pygments.rb 1.2.0 → 2.1.0

data/vendor/pygments-main/pygments/lexers/esoteric.py

@@ -1,11 +1,10 @@
-# -*- coding: utf-8 -*-
 """
     pygments.lexers.esoteric
     ~~~~~~~~~~~~~~~~~~~~~~~~
 
     Lexers for esoteric languages.
 
-    :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2021 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -13,6 +12,8 @@ from pygments.lexer import RegexLexer, include, words
 from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
     Number, Punctuation, Error
 
+import re
+
 __all__ = ['BrainfuckLexer', 'BefungeLexer', 'RedcodeLexer', 'CAmkESLexer',
            'CapDLLexer', 'AheuiLexer']
 
@@ -48,6 +49,31 @@ class BrainfuckLexer(RegexLexer):
         ]
     }
 
+    def analyse_text(text):
+        """It's safe to assume that a program which mostly consists of + -
+        and < > is brainfuck."""
+        plus_minus_count = 0
+        greater_less_count = 0
+
+        range_to_check = max(256, len(text))
+
+        for c in text[:range_to_check]:
+            if c == '+' or c == '-':
+                plus_minus_count += 1
+            if c == '<' or c == '>':
+                greater_less_count += 1
+
+        if plus_minus_count > (0.25 * range_to_check):
+            return 1.0
+        if greater_less_count > (0.25 * range_to_check):
+            return 1.0
+
+        result = 0
+        if '[-]' in text:
+            result += 0.5
+
+        return result
+
 
 class BefungeLexer(RegexLexer):
     """
@@ -245,7 +271,7 @@ class AheuiLexer(RegexLexer):
 
     Aheui_ is esoteric language based on Korean alphabets.
 
-    .. _Aheui:: http://aheui.github.io/
+    .. _Aheui: http://aheui.github.io/
 
     """
 
@@ -255,23 +281,23 @@ class AheuiLexer(RegexLexer):
 
     tokens = {
         'root': [
-            (u'['
-             u'나-낳냐-냫너-넣녀-녛노-놓뇨-눟뉴-닇'
-             u'다-닿댜-댷더-덯뎌-뎧도-돟됴-둫듀-딓'
-             u'따-땋땨-떃떠-떻뗘-뗳또-똫뚀-뚷뜌-띟'
-             u'라-랗랴-럏러-렇려-렿로-롷료-뤃류-릫'
-             u'마-맣먀-먛머-멓며-몋모-뫃묘-뭏뮤-믷'
-             u'바-밯뱌-뱧버-벟벼-볗보-봏뵤-붛뷰-빃'
-             u'빠-빻뺘-뺳뻐-뻫뼈-뼣뽀-뽛뾰-뿧쀼-삏'
-             u'사-샇샤-샿서-섷셔-셯소-솧쇼-숳슈-싛'
-             u'싸-쌓쌰-썋써-쎃쎠-쎻쏘-쏳쑈-쑿쓔-씧'
-             u'자-잫쟈-쟣저-젛져-졓조-좋죠-줗쥬-즿'
-             u'차-챃챠-챻처-첳쳐-쳫초-촣쵸-춯츄-칗'
-             u'카-캏캬-컇커-컿켜-켷코-콯쿄-쿻큐-킣'
-             u'타-탛탸-턓터-텋텨-톃토-톻툐-퉇튜-틯'
-             u'파-팧퍄-퍟퍼-펗펴-폏포-퐇표-풓퓨-픻'
-             u'하-핳햐-햫허-헣혀-혛호-홓효-훟휴-힇'
-             u']', Operator),
+            ('['
+             '나-낳냐-냫너-넣녀-녛노-놓뇨-눟뉴-닇'
+             '다-닿댜-댷더-덯뎌-뎧도-돟됴-둫듀-딓'
+             '따-땋땨-떃떠-떻뗘-뗳또-똫뚀-뚷뜌-띟'
+             '라-랗랴-럏러-렇려-렿로-롷료-뤃류-릫'
+             '마-맣먀-먛머-멓며-몋모-뫃묘-뭏뮤-믷'
+             '바-밯뱌-뱧버-벟벼-볗보-봏뵤-붛뷰-빃'
+             '빠-빻뺘-뺳뻐-뻫뼈-뼣뽀-뽛뾰-뿧쀼-삏'
+             '사-샇샤-샿서-섷셔-셯소-솧쇼-숳슈-싛'
+             '싸-쌓쌰-썋써-쎃쎠-쎻쏘-쏳쑈-쑿쓔-씧'
+             '자-잫쟈-쟣저-젛져-졓조-좋죠-줗쥬-즿'
+             '차-챃챠-챻처-첳쳐-쳫초-촣쵸-춯츄-칗'
+             '카-캏캬-컇커-컿켜-켷코-콯쿄-쿻큐-킣'
+             '타-탛탸-턓터-텋텨-톃토-톻툐-퉇튜-틯'
+             '파-팧퍄-퍟퍼-펗펴-폏포-퐇표-풓퓨-픻'
+             '하-핳햐-햫허-헣혀-혛호-홓효-훟휴-힇'
+             ']', Operator),
             ('.', Comment),
         ],
     }

