diff options
Diffstat (limited to 'pygments/lexers/web.py')
| -rw-r--r-- | pygments/lexers/web.py | 2536 |
1 files changed, 2187 insertions, 349 deletions
diff --git a/pygments/lexers/web.py b/pygments/lexers/web.py index 11bc2175..180c8e8a 100644 --- a/pygments/lexers/web.py +++ b/pygments/lexers/web.py @@ -5,7 +5,7 @@ Lexers for web-related languages and markup. - :copyright: Copyright 2006-2010 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2014 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ @@ -13,20 +13,22 @@ import re import copy from pygments.lexer import RegexLexer, ExtendedRegexLexer, bygroups, using, \ - include, this + include, this from pygments.token import Text, Comment, Operator, Keyword, Name, String, \ - Number, Other, Punctuation, Literal + Number, Other, Punctuation, Literal from pygments.util import get_bool_opt, get_list_opt, looks_like_xml, \ - html_doctype_matches + html_doctype_matches, unirange, iteritems from pygments.lexers.agile import RubyLexer from pygments.lexers.compiled import ScalaLexer -__all__ = ['HtmlLexer', 'XmlLexer', 'JavascriptLexer', 'CssLexer', +__all__ = ['HtmlLexer', 'XmlLexer', 'JavascriptLexer', 'JsonLexer', 'CssLexer', 'PhpLexer', 'ActionScriptLexer', 'XsltLexer', 'ActionScript3Lexer', 'MxmlLexer', 'HaxeLexer', 'HamlLexer', 'SassLexer', 'ScssLexer', - 'ObjectiveJLexer', 'CoffeeScriptLexer', 'DuelLexer', 'ScamlLexer', - 'JadeLexer', 'XQueryLexer'] + 'ObjectiveJLexer', 'CoffeeScriptLexer', 'LiveScriptLexer', + 'DuelLexer', 'ScamlLexer', 'JadeLexer', 'XQueryLexer', + 'DtdLexer', 'DartLexer', 'LassoLexer', 'QmlLexer', 'TypeScriptLexer', + 'KalLexer', 'CirruLexer', 'MaskLexer', 'ZephirLexer'] class JavascriptLexer(RegexLexer): @@ -36,9 +38,9 @@ class JavascriptLexer(RegexLexer): name = 'JavaScript' aliases = ['js', 'javascript'] - filenames = ['*.js'] + filenames = ['*.js', ] mimetypes = ['application/javascript', 'application/x-javascript', - 'text/x-javascript', 'text/javascript'] + 'text/x-javascript', 'text/javascript', ] flags = re.DOTALL tokens = { @@ -56,7 +58,7 @@ class JavascriptLexer(RegexLexer): (r'', Text, '#pop') ], 'badregex': [ - ('\n', Text, '#pop') + (r'\n', Text, '#pop') ], 'root': [ (r'^(?=\s|/|<!--)', Text, 'slashstartsregex'), @@ -66,9 +68,9 @@ class JavascriptLexer(RegexLexer): (r'[{(\[;,]', Punctuation, 'slashstartsregex'), (r'[})\].]', Punctuation), (r'(for|in|while|do|break|return|continue|switch|case|default|if|else|' - r'throw|try|catch|finally|new|delete|typeof|instanceof|void|' + r'throw|try|catch|finally|new|delete|typeof|instanceof|void|yield|' r'this)\b', Keyword, 'slashstartsregex'), - (r'(var|with|function)\b', Keyword.Declaration, 'slashstartsregex'), + (r'(var|let|with|function)\b', Keyword.Declaration, 'slashstartsregex'), (r'(abstract|boolean|byte|char|class|const|debugger|double|enum|export|' r'extends|final|float|goto|implements|import|int|interface|long|native|' r'package|private|protected|public|short|static|super|synchronized|throws|' @@ -89,18 +91,101 @@ class JavascriptLexer(RegexLexer): } +class JsonLexer(RegexLexer): + """ + For JSON data structures. + + .. versionadded:: 1.5 + """ + + name = 'JSON' + aliases = ['json'] + filenames = ['*.json'] + mimetypes = [ 'application/json', ] + + # integer part of a number + int_part = r'-?(0|[1-9]\d*)' + + # fractional part of a number + frac_part = r'\.\d+' + + # exponential part of a number + exp_part = r'[eE](\+|-)?\d+' + + + flags = re.DOTALL + tokens = { + 'whitespace': [ + (r'\s+', Text), + ], + + # represents a simple terminal value + 'simplevalue': [ + (r'(true|false|null)\b', Keyword.Constant), + (('%(int_part)s(%(frac_part)s%(exp_part)s|' + '%(exp_part)s|%(frac_part)s)') % vars(), + Number.Float), + (int_part, Number.Integer), + (r'"(\\\\|\\"|[^"])*"', String.Double), + ], + + + # the right hand side of an object, after the attribute name + 'objectattribute': [ + include('value'), + (r':', Punctuation), + # comma terminates the attribute but expects more + (r',', Punctuation, '#pop'), + # a closing bracket terminates the entire object, so pop twice + (r'}', Punctuation, ('#pop', '#pop')), + ], + + # a json object - { attr, attr, ... } + 'objectvalue': [ + include('whitespace'), + (r'"(\\\\|\\"|[^"])*"', Name.Tag, 'objectattribute'), + (r'}', Punctuation, '#pop'), + ], + + # json array - [ value, value, ... } + 'arrayvalue': [ + include('whitespace'), + include('value'), + (r',', Punctuation), + (r']', Punctuation, '#pop'), + ], + + # a json value - either a simple value or a complex value (object or array) + 'value': [ + include('whitespace'), + include('simplevalue'), + (r'{', Punctuation, 'objectvalue'), + (r'\[', Punctuation, 'arrayvalue'), + ], + + + # the root of a json document whould be a value + 'root': [ + include('value'), + ], + + } + +JSONLexer = JsonLexer # for backwards compatibility with Pygments 1.5 + + class ActionScriptLexer(RegexLexer): """ For ActionScript source code. - *New in Pygments 0.9.* + .. versionadded:: 0.9 """ name = 'ActionScript' aliases = ['as', 'actionscript'] filenames = ['*.as'] - mimetypes = ['application/x-actionscript', 'text/x-actionscript', - 'text/actionscript'] + mimetypes = ['application/x-actionscript3', 'text/x-actionscript3', + 'text/actionscript3'] flags = re.DOTALL tokens = { @@ -172,15 +257,12 @@ class ActionScriptLexer(RegexLexer): ] } - def analyse_text(text): - return 0.05 - class ActionScript3Lexer(RegexLexer): """ For ActionScript 3 source code. - *New in Pygments 0.11.* + .. versionadded:: 0.11 """ name = 'ActionScript 3' @@ -190,6 +272,7 @@ class ActionScript3Lexer(RegexLexer): 'text/actionscript'] identifier = r'[$a-zA-Z_][a-zA-Z0-9_]*' + typeidentifier = identifier + '(?:\.<\w+>)?' flags = re.DOTALL | re.MULTILINE tokens = { @@ -198,12 +281,13 @@ class ActionScript3Lexer(RegexLexer): (r'(function\s+)(' + identifier + r')(\s*)(\()', bygroups(Keyword.Declaration, Name.Function, Text, Operator), 'funcparams'), - (r'(var|const)(\s+)(' + identifier + r')(\s*)(:)(\s*)(' + identifier + r')', + (r'(var|const)(\s+)(' + identifier + r')(\s*)(:)(\s*)(' + + typeidentifier + r')', bygroups(Keyword.Declaration, Text, Name, Text, Punctuation, Text, Keyword.Type)), (r'(import|package)(\s+)((?:' + identifier + r'|\.)+)(\s*)', bygroups(Keyword, Text, Name.Namespace, Text)), - (r'(new)(\s+)(' + identifier + r')(\s*)(\()', + (r'(new)(\s+)(' + typeidentifier + r')(\s*)(\()', bygroups(Keyword, Text, Keyword.Type, Text, Operator)), (r'//.*?\n', Comment.Single), (r'/\*.*?\*/', Comment.Multiline), @@ -229,18 +313,18 @@ class ActionScript3Lexer(RegexLexer): (r'[0-9]+', Number.Integer), (r'"(\\\\|\\"|[^"])*"', String.Double), (r"'(\\\\|\\'|[^'])*'", String.Single), - (r'[~\^\*!%&<>\|+=:;,/?\\{}\[\]();.-]+', Operator), + (r'[~\^\*!%&<>\|+=:;,/?\\{}\[\]().-]+', Operator), ], 'funcparams': [ (r'\s+', Text), (r'(\s*)(\.\.\.)?(' + identifier + r')(\s*)(:)(\s*)(' + - identifier + r'|\*)(\s*)', + typeidentifier + r'|\*)(\s*)', bygroups(Text, Punctuation, Name, Text, Operator, Text, Keyword.Type, Text), 'defval'), (r'\)', Operator, 'type') ], 'type': [ - (r'(\s*)(:)(\s*)(' + identifier + r'|\*)', + (r'(\s*)(:)(\s*)(' + typeidentifier + r'|\*)', bygroups(Text, Operator, Text, Keyword.Type), '#pop:2'), (r'\s*', Text, '#pop:2') ], @@ -252,8 +336,9 @@ class ActionScript3Lexer(RegexLexer): } def analyse_text(text): - if re.match(r'\w+\s*:\s*\w', text): return 0.3 - return 0.1 + if re.match(r'\w+\s*:\s*\w', text): + return 0.3 + return 0 class CssLexer(RegexLexer): @@ -279,7 +364,7 @@ class CssLexer(RegexLexer): (r'\#[a-zA-Z0-9_-]+', Name.Function), (r'@[a-zA-Z0-9_-]+', Keyword, 'atrule'), (r'[a-zA-Z0-9_-]+', Name.Tag), - (r'[~\^\*!%&\[\]\(\)<>\|+=@:;,./?-]', Operator), + (r'[~\^\*!%&$\[\]\(\)<>\|+=@:;,./?-]', Operator), (r'"(\\\\|\\"|[^"])*"', String.Double), (r"'(\\\\|\\'|[^'])*'", String.Single) ], @@ -314,19 +399,19 @@ class CssLexer(RegexLexer): r'list-style-type|list-style-image|list-style-position|' 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'min-height|min-width|opacity|orphans|outline-color|' + r'outline-style|outline-width|outline|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|' + r'pause-after|pause-before|pause|pitch-range|pitch|' r'play-during|position|quotes|richness|right|size|' r'speak-header|speak-numeral|speak-punctuation|speak|' r'speech-rate|stress|table-layout|text-align|text-decoration|' r'text-indent|text-shadow|text-transform|top|unicode-bidi|' r'vertical-align|visibility|voice-family|volume|white-space|' - r'widows|width|word-spacing|z-index|bottom|left|' + r'widows|width|word-spacing|z-index|bottom|' r'above|absolute|always|armenian|aural|auto|avoid|baseline|' - r'behind|below|bidi-override|blink|block|bold|bolder|both|' + r'behind|below|bidi-override|blink|block|bolder|bold|both|' r'capitalize|center-left|center-right|center|circle|' r'cjk-ideographic|close-quote|collapse|condensed|continuous|' r'crop|crosshair|cross|cursive|dashed|decimal-leading-zero|' @@ -336,7 +421,7 @@ class CssLexer(RegexLexer): r'hidden|hide|higher|high|hiragana-iroha|hiragana|icon|' r'inherit|inline-table|inline|inset|inside|invert|italic|' r'justify|katakana-iroha|katakana|landscape|larger|large|' - r'left-side|leftwards|level|lighter|line-through|list-item|' + r'left-side|leftwards|left|level|lighter|line-through|list-item|' r'loud|lower-alpha|lower-greek|lower-roman|lowercase|ltr|' r'lower|low|medium|message-box|middle|mix|monospace|' r'n-resize|narrower|ne-resize|no-close-quote|no-open-quote|' @@ -345,11 +430,11 @@ class CssLexer(RegexLexer): r'relative|repeat-x|repeat-y|repeat|rgb|ridge|right-side|' r'rightwards|s-resize|sans-serif|scroll|se-resize|' r'semi-condensed|semi-expanded|separate|serif|show|silent|' - r'slow|slower|small-caps|small-caption|smaller|soft|solid|' + r'slower|slow|small-caps|small-caption|smaller|soft|solid|' r'spell-out|square|static|status-bar|super|sw-resize|' r'table-caption|table-cell|table-column|table-column-group|' r'table-footer-group|table-header-group|table-row|' - r'table-row-group|text|text-bottom|text-top|thick|thin|' + r'table-row-group|text-bottom|text-top|text|thick|thin|' r'transparent|ultra-condensed|ultra-expanded|underline|' r'upper-alpha|upper-latin|upper-roman|uppercase|url|' r'visible|w-resize|wait|wider|x-fast|x-high|x-large|x-loud|' @@ -382,13 +467,15 @@ class CssLexer(RegexLexer): (r'\!important', Comment.Preproc), (r'/\*(?:.|\n)*?\*/', Comment), (r'\#[a-zA-Z0-9]{1,6}', Number), - (r'[\.-]?[0-9]*[\.]?[0-9]+(em|px|\%|pt|pc|in|mm|cm|ex|s)\b', Number), + (r'[\.-]?[0-9]*[\.]?[0-9]+(em|px|pt|pc|in|mm|cm|ex|s)\b', Number), + # Separate regex for percentages, as can't do word boundaries with % + (r'[\.-]?[0-9]*[\.]?[0-9]+%', Number), (r'-?[0-9]+', Number), (r'[~\^\*!%&<>\|+=@:,./?-]+', Operator), (r'[\[\]();]+', Punctuation), (r'"(\\\\|\\"|[^"])*"', String.Double), (r"'(\\\\|\\'|[^'])*'", String.Single), - (r'[a-zA-Z][a-zA-Z0-9]+', Name) + (r'[a-zA-Z_][a-zA-Z0-9_]*', Name) ] } @@ -397,7 +484,7 @@ class ObjectiveJLexer(RegexLexer): """ For Objective-J source code with preprocessor directives. - *New in Pygments 1.3.* + .. versionadded:: 1.3 """ name = 'Objective-J' @@ -431,13 +518,13 @@ 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'), @@ -458,7 +545,7 @@ class ObjectiveJLexer(RegexLexer): (r'', Text, '#pop'), ], 'badregex': [ - ('\n', Text, '#pop'), + (r'\n', Text, '#pop'), ], 'statements': [ (r'(L|@)?"', String, 'string'), @@ -565,7 +652,7 @@ 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'([$a-zA-Z_][a-zA-Z0-9_]+)', # param name bygroups(using(this), Keyword.Type, using(this), Text)), @@ -577,7 +664,7 @@ class ObjectiveJLexer(RegexLexer): (r'(:)', Name.Function), # var args - (r'(,' + _ws + r'...)', using(this)), + (r'(,' + _ws + r'\.