diff options
| author | Mike Nolta <mike@nolta.net> | 2012-03-11 01:26:19 -0500 |
|---|---|---|
| committer | Mike Nolta <mike@nolta.net> | 2012-03-11 01:26:19 -0500 |
| commit | 086deed92ba378e3d8e37d18f1d0ce668967908d (patch) | |
| tree | 0bb94cca3f9be46317bc383751e2e8769be17813 | |
| parent | 8db91bc577691c7f4ad2a649a734e5067ce58d32 (diff) | |
| parent | 9e80de2655ac91392e77fdb851cb8af940cff89d (diff) | |
| download | pygments-086deed92ba378e3d8e37d18f1d0ce668967908d.tar.gz | |
upstream pull
29 files changed, 578 insertions, 254 deletions
@@ -48,6 +48,7 @@ Other contributors, listed alphabetically, are: * Ben Hollis -- Mason lexer * Tim Howard -- BlitzMax lexer * Ivan Inozemtsev -- Fantom lexer +* Brian R. Jackson -- Tea lexer * Dennis Kaarsemaker -- sources.list lexer * Igor Kalnitsky -- vhdl lexer * Adam Koprowski -- Opa lexer @@ -95,6 +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 @@ -4,9 +4,13 @@ Pygments changelog Issue numbers refer to the tracker at http://bitbucket.org/birkenfeld/pygments-main/issues. +Version 1.5.1 +------------- +(in development) + Version 1.5 ----------- -(codename not decided, released 2012) +(codename Zeitdilatation, released Mar 10, 2012) - Lexers added: @@ -42,6 +46,8 @@ Version 1.5 * VHDL (PR#45) * Scilab (#740) * Elixir (PR#57) + * Tea (PR#56) + * Kotlin (PR#58) - Fix Python 3 terminal highlighting with pygmentize (#691). @@ -78,6 +84,12 @@ Version 1.5 - Add "rrt" style (#727). +- Fix infinite looping in Darcs Patch lexer. + +- Lots of misc fixes to character-eating bugs and ordering problems in many + different lexers. + + Version 1.4 ----------- (codename Unschärfe, released Jan 03, 2011) @@ -343,7 +355,7 @@ Version 1.0 - Added Tango style, written by Andre Roberge for the Crunchy project. -- Added Python3TracebackLexer and ``python3`` option to +- Added Python3TracebackLexer and ``python3`` option to PythonConsoleLexer. - Fixed a few bugs in the Haskell lexer. @@ -681,7 +693,7 @@ Version 0.7 - Added token stream filters, and a pygmentize option to use them. -- Changed behavior of `in` Operator for tokens. +- Changed behavior of `in` Operator for tokens. - Added mimetypes for all lexers. @@ -3,8 +3,6 @@ Todo - suggested new lexers * IPython sessions - * PostgreSQL/SQLite - * Nemerle - lexers that need work: * review perl lexer (numerous bugs, but so far no one had complaints ;) diff --git a/docs/generate.py b/docs/generate.py index 4842dc6e..0ceeb58d 100644..100755 --- a/docs/generate.py +++ b/docs/generate.py @@ -56,7 +56,7 @@ def generate_lexer_docs(): classname, cls.__doc__, ', '.join(data[2]) or 'None', - ', '.join(data[3]).replace('*', '\\*') or 'None', + ', '.join(data[3]).replace('*', '\\*').replace('_', '\\') or 'None', ', '.join(data[4]) or 'None')) if module not in moduledocstrings: moduledocstrings[module] = mod.__doc__ diff --git a/docs/src/tokens.txt b/docs/src/tokens.txt index 9ef0df8d..4900a9ab 100644 --- a/docs/src/tokens.txt +++ b/docs/src/tokens.txt @@ -303,7 +303,7 @@ Comments `Comment.Special` Special data in comments. For example code tags, author and license - informations etc. + information, etc. Generic Tokens diff --git a/pygments/__init__.py b/pygments/__init__.py index 8a0e337e..0ecc167d 100644 --- a/pygments/__init__.py +++ b/pygments/__init__.py @@ -26,7 +26,7 @@ :license: BSD, see LICENSE for details. """ -__version__ = '1.4' +__version__ = '1.5' __docformat__ = 'restructuredtext' __all__ = ['lex', 'format', 'highlight'] diff --git a/pygments/formatters/_mapping.py b/pygments/formatters/_mapping.py index fd380b3a..b64eb685 100755 --- a/pygments/formatters/_mapping.py +++ b/pygments/formatters/_mapping.py @@ -1,7 +1,7 @@ # -*- coding: utf-8 -*- """ pygments.formatters._mapping - ~~~~~~~~~~~~~~~~~~~~~~~~~~~ + ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Formatter mapping defintions. This file is generated by itself. Everytime you change something on a builtin formatter defintion, run this script from diff --git a/pygments/lexers/_mapping.py b/pygments/lexers/_mapping.py index 61ac479f..8bcc1744 100644 --- a/pygments/lexers/_mapping.py +++ b/pygments/lexers/_mapping.py @@ -34,7 +34,7 @@ LEXERS = { 'AwkLexer': ('pygments.lexers.other', 'Awk', ('awk', 'gawk', 'mawk', 'nawk'), ('*.awk',), ('application/x-awk',)), 'BBCodeLexer': ('pygments.lexers.text', 'BBCode', ('bbcode',), (), ('text/x-bbcode',)), 'BaseMakefileLexer': ('pygments.lexers.text', 'Base Makefile', ('basemake',), (), ()), - 'BashLexer': ('pygments.lexers.shell', 'Bash', ('bash', 'sh', 'ksh'), ('*.sh', '*.ksh', '*.bash', '*.ebuild', '*.eclass'), ('application/x-sh', 'application/x-shellscript')), + 'BashLexer': ('pygments.lexers.shell', 'Bash', ('bash', 'sh', 'ksh'), ('*.sh', '*.ksh', '*.bash', '*.ebuild', '*.eclass', '.bashrc', 'bashrc', '.bash_*', 'bash_*'), ('application/x-sh', 'application/x-shellscript')), 'BashSessionLexer': ('pygments.lexers.shell', 'Bash Session', ('console',), ('*.sh-session',), ('application/x-shell-session',)), 'BatchLexer': ('pygments.lexers.shell', 'Batchfile', ('bat',), ('*.bat', '*.cmd'), ('application/x-dos-batch',)), 'BefungeLexer': ('pygments.lexers.other', 'Befunge', ('befunge',), ('*.befunge',), ('application/x-befunge',)), @@ -131,6 +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.jvm', 'Kotlin', ('kotlin',), ('*.kt',), ('text/x-kotlin',)), 'JuliaLexer': ('pygments.lexers.math', 'Julia', ('julia','jl'), ('*.jl',), ('text/x-julia','application/x-julia')), 'JuliaConsoleLexer': ('pygments.lexers.math', 'Julia console', ('jlcon',), (), ()), 'LighttpdConfLexer': ('pygments.lexers.text', 'Lighttpd configuration file', ('lighty', 'lighttpd'), (), ('text/x-lighttpd-conf',)), @@ -229,6 +230,7 @@ LEXERS = { 'SystemVerilogLexer': ('pygments.lexers.hdl', 'systemverilog', ('sv',), ('*.sv', '*.svh'), ('text/x-systemverilog',)), 'TclLexer': ('pygments.lexers.agile', 'Tcl', ('tcl',), ('*.tcl',), ('text/x-tcl', 'text/x-script.tcl', 'application/x-tcl')), 'TcshLexer': ('pygments.lexers.shell', 'Tcsh', ('tcsh', 'csh'), ('*.tcsh', '*.csh'), ('application/x-csh',)), + 'TeaTemplateLexer': ('pygments.lexers.templates', 'Tea', ('tea',), ('*.tea',), ('text/x-tea',)), 'TexLexer': ('pygments.lexers.text', 'TeX', ('tex', 'latex'), ('*.tex', '*.aux', '*.toc'), ('text/x-tex', 'text/x-latex')), 'TextLexer': ('pygments.lexers.special', 'Text only', ('text',), ('*.txt',), ('text/plain',)), 'UrbiscriptLexer': ('pygments.lexers.other', 'UrbiScript', ('urbiscript',), ('*.u',), ('application/x-urbiscript',)), @@ -240,7 +242,7 @@ LEXERS = { 'VelocityXmlLexer': ('pygments.lexers.templates', 'XML+Velocity', ('xml+velocity',), (), ('application/xml+velocity',)), 'VerilogLexer': ('pygments.lexers.hdl', 'verilog', ('v',), ('*.v',), ('text/x-verilog',)), 'VhdlLexer': ('pygments.lexers.hdl', 'vhdl', ('vhdl',), ('*.vhdl', '*.vhd'), ('text/x-vhdl',)), - 'VimLexer': ('pygments.lexers.text', 'VimL', ('vim',), ('*.vim', '.vimrc', '.exrc', '.gvimrc', '_vimrc', '_exrc', '_gvimrc'), ('text/x-vim',)), + 'VimLexer': ('pygments.lexers.text', 'VimL', ('vim',), ('*.vim', '.vimrc', '.exrc', '.gvimrc', '_vimrc', '_exrc', '_gvimrc', 'vimrc', 'gvimrc'), ('text/x-vim',)), 'XQueryLexer': ('pygments.lexers.web', 'XQuery', ('xquery', 'xqy'), ('*.xqy', '*.xquery'), ('text/xquery', 'application/xquery')), 'XmlDjangoLexer': ('pygments.lexers.templates', 'XML+Django/Jinja', ('xml+django', 'xml+jinja'), (), ('application/xml+django', 'application/xml+jinja')), 'XmlErbLexer': ('pygments.lexers.templates', 'XML+Ruby', ('xml+erb', 'xml+ruby'), (), ('application/xml+ruby',)), @@ -290,3 +292,4 @@ if __name__ == '__main__': f.write('LEXERS = {\n %s,\n}\n\n' % ',\n '.join(found_lexers)) f.write(footer) f.close() + diff --git a/pygments/lexers/agile.py b/pygments/lexers/agile.py index 6e4e9d13..024ab8d5 100644 --- a/pygments/lexers/agile.py +++ b/pygments/lexers/agile.py @@ -381,7 +381,7 @@ class PythonTracebackLexer(RegexLexer): bygroups(Text, Name.Builtin, Text, Number, Text)), (r'^( )(.+)(\n)', bygroups(Text, using(PythonLexer), Text)), - (r'^([ \t]*)(...)(\n)', + (r'^([ \t]*)(\.\.\.)(\n)', bygroups(Text, Comment, Text)), # for doctests... (r'^(.+)(: )(.+)(\n)', bygroups(Generic.Error, Text, Name, Text), '#pop'), @@ -417,7 +417,7 @@ class Python3TracebackLexer(RegexLexer): bygroups(Text, Name.Builtin, Text, Number, Text, Name, Text)), (r'^( )(.+)(\n)', bygroups(Text, using(Python3Lexer), Text)), - (r'^([ \t]*)(...)(\n)', + (r'^([ \t]*)(\.\.\.)(\n)', bygroups(Text, Comment, Text)), # for doctests... (r'^(.+)(: )(.+)(\n)', bygroups(Generic.Error, Text, Name, Text), '#pop'), @@ -506,7 +506,7 @@ class RubyLexer(ExtendedRegexLexer): states = {} states['strings'] = [ # easy ones - (r'\:@{0,2}([a-zA-Z_][\w_]*[\!\?]?|\*\*?|[-+]@?|' + (r'\:@{0,2}([a-zA-Z_]\w*[\!\?]?|\*\*?|[-+]@?|' r'[/%&|^`~]|\[\]=?|<<|>>|<=?>|>=?