Mercurial Repositories > eric / file comparison
comparison: eric6/ThirdParty/Pygments/pygments/lexers/esoteric.py
eric6/ThirdParty/Pygments/pygments/lexers/esoteric.py
- changeset 6942
- 2602857055c5
- parent 5713
- 6762afd9f963
- child 7547
- 21b0534faebc
equal
deleted
inserted
replaced
| 6941:f99d60d6b59b | 6942:2602857055c5 |
|---|---|
| 1 # -*- coding: utf-8 -*- | |
| 2 """ | |
| 3 pygments.lexers.esoteric | |
| 4 ~~~~~~~~~~~~~~~~~~~~~~~~ | |
| 5 | |
| 6 Lexers for esoteric languages. | |
| 7 | |
| 8 :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS. | |
| 9 :license: BSD, see LICENSE for details. | |
| 10 """ | |
| 11 | |
| 12 from pygments.lexer import RegexLexer, include, words | |
| 13 from pygments.token import Text, Comment, Operator, Keyword, Name, String, \ | |
| 14 Number, Punctuation, Error | |
| 15 | |
| 16 __all__ = ['BrainfuckLexer', 'BefungeLexer', 'RedcodeLexer', 'CAmkESLexer', | |
| 17 'CapDLLexer', 'AheuiLexer'] | |
| 18 | |
| 19 | |
| 20 class BrainfuckLexer(RegexLexer): | |
| 21 """ | |
| 22 Lexer for the esoteric `BrainFuck <http://www.muppetlabs.com/~breadbox/bf/>`_ | |
| 23 language. | |
| 24 """ | |
| 25 | |
| 26 name = 'Brainfuck' | |
| 27 aliases = ['brainfuck', 'bf'] | |
| 28 filenames = ['*.bf', '*.b'] | |
| 29 mimetypes = ['application/x-brainfuck'] | |
| 30 | |
| 31 tokens = { | |
| 32 'common': [ | |
| 33 # use different colors for different instruction types | |
| 34 (r'[.,]+', Name.Tag), | |
| 35 (r'[+-]+', Name.Builtin), | |
| 36 (r'[<>]+', Name.Variable), | |
| 37 (r'[^.,+\-<>\[\]]+', Comment), | |
| 38 ], | |
| 39 'root': [ | |
| 40 (r'\[', Keyword, 'loop'), | |
| 41 (r'\]', Error), | |
| 42 include('common'), | |
| 43 ], | |
| 44 'loop': [ | |
| 45 (r'\[', Keyword, '#push'), | |
| 46 (r'\]', Keyword, '#pop'), | |
| 47 include('common'), | |
| 48 ] | |
| 49 } | |
| 50 | |
| 51 | |
| 52 class BefungeLexer(RegexLexer): | |
| 53 """ | |
| 54 Lexer for the esoteric `Befunge <http://en.wikipedia.org/wiki/Befunge>`_ | |
| 55 language. | |
| 56 | |
| 57 .. versionadded:: 0.7 | |
| 58 """ | |
| 59 name = 'Befunge' | |
| 60 aliases = ['befunge'] | |
| 61 filenames = ['*.befunge'] | |
| 62 mimetypes = ['application/x-befunge'] | |
| 63 | |
| 64 tokens = { | |
| 65 'root': [ | |
| 66 (r'[0-9a-f]', Number), | |
| 67 (r'[+*/%!`-]', Operator), # Traditional math | |
| 68 (r'[<>^v?\[\]rxjk]', Name.Variable), # Move, imperatives | |
| 69 (r'[:\\$.,n]', Name.Builtin), # Stack ops, imperatives | |
| 70 (r'[|_mw]', Keyword), | |
| 71 (r'[{}]', Name.Tag), # Befunge-98 stack ops | |
| 72 (r'".*?"', String.Double), # Strings don't appear to allow escapes | |
| 73 (r'\'.', String.Single), # Single character | |
| 74 (r'[#;]', Comment), # Trampoline... depends on direction hit | |
| 75 (r'[pg&~=@iotsy]', Keyword), # Misc | |
| 76 (r'[()A-Z]', Comment), # Fingerprints | |
| 77 (r'\s+', Text), # Whitespace doesn't matter | |
| 78 ], | |
| 79 } | |
| 80 | |
| 81 | |
| 82 class CAmkESLexer(RegexLexer): | |
| 83 """ | |
| 84 Basic lexer for the input language for the | |
| 85 `CAmkES <https://sel4.systems/CAmkES/>`_ component platform. | |
| 86 | |
| 87 .. versionadded:: 2.1 | |
| 88 """ | |
| 89 name = 'CAmkES' | |
| 90 aliases = ['camkes', 'idl4'] | |
| 91 filenames = ['*.camkes', '*.idl4'] | |