data/vendor/pygments-main/pygments/lexers/ezhil.py

@@ -1,11 +1,10 @@
-# -*- coding: utf-8 -*-
 """
     pygments.lexers.ezhil
     ~~~~~~~~~~~~~~~~~~~~~
 
     Pygments lexers for Ezhil language.
 
-    :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2021 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -30,20 +29,20 @@ class EzhilLexer(RegexLexer):
     flags = re.MULTILINE | re.UNICODE
     # Refer to tamil.utf8.tamil_letters from open-tamil for a stricter version of this.
     # This much simpler version is close enough, and includes combining marks.
-    _TALETTERS = u'[a-zA-Z_]|[\u0b80-\u0bff]'
+    _TALETTERS = '[a-zA-Z_]|[\u0b80-\u0bff]'
     tokens = {
         'root': [
             include('keywords'),
             (r'#.*\n', Comment.Single),
             (r'[@+/*,^\-%]|[!<>=]=?|&&?|\|\|?', Operator),
-            (u'இல்', Operator.Word),
-            (words((u'assert', u'max', u'min',
-                    u'நீளம்', u'சரம்_இடமாற்று', u'சரம்_கண்டுபிடி',
-                    u'பட்டியல்', u'பின்இணை', u'வரிசைப்படுத்து',
-                    u'எடு', u'தலைகீழ்', u'நீட்டிக்க', u'நுழைக்க', u'வை',
-                    u'கோப்பை_திற', u'கோப்பை_எழுது', u'கோப்பை_மூடு',
-                    u'pi', u'sin', u'cos', u'tan', u'sqrt', u'hypot', u'pow',
-                    u'exp', u'log', u'log10', u'exit',
+            ('இல்', Operator.Word),
+            (words(('assert', 'max', 'min',
+                    'நீளம்', 'சரம்_இடமாற்று', 'சரம்_கண்டுபிடி',
+                    'பட்டியல்', 'பின்இணை', 'வரிசைப்படுத்து',
+                    'எடு', 'தலைகீழ்', 'நீட்டிக்க', 'நுழைக்க', 'வை',
+                    'கோப்பை_திற', 'கோப்பை_எழுது', 'கோப்பை_மூடு',
+                    'pi', 'sin', 'cos', 'tan', 'sqrt', 'hypot', 'pow',
+                    'exp', 'log', 'log10', 'exit',
                     ), suffix=r'\b'), Name.Builtin),
             (r'(True|False)\b', Keyword.Constant),
             (r'[^\S\n]+', Text),
@@ -52,10 +51,10 @@ class EzhilLexer(RegexLexer):
             (r'[(){}\[\]:;.]', Punctuation),
         ],
         'keywords': [
-            (u'பதிப்பி|தேர்ந்தெடு|தேர்வு|ஏதேனில்|ஆனால்|இல்லைஆனால்|இல்லை|ஆக|ஒவ்வொன்றாக|இல்|வரை|செய்|முடியேனில்|பின்கொடு|முடி|நிரல்பாகம்|தொடர்|நிறுத்து|நிரல்பாகம்', Keyword),
+            ('பதிப்பி|தேர்ந்தெடு|தேர்வு|ஏதேனில்|ஆனால்|இல்லைஆனால்|இல்லை|ஆக|ஒவ்வொன்றாக|இல்|வரை|செய்|முடியேனில்|பின்கொடு|முடி|நிரல்பாகம்|தொடர்|நிறுத்து|நிரல்பாகம்', Keyword),
         ],
         'identifier': [
-            (u'(?:'+_TALETTERS+u')(?:[0-9]|'+_TALETTERS+u')*', Name),
+            ('(?:'+_TALETTERS+')(?:[0-9]|'+_TALETTERS+')*', Name),
         ],
         'literal': [
             (r'".*?"', String),
@@ -64,6 +63,14 @@ class EzhilLexer(RegexLexer):
         ]
     }
 