\.\.)', using(this)), # param name (r'([$a-zA-Z_][a-zA-Z0-9_]+)', Text), @@ -638,8 +725,10 @@ class HtmlLexer(RegexLexer): ('<![^>]*>', Comment.Preproc), (r'<\s*script\s*', Name.Tag, ('script-content', 'tag')), (r'<\s*style\s*', Name.Tag, ('style-content', 'tag')), - (r'<\s*[a-zA-Z0-9:]+', Name.Tag, 'tag'), - (r'<\s*/\s*[a-zA-Z0-9:]+\s*>', Name.Tag), + # note: this allows tag names not used in HTML like <x:with-dash>, + # this is to support yet-unknown template engines and the like + (r'<\s*[\w:.-]+', Name.Tag, 'tag'), + (r'<\s*/\s*[\w:.-]+\s*>', Name.Tag), ], 'comment': [ ('[^-]+', Comment), @@ -707,9 +796,16 @@ class PhpLexer(RegexLexer): name = 'PHP' aliases = ['php', 'php3', 'php4', 'php5'] - filenames = ['*.php', '*.php[345]'] + filenames = ['*.php', '*.php[345]', '*.inc'] mimetypes = ['text/x-php'] + # Note that a backslash is included in the following two patterns + # PHP uses a backslash as a namespace separator + _ident_char = r'[\\_a-zA-Z0-9]|[^\x00-\x7f]' + _ident_begin = r'(?:[\\_a-zA-Z]|[^\x00-\x7f])' + _ident_end = r'(?:' + _ident_char + ')*' + _ident_inner = _ident_begin + _ident_end + flags = re.IGNORECASE | re.DOTALL | re.MULTILINE tokens = { 'root': [ @@ -719,7 +815,7 @@ class PhpLexer(RegexLexer): ], 'php': [ (r'\?>', Comment.Preproc, '#pop'), - (r'<<<(\'?)([a-zA-Z_][a-zA-Z0-9_]*)\1\n.*?\n\2\;?\n', String), + (r'<<<(\'?)(' + _ident_inner + ')\1\n.*?\n\2\;?\n', String), (r'\s+', Text), (r'#.*?\n', Comment.Single), (r'//.*?\n', Comment.Single), @@ -728,7 +824,7 @@ class PhpLexer(RegexLexer): (r'/\*\*/', Comment.Multiline), (r'/\*\*.*?\*/', String.Doc), (r'/\*.*?\*/', Comment.Multiline), - (r'(->|::)(\s*)([a-zA-Z_][a-zA-Z0-9_]*)', + (r'(->|::)(\s*)(' + _ident_inner + ')', bygroups(Operator, Text, Name.Attribute)), (r'[~!%^&*+=|:.<>/?@-]+', Operator), (r'[\[\]{}();,]+', Punctuation), @@ -736,7 +832,7 @@ class PhpLexer(RegexLexer): (r'(function)(\s*)(?=\()', bygroups(Keyword, Text)), (r'(function)(\s+)(&?)(\s*)', bygroups(Keyword, Text, Operator, Text), 'functionname'), - (r'(const)(\s+)([a-zA-Z_][a-zA-Z0-9_]*)', + (r'(const)(\s+)(' + _ident_inner + ')', bygroups(Keyword, Text, Name.Constant)), (r'(and|E_PARSE|old_function|E_ERROR|or|as|E_WARNING|parent|' r'eval|PHP_OS|break|exit|case|extends|PHP_VERSION|cfunction|' @@ -747,31 +843,33 @@ class PhpLexer(RegexLexer): r'endif|list|__LINE__|endswitch|new|__sleep|endwhile|not|' 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'\$\{\$+[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), + r'catch|throw|this|use|namespace|trait|yield|' + r'finally)\b', Keyword), + (r'(true|false|null)\b', Keyword.Constant), + (r'\$\{\$+' + _ident_inner + '\}', Name.Variable), + (r'\$+' + _ident_inner, Name.Variable), + (_ident_inner, Name.Other), (r'(\d+\.\d*|\d*\.\d+)([eE][+-]?[0-9]+)?', Number.Float), (r'\d+[eE][+-]?[0-9]+', Number.Float), (r'0[0-7]+', Number.Oct), (r'0[xX][a-fA-F0-9]+', Number.Hex), (r'\d+', Number.Integer), + (r'0b[01]+', Number.Binary), (r"'([^'\\]*(?:\\.[^'\\]*)*)'", String.Single), (r'`([^`\\]*(?:\\.[^`\\]*)*)`', String.Backtick), (r'"', String.Double, 'string'), ], 'classname': [ - (r'[a-zA-Z_][\\a-zA-Z0-9_]*', Name.Class, '#pop') + (_ident_inner, Name.Class, '#pop') ], 'functionname': [ - (r'[a-zA-Z_][a-zA-Z0-9_]*', Name.Function, '#pop') + (_ident_inner, Name.Function, '#pop') ], 'string': [ (r'"', String.Double, '#pop'), (r'[^{$"\\]+', String.Double), (r'\\([nrt\"$\\]|[0-7]{1,3}|x[0-9A-Fa-f]{1,2})', String.Escape), - (r'\$[a-zA-Z_][a-zA-Z0-9_]*(\[\S+\]|->[a-zA-Z_][a-zA-Z0-9_]*)?', + (r'\$' + _ident_inner + '(\[\S+?\]|->' + _ident_inner + ')?', String.Interpol), (r'(\{\$\{)(.*?)(\}\})', bygroups(String.Interpol, using(this, _startinline=True), @@ -800,7 +898,7 @@ class PhpLexer(RegexLexer): self._functions = set() if self.funcnamehighlighting: from pygments.lexers._phpbuiltins import MODULES - for key, value in MODULES.iteritems(): + for key, value in iteritems(MODULES): if key not in self.disabledmodules: self._functions.update(value) RegexLexer.__init__(self, **options) @@ -826,19 +924,106 @@ class PhpLexer(RegexLexer): return rv +class DtdLexer(RegexLexer): + """ + A lexer for DTDs (Document Type Definitions). + + .. versionadded:: 1.5 + """ + + flags = re.MULTILINE | re.DOTALL + + name = 'DTD' + aliases = ['dtd'] + filenames = ['*.dtd'] + mimetypes = ['application/xml-dtd'] + + tokens = { + 'root': [ + include('common'), + + (r'(<!ELEMENT)(\s+)(\S+)', + bygroups(Keyword, Text, Name.Tag), 'element'), + (r'(<!ATTLIST)(\s+)(\S+)', + bygroups(Keyword, Text, Name.Tag), 'attlist'), + (r'(<!ENTITY)(\s+)(\S+)', + bygroups(Keyword, Text, Name.Entity), 'entity'), + (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]+)', + bygroups(Keyword, Text, Name.Tag)), + (r'PUBLIC|SYSTEM', Keyword.Constant), + (r'[\[\]>]', Keyword), + ], + + 'common': [ + (r'\s+', Text), + (r'(%|&)[^;]*;', Name.Entity), + ('<!--', Comment, 'comment'), + (r'[(|)*,?+]', Operator), + (r'"[^"]*"', String.Double), + (r'\'[^\']*\'', String.Single), + ], + + 'comment': [ + ('[^-]+', Comment), + ('-->', Comment, '#pop'), + ('-', Comment), + ], + + 'element': [ + include('common'), + (r'EMPTY|ANY|#PCDATA', Keyword.Constant), + (r'[^>\s\|()?+*,]+', Name.Tag), + (r'>', Keyword, '#pop'), + ], + + 'attlist': [ + include('common'), + (r'CDATA|IDREFS|IDREF|ID|NMTOKENS|NMTOKEN|ENTITIES|ENTITY|NOTATION', + Keyword.Constant), + (r'#REQUIRED|#IMPLIED|#FIXED', Keyword.Constant), + (r'xml:space|xml:lang', Keyword.Reserved), + (r'[^>\s\|()?+*,]+', Name.Attribute), + (r'>', Keyword, '#pop'), + ], + + 'entity': [ + include('common'), + (r'SYSTEM|PUBLIC|NDATA', Keyword.Constant), + (r'[^>\s\|()?+*,]+', Name.Entity), + (r'>', Keyword, '#pop'), + ], + + 'notation': [ + include('common'), + (r'SYSTEM|PUBLIC', Keyword.Constant), + (r'[^>\s\|()?+*,]+', Name.Attribute), + (r'>', Keyword, '#pop'), + ], + } + + def analyse_text(text): + if not looks_like_xml(text) and \ + ('<!ELEMENT' in text or '<!ATTLIST' in text or '<!ENTITY' in text): + return 0.8 + class XmlLexer(RegexLexer): """ Generic lexer for XML (eXtensible Markup Language). """ - flags = re.MULTILINE | re.DOTALL + flags = re.MULTILINE | re.DOTALL | re.UNICODE name = 'XML' aliases = ['xml'] - filenames = ['*.xml', '*.xsl', '*.rss', '*.xslt', '*.xsd', '*.wsdl'] + filenames = ['*.xml', '*.xsl', '*.rss', '*.xslt', '*.xsd', + '*.wsdl', '*.wsf'] mimetypes = ['text/xml', 'application/xml', 'image/svg+xml', - 'application/rss+xml', 'application/atom+xml', - 'application/xsl+xml', 'application/xslt+xml'] + 'application/rss+xml', 'application/atom+xml'] tokens = { 'root': [ @@ -848,8 +1033,8 @@ class XmlLexer(RegexLexer): ('<!--', Comment, 'comment'), (r'<\?.*?\?>', Comment.Preproc), ('<![^>]*>', Comment.Preproc), - (r'<\s*[a-zA-Z0-9:._-]+', Name.Tag, 'tag'), - (r'<\s*/\s*[a-zA-Z0-9:._-]+\s*>', Name.Tag), + (r'<\s*[\w:.-]+', Name.Tag, 'tag'), + (r'<\s*/\s*[\w:.-]+\s*>', Name.Tag), ], 'comment': [ ('[^-]+', Comment), @@ -858,7 +1043,7 @@ class XmlLexer(RegexLexer): ], 'tag': [ (r'\s+', Text), - (r'[a-zA-Z0-9_.:-]+\s*=', Name.Attribute, 'attr'), + (r'[\w.:-]+\s*=', Name.Attribute, 'attr'), (r'/?\s*>', Name.Tag, '#pop'), ], 'attr': [ @@ -878,12 +1063,13 @@ class XsltLexer(XmlLexer): ''' A lexer for XSLT. - *New in Pygments 0.10.* + .. versionadded:: 0.10 ''' name = 'XSLT' aliases = ['xslt'] - filenames = ['*.xsl', '*.xslt'] + filenames = ['*.xsl', '*.xslt', '*.xpl'] # xpl is XProc + mimetypes = ['application/xsl+xml', 'application/xslt+xml'] EXTRA_KEYWORDS = set([ 'apply-imports', 'apply-templates', 'attribute', @@ -914,6 +1100,8 @@ class MxmlLexer(RegexLexer): """ For MXML markup. Nested AS3 in <script> tags is highlighted by the appropriate lexer. + + .. versionadded:: 1.1 """ flags = re.MULTILINE | re.DOTALL name = 'MXML' @@ -952,225 +1140,840 @@ class MxmlLexer(RegexLexer): } -class HaxeLexer(RegexLexer): +class HaxeLexer(ExtendedRegexLexer): """ - For haXe source code (http://haxe.org/). + For Haxe source code (http://haxe.org/). + + .. versionadded:: 1.3 """ - name = 'haXe' - aliases = ['hx', 'haXe'] - filenames = ['*.hx'] - mimetypes = ['text/haxe'] + name = 'Haxe' + aliases = ['hx', 'haxe', 'hxsl'] + filenames = ['*.hx', '*.hxsl'] + mimetypes = ['text/haxe', 'text/x-haxe', 'text/x-hx'] - ident = r'(?:[a-zA-Z_][a-zA-Z0-9_]*)' - typeid = r'(?:(?:[a-z0-9_\.])*[A-Z_][A-Za-z0-9_]*)' - key_prop = r'(?:default|null|never)' - key_decl_mod = r'(?:public|private|override|static|inline|extern|dynamic)' + # keywords extracted from lexer.mll in the haxe compiler source + keyword = (r'(?:function|class|static|var|if|else|while|do|for|' + r'break|return|continue|extends|implements|import|' + r'switch|case|default|public|private|try|untyped|' + r'catch|new|this|throw|extern|enum|in|interface|' + r'cast|override|dynamic|typedef|package|' + r'inline|using|null|true|false|abstract)\b') + + # idtype in lexer.mll + typeid = r'_*[A-Z][_a-zA-Z0-9]*' + + # combined ident and dollar and idtype + ident = r'(?:_*[a-z][_a-zA-Z0-9]*|_+[0-9][_a-zA-Z0-9]*|' + typeid + \ + '|_+|\$[_a-zA-Z0-9]+)' + + binop = (r'(?:%=|&=|\|=|\^=|\+=|\-=|\*=|/=|<<=|>\s*>\s*=|>\s*>\s*>\s*=|==|' + r'!=|<=|>\s*=|&&|\|\||<<|>>>|>\s*>|\.\.\.|<|>|%|&|\||\^|\+|\*|' + r'/|\-|=>|=)') + + # ident except keywords + ident_no_keyword = r'(?!' + keyword + ')' + ident flags = re.DOTALL | re.MULTILINE + preproc_stack = [] + + def preproc_callback(self, match, ctx): + proc = match.group(2) + + if proc == 'if': + # store the current stack + self.preproc_stack.append(ctx.stack[:]) + elif proc in ['else', 'elseif']: + # restore the stack back to right before #if + if self.preproc_stack: ctx.stack = self.preproc_stack[-1][:] + elif proc == 'end': + # remove the saved stack of previous #if + if self.preproc_stack: self.preproc_stack.pop() + + # #if and #elseif should follow by an expr + if proc in ['if', 'elseif']: + ctx.stack.append('preproc-expr') + + # #error can be optionally follow by the error msg + if proc in ['error']: + ctx.stack.append('preproc-error') + + yield match.start(), Comment.Preproc, '#' + proc + ctx.pos = match.end() + + tokens = { 'root': [ - include('whitespace'), - include('comments'), - (key_decl_mod, Keyword.Declaration), - include('enumdef'), - include('typedef'), - include('classdef'), - include('imports'), + include('spaces'), + include('meta'), + (r'(?:package)\b', Keyword.Namespace, ('semicolon', 'package')), + (r'(?:import)\b', Keyword.Namespace, ('semicolon', 'import')), + (r'(?:using)\b', Keyword.Namespace, ('semicolon', 'using')), + (r'(?:extern|private)\b', Keyword.Declaration), + (r'(?:abstract)\b', Keyword.Declaration, 'abstract'), + (r'(?:class|interface)\b', Keyword.Declaration, 'class'), + (r'(?:enum)\b', Keyword.Declaration, 'enum'), + (r'(?:typedef)\b', Keyword.Declaration, 'typedef'), + + # top-level expression + # although it is not supported in haxe, but it is common to write + # expression in web pages the positive lookahead here is to prevent + # an infinite loop at the EOF + (r'(?=.)', Text, 'expr-statement'), + ], + + # space/tab/comment/preproc + 'spaces': [ + (r'\s+', Text), + (r'//[^\n\r]*', Comment.Single), + (r'/\*.*?\*/', Comment.Multiline), + (r'(#)(if|elseif|else|end|error)\b', preproc_callback), ], - # General constructs - 'comments': [ - (r'//.*?