diff options
Diffstat (limited to 'pygments/lexers/other.py')
| -rw-r--r-- | pygments/lexers/other.py | 385 |
1 files changed, 302 insertions, 83 deletions
diff --git a/pygments/lexers/other.py b/pygments/lexers/other.py index 8491d19d..80b06b28 100644 --- a/pygments/lexers/other.py +++ b/pygments/lexers/other.py @@ -5,7 +5,7 @@ Lexers for other languages. - :copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2014 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ @@ -14,7 +14,8 @@ import re from pygments.lexer import RegexLexer, include, bygroups, using, \ this, combined, ExtendedRegexLexer from pygments.token import Error, Punctuation, Literal, Token, \ - Text, Comment, Operator, Keyword, Name, String, Number, Generic + Text, Comment, Operator, Keyword, Name, String, Number, Generic, \ + Whitespace from pygments.util import get_bool_opt from pygments.lexers.web import HtmlLexer @@ -35,7 +36,7 @@ __all__ = ['BrainfuckLexer', 'BefungeLexer', 'RedcodeLexer', 'MOOCodeLexer', 'ECLLexer', 'UrbiscriptLexer', 'OpenEdgeLexer', 'BroLexer', 'MscgenLexer', 'KconfigLexer', 'VGLLexer', 'SourcePawnLexer', 'RobotFrameworkLexer', 'PuppetLexer', 'NSISLexer', 'RPMSpecLexer', - 'CbmBasicV2Lexer', 'AutoItLexer'] + 'CbmBasicV2Lexer', 'AutoItLexer', 'RexxLexer', 'APLLexer'] class ECLLexer(RegexLexer): @@ -44,7 +45,7 @@ class ECLLexer(RegexLexer): <http://hpccsystems.com/community/docs/ecl-language-reference/html>`_ language. - *New in Pygments 1.5.* + .. versionadded:: 1.5 """ name = 'ECL' @@ -175,7 +176,7 @@ class BefungeLexer(RegexLexer): Lexer for the esoteric `Befunge <http://en.wikipedia.org/wiki/Befunge>`_ language. - *New in Pygments 0.7.* + .. versionadded:: 0.7 """ name = 'Befunge' aliases = ['befunge'] @@ -205,7 +206,7 @@ class RedcodeLexer(RegexLexer): A simple Redcode lexer based on ICWS'94. Contributed by Adam Blinkinsop <blinks@acm.org>. - *New in Pygments 0.8.* + .. versionadded:: 0.8 """ name = 'Redcode' aliases = ['redcode'] @@ -241,11 +242,11 @@ class MOOCodeLexer(RegexLexer): For `MOOCode <http://www.moo.mud.org/>`_ (the MOO scripting language). - *New in Pygments 0.9.* + .. versionadded:: 0.9 """ name = 'MOOCode' filenames = ['*.moo'] - aliases = ['moocode'] + aliases = ['moocode', 'moo'] mimetypes = ['text/x-moocode'] tokens = { @@ -285,11 +286,11 @@ class SmalltalkLexer(RegexLexer): Contributed by Stefan Matthias Aust. Rewritten by Nils Winter. - *New in Pygments 0.10.* + .. versionadded:: 0.10 """ name = 'Smalltalk' filenames = ['*.st'] - aliases = ['smalltalk', 'squeak'] + aliases = ['smalltalk', 'squeak', 'st'] mimetypes = ['text/x-smalltalk'] tokens = { @@ -363,7 +364,7 @@ class SmalltalkLexer(RegexLexer): include('literals'), ], 'afterobject' : [ - (r'! !$', Keyword , '#pop'), # squeak chunk delimeter + (r'! !$', Keyword , '#pop'), # squeak chunk delimiter include('whitespaces'), (r'\b(ifTrue:|ifFalse:|whileTrue:|whileFalse:|timesRepeat:)', Name.Builtin, '#pop'), @@ -404,7 +405,7 @@ class LogtalkLexer(RegexLexer): """ For `Logtalk <http://logtalk.org/>`_ source code. - *New in Pygments 0.10.* + .. versionadded:: 0.10 """ name = 'Logtalk' @@ -632,7 +633,7 @@ class GnuplotLexer(RegexLexer): """ For `Gnuplot <http://gnuplot.info/>`_ plotting scripts. - *New in Pygments 0.11.* + .. versionadded:: 0.11 """ name = 'Gnuplot' @@ -791,7 +792,7 @@ class PovrayLexer(RegexLexer): """ For `Persistence of Vision Raytracer <http://www.povray.org/>`_ files. - *New in Pygments 0.11.* + .. versionadded:: 0.11 """ name = 'POVRay' aliases = ['pov'] @@ -1149,18 +1150,18 @@ class AppleScriptLexer(RegexLexer): tokens = { 'root': [ (r'\s+', Text), - (ur'¬\n', String.Escape), + (u'¬\\n', String.Escape), (r"'s\s+", Text), # This is a possessive, consider moving (r'(--|#).*?