+    def analyse_text(text):
+        """This language uses Tamil-script. We'll assume that if there's a
+        decent amount of Tamil-characters, it's this language. This assumption
+        is obviously horribly off if someone uses string literals in tamil
+        in another language."""
+        if len(re.findall(r'[\u0b80-\u0bff]', text)) > 10:
+            return 0.25
+
     def __init__(self, **options):
-        super(EzhilLexer, self).__init__(**options)
+        super().__init__(**options)
         self.encoding = options.get('encoding', 'utf-8')

data/vendor/pygments-main/pygments/lexers/factor.py

@@ -1,11 +1,10 @@
-# -*- coding: utf-8 -*-
 """
     pygments.lexers.factor
     ~~~~~~~~~~~~~~~~~~~~~~
 
     Lexers for the Factor language.
 
-    :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2021 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -265,7 +264,7 @@ class FactorLexer(RegexLexer):
             (r'(?:<PRIVATE|PRIVATE>)\s', Keyword.Namespace),
 
             # strings
-            (r'"""\s+(?:.|\n)*?\s+"""', String),
+            (r'"""\s(?:.|\n)*?\s"""', String),
             (r'"(?:\\\\|\\"|[^"])*"', String),
             (r'\S+"\s+(?:\\\\|\\"|[^"])*"', String),
             (r'CHAR:\s+(?:\\[\\abfnrstv]|[^\\]\S*)\s', String.Char),
@@ -322,7 +321,7 @@ class FactorLexer(RegexLexer):
         'slots': [
             (r'\s+', Text),
             (r';\s', Keyword, '#pop'),
-            (r'(\{\s+)(\S+)(\s+[^}]+\s+\}\s)',
+            (r'(\{\s+)(\S+)(\s[^}]+\s\}\s)',
              bygroups(Text, Name.Variable, Text)),
             (r'\S+', Name.Variable),
         ],

data/vendor/pygments-main/pygments/lexers/fantom.py

@@ -1,11 +1,10 @@
-# -*- coding: utf-8 -*-
 """
     pygments.lexers.fantom
     ~~~~~~~~~~~~~~~~~~~~~~
 
     Lexer for the Fantom language.
 
-    :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2021 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 

data/vendor/pygments-main/pygments/lexers/felix.py

@@ -1,11 +1,10 @@
-# -*- coding: utf-8 -*-
 """
     pygments.lexers.felix
     ~~~~~~~~~~~~~~~~~~~~~
 
     Lexer for the Felix language.
 