|===?)', String.Symbol), (r":'(\\\\|\\'|[^'])*'", String.Symbol), (r"'(\\\\|\\'|[^'])*'", String.Single), @@ -703,7 +703,7 @@ class RubyLexer(ExtendedRegexLexer): # like keywords (class) or like this: ` ?!? (r'(\.|::)([a-zA-Z_]\w*[\!\?]?|[*%&^`~+-/\[<>=])', bygroups(Operator, Name)), - (r'[a-zA-Z_][\w_]*[\!\?]?', Name), + (r'[a-zA-Z_]\w*[\!\?]?', Name), (r'(\[|\]|\*\*|<<?|>>?|>=|<=|<=>|=~|={3}|' r'!~|&&?|\|\||\.{1,3})', Operator), (r'[-+/*%=<>&!^|~]=?', Operator), @@ -713,7 +713,7 @@ class RubyLexer(ExtendedRegexLexer): 'funcname': [ (r'\(', Punctuation, 'defexpr'), (r'(?:([a-zA-Z_][a-zA-Z0-9_]*)(\.))?' - r'([a-zA-Z_][\w_]*[\!\?]?|\*\*?|[-+]@?|' + r'([a-zA-Z_]\w*[\!\?]?|\*\*?|[-+]@?|' r'[/%&|^`~]|\[\]=?|<<|>>|<=?>|>=?|===?)', bygroups(Name.Class, Operator, Name.Function), '#pop'), (r'', Text, '#pop') @@ -721,7 +721,7 @@ class RubyLexer(ExtendedRegexLexer): 'classname': [ (r'\(', Punctuation, 'defexpr'), (r'<<', Operator, '#pop'), - (r'[A-Z_][\w_]*', Name.Class, '#pop'), + (r'[A-Z_]\w*', Name.Class, '#pop'), (r'', Text, '#pop') ], 'defexpr': [ @@ -924,7 +924,7 @@ class PerlLexer(RegexLexer): (r'(q|qq|qw|qr|qx)([^a-zA-Z0-9])(.|\n)*?\2', String.Other), (r'package\s+', Keyword, 'modulename'), (r'sub\s+', Keyword, 'funcname'), - (r'(\[\]|\*\*|::|<<|>>|>=|<=|<=>|={3}|!=|=~|' + (r'(\[\]|\*\*|::|<<|>>|>=|<=>|<=|={3}|!=|=~|' r'!~|&&?|\|\||\.{1,3})', Operator), (r'[-+/*%=<>&^|!\\~]=?', Operator), (r'[\(\)\[\]:;,<>/\?\{\}]', Punctuation), # yes, there's no shortage @@ -949,10 +949,10 @@ class PerlLexer(RegexLexer): (r'(?=[^a-zA-Z0-9_])', Text, '#pop'), ], 'modulename': [ - (r'[a-zA-Z_][\w_]*', Name.Namespace, '#pop') + (r'[a-zA-Z_]\w*', Name.Namespace, '#pop') ], 'funcname': [ - (r'[a-zA-Z_][\w_]*[\!\?]?', Name.Function), + (r'[a-zA-Z_]\w*[\!\?]?', Name.Function), (r'\s+', Text), # argument declaration (r'(\([$@%]*\))(\s*)', bygroups(Punctuation, Text)), @@ -1151,13 +1151,13 @@ class MoonScriptLexer(LuaLexer): (r'(?s)\[(=*)\[.*?\]\1\]', String), (r'(->|=>)', Name.Function), (r':[a-zA-Z_][a-zA-Z0-9_]*', Name.Variable), - (r'(==|!=|~=|<=|>=|\.\.|\.\.\.|[=+\-*/%^<>#!.\\:])', Operator), + (r'(==|!=|~=|<=|>=|\.\.\.|\.\.|[=+\-*/%^<>#!.\\:])', Operator), (r'[;,]', Punctuation), (r'[\[\]\{\}\(\)]', Keyword.Type), (r'[a-zA-Z_][a-zA-Z0-9_]*:', Name.Variable), (r"(class|extends|if|then|super|do|with|import|export|" - r"while|elseif|return|for|in|from|when|using|else|" - r"and|or|not|switch|break)\b", Keyword), + r"while|elseif|return|for|in|from|when|using|else|" + r"and|or|not|switch|break)\b", Keyword), (r'(true|false|nil)\b', Keyword.Constant), (r'(and|or|not)\b', Operator.Word), (r'(self)\b', Name.Builtin.Pseudo), @@ -1286,7 +1286,7 @@ class IoLexer(RegexLexer): # constants (r'(nil|false|true)\b', Name.Constant), # names - ('(Object|list|List|Map|args|Sequence|Coroutine|File)\b', + (r'(Object|list|List|Map|args|Sequence|Coroutine|File)\b', Name.Builtin), ('[a-zA-Z_][a-zA-Z0-9_]*', Name), # numbers @@ -1378,7 +1378,7 @@ class TclLexer(RegexLexer): 'params': [ (r';', Keyword, '#pop'), (r'\n', Text, '#pop'), - (r'(else|elseif|then)', Keyword), + (r'(else|elseif|then)\b', Keyword), include('basic'), include('data'), ], @@ -1785,7 +1785,7 @@ class FancyLexer(RegexLexer): ('[A-Z][a-zA-Z0-9_]*', Name.Constant), ('@[a-zA-Z_][a-zA-Z0-9_]*', Name.Variable.Instance), ('@@[a-zA-Z_][a-zA-Z0-9_]*', Name.Variable.Class), - ('(@|@@)', Operator), + ('@@?', Operator), ('[a-zA-Z_][a-zA-Z0-9_]*', Name), # numbers - / checks are necessary to avoid mismarking regexes, # see comment in RubyLexer diff --git a/pygments/lexers/asm.py b/pygments/lexers/asm.py index 26951f7e..11964a77 100644 --- a/pygments/lexers/asm.py +++ b/pygments/lexers/asm.py @@ -136,17 +136,17 @@ class ObjdumpLexer(RegexLexer): ('( *)('+hex+r'+:)(\t)((?:'+hex+hex+' )+)$', bygroups(Text, Name.Label, Text, Number.Hex)), # Skipped a few bytes - ('\t\.\.\.$', Text), + (r'\t\.\.\.$', Text), # Relocation line # (With offset) - ('(\t\t\t)('+hex+'+:)( )([^\t]+)(\t)(.*?)([-+])(0x' + hex + '+)$', + (r'(\t\t\t)('+hex+r'+:)( )([^\t]+)(\t)(.*?)([-+])(0x' + hex + '+)$', bygroups(Text, Name.Label, Text, Name.Property, Text, Name.Constant, Punctuation, Number.Hex)), # (Without offset) - ('(\t\t\t)('+hex+'+:)( )([^\t]+)(\t)(.*?)$', + (r'(\t\t\t)('+hex+r'+:)( )([^\t]+)(\t)(.*?)$', bygroups(Text, Name.Label, Text, Name.Property, Text, Name.Constant)), - ('[^\n]+\n', Other) + (r'[^\n]+\n', Other) ] } diff --git a/pygments/lexers/compiled.py b/pygments/lexers/compiled.py index eeab8d57..04077ec6 100644 --- a/pygments/lexers/compiled.py +++ b/pygments/lexers/compiled.py @@ -1058,7 +1058,7 @@ class DylanLexer(RegexLexer): tokens = { 'root': [ (r'\b(subclass|abstract|block|c(on(crete|stant)|lass)|domain' - r'|ex(c(eption|lude)|port)|f(unction(|al))|generic|handler' + r'|ex(c(eption|lude)|port)|f(unction(al)?)|generic|handler' r'|i(n(herited|line|stance|terface)|mport)|library|m(acro|ethod)' r'|open|primary|sealed|si(deways|ngleton)|slot' r'|v(ariable|irtual))\b', Name.Builtin), @@ -1068,7 +1068,7 @@ class DylanLexer(RegexLexer): (r'"', String, 'string'), (r"'(\\.|\\[0-7]{1,3}|\\x[a-fA-F0-9]{1,2}|[^\\\'\n])'", String.Char), (r'=>|\b(a(bove|fterwards)|b(e(gin|low)|y)|c(ase|leanup|reate)' - r'|define|else(|if)|end|f(inally|or|rom)|i[fn]|l(et|ocal)|otherwise' + r'|define|else(if)?|end|f(inally|or|rom)|i[fn]|l(et|ocal)|otherwise' r'|rename|s(elect|ignal)|t(hen|o)|u(n(less|til)|se)|wh(en|ile))\b', Keyword), (r'([ \t])([!\$%&\*\/:<=>\?~_^a-zA-Z0-9.+\-]*:)', @@ -2186,7 +2186,7 @@ class AdaLexer(RegexLexer): 'end' : [ ('(if|case|record|loop|select)', Keyword.Reserved), ('"[^"]+"|[a-zA-Z0-9_.]+', Name.Function), - ('[\n\s]+', Text), + ('\s+', Text), (';', Punctuation, '#pop'), ], 'type_def': [ @@ -2572,7 +2572,7 @@ class NimrodLexer(RegexLexer): (r'##.*$', String.Doc), (r'#.*$', Comment), (r'\*|=|>|<|\+|-|/|@|\$|~|&|%|\!|\?|\||\\|\[|\]', Operator), - (r'\.\.|\.|,|[\.|\.]|{\.|\.}|\(\.|\.\)|{|}|\(|\)|:|\^|`|;', + (r'\.\.|\.|,|\[\.|\.\]|{\.|\.}|\(\.|\.\)|{|}|\(|\)|:|\^|`|;', Punctuation), # Strings @@ -2679,7 +2679,7 @@ class FantomLexer(RegexLexer): id = r'[a-zA-Z_][a-zA-Z0-9_]*', # all chars which can be part of type definition. Starts with # either letter, or [ (maps), or | (funcs) - type = r'(?:\[|[a-zA-Z_]|\|)[:\w_\[\]\|\->\?]*?', + type = r'(?:\[|[a-zA-Z_]|\|)[:\w\[\]\|\->\?]*?', ) ) @@ -2810,7 +2810,7 @@ class FantomLexer(RegexLexer): ### ArgType argName, ##### (s(r'($type)(\s+)($id)(\s*)(,)'), - bygroups(using(this, state= 'inType'), Text, Name.Variable, + bygroups(using(this, state='inType'), Text, Name.Variable, Text, Punctuation)), #### ArgType argName) #### @@ -2818,13 +2818,13 @@ class FantomLexer(RegexLexer): ### ArgType argName -> ArgType| ### (s(r'($type)(\s+)($id)(\s*)(\->)(\s*)($type)(\|)'), - bygroups(using(this, state= 'inType'), Text, Name.Variable, + bygroups(using(this, state='inType'), Text, Name.Variable, Text, Punctuation, Text, using(this, state = 'inType'), Punctuation)), ### ArgType argName| ### (s(r'($type)(\s+)($id)(\s*)(\|)'), - bygroups(using(this, state= 'inType'), Text, Name.Variable, + bygroups(using(this, state='inType'), Text, Name.Variable, Text, Punctuation)), ### Type var @@ -2843,7 +2843,7 @@ class FantomLexer(RegexLexer): 'insideMethodDeclArgs': [ (r'\)', Punctuation, '#pop'), (s(r'($type)(\s+)($id)(\s*)(\))'), - bygroups(using(this, state= 'inType'), Text, Name.Variable, + bygroups(using(this, state='inType'), Text, Name.Variable, Text, Punctuation), '#pop'), include('root'), ], diff --git a/pygments/lexers/dotnet.py b/pygments/lexers/dotnet.py index 8b7a0b89..278ba546 100644 --- a/pygments/lexers/dotnet.py +++ b/pygments/lexers/dotnet.py @@ -344,7 +344,7 @@ class BooLexer(RegexLexer): (r"'(\\\\|\\'|[^']*?)'", String.Single), (r'[a-zA-Z_][a-zA-Z0-9_]*', Name), (r'(\d+\.\d*|\d*\.\d+)([fF][+-]?[0-9]+)?', Number.Float), - (r'[0-9][0-9\.]*(m|ms|d|h|s)', Number), + (r'[0-9][0-9\.]*(ms?|d|h|s)', Number), (r'0\d+', Number.Oct), (r'0x[a-fA-F0-9]+', Number.Hex), (r'\d+L', Number.Integer.Long), @@ -559,10 +559,10 @@ class FSharpLexer(RegexLexer): 'with', 'yield', 'yield!' ] keyopts = [ - '!=','#','&','&&','\(','\)','\*','\+',',','-', - '-\.','->','\.','\.\.',':','::',':=',':>',';',';;','<', - '<-','>','>]','\?','\?\?','\[','\[<','\[>','\[\|', - ']','_','`','{','\|','\|]','}','~','<@','=','@>' + '!=','#','&&','&','\(','\)','\*','\+',',','-\.', + '->','-','\.\.','\.','::',':=',':>',':',';;',';','<-', + '<','>]','>','\?\?','\?','\[<','\[>','\[\|','\[', + ']','_','`','{','\|\]','\|','}','~','<@','=','@>' ] operators = r'[!$%&*+\./:<=>?@^|~-]' diff --git a/pygments/lexers/functional.py b/pygments/lexers/functional.py index 583adadb..ee44f7ce 100644 --- a/pygments/lexers/functional.py +++ b/pygments/lexers/functional.py @@ -113,7 +113,7 @@ class SchemeLexer(RegexLexer): # strings, symbols and characters (r'"(\\\\|\\"|[^"])*"', String), (r"'" + valid_name, String.Symbol), - (r"#\\([()/'\".'