$', Comment), (r'\(\*', Comment.Multiline, 'comment'), (r'[\(\){}!,.:]', Punctuation), - (ur'(«)([^»]+)(»)', + (u'(«)([^»]+)(»)', bygroups(Text, Name.Builtin, Text)), (r'\b((?:considering|ignoring)\s*)' r'(application responses|case|diacriticals|hyphens|' r'numeric strings|punctuation|white space)', bygroups(Keyword, Name.Builtin)), - (ur'(-|\*|\+|&|≠|>=?|<=?|=|≥|≤|/|÷|\^)', Operator), + (u'(-|\\*|\\+|&|≠|>=?|<=?|=|≥|≤|/|÷|\\^)', Operator), (r"\b(%s)\b" % '|'.join(Operators), Operator.Word), (r'^(\s*(?:on|end)\s+)' r'(%s)' % '|'.join(StudioEvents[::-1]), @@ -1197,7 +1198,7 @@ class ModelicaLexer(RegexLexer): """ For `Modelica <http://www.modelica.org/>`_ source code. - *New in Pygments 1.1.* + .. versionadded:: 1.1 """ name = 'Modelica' aliases = ['modelica'] @@ -1220,11 +1221,16 @@ class ModelicaLexer(RegexLexer): (r'(\d+\.\d*|\.\d+)', Number.Float), (r'\d+[Ll]?', Number.Integer), (r'[~!%^&*+=|?:<>/-]', Operator), - (r'[()\[\]{},.;]', Punctuation), (r'(true|false|NULL|Real|Integer|Boolean)\b', Name.Builtin), - (r"([a-zA-Z_][\w]*|'[a-zA-Z_\+\-\*\/\^][\w]*')" - r"(\.([a-zA-Z_][\w]*|'[a-zA-Z_\+\-\*\/\^][\w]*'))+", Name.Class), - (r"('[\w\+\-\*\/\^]+'|\w+)", Name), + (r'([a-zA-Z_][\w]*|[\'][^\']+[\'])' + r'([\[\d,:\]]*)' + r'(\.([a-zA-Z_][\w]*|[\'][^\']+[\']))+' + r'([\[\d,:\]]*)', Name.Class), + (r'([a-zA-Z_][\w]*|[\'][^\']+[\'])' + r'([\[\d,:\]]+)', Name.Class), + (r'(\'[\w\+\-\*\/\^]+\'|\w+)', Name), + (r'[()\[\]{},.;]', Punctuation), + (r'\'', Name, 'quoted_ident'), ], 'root': [ include('whitespace'), @@ -1238,7 +1244,7 @@ class ModelicaLexer(RegexLexer): 'keywords': [ (r'(algorithm|annotation|break|connect|constant|constrainedby|' r'discrete|each|else|elseif|elsewhen|encapsulated|enumeration|' - r'end|equation|exit|expandable|extends|' + r'equation|exit|expandable|extends|' r'external|false|final|flow|for|if|import|impure|in|initial\sequation|' r'inner|input|loop|nondiscrete|outer|output|parameter|partial|' r'protected|public|pure|redeclare|replaceable|stream|time|then|true|' @@ -1251,15 +1257,20 @@ class ModelicaLexer(RegexLexer): r'tanh|zeros)\b', Name.Function), ], 'operators': [ - (r'(actualStream|and|assert|cardinality|change|Clock|delay|der|edge|' - r'hold|homotopy|initial|inStream|noEvent|not|or|pre|previous|reinit|' - r'return|sample|smooth|spatialDistribution|subSample|terminal|' + (r'(actualStream|and|assert|backSample|cardinality|change|Clock|' + r'delay|der|edge|hold|homotopy|initial|inStream|noClock|noEvent|' + r'not|or|pre|previous|reinit|return|sample|smooth|' + r'spatialDistribution|shiftSample|subSample|superSample|terminal|' r'terminate)\b', Name.Builtin), ], 'classes': [ - (r'(block|class|connector|function|model|package|' - r'record|type)(\s+)([A-Za-z_]+)', - bygroups(Keyword, Text, Name.Class)) + (r'(block|class|connector|end|function|model|package|' + r'record|type)(\s+)((?!if|when|while)[A-Za-z_]\w*|[\'][^\']+[\'])([;]?)', + bygroups(Keyword, Text, Name.Class, Text)) + ], + 'quoted_ident': [ + (r'\'', Name, '#pop'), + (r'[^\']+', Name), # all other characters ], 'string': [ (r'"', String, '#pop'), @@ -1270,7 +1281,7 @@ class ModelicaLexer(RegexLexer): (r'\\', String), # stray backslash ], 'html-content': [ - (r'<\s*/\s*html\s*>', Name.Tag, '#pop'), + (r'<\s*/\s*html\s*>"', Name.Tag, '#pop'), (r'.+?(?=<\s*/\s*html\s*>)', using(HtmlLexer)), ] } @@ -1280,7 +1291,7 @@ class RebolLexer(RegexLexer): """ A `REBOL <http://www.rebol.com/>`_ lexer. - *New in Pygments 1.1.* + .. versionadded:: 1.1 """ name = 'REBOL' aliases = ['rebol'] @@ -1380,9 +1391,9 @@ class RebolLexer(RegexLexer): tokens = { 'root': [ - (r'REBOL', Generic.Strong, 'script'), - (r'R', Comment), (r'[^R]+', Comment), + (r'REBOL\s+\[', Generic.Strong, 'script'), + (r'R', Comment) ], 'script': [ (r'\s+', Text), @@ -1399,8 +1410,8 @@ class RebolLexer(RegexLexer): (r'%[^(\^{^")\s\[\]]+', Name.Decorator), (r'[+-]?([a-zA-Z]{1,3})?\$\d+(\.\d+)?', Number.Float), # money (r'[+-]?\d+\:\d+(\:\d+)?(\.\d+)?', String.Other), # time - (r'\d+\-[0-9a-zA-Z]+\-\d+(\/\d+\:\d+(\:\d+)?' - r'([\.\d+]?([+-]?\d+:\d+)?)?)