Mercurial Repositories > eric / file comparison
comparison: eric6/ThirdParty/Pygments/pygments/lexers/perl.py
eric6/ThirdParty/Pygments/pygments/lexers/perl.py
- changeset 6942
- 2602857055c5
- parent 6651
- e8f3b5568b21
- child 7547
- 21b0534faebc
equal
deleted
inserted
replaced
| 6941:f99d60d6b59b | 6942:2602857055c5 |
|---|---|
| 1 # -*- coding: utf-8 -*- | |
| 2 """ | |
| 3 pygments.lexers.perl | |
| 4 ~~~~~~~~~~~~~~~~~~~~ | |
| 5 | |
| 6 Lexers for Perl and related languages. | |
| 7 | |
| 8 :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS. | |
| 9 :license: BSD, see LICENSE for details. | |
| 10 """ | |
| 11 | |
| 12 import re | |
| 13 | |
| 14 from pygments.lexer import RegexLexer, ExtendedRegexLexer, include, bygroups, \ | |
| 15 using, this, default, words | |
| 16 from pygments.token import Text, Comment, Operator, Keyword, Name, String, \ | |
| 17 Number, Punctuation | |
| 18 from pygments.util import shebang_matches | |
| 19 | |
| 20 __all__ = ['PerlLexer', 'Perl6Lexer'] | |
| 21 | |
| 22 | |
| 23 class PerlLexer(RegexLexer): | |
| 24 """ | |
| 25 For `Perl <http://www.perl.org>`_ source code. | |
| 26 """ | |
| 27 | |
| 28 name = 'Perl' | |
| 29 aliases = ['perl', 'pl'] | |
| 30 filenames = ['*.pl', '*.pm', '*.t'] | |
| 31 mimetypes = ['text/x-perl', 'application/x-perl'] | |
| 32 | |
| 33 flags = re.DOTALL | re.MULTILINE | |
| 34 # TODO: give this to a perl guy who knows how to parse perl... | |
| 35 tokens = { | |
| 36 'balanced-regex': [ | |
| 37 (r'/(\\\\|\\[^\\]|[^\\/])*/[egimosx]*', String.Regex, '#pop'), | |
| 38 (r'!(\\\\|\\[^\\]|[^\\!])*![egimosx]*', String.Regex, '#pop'), | |
| 39 (r'\\(\\\\|[^\\])*\\[egimosx]*', String.Regex, '#pop'), | |
| 40 (r'\{(\\\\|\\[^\\]|[^\\}])*\}[egimosx]*', String.Regex, '#pop'), | |
| 41 (r'<(\\\\|\\[^\\]|[^\\>])*>[egimosx]*', String.Regex, '#pop'), | |
| 42 (r'\[(\\\\|\\[^\\]|[^\\\]])*\][egimosx]*', String.Regex, '#pop'), | |
| 43 (r'\((\\\\|\\[^\\]|[^\\)])*\)[egimosx]*', String.Regex, '#pop'), | |
| 44 (r'@(\\\\|\\[^\\]|[^\\@])*@[egimosx]*', String.Regex, '#pop'), | |
| 45 (r'%(\\\\|\\[^\\]|[^\\%])*%[egimosx]*', String.Regex, '#pop'), | |
| 46 (r'\$(\\\\|\\[^\\]|[^\\$])*\$[egimosx]*', String.Regex, '#pop'), | |
| 47 ], | |
| 48 'root': [ | |
| 49 (r'\A\#!.+?$', Comment.Hashbang), | |
| 50 (r'\#.*?$', Comment.Single), | |
| 51 (r'^=[a-zA-Z0-9]+\s+.*?\n=cut', Comment.Multiline), | |
| 52 (words(( | |
| 53 'case', 'continue', 'do', 'else', 'elsif', 'for', 'foreach', | |
| 54 'if', 'last', 'my', 'next', 'our', 'redo', 'reset', 'then', | |
| 55 'unless', 'until', 'while', 'print', 'new', 'BEGIN', | |
| 56 'CHECK', 'INIT', 'END', 'return'), suffix=r'\b'), | |
| 57 Keyword), | |
| 58 (r'(format)(\s+)(\w+)(\s*)(=)(\s*\n)', | |
| 59 bygroups(Keyword, Text, Name, Text, Punctuation, Text), 'format'), | |
| 60 (r'(eq|lt|gt|le|ge|ne|not|and|or|cmp)\b', Operator.Word), | |
| 61 # common delimiters | |
| 62 (r's/(\\\\|\\[^\\]|[^\\/])*/(\\\\|\\[^\\]|[^\\/])*/[egimosx]*', | |
| 63 String.Regex), | |
| 64 (r's!(\\\\|\\!|[^!])*!(\\\\|\\!|[^!])*![egimosx]*', String.Regex), | |
| 65 (r's\\(\\\\|[^\\])*\\(\\\\|[^\\])*\\[egimosx]*', String.Regex), | |
| 66 (r's@(\\\\|\\[^\\]|[^\\@])*@(\\\\|\\[^\\]|[^\\@])*@[egimosx]*', | |
| 67 String.Regex), | |
| 68 (r's%(\\\\|\\[^\\]|[^\\%])*%(\\\\|\\[^\\]|[^\\%])*%[egimosx]*', | |
| 69 String.Regex), | |
| 70 # balanced delimiters | |
| 71 (r's\{(\\\\|\\[^\\]|[^\\}])*\}\s*', String.Regex, 'balanced-regex'), | |