-    :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2021 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 

data/vendor/pygments-main/pygments/lexers/floscript.py

@@ -0,0 +1,82 @@
+"""
+    pygments.lexers.floscript
+    ~~~~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexer for FloScript
+
+    :copyright: Copyright 2006-2021 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.lexer import RegexLexer, include
+from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation
+
+__all__ = ['FloScriptLexer']
+
+
+class FloScriptLexer(RegexLexer):
+    """
+    For `FloScript <https://github.com/ioflo/ioflo>`_ configuration language source code.
+
+    .. versionadded:: 2.4
+    """
+
+    name = 'FloScript'
+    aliases = ['floscript', 'flo']
+    filenames = ['*.flo']
+
+    def innerstring_rules(ttype):
+        return [
+            # the old style '%s' % (...) string formatting
+            (r'%(\(\w+\))?[-#0 +]*([0-9]+|[*])?(\.([0-9]+|[*]))?'
+             '[hlL]?[E-GXc-giorsux%]', String.Interpol),
+            # backslashes, quotes and formatting signs must be parsed one at a time
+            (r'[^\\\'"%\n]+', ttype),
+            (r'[\'"\\]', ttype),
+            # unhandled string formatting sign
+            (r'%', ttype),
+            # newlines are an error (use "nl" state)
+        ]
+
+    tokens = {
+        'root': [
+            (r'\n', Text),
+            (r'[^\S\n]+', Text),
+
+            (r'[]{}:(),;[]', Punctuation),
+            (r'\\\n', Text),
+            (r'\\', Text),
+            (r'(to|by|with|from|per|for|cum|qua|via|as|at|in|of|on|re|is|if|be|into|'
+             r'and|not)\b', Operator.Word),
+            (r'!=|==|<<|>>|[-~+/*%=<>&^|.]', Operator),
+            (r'(load|init|server|logger|log|loggee|first|over|under|next|done|timeout|'
+             r'repeat|native|benter|enter|recur|exit|precur|renter|rexit|print|put|inc|'
+             r'copy|set|aux|rear|raze|go|let|do|bid|ready|start|stop|run|abort|use|flo|'
+             r'give|take)\b', Name.Builtin),
+            (r'(frame|framer|house)\b', Keyword),
+            ('"', String, 'string'),
+
+            include('name'),
+            include('numbers'),
+            (r'#.+$', Comment.Singleline),
+        ],
+        'string': [
+            ('[^"]+', String),
+            ('"', String, '#pop'),
+        ],
+        'numbers': [
+            (r'(\d+\.\d*|\d*\.\d+)([eE][+-]?[0-9]+)?j?', Number.Float),
+            (r'\d+[eE][+-]?[0-9]+j?', Number.Float),
+            (r'0[0-7]+j?', Number.Oct),
+            (r'0[bB][01]+', Number.Bin),
+            (r'0[xX][a-fA-F0-9]+', Number.Hex),
+            (r'\d+L', Number.Integer.Long),
+            (r'\d+j?', Number.Integer)
+        ],
+
+        'name': [
+            (r'@[\w.]+', Name.Decorator),
+            (r'[a-zA-Z_]\w*', Name),
+        ],
+    }

data/vendor/pygments-main/pygments/lexers/forth.py

@@ -1,17 +1,17 @@
-# -*- coding: utf-8 -*-
 """
     pygments.lexers.forth
     ~~~~~~~~~~~~~~~~~~~~~
 
-    :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS.
+    Lexer for the Forth language.
+
+    :copyright: Copyright 2006-2021 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
 import re
 
-from pygments.lexer import RegexLexer, include, bygroups
-from pygments.token import Error, Punctuation, Literal, Token, \
-     Text, Comment, Operator, Keyword, Name, String, Number, Generic