?', String.Other), # date + (r'\d+[\-\/][0-9a-zA-Z]+[\-\/]\d+(\/\d+\:\d+((\:\d+)?' + r'([\.\d+]?([+-]?\d+:\d+)?)?)?)?', String.Other), # date (r'\d+(\.\d+)+\.\d+', Keyword.Constant), # tuple (r'\d+[xX]\d+', Keyword.Constant), # pair (r'[+-]?\d+(\'\d+)?([\.,]\d*)?[eE][+-]?\d+', Number.Float), @@ -1492,13 +1503,23 @@ class RebolLexer(RegexLexer): (r'[^(\[\])]+', Comment), ], } + def analyse_text(text): + """ + Check if code contains REBOL header and so it probably not R code + """ + if re.match(r'^\s*REBOL\s*\[', text, re.IGNORECASE): + # The code starts with REBOL header + return 1.0 + elif re.search(r'\s*REBOL\s*[', text, re.IGNORECASE): + # The code contains REBOL header but also some text before it + return 0.5 class ABAPLexer(RegexLexer): """ Lexer for ABAP, SAP's integrated language. - *New in Pygments 1.1.* + .. versionadded:: 1.1 """ name = 'ABAP' aliases = ['abap'] @@ -1679,6 +1700,7 @@ class ABAPLexer(RegexLexer): # because < and > are part of field symbols. (r'[?*<>=\-+]', Operator), (r"'(''|[^'])*'", String.Single), + (r"`([^`])*`", String.Single), (r'[/;:()\[\],\.]', Punctuation) ], } @@ -1745,17 +1767,17 @@ class GherkinLexer(RegexLexer): """ For `Gherkin <http://github.com/aslakhellesoy/gherkin/>` syntax. - *New in Pygments 1.2.* + .. versionadded:: 1.2 """ name = 'Gherkin' - aliases = ['Cucumber', 'cucumber', 'Gherkin', 'gherkin'] + aliases = ['cucumber', 'gherkin'] filenames = ['*.feature'] mimetypes = ['text/x-gherkin'] - feature_keywords = ur'^(기능|機能|功能|フィーチャ|خاصية|תכונה|Функціонал|Функционалност|Функционал|Фича|Особина|Могућност|Özellik|Właściwość|Tính năng|Trajto|Savybė|Požiadavka|Požadavek|Osobina|Ominaisuus|Omadus|OH HAI|Mogućnost|Mogucnost|Jellemző|Fīča|Funzionalità|Funktionalität|Funkcionalnost|Funkcionalitāte|Funcționalitate|Functionaliteit|Functionalitate|Funcionalitat|Funcionalidade|Fonctionnalité|Fitur|Feature|Egenskap|Egenskab|Crikey|Característica|Arwedd)(:)(.*)$' - feature_element_keywords = ur'^(\s*)(시나리오 개요|시나리오|배경|背景|場景大綱|場景|场景大纲|场景|劇本大綱|劇本|テンプレ|シナリオテンプレート|シナリオテンプレ|シナリオアウトライン|シナリオ|سيناريو مخطط|سيناريو|الخلفية|תרחיש|תבנית תרחיש|רקע|Тарих|Сценарій|Сценарио|Сценарий структураси|Сценарий|Структура сценарію|Структура сценарија|Структура сценария|Скица|Рамка на сценарий|Пример|Предыстория|Предистория|Позадина|Передумова|Основа|Концепт|Контекст|Założenia|Wharrimean is|Tình huống|The thing of it is|Tausta|Taust|Tapausaihio|Tapaus|Szenariogrundriss|Szenario|Szablon scenariusza|Stsenaarium|Struktura scenarija|Skica|Skenario konsep|Skenario|Situācija|Senaryo taslağı|Senaryo|Scénář|Scénario|Schema dello scenario|Scenārijs pēc parauga|Scenārijs|Scenár|Scenaro|Scenariusz|Scenariul de şablon|Scenariul de sablon|Scenariu|Scenario Outline|Scenario Amlinellol|Scenario|Scenarijus|Scenarijaus šablonas|Scenarij|Scenarie|Rerefons|Raamstsenaarium|Primer|Pozadí|Pozadina|Pozadie|Plan du scénario|Plan du Scénario|Osnova scénáře|Osnova|Náčrt Scénáře|Náčrt Scenáru|Mate|MISHUN SRSLY|MISHUN|Kịch bản|Konturo de la scenaro|Kontext|Konteksts|Kontekstas|Kontekst|Koncept|Khung tình huống|Khung kịch bản|Háttér|Grundlage|Geçmiş|Forgatókönyv vázlat|Forgatókönyv|Fono|Esquema do Cenário|Esquema do Cenario|Esquema del escenario|Esquema de l\'escenari|Escenario|Escenari|Dis is what went down|Dasar|Contexto|Contexte|Contesto|Condiţii|Conditii|Cenário|Cenario|Cefndir|Bối cảnh|Blokes|Bakgrunn|Bakgrund|Baggrund|Background|B4|Antecedents|Antecedentes|All y\'all|Achtergrond|Abstrakt Scenario|Abstract Scenario)(:)(.*)$' - examples_keywords = ur'^(\s*)(예|例子|例|サンプル|امثلة|דוגמאות|Сценарији|Примери|Приклади|Мисоллар|Значения|Örnekler|Voorbeelden|Variantai|Tapaukset|Scenarios|Scenariji|Scenarijai|Příklady|Példák|Príklady|Przykłady|Primjeri|Primeri|Piemēri|Pavyzdžiai|Paraugs|Juhtumid|Exemplos|Exemples|Exemplele|Exempel|Examples|Esempi|Enghreifftiau|Ekzemploj|Eksempler|Ejemplos|EXAMPLZ|Dữ liệu|Contoh|Cobber|Beispiele)(:)(.