| 72 (r's<(\\\\|\\[^\\]|[^\\>])*>\s*', String.Regex, 'balanced-regex'), | |
| 73 (r's\[(\\\\|\\[^\\]|[^\\\]])*\]\s*', String.Regex, | |
| 74 'balanced-regex'), | |
| 75 (r's\((\\\\|\\[^\\]|[^\\)])*\)\s*', String.Regex, | |
| 76 'balanced-regex'), | |
| 77 | |
| 78 (r'm?/(\\\\|\\[^\\]|[^\\/\n])*/[gcimosx]*', String.Regex), | |
| 79 (r'm(?=[/!\\{<\[(@%$])', String.Regex, 'balanced-regex'), | |
| 80 (r'((?<==~)|(?<=\())\s*/(\\\\|\\[^\\]|[^\\/])*/[gcimosx]*', | |
| 81 String.Regex), | |
| 82 (r'\s+', Text), | |
| 83 (words(( | |
| 84 'abs', 'accept', 'alarm', 'atan2', 'bind', 'binmode', 'bless', 'caller', 'chdir', | |
| 85 'chmod', 'chomp', 'chop', 'chown', 'chr', 'chroot', 'close', 'closedir', 'connect', | |
| 86 'continue', 'cos', 'crypt', 'dbmclose', 'dbmopen', 'defined', 'delete', 'die', | |
| 87 'dump', 'each', 'endgrent', 'endhostent', 'endnetent', 'endprotoent', | |
| 88 'endpwent', 'endservent', 'eof', 'eval', 'exec', 'exists', 'exit', 'exp', 'fcntl', | |
| 89 'fileno', 'flock', 'fork', 'format', 'formline', 'getc', 'getgrent', 'getgrgid', | |
| 90 'getgrnam', 'gethostbyaddr', 'gethostbyname', 'gethostent', 'getlogin', | |
| 91 'getnetbyaddr', 'getnetbyname', 'getnetent', 'getpeername', 'getpgrp', | |
| 92 'getppid', 'getpriority', 'getprotobyname', 'getprotobynumber', | |
| 93 'getprotoent', 'getpwent', 'getpwnam', 'getpwuid', 'getservbyname', | |
| 94 'getservbyport', 'getservent', 'getsockname', 'getsockopt', 'glob', 'gmtime', | |
| 95 'goto', 'grep', 'hex', 'import', 'index', 'int', 'ioctl', 'join', 'keys', 'kill', 'last', | |
| 96 'lc', 'lcfirst', 'length', 'link', 'listen', 'local', 'localtime', 'log', 'lstat', | |
| 97 'map', 'mkdir', 'msgctl', 'msgget', 'msgrcv', 'msgsnd', 'my', 'next', 'oct', 'open', | |
| 98 'opendir', 'ord', 'our', 'pack', 'pipe', 'pop', 'pos', 'printf', | |
| 99 'prototype', 'push', 'quotemeta', 'rand', 'read', 'readdir', | |
| 100 'readline', 'readlink', 'readpipe', 'recv', 'redo', 'ref', 'rename', | |
| 101 'reverse', 'rewinddir', 'rindex', 'rmdir', 'scalar', 'seek', 'seekdir', | |
| 102 'select', 'semctl', 'semget', 'semop', 'send', 'setgrent', 'sethostent', 'setnetent', | |
| 103 'setpgrp', 'setpriority', 'setprotoent', 'setpwent', 'setservent', | |
| 104 'setsockopt', 'shift', 'shmctl', 'shmget', 'shmread', 'shmwrite', 'shutdown', | |
| 105 'sin', 'sleep', 'socket', 'socketpair', 'sort', 'splice', 'split', 'sprintf', 'sqrt', | |
| 106 'srand', 'stat', 'study', 'substr', 'symlink', 'syscall', 'sysopen', 'sysread', | |
| 107 'sysseek', 'system', 'syswrite', 'tell', 'telldir', 'tie', 'tied', 'time', 'times', 'tr', | |
| 108 'truncate', 'uc', 'ucfirst', 'umask', 'undef', 'unlink', 'unpack', 'unshift', 'untie', | |
| 109 'utime', 'values', 'vec', 'wait', 'waitpid', 'wantarray', 'warn', 'write'), suffix=r'\b'), | |
| 110 Name.Builtin), | |
| 111 (r'((__(DATA|DIE|WARN)__)|(STD(IN|OUT|ERR)))\b', Name.Builtin.Pseudo), | |
| 112 (r'(<<)([\'"]?)([a-zA-Z_]\w*)(\2;?\n.*?\n)(\3)(\n)', | |
| 113 bygroups(String, String, String.Delimiter, String, String.Delimiter, Text)), | |
| 114 (r'__END__', Comment.Preproc, 'end-part'), | |
| 115 (r'\$\^[ADEFHILMOPSTWX]', Name.Variable.Global), | |
| 116 (r"\$[\\\"\[\]'&`+*.,;=%~?@$!<>(^|/-](?!\w)", Name.Variable.Global), | |
| 117 (r'[$@%#]+', Name.Variable, 'varname'), | |
| 118 (r'0_?[0-7]+(_[0-7]+)*', Number.Oct), | |
| 119 (r'0x[0-9A-Fa-f]+(_[0-9A-Fa-f]+)*', Number.Hex), | |