\n', Comment.Single), - (r'/\*.*?\*/', Comment.Multiline), - (r'#[^\n]*', Comment.Preproc), + 'string-single-interpol': [ + (r'\$\{', String.Interpol, ('string-interpol-close', 'expr')), + (r'\$\$', String.Escape), + (r'\$(?=' + ident + ')', String.Interpol, 'ident'), + include('string-single'), ], - 'whitespace': [ - include('comments'), - (r'\s+', Text), + + 'string-single': [ + (r"'", String.Single, '#pop'), + (r'\\.', String.Escape), + (r'.', String.Single), ], - 'codekeywords': [ - (r'\b(if|else|while|do|for|in|break|continue|' - r'return|switch|case|try|catch|throw|null|trace|' - r'new|this|super|untyped|cast|callback|here)\b', - Keyword.Reserved), + + 'string-double': [ + (r'"', String.Double, '#pop'), + (r'\\.', String.Escape), + (r'.', String.Double), ], - 'literals': [ - (r'0[xX][0-9a-fA-F]+', Number.Hex), - (r'[0-9]+', Number.Integer), - (r'[0-9][0-9]*\.[0-9]+([eE][0-9]+)?[fd]?', Number.Float), - (r"'(\\\\|\\'|[^'])*'", String.Single), - (r'"(\\\\|\\"|[^"])*"', String.Double), - (r'~/([^\n])*?/[gisx]*', String.Regex), - (r'\b(true|false|null)\b', Keyword.Constant), - ], - 'codeblock': [ - include('whitespace'), - include('new'), - include('case'), - include('anonfundef'), - include('literals'), - include('vardef'), - include('codekeywords'), - (r'[();,\[\]]', Punctuation), - (r'(?:=|\+=|-=|\*=|/=|%=|&=|\|=|\^=|<<=|>>=|>>>=|\|\||&&|' - r'\.\.\.|==|!=|>|<|>=|<=|\||&|\^|<<|>>|>>>|\+|\-|\*|/|%|' - r'!|\+\+|\-\-|~|\.|\?|\:)', - Operator), - (ident, Name), - - (r'}', Punctuation,'#pop'), - (r'{', Punctuation,'#push'), - ], - - # Instance/Block level constructs - 'propertydef': [ - (r'(\()(' + key_prop + ')(,)(' + key_prop + ')(\))', - bygroups(Punctuation, Keyword.Reserved, Punctuation, - Keyword.Reserved, Punctuation)), + + 'string-interpol-close': [ + (r'\$'+ident, String.Interpol), + (r'\}', String.Interpol, '#pop'), ], - 'new': [ - (r'\bnew\b', Keyword, 'typedecl'), + + 'package': [ + include('spaces'), + (ident, Name.Namespace), + (r'\.', Punctuation, 'import-ident'), + (r'', Text, '#pop'), ], - 'case': [ - (r'\b(case)(\s+)(' + ident + ')(\s*)(\()', - bygroups(Keyword.Reserved, Text, Name, Text, Punctuation), - 'funargdecl'), + + 'import': [ + include('spaces'), + (ident, Name.Namespace), + (r'\*', Keyword), # wildcard import + (r'\.', Punctuation, 'import-ident'), + (r'in', Keyword.Namespace, 'ident'), + (r'', Text, '#pop'), ], - 'vardef': [ - (r'\b(var)(\s+)(' + ident + ')', - bygroups(Keyword.Declaration, Text, Name.Variable), 'vardecl'), + + 'import-ident': [ + include('spaces'), + (r'\*', Keyword, '#pop'), # wildcard import + (ident, Name.Namespace, '#pop'), ], - 'vardecl': [ - include('whitespace'), - include('typelabel'), - (r'=', Operator,'#pop'), - (r';', Punctuation,'#pop'), + + 'using': [ + include('spaces'), + (ident, Name.Namespace), + (r'\.', Punctuation, 'import-ident'), + (r'', Text, '#pop'), ], - 'instancevardef': [ - (key_decl_mod,Keyword.Declaration), - (r'\b(var)(\s+)(' + ident + ')', - bygroups(Keyword.Declaration, Text, Name.Variable.Instance), - 'instancevardecl'), + + 'preproc-error': [ + (r'\s+', Comment.Preproc), + (r"'", String.Single, ('#pop', 'string-single')), + (r'"', String.Double, ('#pop', 'string-double')), + (r'', Text, '#pop'), ], - 'instancevardecl': [ - include('vardecl'), - include('propertydef'), + + 'preproc-expr': [ + (r'\s+', Comment.Preproc), + (r'\!', Comment.Preproc), + (r'\(', Comment.Preproc, ('#pop', 'preproc-parenthesis')), + + (ident, Comment.Preproc, '#pop'), + (r"'", String.Single, ('#pop', 'string-single')), + (r'"', String.Double, ('#pop', 'string-double')), ], - 'anonfundef': [ - (r'\bfunction\b', Keyword.Declaration, 'fundecl'), + 'preproc-parenthesis': [ + (r'\s+', Comment.Preproc), + (r'\)', Comment.Preproc, '#pop'), + ('', Text, 'preproc-expr-in-parenthesis'), ], - 'instancefundef': [ - (key_decl_mod, Keyword.Declaration), - (r'\b(function)(\s+)(' + ident + ')', - bygroups(Keyword.Declaration, Text, Name.Function), 'fundecl'), + + 'preproc-expr-chain': [ + (r'\s+', Comment.Preproc), + (binop, Comment.Preproc, ('#pop', 'preproc-expr-in-parenthesis')), + (r'', Text, '#pop'), ], - 'fundecl': [ - include('whitespace'), - include('typelabel'), - include('generictypedecl'), - (r'\(',Punctuation,'funargdecl'), - (r'(?=[a-zA-Z0-9_])',Text,'#pop'), - (r'{',Punctuation,('#pop','codeblock')), - (r';',Punctuation,'#pop'), - ], - 'funargdecl': [ - include('whitespace'), - (ident, Name.Variable), - include('typelabel'), - include('literals'), - (r'=', Operator), + + # same as 'preproc-expr' but able to chain 'preproc-expr-chain' + 'preproc-expr-in-parenthesis': [ + (r'\s+', Comment.Preproc), + (r'\!', Comment.Preproc), + (r'\(', Comment.Preproc, + ('#pop', 'preproc-expr-chain', 'preproc-parenthesis')), + + (ident, Comment.Preproc, ('#pop', 'preproc-expr-chain')), + (r"'", String.Single, + ('#pop', 'preproc-expr-chain', 'string-single')), + (r'"', String.Double, + ('#pop', 'preproc-expr-chain', 'string-double')), + ], + + 'abstract' : [ + include('spaces'), + (r'', Text, ('#pop', 'abstract-body', 'abstract-relation', + 'abstract-opaque', 'type-param-constraint', 'type-name')), + ], + + 'abstract-body' : [ + include('spaces'), + (r'\{', Punctuation, ('#pop', 'class-body')), + ], + + 'abstract-opaque' : [ + include('spaces'), + (r'\(', Punctuation, ('#pop', 'parenthesis-close', 'type')), + (r'', Text, '#pop'), + ], + + 'abstract-relation': [ + include('spaces'), + (r'(?:to|from)', Keyword.Declaration, 'type'), (r',', Punctuation), + (r'', Text, '#pop'), + ], + + 'meta': [ + include('spaces'), + (r'@', Name.Decorator, ('meta-body', 'meta-ident', 'meta-colon')), + ], + + # optional colon + 'meta-colon': [ + include('spaces'), + (r':', Name.Decorator, '#pop'), + (r'', Text, '#pop'), + ], + + # same as 'ident' but set token as Name.Decorator instead of Name + 'meta-ident': [ + include('spaces'), + (ident, Name.Decorator, '#pop'), + ], + + 'meta-body': [ + include('spaces'), + (r'\(', Name.Decorator, ('#pop', 'meta-call')), + (r'', Text, '#pop'), + ], + + 'meta-call': [ + include('spaces'), + (r'\)', Name.Decorator, '#pop'), + (r'', Text, ('#pop', 'meta-call-sep', 'expr')), + ], + + 'meta-call-sep': [ + include('spaces'), + (r'\)', Name.Decorator, '#pop'), + (r',', Punctuation, ('#pop', 'meta-call')), + ], + + 'typedef': [ + include('spaces'), + (r'', Text, ('#pop', 'typedef-body', 'type-param-constraint', + 'type-name')), + ], + + 'typedef-body': [ + include('spaces'), + (r'=', Operator, ('#pop', 'optional-semicolon', 'type')), + ], + + 'enum': [ + include('spaces'), + (r'', Text, ('#pop', 'enum-body', 'bracket-open', + 'type-param-constraint', 'type-name')), + ], + + 'enum-body': [ + include('spaces'), + include('meta'), + (r'\}', Punctuation, '#pop'), + (ident_no_keyword, Name, ('enum-member', 'type-param-constraint')), + ], + + 'enum-member': [ + include('spaces'), + (r'\(', Punctuation, + ('#pop', 'semicolon', 'flag', 'function-param')), + (r'', Punctuation, ('#pop', 'semicolon', 'flag')), + ], + + 'class': [ + include('spaces'), + (r'', Text, ('#pop', 'class-body', 'bracket-open', 'extends', + 'type-param-constraint', 'type-name')), + ], + + 'extends': [ + include('spaces'), + (r'(?:extends|implements)\b', Keyword.Declaration, 'type'), + (r',', Punctuation), # the comma is made optional here, since haxe2 + # requires the comma but haxe3 does not allow it + (r'', Text, '#pop'), + ], + + 'bracket-open': [ + include('spaces'), + (r'\{', Punctuation, '#pop'), + ], + + 'bracket-close': [ + include('spaces'), + (r'\}', Punctuation, '#pop'), + ], + + 'class-body': [ + include('spaces'), + include('meta'), + (r'\}', Punctuation, '#pop'), + (r'(?:static|public|private|override|dynamic|inline|macro)\b', + Keyword.Declaration), + (r'', Text, 'class-member'), + ], + + 'class-member': [ + include('spaces'), + (r'(var)\b', Keyword.Declaration, + ('#pop', 'optional-semicolon', 'prop')), + (r'(function)\b', Keyword.Declaration, + ('#pop', 'optional-semicolon', 'class-method')), + ], + + # local function, anonymous or not + 'function-local': [ + include('spaces'), + (r'(' + ident_no_keyword + ')?', Name.Function, + ('#pop', 'expr', 'flag', 'function-param', + 'parenthesis-open', 'type-param-constraint')), + ], + + 'optional-expr': [ + include('spaces'), + include('expr'), + (r'', Text, '#pop'), + ], + + 'class-method': [ + include('spaces'), + (ident, Name.Function, ('#pop', 'optional-expr', 'flag', + 'function-param', 'parenthesis-open', + 'type-param-constraint')), + ], + + # function arguments + 'function-param': [ + include('spaces'), + (r'\)', Punctuation, '#pop'), (r'\?', Punctuation), + (ident_no_keyword, Name, + ('#pop', 'function-param-sep', 'assign', 'flag')), + ], + + 'function-param-sep': [ + include('spaces'), (r'\)', Punctuation, '#pop'), + (r',', Punctuation, ('#pop', 'function-param')), ], - 'typelabel': [ - (r':', Punctuation, 'type'), + # class property + # eg. var prop(default, null):String; + 'prop': [ + include('spaces'), + (ident_no_keyword, Name, ('#pop', 'assign', 'flag', 'prop-get-set')), ], - 'typedecl': [ - include('whitespace'), - (typeid, Name.Class), - (r'<', Punctuation, 'generictypedecl'), - (r'(?=[{}()=,a-z])', Text,'#pop'), + + 'prop-get-set': [ + include('spaces'), + (r'\(', Punctuation, ('#pop', 'parenthesis-close', + 'prop-get-set-opt', 'comma', 'prop-get-set-opt')), + (r'', Text, '#pop'), + ], + + 'prop-get-set-opt': [ + include('spaces'), + (r'(?:default|null|never|dynamic|get|set)\b', Keyword, '#pop'), + (ident_no_keyword, Text, '#pop'), #custom getter/setter + ], + + 'expr-statement': [ + include('spaces'), + # makes semicolon optional here, just to avoid checking the last + # one is bracket or not. + (r'', Text, ('#pop', 'optional-semicolon', 'expr')), + ], + + 'expr': [ + include('spaces'), + (r'@', Name.Decorator, ('#pop', 'optional-expr', 'meta-body', + 'meta-ident', 'meta-colon')), + (r'(?:\+\+|\-\-|~(?!/)|!|\-)', Operator), + (r'\(', Punctuation, ('#pop', 'expr-chain', 'parenthesis')), + (r'(?:inline)\b', Keyword.Declaration), + (r'(?:function)\b', Keyword.Declaration, ('#pop', 'expr-chain', + 'function-local')), + (r'\{', Punctuation, ('#pop', 'expr-chain', 'bracket')), + (r'(?:true|false|null)\b', Keyword.Constant, ('#pop', 'expr-chain')), + (r'(?:this)\b', Keyword, ('#pop', 'expr-chain')), + (r'(?:cast)\b', Keyword, ('#pop', 'expr-chain', 'cast')), + (r'(?:try)\b', Keyword, ('#pop', 'catch', 'expr')), + (r'(?:var)\b', Keyword.Declaration, ('#pop', 'var')), + (r'(?:new)\b', Keyword, ('#pop', 'expr-chain', 'new')), + (r'(?:switch)\b', Keyword, ('#pop', 'switch')), + (r'(?:if)\b', Keyword, ('#pop', 'if')), + (r'(?:do)\b', Keyword, ('#pop', 'do')), + (r'(?:while)\b', Keyword, ('#pop', 'while')), + (r'(?:for)\b', Keyword, ('#pop', 'for')), + (r'(?:untyped|throw)\b', Keyword), + (r'(?:return)\b', Keyword, ('#pop', 'optional-expr')), + (r'(?:macro)\b', Keyword, ('#pop', 'macro')), + (r'(?:continue|break)\b', Keyword, '#pop'), + (r'(?:\$\s*[a-z]\b|\$(?!'+ident+'))', Name, ('#pop', 'dollar')), + (ident_no_keyword, Name, ('#pop', 'expr-chain')), + + # Float + (r'\.[0-9]+', Number.Float, ('#pop', 'expr-chain')), + (r'[0-9]+[eE][\+\-]?[0-9]+', Number.Float, ('#pop', 'expr-chain')), + (r'[0-9]+\.[0-9]*[eE][\+\-]?[0-9]+', Number.Float, ('#pop', 'expr-chain')), + (r'[0-9]+\.[0-9]+', Number.Float, ('#pop', 'expr-chain')), + (r'[0-9]+\.(?!' + ident + '|\.