_!§$%& ?=+-]{1}|[a-zA-Z0-9]+)", String.Char), + (r"#\\([()/'\"._!§$%& ?=+-]{1}|[a-zA-Z0-9]+)", String.Char), # constants (r'(#t|#f)', Name.Constant), @@ -560,7 +560,10 @@ class SMLLexer(RegexLexer): return [ (r'[^"\\]', whatkind), (r'\\[\\\"abtnvfr]', String.Escape), - (r'\\\^[@-^]', String.Escape), + # Control-character notation is used for codes < 32, + # where \^@ == \000 + (r'\\\^[\x40-\x5e]', String.Escape), + # Docs say 'decimal digits' (r'\\[0-9]{3}', String.Escape), (r'\\u[0-9a-fA-F]{4}', String.Escape), (r'\\\s+\\', String.Interpol), @@ -885,9 +888,9 @@ class OcamlLexer(RegexLexer): (r'\b([A-Z][A-Za-z0-9_\']*)(?=\s*\.)', Name.Namespace, 'dotted'), (r'\b([A-Z][A-Za-z0-9_\']*)', Name.Class), - (r'\(\*', Comment, 'comment'), + (r'\(\*(?![)])', Comment, 'comment'), (r'\b(%s)\b' % '|'.join(keywords), Keyword), - (r'(%s)' % '|'.join(keyopts), Operator), + (r'(%s)' % '|'.join(keyopts[::-1]), Operator), (r'(%s|%s)?%s' % (infix_syms, prefix_syms, operators), Operator), (r'\b(%s)\b' % '|'.join(word_operators), Operator.Word), (r'\b(%s)\b' % '|'.join(primitives), Keyword.Type), @@ -980,7 +983,7 @@ class ErlangLexer(RegexLexer): 'universaltime_to_localtime', 'unlink', 'unregister', 'whereis' ] - operators = r'(\+|-|\*|/|<|>|=|==|/=|=:=|=/=|=<|>=|\+\+|--|<-|!|\?)' + operators = r'(\+\+?|--?|\*|/|<|>|/=|=:=|=/=|=<|>=|==?|<-|!|\?)' word_operators = [ 'and', 'andalso', 'band', 'bnot', 'bor', 'bsl', 'bsr', 'bxor', 'div', 'not', 'or', 'orelse', 'rem', 'xor' @@ -1494,7 +1497,7 @@ class CoqLexer(RegexLexer): (r'\b([A-Z][A-Za-z0-9_\']*)(?=\s*\.)', Name.Namespace, 'dotted'), (r'\b([A-Z][A-Za-z0-9_\']*)', Name.Class), - (r'(%s)' % '|'.join(keyopts), Operator), + (r'(%s)' % '|'.join(keyopts[::-1]), Operator), (r'(%s|%s)?%s' % (infix_syms, prefix_syms, operators), Operator), (r'\b(%s)\b' % '|'.join(word_operators), Operator.Word), (r'\b(%s)\b' % '|'.join(primitives), Keyword.Type), @@ -1704,13 +1707,14 @@ class ElixirLexer(RegexLexer): r'<=>|&&?|%\(\)|%\[\]|%\{\}|\+\+?|\-\-?|\|\|?|\!|//|[%&`/\|]|' r'\*\*?|=?~|<\-)|([a-zA-Z_]\w*([?!])?)(:)(?!:)', String.Symbol), (r':"', String.Symbol, 'interpoling_symbol'), - (r'\b(nil|true|false)\b(?![?!])|\b[A-Z]\w*\b', Name.Constant), + (r'\b(nil|true|false)\b(?![?!])', Name.Constant), + (r'\b[A-Z]\w*\b', Name.Constant), (r'\b(__(FILE|LINE|MODULE|STOP_ITERATOR|EXCEPTION|OP|REF|FUNCTION|' r'BLOCK|KVBLOCK)__)\b(?![?!])', Name.Builtin.Pseudo), - (r'[a-zA-Z_][\w_]*[\!\?]?', Name), + (r'[a-zA-Z_!]\w*[!\?]?', Name), (r'[(){};,/\|:\\\[\]]', Punctuation), (r'@[a-zA-Z_]\w*|&\d', Name.Variable), - (r'\b(0[xX][0-9A-Fa-f]+|\d(_?\d)*(\.(?![^[:space:][:digit:]])' + (r'\b(0[xX][0-9A-Fa-f]+|\d(_?\d)*(\.(?![^\d\s])' r'(_?\d)*)?([eE][-+]?\d(_?\d)*)?|0[bB][01]+)\b', Number), include('strings'), ], diff --git a/pygments/lexers/hdl.py b/pygments/lexers/hdl.py index b4eccd3b..0db35e74 100644 --- a/pygments/lexers/hdl.py +++ b/pygments/lexers/hdl.py @@ -56,8 +56,9 @@ class VerilogLexer(RegexLexer): (r'[()\[\],.;\']', Punctuation), (r'`[a-zA-Z_][a-zA-Z0-9_]*', Name.Constant), - (r'^\s*(package)(\s+)', bygroups(Keyword.Namespace, Text)), - (r'^\s*(import)(\s+)', bygroups(Keyword.Namespace, Text), 'import'), + (r'^(\s*)(package)(\s+)', bygroups(Text, Keyword.Namespace, Text)), + (r'^(\s*)(import)(\s+)', bygroups(Text, Keyword.Namespace, Text), + 'import'), (r'(always|always_comb|always_ff|always_latch|and|assign|automatic|' r'begin|break|buf|bufif0|bufif1|case|casex|casez|cmos|const|' @@ -75,21 +76,21 @@ class VerilogLexer(RegexLexer): r'unsigned|var|vectored|void|wait|weak0|weak1|while|' r'xnor|xor)\b', Keyword), - (r'(`accelerate|`autoexpand_vectornets|`celldefine|`default_nettype|' - r'`else|`elsif|`endcelldefine|`endif|`endprotect|`endprotected|' - r'`expand_vectornets|`ifdef|`ifndef|`include|`noaccelerate|`noexpand_vectornets|' - r'`noremove_gatenames|`noremove_netnames|`nounconnected_drive|' - r'`protect|`protected|`remove_gatenames|`remove_netnames|`resetall|' - r'`timescale|`unconnected_drive|`undef)\b', Comment.Preproc), - - (r'(\$bits|\$bitstoreal|\$bitstoshortreal|\$countdrivers|\$display|\$fclose|' - r'\$fdisplay|\$finish|\$floor|\$fmonitor|\$fopen|\$fstrobe|\$fwrite|' - r'\$getpattern|\$history|\$incsave|\$input|\$itor|\$key|\$list|\$log|' - r'\$monitor|\$monitoroff|\$monitoron|\$nokey|\$nolog|\$printtimescale|' - r'\$random|\$readmemb|\$readmemh|\$realtime|\$realtobits|\$reset|\$reset_count|' - r'\$reset_value|\$restart|\$rtoi|\$save|\$scale|\$scope|\$shortrealtobits|' - r'\$showscopes|\$showvariables|\$showvars|\$sreadmemb|\$sreadmemh|' - r'\$stime|\$stop|\$strobe|\$time|\$timeformat|\$write)\b', Name.Builtin), + (r'`(accelerate|autoexpand_vectornets|celldefine|default_nettype|' + r'else|elsif|endcelldefine|endif|endprotect|endprotected|' + r'expand_vectornets|ifdef|ifndef|include|noaccelerate|noexpand_vectornets|' + r'noremove_gatenames|noremove_netnames|nounconnected_drive|' + r'protect|protected|remove_gatenames|remove_netnames|resetall|' + r'timescale|unconnected_drive|undef)\b', Comment.Preproc), + + (r'\$(bits|bitstoreal|bitstoshortreal|countdrivers|display|fclose|' + r'fdisplay|finish|floor|fmonitor|fopen|fstrobe|fwrite|' + r'getpattern|history|incsave|input|itor|key|list|log|' + r'monitor|monitoroff|monitoron|nokey|nolog|printtimescale|' + r'random|readmemb|readmemh|realtime|realtobits|reset|reset_count|' + r'reset_value|restart|rtoi|save|scale|scope|shortrealtobits|' + r'showscopes|showvariables|showvars|sreadmemb|sreadmemh|' + r'stime|stop|strobe|time|timeformat|write)\b', Name.Builtin), (r'(byte|shortint|int|longint|integer|time|' r'bit|logic|reg|' @@ -146,6 +147,9 @@ class SystemVerilogLexer(RegexLexer): tokens = { 'root': [ (r'^\s*`define', Comment.Preproc, 'macro'), + (r'^(\s*)(package)(\s+)', bygroups(Text, Keyword.Namespace, Text)), + (r'^(\s*)(import)(\s+)', bygroups(Text, Keyword.Namespace, Text), 'import'), + (r'\n', Text), (r'\s+', Text), (r'\\\n', Text), # line continuation @@ -167,11 +171,6 @@ class SystemVerilogLexer(RegexLexer): (r'[()\[\],.;\']', Punctuation), (r'`[a-zA-Z_][a-zA-Z0-9_]*', Name.Constant), - (r'^\s*(package)(\s+)', bygroups(Keyword.Namespace, Text)), - (r'^\s*(import)(\s+)', bygroups(Keyword.Namespace, Text), 'import'), - - - (r'(accept_on|alias|always|always_comb|always_ff|always_latch|' r'and|assert|assign|assume|automatic|before|begin|bind|bins|' r'binsof|bit|break|buf|bufif0|bufif1|byte|case|casex|casez|' diff --git a/pygments/lexers/jvm.py b/pygments/lexers/jvm.py index 83b45613..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): @@ -117,7 +119,7 @@ class ScalaLexer(RegexLexer): ur'lazy|match|new|override|pr(?:ivate|otected)' ur'|re(?:quires|turn)|s(?:ealed|uper)|' ur't(?:h(?:is|row)|ry)|va[lr]|w(?:hile|ith)|yield)\b|' - u'(<[%:-]|=>|>:|[#=@_\u21D2\u2190])(\b|(?=\\s)|$)', Keyword), + u'(<[%:-]|=>|>:|[#=@_\u21D2\u2190])(\\b|(?=\\s)|$)', Keyword), (ur':(?!%s)' % op, Keyword, 'type'), (ur'%s%s\b' % (upper, idrest), Name.Class), (r'(true|false|null)\b', Keyword.Constant), @@ -125,7 +127,7 @@ class ScalaLexer(RegexLexer): (r'(type)(\s+)', bygroups(Keyword, Text), 'type'), (r'""".*?"""', String), (r'"(\\\\|\\"|[^"])*"', String), - (ur"'\\.'|'[^\\]'|'\\u[0-9a-f]{4}'", String.Char), + (r"'\\.'|'[^\\]'|'\\u[0-9a-f]{4}'", String.Char), # (ur'(\.)(%s|%s|`[^`]+`)' % (idrest, op), bygroups(Operator, # Name.Attribute)), (idrest, Name), @@ -133,7 +135,7 @@ class ScalaLexer(RegexLexer): (r'\[', Operator, 'typeparam'), (r'[\(\)\{\};,.#]', Operator), (op, Operator), - (ur'([0-9][0-9]*\.[0-9]*|\.[0-9]+)([eE][+-]?[0-9]+)?[fFdD]?', + (r'([0-9][0-9]*\.[0-9]*|\.[0-9]+)([eE][+-]?[0-9]+)?[fFdD]?', Number.Float), (r'0x[0-9a-f]+', Number.Hex), (r'[0-9]+L?', Number.Integer), @@ -142,7 +144,7 @@ class ScalaLexer(RegexLexer): 'class': [ (ur'(%s|%s|`[^`]+`)(\s*)(\[)' % (idrest, op), bygroups(Name.Class, Text, Operator), 'typeparam'), - (r'[\s\n]+', Text), + (r'\s+', Text), (r'{', Operator, '#pop'), (r'\(', Operator, '#pop'), (r'//.*?\n', Comment.Single, '#pop'), @@ -151,7 +153,7 @@ class ScalaLexer(RegexLexer): 'type': [ (r'\s+', Text), (u'<[%:]|>:|[#_\u21D2]|forSome|type', Keyword), - (r'([,\);}]|=>|=)([\s\n]*)', bygroups(Operator, Text), '#pop'), + (r'([,\);}]|=>|=)(\s*)', bygroups(Operator, Text), '#pop'), (r'[\(\{]', Operator, '#push'), (ur'((?:%s|%s|`[^`]+`)(?:\.(?:%s|%s|`[^`]+`))*)(\s*)(\[)' % (idrest, op, idrest, op), @@ -163,7 +165,7 @@ class ScalaLexer(RegexLexer): (ur'\.|%s|%s|`[^`]+`' % (idrest, op), Keyword.Type) ], 'typeparam': [ - (r'[\s\n,]+', Text), + (r'[\s,]+', Text), (u'<[%:]|=>|>:|[#_\u21D2]|forSome|type', Keyword), (r'([\]\)\}])', Operator, '#pop'), (r'[\(\[\{]', Operator, '#push'), @@ -421,7 +423,7 @@ class IokeLexer(RegexLexer): #Documentation (r'((?<=fn\()|(?<=fnx\()|(?<=method\()|(?<=macro\()|(?<=lecro\()' r'|(?<=syntax\()|(?<=dmacro\()|(?