+from pygments.lexer import RegexLexer, bygroups
+from pygments.token import Text, Comment, Keyword, Name, String, Number
 
 
 __all__ = ['ForthLexer']
@@ -28,12 +28,6 @@ class ForthLexer(RegexLexer):
     filenames = ['*.frt', '*.fs']
     mimetypes = ['application/x-forth']
 
-    delimiter = r'\s'
-    delimiter_end = r'(?=[%s])' % delimiter
-
-    valid_name_chars = r'[^%s]' % delimiter
-    valid_name = r"%s+%s" % (valid_name_chars, delimiter_end)
-
     flags = re.IGNORECASE | re.MULTILINE
 
     tokens = {
@@ -69,7 +63,7 @@ class ForthLexer(RegexLexer):
              r'then|type|u\.|u\<|um\*|um\/mod|unloop|until|'
              r'variable|while|word|xor|\[char\]|\[\'\]|'
              r'@|!|\#|<\#|\#>|:|;|\+|-|\*|\/|,|<|>|\|1\+|1-|\.|'
-            # *** Wordset CORE-EXT
+             # *** Wordset CORE-EXT
              r'\.r|0<>|'
              r'0>|2>r|2r>|2r@|:noname|\?do|again|c\"|'
              r'case|compile,|endcase|endof|erase|false|'
@@ -77,38 +71,38 @@ class ForthLexer(RegexLexer):
              r'restore-input|roll|save-input|source-id|to|'
              r'true|tuck|u\.r|u>|unused|value|within|'
              r'\[compile\]|'
-            # *** Wordset CORE-EXT-obsolescent
+             # *** Wordset CORE-EXT-obsolescent
              r'\#tib|convert|expect|query|span|'
              r'tib|'
-            # *** Wordset DOUBLE
+             # *** Wordset DOUBLE
              r'2constant|2literal|2variable|d\+|d-|'
              r'd\.|d\.r|d0<|d0=|d2\*|d2\/|d<|d=|d>s|'
              r'dabs|dmax|dmin|dnegate|m\*\/|m\+|'
-            # *** Wordset DOUBLE-EXT
+             # *** Wordset DOUBLE-EXT
              r'2rot|du<|'
-            # *** Wordset EXCEPTION
+             # *** Wordset EXCEPTION
              r'catch|throw|'
-            # *** Wordset EXCEPTION-EXT
+             # *** Wordset EXCEPTION-EXT
              r'abort|abort\"|'
-            # *** Wordset FACILITY
+             # *** Wordset FACILITY
              r'at-xy|key\?|page|'
-            # *** Wordset FACILITY-EXT
+             # *** Wordset FACILITY-EXT
              r'ekey|ekey>char|ekey\?|emit\?|ms|time&date|'
-            # *** Wordset FILE
+             # *** Wordset FILE
              r'BIN|CLOSE-FILE|CREATE-FILE|DELETE-FILE|FILE-POSITION|'
              r'FILE-SIZE|INCLUDE-FILE|INCLUDED|OPEN-FILE|R\/O|'
              r'R\/W|READ-FILE|READ-LINE|REPOSITION-FILE|RESIZE-FILE|'
              r'S\"|SOURCE-ID|W/O|WRITE-FILE|WRITE-LINE|'
-            # *** Wordset FILE-EXT
+             # *** Wordset FILE-EXT
              r'FILE-STATUS|FLUSH-FILE|REFILL|RENAME-FILE|'
-            # *** Wordset FLOAT
+             # *** Wordset FLOAT
              r'>float|d>f|'
              r'f!|f\*|f\+|f-|f\/|f0<|f0=|f<|f>d|f@|'
              r'falign|faligned|fconstant|fdepth|fdrop|fdup|'
              r'fliteral|float\+|floats|floor|fmax|fmin|'
              r'fnegate|fover|frot|fround|fswap|fvariable|'
              r'represent|'
-            # *** Wordset FLOAT-EXT
+             # *** Wordset FLOAT-EXT
              r'df!|df@|dfalign|dfaligned|dfloat\+|'
              r'dfloats|f\*\*|f\.|fabs|facos|facosh|falog|'
              r'fasin|fasinh|fatan|fatan2|fatanh|fcos|fcosh|'
@@ -116,34 +110,34 @@ class ForthLexer(RegexLexer):
              r'fsincos|fsinh|fsqrt|ftan|ftanh|f~|precision|'
              r'set-precision|sf!|sf@|sfalign|sfaligned|sfloat\+|'