| 120 (r'0b[01]+(_[01]+)*', Number.Bin), | |
| 121 (r'(?i)(\d*(_\d*)*\.\d+(_\d*)*|\d+(_\d*)*\.\d+(_\d*)*)(e[+-]?\d+)?', | |
| 122 Number.Float), | |
| 123 (r'(?i)\d+(_\d*)*e[+-]?\d+(_\d*)*', Number.Float), | |
| 124 (r'\d+(_\d+)*', Number.Integer), | |
| 125 (r"'(\\\\|\\[^\\]|[^'\\])*'", String), | |
| 126 (r'"(\\\\|\\[^\\]|[^"\\])*"', String), | |
| 127 (r'`(\\\\|\\[^\\]|[^`\\])*`', String.Backtick), | |
| 128 (r'<([^\s>]+)>', String.Regex), | |
| 129 (r'(q|qq|qw|qr|qx)\{', String.Other, 'cb-string'), | |
| 130 (r'(q|qq|qw|qr|qx)\(', String.Other, 'rb-string'), | |
| 131 (r'(q|qq|qw|qr|qx)\[', String.Other, 'sb-string'), | |
| 132 (r'(q|qq|qw|qr|qx)\<', String.Other, 'lt-string'), | |
| 133 (r'(q|qq|qw|qr|qx)([\W_])(.|\n)*?\2', String.Other), | |
| 134 (r'(package)(\s+)([a-zA-Z_]\w*(?:::[a-zA-Z_]\w*)*)', | |
| 135 bygroups(Keyword, Text, Name.Namespace)), | |
| 136 (r'(use|require|no)(\s+)([a-zA-Z_]\w*(?:::[a-zA-Z_]\w*)*)', | |
| 137 bygroups(Keyword, Text, Name.Namespace)), | |
| 138 (r'(sub)(\s+)', bygroups(Keyword, Text), 'funcname'), | |
| 139 (words(( | |
| 140 'no', 'package', 'require', 'use'), suffix=r'\b'), | |
| 141 Keyword), | |
| 142 (r'(\[\]|\*\*|::|<<|>>|>=|<=>|<=|={3}|!=|=~|' | |
| 143 r'!~|&&?|\|\||\.{1,3})', Operator), | |
| 144 (r'[-+/*%=<>&^|!\\~]=?', Operator), | |
| 145 (r'[()\[\]:;,<>/?{}]', Punctuation), # yes, there's no shortage | |
| 146 # of punctuation in Perl! | |
| 147 (r'(?=\w)', Name, 'name'), | |
| 148 ], | |
| 149 'format': [ | |
| 150 (r'\.\n', String.Interpol, '#pop'), | |
| 151 (r'[^\n]*\n', String.Interpol), | |
| 152 ], | |
| 153 'varname': [ | |
| 154 (r'\s+', Text), | |
| 155 (r'\{', Punctuation, '#pop'), # hash syntax? | |
| 156 (r'\)|,', Punctuation, '#pop'), # argument specifier | |
| 157 (r'\w+::', Name.Namespace), | |
| 158 (r'[\w:]+', Name.Variable, '#pop'), | |
| 159 ], | |
| 160 'name': [ | |
| 161 (r'[a-zA-Z_]\w*(::[a-zA-Z_]\w*)*(::)?(?=\s*->)', Name.Namespace, '#pop'), | |
| 162 (r'[a-zA-Z_]\w*(::[a-zA-Z_]\w*)*::', Name.Namespace, '#pop'), | |
| 163 (r'[\w:]+', Name, '#pop'), | |
| 164 (r'[A-Z_]+(?=\W)', Name.Constant, '#pop'), | |
| 165 (r'(?=\W)', Text, '#pop'), | |
| 166 ], | |
| 167 'funcname': [ | |
| 168 (r'[a-zA-Z_]\w*[!?]?', Name.Function), | |
| 169 (r'\s+', Text), | |
| 170 # argument declaration | |
| 171 (r'(\([$@%]*\))(\s*)', bygroups(Punctuation, Text)), | |
| 172 (r';', Punctuation, '#pop'), | |
| 173 (r'.*?\{', Punctuation, '#pop'), | |
| 174 ], | |
| 175 'cb-string': [ | |
| 176 (r'\\[{}\\]', String.Other), | |
| 177 (r'\\', String.Other), | |
| 178 (r'\{', String.Other, 'cb-string'), | |
| 179 (r'\}', String.Other, '#pop'), | |
| 180 (r'[^{}\\]+', String.Other) | |
| 181 ], | |
| 182 'rb-string': [ | |
| 183 (r'\\[()\\]', String.Other), | |
| 184 (r'\\', String.Other), | |
| 185 (r'\(', String.Other, 'rb-string'), | |
| 186 (r'\)', String.Other, '#pop'), | |
| 187 (r'[^()]+', String.Other) | |
| 188 ], | |
| 189 'sb-string': [ | |
| 190 (r'\\[\[\]\\]', String.Other), | |
| 191 (r'\\', String.Other), | |
| 192 (r'\[', String.Other, 'sb-string'), | |
| 193 (r'\]', String.Other, '#pop'), | |
| 194 (r'[^\[\]]+', String.Other) | |
| 195 ], | |
| 196 'lt-string': [ | |
| 197 (r'\\[<>\\]', String.Other), | |
| 198 (r'\\', String.Other), | |
| 199 (r'\<', String.Other, 'lt-string'), | |
| 200 (r'\>', String.Other, '#pop'), | |
| 201 (r'[^<>]+', String.Other) | |