<=dlecro\()|(?<=dlecrox\()' - r'|(?<=dsyntax\())[\s\n\r]*"', String.Doc, 'documentation'), + r'|(?<=dsyntax\())\s*"', String.Doc, 'documentation'), #Text (r'"', String, 'text'), @@ -526,7 +528,7 @@ class IokeLexer(RegexLexer): Operator), # Punctuation - (r'(\`\`|\`|\'\'|\'|\.|\,|@|@@|\[|\]|\(|\)|{|})', Punctuation), + (r'(\`\`|\`|\'\'|\'|\.|\,|@@|@|\[|\]|\(|\)|{|})', Punctuation), #kinds (r'[A-Z][a-zA-Z0-9_!:?]*', Name.Class), @@ -676,3 +678,170 @@ class ClojureLexer(RegexLexer): (r'(\(|\))', Punctuation), ], } + + +class TeaLangLexer(RegexLexer): + """ + For `Tea <http://teatrove.org/>`_ source code. Only used within a + TeaTemplateLexer. + + *New in Pygments 1.5.* + """ + + flags = re.MULTILINE | re.DOTALL + + #: optional Comment or Whitespace + _ws = r'(?:\s|//.*?\n|/[*].*?[*]/)+' + + tokens = { + 'root': [ + # method names + (r'^(\s*(?:[a-zA-Z_][a-zA-Z0-9_\.\[\]]*\s+)+?)' # return arguments + r'([a-zA-Z_][a-zA-Z0-9_]*)' # method name + r'(\s*)(\()', # signature start + bygroups(using(this), Name.Function, Text, Operator)), + (r'[^\S\n]+', Text), + (r'//.*?\n', Comment.Single), + (r'/\*.*?\*/', Comment.Multiline), + (r'@[a-zA-Z_][a-zA-Z0-9_\.]*', Name.Decorator), + (r'(and|break|else|foreach|if|in|not|or|reverse)\b', + Keyword), + (r'(as|call|define)\b', Keyword.Declaration), + (r'(true|false|null)\b', Keyword.Constant), + (r'(template)(\s+)', bygroups(Keyword.Declaration, Text), 'template'), + (r'(import)(\s+)', bygroups(Keyword.Namespace, Text), 'import'), + (r'"(\\\\|\\"|[^"])*"', String), + (r'\'(\\\\|\\\'|[^\'])*\'', String), + (r'(\.)([a-zA-Z_][a-zA-Z0-9_]*)', bygroups(Operator, Name.Attribute)), + (r'[a-zA-Z_][a-zA-Z0-9_]*:', Name.Label), + (r'[a-zA-Z_\$][a-zA-Z0-9_]*', Name), + (r'(isa|[.]{3}|[.]{2}|[=#!<>+-/%&;,.\*\\\(\)\[\]\{\}])', Operator), + (r'[0-9][0-9]*\.[0-9]+([eE][0-9]+)?[fd]?', Number.Float), + (r'0x[0-9a-f]+', Number.Hex), + (r'[0-9]+L?', Number.Integer), + (r'\n', Text) + ], + 'template': [ + (r'[a-zA-Z_][a-zA-Z0-9_]*', Name.Class, '#pop') + ], + 'import': [ + (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/math.py b/pygments/lexers/math.py index 92eebef1..7ae7d6b2 100644 --- a/pygments/lexers/math.py +++ b/pygments/lexers/math.py @@ -230,8 +230,8 @@ class MuPADLexer(RegexLexer): #(r'\b(?:adt|linalg|newDomain|hold)\b', Name.Builtin), (r'''(?x) ((?:[a-zA-Z_#][a-zA-Z_#0-9]*|`[^`]*`) - (?:::[a-zA-Z_#][a-zA-Z_#0-9]*|`[^`]*`)*)\s*([(])''', - bygroups(Name.Function, Punctuation)), + (?:::[a-zA-Z_#][a-zA-Z_#0-9]*|`[^`]*`)*)(\s*)([(])''', + bygroups(Name.Function, Text, Punctuation)), (r'''(?x) (?:[a-zA-Z_#][a-zA-Z_#0-9]*|`[^`]*`) (?:::[a-zA-Z_#][a-zA-Z_#0-9]*|`[^`]*`)*''', Name.Variable), @@ -823,7 +823,7 @@ class ScilabLexer(RegexLexer): _scilab_builtins.macros_kw ) + r')\b', Name.Builtin), - ("(" + "|".join(_scilab_builtins.builtin_consts) + r')\b', + (r'(%s)\b' % "|".join(map(re.escape, _scilab_builtins.builtin_consts)), Name.Constant), # operators: @@ -832,7 +832,7 @@ class ScilabLexer(RegexLexer): (r'\.\*|\*|\+|\.\^|\.\\|\.\/|\/|\\', Operator), # punctuation: - (r'[\[\](){}:@.,=:;]', Punctuation), + (r'[\[\](){}@.,=:;]', Punctuation), (r'"[^"]*"', String), diff --git a/pygments/lexers/other.py b/pygments/lexers/other.py index a64022e4..c9718142 100644 --- a/pygments/lexers/other.py +++ b/pygments/lexers/other.py @@ -79,7 +79,7 @@ class ECLLexer(RegexLexer): (r'^#.*$', Comment.Preproc), ], 'types': [ - (r'(RECORD|END)[^\d]', Keyword.Declaration), + (r'(RECORD|END)\D', Keyword.Declaration), (r'((?:ASCII|BIG_ENDIAN|BOOLEAN|DATA|DECIMAL|EBCDIC|INTEGER|PATTERN|' r'QSTRING|REAL|RECORD|RULE|SET OF|STRING|TOKEN|UDECIMAL|UNICODE|' r'UNSIGNED|VARSTRING|VARUNICODE)\d*)(\s+)', @@ -310,7 +310,7 @@ class SmalltalkLexer(RegexLexer): ], 'blockvariables' : [ include('whitespaces'), - (r'(:)(\s*)([A-Za-z\w]+)', + (r'(:)(\s*)(\w+)', bygroups(Operator, Text, Name.Variable)), (r'\|', Operator, '#pop'), (r'', Text, '#pop'), # else pop @@ -325,7 +325,7 @@ class SmalltalkLexer(RegexLexer): '_parenth_helper' : [ include('whitespaces'), (r'(\d+r)?-?\d+(\.\d+)?(e-?\d+)?', Number), - (r'[-+*/\\~<>=|&#!?,@%\w+:]+', String.Symbol), + (r'[-+*/\\~<>=|&#!?,@%\w:]+', String.Symbol), # literals (r'\'[^\']*\'', String), (r'\$.', String.Char), @@ -541,12 +541,12 @@ class LogtalkLexer(RegexLexer): (r'[()\[\],.|]', Text), # Atoms (r"[a-z][a-zA-Z0-9_]*", Text), - (r"[']", String, 'quoted_atom'), + (r"'", String, 'quoted_atom'), ], 'quoted_atom': [ - (r"['][']", String), - (r"[']", String, '#pop'), + (r"''", String), + (r"'", String, '#pop'), (r'\\([\\abfnrtv"\']|(x[a-fA-F0-9]+|[0-7]+)\\)', String.Escape), (r"[^\\'\n]+", String), (r'\\', String), @@ -588,7 +588,7 @@ class LogtalkLexer(RegexLexer): (r'([A-Z_][a-zA-Z0-9_]*)', Name.Variable), # Atoms (r"[a-z][a-zA-Z0-9_]*", Text), - (r"[']", String, 'quoted_atom'), + (r"'", String, 'quoted_atom'), # Strings (r'"(\\\\|\\"|[^"])*"', String), # End of entity-opening directive @@ -798,9 +798,9 @@ class PovrayLexer(RegexLexer): (r'/\*[\w\W]*?\*/', Comment.Multiline), (r'//.*\n', Comment.Single), (r'(?s)"(?:\\.|[^"\\])+"', String.Double), - (r'#(debug|default|else|end|error|fclose|fopen|if|ifdef|ifndef|' + (r'#(debug|default|else|end|error|fclose|fopen|ifdef|ifndef|' r'include|range|read|render|statistics|switch|undef|version|' - r'warning|while|write|define|macro|local|declare)', + r'warning|while|write|define|macro|local|declare)\b', Comment.Preproc), (r'\b(aa_level|aa_threshold|abs|acos|acosh|adaptive|adc_bailout|' r'agate|agate_turb|all|alpha|ambient|ambient_light|angle|' @@ -850,11 +850,11 @@ class PovrayLexer(RegexLexer): r'vnormalize|volume_object|volume_rendered|vol_with_light|' r'vrotate|v_steps|warning|warp|water_level|waves|while|width|' r'wood|wrinkles|yes)\b', Keyword), - (r'bicubic_patch|blob|box|camera|cone|cubic|cylinder|difference|' + (r'(bicubic_patch|blob|box|camera|cone|cubic|cylinder|difference|' r'disc|height_field|intersection|julia_fractal|lathe|' r'light_source|merge|mesh|object|plane|poly|polygon|prism|' r'quadric|quartic|smooth_triangle|sor|sphere|superellipsoid|' - r'text|torus|triangle|union', Name.Builtin), + r'text|torus|triangle|union)\b', Name.Builtin), # TODO: <=, etc (r'[\[\](){}<>;,]', Punctuation), (r'[-+*/=]', Operator), @@ -892,7 +892,7 @@ class AppleScriptLexer(RegexLexer): Classes = ['alias ', 'application ', 'boolean ', 'class ', 'constant ', 'date ', 'file ', 'integer ', 'list ', 'number ', 'POSIX file ', 'real ', 'record ', 'reference ', 'RGB color ', 'script ', - 'text ', 'unit types', '(Unicode )?text', 'string'] + 'text ', 'unit types', '(?:Unicode )?text', 'string'] BuiltIn = ['attachment', 'attribute run', 'character', 'day', 'month', 'paragraph', 'word', 'year'] HandlerParams = ['about', 'above', 'against', 'apart from', 'around', @@ -1158,7 +1158,7 @@ class AppleScriptLexer(RegexLexer): (ur'(-|\*|\+|&|≠|>=?|<=?|=|≥|≤|/|÷|\^)', Operator), (r"\b(%s)\b" % '|'.join(Operators), Operator.Word), (r'^(\s*(?:on|end)\s+)' - r'(%s)' % '|'.join(StudioEvents), + r'(%s)' % '|'.join(StudioEvents[::-1]), bygroups(Keyword, Name.Function)), (r'^(\s*)(in|on|script|to)(\s+)', bygroups(Text, Keyword, Text)), (r'\b(as )(%s)\b' % '|'.join(Classes), @@ -1240,11 +1240,11 @@ class ModelicaLexer(RegexLexer): ], 'functions': [ (r'(abs|acos|acosh|asin|asinh|atan|atan2|atan3|ceil|cos|cosh|' - r'cross|div|exp|floor|log|log10|mod|rem|sign|sin|sinh|size|' - r'sqrt|tan|tanh|zeros)\b', Name.Function) + r'cross|div|exp|floor|log|log10|mod|rem|semiLinear|sign|sin|' + r'sinh|size|sqrt|tan|tanh|zeros)\b', Name.Function) ], 'operators': [ - (r'(and|assert|cardinality|change|delay|der|edge|initial|' + (r'(and|assert|cardinality|change|delay|der|edge|homotopy|initial|' r'noEvent|not|or|pre|reinit|return|sample|smooth|' r'terminal|terminate)\b', Name.Builtin) ], @@ -1501,7 +1501,7 @@ class ABAPLexer(RegexLexer): ], 'variable-names': [ (r'<[\S_]+>', Name.Variable), - (r'[\w][\w_~]*(?:(\[\])|->\*)?', Name.Variable), + (r'\w[\w~]*(?:(\[\])|->\*)?', Name.Variable), ], 'root': [ include('common'), @@ -1511,21 +1511,21 @@ class ABAPLexer(RegexLexer): (r'(CALL\s+(?:DIALOG|SCREEN|SUBSCREEN|SELECTION-SCREEN|' r'TRANSACTION|TRANSFORMATION))\b', Keyword), - (r'(FORM|PERFORM)(\s+)([\w_]+)', + (r'(FORM|PERFORM)(\s+)(\w+)', bygroups(Keyword, Text, Name.Function)), - (r'(PERFORM)(\s+)(\()([\w_]+)(\))', + (r'(PERFORM)(\s+)(\()(\w+)(\))', bygroups(Keyword, Text, Punctuation, Name.Variable, Punctuation )), (r'(MODULE)(\s+)(\S+)(\s+)(INPUT|OUTPUT)', bygroups(Keyword, Text, Name.Function, Text, Keyword)), # method implementation - (r'(METHOD)(\s+)([\w_~]+)', + (r'(METHOD)(\s+)([\w~]+)', bygroups(Keyword, Text, Name.Function)), # method calls - (r'(\s+)([\w_\-]+)([=\-]>)([\w_\-~]+)', + (r'(\s+)([\w\-]+)([=\-]>)([\w\-~]+)', bygroups(Text, Name.Variable, Operator, Name.Function)), # call methodnames returning style - (r'(?