*)$' - step_keywords = ur'^(\s*)(하지만|조건|먼저|만일|만약|단|그리고|그러면|那麼|那么|而且|當|当|前提|假設|假如|但是|但し|並且|もし|ならば|ただし|しかし|かつ|و |متى |لكن |عندما |ثم |بفرض |اذاً |כאשר |וגם |בהינתן |אזי |אז |אבל |Якщо |Унда |То |Припустимо, що |Припустимо |Онда |Но |Нехай |Лекин |Когато |Када |Кад |К тому же |И |Задато |Задати |Задате |Если |Допустим |Дадено |Ва |Бирок |Аммо |Али |Але |Агар |А |І |Și |És |Zatati |Zakładając |Zadato |Zadate |Zadano |Zadani |Zadan |Youse know when youse got |Youse know like when |Yna |Ya know how |Ya gotta |Y |Wun |Wtedy |When y\'all |When |Wenn |WEN |Và |Ve |Und |Un |Thì |Then y\'all |Then |Tapi |Tak |Tada |Tad |Så |Stel |Soit |Siis |Si |Sed |Se |Quando |Quand |Quan |Pryd |Pokud |Pokiaľ |Però |Pero |Pak |Oraz |Onda |Ond |Oletetaan |Og |Och |O zaman |Når |När |Niin |Nhưng |N |Mutta |Men |Mas |Maka |Majd |Mais |Maar |Ma |Lorsque |Lorsqu\'|Kun |Kuid |Kui |Khi |Keď |Ketika |Když |Kaj |Kai |Kada |Kad |Jeżeli |Ja |Ir |I CAN HAZ |I |Ha |Givun |Givet |Given y\'all |Given |Gitt |Gegeven |Gegeben sei |Fakat |Eğer ki |Etant donné |Et |Então |Entonces |Entao |En |Eeldades |E |Duota |Dun |Donitaĵo |Donat |Donada |Do |Diyelim ki |Dengan |Den youse gotta |De |Dato |Dar |Dann |Dan |Dado |Dacă |Daca |DEN |Când |Cuando |Cho |Cept |Cand |Cal |But y\'all |But |Buh |Biết |Bet |BUT |Atès |Atunci |Atesa |Anrhegedig a |Angenommen |And y\'all |And |An |Ama |Als |Alors |Allora |Ali |Aleshores |Ale |Akkor |Aber |AN |A také |A |\* )' + feature_keywords = u'^(기능|機能|功能|フィーチャ|خاصية|תכונה|Функціонал|Функционалност|Функционал|Фича|Особина|Могућност|Özellik|Właściwość|Tính năng|Trajto|Savybė|Požiadavka|Požadavek|Osobina|Ominaisuus|Omadus|OH HAI|Mogućnost|Mogucnost|Jellemző|Fīča|Funzionalità|Funktionalität|Funkcionalnost|Funkcionalitāte|Funcționalitate|Functionaliteit|Functionalitate|Funcionalitat|Funcionalidade|Fonctionnalité|Fitur|Feature|Egenskap|Egenskab|Crikey|Característica|Arwedd)(:)(.*)$' + feature_element_keywords = u'^(\\s*)(시나리오 개요|시나리오|배경|背景|場景大綱|場景|场景大纲|场景|劇本大綱|劇本|テンプレ|シナリオテンプレート|シナリオテンプレ|シナリオアウトライン|シナリオ|سيناريو مخطط|سيناريو|الخلفية|תרחיש|תבנית תרחיש|רקע|Тарих|Сценарій|Сценарио|Сценарий структураси|Сценарий|Структура сценарію|Структура сценарија|Структура сценария|Скица|Рамка на сценарий|Пример|Предыстория|Предистория|Позадина|Передумова|Основа|Концепт|Контекст|Założenia|Wharrimean is|Tình huống|The thing of it is|Tausta|Taust|Tapausaihio|Tapaus|Szenariogrundriss|Szenario|Szablon scenariusza|Stsenaarium|Struktura scenarija|Skica|Skenario konsep|Skenario|Situācija|Senaryo taslağı|Senaryo|Scénář|Scénario|Schema dello scenario|Scenārijs pēc parauga|Scenārijs|Scenár|Scenaro|Scenariusz|Scenariul de şablon|Scenariul de sablon|Scenariu|Scenario Outline|Scenario Amlinellol|Scenario|Scenarijus|Scenarijaus šablonas|Scenarij|Scenarie|Rerefons|Raamstsenaarium|Primer|Pozadí|Pozadina|Pozadie|Plan du scénario|Plan du Scénario|Osnova scénáře|Osnova|Náčrt Scénáře|Náčrt Scenáru|Mate|MISHUN SRSLY|MISHUN|Kịch bản|Konturo de la scenaro|Kontext|Konteksts|Kontekstas|Kontekst|Koncept|Khung tình huống|Khung kịch bản|Háttér|Grundlage|Geçmiş|Forgatókönyv vázlat|Forgatókönyv|Fono|Esquema do Cenário|Esquema do Cenario|Esquema del escenario|Esquema de l\'escenari|Escenario|Escenari|Dis is what went down|Dasar|Contexto|Contexte|Contesto|Condiţii|Conditii|Cenário|Cenario|Cefndir|Bối cảnh|Blokes|Bakgrunn|Bakgrund|Baggrund|Background|B4|Antecedents|Antecedentes|All y\'all|Achtergrond|Abstrakt Scenario|Abstract Scenario)(:)(.*)$' + examples_keywords = u'^(\\s*)(예|例子|例|サンプル|امثلة|דוגמאות|Сценарији|Примери|Приклади|Мисоллар|Значения|Örnekler|Voorbeelden|Variantai|Tapaukset|Scenarios|Scenariji|Scenarijai|Příklady|Példák|Príklady|Przykłady|Primjeri|Primeri|Piemēri|Pavyzdžiai|Paraugs|Juhtumid|Exemplos|Exemples|Exemplele|Exempel|Examples|Esempi|Enghreifftiau|Ekzemploj|Eksempler|Ejemplos|EXAMPLZ|Dữ liệu|Contoh|Cobber|Beispiele)(:)(.