| 202 ], | |
| 203 'end-part': [ | |
| 204 (r'.+', Comment.Preproc, '#pop') | |
| 205 ] | |
| 206 } | |
| 207 | |
| 208 def analyse_text(text): | |
| 209 if shebang_matches(text, r'perl'): | |
| 210 return True | |
| 211 if re.search(r'(?:my|our)\s+[$@%(]', text): | |
| 212 return 0.9 | |
| 213 | |
| 214 | |
| 215 class Perl6Lexer(ExtendedRegexLexer): | |
| 216 """ | |
| 217 For `Perl 6 <http://www.perl6.org>`_ source code. | |
| 218 | |
| 219 .. versionadded:: 2.0 | |
| 220 """ | |
| 221 | |
| 222 name = 'Perl6' | |
| 223 aliases = ['perl6', 'pl6'] | |
| 224 filenames = ['*.pl', '*.pm', '*.nqp', '*.p6', '*.6pl', '*.p6l', '*.pl6', | |
| 225 '*.6pm', '*.p6m', '*.pm6', '*.t'] | |
| 226 mimetypes = ['text/x-perl6', 'application/x-perl6'] | |
| 227 flags = re.MULTILINE | re.DOTALL | re.UNICODE | |
| 228 | |
| 229 PERL6_IDENTIFIER_RANGE = r"['\w:-]" | |
| 230 | |
| 231 PERL6_KEYWORDS = ( | |
| 232 'BEGIN', 'CATCH', 'CHECK', 'CONTROL', 'END', 'ENTER', 'FIRST', 'INIT', | |
| 233 'KEEP', 'LAST', 'LEAVE', 'NEXT', 'POST', 'PRE', 'START', 'TEMP', | |
| 234 'UNDO', 'as', 'assoc', 'async', 'augment', 'binary', 'break', 'but', | |
| 235 'cached', 'category', 'class', 'constant', 'contend', 'continue', | |
| 236 'copy', 'deep', 'default', 'defequiv', 'defer', 'die', 'do', 'else', | |
| 237 'elsif', 'enum', 'equiv', 'exit', 'export', 'fail', 'fatal', 'for', | |
| 238 'gather', 'given', 'goto', 'grammar', 'handles', 'has', 'if', 'inline', | |
| 239 'irs', 'is', 'last', 'leave', 'let', 'lift', 'loop', 'looser', 'macro', | |
| 240 'make', 'maybe', 'method', 'module', 'multi', 'my', 'next', 'of', | |
| 241 'ofs', 'only', 'oo', 'ors', 'our', 'package', 'parsed', 'prec', | |
| 242 'proto', 'readonly', 'redo', 'ref', 'regex', 'reparsed', 'repeat', | |
| 243 'require', 'required', 'return', 'returns', 'role', 'rule', 'rw', | |
| 244 'self', 'slang', 'state', 'sub', 'submethod', 'subset', 'supersede', | |
| 245 'take', 'temp', 'tighter', 'token', 'trusts', 'try', 'unary', | |
| 246 'unless', 'until', 'use', 'warn', 'when', 'where', 'while', 'will', | |
| 247 ) | |
| 248 | |
| 249 PERL6_BUILTINS = ( | |
| 250 'ACCEPTS', 'HOW', 'REJECTS', 'VAR', 'WHAT', 'WHENCE', 'WHERE', 'WHICH', | |
| 251 'WHO', 'abs', 'acos', 'acosec', 'acosech', 'acosh', 'acotan', 'acotanh', | |
| 252 'all', 'any', 'approx', 'arity', 'asec', 'asech', 'asin', 'asinh', | |
| 253 'assuming', 'atan', 'atan2', 'atanh', 'attr', 'bless', 'body', 'by', | |
| 254 'bytes', 'caller', 'callsame', 'callwith', 'can', 'capitalize', 'cat', | |
| 255 'ceiling', 'chars', 'chmod', 'chomp', 'chop', 'chr', 'chroot', | |
| 256 'circumfix', 'cis', 'classify', 'clone', 'close', 'cmp_ok', 'codes', | |
| 257 'comb', 'connect', 'contains', 'context', 'cos', 'cosec', 'cosech', | |
| 258 'cosh', 'cotan', 'cotanh', 'count', 'defined', 'delete', 'diag', | |
| 259 'dies_ok', 'does', 'e', 'each', 'eager', 'elems', 'end', 'eof', 'eval', | |
| 260 'eval_dies_ok', 'eval_elsewhere', 'eval_lives_ok', 'evalfile', 'exists', | |
| 261 'exp', 'first', 'flip', 'floor', 'flunk', 'flush', 'fmt', 'force_todo', | |
| 262 'fork', 'from', 'getc', 'gethost', 'getlogin', 'getpeername', 'getpw', | |
| 263 'gmtime', 'graphs', 'grep', 'hints', 'hyper', 'im', 'index', 'infix', | |
| 264 'invert', 'is_approx', 'is_deeply', 'isa', 'isa_ok', 'isnt', 'iterator', | |
| 265 'join', 'key', 'keys', 'kill', 'kv', 'lastcall', 'lazy', 'lc', 'lcfirst', | |