<=(=|-)>)([\w_\-~]+)(?=\()', Name.Function), + (r'(?<=(=|-)>)([\w\-~]+)(?=\()', Name.Function), # keywords with dashes in them. # these need to be first, because for instance the -ID part @@ -2034,7 +2034,7 @@ class PostScriptLexer(RegexLexer): ], 'escape': [ - (r'([0-8]{3}|n|r|t|b|f|\\|\(|\)|)', String.Escape, '#pop'), + (r'([0-8]{3}|n|r|t|b|f|\\|\(|\))?', String.Escape, '#pop'), ], } @@ -2394,7 +2394,7 @@ class HybrisLexer(RegexLexer): # method names (r'^(\s*(?:function|method|operator\s+)+?)' r'([a-zA-Z_][a-zA-Z0-9_]*)' - r'(\s*)(\()', bygroups(Name.Function, Text, Operator)), + r'(\s*)(\()', bygroups(Keyword, Name.Function, Text, Operator)), (r'[^\S\n]+', Text), (r'//.*?\n', Comment.Single), (r'/\*.*?\*/', Comment.Multiline), @@ -2478,7 +2478,7 @@ class AwkLexer(RegexLexer): (r'', Text, '#pop') ], 'badregex': [ - ('\n', Text, '#pop') + (r'\n', Text, '#pop') ], 'root': [ (r'^(?=\s|/)', Text, 'slashstartsregex'), @@ -2608,7 +2608,7 @@ class SnobolLexer(RegexLexer): # ASCII equivalents of original operators # | for the EBCDIC equivalent, ! likewise # \ for EBCDIC negation - (r'\*\*|[\?\$\.!%\*/#+\-@\|&\\!=]', Operator), + (r'\*\*|[\?\$\.!%\*/#+\-@\|&\\=]', Operator), (r'"[^"]*"', String), (r"'[^']*'", String), # Accept SPITBOL syntax for real numbers @@ -3244,8 +3244,8 @@ class OpenEdgeLexer(RegexLexer): (r'[0-9][0-9]*\.[0-9]+([eE][0-9]+)?[fd]?', Number.Float), (r'[0-9]+', Number.Integer), (r'\s+', Text), - (r'[\\+\\-\\*\\/\\=]', Operator), - (r'[\\.\\:\\(\\)]', Punctuation), + (r'[+*/=-]', Operator), + (r'[.:()]', Punctuation), (r'.', Name.Variable), # Lazy catch-all ], 'comment': [ @@ -3279,7 +3279,7 @@ class BroLexer(RegexLexer): tokens = { 'root': [ # Whitespace - ('^@.*?\n', Comment.Preproc), + (r'^@.*?\n', Comment.Preproc), (r'#.*?\n', Comment.Single), (r'\n', Text), (r'\s+', Text), @@ -3315,8 +3315,8 @@ class BroLexer(RegexLexer): (r'/', String.Regex, 'regex'), (r'"', String, 'string'), # Operators - (r'[!%*/+-:<=>?~|]', Operator), - (r'([-+=&|]{2}|[+-=!><]=)', Operator), + (r'[!%*/+:<=>?~|-]', Operator), + (r'([-+=&|]{2}|[+=!><-]=)', Operator), (r'(in|match)\b', Operator.Word), (r'[{}()\[\]$.,;]', Punctuation), # Identfier diff --git a/pygments/lexers/parsers.py b/pygments/lexers/parsers.py index c4aacf22..2b5f954f 100644 --- a/pygments/lexers/parsers.py +++ b/pygments/lexers/parsers.py @@ -72,8 +72,8 @@ class RagelLexer(RegexLexer): ], 'operators': [ (r',', Operator), # Join - (r'\||&|-|--', Operator), # Union, Intersection and Subtraction - (r'\.|<:|:>|:>>', Operator), # Concatention + (r'\||&|--?', Operator), # Union, Intersection and Subtraction + (r'\.|<:|:>>?', Operator), # Concatention (r':', Operator), # Label (r'->', Operator), # Epsilon Transition (r'(>|\$|%|<|@|<>)(/|eof\b)', Operator), # EOF Actions @@ -393,7 +393,7 @@ class AntlrLexer(RegexLexer): # throwsSpec (r'(throws)(\s+)(' + _id + ')', bygroups(Keyword, Whitespace, Name.Label)), - (r'(?:(,)(\s*)(' + _id + '))+', + (r'(,)(\s*)(' + _id + ')', bygroups(Punctuation, Whitespace, Name.Label)), # Additional throws # optionsSpec (r'options\b', Keyword, 'options'), diff --git a/pygments/lexers/shell.py b/pygments/lexers/shell.py index 8c78d158..b6afa353 100644 --- a/pygments/lexers/shell.py +++ b/pygments/lexers/shell.py @@ -32,7 +32,8 @@ class BashLexer(RegexLexer): name = 'Bash' aliases = ['bash', 'sh', 'ksh'] - filenames = ['*.sh', '*.ksh', '*.bash', '*.ebuild', '*.eclass'] + filenames = ['*.sh', '*.ksh', '*.bash', '*.ebuild', '*.eclass', + '.bashrc', 'bashrc', '.bash_*', 'bash_*'] mimetypes = ['application/x-sh', 'application/x-shellscript'] tokens = { @@ -67,7 +68,7 @@ class BashLexer(RegexLexer): (r"(?s)\$?'(\\\\|\\[0-7]+|\\.|[^'\\])*'", String.Single), (r';', Text), (r'\s+', Text), - (r'[^=\s\n\[\]{}()$"\'`\\<]+', Text), + (r'[^=\s\[\]{}()$"\'`\\<]+', Text), (r'\d+(?= |\Z)', Number), (r'\$#?(\w+|.)', Name.Variable), (r'<', Text), @@ -121,8 +122,8 @@ class BashSessionLexer(Lexer): for match in line_re.finditer(text): line = match.group() - m = re.match(r'^((?:|sh\S*?|\w+\S+[@:]\S+(?:\s+\S+)?|\[\S+[@:]' - r'[^\n]+\].+)[$#%])(.*\n?)', line) + m = re.match(r'^((?:\(\S+\))?(?:|sh\S*?|\w+\S+[@:]\S+(?:\s+\S+)' + r'?|\[\S+[@:][^\n]+\].+)[$#%])(.*\n?)' , line) if m: # To support output lexers (say diff output), the output # needs to be broken by prompts whenever the output lexer @@ -251,7 +252,7 @@ class TcshLexer(RegexLexer): (r'(?s)"(\\\\|\\[0-7]+|\\.|[^"\\])*"', String.Double), (r"(?s)'(\\\\|\\[0-7]+|\\.|[^'\\])*'", String.Single), (r'\s+', Text), - (r'[^=\s\n\[\]{}()$"\'`\\]+', Text), + (r'[^=\s\[\]{}()$"\'`\\]+', Text), (r'\d+(?= |\Z)', Number), (r'\$#?(\w+|.)', Name.Variable), ], @@ -315,7 +316,7 @@ class PowerShellLexer(RegexLexer): commenthelp = ( 'component description example externalhelp forwardhelpcategory ' - 'forwardhelptargetname forwardhelptargetname functionality inputs link ' + 'forwardhelptargetname functionality inputs link ' 'notes outputs parameter remotehelprunspace role synopsis').split() tokens = { diff --git a/pygments/lexers/sql.py b/pygments/lexers/sql.py index d5444fcb..656d29a7 100644 --- a/pygments/lexers/sql.py +++ b/pygments/lexers/sql.py @@ -147,14 +147,14 @@ class PostgresLexer(PostgresBase, RegexLexer): for s in DATATYPES + PSEUDO_TYPES]) + r')\b', Name.Builtin), (r'(' + '|'.join(KEYWORDS) + r')\b', Keyword), - (r'[+*/<>=~!@#%^&|`?^-]+', Operator), + (r'[+*/<>=~!@#%^&|`?-]+', Operator), (r'::', Operator), # cast (r'\$\d+', Name.Variable), (r'([0-9]*\.[0-9]*|[0-9]+)(e[+-]?[0-9]+)?', Number.Float), (r'[0-9]+', Number.Integer), (r"(E|U&)?'(''|[^'])*'", String.Single), (r'(U&)?"(""|[^"])*"', String.Name), # quoted identifier - (r'(?ms)(\$[^\$]*\$)(.*?)(\1)', language_callback), + (r'(?s)(\$[^\$]*\$)(.*?)(\1)', language_callback), (r'[a-zA-Z_][a-zA-Z0-9_]*', Name), # psql variable in SQL @@ -434,7 +434,7 @@ class SqlLexer(RegexLexer): r'DEC|DECIMAL|FLOAT|INT|INTEGER|INTERVAL|NUMBER|NUMERIC|REAL|' r'SERIAL|SMALLINT|VARCHAR|VARYING|INT8|SERIAL8|TEXT)\b', Name.Builtin), - (r'[+*/<>=~!@#%^&|`?^-]', Operator), + (r'[+*/<>=~!@#%^&|`?-]', Operator), (r'[0-9]+', Number.Integer), # TODO: Backslash escapes? (r"'(''|[^'])*'", String.Single), @@ -472,7 +472,7 @@ class MySqlLexer(RegexLexer): (r"'(''|[^'])*'", String.Single), (r'"(""|[^"])*"', String.Double), (r"`(``|[^`])*`", String.Symbol), - (r'[+*/<>=~!@#%^&|`?^-]', Operator), + (r'[+*/<>=~!@#%^&|`?-]', Operator), (r'\b(tinyint|smallint|mediumint|int|integer|bigint|date|' r'datetime|time|bit|bool|tinytext|mediumtext|longtext|text|' r'tinyblob|mediumblob|longblob|blob|float|double|double\s+' diff --git a/pygments/lexers/templates.py b/pygments/lexers/templates.py index 717d689f..84850728 100644 --- a/pygments/lexers/templates.py +++ b/pygments/lexers/templates.py @@ -15,6 +15,7 @@ from pygments.lexers.web import \ PhpLexer, HtmlLexer, XmlLexer, JavascriptLexer, CssLexer from pygments.lexers.agile import PythonLexer, PerlLexer from pygments.lexers.compiled import JavaLexer +from pygments.lexers.jvm import TeaLangLexer from pygments.lexer import Lexer, DelegatingLexer, RegexLexer, bygroups, \ include, using, this from pygments.token import Error, Punctuation, \ @@ -33,11 +34,10 @@ __all__ = ['HtmlPhpLexer', 'XmlPhpLexer', 'CssPhpLexer', 'MyghtyCssLexer', 'MyghtyJavascriptLexer', 'MasonLexer', 'MakoLexer', 'MakoHtmlLexer', 'MakoXmlLexer', 'MakoJavascriptLexer', 'MakoCssLexer', 'JspLexer', 'CheetahLexer', 'CheetahHtmlLexer', - 'CheetahXmlLexer', 'CheetahJavascriptLexer', - 'EvoqueLexer', 'EvoqueHtmlLexer', 'EvoqueXmlLexer', - 'ColdfusionLexer', 'ColdfusionHtmlLexer', - 'VelocityLexer', 'VelocityHtmlLexer', 'VelocityXmlLexer', - 'SspLexer'] + 'CheetahXmlLexer', 'CheetahJavascriptLexer', 'EvoqueLexer', + 'EvoqueHtmlLexer', 'EvoqueXmlLexer', 'ColdfusionLexer', + 'ColdfusionHtmlLexer', 'VelocityLexer', 'VelocityHtmlLexer', + 'VelocityXmlLexer', 'SspLexer', 'TeaTemplateLexer'] class ErbLexer(Lexer): @@ -168,7 +168,7 @@ class SmartyLexer(RegexLexer): (r'#[a-zA-Z_][a-zA-Z0-9_]*#', Name.Variable), (r'\$[a-zA-Z_][a-zA-Z0-9_]*(\.[a-zA-Z0-9_]+)*', Name.Variable), (r'[~!%^&*()+=|\[\]:;,.<>/?{}@-]', Operator), - ('(true|false|null)\b', Keyword.Constant), + (r'(true|false|null)\b', Keyword.Constant), (r"[0-9](\.[0-9]*)?(eE[+-][0-9])?[flFLdD]?|" r"0[xX][0-9a-fA-F]+[Ll]?", Number), (r'"(\\\\|\\"|[^"])*"', String.Double), @@ -406,11 +406,11 @@ class MyghtyLexer(RegexLexer): tokens = { 'root': [ (r'\s+', Text), - (r'(<%(def|method))(\s*)(.*?)(>)(.*?)(</%\2\s*>)(?s)', - bygroups(Name.Tag, None, Text, Name.Function, Name.Tag, + (r'(<%(?:def|method))(\s*)(.*?)(>)(.*?)(</%\2\s*>)(?s)', + bygroups(Name.Tag, Text, Name.Function, Name.Tag, using(this), Name.Tag)), - (r'(<%(\w+))(.*?)(>)(.*?)(</%\2\s*>)(?s)', - bygroups(Name.Tag, None, Name.Function, Name.Tag, + (r'(<%\w+)(.*?)(>)(.*?)(</%\2\s*>)(?s)', + bygroups(Name.Tag, Name.Function, Name.Tag, using(PythonLexer), Name.Tag)), (r'(<&[^|])(.