| 92 | |
| 93 tokens = { | |
| 94 'root': [ | |
| 95 # C pre-processor directive | |
| 96 (r'^\s*#.*\n', Comment.Preproc), | |
| 97 | |
| 98 # Whitespace, comments | |
| 99 (r'\s+', Text), | |
| 100 (r'/\*(.|\n)*?\*/', Comment), | |
| 101 (r'//.*\n', Comment), | |
| 102 | |
| 103 (r'[\[(){},.;\]]', Punctuation), | |
| 104 (r'[~!%^&*+=|?:<>/-]', Operator), | |
| 105 | |
| 106 (words(('assembly', 'attribute', 'component', 'composition', | |
| 107 'configuration', 'connection', 'connector', 'consumes', | |
| 108 'control', 'dataport', 'Dataport', 'Dataports', 'emits', | |
| 109 'event', 'Event', 'Events', 'export', 'from', 'group', | |
| 110 'hardware', 'has', 'interface', 'Interface', 'maybe', | |
| 111 'procedure', 'Procedure', 'Procedures', 'provides', | |
| 112 'template', 'thread', 'threads', 'to', 'uses', 'with'), | |
| 113 suffix=r'\b'), Keyword), | |
| 114 | |
| 115 (words(('bool', 'boolean', 'Buf', 'char', 'character', 'double', | |
| 116 'float', 'in', 'inout', 'int', 'int16_6', 'int32_t', | |
| 117 'int64_t', 'int8_t', 'integer', 'mutex', 'out', 'real', | |
| 118 'refin', 'semaphore', 'signed', 'string', 'struct', | |
| 119 'uint16_t', 'uint32_t', 'uint64_t', 'uint8_t', 'uintptr_t', | |
| 120 'unsigned', 'void'), | |
| 121 suffix=r'\b'), Keyword.Type), | |
| 122 | |
| 123 # Recognised attributes | |
| 124 (r'[a-zA-Z_]\w*_(priority|domain|buffer)', Keyword.Reserved), | |
| 125 (words(('dma_pool', 'from_access', 'to_access'), suffix=r'\b'), | |
| 126 Keyword.Reserved), | |
| 127 | |
| 128 # CAmkES-level include | |
| 129 (r'import\s+(<[^>]*>|"[^"]*");', Comment.Preproc), | |
| 130 | |
| 131 # C-level include | |
| 132 (r'include\s+(<[^>]*>|"[^"]*");', Comment.Preproc), | |
| 133 | |
| 134 # Literals | |
| 135 (r'0[xX][\da-fA-F]+', Number.Hex), | |
| 136 (r'-?[\d]+', Number), | |
| 137 (r'-?[\d]+\.[\d]+', Number.Float), | |
| 138 (r'"[^"]*"', String), | |
| 139 (r'[Tt]rue|[Ff]alse', Name.Builtin), | |
| 140 | |
| 141 # Identifiers | |
| 142 (r'[a-zA-Z_]\w*', Name), | |
| 143 ], | |
| 144 } | |
| 145 | |
| 146 | |
| 147 class CapDLLexer(RegexLexer): | |
| 148 """ | |
| 149 Basic lexer for | |
| 150 `CapDL <https://ssrg.nicta.com.au/publications/nictaabstracts/Kuz_KLW_10.abstract.pml>`_. | |
| 151 | |
| 152 The source of the primary tool that reads such specifications is available | |
| 153 at https://github.com/seL4/capdl/tree/master/capDL-tool. Note that this | |
| 154 lexer only supports a subset of the grammar. For example, identifiers can | |
| 155 shadow type names, but these instances are currently incorrectly | |
| 156 highlighted as types. Supporting this would need a stateful lexer that is | |
| 157 considered unnecessarily complex for now. | |
| 158 | |
| 159 .. versionadded:: 2.2 | |
| 160 """ | |
| 161 name = 'CapDL' | |
| 162 aliases = ['capdl'] | |
| 163 filenames = ['*.cdl'] | |
| 164 | |
| 165 tokens = { | |
| 166 'root': [ | |
| 167 # C pre-processor directive | |
| 168 (r'^\s*#.*\n', Comment.Preproc), | |
| 169 | |
| 170 # Whitespace, comments | |
| 171 (r'\s+', Text), | |
| 172 (r'/\*(.|\n)*?\*/', Comment), | |
| 173 (r'(//|--).*\n', Comment), | |
| 174 | |
| 175 (r'[<>\[(){},:;=\]]', Punctuation), | |
| 176 (r'\.\.', Punctuation), | |
| 177 | |