\.)', Number.Float, ('#pop', 'expr-chain')), + + # Int + (r'0x[0-9a-fA-F]+', Number.Hex, ('#pop', 'expr-chain')), + (r'[0-9]+', Number.Integer, ('#pop', 'expr-chain')), + + # String + (r"'", String.Single, ('#pop', 'expr-chain', 'string-single-interpol')), + (r'"', String.Double, ('#pop', 'expr-chain', 'string-double')), + + # EReg + (r'~/(\\\\|\\/|[^/\n])*/[gimsu]*', String.Regex, ('#pop', 'expr-chain')), + + # Array + (r'\[', Punctuation, ('#pop', 'expr-chain', 'array-decl')), + ], + + 'expr-chain': [ + include('spaces'), + (r'(?:\+\+|\-\-)', Operator), + (binop, Operator, ('#pop', 'expr')), + (r'(?:in)\b', Keyword, ('#pop', 'expr')), + (r'\?', Operator, ('#pop', 'expr', 'ternary', 'expr')), + (r'(\.)(' + ident_no_keyword + ')', bygroups(Punctuation, Name)), + (r'\[', Punctuation, 'array-access'), + (r'\(', Punctuation, 'call'), + (r'', Text, '#pop'), + ], + + # macro reification + 'macro': [ + include('spaces'), + (r':', Punctuation, ('#pop', 'type')), + (r'', Text, ('#pop', 'expr')), + ], + + # cast can be written as "cast expr" or "cast(expr, type)" + 'cast': [ + include('spaces'), + (r'\(', Punctuation, ('#pop', 'parenthesis-close', + 'cast-type', 'expr')), + (r'', Text, ('#pop', 'expr')), + ], + + # optionally give a type as the 2nd argument of cast() + 'cast-type': [ + include('spaces'), + (r',', Punctuation, ('#pop', 'type')), + (r'', Text, '#pop'), + ], + + 'catch': [ + include('spaces'), + (r'(?:catch)\b', Keyword, ('expr', 'function-param', + 'parenthesis-open')), + (r'', Text, '#pop'), + ], + + # do-while loop + 'do': [ + include('spaces'), + (r'', Punctuation, ('#pop', 'do-while', 'expr')), + ], + + # the while after do + 'do-while': [ + include('spaces'), + (r'(?:while)\b', Keyword, ('#pop', 'parenthesis', + 'parenthesis-open')), + ], + + 'while': [ + include('spaces'), + (r'\(', Punctuation, ('#pop', 'expr', 'parenthesis')), + ], + + 'for': [ + include('spaces'), + (r'\(', Punctuation, ('#pop', 'expr', 'parenthesis')), + ], + + 'if': [ + include('spaces'), + (r'\(', Punctuation, ('#pop', 'else', 'optional-semicolon', 'expr', + 'parenthesis')), + ], + + 'else': [ + include('spaces'), + (r'(?:else)\b', Keyword, ('#pop', 'expr')), + (r'', Text, '#pop'), + ], + + 'switch': [ + include('spaces'), + (r'', Text, ('#pop', 'switch-body', 'bracket-open', 'expr')), + ], + + 'switch-body': [ + include('spaces'), + (r'(?:case|default)\b', Keyword, ('case-block', 'case')), + (r'\}', Punctuation, '#pop'), + ], + + 'case': [ + include('spaces'), + (r':', Punctuation, '#pop'), + (r'', Text, ('#pop', 'case-sep', 'case-guard', 'expr')), + ], + + 'case-sep': [ + include('spaces'), + (r':', Punctuation, '#pop'), + (r',', Punctuation, ('#pop', 'case')), + ], + + 'case-guard': [ + include('spaces'), + (r'(?:if)\b', Keyword, ('#pop', 'parenthesis', 'parenthesis-open')), + (r'', Text, '#pop'), + ], + + # optional multiple expr under a case + 'case-block': [ + include('spaces'), + (r'(?!(?:case|default)\b|\})', Keyword, 'expr-statement'), + (r'', Text, '#pop'), + ], + + 'new': [ + include('spaces'), + (r'', Text, ('#pop', 'call', 'parenthesis-open', 'type')), + ], + + 'array-decl': [ + include('spaces'), + (r'\]', Punctuation, '#pop'), + (r'', Text, ('#pop', 'array-decl-sep', 'expr')), + ], + + 'array-decl-sep': [ + include('spaces'), + (r'\]', Punctuation, '#pop'), + (r',', Punctuation, ('#pop', 'array-decl')), + ], + + 'array-access': [ + include('spaces'), + (r'', Text, ('#pop', 'array-access-close', 'expr')), + ], + + 'array-access-close': [ + include('spaces'), + (r'\]', Punctuation, '#pop'), + ], + + 'comma': [ + include('spaces'), + (r',', Punctuation, '#pop'), + ], + + 'colon': [ + include('spaces'), + (r':', Punctuation, '#pop'), + ], + + 'semicolon': [ + include('spaces'), + (r';', Punctuation, '#pop'), + ], + + 'optional-semicolon': [ + include('spaces'), + (r';', Punctuation, '#pop'), + (r'', Text, '#pop'), + ], + + # identity that CAN be a Haxe keyword + 'ident': [ + include('spaces'), + (ident, Name, '#pop'), + ], + + 'dollar': [ + include('spaces'), + (r'\{', Keyword, ('#pop', 'bracket-close', 'expr')), + (r'', Text, ('#pop', 'expr-chain')), + ], + + 'type-name': [ + include('spaces'), + (typeid, Name, '#pop'), + ], + + 'type-full-name': [ + include('spaces'), + (r'\.', Punctuation, 'ident'), + (r'', Text, '#pop'), ], + 'type': [ - include('whitespace'), - (typeid, Name.Class), - (r'<', Punctuation, 'generictypedecl'), - (r'->', Keyword.Type), - (r'(?=[{}(),;=])', Text, '#pop'), + include('spaces'), + (r'\?', Punctuation), + (ident, Name, ('#pop', 'type-check', 'type-full-name')), + (r'\{', Punctuation, ('#pop', 'type-check', 'type-struct')), + (r'\(', Punctuation, ('#pop', 'type-check', 'type-parenthesis')), ], - 'generictypedecl': [ - include('whitespace'), - (typeid, Name.Class), - (r'<', Punctuation, '#push'), + + 'type-parenthesis': [ + include('spaces'), + (r'', Text, ('#pop', 'parenthesis-close', 'type')), + ], + + 'type-check': [ + include('spaces'), + (r'->', Punctuation, ('#pop', 'type')), + (r'<(?!=)', Punctuation, 'type-param'), + (r'', Text, '#pop'), + ], + + 'type-struct': [ + include('spaces'), + (r'\}', Punctuation, '#pop'), + (r'\?', Punctuation), + (r'>', Punctuation, ('comma', 'type')), + (ident_no_keyword, Name, ('#pop', 'type-struct-sep', 'type', 'colon')), + include('class-body'), + ], + + 'type-struct-sep': [ + include('spaces'), + (r'\}', Punctuation, '#pop'), + (r',', Punctuation, ('#pop', 'type-struct')), + ], + + # type-param can be a normal type or a constant literal... + 'type-param-type': [ + # Float + (r'\.[0-9]+', Number.Float, '#pop'), + (r'[0-9]+[eE][\+\-]?[0-9]+', Number.Float, '#pop'), + (r'[0-9]+\.[0-9]*[eE][\+\-]?[0-9]+', Number.Float, '#pop'), + (r'[0-9]+\.[0-9]+', Number.Float, '#pop'), + (r'[0-9]+\.(?!' + ident + '|\.\.)', Number.Float, '#pop'), + + # Int + (r'0x[0-9a-fA-F]+', Number.Hex, '#pop'), + (r'[0-9]+', Number.Integer, '#pop'), + + # String + (r"'", String.Single, ('#pop', 'string-single')), + (r'"', String.Double, ('#pop', 'string-double')), + + # EReg + (r'~/(\\\\|\\/|[^/\n])*/[gim]*', String.Regex, '#pop'), + + # Array + (r'\[', Operator, ('#pop', 'array-decl')), + + include('type'), + ], + + # type-param part of a type + # ie. the <A,B> path in Map<A,B> + 'type-param': [ + include('spaces'), + (r'', Text, ('#pop', 'type-param-sep', 'type-param-type')), + ], + + 'type-param-sep': [ + include('spaces'), (r'>', Punctuation, '#pop'), - (r',', Punctuation), + (r',', Punctuation, ('#pop', 'type-param')), ], - # Top level constructs - 'imports': [ - (r'(package|import|using)(\s+)([^;]+)(;)', - bygroups(Keyword.Namespace, Text, Name.Namespace,Punctuation)), + # optional type-param that may include constraint + # ie. <T:Constraint, T2:(ConstraintA,ConstraintB)> + 'type-param-constraint': [ + include('spaces'), + (r'<(?!=)', Punctuation, ('#pop', 'type-param-constraint-sep', + 'type-param-constraint-flag', 'type-name')), + (r'', Text, '#pop'), ], - 'typedef': [ - (r'typedef', Keyword.Declaration, ('typedefprebody', 'typedecl')), + + 'type-param-constraint-sep': [ + include('spaces'), + (r'>', Punctuation, '#pop'), + (r',', Punctuation, ('#pop', 'type-param-constraint-sep', + 'type-param-constraint-flag', 'type-name')), ], - 'typedefprebody': [ - include('whitespace'), - (r'(=)(\s*)({)', bygroups(Punctuation, Text, Punctuation), - ('#pop', 'typedefbody')), + + # the optional constraint inside type-param + 'type-param-constraint-flag': [ + include('spaces'), + (r':', Punctuation, ('#pop', 'type-param-constraint-flag-type')), + (r'', Text, '#pop'), ], - 'enumdef': [ - (r'enum', Keyword.Declaration, ('enumdefprebody', 'typedecl')), + + 'type-param-constraint-flag-type': [ + include('spaces'), + (r'\(', Punctuation, ('#pop', 'type-param-constraint-flag-type-sep', + 'type')), + (r'', Text, ('#pop', 'type')), ], - 'enumdefprebody': [ - include('whitespace'), - (r'{', Punctuation, ('#pop','enumdefbody')), + + 'type-param-constraint-flag-type-sep': [ + include('spaces'), + (r'\)', Punctuation, '#pop'), + (r',', Punctuation, 'type'), ], - 'classdef': [ - (r'class', Keyword.Declaration, ('classdefprebody', 'typedecl')), + + # a parenthesis expr that contain exactly one expr + 'parenthesis': [ + include('spaces'), + (r'', Text, ('#pop', 'parenthesis-close', 'expr')), ], - 'classdefprebody': [ - include('whitespace'), - (r'(extends|implements)', Keyword.Declaration,'typedecl'), - (r'{', Punctuation, ('#pop', 'classdefbody')), + + 'parenthesis-open': [ + include('spaces'), + (r'\(', Punctuation, '#pop'), ], - 'interfacedef': [ - (r'interface', Keyword.Declaration, - ('interfacedefprebody', 'typedecl')), + + 'parenthesis-close': [ + include('spaces'), + (r'\)', Punctuation, '#pop'), ], - 'interfacedefprebody': [ - include('whitespace'), - (r'(extends)', Keyword.Declaration, 'typedecl'), - (r'{', Punctuation, ('#pop', 'classdefbody')), - ], - - 'typedefbody': [ - include('whitespace'), - include('instancevardef'), - include('instancefundef'), - (r'>', Punctuation, 'typedecl'), - (r',', Punctuation), - (r'}', Punctuation, '#pop'), - ], - 'enumdefbody': [ - include('whitespace'), - (ident, Name.Variable.Instance), - (r'\(', Punctuation, 'funargdecl'), - (r';', Punctuation), - (r'}', Punctuation, '#pop'), - ], - 'classdefbody': [ - include('whitespace'), - include('instancevardef'), - include('instancefundef'), - (r'}', Punctuation, '#pop'), - include('codeblock'), + + 'var': [ + include('spaces'), + (ident_no_keyword, Text, ('#pop', 'var-sep', 'assign', 'flag')), + ], + + # optional more var decl. + 'var-sep': [ + include('spaces'), + (r',', Punctuation, ('#pop', 'var')), + (r'', Text, '#pop'), + ], + + # optional assignment + 'assign': [ + include('spaces'), + (r'=', Operator, ('#pop', 'expr')), + (r'', Text, '#pop'), + ], + + # optional type flag + 'flag': [ + include('spaces'), + (r':', Punctuation, ('#pop', 'type')), + (r'', Text, '#pop'), + ], + + # colon as part of a ternary operator (?:) + 'ternary': [ + include('spaces'), + (r':', Operator, '#pop'), + ], + + # function call + 'call': [ + include('spaces'), + (r'\)', Punctuation, '#pop'), + (r'', Text, ('#pop', 'call-sep', 'expr')), + ], + + # after a call param + 'call-sep': [ + include('spaces'), + (r'\)', Punctuation, '#pop'), + (r',', Punctuation, ('#pop', 'call')), + ], + + # bracket can be block or object + 'bracket': [ + include('spaces'), + (r'(?!(?:\$\s*[a-z]\b|\$(?!'+ident+')))' + ident_no_keyword, Name, + ('#pop', 'bracket-check')), + (r"'", String.Single, ('#pop', 'bracket-check', 'string-single')), + (r'"', String.Double, ('#pop', 'bracket-check', 'string-double')), + (r'', Text, ('#pop', 'block')), ], + + 'bracket-check': [ + include('spaces'), + (r':', Punctuation, ('#pop', 'object-sep', 'expr')), #is object + (r'', Text, ('#pop', 'block', 'optional-semicolon', 'expr-chain')), #is block + ], + + # code block + 'block': [ + include('spaces'), + (r'\}', Punctuation, '#pop'), + (r'', Text, 'expr-statement'), + ], + + # object in key-value pairs + 'object': [ + include('spaces'), + (r'\}', Punctuation, '#pop'), + (r'', Text, ('#pop', 'object-sep', 'expr', 'colon', 'ident-or-string')) + ], + + # a key of an object + 'ident-or-string': [ + include('spaces'), + (ident_no_keyword, Name, '#pop'), + (r"'", String.Single, ('#pop', 'string-single')), + (r'"', String.Double, ('#pop', 'string-double')), + ], + + # after a key-value pair in object + 'object-sep': [ + include('spaces'), + (r'\}', Punctuation, '#pop'), + (r',', Punctuation, ('#pop', 'object')), + ], + + + } def analyse_text(text): @@ -1211,11 +2014,11 @@ class HamlLexer(ExtendedRegexLexer): """ For Haml markup. - *New in Pygments 1.3.