*?)(,.*?)?(&>)', bygroups(Name.Tag, Name.Function, using(PythonLexer), Name.Tag)), @@ -525,11 +525,11 @@ class MasonLexer(RegexLexer): (r'\s+', Text), (r'(<%doc>)(.*?)(</%doc>)(?s)', bygroups(Name.Tag, Comment.Multiline, Name.Tag)), - (r'(<%(def|method))(\s*)(.*?)(>)(.*?)(</%\2\s*>)(?s)', - bygroups(Name.Tag, None, Text, Name.Function, Name.Tag, + (r'(<%(?:def|method))(\s*)(.*?)(>)(.*?)(</%\2\s*>)(?s)', + bygroups(Name.Tag, Text, Name.Function, Name.Tag, using(this), Name.Tag)), - (r'(<%(\w+))(.*?)(>)(.*?)(</%\2\s*>)(?s)', - bygroups(Name.Tag, None, Name.Function, Name.Tag, + (r'(<%\w+)(.*?)(>)(.*?)(</%\2\s*>)(?s)', + bygroups(Name.Tag, Name.Function, Name.Tag, using(PerlLexer), Name.Tag)), (r'(<&[^|])(.*?)(,.*?)?(&>)(?s)', bygroups(Name.Tag, Name.Function, using(PerlLexer), Name.Tag)), @@ -616,8 +616,8 @@ class MakoLexer(RegexLexer): include('tag'), ], 'tag': [ - (r'((?:\w+)\s*=)\s*(".*?")', - bygroups(Name.Attribute, String)), + (r'((?:\w+)\s*=)(\s*)(".*?")', + bygroups(Name.Attribute, Text, String)), (r'/?\s*>', Comment.Preproc, '#pop'), (r'\s+', Text), ], @@ -1403,7 +1403,7 @@ class EvoqueLexer(RegexLexer): # directives: begin, end (r'(\$)(begin|end)(\{(%)?)(.*?)((?(4)%)\})', bygroups(Punctuation, Name.Builtin, Punctuation, None, - String, Punctuation, None)), + String, Punctuation)), # directives: evoque, overlay # see doc for handling first name arg: /directives/evoque/ #+ minor inconsistency: the "name" in e.g. $overlay{name=site_base} @@ -1411,17 +1411,17 @@ class EvoqueLexer(RegexLexer): (r'(\$)(evoque|overlay)(\{(%)?)(\s*[#\w\-"\'.]+[^=,%}]+?)?' r'(.*?)((?(4)%)\})', bygroups(Punctuation, Name.Builtin, Punctuation, None, - String, using(PythonLexer), Punctuation, None)), + String, using(PythonLexer), Punctuation)), # directives: if, for, prefer, test (r'(\$)(\w+)(\{(%)?)(.*?)((?(4)%)\})', bygroups(Punctuation, Name.Builtin, Punctuation, None, - using(PythonLexer), Punctuation, None)), + using(PythonLexer), Punctuation)), # directive clauses (no {} expression) (r'(\$)(else|rof|fi)', bygroups(Punctuation, Name.Builtin)), # expressions (r'(\$\{(%)?)(.*?)((!)(.*?))?((?(2)%)\})', bygroups(Punctuation, None, using(PythonLexer), - Name.Builtin, None, None, Punctuation, None)), + Name.Builtin, None, None, Punctuation)), (r'#', Other), ], 'comment': [ @@ -1489,7 +1489,8 @@ class ColdfusionLexer(RegexLexer): (r"'.*?'", String.Single), (r'\d+', Number), (r'(if|else|len|var|case|default|break|switch)\b', Keyword), - (r'([A-Za-z_$][A-Za-z0-9_.]*)\s*(\()', bygroups(Name.Function, Punctuation)), + (r'([A-Za-z_$][A-Za-z0-9_.]*)(\s*)(\()', + bygroups(Name.Function, Text, Punctuation)), (r'[A-Za-z_$][A-Za-z0-9_.]*', Name.Variable), (r'[()\[\]{};:,.\\]', Punctuation), (r'\s+', Text), @@ -1581,3 +1582,49 @@ class SspLexer(DelegatingLexer): 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. + + *New in Pygments 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 <http://teatrove.org/>`_. + + *New in Pygments 1.5.* + """ + name = 'Tea' + aliases = ['tea'] + filenames = ['*.tea'] + mimetypes = ['text/x-tea'] + + def __init__(self, **options): + super(TeaTemplateLexer, self).__init__(XmlLexer, + TeaTemplateRootLexer, **options) + + def analyse_text(text): + rv = TeaLangLexer.analyse_text(text) - 0.01 + if looks_like_xml(text): + rv += 0.4 + if '<%' in text and '%>' in text: + rv += 0.1 + return rv diff --git a/pygments/lexers/text.py b/pygments/lexers/text.py index 9c1a9d95..0796312f 100644 --- a/pygments/lexers/text.py +++ b/pygments/lexers/text.py @@ -292,12 +292,12 @@ class DarcsPatchLexer(RegexLexer): 'insert': [ include('specialText'), (r'\[', Generic.Inserted), - (r'[^\n\[]*', Generic.Inserted), + (r'[^\n\[]+', Generic.Inserted), ], 'delete': [ include('specialText'), (r'\[', Generic.Deleted), - (r'[^\n\[]*', Generic.Deleted), + (r'[^\n\[]+', Generic.Deleted), ], } @@ -346,18 +346,18 @@ class IrcLogsLexer(RegexLexer): # /me msgs ("^" + timestamp + r""" (\s*[*]\s+) # Star - ([^\s]+\s+.*?\n) # Nick + rest of message """, + (\S+\s+.*?\n) # Nick + rest of message """, bygroups(Comment.Preproc, Keyword, Generic.Inserted)), # join/part msgs ("^" + timestamp + r""" (\s*(?:\*{3}|<?-[!@=P]?->?)\s*) # Star(s) or symbols - ([^\s]+\s+) # Nick + Space + (\S+\s+) # Nick + Space (.*?\n) # Rest of message """, bygroups(Comment.Preproc, Keyword, String, Comment)), (r"^.*?\n", Text), ], 'msg': [ - (r"[^\s]+:(?!//)", Name.Attribute), # Prefix + (r"\S+:(?!//)", Name.Attribute), # Prefix (r".*\n", Text, '#pop'), ], } @@ -468,7 +468,7 @@ class GroffLexer(RegexLexer): tokens = { 'root': [ - (r'(?i)(\.)(\w+)', bygroups(Text, Keyword), 'request'), + (r'(\.)(\w+)', bygroups(Text, Keyword), 'request'), (r'\.', Punctuation, 'request'), # Regular characters, slurp till we find a backslash or newline (r'[^\\\n]*', Text, 'textline'), @@ -482,7 +482,7 @@ class GroffLexer(RegexLexer): # groff has many ways to write escapes. (r'\\"[^\n]*', Comment), (r'\\[fn]\w', String.Escape), - (r'\\\(..', String.Escape), + (r'\\\(.{2}', String.Escape), (r'\\.\[.*\]', String.Escape), (r'\\.', String.Escape), (r'\\\n', Text, 'request'), @@ -768,7 +768,7 @@ class VimLexer(RegexLexer): name = 'VimL' aliases = ['vim'] filenames = ['*.vim', '.vimrc', '.exrc', '.gvimrc', - '_vimrc', '_exrc', '_gvimrc'] + '_vimrc', '_exrc', '_gvimrc', 'vimrc', 'gvimrc'] mimetypes = ['text/x-vim'] flags = re.MULTILINE @@ -1018,11 +1018,11 @@ class DebianControlLexer(RegexLexer): (r'^(Description)', Keyword, 'description'), (r'^(Maintainer)(:\s*)', bygroups(Keyword, Text), 'maintainer'), (r'^((Build-)?Depends)', Keyword, 'depends'), - (r'^((?:Python-)?Version)(:\s*)([^\s]+)$', + (r'^((?:Python-)?Version)(:\s*)(\S+)$', bygroups(Keyword, Text, Number)), - (r'^((?:Installed-)?Size)(:\s*)([^\s]+)$', + (r'^((?:Installed-)?Size)(:\s*)(\S+)$', bygroups(Keyword, Text, Number)), - (r'^(MD5Sum|SHA1|SHA256)(:\s*)([^\s]+)$', + (r'^(MD5Sum|SHA1|SHA256)(:\s*)(\S+)$', bygroups(Keyword, Text, Number)), (r'^([a-zA-Z\-0-9\.]*?)(:\s*)(.*?)$', bygroups(Keyword, Whitespace, String)), @@ -1034,7 +1034,7 @@ class DebianControlLexer(RegexLexer): (r'.', Text), ], 'description': [ - (r'(.*)(Homepage)(: )([^\s]+)', + (r'(.*)(Homepage)(: )(\S+)', bygroups(Text, String, Name, Name.Class)), (r':.*\n', Generic.Strong), (r' .*\n', Text), @@ -1048,9 +1048,9 @@ class DebianControlLexer(RegexLexer): (r'\|', Operator), (r'[\s]+', Text), (r'[}\)]\s*$', Text, '#pop'), - (r'[}]', Text), + (r'}', Text), (r'[^,]$', Name.Function, '#pop'), - (r'([\+\.a-zA-Z0-9-][\s\n]*)', Name.Function), + (r'([\+\.a-zA-Z0-9-])(\s*)', bygroups(Name.Function, Text)), (r'\[.*?\]', Name.Entity), ], 'depend_vers': [ @@ -1387,7 +1387,8 @@ class YamlLexer(ExtendedRegexLexer): # ignored and regular whitespaces in quoted scalars 'quoted-scalar-whitespaces': [ # leading and trailing whitespaces are ignored - (r'^[ ]+|[ ]+$', Text), + (r'^[ ]+', Text), + (r'[ ]+$', Text), # line breaks are ignored (r'\n+', Text), # other whitespaces are a part of the value @@ -1456,7 +1457,8 @@ class YamlLexer(ExtendedRegexLexer): # the scalar ends with a comment (r'[ ]+(?=#)', Text, '#pop'), # leading and trailing whitespaces are ignored - (r'^[ ]+|[ ]+$', Text), + (r'^[ ]+', Text), + (r'[ ]+$', Text), # line breaks are ignored (r'\n+', Text), # other whitespaces are a part of the value @@ -1702,7 +1704,7 @@ class PyPyLogLexer(RegexLexer): (r"^\+\d+: ", Comment), (r"[ifp]\d+", Name), (r"ptr\d+", Name), - (r"(\()([\w_]+(?:\.[\w_]+)?)(\))", + (r"(\()(\w+(?:\.\w+)?)(\))", bygroups(Punctuation, Name.Builtin, Punctuation)), (r"[\[\]=,()]", Punctuation), (r"(\d+\.\d+|inf|-inf)", Number.Float), @@ -1728,8 +1730,7 @@ class PyPyLogLexer(RegexLexer): r"arraylen_gc|" r"getarrayitem_gc_pure|getarrayitem_gc|setarrayitem_gc|" r"getarrayitem_raw|setarrayitem_raw|getfield_gc_pure|" - r"getfield_gc|getinteriorfield_gc|" - r"getinteriorfield_gc|setinteriorfield_gc|" + r"getfield_gc|getinteriorfield_gc|setinteriorfield_gc|" r"getfield_raw|setfield_gc|setfield_raw|" r"strgetitem|strsetitem|strlen|copystrcontent|" r"unicodegetitem|unicodesetitem|unicodelen|" @@ -1741,12 +1742,12 @@ class PyPyLogLexer(RegexLexer): ], "jit-backend-counts": [ (r"\[\w+\] jit-backend-counts}$", Keyword, "#pop"), - (r"[:]", Punctuation), + (r":", Punctuation), (r"\d+", Number), include("extra-stuff"), ], "extra-stuff": [ - (r"[\n\s]+", Text), + (r"\s+", Text), (r"#.*?$", Comment), ], } diff --git a/pygments/lexers/web.py b/pygments/lexers/web.py index 38f75619..f45abf57 100644 --- a/pygments/lexers/web.py +++ b/pygments/lexers/web.py @@ -56,7 +56,7 @@ class JavascriptLexer(RegexLexer): (r'', Text, '#pop') ], 'badregex': [ - ('\n', Text, '#pop') + (r'\n', Text, '#pop') ], 'root': [ (r'^(?=\s|/|<!