| 266 'like', 'lines', 'link', 'lives_ok', 'localtime', 'log', 'log10', 'map', | |
| 267 'max', 'min', 'minmax', 'name', 'new', 'nextsame', 'nextwith', 'nfc', | |
| 268 'nfd', 'nfkc', 'nfkd', 'nok_error', 'nonce', 'none', 'normalize', 'not', | |
| 269 'nothing', 'ok', 'once', 'one', 'open', 'opendir', 'operator', 'ord', | |
| 270 'p5chomp', 'p5chop', 'pack', 'pair', 'pairs', 'pass', 'perl', 'pi', | |
| 271 'pick', 'plan', 'plan_ok', 'polar', 'pop', 'pos', 'postcircumfix', | |
| 272 'postfix', 'pred', 'prefix', 'print', 'printf', 'push', 'quasi', | |
| 273 'quotemeta', 'rand', 're', 'read', 'readdir', 'readline', 'reduce', | |
| 274 'reverse', 'rewind', 'rewinddir', 'rindex', 'roots', 'round', | |
| 275 'roundrobin', 'run', 'runinstead', 'sameaccent', 'samecase', 'say', | |
| 276 'sec', 'sech', 'sech', 'seek', 'shape', 'shift', 'sign', 'signature', | |
| 277 'sin', 'sinh', 'skip', 'skip_rest', 'sleep', 'slurp', 'sort', 'splice', | |
| 278 'split', 'sprintf', 'sqrt', 'srand', 'strand', 'subst', 'substr', 'succ', | |
| 279 'sum', 'symlink', 'tan', 'tanh', 'throws_ok', 'time', 'times', 'to', | |
| 280 'todo', 'trim', 'trim_end', 'trim_start', 'true', 'truncate', 'uc', | |
| 281 'ucfirst', 'undef', 'undefine', 'uniq', 'unlike', 'unlink', 'unpack', | |
| 282 'unpolar', 'unshift', 'unwrap', 'use_ok', 'value', 'values', 'vec', | |
| 283 'version_lt', 'void', 'wait', 'want', 'wrap', 'write', 'zip', | |
| 284 ) | |
| 285 | |
| 286 PERL6_BUILTIN_CLASSES = ( | |
| 287 'Abstraction', 'Any', 'AnyChar', 'Array', 'Associative', 'Bag', 'Bit', | |
| 288 'Blob', 'Block', 'Bool', 'Buf', 'Byte', 'Callable', 'Capture', 'Char', 'Class', | |
| 289 'Code', 'Codepoint', 'Comparator', 'Complex', 'Decreasing', 'Exception', | |
| 290 'Failure', 'False', 'Grammar', 'Grapheme', 'Hash', 'IO', 'Increasing', | |
| 291 'Int', 'Junction', 'KeyBag', 'KeyExtractor', 'KeyHash', 'KeySet', | |
| 292 'KitchenSink', 'List', 'Macro', 'Mapping', 'Match', 'Matcher', 'Method', | |
| 293 'Module', 'Num', 'Object', 'Ordered', 'Ordering', 'OrderingPair', | |
| 294 'Package', 'Pair', 'Positional', 'Proxy', 'Range', 'Rat', 'Regex', | |
| 295 'Role', 'Routine', 'Scalar', 'Seq', 'Set', 'Signature', 'Str', 'StrLen', | |
| 296 'StrPos', 'Sub', 'Submethod', 'True', 'UInt', 'Undef', 'Version', 'Void', | |
| 297 'Whatever', 'bit', 'bool', 'buf', 'buf1', 'buf16', 'buf2', 'buf32', | |
| 298 'buf4', 'buf64', 'buf8', 'complex', 'int', 'int1', 'int16', 'int2', | |
| 299 'int32', 'int4', 'int64', 'int8', 'num', 'rat', 'rat1', 'rat16', 'rat2', | |
| 300 'rat32', 'rat4', 'rat64', 'rat8', 'uint', 'uint1', 'uint16', 'uint2', | |
| 301 'uint32', 'uint4', 'uint64', 'uint8', 'utf16', 'utf32', 'utf8', | |
| 302 ) | |
| 303 | |
| 304 PERL6_OPERATORS = ( | |
| 305 'X', 'Z', 'after', 'also', 'and', 'andthen', 'before', 'cmp', 'div', | |
| 306 'eq', 'eqv', 'extra', 'ff', 'fff', 'ge', 'gt', 'le', 'leg', 'lt', 'm', | |
| 307 'mm', 'mod', 'ne', 'or', 'orelse', 'rx', 's', 'tr', 'x', 'xor', 'xx', | |
| 308 '++', '--', '**', '!', '+', '-', '~', '?', '|', '||', '+^', '~^', '?^', | |
| 309 '^', '*', '/', '%', '%%', '+&', '+<', '+>', '~&', '~<', '~>', '?&', | |
| 310 'gcd', 'lcm', '+', '-', '+|', '+^', '~|', '~^', '?|', '?^', | |
| 311 '~', '&', '^', 'but', 'does', '<=>', '..', '..^', '^..', '^..^', | |
| 312 '!=', '==', '<', '<=', '>', '>=', '~~', '===', '!eqv', | |
| 313 '&&', '||', '^^', '//', 'min', 'max', '??', '!!', 'ff', 'fff', 'so', | |