* + .. versionadded:: 1.3 """ name = 'Haml' - aliases = ['haml', 'HAML'] + aliases = ['haml'] filenames = ['*.haml'] mimetypes = ['text/x-haml'] @@ -1241,7 +2044,7 @@ 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'), @@ -1250,18 +2053,18 @@ 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'), ], @@ -1488,11 +2291,11 @@ class SassLexer(ExtendedRegexLexer): """ For Sass stylesheets. - *New in Pygments 1.3.* + .. versionadded:: 1.3 """ name = 'Sass' - aliases = ['sass', 'SASS'] + aliases = ['sass'] filenames = ['*.sass'] mimetypes = ['text/x-sass'] @@ -1536,7 +2339,7 @@ class SassLexer(ExtendedRegexLexer): 'import': [ (r'[ \t]+', Text), - (r'[^\s]+', String), + (r'\S+', String), (r'\n', Text, 'root'), ], @@ -1559,7 +2362,7 @@ class SassLexer(ExtendedRegexLexer): (r"\*/", Comment, '#pop'), ], } - for group, common in common_sass_tokens.iteritems(): + for group, common in iteritems(common_sass_tokens): tokens[group] = copy.copy(common) tokens['value'].append((r'\n', Text, 'root')) tokens['selector'].append((r'\n', Text, 'root')) @@ -1588,7 +2391,7 @@ class ScssLexer(RegexLexer): (r'(@include)( [\w-]+)', bygroups(Keyword, Name.Decorator), 'value'), (r'@extend', Keyword, 'selector'), (r'@[a-z0-9_-]+', Keyword, 'selector'), - (r'(\$[\w-]\w*)([ \t]*:)', bygroups(Name.Variable, Operator), 'value'), + (r'(\$[\w-]*\w)([ \t]*:)', bygroups(Name.Variable, Operator), 'value'), (r'(?=[^;{}][;}])', Name.Attribute, 'attr'), (r'(?=[^;{}:]+:[^a-z])', Name.Attribute, 'attr'), (r'', Text, 'selector'), @@ -1606,7 +2409,7 @@ class ScssLexer(RegexLexer): (r"\*/", Comment, '#pop'), ], } - for group, common in common_sass_tokens.iteritems(): + for group, common in iteritems(common_sass_tokens): tokens[group] = copy.copy(common) tokens['value'].extend([(r'\n', Text), (r'[;{}]', Punctuation, 'root')]) tokens['selector'].extend([(r'\n', Text), (r'[;{}]', Punctuation, 'root')]) @@ -1618,11 +2421,11 @@ class CoffeeScriptLexer(RegexLexer): .. _CoffeeScript: http://coffeescript.org - *New in Pygments 1.3.* + .. versionadded:: 1.3 """ name = 'CoffeeScript' - aliases = ['coffee-script', 'coffeescript'] + aliases = ['coffee-script', 'coffeescript', 'coffee'] filenames = ['*.coffee'] mimetypes = ['text/coffeescript'] @@ -1630,61 +2433,333 @@ class CoffeeScriptLexer(RegexLexer): tokens = { 'commentsandwhitespace': [ (r'\s+', Text), - (r'#.*?\n', Comment.Single), + (r'###[^#].*?###', Comment.Multiline), + (r'#(?!##[^#]).*?\n', Comment.Single), + ], + 'multilineregex': [ + (r'[^/#]+', String.Regex), + (r'///([gim]+\b|\B)', String.Regex, '#pop'), + (r'#{', String.Interpol, 'interpoling_string'), + (r'[/#]', String.Regex), ], 'slashstartsregex': [ include('commentsandwhitespace'), - (r'/(\\.|[^[/\\\n]|\[(\\.|[^\]\\\n])*])+/' + (r'///', String.Regex, ('#pop', 'multilineregex')), + (r'/(?! )(\\.|[^[/\\\n]|\[(\\.|[^\]\\\n])*])+/' r'([gim]+\b|\B)', String.Regex, '#pop'), - (r'(?=/)', Text, ('#pop', 'badregex')), (r'', Text, '#pop'), ], - 'badregex': [ - ('\n', Text, '#pop'), - ], 'root': [ - (r'^(?=\s|/|<!--)', Text, 'slashstartsregex'), + # this next expr leads to infinite loops root -> slashstartsregex + #(r'^(?=\s|/|<!--)', Text, 'slashstartsregex'), include('commentsandwhitespace'), - (r'\+\+|--|~|&&|\band\b|\bor\b|\bis\b|\bisnt\b|\bnot\b|\?|:|=|' - r'\|\||\\(?=\n)|(<<|>>>?|==?|!=?|[-<>+*`%&\|\^/])=?', + (r'\+\+|~|&&|\band\b|\bor\b|\bis\b|\bisnt\b|\bnot\b|\?|:|' + r'\|\||\\(?=\n)|' + r'(<<|>>>?|==?(?!>)|!=?|=(?!>)|-(?!>)|[<>+*`%&\|\^/])=?', Operator, 'slashstartsregex'), - (r'\([^()]*\)\s*->', Name.Function), + (r'(?:\([^()]*\))?\s*[=-]>', Name.Function), (r'[{(\[;,]', Punctuation, 'slashstartsregex'), (r'[})\].]', Punctuation), - (r'(for|in|of|while|break|return|continue|switch|when|then|if|else|' + (r'(?<![\.\$])(for|own|in|of|while|until|' + r'loop|break|return|continue|' + r'switch|when|then|if|unless|else|' r'throw|try|catch|finally|new|delete|typeof|instanceof|super|' r'extends|this|class|by)\b', Keyword, 'slashstartsregex'), - (r'(true|false|yes|no|on|off|null|NaN|Infinity|undefined)\b', + (r'(?<![\.\$])(true|false|yes|no|on|off|null|' + r'NaN|Infinity|undefined)\b', Keyword.Constant), (r'(Array|Boolean|Date|Error|Function|Math|netscape|' r'Number|Object|Packages|RegExp|String|sun|decodeURI|' r'decodeURIComponent|encodeURI|encodeURIComponent|' r'eval|isFinite|isNaN|parseFloat|parseInt|document|window)\b', Name.Builtin), - (r'[$a-zA-Z_][a-zA-Z0-9_\.:]*\s*[:=]\s', Name.Variable, + (r'[$a-zA-Z_][a-zA-Z0-9_\.:\$]*\s*[:=]\s', Name.Variable, 'slashstartsregex'), - (r'@[$a-zA-Z_][a-zA-Z0-9_\.:]*\s*[:=]\s', Name.Variable.Instance, + (r'@[$a-zA-Z_][a-zA-Z0-9_\.:\$]*\s*[:=]\s', Name.Variable.Instance, 'slashstartsregex'), - (r'@?[$a-zA-Z_][a-zA-Z0-9_]*', Name.Other, 'slashstartsregex'), + (r'@', Name.Other, 'slashstartsregex'), + (r'@?[$a-zA-Z_][a-zA-Z0-9_\$]*', Name.Other, 'slashstartsregex'), (r'[0-9][0-9]*\.[0-9]+([eE][0-9]+)?[fd]?', Number.Float), (r'0x[0-9a-fA-F]+', Number.Hex), (r'[0-9]+', Number.Integer), - (r'"(\\\\|\\"|[^"])*"', String.Double), - (r"'(\\\\|\\'|[^'])*'", String.Single), - ] + ('"""', String, 'tdqs'), + ("'''", String, 'tsqs'), + ('"', String, 'dqs'), + ("'", String, 'sqs'), + ], + 'strings': [ + (r'[^#\\\'"]+', String), + # note that all coffee script strings are multi-line. + # hashmarks, quotes and backslashes must be parsed one at a time + ], + 'interpoling_string' : [ + (r'}', String.Interpol, "#pop"), + include('root') + ], + 'dqs': [ + (r'"', String, '#pop'), + (r'\\.|\'', String), # double-quoted string don't need ' escapes + (r'#{', String.Interpol, "interpoling_string"), + include('strings') + ], + 'sqs': [ + (r"'", String, '#pop'), + (r'#|\\.|"', String), # single quoted strings don't need " escapses + include('strings') + ], + 'tdqs': [ + (r'"""', String, '#pop'), + (r'\\.|\'|"', String), # no need to escape quotes in triple-string + (r'#{', String.Interpol, "interpoling_string"), + include('strings'), + ], + 'tsqs': [ + (r"'''", String, '#pop'), + (r'#|\\.|\'|"', String), # no need to escape quotes in triple-strings + include('strings') + ], } + +class KalLexer(RegexLexer): + """ + For `Kal`_ source code. + + .. _Kal: http://rzimmerman.github.io/kal + + + .. versionadded:: 2.0 + """ + + name = 'Kal' + aliases = ['kal'] + filenames = ['*.kal'] + mimetypes = ['text/kal', 'application/kal'] + + flags = re.DOTALL + tokens = { + 'commentsandwhitespace': [ + (r'\s+', Text), + (r'###[^#].*?###', Comment.Multiline), + (r'#(?!##[^#]).*?\n', Comment.Single), + ], + 'functiondef': [ + (r'[$a-zA-Z_][a-zA-Z0-9_\$]*\s*', Name.Function, '#pop'), + include('commentsandwhitespace'), + ], + 'classdef': [ + (r'\binherits\s+from\b', Keyword), + (r'[$a-zA-Z_][a-zA-Z0-9_\$]*\s*\n', Name.Class, '#pop'), + (r'[$a-zA-Z_][a-zA-Z0-9_\$]*\s*', Name.Class), + include('commentsandwhitespace'), + ], + 'listcomprehension': [ + (r'\]', Punctuation, '#pop'), + (r'\b(property|value)\b', Keyword), + include('root'), + ], + 'waitfor': [ + (r'\n', Punctuation, '#pop'), + (r'\bfrom\b', Keyword), + include('root'), + ], + 'root': [ + include('commentsandwhitespace'), + (r'/(?! )(\\.|[^[/\\\n]|\[(\\.|[^\]\\\n])*])+/' + r'([gim]+\b|\B)', String.Regex), + (r'\?|:|_(?=\n)|==?|!=|-(?!>)|[<>+*/-]=?', + Operator), + (r'\band\b|\bor\b|\bis\b|\bisnt\b|\bnot\b|' + r'\bbut\b|\bbitwise\b|\bmod\b|\^|\bxor\b|\bexists\b|\bdoesnt\s+exist\b', + Operator.Word), + (r'(?:\([^()]+\))?\s*>', Name.Function), + (r'[{(]', Punctuation), + (r'\[', Punctuation, 'listcomprehension'), + (r'[})\]\.\,]', Punctuation), + (r'\b(function|method|task)\b', Keyword.Declaration, 'functiondef'), + (r'\bclass\b', Keyword.Declaration, 'classdef'), + (r'\b(safe\s+)?wait\s+for\b', Keyword, 'waitfor'), + (r'\b(me|this)(\.[$a-zA-Z_][a-zA-Z0-9_\.\$]*)?\b', Name.Variable.Instance), + (r'(?<![\.\$])(for(\s+(parallel|series))?|in|of|while|until|' + r'break|return|continue|' + r'when|if|unless|else|otherwise|except\s+when|' + r'throw|raise|fail\s+with|try|catch|finally|new|delete|' + r'typeof|instanceof|super|run\s+in\s+parallel|' + r'inherits\s+from)\b', Keyword), + (r'(?<![\.\$])(true|false|yes|no|on|off|null|nothing|none|' + r'NaN|Infinity|undefined)\b', + Keyword.Constant), + (r'(Array|Boolean|Date|Error|Function|Math|netscape|' + r'Number|Object|Packages|RegExp|String|sun|decodeURI|' + r'decodeURIComponent|encodeURI|encodeURIComponent|' + r'eval|isFinite|isNaN|parseFloat|parseInt|document|window|' + r'print)\b', + Name.Builtin), + (r'[$a-zA-Z_][a-zA-Z0-9_\.\$]*\s*(:|[\+\-\*\/]?\=)?\b', Name.Variable), + (r'[0-9][0-9]*\.[0-9]+([eE][0-9]+)?[fd]?', Number.Float), + (r'0x[0-9a-fA-F]+', Number.Hex), + (r'[0-9]+', Number.Integer), + ('"""', String, 'tdqs'), + ("'''", String, 'tsqs'), + ('"', String, 'dqs'), + ("'", String, 'sqs'), + ], + 'strings': [ + (r'[^#\\\'"]+', String), + # note that all kal strings are multi-line. + # hashmarks, quotes and backslashes must be parsed one at a time + ], + 'interpoling_string' : [ + (r'}', String.Interpol, "#pop"), + include('root') + ], + 'dqs': [ + (r'"', String, '#pop'), + (r'\\.|\'', String), # double-quoted string don't need ' escapes + (r'#{', String.Interpol, "interpoling_string"), + include('strings') + ], + 'sqs': [ + (r"'", String, '#pop'), + (r'#|\\.|"', String), # single quoted strings don't need " escapses + include('strings') + ], + 'tdqs': [ + (r'"""', String, '#pop'), + (r'\\.|\'|"', String), # no need to escape quotes in triple-string + (r'#{', String.Interpol, "interpoling_string"), + include('strings'), + ], + 'tsqs': [ + (r"'''", String, '#pop'), + (r'#|\\.|\'|"', String), # no need to escape quotes in triple-strings + include('strings') + ], + } + + +class LiveScriptLexer(RegexLexer): + """ + For `LiveScript`_ source code. + + .. _LiveScript: http://gkz.github.com/LiveScript/ + + New in Pygments 1.6. + """ + + name = 'LiveScript' + aliases = ['live-script', 'livescript'] + filenames = ['*.ls'] + mimetypes = ['text/livescript'] + + flags = re.DOTALL + tokens = { + 'commentsandwhitespace': [ + (r'\s+', Text), + (r'/\*.*?\*/', Comment.Multiline), + (r'#.*?\n', Comment.Single), + ], + 'multilineregex': [ + include('commentsandwhitespace'), + (r'//([gim]+\b|\B)', String.Regex, '#pop'), + (r'/', String.Regex), + (r'[^/#]+', String.Regex) + ], + 'slashstartsregex': [ + include('commentsandwhitespace'), + (r'//', String.Regex, ('#pop', 'multilineregex')), + (r'/(?! )(\\.|[^[/\\\n]|\[(\\.|[^\]\\\n])*])+/' + r'([gim]+\b|\B)', String.Regex, '#pop'), + (r'', Text, '#pop'), + ], + 'root': [ + # this next expr leads to infinite loops root -> slashstartsregex + #(r'^(?=\s|/|<!--)', Text, 'slashstartsregex'), + include('commentsandwhitespace'), + (r'(?:\([^()]+\))?[ ]*[~-]{1,2}>|' + r'(?:\(?[^()\n]+\)?)?[ ]*<[~-]{1,2}', Name.Function), + (r'\+\+|&&|(?<![\.\$])\b(?:and|x?or|is|isnt|not)\b|\?|:|=|' + r'\|\||\\(?=\n)|(<<|>>>?|==?|!=?|' + r'~(?!\~?>)|-(?!\-?>)|<(?!\[)|(?<!\])>|' + r'[+*`%&\|\^/])=?', + Operator, 'slashstartsregex'), + (r'[{(\[;,]', Punctuation, 'slashstartsregex'), + (r'[})\].]', Punctuation), + (r'(?<![\.\$])(for|own|in|of|while|until|loop|break|' + r'return|continue|switch|when|then|if|unless|else|' + r'throw|try|catch|finally|new|delete|typeof|instanceof|super|' + r'extends|this|class|by|const|var|to|til)\b', Keyword, + 'slashstartsregex'), + (r'(?<![\.\$])(true|false|yes|no|on|off|' + r'null|NaN|Infinity|undefined|void)\b', + Keyword.Constant), + (r'(Array|Boolean|Date|Error|Function|Math|netscape|' + r'Number|Object|Packages|RegExp|String|sun|decodeURI|' + r'decodeURIComponent|encodeURI|encodeURIComponent|' + r'eval|isFinite|isNaN|parseFloat|parseInt|document|window)\b', + Name.Builtin), + (r'[$a-zA-Z_][a-zA-Z0-9_\.