| 178 (words(('arch', 'arm11', 'caps', 'child_of', 'ia32', 'irq', 'maps', | |
| 179 'objects'), suffix=r'\b'), Keyword), | |
| 180 | |
| 181 (words(('aep', 'asid_pool', 'cnode', 'ep', 'frame', 'io_device', | |
| 182 'io_ports', 'io_pt', 'notification', 'pd', 'pt', 'tcb', | |
| 183 'ut', 'vcpu'), suffix=r'\b'), Keyword.Type), | |
| 184 | |
| 185 # Properties | |
| 186 (words(('asid', 'addr', 'badge', 'cached', 'dom', 'domainID', 'elf', | |
| 187 'fault_ep', 'G', 'guard', 'guard_size', 'init', 'ip', | |
| 188 'prio', 'sp', 'R', 'RG', 'RX', 'RW', 'RWG', 'RWX', 'W', | |
| 189 'WG', 'WX', 'level', 'masked', 'master_reply', 'paddr', | |
| 190 'ports', 'reply', 'uncached'), suffix=r'\b'), | |
| 191 Keyword.Reserved), | |
| 192 | |
| 193 # Literals | |
| 194 (r'0[xX][\da-fA-F]+', Number.Hex), | |
| 195 (r'\d+(\.\d+)?(k|M)?', Number), | |
| 196 (words(('bits',), suffix=r'\b'), Number), | |
| 197 (words(('cspace', 'vspace', 'reply_slot', 'caller_slot', | |
| 198 'ipc_buffer_slot'), suffix=r'\b'), Number), | |
| 199 | |
| 200 # Identifiers | |
| 201 (r'[a-zA-Z_][-@\.\w]*', Name), | |
| 202 ], | |
| 203 } | |
| 204 | |
| 205 | |
| 206 class RedcodeLexer(RegexLexer): | |
| 207 """ | |
| 208 A simple Redcode lexer based on ICWS'94. | |
| 209 Contributed by Adam Blinkinsop <blinks@acm.org>. | |
| 210 | |
| 211 .. versionadded:: 0.8 | |
| 212 """ | |
| 213 name = 'Redcode' | |
| 214 aliases = ['redcode'] | |
| 215 filenames = ['*.cw'] | |
| 216 | |
| 217 opcodes = ('DAT', 'MOV', 'ADD', 'SUB', 'MUL', 'DIV', 'MOD', | |
| 218 'JMP', 'JMZ', 'JMN', 'DJN', 'CMP', 'SLT', 'SPL', | |
| 219 'ORG', 'EQU', 'END') | |
| 220 modifiers = ('A', 'B', 'AB', 'BA', 'F', 'X', 'I') | |
| 221 | |
| 222 tokens = { | |
| 223 'root': [ | |
| 224 # Whitespace: | |
| 225 (r'\s+', Text), | |
| 226 (r';.*$', Comment.Single), | |
| 227 # Lexemes: | |
| 228 # Identifiers | |
| 229 (r'\b(%s)\b' % '|'.join(opcodes), Name.Function), | |
| 230 (r'\b(%s)\b' % '|'.join(modifiers), Name.Decorator), | |
| 231 (r'[A-Za-z_]\w+', Name), | |
| 232 # Operators | |
| 233 (r'[-+*/%]', Operator), | |
| 234 (r'[#$@<>]', Operator), # mode | |
| 235 (r'[.,]', Punctuation), # mode | |
| 236 # Numbers | |
| 237 (r'[-+]?\d+', Number.Integer), | |
| 238 ], | |
| 239 } | |
| 240 | |
| 241 | |
| 242 class AheuiLexer(RegexLexer): | |
| 243 """ | |
| 244 Aheui_ Lexer. | |
| 245 | |
| 246 Aheui_ is esoteric language based on Korean alphabets. | |
| 247 | |
| 248 .. _Aheui:: http://aheui.github.io/ | |
| 249 | |
| 250 """ | |
| 251 | |
| 252 name = 'Aheui' | |
| 253 aliases = ['aheui'] | |
| 254 filenames = ['*.aheui'] | |
| 255 | |
| 256 tokens = { | |
| 257 'root': [ | |
| 258 (u'[' | |
| 259 u'나-낳냐-냫너-넣녀-녛노-놓뇨-눟뉴-닇' | |
| 260 u'다-닿댜-댷더-덯뎌-뎧도-돟됴-둫듀-딓' | |
| 261 u'따-땋땨-떃떠-떻뗘-뗳또-똫뚀-뚷뜌-띟' | |
| 262 u'라-랗랴-럏러-렇려-렿로-롷료-뤃류-릫' | |
| 263 u'마-맣먀-먛머-멓며-몋모-뫃묘-뭏뮤-믷' | |
| 264 u'바-밯뱌-뱧버-벟벼-볗보-봏뵤-붛뷰-빃' | |
| 265 u'빠-빻뺘-뺳뻐-뻫뼈-뼣뽀-뽛뾰-뿧쀼-삏' | |
| 266 u'사-샇샤-샿서-섷셔-셯소-솧쇼-숳슈-싛' | |
| 267 u'싸-쌓쌰-썋써-쎃쎠-쎻쏘-쏳쑈-쑿쓔-씧' | |
| 268 u'자-잫쟈-쟣저-젛져-졓조-좋죠-줗쥬-즿' | |
| 269 u'차-챃챠-챻처-첳쳐-쳫초-촣쵸-춯츄-칗' | |
| 270 u'카-캏캬-컇커-컿켜-켷코-콯쿄-쿻큐-킣' | |
| 271 u'타-탛탸-턓터-텋텨-톃토-톻툐-퉇튜-틯' | |
| 272 u'파-팧퍄-퍟퍼-펗펴-폏포-퐇표-풓퓨-픻' | |
| 273 u'하-핳햐-햫허-헣혀-혛호-홓효-훟휴-힇' | |
| 274 u']', Operator), | |
| 275 ('.', Comment), | |
| 276 ], | |
| 277 } |