| 314 'not', '<==', '==>', '<<==', '==>>', | |
| 315 ) | |
| 316 | |
| 317 # Perl 6 has a *lot* of possible bracketing characters | |
| 318 # this list was lifted from STD.pm6 (https://github.com/perl6/std) | |
| 319 PERL6_BRACKETS = { | |
| 320 u'\u0028': u'\u0029', u'\u003c': u'\u003e', u'\u005b': u'\u005d', | |
| 321 u'\u007b': u'\u007d', u'\u00ab': u'\u00bb', u'\u0f3a': u'\u0f3b', | |
| 322 u'\u0f3c': u'\u0f3d', u'\u169b': u'\u169c', u'\u2018': u'\u2019', | |
| 323 u'\u201a': u'\u2019', u'\u201b': u'\u2019', u'\u201c': u'\u201d', | |
| 324 u'\u201e': u'\u201d', u'\u201f': u'\u201d', u'\u2039': u'\u203a', | |
| 325 u'\u2045': u'\u2046', u'\u207d': u'\u207e', u'\u208d': u'\u208e', | |
| 326 u'\u2208': u'\u220b', u'\u2209': u'\u220c', u'\u220a': u'\u220d', | |
| 327 u'\u2215': u'\u29f5', u'\u223c': u'\u223d', u'\u2243': u'\u22cd', | |
| 328 u'\u2252': u'\u2253', u'\u2254': u'\u2255', u'\u2264': u'\u2265', | |
| 329 u'\u2266': u'\u2267', u'\u2268': u'\u2269', u'\u226a': u'\u226b', | |
| 330 u'\u226e': u'\u226f', u'\u2270': u'\u2271', u'\u2272': u'\u2273', | |
| 331 u'\u2274': u'\u2275', u'\u2276': u'\u2277', u'\u2278': u'\u2279', | |
| 332 u'\u227a': u'\u227b', u'\u227c': u'\u227d', u'\u227e': u'\u227f', | |
| 333 u'\u2280': u'\u2281', u'\u2282': u'\u2283', u'\u2284': u'\u2285', | |
| 334 u'\u2286': u'\u2287', u'\u2288': u'\u2289', u'\u228a': u'\u228b', | |
| 335 u'\u228f': u'\u2290', u'\u2291': u'\u2292', u'\u2298': u'\u29b8', | |
| 336 u'\u22a2': u'\u22a3', u'\u22a6': u'\u2ade', u'\u22a8': u'\u2ae4', | |
| 337 u'\u22a9': u'\u2ae3', u'\u22ab': u'\u2ae5', u'\u22b0': u'\u22b1', | |
| 338 u'\u22b2': u'\u22b3', u'\u22b4': u'\u22b5', u'\u22b6': u'\u22b7', | |
| 339 u'\u22c9': u'\u22ca', u'\u22cb': u'\u22cc', u'\u22d0': u'\u22d1', | |
| 340 u'\u22d6': u'\u22d7', u'\u22d8': u'\u22d9', u'\u22da': u'\u22db', | |
| 341 u'\u22dc': u'\u22dd', u'\u22de': u'\u22df', u'\u22e0': u'\u22e1', | |
| 342 u'\u22e2': u'\u22e3', u'\u22e4': u'\u22e5', u'\u22e6': u'\u22e7', | |
| 343 u'\u22e8': u'\u22e9', u'\u22ea': u'\u22eb', u'\u22ec': u'\u22ed', | |
| 344 u'\u22f0': u'\u22f1', u'\u22f2': u'\u22fa', u'\u22f3': u'\u22fb', | |
| 345 u'\u22f4': u'\u22fc', u'\u22f6': u'\u22fd', u'\u22f7': u'\u22fe', | |
| 346 u'\u2308': u'\u2309', u'\u230a': u'\u230b', u'\u2329': u'\u232a', | |
| 347 u'\u23b4': u'\u23b5', u'\u2768': u'\u2769', u'\u276a': u'\u276b', | |
| 348 u'\u276c': u'\u276d', u'\u276e': u'\u276f', u'\u2770': u'\u2771', | |
| 349 u'\u2772': u'\u2773', u'\u2774': u'\u2775', u'\u27c3': u'\u27c4', | |
| 350 u'\u27c5': u'\u27c6', u'\u27d5': u'\u27d6', u'\u27dd': u'\u27de', | |
| 351 u'\u27e2': u'\u27e3', u'\u27e4': u'\u27e5', u'\u27e6': u'\u27e7', | |
| 352 u'\u27e8': u'\u27e9', u'\u27ea': u'\u27eb', u'\u2983': u'\u2984', | |
| 353 u'\u2985': u'\u2986', u'\u2987': u'\u2988', u'\u2989': u'\u298a', | |
| 354 u'\u298b': u'\u298c', u'\u298d': u'\u298e', u'\u298f': u'\u2990', | |
| 355 u'\u2991': u'\u2992', u'\u2993': u'\u2994', u'\u2995': u'\u2996', | |
| 356 u'\u2997': u'\u2998', u'\u29c0': u'\u29c1', u'\u29c4': u'\u29c5', | |
| 357 u'\u29cf': u'\u29d0', u'\u29d1': u'\u29d2', u'\u29d4': u'\u29d5', | |
| 358 u'\u29d8': u'\u29d9', u'\u29da': u'\u29db', u'\u29f8': u'\u29f9', | |
| 359 u'\u29fc': u'\u29fd', u'\u2a2b': u'\u2a2c', u'\u2a2d': u'\u2a2e', | |
| 360 u'\u2a34': u'\u2a35', u'\u2a3c': u'\u2a3d', u'\u2a64': u'\u2a65', | |
| 361 u'\u2a79': u'\u2a7a', u'\u2a7d': u'\u2a7e', u'\u2a7f': u'\u2a80', | |