\-:\$]*\s*[:=]\s', Name.Variable, + 'slashstartsregex'), + (r'@[$a-zA-Z_][a-zA-Z0-9_\.\-:\$]*\s*[:=]\s', Name.Variable.Instance, + 'slashstartsregex'), + (r'@', Name.Other, 'slashstartsregex'), + (r'@?[$a-zA-Z_][a-zA-Z0-9_\-]*', Name.Other, 'slashstartsregex'), + (r'[0-9]+\.[0-9]+([eE][0-9]+)?[fd]?(?:[a-zA-Z_]+)?', Number.Float), + (r'[0-9]+(~[0-9a-z]+)?(?:[a-zA-Z_]+)?', Number.Integer), + ('"""', String, 'tdqs'), + ("'''", String, 'tsqs'), + ('"', String, 'dqs'), + ("'", String, 'sqs'), + (r'\\\S+', String), + (r'<\[.*?\]>', String), + ], + 'strings': [ + (r'[^#\\\'"]+', String), + # note that all coffee script strings are multi-line. + # hashmarks, quotes and backslashes must be parsed one at a time + ], + 'interpoling_string' : [ + (r'}', String.Interpol, "#pop"), + include('root') + ], + 'dqs': [ + (r'"', String, '#pop'), + (r'\\.|\'', String), # double-quoted string don't need ' escapes + (r'#{', String.Interpol, "interpoling_string"), + (r'#', String), + include('strings') + ], + 'sqs': [ + (r"'", String, '#pop'), + (r'#|\\.|"', String), # single quoted strings don't need " escapses + include('strings') + ], + 'tdqs': [ + (r'"""', String, '#pop'), + (r'\\.|\'|"', String), # no need to escape quotes in triple-string + (r'#{', String.Interpol, "interpoling_string"), + (r'#', String), + include('strings'), + ], + 'tsqs': [ + (r"'''", String, '#pop'), + (r'#|\\.|\'|"', String), # no need to escape quotes in triple-strings + include('strings') + ], + } + + class DuelLexer(RegexLexer): """ Lexer for Duel Views Engine (formerly JBST) markup with JavaScript code blocks. See http://duelengine.org/. See http://jsonml.org/jbst/. - *New in Pygments 1.4.* + .. versionadded:: 1.4 """ name = 'Duel' - aliases = ['duel', 'Duel Engine', 'Duel View', 'JBST', 'jbst', 'JsonML+BST'] + aliases = ['duel', 'jbst', 'jsonml+bst'] filenames = ['*.duel','*.jbst'] mimetypes = ['text/x-duel','text/x-jbst'] @@ -1711,11 +2786,11 @@ class ScamlLexer(ExtendedRegexLexer): """ For `Scaml markup <http://scalate.fusesource.org/>`_. Scaml is Haml for Scala. - *New in Pygments 1.4.* + .. versionadded:: 1.4 """ name = 'Scaml' - aliases = ['scaml', 'SCAML'] + aliases = ['scaml'] filenames = ['*.scaml'] mimetypes = ['text/x-scaml'] @@ -1739,7 +2814,7 @@ class ScamlLexer(ExtendedRegexLexer): 'eval-or-plain': [ (r'[&!]?==', Punctuation, 'plain'), - (r'([&!]?[=~])(' + _dot + '*\n)', + (r'([&!]?[=~])(' + _dot + r'*\n)', bygroups(Punctuation, using(ScalaLexer)), 'root'), (r'', Text, 'plain'), @@ -1748,21 +2823,21 @@ 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'), ], @@ -1825,11 +2900,11 @@ class JadeLexer(ExtendedRegexLexer): Jade is a variant of Scaml, see: http://scalate.fusesource.org/documentation/scaml-reference.html - *New in Pygments 1.4.* + .. versionadded:: 1.4 """ name = 'Jade' - aliases = ['jade', 'JADE'] + aliases = ['jade'] filenames = ['*.jade'] mimetypes = ['text/x-jade'] @@ -1849,31 +2924,31 @@ 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': [ @@ -1933,11 +3008,11 @@ class XQueryLexer(ExtendedRegexLexer): An XQuery lexer, parsing a stream and outputting the tokens needed to highlight xquery code. - *New in Pygments 1.4.* + .. versionadded:: 1.4 """ name = 'XQuery' - aliases = ['xquery', 'xqy'] - filenames = ['*.xqy', '*.xquery'] + aliases = ['xquery', 'xqy', 'xq', 'xql', 'xqm'] + filenames = ['*.xqy', '*.xquery', '*.xq', '*.xql', '*.xqm'] mimetypes = ['text/xquery', 'application/xquery'] xquery_parse_state = [] @@ -1949,24 +3024,24 @@ 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]|' @@ -1986,6 +3061,12 @@ class XQueryLexer(ExtendedRegexLexer): flags = re.DOTALL | re.MULTILINE | re.UNICODE + def punctuation_root_callback(lexer, match, ctx): + yield match.start(), Punctuation, match.group(1) + # transition to root always - don't pop off stack + ctx.stack = ['root'] + ctx.pos = match.end() + def operator_root_callback(lexer, match, ctx): yield match.start(), Operator, match.group(1) # transition to root always - don't pop off stack @@ -2167,6 +3248,11 @@ class XQueryLexer(ExtendedRegexLexer): ctx.stack = ['root']#.append('root') ctx.pos = match.end() + def pushstate_operator_attribute_callback(lexer, match, ctx): + yield match.start(), Name.Attribute, match.group(1) + ctx.stack.append('operator') + ctx.pos = match.end() + def pushstate_operator_callback(lexer, match, ctx): yield match.start(), Keyword, match.group(1) yield match.start(), Text, match.group(2) @@ -2192,19 +3278,24 @@ class XQueryLexer(ExtendedRegexLexer): (r'(\{)', pushstate_root_callback), (r'then|else|external|at|div|except', Keyword, 'root'), + (r'order by', Keyword, 'root'), (r'is|mod|order\s+by|stable\s+order\s+by', Keyword, 'root'), (r'and|or', Operator.Word, 'root'), (r'(eq|ge|gt|le|lt|ne|idiv|intersect|in)(?=\b)', Operator.Word, 'root'), (r'return|satisfies|to|union|where|preserve\s+strip', Keyword, 'root'), - (r'(::|;|>=|>>|>|\[|<=|<<|<|-|\*|!=|\+|//|/|\||:=|,|=)', + (r'(>=|>>|>|<=|<<|<|-|\*|!=|\+|\||:=|=)', operator_root_callback), - (r'(castable|cast)(\s+)(as)', + (r'(::|;|\[|//|/|,)', + punctuation_root_callback), + (r'(castable|cast)(\s+)(as)\b', bygroups(Keyword, Text, Keyword), 'singletype'), - (r'(instance)(\s+)(of)|(treat)(\s+)(as)', + (r'(instance)(\s+)(of)\b', + bygroups(Keyword, Text, Keyword), 'itemtype'), + (r'(treat)(\s+)(as)\b', bygroups(Keyword, Text, Keyword), 'itemtype'), - (r'(case)|(as)', Keyword, 'itemtype'), + (r'(case|as)\b', Keyword, 'itemtype'), (r'(\))(\s*)(as)', bygroups(Punctuation, Text, Keyword), 'itemtype'), (r'\$', Name.Variable, 'varname'), @@ -2229,8 +3320,8 @@ 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), @@ -2262,10 +3353,10 @@ class XQueryLexer(ExtendedRegexLexer): include('whitespace'), (r'\(:', Comment, 'comment'), (r'\$', Punctuation, 'varname'), - (r'void\s*\(\s*\)', + (r'(void)(\s*)(\()(\s*)(\))', bygroups(Keyword, Text, Punctuation, Text, Punctuation), 'operator'), (r'(element|attribute|schema-element|schema-attribute|comment|text|' - r'node|binary|document-node)(\s*)(\()', + r'node|binary|document-node|empty-sequence)(\s*)(\()', pushstate_occurrenceindicator_kindtest_callback), # Marklogic specific type? (r'(processing-instruction)(\s*)(\()', @@ -2277,9 +3368,9 @@ class XQueryLexer(ExtendedRegexLexer): (r'\(\#', Punctuation, 'pragma'), (r';', Punctuation, '#pop'), (r'then|else', Keyword, '#pop'), - (r'(at)(\s+)' + stringdouble, + (r'(at)(\s+)(' + stringdouble + ')', bygroups(Keyword, Text, String.Double), 'namespacedecl'), - (r'(at)(\s+)' + stringsingle, + (r'(at)(\s+)(' + stringsingle + ')', bygroups(Keyword, Text, String.Single), 'namespacedecl'), (r'except|intersect|in|is|return|satisfies|to|union|where', Keyword, 'root'), @@ -2290,16 +3381,16 @@ class XQueryLexer(ExtendedRegexLexer): bygroups(Keyword, Text, Keyword, Text, Keyword), 'root'), (r'(castable|cast)(\s+)(as)', bygroups(Keyword, Text, Keyword), 'singletype'), - (r'(instance)(\s+)(of)|(treat)(\s+)(as)', - bygroups(Keyword, Text, Keyword)), + (r'(treat)(\s+)(as)', bygroups(Keyword, Text, Keyword)), + (r'(instance)(\s+)(of)', bygroups(Keyword, Text, Keyword)), (r'case|as', Keyword, 'itemtype'), (r'(\))(\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'), @@ -2308,7 +3399,7 @@ 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), ], @@ -2322,8 +3413,8 @@ 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), + (u'\\t|\\r|\\n|[\u0020-\uD7FF]|[\uE000-\uFFFD]|' + + unirange(0x10000, 0x10ffff), Literal), ], 'processing_instruction': [ (r'\s+', Text, 'processing_instruction_content'), @@ -2332,13 +3423,13 @@ class XQueryLexer(ExtendedRegexLexer): ], 'processing_instruction_content': [ (r'\?>', String.Doc, '#pop'), - (r'\u009|\u00A|\u00D|[\u0020-\uD7FF]|[\uE000-\uFFFD]|' - r'[\u10000-\u10FFFF]', Literal), + (u'\\t|\\r|\\n|[\u0020-\uD7FF]|[\uE000-\uFFFD]|' + + unirange(0x10000, 0x10ffff), Literal), ], 'cdata_section': [ (r']]>', String.Doc, '#pop'), - (r'\u009|\u00A|\u00D|[\u0020-\uD7FF]|[\uE000-\uFFFD]|' - r'[\u10000-\u10FFFF]', Literal), + (u'\\t|\\r|\\n|[\u0020-\uD7FF]|[\uE000-\uFFFD]|' + + unirange(0x10000, 0x10ffff), Literal), ], 'start_tag': [ include('whitespace'), @@ -2406,9 +3497,9 @@ class XQueryLexer(ExtendedRegexLexer): ], 'pragmacontents': [ (r'#\)', Punctuation, 'operator'), - (r'\u009|\u00A|\u00D|[\u0020-\u00D7FF]|[\u00E000-\u00FFFD]|' - r'[\u0010000-\u0010FFFF]', Literal), - (r'(\s*)', Text), + (u'\\t|\\r|\\n|[\u0020-\uD7FF]|[\uE000-\uFFFD]|' + + unirange(0x10000, 0x10ffff), Literal), + (r'(\s+)', Text), ], 'occurrenceindicator': [ include('whitespace'), @@ -2442,12 +3533,14 @@ class XQueryLexer(ExtendedRegexLexer): (r'(\.\d+)[eE][\+\-]?\d+', Number.Double, 'operator'), (r'(\.\d+|\d+\.\d*)', Number, 'operator'), (r'(\d+)', Number.Integer, 'operator'), - (r'(\.\.|\.|\)|\*)', Punctuation, 'operator'), + (r'(\.\.|\.|\))', Punctuation, 'operator'), (r'(declare)(\s+)(construction)', bygroups(Keyword, Text, Keyword), 'operator'), (r'(declare)(\s+)(default)(\s+)(order)', bygroups(Keyword, Text, Keyword, Text, Keyword), 'operator'), (ncname + ':\*', Name, 'operator'), + ('\*:'+ncname, Name.Tag, 'operator'), + ('\*', Name.Tag, 'operator'), (stringdouble, String.Double, 'operator'), (stringsingle, String.Single, 'operator'), @@ -2480,7 +3573,7 @@ class XQueryLexer(ExtendedRegexLexer): (r'(\))(\s+)(as)', bygroups(Operator, Text, Keyword), 'itemtype'), (r'(element|attribute|schema-element|schema-attribute|comment|' - r'text|node|document-node)(\s+)(\()', + r'text|node|document-node|empty-sequence)(\s+)(\()', pushstate_operator_kindtest_callback), (r'(processing-instruction)(\s+)(\()', @@ -2514,8 +3607,9 @@ 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)), @@ -2557,16 +3651,760 @@ class XQueryLexer(ExtendedRegexLexer): (r'(catch)(\s*)(\()(\$)', bygroups(Keyword, Text, Punctuation, Name.Variable), 'varname'), - (r'@' + qname, Name.Attribute), - (r'@\*', Name.Attribute), - (r'@' + ncname, Name.Attribute), + (r'(@'+qname+')', Name.Attribute), + (r'(@'+ncname+')', Name.Attribute), + (r'@\*:'+ncname, Name.Attribute), + (r'(@)', Name.Attribute), (r'//|/|\+|-|;|,|\(|\)', Punctuation), # STANDALONE QNAMES - (qname + r'(?=\s*[{])', Name.Variable, 'qname_braren'), - (qname + r'(?=\s*[(])', Name.Function, 'qname_braren'), - (qname, Name.Variable, 'operator'), + (qname + r'(?=\s*{)', Name.Tag, 'qname_braren'), + (qname + r'(?=\s*\([^:])', Name.Function, 'qname_braren'), + (qname, Name.Tag, 'operator'), ] } + +class DartLexer(RegexLexer): + """ + For `Dart <http://dartlang.org/>`_ source code. + + .. versionadded:: 1.5 + """ + + name = 'Dart' + aliases = ['dart'] + filenames = ['*.dart'] + mimetypes = ['text/x-dart'] + + flags = re.MULTILINE | re.DOTALL + + tokens = { + 'root': [ + include('string_literal'), + (r'#!(.*?)$', Comment.Preproc), + (r'\b(import|export)\b', Keyword, 'import_decl'), + (r'\b(library|source|part of|part)\b', Keyword), + (r'[^\S\n]+', Text), + (r'//.*?\n', Comment.Single), + (r'/\*.*?\*/', Comment.Multiline), + (r'\b(class)\b(\s+)', + bygroups(Keyword.Declaration, Text), 'class'), + (r'\b(assert|break|case|catch|continue|default|do|else|finally|for|' + r'if|in|is|new|return|super|switch|this|throw|try|while)\b', + Keyword), + (r'\b(abstract|const|extends|factory|final|get|implements|' + r'native|operator|set|static|typedef|var)\b', Keyword.Declaration), + (r'\b(bool|double|Dynamic|int|num|Object|String|void)\b', Keyword.Type), + (r'\b(false|null|true)\b', Keyword.Constant), + (r'[~!