*)$' + step_keywords = u'^(\\s*)(하지만|조건|먼저|만일|만약|단|그리고|그러면|那麼|那么|而且|當|当|前提|假設|假如|但是|但し|並且|もし|ならば|ただし|しかし|かつ|و |متى |لكن |عندما |ثم |بفرض |اذاً |כאשר |וגם |בהינתן |אזי |אז |אבל |Якщо |Унда |То |Припустимо, що |Припустимо |Онда |Но |Нехай |Лекин |Когато |Када |Кад |К тому же |И |Задато |Задати |Задате |Если |Допустим |Дадено |Ва |Бирок |Аммо |Али |Але |Агар |А |І |Și |És |Zatati |Zakładając |Zadato |Zadate |Zadano |Zadani |Zadan |Youse know when youse got |Youse know like when |Yna |Ya know how |Ya gotta |Y |Wun |Wtedy |When y\'all |When |Wenn |WEN |Và |Ve |Und |Un |Thì |Then y\'all |Then |Tapi |Tak |Tada |Tad |Så |Stel |Soit |Siis |Si |Sed |Se |Quando |Quand |Quan |Pryd |Pokud |Pokiaľ |Però |Pero |Pak |Oraz |Onda |Ond |Oletetaan |Og |Och |O zaman |Når |När |Niin |Nhưng |N |Mutta |Men |Mas |Maka |Majd |Mais |Maar |Ma |Lorsque |Lorsqu\'|Kun |Kuid |Kui |Khi |Keď |Ketika |Když |Kaj |Kai |Kada |Kad |Jeżeli |Ja |Ir |I CAN HAZ |I |Ha |Givun |Givet |Given y\'all |Given |Gitt |Gegeven |Gegeben sei |Fakat |Eğer ki |Etant donné |Et |Então |Entonces |Entao |En |Eeldades |E |Duota |Dun |Donitaĵo |Donat |Donada |Do |Diyelim ki |Dengan |Den youse gotta |De |Dato |Dar |Dann |Dan |Dado |Dacă |Daca |DEN |Când |Cuando |Cho |Cept |Cand |Cal |But y\'all |But |Buh |Biết |Bet |BUT |Atès |Atunci |Atesa |Anrhegedig a |Angenommen |And y\'all |And |An |Ama |Als |Alors |Allora |Ali |Aleshores |Ale |Akkor |Aber |AN |A také |A |\* )' tokens = { 'comments': [ @@ -1779,6 +1801,7 @@ class GherkinLexer(RegexLexer): 'examples_table_header': [ (r"\s+\|\s*$", Keyword, "#pop:2"), include('comments'), + (r"\\\|", Name.Variable), (r"\s*\|", Keyword), (r"[^\|]", Name.Variable), ], @@ -1821,6 +1844,7 @@ class GherkinLexer(RegexLexer): 'table_content': [ (r"\s+\|\s*$", Keyword, "#pop"), include('comments'), + (r"\\\|", String), (r"\s*\|", Keyword), include('string'), ], @@ -1855,7 +1879,7 @@ class AsymptoteLexer(RegexLexer): """ For `Asymptote <http://asymptote.sf.net/>`_ source code. - *New in Pygments 1.2.* + .. versionadded:: 1.2 """ name = 'Asymptote' aliases = ['asy', 'asymptote'] @@ -1961,11 +1985,11 @@ class AsymptoteLexer(RegexLexer): from pygments.lexers._asybuiltins import ASYFUNCNAME, ASYVARNAME for index, token, value in \ RegexLexer.get_tokens_unprocessed(self, text): - if token is Name and value in ASYFUNCNAME: - token = Name.Function - elif token is Name and value in ASYVARNAME: - token = Name.Variable - yield index, token, value + if token is Name and value in ASYFUNCNAME: + token = Name.Function + elif token is Name and value in ASYVARNAME: + token = Name.Variable + yield index, token, value class PostScriptLexer(RegexLexer): @@ -1976,10 +2000,10 @@ class PostScriptLexer(RegexLexer): <http://partners.adobe.com/public/developer/en/ps/PLRM.pdf> is the authority for this. - *New in Pygments 1.4.* + .. versionadded:: 1.4 """ name = 'PostScript' - aliases = ['postscript'] + aliases = ['postscript', 'postscr'] filenames = ['*.ps', '*.eps'] mimetypes = ['application/postscript'] @@ -2064,10 +2088,10 @@ class AutohotkeyLexer(RegexLexer): """ For `autohotkey <http://www.autohotkey.com/>`_ source code. - *New in Pygments 1.4.* + .. versionadded:: 1.4 """ name = 'autohotkey' - aliases = ['ahk'] + aliases = ['ahk', 'autohotkey'] filenames = ['*.ahk', '*.ahkl'] mimetypes = ['text/x-autohotkey'] @@ -2244,7 +2268,7 @@ class MaqlLexer(RegexLexer): <https://secure.gooddata.com/docs/html/advanced.metric.tutorial.html>`_ scripts. - *New in Pygments 1.4.* + .. versionadded:: 1.4 """ name = 'MAQL' @@ -2303,7 +2327,7 @@ class GoodDataCLLexer(RegexLexer): Lexer for `GoodData-CL <http://github.com/gooddata/GoodData-CL/raw/master/cli/src/main/resources/com/gooddata/processor/COMMANDS.txt>`_ script files. - *New in Pygments 1.4.* + .. versionadded:: 1.4 """ name = 'GoodData-CL' @@ -2348,11 +2372,11 @@ class ProtoBufLexer(RegexLexer): Lexer for `Protocol Buffer <http://code.google.com/p/protobuf/>`_ definition files. - *New in Pygments 1.4.