| 362 u'\u2a81': u'\u2a82', u'\u2a83': u'\u2a84', u'\u2a8b': u'\u2a8c', | |
| 363 u'\u2a91': u'\u2a92', u'\u2a93': u'\u2a94', u'\u2a95': u'\u2a96', | |
| 364 u'\u2a97': u'\u2a98', u'\u2a99': u'\u2a9a', u'\u2a9b': u'\u2a9c', | |
| 365 u'\u2aa1': u'\u2aa2', u'\u2aa6': u'\u2aa7', u'\u2aa8': u'\u2aa9', | |
| 366 u'\u2aaa': u'\u2aab', u'\u2aac': u'\u2aad', u'\u2aaf': u'\u2ab0', | |
| 367 u'\u2ab3': u'\u2ab4', u'\u2abb': u'\u2abc', u'\u2abd': u'\u2abe', | |
| 368 u'\u2abf': u'\u2ac0', u'\u2ac1': u'\u2ac2', u'\u2ac3': u'\u2ac4', | |
| 369 u'\u2ac5': u'\u2ac6', u'\u2acd': u'\u2ace', u'\u2acf': u'\u2ad0', | |
| 370 u'\u2ad1': u'\u2ad2', u'\u2ad3': u'\u2ad4', u'\u2ad5': u'\u2ad6', | |
| 371 u'\u2aec': u'\u2aed', u'\u2af7': u'\u2af8', u'\u2af9': u'\u2afa', | |
| 372 u'\u2e02': u'\u2e03', u'\u2e04': u'\u2e05', u'\u2e09': u'\u2e0a', | |
| 373 u'\u2e0c': u'\u2e0d', u'\u2e1c': u'\u2e1d', u'\u2e20': u'\u2e21', | |
| 374 u'\u3008': u'\u3009', u'\u300a': u'\u300b', u'\u300c': u'\u300d', | |
| 375 u'\u300e': u'\u300f', u'\u3010': u'\u3011', u'\u3014': u'\u3015', | |
| 376 u'\u3016': u'\u3017', u'\u3018': u'\u3019', u'\u301a': u'\u301b', | |
| 377 u'\u301d': u'\u301e', u'\ufd3e': u'\ufd3f', u'\ufe17': u'\ufe18', | |
| 378 u'\ufe35': u'\ufe36', u'\ufe37': u'\ufe38', u'\ufe39': u'\ufe3a', | |
| 379 u'\ufe3b': u'\ufe3c', u'\ufe3d': u'\ufe3e', u'\ufe3f': u'\ufe40', | |
| 380 u'\ufe41': u'\ufe42', u'\ufe43': u'\ufe44', u'\ufe47': u'\ufe48', | |
| 381 u'\ufe59': u'\ufe5a', u'\ufe5b': u'\ufe5c', u'\ufe5d': u'\ufe5e', | |
| 382 u'\uff08': u'\uff09', u'\uff1c': u'\uff1e', u'\uff3b': u'\uff3d', | |
| 383 u'\uff5b': u'\uff5d', u'\uff5f': u'\uff60', u'\uff62': u'\uff63', | |
| 384 } | |
| 385 | |
| 386 def _build_word_match(words, boundary_regex_fragment=None, prefix='', suffix=''): | |
| 387 if boundary_regex_fragment is None: | |
| 388 return r'\b(' + prefix + r'|'.join(re.escape(x) for x in words) + \ | |
| 389 suffix + r')\b' | |
| 390 else: | |
| 391 return r'(?<!' + boundary_regex_fragment + r')' + prefix + r'(' + \ | |
| 392 r'|'.join(re.escape(x) for x in words) + r')' + suffix + r'(?!' + \ | |
| 393 boundary_regex_fragment + r')' | |
| 394 | |
| 395 def brackets_callback(token_class): | |
| 396 def callback(lexer, match, context): | |
| 397 groups = match.groupdict() | |
| 398 opening_chars = groups['delimiter'] | |
| 399 n_chars = len(opening_chars) | |
| 400 adverbs = groups.get('adverbs') | |
| 401 | |
| 402 closer = Perl6Lexer.PERL6_BRACKETS.get(opening_chars[0]) | |
| 403 text = context.text | |
| 404 | |
| 405 if closer is None: # it's not a mirrored character, which means we | |
| 406 # just need to look for the next occurrence | |
| 407 | |
| 408 end_pos = text.find(opening_chars, match.start('delimiter') + n_chars) | |
| 409 else: # we need to look for the corresponding closing character, | |
| 410 # keep nesting in mind | |
| 411 closing_chars = closer * n_chars | |
| 412 nesting_level = 1 | |
| 413 | |
| 414 search_pos = match.start('delimiter') | |
| 415 | |
| 416 while nesting_level > 0: | |
| 417 next_open_pos = text.find(opening_chars, search_pos + n_chars) | |
| 418 next_close_pos = text.find(closing_chars, search_pos + n_chars) | |
| 419 | |
| 420 if next_close_pos == -1: | |
| 421 next_close_pos = len(text) | |
| 422 nesting_level = 0 | |
| 423 elif next_open_pos != -1 and next_open_pos < next_close_pos: | |
| 424 nesting_level += 1 | |