--)', Text, 'slashstartsregex'), @@ -296,7 +296,7 @@ class ActionScript3Lexer(RegexLexer): (r'[0-9]+', Number.Integer), (r'"(\\\\|\\"|[^"])*"', String.Double), (r"'(\\\\|\\'|[^'])*'", String.Single), - (r'[~\^\*!%&<>\|+=:;,/?\\{}\[\]();.-]+', Operator), + (r'[~\^\*!%&<>\|+=:;,/?\\{}\[\]().-]+', Operator), ], 'funcparams': [ (r'\s+', Text), @@ -383,7 +383,7 @@ class CssLexer(RegexLexer): r'list-style|margin-bottom|margin-left|margin-right|' r'margin-top|margin|marker-offset|marks|max-height|max-width|' r'min-height|min-width|opacity|orphans|outline|outline-color|' - r'outline-style|outline-width|overflow(?:-x|-y|)|padding-bottom|' + r'outline-style|outline-width|overflow(?:-x|-y)?|padding-bottom|' r'padding-left|padding-right|padding-top|padding|page|' r'page-break-after|page-break-before|page-break-inside|' r'pause-after|pause-before|pause|pitch|pitch-range|' @@ -499,13 +499,13 @@ class ObjectiveJLexer(RegexLexer): (';', Punctuation), ], 'whitespace': [ - (r'(@import)(\s+)("(\\\\|\\"|[^"])*")', + (r'(@import)(\s+)("(?:\\\\|\\"|[^"])*")', bygroups(Comment.Preproc, Text, String.Double)), - (r'(@import)(\s+)(<(\\\\|\\>|[^>])*>)', + (r'(@import)(\s+)(<(?:\\\\|\\>|[^>])*>)', bygroups(Comment.Preproc, Text, String.Double)), - (r'(#(?:include|import))(\s+)("(\\\\|\\"|[^"])*")', + (r'(#(?:include|import))(\s+)("(?:\\\\|\\"|[^"])*")', bygroups(Comment.Preproc, Text, String.Double)), - (r'(#(?:include|import))(\s+)(<(\\\\|\\>|[^>])*>)', + (r'(#(?:include|import))(\s+)(<(?:\\\\|\\>|[^>])*>)', bygroups(Comment.Preproc, Text, String.Double)), (r'#if\s+0', Comment.Preproc, 'if0'), @@ -526,7 +526,7 @@ class ObjectiveJLexer(RegexLexer): (r'', Text, '#pop'), ], 'badregex': [ - ('\n', Text, '#pop'), + (r'\n', Text, '#pop'), ], 'statements': [ (r'(L|@)?"', String, 'string'), @@ -633,7 +633,7 @@ class ObjectiveJLexer(RegexLexer): # parameters (r'(\(' + _ws + ')' # open paren r'([^\)]+)' # type - r'(' + _ws + r'\)' + _ws + r')+' # close paren + r'(' + _ws + r'\)' + _ws + r')' # close paren r'([$a-zA-Z_][a-zA-Z0-9_]+)', # param name bygroups(using(this), Keyword.Type, using(this), Text)), @@ -645,7 +645,7 @@ class ObjectiveJLexer(RegexLexer): (r'(:)', Name.Function), # var args - (r'(,' + _ws + r'...)', using(this)), + (r'(,' + _ws + r'\.\.\.)', using(this)), # param name (r'([$a-zA-Z_][a-zA-Z0-9_]+)', Text), @@ -816,7 +816,7 @@ class PhpLexer(RegexLexer): r'array|__wakeup|E_ALL|NULL|final|php_user_filter|interface|' r'implements|public|private|protected|abstract|clone|try|' r'catch|throw|this|use|namespace)\b', Keyword), - ('(true|false|null)\b', Keyword.Constant), + (r'(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), (r'[\\a-zA-Z_][\\a-zA-Z0-9_]*', Name.Other), @@ -912,18 +912,18 @@ class DtdLexer(RegexLexer): 'root': [ include('common'), - (r'(<!ELEMENT)(\s+)([^\s]+)', + (r'(<!ELEMENT)(\s+)(\S+)', bygroups(Keyword, Text, Name.Tag), 'element'), - (r'(<!ATTLIST)(\s+)([^\s]+)', + (r'(<!ATTLIST)(\s+)(\S+)', bygroups(Keyword, Text, Name.Tag), 'attlist'), - (r'(<!ENTITY)(\s+)([^\s]+)', + (r'(<!ENTITY)(\s+)(\S+)', bygroups(Keyword, Text, Name.Entity), 'entity'), - (r'(<!NOTATION)(\s+)([^\s]+)', + (r'(<!NOTATION)(\s+)(\S+)', bygroups(Keyword, Text, Name.Tag), 'notation'), (r'(<!\[)([^\[\s]+)(\s*)(\[)', # conditional sections bygroups(Keyword, Name.Entity, Text, Keyword)), - (r'(<!DOCTYPE)(\s+)([^>\s]+)', + (r'(<!DOCTYPE)(\s+)([^>\s]+)', bygroups(Keyword, Text, Name.Tag)), (r'PUBLIC|SYSTEM', Keyword.Constant), (r'[\[\]>]', Keyword), @@ -937,7 +937,7 @@ class DtdLexer(RegexLexer): (r'"[^"]*"', String.Double), (r'\'[^\']*\'', String.Single), ], - + 'comment': [ ('[^-]+', Comment), ('-->', Comment, '#pop'), @@ -966,7 +966,7 @@ class DtdLexer(RegexLexer): (r'[^>\s\|()?+*,]+', Name.Entity), (r'>', Keyword, '#pop'), ], - + 'notation': [ include('common'), (r'SYSTEM|PUBLIC', Keyword.Constant), @@ -1169,7 +1169,7 @@ class HaxeLexer(RegexLexer): include('codekeywords'), (r'[();,\[\]]', Punctuation), (r'(?:=|\+=|-=|\*=|/=|%=|&=|\|=|\^=|<<=|>>=|>>>=|\|\||&&|' - r'\.\.\.|==|!=|>|<|>=|<=|\||&|\^|<<|>>|>>>|\+|\-|\*|/|%|' + r'\.\.\.|==|!=|>|<|>=|<=|\||&|\^|<<|>>>|>>|\+|\-|\*|/|%|' r'!|\+\+|\-\-|~|\.|\?|\:)', Operator), (ident, Name), @@ -1395,7 +1395,7 @@ class HamlLexer(ExtendedRegexLexer): 'eval-or-plain': [ (r'[&!]?==', Punctuation, 'plain'), - (r'([&!]?[=~])(' + _comma_dot + '*\n)', + (r'([&!]?[=~])(' + _comma_dot + r'*\n)', bygroups(Punctuation, using(RubyLexer)), 'root'), (r'', Text, 'plain'), @@ -1404,18 +1404,18 @@ class HamlLexer(ExtendedRegexLexer): 'content': [ include('css'), (r'%[a-z0-9_:-]+', Name.Tag, 'tag'), - (r'!!!' + _dot + '*\n', Name.Namespace, '#pop'), - (r'(/)(\[' + _dot + '*?\])(' + _dot + '*\n)', + (r'!!!' + _dot + r'*\n', Name.Namespace, '#pop'), + (r'(/)(\[' + _dot + '*?\])(' + _dot + r'*\n)', bygroups(Comment, Comment.Special, Comment), '#pop'), - (r'/' + _dot + '*\n', _starts_block(Comment, 'html-comment-block'), + (r'/' + _dot + r'*\n', _starts_block(Comment, 'html-comment-block'), '#pop'), - (r'-#' + _dot + '*\n', _starts_block(Comment.Preproc, + (r'-#' + _dot + r'*\n', _starts_block(Comment.Preproc, 'haml-comment-block'), '#pop'), - (r'(-)(' + _comma_dot + '*\n)', + (r'(-)(' + _comma_dot + r'*\n)', bygroups(Punctuation, using(RubyLexer)), '#pop'), - (r':' + _dot + '*\n', _starts_block(Name.Decorator, 'filter-block'), + (r':' + _dot + r'*\n', _starts_block(Name.Decorator, 'filter-block'), '#pop'), include('eval-or-plain'), ], @@ -1690,7 +1690,7 @@ class SassLexer(ExtendedRegexLexer): 'import': [ (r'[ \t]+', Text), - (r'[^\s]+', String), + (r'\S+', String), (r'\n', Text, 'root'), ], @@ -1932,7 +1932,7 @@ class ScamlLexer(ExtendedRegexLexer): 'eval-or-plain': [ (r'[&!]?==', Punctuation, 'plain'), - (r'([&!]?[=~])(' + _dot + '*\n)', + (r'([&!]?[=~])(' + _dot + r'*\n)', bygroups(Punctuation, using(ScalaLexer)), 'root'), (r'', Text, 'plain'), @@ -1941,21 +1941,21 @@ class ScamlLexer(ExtendedRegexLexer): 'content': [ include('css'), (r'%[a-z0-9_:-]+', Name.Tag, 'tag'), - (r'!!!' + _dot + '*\n', Name.Namespace, '#pop'), - (r'(/)(\[' + _dot + '*?\])(' + _dot + '*\n)', + (r'!!!' + _dot + r'*\n', Name.Namespace, '#pop'), + (r'(/)(\[' + _dot + '*?\])(' + _dot + r'*\n)', bygroups(Comment, Comment.Special, Comment), '#pop'), - (r'/' + _dot + '*\n', _starts_block(Comment, 'html-comment-block'), + (r'/' + _dot + r'*\n', _starts_block(Comment, 'html-comment-block'), '#pop'), - (r'-#' + _dot + '*\n', _starts_block(Comment.Preproc, + (r'-#' + _dot + r'*\n', _starts_block(Comment.Preproc, 'scaml-comment-block'), '#pop'), - (r'(-@\s*)(import)?(' + _dot + '*\n)', + (r'(-@\s*)(import)?(' + _dot + r'*\n)', bygroups(Punctuation, Keyword, using(ScalaLexer)), '#pop'), - (r'(-)(' + _dot + '*\n)', + (r'(-)(' + _dot + r'*\n)', bygroups(Punctuation, using(ScalaLexer)), '#pop'), - (r':' + _dot + '*\n', _starts_block(Name.Decorator, 'filter-block'), + (r':' + _dot + r'*\n', _starts_block(Name.Decorator, 'filter-block'), '#pop'), include('eval-or-plain'), ], @@ -2042,31 +2042,31 @@ class JadeLexer(ExtendedRegexLexer): 'eval-or-plain': [ (r'[&!]?==', Punctuation, 'plain'), - (r'([&!]?[=~])(' + _dot + '*\n)', + (r'([&!]?[=~])(' + _dot + r'*\n)', bygroups(Punctuation, using(ScalaLexer)), 'root'), (r'', Text, 'plain'), ], 'content': [ include('css'), - (r'!!!' + _dot + '*\n', Name.Namespace, '#pop'), - (r'(/)(\[' + _dot + '*?\])(' + _dot + '*\n)', + (r'!!!' + _dot + r'*\n', Name.Namespace, '#pop'), + (r'(/)(\[' + _dot + '*?\])(' + _dot + r'*\n)', bygroups(Comment, Comment.Special, Comment), '#pop'), - (r'/' + _dot + '*\n', _starts_block(Comment, 'html-comment-block'), + (r'/' + _dot + r'*\n', _starts_block(Comment, 'html-comment-block'), '#pop'), - (r'-#' + _dot + '*\n', _starts_block(Comment.Preproc, + (r'-#' + _dot + r'*\n', _starts_block(Comment.Preproc, 'scaml-comment-block'), '#pop'), - (r'(-@\s*)(import)?(' + _dot + '*\n)', + (r'(-@\s*)(import)?(' + _dot + r'*\n)', bygroups(Punctuation, Keyword, using(ScalaLexer)), '#pop'), - (r'(-)(' + _dot + '*\n)', + (r'(-)(' + _dot + r'*\n)', bygroups(Punctuation, using(ScalaLexer)), '#pop'), - (r':' + _dot + '*\n', _starts_block(Name.Decorator, 'filter-block'), + (r':' + _dot + r'*\n', _starts_block(Name.Decorator, 'filter-block'), '#pop'), (r'[a-z0-9_:-]+', Name.Tag, 'tag'), - (r'|', Text, 'eval-or-plain'), + (r'\|', Text, 'eval-or-plain'), ], 'tag': [ @@ -2142,24 +2142,24 @@ class XQueryLexer(ExtendedRegexLexer): # ur"[\u2C00-\u2FEF]|[\u3001-\uD7FF]|[\uF900-\uFDCF]|[\uFDF0-\uFFFD]|" # ur"[\u10000-\uEFFFF]" #) - ncnamestartchar = r"[A-Z]|_|[a-z]" + ncnamestartchar = r"(?:[A-Z]|_|[a-z])" # FIX UNICODE LATER #ncnamechar = ncnamestartchar + (ur"|-|\.|[0-9]|\u00B7|[\u0300-\u036F]|" # ur"[\u203F-\u2040]") - ncnamechar = ncnamestartchar + r"|-|\.|[0-9]" - ncname = "((%s)+(%s)*)" % (ncnamestartchar, ncnamechar) - pitarget_namestartchar = r"[A-KN-WY-Z]|_|:|[a-kn-wy-z]" - pitarget_namechar = pitarget_namestartchar + r"|-|\.