%^&*+=|?:<>/-]|as\b', Operator), + (r'[a-zA-Z_$][a-zA-Z0-9_]*:', Name.Label), + (r'[a-zA-Z_$][a-zA-Z0-9_]*', Name), + (r'[(){}\[\],.;]', Punctuation), + (r'0[xX][0-9a-fA-F]+', Number.Hex), + # DIGIT+ (‘.’ DIGIT*)? EXPONENT? + (r'\d+(\.\d*)?([eE][+-]?\d+)?', Number), + (r'\.\d+([eE][+-]?\d+)?', Number), # ‘.’ DIGIT+ EXPONENT? + (r'\n', Text) + # pseudo-keyword negate intentionally left out + ], + 'class': [ + (r'[a-zA-Z_$][a-zA-Z0-9_]*', Name.Class, '#pop') + ], + 'import_decl': [ + include('string_literal'), + (r'\s+', Text), + (r'\b(as|show|hide)\b', Keyword), + (r'[a-zA-Z_$][a-zA-Z0-9_]*', Name), + (r'\,', Punctuation), + (r'\;', Punctuation, '#pop') + ], + 'string_literal': [ + # Raw strings. + (r'r"""([\s|\S]*?)"""', String.Double), + (r"r'''([\s|\S]*?)'''", String.Single), + (r'r"(.*?)"', String.Double), + (r"r'(.*?)'", String.Single), + # Normal Strings. + (r'"""', String.Double, 'string_double_multiline'), + (r"'''", String.Single, 'string_single_multiline'), + (r'"', String.Double, 'string_double'), + (r"'", String.Single, 'string_single') + ], + 'string_common': [ + (r"\\(x[0-9A-Fa-f]{2}|u[0-9A-Fa-f]{4}|u\{[0-9A-Fa-f]*\}|[a-z\'\"$\\])", + String.Escape), + (r'(\$)([a-zA-Z_][a-zA-Z0-9_]*)', bygroups(String.Interpol, Name)), + (r'(\$\{)(.*?)(\})', + bygroups(String.Interpol, using(this), String.Interpol)) + ], + 'string_double': [ + (r'"', String.Double, '#pop'), + (r'[^\"$\\\n]+', String.Double), + include('string_common'), + (r'\$+', String.Double) + ], + 'string_double_multiline': [ + (r'"""', String.Double, '#pop'), + (r'[^\"$\\]+', String.Double), + include('string_common'), + (r'(\$|\")+', String.Double) + ], + 'string_single': [ + (r"'", String.Single, '#pop'), + (r"[^\'$\\\n]+", String.Single), + include('string_common'), + (r'\$+', String.Single) + ], + 'string_single_multiline': [ + (r"'''", String.Single, '#pop'), + (r'[^\'$\\]+', String.Single), + include('string_common'), + (r'(\$|\')+', String.Single) + ] + } + + +class TypeScriptLexer(RegexLexer): + """ + For `TypeScript <http://typescriptlang.org/>`_ source code. + + .. versionadded:: 1.6 + """ + + name = 'TypeScript' + aliases = ['ts'] + filenames = ['*.ts'] + mimetypes = ['text/x-typescript'] + + flags = re.DOTALL + tokens = { + 'commentsandwhitespace': [ + (r'\s+', Text), + (r'<!--', Comment), + (r'//.*?\n', Comment.Single), + (r'/\*.*?\*/', Comment.Multiline) + ], + 'slashstartsregex': [ + include('commentsandwhitespace'), + (r'/(\\.|[^[/\\\n]|\[(\\.|[^\]\\\n])*])+/' + r'([gim]+\b|\B)', String.Regex, '#pop'), + (r'(?=/)', Text, ('#pop', 'badregex')), + (r'', Text, '#pop') + ], + 'badregex': [ + (r'\n', Text, '#pop') + ], + 'root': [ + (r'^(?=\s|/|<!--)', Text, 'slashstartsregex'), + include('commentsandwhitespace'), + (r'\+\+|--|~|&&|\?|:|\|\||\\(?=\n)|' + r'(<<|>>>?|==?|!=?|[-<>+*%&\|\^/])=?', Operator, 'slashstartsregex'), + (r'[{(\[;,]', Punctuation, 'slashstartsregex'), + (r'[})\].]', Punctuation), + (r'(for|in|while|do|break|return|continue|switch|case|default|if|else|' + r'throw|try|catch|finally|new|delete|typeof|instanceof|void|' + r'this)\b', Keyword, 'slashstartsregex'), + (r'(var|let|with|function)\b', Keyword.Declaration, 'slashstartsregex'), + (r'(abstract|boolean|byte|char|class|const|debugger|double|enum|export|' + r'extends|final|float|goto|implements|import|int|interface|long|native|' + r'package|private|protected|public|short|static|super|synchronized|throws|' + r'transient|volatile)\b', Keyword.Reserved), + (r'(true|false|null|NaN|Infinity|undefined)\b', Keyword.Constant), + (r'(Array|Boolean|Date|Error|Function|Math|netscape|' + r'Number|Object|Packages|RegExp|String|sun|decodeURI|' + r'decodeURIComponent|encodeURI|encodeURIComponent|' + r'Error|eval|isFinite|isNaN|parseFloat|parseInt|document|this|' + r'window)\b', Name.Builtin), + # Match stuff like: module name {...} + (r'\b(module)(\s*)(\s*[a-zA-Z0-9_?.$][\w?.$]*)(\s*)', + bygroups(Keyword.Reserved, Text, Name.Other, Text), 'slashstartsregex'), + # Match variable type keywords + (r'\b(string|bool|number)\b', Keyword.Type), + # Match stuff like: constructor + (r'\b(constructor|declare|interface|as|AS)\b', Keyword.Reserved), + # Match stuff like: super(argument, list) + (r'(super)(\s*)(\([a-zA-Z0-9,_?.$\s]+\s*\))', + bygroups(Keyword.Reserved, Text), 'slashstartsregex'), + # Match stuff like: function() {...} + (r'([a-zA-Z_?.$][\w?.$]*)\(\) \{', Name.Other, 'slashstartsregex'), + # Match stuff like: (function: return type) + (r'([a-zA-Z0-9_?.$][\w?.$]*)(\s*:\s*)([a-zA-Z0-9_?.$][\w?.$]*)', + bygroups(Name.Other, Text, Keyword.Type)), + (r'[$a-zA-Z_][a-zA-Z0-9_]*', Name.Other), + (r'[0-9][0-9]*\.[0-9]+([eE][0-9]+)?[fd]?', Number.Float), + (r'0x[0-9a-fA-F]+', Number.Hex), + (r'[0-9]+', Number.Integer), + (r'"(\\\\|\\"|[^"])*"', String.Double), + (r"'(\\\\|\\'|[^'])*'", String.Single), + ] + } + + +class LassoLexer(RegexLexer): + """ + For `Lasso <http://www.lassosoft.com/>`_ source code, covering both Lasso 9 + syntax and LassoScript for Lasso 8.6 and earlier. For Lasso embedded in + HTML, use the `LassoHtmlLexer`. + + Additional options accepted: + + `builtinshighlighting` + If given and ``True``, highlight builtin types, traits, methods, and + members (default: ``True``). + `requiredelimiters` + If given and ``True``, only highlight code between delimiters as Lasso + (default: ``False``). + + .. versionadded:: 1.6 + """ + + name = 'Lasso' + aliases = ['lasso', 'lassoscript'] + filenames = ['*.lasso', '*.lasso[89]'] + alias_filenames = ['*.incl', '*.inc', '*.las'] + mimetypes = ['text/x-lasso'] + flags = re.IGNORECASE | re.DOTALL | re.MULTILINE + + tokens = { + 'root': [ + (r'^#!.+lasso9\b', Comment.Preproc, 'lasso'), + (r'\[no_square_brackets\]', Comment.Preproc, 'nosquarebrackets'), + (r'\[noprocess\]', Comment.Preproc, ('delimiters', 'noprocess')), + (r'\[', Comment.Preproc, ('delimiters', 'squarebrackets')), + (r'<\?(LassoScript|lasso|=)', Comment.Preproc, + ('delimiters', 'anglebrackets')), + (r'<(!--.*?-->)?', Other, 'delimiters'), + (r'\s+', Other), + (r'', Other, ('delimiters', 'lassofile')), + ], + 'delimiters': [ + (r'\[no_square_brackets\]', Comment.Preproc, 'nosquarebrackets'), + (r'\[noprocess\]', Comment.Preproc, 'noprocess'), + (r'\[', Comment.Preproc, 'squarebrackets'), + (r'<\?(LassoScript|lasso|=)', Comment.Preproc, 'anglebrackets'), + (r'<(!--.*?-->)?', Other), + (r'[^[<]+', Other), + ], + 'nosquarebrackets': [ + (r'<\?(LassoScript|lasso|=)', Comment.Preproc, 'anglebrackets'), + (r'<', Other), + (r'[^<]+', Other), + ], + 'noprocess': [ + (r'\[/noprocess\]', Comment.Preproc, '#pop'), + (r'\[', Other), + (r'[^[]', Other), + ], + 'squarebrackets': [ + (r'\]', Comment.Preproc, '#pop'), + include('lasso'), + ], + 'anglebrackets': [ + (r'\?>', Comment.Preproc, '#pop'), + include('lasso'), + ], + 'lassofile': [ + (r'\]|\?>', Comment.Preproc, '#pop'), + include('lasso'), + ], + 'whitespacecomments': [ + (r'\s+', Text), + (r'//.*?\n', Comment.Single), + (r'/\*\*!.*?\*/', String.Doc), + (r'/\*.*?\*/', Comment.Multiline), + ], + 'lasso': [ + # whitespace/comments + include('whitespacecomments'), + + # literals + (r'\d*\.\d+(e[+-]?\d+)?', Number.Float), + (r'0x[\da-f]+', Number.Hex), + (r'\d+', Number.Integer), + (r'([+-]?)(infinity|NaN)\b', bygroups(Operator, Number)), + (r"'", String.Single, 'singlestring'), + (r'"', String.Double, 'doublestring'), + (r'`[^`]*`', String.Backtick), + + # names + (r'\$[a-z_][\w.]*', Name.Variable), + (r'#([a-z_][\w.]*|\d+)', Name.Variable.Instance), + (r"(\.)('[a-z_][\w.]*')", + bygroups(Name.Builtin.Pseudo, Name.Variable.Class)), + (r"(self)(\s*->\s*)('[a-z_][\w.]*')", + bygroups(Name.Builtin.Pseudo, Operator, Name.Variable.Class)), + (r'(\.\.?)([a-z_][\w.]*(=(?!=))?)', + bygroups(Name.Builtin.Pseudo, Name.Other.Member)), + (r'(->\\?\s*|&\s*)([a-z_][\w.]*(=(?!=))?)', + bygroups(Operator, Name.Other.Member)), + (r'(self|inherited)\b', Name.Builtin.Pseudo), + (r'-[a-z_][\w.]*', Name.Attribute), + (r'::\s*[a-z_][\w.]*', Name.Label), + (r'(error_(code|msg)_\w+|Error_AddError|Error_ColumnRestriction|' + r'Error_DatabaseConnectionUnavailable|Error_DatabaseTimeout|' + r'Error_DeleteError|Error_FieldRestriction|Error_FileNotFound|' + r'Error_InvalidDatabase|Error_InvalidPassword|' + r'Error_InvalidUsername|Error_ModuleNotFound|' + r'Error_NoError|Error_NoPermission|Error_OutOfMemory|' + r'Error_ReqColumnMissing|Error_ReqFieldMissing|' + r'Error_RequiredColumnMissing|Error_RequiredFieldMissing|' + r'Error_UpdateError)\b', Name.Exception), + + # definitions + (r'(define)(\s+)([a-z_][\w.]*)(\s*=>\s*)(type|trait|thread)\b', + bygroups(Keyword.Declaration, Text, Name.Class, Operator, Keyword)), + (r'(define)(\s+)([a-z_][\w.]*)(\s*->\s*)([a-z_][\w.]*=?|[-+*/%])', + bygroups(Keyword.Declaration, Text, Name.Class, Operator, + Name.Function), 'signature'), + (r'(define)(\s+)([a-z_][\w.]*)', + bygroups(Keyword.Declaration, Text, Name.Function), 'signature'), + (r'(public|protected|private|provide)(\s+)(([a-z_][\w.]*=?|[-+*/%])' + r'(?=\s*\())', bygroups(Keyword, Text, Name.Function), + 'signature'), + (r'(public|protected|private|provide)(\s+)([a-z_][\w.]*)', + bygroups(Keyword, Text, Name.Function)), + + # keywords + (r'(true|false|none|minimal|full|all|void)\b', Keyword.Constant), + (r'(local|var|variable|global|data(?=\s))\b', Keyword.Declaration), + (r'(array|date|decimal|duration|integer|map|pair|string|tag|xml|' + r'null|bytes|list|queue|set|stack|staticarray|tie)\b', Keyword.Type), + (r'([a-z_][\w.]*)(\s+)(in)\b', bygroups(Name, Text, Keyword)), + (r'(let|into)(\s+)([a-z_][\w.]*)', bygroups(Keyword, Text, Name)), + (r'require\b', Keyword, 'requiresection'), + (r'(/?)(Namespace_Using)\b', bygroups(Punctuation, Keyword.Namespace)), + (r'(/?)(Cache|Database_Names|Database_SchemaNames|' + r'Database_TableNames|Define_Tag|Define_Type|Email_Batch|' + r'Encode_Set|HTML_Comment|Handle|Handle_Error|Header|If|Inline|' + r'Iterate|LJAX_Target|Link|Link_CurrentAction|Link_CurrentGroup|' + r'Link_CurrentRecord|Link_Detail|Link_FirstGroup|' + r'Link_FirstRecord|Link_LastGroup|Link_LastRecord|Link_NextGroup|' + r'Link_NextRecord|Link_PrevGroup|Link_PrevRecord|Log|Loop|' + r'NoProcess|Output_None|Portal|Private|Protect|Records|Referer|' + r'Referrer|Repeating|ResultSet|Rows|Search_Args|Search_Arguments|' + r'Select|Sort_Args|Sort_Arguments|Thread_Atomic|Value_List|While|' + r'Abort|Case|Else|If_Empty|If_False|If_Null|If_True|Loop_Abort|' + r'Loop_Continue|Loop_Count|Params|Params_Up|Return|Return_Value|' + r'Run_Children|SOAP_DefineTag|SOAP_LastRequest|SOAP_LastResponse|' + r'Tag_Name|ascending|average|by|define|descending|do|equals|' + r'frozen|group|handle_failure|import|in|into|join|let|match|max|' + r'min|on|order|parent|protected|provide|public|require|returnhome|' + r'skip|split_thread|sum|take|thread|to|trait|type|where|with|' + r'yield|yieldhome)\b', + bygroups(Punctuation, Keyword)), + + # other + (r',', Punctuation, 'commamember'), + (r'(and|or|not)\b', Operator.Word), + (r'([a-z_][\w.]*)(\s*::\s*[a-z_][\w.]*)?(\s*=(?!=))', + bygroups(Name, Name.Label, Operator)), + (r'(/?)([\w.]+)', bygroups(Punctuation, Name.Other)), + (r'(=)(n?bw|n?ew|n?cn|lte?|gte?|n?eq|n?rx|ft)\b', + bygroups(Operator, Operator.Word)), + (r':=|[-+*/%=<>&|!?