* + .. versionadded:: 1.4 """ name = 'Protocol Buffer' - aliases = ['protobuf'] + aliases = ['protobuf', 'proto'] filenames = ['*.proto'] tokens = { @@ -2400,7 +2424,7 @@ class HybrisLexer(RegexLexer): """ For `Hybris <http://www.hybris-lang.org>`_ source code. - *New in Pygments 1.4.* + .. versionadded:: 1.4 """ name = 'Hybris' @@ -2478,7 +2502,7 @@ class AwkLexer(RegexLexer): """ For Awk scripts. - *New in Pygments 1.5.* + .. versionadded:: 1.5 """ name = 'Awk' @@ -2504,11 +2528,11 @@ class AwkLexer(RegexLexer): 'root': [ (r'^(?=\s|/)', Text, 'slashstartsregex'), include('commentsandwhitespace'), - (r'\+\+|--|\|\||&&|in|\$|!?~|' + (r'\+\+|--|\|\||&&|in\b|\$|!?~|' r'(\*\*|[-<>+*%\^/!=])=?', Operator, 'slashstartsregex'), (r'[{(\[;,]', Punctuation, 'slashstartsregex'), (r'[})\].]', Punctuation), - (r'(break|continue|do|while|exit|for|if|' + (r'(break|continue|do|while|exit|for|if|else|' r'return)\b', Keyword, 'slashstartsregex'), (r'function\b', Keyword.Declaration, 'slashstartsregex'), (r'(atan2|cos|exp|int|log|rand|sin|sqrt|srand|gensub|gsub|index|' @@ -2532,7 +2556,7 @@ class Cfengine3Lexer(RegexLexer): """ Lexer for `CFEngine3 <http://cfengine.org>`_ policy files. - *New in Pygments 1.5.* + .. versionadded:: 1.5 """ name = 'CFEngine3' @@ -2596,7 +2620,7 @@ class SnobolLexer(RegexLexer): Recognizes the common ASCII equivalents of the original SNOBOL4 operators. Does not require spaces around binary operators. - *New in Pygments 1.5.* + .. versionadded:: 1.5 """ name = "Snobol" @@ -2660,7 +2684,7 @@ class UrbiscriptLexer(ExtendedRegexLexer): """ For UrbiScript source code. - *New in Pygments 1.5.* + .. versionadded:: 1.5 """ name = 'UrbiScript' @@ -2767,7 +2791,7 @@ class OpenEdgeLexer(RegexLexer): Lexer for `OpenEdge ABL (formerly Progress) <http://web.progress.com/en/openedge/abl.html>`_ source code. - *New in Pygments 1.5.* + .. versionadded:: 1.5 """ name = 'OpenEdge ABL' aliases = ['openedge', 'abl', 'progress'] @@ -2819,7 +2843,7 @@ class BroLexer(RegexLexer): """ For `Bro <http://bro-ids.org/>`_ scripts. - *New in Pygments 1.5.* + .. versionadded:: 1.5 """ name = 'Bro' aliases = ['bro'] @@ -2839,8 +2863,8 @@ class BroLexer(RegexLexer): (r'\\\n', Text), # Keywords (r'(add|alarm|break|case|const|continue|delete|do|else|enum|event' - r'|export|for|function|if|global|local|module|next' - r'|of|print|redef|return|schedule|type|when|while)\b', Keyword), + r'|export|for|function|if|global|hook|local|module|next' + r'|of|print|redef|return|schedule|switch|type|when|while)\b', Keyword), (r'(addr|any|bool|count|counter|double|file|int|interval|net' r'|pattern|port|record|set|string|subnet|table|time|timer' r'|vector)\b', Keyword.Type), @@ -2897,7 +2921,7 @@ class CbmBasicV2Lexer(RegexLexer): """ For CBM BASIC V2 sources. - *New in Pygments 1.6.* + .. versionadded:: 1.6 """ name = 'CBM BASIC V2' aliases = ['cbmbas'] @@ -2935,7 +2959,7 @@ class MscgenLexer(RegexLexer): """ For `Mscgen <http://www.mcternan.me.uk/mscgen/>`_ files. - *New in Pygments 1.6.* + .. versionadded:: 1.6 """ name = 'Mscgen' aliases = ['mscgen', 'msc'] @@ -2996,7 +3020,7 @@ class KconfigLexer(RegexLexer): """ For Linux-style Kconfig files. - *New in Pygments 1.6.* + .. versionadded:: 1.6 """ name = 'Kconfig' @@ -3071,7 +3095,7 @@ class VGLLexer(RegexLexer): For `SampleManager VGL <http://www.thermoscientific.com/samplemanager>`_ source code. - *New in Pygments 1.6.* + .. versionadded:: 1.6 """ name = 'VGL' aliases = ['vgl'] @@ -3104,7 +3128,7 @@ class SourcePawnLexer(RegexLexer): """ For SourcePawn source code with preprocessor directives. - *New in Pygments 1.6.