|[0-9]" - pitarget = "(%s)+(%s)*" % (pitarget_namestartchar, pitarget_namechar) + ncnamechar = r"(?:" + ncnamestartchar + r"|-|\.|[0-9])" + ncname = "(?:%s+%s*)" % (ncnamestartchar, ncnamechar) + pitarget_namestartchar = r"(?:[A-KN-WY-Z]|_|:|[a-kn-wy-z])" + pitarget_namechar = r"(?:" + pitarget_namestartchar + r"|-|\.|[0-9])" + pitarget = "%s+%s*" % (pitarget_namestartchar, pitarget_namechar) prefixedname = "%s:%s" % (ncname, ncname) unprefixedname = ncname - qname = "((%s)|(%s))" %(prefixedname, unprefixedname) + qname = "(?:%s|%s)" % (prefixedname, unprefixedname) - entityref = r'&(lt|gt|amp|quot|apos|nbsp);' - charref = r'&#[0-9]+;|&#x[0-9a-fA-F]+;' + entityref = r'(?:&(?:lt|gt|amp|quot|apos|nbsp);)' + charref = r'(?:&#[0-9]+;|&#x[0-9a-fA-F]+;)' - stringdouble = r'("((' + entityref + r')|(' + charref + r')|("")|([^&"]))*")' - stringsingle = r"('((" + entityref + r")|(" + charref + r")|('')|([^&']))*')" + stringdouble = r'(?:"(?:' + entityref + r'|' + charref + r'|""|[^&"])*")' + stringsingle = r"(?:'(?:" + entityref + r"|" + charref + r"|''|[^&'])*')" # FIX UNICODE LATER #elementcontentchar = (ur'\t|\r|\n|[\u0020-\u0025]|[\u0028-\u003b]|' @@ -2407,11 +2407,13 @@ class XQueryLexer(ExtendedRegexLexer): operator_root_callback), (r'(::|;|\[|//|/|,)', punctuation_root_callback), - (r'(castable|cast)(\s+)(as)', + (r'(castable|cast)(\s+)(as)\b', bygroups(Keyword, Text, Keyword), 'singletype'), - (r'(instance)(\s+)(of)', bygroups(Keyword, Text, Keyword), 'itemtype'), - (r'(treat)(\s+)(as)', bygroups(Keyword, Text, Keyword), 'itemtype'), - (r'case|as', Keyword, 'itemtype'), + (r'(instance)(\s+)(of)\b', + bygroups(Keyword, Text, Keyword), 'itemtype'), + (r'(treat)(\s+)(as)\b', + bygroups(Keyword, Text, Keyword), 'itemtype'), + (r'(case|as)\b', Keyword, 'itemtype'), (r'(\))(\s*)(as)', bygroups(Punctuation, Text, Keyword), 'itemtype'), (r'\$', Name.Variable, 'varname'), @@ -2436,8 +2438,8 @@ class XQueryLexer(ExtendedRegexLexer): 'namespacedecl': [ include('whitespace'), (r'\(:', Comment, 'comment'), - (r'(at)(\s+)'+stringdouble, bygroups(Keyword, Text, String.Double)), - (r"(at)(\s+)"+stringsingle, bygroups(Keyword, Text, String.Single)), + (r'(at)(\s+)('+stringdouble+')', bygroups(Keyword, Text, String.Double)), + (r"(at)(\s+)("+stringsingle+')', bygroups(Keyword, Text, String.Single)), (stringdouble, String.Double), (stringsingle, String.Single), (r',', Punctuation), @@ -2484,9 +2486,9 @@ class XQueryLexer(ExtendedRegexLexer): (r'\(\#', Punctuation, 'pragma'), (r';', Punctuation, '#pop'), (r'then|else', Keyword, '#pop'), - (r'(at)(\s+)' + stringdouble, + (r'(at)(\s+)(' + stringdouble + ')', bygroups(Keyword, Text, String.Double), 'namespacedecl'), - (r'(at)(\s+)' + stringsingle, + (r'(at)(\s+)(' + stringsingle + ')', bygroups(Keyword, Text, String.Single), 'namespacedecl'), (r'except|intersect|in|is|return|satisfies|to|union|where', Keyword, 'root'), @@ -2501,12 +2503,12 @@ class XQueryLexer(ExtendedRegexLexer): (r'(instance)(\s+)(of)', bygroups(Keyword, Text, Keyword)), (r'case|as', Keyword, 'itemtype'), (r'(\))(\s*)(as)', bygroups(Operator, Text, Keyword), 'itemtype'), - (ncname + r'(:\*)', Keyword.Type, 'operator'), + (ncname + r':\*', Keyword.Type, 'operator'), (qname, Keyword.Type, 'occurrenceindicator'), ], 'kindtest': [ (r'\(:', Comment, 'comment'), - (r'({)', Punctuation, 'root'), + (r'{', Punctuation, 'root'), (r'(\))([*+?]?)', popstate_kindtest_callback), (r'\*', Name, 'closekindtest'), (qname, Name, 'closekindtest'), @@ -2515,7 +2517,7 @@ class XQueryLexer(ExtendedRegexLexer): 'kindtestforpi': [ (r'\(:', Comment, 'comment'), (r'\)', Punctuation, '#pop'), - (ncname, bygroups(Name.Variable, Name.Variable)), + (ncname, Name.Variable), (stringdouble, String.Double), (stringsingle, String.Single), ], @@ -2529,8 +2531,8 @@ class XQueryLexer(ExtendedRegexLexer): 'xml_comment': [ (r'(-->)', popstate_xmlcomment_callback), (r'[^-]{1,2}', Literal), - (r'\u009|\u00A|\u00D|[\u0020-\u00D7FF]|[\u00E000-\u00FFFD]|' - r'[\u0010000-\u0010FFFF]', Literal), + (ur'\t|\r|\n|[\u0020-\U0000D7FF]|[\U0000E000-\U0000FFFD]|' + ur'[\U00010000-\U0010FFFF]', Literal), ], 'processing_instruction': [ (r'\s+', Text, 'processing_instruction_content'), @@ -2539,13 +2541,13 @@ class XQueryLexer(ExtendedRegexLexer): ], 'processing_instruction_content': [ (r'\?>', String.Doc, '#pop'), - (r'\u009|\u00A|\u00D|[\u0020-\uD7FF]|[\uE000-\uFFFD]|' - r'[\u10000-\u10FFFF]', Literal), + (ur'\t|\r|\n|[\u0020-\uD7FF]|[\uE000-\uFFFD]|' + ur'[\U00010000-\U0010FFFF]', Literal), ], 'cdata_section': [ (r']]>', String.Doc, '#pop'), - (r'\u009|\u00A|\u00D|[\u0020-\uD7FF]|[\uE000-\uFFFD]|' - r'[\u10000-\u10FFFF]', Literal), + (ur'\t|\r|\n|[\u0020-\uD7FF]|[\uE000-\uFFFD]|' + ur'[\U00010000-\U0010FFFF]', Literal), ], 'start_tag': [ include('whitespace'), @@ -2613,9 +2615,9 @@ class XQueryLexer(ExtendedRegexLexer): ], 'pragmacontents': [ (r'#\)', Punctuation, 'operator'), - (r'\u009|\u00A|\u00D|[\u0020-\u00D7FF]|[\u00E000-\u00FFFD]|' - r'[\u0010000-\u0010FFFF]', Literal), - (r'(\s*)', Text), + (ur'\t|\r|\n|[\u0020-\U0000D7FF]|[\U0000E000-\U0000FFFD]|' + ur'[\U00010000-\U0010FFFF]', Literal), + (r'(\s+)', Text), ], 'occurrenceindicator': [ include('whitespace'), @@ -2721,8 +2723,9 @@ class XQueryLexer(ExtendedRegexLexer): (r'(element)(\s+)(?=' +qname+ r')', bygroups(Keyword, Text), 'element_qname'), #PROCESSING_INSTRUCTION - (r'(processing-instruction)(\s+)' + ncname + r'(\s*)(\{)', - bygroups(Keyword, Text, Name.Variable, Text, Punctuation), 'operator'), + (r'(processing-instruction)(\s+)(' + ncname + r')(\s*)(\{)', + bygroups(Keyword, Text, Name.Variable, Text, Punctuation), + 'operator'), (r'(declare|define)(\s+)(function)', bygroups(Keyword, Text, Keyword)), @@ -2771,8 +2774,8 @@ class XQueryLexer(ExtendedRegexLexer): (r'//|/|\+|-|;|,|\(|\)', Punctuation), # STANDALONE QNAMES - (qname + r'(?=\s*[{])', Name.Variable, 'qname_braren'), - (qname + r'(?=\s*[(])', Name.Function, 'qname_braren'), + (qname + r'(?=\s*{)', Name.Variable, 'qname_braren'), + (qname + r'(?=\s*\()', Name.Function, 'qname_braren'), (qname, Name.Variable, 'operator'), ] } @@ -60,7 +60,7 @@ else: setup( name = 'Pygments', - version = '1.4', + version = '1.5', url = 'http://pygments.org/', license = 'BSD License', author = 'Georg Brandl', diff --git a/tests/examplefiles/antlr_throws b/tests/examplefiles/antlr_throws new file mode 100644 index 00000000..816d8914 --- /dev/null +++ b/tests/examplefiles/antlr_throws @@ -0,0 +1 @@ +public f throws a, b, c : x ; diff --git a/tests/examplefiles/example.kt b/tests/examplefiles/example.kt new file mode 100644 index 00000000..59291333 --- /dev/null +++ b/tests/examplefiles/example.kt @@ -0,0 +1,47 @@ +package addressbook + +class Contact( + val name : String, + val emails : List<EmailAddress>, + val addresses : List<PostalAddress>, + val phonenums : List<PhoneNumber> +) + +class EmailAddress( + val user : String, + val host : String +) + +class PostalAddress( + val streetAddress : String, + val city : String, + val zip : String, + val state : USState?, + val country : Country +) { + assert {(state == null) xor (country == Countries["US"]) } +} + +class PhoneNumber( + val country : Country, + val areaCode : Int, + val number : Long +) + +object Countries { + fun get(id : CountryID) : Country = countryTable[id] + + private var table : Map<String, Country>? = null + private val countryTable : Map<String, Country> + get() { + if (table == null) { + table = HashMap() + for (line in TextFile("countries.txt").lines(stripWhiteSpace = true)) { + table[line] = Country(line) + } + } + return table + } +} + +class Country(val name : String)
\ No newline at end of file diff --git a/tests/examplefiles/example.sh-session b/tests/examplefiles/example.sh-session index 35b81ebb..02f3bb0d 100644 --- a/tests/examplefiles/example.sh-session +++ b/tests/examplefiles/example.sh-session @@ -15,3 +15,5 @@ user@host:~/path$ su root@host:~# sh-3.1$ # on hardy sh$ # on etch +(virtualenv-name)user@host:~$ ls -a + diff --git a/tests/examplefiles/example.tea b/tests/examplefiles/example.tea new file mode 100644 index 00000000..6859e34d --- /dev/null +++ b/tests/examplefiles/example.tea @@ -0,0 +1,34 @@ +<% template example() {...} +a = 123 +b = "test"; +c = 4.5 +d = call other() +f = other2() + +define g as String + +h = true +i = false +j = null +%> +<html> +<head> +<title>Example<title> +<body> +<a href="http://example.com">Test link</a> +<% // Second block +if(a == 123 and b == "test") { + 'yes' +} else { + 'no' +} + +foreach(i in 1..10) { + i & "," +} + +foreach(i in #(1,2,3) reverse { + i & ";" +} + +%>
\ No newline at end of file diff --git a/tests/examplefiles/function.mu b/tests/examplefiles/function.mu new file mode 100644 index 00000000..46bb259d --- /dev/null +++ b/tests/examplefiles/function.mu @@ -0,0 +1 @@ +a::b () |