\\]+', Operator), + (r'[{}():;,@^]', Punctuation), + ], + 'singlestring': [ + (r"'", String.Single, '#pop'), + (r"[^'\\]+", String.Single), + include('escape'), + (r"\\", String.Single), + ], + 'doublestring': [ + (r'"', String.Double, '#pop'), + (r'[^"\\]+', String.Double), + include('escape'), + (r'\\', String.Double), + ], + 'escape': [ + (r'\\(U[\da-f]{8}|u[\da-f]{4}|x[\da-f]{1,2}|[0-7]{1,3}|:[^:]+:|' + r'[abefnrtv?\"\'\\]|$)', String.Escape), + ], + 'signature': [ + (r'=>', Operator, '#pop'), + (r'\)', Punctuation, '#pop'), + (r'[(,]', Punctuation, 'parameter'), + include('lasso'), + ], + 'parameter': [ + (r'\)', Punctuation, '#pop'), + (r'-?[a-z_][\w.]*', Name.Attribute, '#pop'), + (r'\.\.\.', Name.Builtin.Pseudo), + include('lasso'), + ], + 'requiresection': [ + (r'(([a-z_][\w.]*=?|[-+*/%])(?=\s*\())', Name, 'requiresignature'), + (r'(([a-z_][\w.]*=?|[-+*/%])(?=(\s*::\s*[\w.]+)?\s*,))', Name), + (r'[a-z_][\w.]*=?|[-+*/%]', Name, '#pop'), + (r'::\s*[a-z_][\w.]*', Name.Label), + (r',', Punctuation), + include('whitespacecomments'), + ], + 'requiresignature': [ + (r'(\)(?=(\s*::\s*[\w.]+)?\s*,))', Punctuation, '#pop'), + (r'\)', Punctuation, '#pop:2'), + (r'-?[a-z_][\w.]*', Name.Attribute), + (r'::\s*[a-z_][\w.]*', Name.Label), + (r'\.\.\.', Name.Builtin.Pseudo), + (r'[(,]', Punctuation), + include('whitespacecomments'), + ], + 'commamember': [ + (r'(([a-z_][\w.]*=?|[-+*/%])' + r'(?=\s*(\(([^()]*\([^()]*\))*[^)]*\)\s*)?(::[\w.\s]+)?=>))', + Name.Function, 'signature'), + include('whitespacecomments'), + (r'', Text, '#pop'), + ], + } + + def __init__(self, **options): + self.builtinshighlighting = get_bool_opt( + options, 'builtinshighlighting', True) + self.requiredelimiters = get_bool_opt( + options, 'requiredelimiters', False) + + self._builtins = set() + self._members = set() + if self.builtinshighlighting: + from pygments.lexers._lassobuiltins import BUILTINS, MEMBERS + for key, value in iteritems(BUILTINS): + self._builtins.update(value) + for key, value in iteritems(MEMBERS): + self._members.update(value) + RegexLexer.__init__(self, **options) + + def get_tokens_unprocessed(self, text): + stack = ['root'] + if self.requiredelimiters: + stack.append('delimiters') + for index, token, value in \ + RegexLexer.get_tokens_unprocessed(self, text, stack): + if (token is Name.Other and value.lower() in self._builtins or + token is Name.Other.Member and + value.lower().rstrip('=') in self._members): + yield index, Name.Builtin, value + continue + yield index, token, value + + def analyse_text(text): + rv = 0.0 + if 'bin/lasso9' in text: + rv += 0.8 + if re.search(r'<\?(=|lasso)|\A\[', text, re.I): + rv += 0.4 + if re.search(r'local\(', text, re.I): + rv += 0.4 + if '?>' in text: + rv += 0.1 + return rv + + +class QmlLexer(RegexLexer): + """ + For QML files. See http://doc.qt.digia.com/4.7/qdeclarativeintroduction.html. + + .. versionadded:: 1.6 + """ + + # QML is based on javascript, so much of this is taken from the + # JavascriptLexer above. + + name = 'QML' + aliases = ['qml'] + filenames = ['*.qml',] + mimetypes = [ 'application/x-qml',] + + + # pasted from JavascriptLexer, with some additions + flags = re.DOTALL + tokens = { + 'commentsandwhitespace': [ + (r'\s+', Text), + (r'<!--', Comment), + (r'//.*?\n', Comment.Single), + (r'/\*.*?\*/', Comment.Multiline) + ], + 'slashstartsregex': [ + include('commentsandwhitespace'), + (r'/(\\.|[^[/\\\n]|\[(\\.|[^\]\\\n])*])+/' + r'([gim]+\b|\B)', String.Regex, '#pop'), + (r'(?=/)', Text, ('#pop', 'badregex')), + (r'', Text, '#pop') + ], + 'badregex': [ + (r'\n', Text, '#pop') + ], + 'root' : [ + (r'^(?=\s|/|<!--)', Text, 'slashstartsregex'), + include('commentsandwhitespace'), + (r'\+\+|--|~|&&|\?|:|\|\||\\(?=\n)|' + r'(<<|>>>?|==?|!=?|[-<>+*%&\|\^/])=?', Operator, 'slashstartsregex'), + (r'[{(\[;,]', Punctuation, 'slashstartsregex'), + (r'[})\].]', Punctuation), + + # QML insertions + (r'\bid\s*:\s*[A-Za-z][_A-Za-z.0-9]*',Keyword.Declaration, + 'slashstartsregex'), + (r'\b[A-Za-z][_A-Za-z.0-9]*\s*:',Keyword, 'slashstartsregex'), + + # the rest from JavascriptLexer + (r'(for|in|while|do|break|return|continue|switch|case|default|if|else|' + r'throw|try|catch|finally|new|delete|typeof|instanceof|void|' + r'this)\b', Keyword, 'slashstartsregex'), + (r'(var|let|with|function)\b', Keyword.Declaration, 'slashstartsregex'), + (r'(abstract|boolean|byte|char|class|const|debugger|double|enum|export|' + r'extends|final|float|goto|implements|import|int|interface|long|native|' + r'package|private|protected|public|short|static|super|synchronized|throws|' + r'transient|volatile)\b', Keyword.Reserved), + (r'(true|false|null|NaN|Infinity|undefined)\b', Keyword.Constant), + (r'(Array|Boolean|Date|Error|Function|Math|netscape|' + r'Number|Object|Packages|RegExp|String|sun|decodeURI|' + r'decodeURIComponent|encodeURI|encodeURIComponent|' + r'Error|eval|isFinite|isNaN|parseFloat|parseInt|document|this|' + r'window)\b', Name.Builtin), + (r'[$a-zA-Z_][a-zA-Z0-9_]*', Name.Other), + (r'[0-9][0-9]*\.[0-9]+([eE][0-9]+)?[fd]?', Number.Float), + (r'0x[0-9a-fA-F]+', Number.Hex), + (r'[0-9]+', Number.Integer), + (r'"(\\\\|\\"|[^"])*"', String.Double), + (r"'(\\\\|\\'|[^'])*'", String.Single), + ] + } + + +class CirruLexer(RegexLexer): + """ + Syntax rules of Cirru can be found at: + http://grammar.cirru.org/ + + * using ``()`` to markup blocks, but limited in the same line + * using ``""`` to markup strings, allow ``\`` to escape + * using ``$`` as a shorthand for ``()`` till indentation end or ``)`` + * using indentations for create nesting + + .. versionadded:: 2.0 + """ + + name = 'Cirru' + aliases = ['cirru'] + filenames = ['*.cirru', '*.cr'] + mimetypes = ['text/x-cirru'] + flags = re.MULTILINE + + tokens = { + 'string': [ + (r'[^"\\\n]', String), + (r'\\', String.Escape, 'escape'), + (r'"', String, '#pop'), + ], + 'escape': [ + (r'.', String.Escape, '#pop'), + ], + 'function': [ + (r'[\w-][^\s\(\)\"]*', Name.Function, '#pop'), + (r'\)', Operator, '#pop'), + (r'(?=\n)', Text, '#pop'), + (r'\(', Operator, '#push'), + (r'"', String, ('#pop', 'string')), + (r'\s+', Text.Whitespace), + (r'\,', Operator, '#pop'), + ], + 'line': [ + (r'^\B', Text.Whitespace, 'function'), + (r'\$', Operator, 'function'), + (r'\(', Operator, 'function'), + (r'\)', Operator), + (r'(?=\n)', Text, '#pop'), + (r'\n', Text, '#pop'), + (r'"', String, 'string'), + (r'\s+', Text.Whitespace), + (r'[\d\.]+', Number), + (r'[\w-][^\"\(\)\s]*', Name.Variable), + (r'--', Comment.Single) + ], + 'root': [ + (r'^\s*', Text.Whitespace, ('line', 'function')), + (r'^\s+$', Text.Whitespace), + ] + } + + +class MaskLexer(RegexLexer): + """ + For `Mask <http://github.com/atmajs/MaskJS>`__ markup. + + .. versionadded:: 2.0 + """ + name = 'Mask' + aliases = ['mask'] + filenames = ['*.mask'] + mimetypes = ['text/x-mask'] + + flags = re.MULTILINE | re.IGNORECASE | re.DOTALL + tokens = { + 'root': [ + (r'\s+', Text), + (r'//.*?\n', Comment.Single), + (r'/\*.*?\*/', Comment.Multiline), + (r'[\{\};>]', Punctuation), + (r"'''", String, 'string-trpl-single'), + (r'"""', String, 'string-trpl-double'), + (r"'", String, 'string-single'), + (r'"', String, 'string-double'), + (r'([\w-]+)', Name.Tag, 'node'), + (r'([^\.#;{>\s]+)', Name.Class, 'node'), + (r'(#[\w_-]+)', Name.Function, 'node'), + (r'(\.[\w_-]+)', Name.Variable.Class, 'node') + ], + 'string-base': [ + (r'\\.', String.Escape), + (r'~\[', String.Interpol, 'interpolation'), + (r'.', String.Single), + ], + 'string-single':[ + (r"'", String.Single, '#pop'), + include('string-base') + ], + 'string-double':[ + (r'"', String.Single, '#pop'), + include('string-base') + ], + 'string-trpl-single':[ + (r"'''", String.Single, '#pop'), + include('string-base') + ], + 'string-trpl-double':[ + (r'"""', String.Single, '#pop'), + include('string-base') + ], + 'interpolation': [ + (r'\]', String.Interpol, '#pop'), + (r'\s*:', String.Interpol, 'expression'), + (r'\s*\w+:', Name.Other), + (r'[^\]]+', String.Interpol) + ], + 'expression': [ + (r'[^\]]+', using(JavascriptLexer), '#pop') + ], + 'node': [ + (r'\s+', Text), + (r'\.', Name.Variable.Class, 'node-class'), + (r'\#', Name.Function, 'node-id'), + (r'style[ \t]*=', Name.Attribute, 'node-attr-style-value'), + (r'[\w_:-]+[ \t]*=', Name.Attribute, 'node-attr-value'), + (r'[\w_:-]+', Name.Attribute), + (r'[>{;]', Punctuation, '#pop') + ], + 'node-class': [ + (r'[\w-]+', Name.Variable.Class), + (r'~\[', String.Interpol, 'interpolation'), + (r'', Text, '#pop') + ], + 'node-id': [ + (r'[\w-]+', Name.Function), + (r'~\[', String.Interpol, 'interpolation'), + (r'', Text, '#pop') + ], + 'node-attr-value':[ + (r'\s+', Text), + (r'[\w_]+', Name.Variable, '#pop'), + (r"'", String, 'string-single-pop2'), + (r'"', String, 'string-double-pop2'), + (r'', Text, '#pop') + ], + 'node-attr-style-value':[ + (r'\s+', Text), + (r"'", String.Single, 'css-single-end'), + (r'"', String.Single, 'css-double-end'), + include('node-attr-value') + ], + 'css-base': [ + (r'\s+', Text), + (r"[;]", Punctuation), + (r"[\w\-_]+\s*:", Name.Builtin) + ], + 'css-single-end': [ + include('css-base'), + (r"'", String.Single, '#pop:2'), + (r"[^;']+", Name.Entity) + ], + 'css-double-end': [ + include('css-base'), + (r'"', String.Single, '#pop:2'), + (r"[^;\"]+", Name.Entity) + ], + 'string-single-pop2':[ + (r"'", String.Single, '#pop:2'), + include('string-base') + ], + 'string-double-pop2':[ + (r'"', String.Single, '#pop:2'), + include('string-base') + ], + } + + +class ZephirLexer(RegexLexer): + """ + For `Zephir language <http://zephir-lang.com/>`_ source code. + + Zephir is a compiled high level language aimed + to the creation of C-extensions for PHP. + + .. versionadded:: 2.0 + """ + + name = 'Zephir' + aliases = ['zephir'] + filenames = ['*.zep'] + + zephir_keywords = [ 'fetch', 'echo', 'isset', 'empty'] + zephir_type = [ 'bit', 'bits' , 'string' ] + + flags = re.DOTALL | re.MULTILINE + + tokens = { + 'commentsandwhitespace': [ + (r'\s+', Text), + (r'//.*?\n', Comment.Single), + (r'/\*.*?\*/', Comment.Multiline) + ], + 'slashstartsregex': [ + include('commentsandwhitespace'), + (r'/(\\.|[^[/\\\n]|\[(\\.|[^\]\\\n])*])+/' + r'([gim]+\b|\B)', String.Regex, '#pop'), + (r'', Text, '#pop') + ], + 'badregex': [ + (r'\n', Text, '#pop') + ], + 'root': [ + (r'^(?=\s|/|<!--)', Text, 'slashstartsregex'), + include('commentsandwhitespace'), + (r'\+\+|--|~|&&|\?|:|\|\||\\(?=\n)|' + r'(<<|>>>?|==?|!=?|->|[-<>+*%&\|\^/])=?', Operator, 'slashstartsregex'), + (r'[{(\[;,]', Punctuation, 'slashstartsregex'), + (r'[})\].]', Punctuation), + (r'(for|in|while|do|break|return|continue|switch|case|default|if|else|loop|require|inline|' + r'throw|try|catch|finally|new|delete|typeof|instanceof|void|namespace|use|extends|' + r'this|fetch|isset|unset|echo|fetch|likely|unlikely|empty)\b', Keyword, 'slashstartsregex'), + (r'(var|let|with|function)\b', Keyword.Declaration, 'slashstartsregex'), + (r'(abstract|boolean|bool|char|class|const|double|enum|export|' + r'extends|final|float|goto|implements|import|int|string|interface|long|ulong|char|uchar|native|unsigned|' + r'private|protected|public|short|static|self|throws|reverse|' + r'transient|volatile)\b', Keyword.Reserved), + (r'(true|false|null|undefined)\b', Keyword.Constant), + (r'(Array|Boolean|Date|_REQUEST|_COOKIE|_SESSION|' + r'_GET|_POST|_SERVER|this|stdClass|range|count|iterator|' + r'window)\b', Name.Builtin), + (r'[$a-zA-Z_][a-zA-Z0-9_\\]*', Name.Other), + (r'[0-9][0-9]*\.[0-9]+([eE][0-9]+)?[fd]?', Number.Float), + (r'0x[0-9a-fA-F]+', Number.Hex), + (r'[0-9]+', Number.Integer), + (r'"(\\\\|\\"|[^"])*"', String.Double), + (r"'(\\\\|\\'|[^'])*'", String.Single), + ] + } |