              r'sfloats|'
-            # *** Wordset LOCAL
+             # *** Wordset LOCAL
              r'\(local\)|to|'
-            # *** Wordset LOCAL-EXT
+             # *** Wordset LOCAL-EXT
              r'locals\||'
-            # *** Wordset MEMORY
+             # *** Wordset MEMORY
              r'allocate|free|resize|'
-            # *** Wordset SEARCH
+             # *** Wordset SEARCH
              r'definitions|find|forth-wordlist|get-current|'
              r'get-order|search-wordlist|set-current|set-order|'
              r'wordlist|'
-            # *** Wordset SEARCH-EXT
+             # *** Wordset SEARCH-EXT
              r'also|forth|only|order|previous|'
-            # *** Wordset STRING
+             # *** Wordset STRING
              r'-trailing|\/string|blank|cmove|cmove>|compare|'
              r'search|sliteral|'
-            # *** Wordset TOOLS
+             # *** Wordset TOOLS
              r'.s|dump|see|words|'
-            # *** Wordset TOOLS-EXT
+             # *** Wordset TOOLS-EXT
              r';code|'
              r'ahead|assembler|bye|code|cs-pick|cs-roll|'
              r'editor|state|\[else\]|\[if\]|\[then\]|'
-            # *** Wordset TOOLS-EXT-obsolescent
-            r'forget|'
-            # Forth 2012
-            r'defer|defer@|defer!|action-of|begin-structure|field:|buffer:|'
-            r'parse-name|buffer:|traverse-wordlist|n>r|nr>|2value|fvalue|'
-            r'name>interpret|name>compile|name>string|'
-            r'cfield:|end-structure)'+delimiter, Keyword),
+             # *** Wordset TOOLS-EXT-obsolescent
+             r'forget|'
+             # Forth 2012
+             r'defer|defer@|defer!|action-of|begin-structure|field:|buffer:|'
+             r'parse-name|buffer:|traverse-wordlist|n>r|nr>|2value|fvalue|'
+             r'name>interpret|name>compile|name>string|'
+             r'cfield:|end-structure)(?!\S)', Keyword),
 
             # Numbers
             (r'(\$[0-9A-F]+)', Number.Hex),
@@ -154,18 +148,18 @@ class ForthLexer(RegexLexer):
              r'itype|icompare|sp@|sp!|rp@|rp!|up@|up!|'
              r'>a|a>|a@|a!|a@+|a@-|>b|b>|b@|b!|b@+|b@-|'
              r'find-name|1ms|'
-             r'sp0|rp0|\(evaluate\)|int-trap|int!)' + delimiter,
+             r'sp0|rp0|\(evaluate\)|int-trap|int!)(?!\S)',
              Name.Constant),
             # a proposal
             (r'(do-recognizer|r:fail|recognizer:|get-recognizers|'
              r'set-recognizers|r:float|r>comp|r>int|r>post|'
              r'r:name|r:word|r:dnum|r:num|recognizer|forth-recognizer|'
-             r'rec:num|rec:float|rec:word)' + delimiter, Name.Decorator),
+             r'rec:num|rec:float|rec:word)(?!\S)', Name.Decorator),
             # defining words. The next word is a new command name
             (r'(Evalue|Rvalue|Uvalue|Edefer|Rdefer|Udefer)(\s+)',
              bygroups(Keyword.Namespace, Text), 'worddef'),
 
-            (valid_name, Name.Function),      # Anything else is executed
+            (r'\S+', Name.Function),      # Anything else is executed
 
         ],
         'worddef': [
@@ -175,3 +169,9 @@ class ForthLexer(RegexLexer):
             (r'[^"]+', String, '#pop'),
         ],
     }
+
+    def analyse_text(text):
+        """Forth uses : COMMAND ; quite a lot in a single line, so we're trying
+        to find that."""
+        if re.search('\n:[^\n]+;\n', text):
+            return 0.3