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)
class KotlinLexer(RegexLexer):
"""
For `Kotlin <http://confluence.jetbrains.net/display/Kotlin/>`_
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``.
*New in Pygments 1.5.*
"""
name = 'Kotlin'
aliases = ['kotlin']
filenames = ['*.kt']
mimetypes = ['text/x-kotlin'] # 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][a-zA-Z0-9_]*',
'basic': ('@?[_' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl + ']' +
'[' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl + uni.Nd +
uni.Pc + uni.Cf + uni.Mn + uni.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 list(levels.items()):
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'/[*](.|\n)*?[*]/', 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|break|catch|'
r'fun|continue|default|delegate|'
r'do|else|enum|extern|false|finally|'
r'fixed|for|goto|if|implicit|in|interface|'
r'internal|is|lock|null|'
r'out|override|private|protected|public|readonly|'
r'ref|return|sealed|sizeof|'
r'when|this|throw|true|try|typeof|'
r'unchecked|unsafe|virtual|void|while|'
r'get|set|new|partial|yield|val|var)\b', Keyword),
(r'(global)(::)', bygroups(Keyword, Punctuation)),
(r'(bool|byte|char|decimal|double|dynamic|float|int|long|'
r'short)\b\??', Keyword.Type),
(r'(class|struct)(\s+)', bygroups(Keyword, Text), 'class'),
(r'(package|using)(\s+)', bygroups(Keyword, Text), 'package'),
(cs_ident, Name),
],
'class': [(cs_ident, Name.Class, '#pop')],
'package': [
(r'(?=\()', Text, '#pop'), # using (resource)
('(' + cs_ident + r'|\.)+', Name.Namespace, '#pop')
]
}
def __init__(self, **options):
level = get_choice_opt(options, 'unicodelevel',
list(self.tokens.keys()), '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)