* + .. versionadded:: 1.6 """ name = 'SourcePawn' aliases = ['sp'] @@ -3167,7 +3191,7 @@ class SourcePawnLexer(RegexLexer): ] } - SM_TYPES = ['Action', 'bool', 'Float', 'Plugin', 'String', 'any', + SM_TYPES = set(['Action', 'bool', 'Float', 'Plugin', 'String', 'any', 'AdminFlag', 'OverrideType', 'OverrideRule', 'ImmunityType', 'GroupId', 'AdminId', 'AdmAccessMode', 'AdminCachePart', 'CookieAccess', 'CookieMenu', 'CookieMenuAction', 'NetFlow', @@ -3185,16 +3209,16 @@ class SourcePawnLexer(RegexLexer): 'SortFunc2D', 'APLRes', 'FeatureType', 'FeatureStatus', 'SMCResult', 'SMCError', 'TFClassType', 'TFTeam', 'TFCond', 'TFResourceType', 'Timer', 'TopMenuAction', 'TopMenuObjectType', - 'TopMenuPosition', 'TopMenuObject', 'UserMsg'] + 'TopMenuPosition', 'TopMenuObject', 'UserMsg']) def __init__(self, **options): self.smhighlighting = get_bool_opt(options, 'sourcemod', True) - self._functions = [] + self._functions = set() if self.smhighlighting: from pygments.lexers._sourcemodbuiltins import FUNCTIONS - self._functions.extend(FUNCTIONS) + self._functions.update(FUNCTIONS) RegexLexer.__init__(self, **options) def get_tokens_unprocessed(self, text): @@ -3213,7 +3237,7 @@ class PuppetLexer(RegexLexer): """ For `Puppet <http://puppetlabs.com/>`__ configuration DSL. - *New in Pygments 1.6.* + .. versionadded:: 1.6 """ name = 'Puppet' aliases = ['puppet'] @@ -3294,7 +3318,7 @@ class NSISLexer(RegexLexer): """ For `NSIS <http://nsis.sourceforge.net/>`_ scripts. - *New in Pygments 1.6.* + .. versionadded:: 1.6 """ name = 'NSIS' aliases = ['nsis', 'nsi', 'nsh'] @@ -3416,9 +3440,9 @@ class NSISLexer(RegexLexer): class RPMSpecLexer(RegexLexer): """ - For RPM *.spec files + For RPM ``.spec`` files. - *New in Pygments 1.6.* + .. versionadded:: 1.6 """ name = 'RPMSpec' @@ -3494,10 +3518,10 @@ class AutoItLexer(RegexLexer): AutoIt is a freeware BASIC-like scripting language designed for automating the Windows GUI and general scripting - *New in Pygments 1.6.* + .. versionadded:: 1.6 """ name = 'AutoIt' - aliases = ['autoit', 'Autoit'] + aliases = ['autoit'] filenames = ['*.au3'] mimetypes = ['text/x-autoit'] @@ -3624,7 +3648,7 @@ class AutoItLexer(RegexLexer): (r'[a-zA-Z_#@$][a-zA-Z0-9_#@$]*', Name), (r'\\|\'', Text), (r'\`([\,\%\`abfnrtv\-\+;])', String.Escape), - (r'_\n', Text), # Line continuation + (r'_\n', Text), # Line continuation include('garbage'), ], 'commands': [ @@ -3665,3 +3689,198 @@ class AutoItLexer(RegexLexer): (r'[^\S\n]', Text), ], } + + +class RexxLexer(RegexLexer): + """ + `Rexx <http://www.rexxinfo.org/>`_ is a scripting language available for + a wide range of different platforms with its roots found on mainframe + systems. It is popular for I/O- and data based tasks and can act as glue + language to bind different applications together. + + .. versionadded:: 2.0 + """ + name = 'Rexx' + aliases = ['rexx', 'arexx'] + filenames = ['*.rexx', '*.rex', '*.rx', '*.arexx'] + mimetypes = ['text/x-rexx'] + flags = re.IGNORECASE + + tokens = { + 'root': [ + (r'\s', Whitespace), + (r'/\*', Comment.Multiline, 'comment'), + (r'"', String, 'string_double'), + (r"'", String, 'string_single'), + (r'[0-9]+(\.[0-9]+)?(e[+-]?[0-9])?', Number), + (r'([a-z_][a-z0-9_]*)(\s*)(:)(\s*)(procedure)\b', + bygroups(Name.Function, Whitespace, Operator, Whitespace, + Keyword.Declaration)), + (r'([a-z_][a-z0-9_]*)(\s*)(:)', + bygroups(Name.Label, Whitespace, Operator)), + include('function'), + include('keyword'), + include('operator'), + (r'[a-z_][a-z0-9_]*', Text), + ], + 'function': [ + (r'(abbrev|abs|address|arg|b2x|bitand|bitor|bitxor|c2d|c2x|' + r'center|charin|charout|chars|compare|condition|copies|d2c|' + r'd2x|datatype|date|delstr|delword|digits|errortext|form|' + r'format|fuzz|insert|lastpos|left|length|linein|lineout|lines|' + r'max|min|overlay|pos|queued|random|reverse|right|sign|' + r'sourceline|space|stream|strip|substr|subword|symbol|time|' + r'trace|translate|trunc|value|verify|word|wordindex|' + r'wordlength|wordpos|words|x2b|x2c|x2d|xrange)(\s*)(\()', + bygroups(Name.Builtin, Whitespace, Operator)), + ], + 'keyword': [ + (r'(address|arg|by|call|do|drop|else|end|exit|for|forever|if|' + r'interpret|iterate|leave|nop|numeric|off|on|options|parse|' + r'pull|push|queue|return|say|select|signal|to|then|trace|until|' + r'while)\b', Keyword.Reserved), + ], + 'operator': [ + (r'(-|//|/|\(|\)|\*\*|\*|\\<<|\\<|\\==|\\=|\\>>|\\>|\\|\|\||\||' + r'&&|&|%|\+|<<=|<<|<=|<>|<|==|=|><|>=|>>=|>>|>|¬<<|¬<|¬==|¬=|' + r'¬>>|¬>|¬|\.