})')
JS_IDENT_PART = ('(?:[$' + uni.combine('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl',
'Mn', 'Mc', 'Nd', 'Pc') +
u'\u200c\u200d]|\\\\u[a-fA-F0-9]{4})')
JS_IDENT = JS_IDENT_START + '(?:' + JS_IDENT_PART + ')*'
class JavascriptLexer(RegexLexer):
"""
For JavaScript source code.
"""
name = 'JavaScript'
aliases = ['js', 'javascript']
filenames = ['*.js', ]
Keyword,
Name,
String,
Number,
Punctuation,
Other,
)
from pygments.util import get_bool_opt
import pygments.unistring as uni
def setup(app):
app.add_lexer("edh", EdhLexer)
EDH_IDENT_START = ("(?:[_" + uni.combine("Lu", "Ll", "Lt", "Lm", "Lo", "Nl") +
"]|\\\\u[a-fA-F0-9]{4})")
EDH_IDENT_PART = (
"(?:[_'" +
uni.combine("Lu", "Ll", "Lt", "Lm", "Lo", "Nl", "Mn", "Mc", "Nd", "Pc") +
"\u200c\u200d]|\\\\u[a-fA-F0-9]{4})")
EDH_IDENT = EDH_IDENT_START + "(?:" + EDH_IDENT_PART + ")*"
class EdhLexer(RegexLexer):
"""
For Edh source code.
"""
name = "Edh"
aliases = [
#!/usr/bin/env python
# vim:fileencoding=utf-8
from __future__ import unicode_literals, division, absolute_import, print_function
__license__ = "GPL v3"
__copyright__ = "2014, Kovid Goyal <kovid at kovidgoyal.net>"
import re
from pygments.lexer import RegexLexer, default, include
from pygments.token import Comment, Punctuation, Number, Keyword, Text, String, Operator, Name
import pygments.unistring as uni
from calibre.gui2.tweak_book.editor.syntax.pygments_highlighter import create_highlighter
JS_IDENT_START = "(?:[$_" + uni.combine("Lu", "Ll", "Lt", "Lm", "Lo", "Nl") + "]|\\\\u[a-fA-F0-9]{4})"
JS_IDENT_PART = (
"(?:[$"
+ uni.combine("Lu", "Ll", "Lt", "Lm", "Lo", "Nl", "Mn", "Mc", "Nd", "Pc")
+ "\u200c\u200d]|\\\\u[a-fA-F0-9]{4})"
)
JS_IDENT = JS_IDENT_START + "(?:" + JS_IDENT_PART + ")*"
class JavascriptLexer(RegexLexer):
"""
For JavaScript source code. This is based on the pygments JS highlighter,
bu that does not handle multi-line comments in streaming mode, so we had to
modify it.
"""
class CSharp6Lexer(RegexLexer):
name = 'C#6'
aliases = ['csharp6', 'c#6']
filenames = ['*.cs']
mimetypes = ['text/x-csharp']
flags = re.MULTILINE | re.DOTALL | re.UNICODE
cs_ident = ('@?[_' + uni.combine('Lu', 'Ll', 'Lt', 'Lm', 'Nl') + ']' +
'[' + uni.combine('Lu', 'Ll', 'Lt', 'Lm', 'Nl', 'Nd', 'Pc',
'Cf', 'Mn', 'Mc') + ']*')
tokens = {
'root': [
# method names
(r'^([ \t]*(?:' + cs_ident + r'(?:\[\])?\s+)+?)' # return type
r'(' + cs_ident + ')' # method name
r'(\s*)(\()', # signature start
bygroups(using(this), Name.Function, Text, Punctuation)),
(r'^\s*\[.*?\]', Name.Attribute),
(r'[^\S\n]+', Text),
(r'\\\n', Text), # line continuation
(r'//.*?\n', Comment.Single),
(r'/[*].*?[*]/', Comment.Multiline),
(r'\n', Text),
(r'[~!%^&*()+=|\[\]:;,.<>/?-]', Punctuation),
(r'[{}]', Punctuation),
(r'@\$?"(""|[^"])*"', String),
(r'"\$?(\\\\|\\"|[^"\n])*["\n]', String),
(r"'\\.'|'[^\\]'", String.Char),
(r"[0-9](\.[0-9]*)?([eE][+-][0-9]+)?"
r"[flFLdD]?|0[xX][0-9a-fA-F]+[Ll]?", Number),
(r'#[ \t]*(if|endif|else|elif|define|undef|'
r'line|error|warning|region|endregion|pragma)\b.*?\n',
Comment.Preproc),
(r'\b(extern)(\s+)(alias)\b', bygroups(Keyword, Text,
Keyword)),
(r'(abstract|as|async|await|base|break|case|catch|'
r'checked|const|continue|default|delegate|'
r'do|else|enum|event|explicit|extern|false|finally|'
r'fixed|for|foreach|goto|if|implicit|in|interface|'
r'internal|is|lock|new|null|operator|'
r'out|override|params|private|protected|public|readonly|'
r'ref|return|sealed|sizeof|stackalloc|static|'
r'switch|this|throw|true|try|typeof|'
r'unchecked|unsafe|virtual|var|void|while|'
r'get|set|new|partial|yield|add|remove|value|alias|ascending|'
r'descending|from|group|into|orderby|select|where|'
r'join|equals)\b', Keyword),
(r'(global)(::)', bygroups(Keyword, Punctuation)),
(r'(bool|byte|char|decimal|double|dynamic|float|int|long|object|'
r'sbyte|short|string|uint|ulong|ushort|var)\b\??', Keyword.Type),
(r'(class|struct)(\s+)', bygroups(Keyword, Text), 'class'),
(r'(namespace|using)(\s+)', bygroups(Keyword, Text), 'namespace'),
(cs_ident, Name),
],
'class': [
(cs_ident, Name.Class, '#pop'),
default('#pop'),
],
'namespace': [
(r'(?=\()', Text, '#pop'), # using (resource)
('(' + cs_ident + r'|\.)+', Name.Namespace, '#pop'),
]
}
