diff options
| -rw-r--r-- | AUTHORS | 1 | ||||
| -rw-r--r-- | CHANGES | 1 | ||||
| -rw-r--r-- | pygments/lexers/_mapping.py | 2 | ||||
| -rw-r--r-- | pygments/lexers/jvm.py | 121 | ||||
| -rw-r--r-- | pygments/lexers/kotlin.py | 138 |
5 files changed, 123 insertions, 140 deletions
@@ -96,6 +96,7 @@ Other contributors, listed alphabetically, are: * Kirill Simonov -- YAML lexer * Steve Spigarelli -- XQuery lexer * Jerome St-Louis -- eC lexer +* James Strachan -- Kotlin lexer * Tiberius Teng -- default style overhaul * Jeremy Thurgood -- Erlang, Squid config lexers * Erick Tryzelaar -- Felix lexer @@ -43,6 +43,7 @@ Version 1.5 * Scilab (#740) * Elixir (PR#57) * Tea (PR#56) + * Kotlin (PR#58) - Fix Python 3 terminal highlighting with pygmentize (#691). diff --git a/pygments/lexers/_mapping.py b/pygments/lexers/_mapping.py index 91161556..7c745a89 100644 --- a/pygments/lexers/_mapping.py +++ b/pygments/lexers/_mapping.py @@ -131,7 +131,7 @@ LEXERS = { 'JavascriptPhpLexer': ('pygments.lexers.templates', 'JavaScript+PHP', ('js+php', 'javascript+php'), (), ('application/x-javascript+php', 'text/x-javascript+php', 'text/javascript+php')), 'JavascriptSmartyLexer': ('pygments.lexers.templates', 'JavaScript+Smarty', ('js+smarty', 'javascript+smarty'), (), ('application/x-javascript+smarty', 'text/x-javascript+smarty', 'text/javascript+smarty')), 'JspLexer': ('pygments.lexers.templates', 'Java Server Page', ('jsp',), ('*.jsp',), ('application/x-jsp',)), - 'KotlinLexer': ('pygments.lexers.kotlin', 'Kotlin', ('kotlin',), ('*.kt',), ('application/x-kotlin',)), + 'KotlinLexer': ('pygments.lexers.jvm', 'Kotlin', ('kotlin',), ('*.kt',), ('text/x-kotlin',)), 'LighttpdConfLexer': ('pygments.lexers.text', 'Lighttpd configuration file', ('lighty', 'lighttpd'), (), ('text/x-lighttpd-conf',)), 'LiterateHaskellLexer': ('pygments.lexers.functional', 'Literate Haskell', ('lhs', 'literate-haskell'), ('*.lhs',), ('text/x-literate-haskell',)), 'LlvmLexer': ('pygments.lexers.asm', 'LLVM', ('llvm',), ('*.ll',), ('text/x-llvm',)), diff --git a/pygments/lexers/jvm.py b/pygments/lexers/jvm.py index 6e3e103f..b56d4582 100644 --- a/pygments/lexers/jvm.py +++ b/pygments/lexers/jvm.py @@ -15,10 +15,12 @@ from pygments.lexer import Lexer, RegexLexer, include, bygroups, using, \ this from pygments.token import Text, Comment, Operator, Keyword, Name, String, \ Number, Punctuation +from pygments.util import get_choice_opt +from pygments import unistring as uni __all__ = ['JavaLexer', 'ScalaLexer', 'GosuLexer', 'GosuTemplateLexer', - 'GroovyLexer', 'IokeLexer', 'ClojureLexer'] + 'GroovyLexer', 'IokeLexer', 'ClojureLexer', 'KotlinLexer'] class JavaLexer(RegexLexer): @@ -726,3 +728,120 @@ class TeaLangLexer(RegexLexer): (r'[a-zA-Z0-9_.]+\*?', Name.Namespace, '#pop') ], } + + +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 + + def _escape(st): + return st.replace(u'\\', ur'\\').replace(u'-', ur'\-').\ + replace(u'[', ur'\[').replace(u']', ur'\]') + + 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': ('@?(?:_|[^' + + _escape(uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl')) + '])' + + '[^' + _escape(uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', + 'Nl', 'Nd', 'Pc', 'Cf', 'Mn', + 'Mc')) + ']*'), + } + + tokens = {} + token_variants = True + + for levelname, cs_ident in 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', 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) diff --git a/pygments/lexers/kotlin.py b/pygments/lexers/kotlin.py deleted file mode 100644 index d8a31138..00000000 --- a/pygments/lexers/kotlin.py +++ /dev/null @@ -1,138 +0,0 @@ -# -*- coding: utf-8 -*- -""" - pygments.lexers.kotlin - ~~~~~~~~~~~~~~~~~~~~~~ - - Lexer for the Kotlin programming language. - http://confluence.jetbrains.net/display/Kotlin/ - - :copyright: Copyright 2006-2012 by the Pygments team, see AUTHORS. - :license: BSD, see LICENSE for details. -""" -import re - -from pygments.lexer import RegexLexer, DelegatingLexer, bygroups, include, \ - using, this -from pygments.token import Punctuation, \ - Text, Comment, Operator, Keyword, Name, String, Number, Literal, Other -from pygments.util import get_choice_opt -from pygments import unistring as uni - -from pygments.lexers.web import XmlLexer - -__all__ = ['KotlinLexer'] - - -def _escape(st): - return st.replace(u'\\', ur'\\').replace(u'-', ur'\-').\ - replace(u'[', ur'\[').replace(u']', ur'\]') - -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 0.8.* - """ - - 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': ('@?(?:_|[^' + - _escape(uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl')) + '])' - + '[^' + _escape(uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', - 'Nl', 'Nd', 'Pc', 'Cf', 'Mn', - 'Mc')) + ']*'), - } - - tokens = {} - token_variants = True - - for levelname, cs_ident in 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|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', 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) |