|,)', Operator), + ], + 'string_double': [ + (r'[^"\n]+', String), + (r'""', String), + (r'"', String, '#pop'), + (r'\n', Text, '#pop'), # Stray linefeed also terminates strings. + ], + 'string_single': [ + (r'[^\'\n]', String), + (r'\'\'', String), + (r'\'', String, '#pop'), + (r'\n', Text, '#pop'), # Stray linefeed also terminates strings. + ], + 'comment': [ + (r'[^*]+', Comment.Multiline), + (r'\*/', Comment.Multiline, '#pop'), + (r'\*', Comment.Multiline), + ] + } + + _c = lambda s: re.compile(s, re.MULTILINE) + _ADDRESS_COMMAND_PATTERN = _c(r'^\s*address\s+command\b') + _ADDRESS_PATTERN = _c(r'^\s*address\s+') + _DO_WHILE_PATTERN = _c(r'^\s*do\s+while\b') + _IF_THEN_DO_PATTERN = _c(r'^\s*if\b.+\bthen\s+do\s*$') + _PROCEDURE_PATTERN = _c(r'^\s*([a-z_][a-z0-9_]*)(\s*)(:)(\s*)(procedure)\b') + _ELSE_DO_PATTERN = _c(r'\belse\s+do\s*$') + _PARSE_ARG_PATTERN = _c(r'^\s*parse\s+(upper\s+)?(arg|value)\b') + PATTERNS_AND_WEIGHTS = ( + (_ADDRESS_COMMAND_PATTERN, 0.2), + (_ADDRESS_PATTERN, 0.05), + (_DO_WHILE_PATTERN, 0.1), + (_ELSE_DO_PATTERN, 0.1), + (_IF_THEN_DO_PATTERN, 0.1), + (_PROCEDURE_PATTERN, 0.5), + (_PARSE_ARG_PATTERN, 0.2), + ) + + def analyse_text(text): + """ + Check for inital comment and patterns that distinguish Rexx from other + C-like languages. + """ + if re.search(r'/\*\**\s*rexx', text, re.IGNORECASE): + # Header matches MVS Rexx requirements, this is certainly a Rexx + # script. + return 1.0 + elif text.startswith('/*'): + # Header matches general Rexx requirements; the source code might + # still be any language using C comments such as C++, C# or Java. + lowerText = text.lower() + result = sum(weight + for (pattern, weight) in RexxLexer.PATTERNS_AND_WEIGHTS + if pattern.search(lowerText)) + 0.01 + return min(result, 1.0) + + +class APLLexer(RegexLexer): + """ + A simple APL lexer. + + .. versionadded:: 2.0 + """ + name = 'APL' + aliases = ['apl'] + filenames = ['*.apl'] + + tokens = { + 'root': [ + # Whitespace + # ========== + (r'\s+', Text), + # + # Comment + # ======= + # '⍝' is traditional; '#' is supported by GNU APL and NGN (but not Dyalog) + (u'[⍝#].*$', Comment.Single), + # + # Strings + # ======= + (r'\'((\'\')|[^\'])*\'', String.Single), + (r'"(("")|[^"])*"', String.Double), # supported by NGN APL + # + # Punctuation + # =========== + # This token type is used for diamond and parenthesis + # but not for bracket and ; (see below) + (u'[⋄◇()]', Punctuation), + # + # Array indexing + # ============== + # Since this token type is very important in APL, it is not included in + # the punctuation token type but rather in the following one + (r'[\[\];]', String.Regex), + # + # Distinguished names + # =================== + # following IBM APL2 standard + (u'⎕[A-Za-zΔ∆⍙][A-Za-zΔ∆⍙_¯0-9]*', Name.Function), + # + # Labels + # ====== + # following IBM APL2 standard + # (u'[A-Za-zΔ∆⍙][A-Za-zΔ∆⍙_¯0-9]*:', Name.Label), + # + # Variables + # ========= + # following IBM APL2 standard + (u'[A-Za-zΔ∆⍙][A-Za-zΔ∆⍙_¯0-9]*', Name.Variable), + # + # Numbers + # ======= + (u'¯?(0[Xx][0-9A-Fa-f]+|[0-9]*\.?[0-9]+([Ee][+¯]?[0-9]+)?|¯|∞)' + u'([Jj]¯?(0[Xx][0-9A-Fa-f]+|[0-9]*\.?[0-9]+([Ee][+¯]?[0-9]+)?|¯|∞))?', + Number), + # + # Operators + # ========== + (u'[\.\\\/⌿⍀¨⍣⍨⍠⍤∘]', Name.Attribute), # closest token type + (u'[+\-×÷⌈⌊∣|⍳?*⍟○!⌹<≤=>≥≠≡≢∊⍷∪∩~∨∧⍱⍲⍴,⍪⌽⊖⍉↑↓⊂⊃⌷⍋⍒⊤⊥⍕⍎⊣⊢⍁⍂≈⌸⍯↗]', + Operator), + # + # Constant + # ======== + (u'⍬', Name.Constant), + # + # Quad symbol + # =========== + (u'[⎕⍞]', Name.Variable.Global), + # + # Arrows left/right + # ================= + (u'[←→]', Keyword.Declaration), + # + # D-Fn + # ==== + (u'[⍺⍵⍶⍹∇:]', Name.Builtin.Pseudo), + (r'[{}]', Keyword.Type), + ], + } |