| 425 search_pos = next_open_pos | |
| 426 else: # next_close_pos < next_open_pos | |
| 427 nesting_level -= 1 | |
| 428 search_pos = next_close_pos | |
| 429 | |
| 430 end_pos = next_close_pos | |
| 431 | |
| 432 if end_pos < 0: # if we didn't find a closer, just highlight the | |
| 433 # rest of the text in this class | |
| 434 end_pos = len(text) | |
| 435 | |
| 436 if adverbs is not None and re.search(r':to\b', adverbs): | |
| 437 heredoc_terminator = text[match.start('delimiter') + n_chars:end_pos] | |
| 438 end_heredoc = re.search(r'^\s*' + re.escape(heredoc_terminator) + | |
| 439 r'\s*$', text[end_pos:], re.MULTILINE) | |
| 440 | |
| 441 if end_heredoc: | |
| 442 end_pos += end_heredoc.end() | |
| 443 else: | |
| 444 end_pos = len(text) | |
| 445 | |
| 446 yield match.start(), token_class, text[match.start():end_pos + n_chars] | |
| 447 context.pos = end_pos + n_chars | |
| 448 | |
| 449 return callback | |
| 450 | |
| 451 def opening_brace_callback(lexer, match, context): | |
| 452 stack = context.stack | |
| 453 | |
| 454 yield match.start(), Text, context.text[match.start():match.end()] | |
| 455 context.pos = match.end() | |
| 456 | |
| 457 # if we encounter an opening brace and we're one level | |
| 458 # below a token state, it means we need to increment | |
| 459 # the nesting level for braces so we know later when | |
| 460 # we should return to the token rules. | |
| 461 if len(stack) > 2 and stack[-2] == 'token': | |
| 462 context.perl6_token_nesting_level += 1 | |
| 463 | |
| 464 def closing_brace_callback(lexer, match, context): | |
| 465 stack = context.stack | |
| 466 | |
| 467 yield match.start(), Text, context.text[match.start():match.end()] | |
| 468 context.pos = match.end() | |
| 469 | |
| 470 # if we encounter a free closing brace and we're one level | |
| 471 # below a token state, it means we need to check the nesting | |
| 472 # level to see if we need to return to the token state. | |
| 473 if len(stack) > 2 and stack[-2] == 'token': | |
| 474 context.perl6_token_nesting_level -= 1 | |
| 475 if context.perl6_token_nesting_level == 0: | |
| 476 stack.pop() | |
| 477 | |
| 478 def embedded_perl6_callback(lexer, match, context): | |
| 479 context.perl6_token_nesting_level = 1 | |
| 480 yield match.start(), Text, context.text[match.start():match.end()] | |
| 481 context.pos = match.end() | |
| 482 context.stack.append('root') | |
| 483 | |
| 484 # If you're modifying these rules, be careful if you need to process '{' or '}' | |
| 485 # characters. We have special logic for processing these characters (due to the fact | |
| 486 # that you can nest Perl 6 code in regex blocks), so if you need to process one of | |
| 487 # them, make sure you also process the corresponding one! | |
| 488 tokens = { | |
| 489 'common': [ | |
| 490 (r'#[`|=](?P<delimiter>(?P<first_char>[' + ''.join(PERL6_BRACKETS) + r'])(?P=first_char)*)', | |
| 491 brackets_callback(Comment.Multiline)), | |
| 492 (r'#[^\n]*$', Comment.Single), | |
| 493 (r'^(\s*)=begin\s+(\w+)\b.*?^\1=end\s+\2', Comment.Multiline), | |
| 494 (r'^(\s*)=for.*?\n\s*?\n', Comment.Multiline), | |
| 495 (r'^=.*?\n\s*?\n', Comment.Multiline), | |
| 496 (r'(regex|token|rule)(\s*' + PERL6_IDENTIFIER_RANGE + '+:sym)', | |
| 497 bygroups(Keyword, Name), 'token-sym-brackets'), | |
| 498 (r'(regex|token|rule)(?!' + PERL6_IDENTIFIER_RANGE + r')(\s*' + PERL6_IDENTIFIER_RANGE + '+)?', | |
| 499 bygroups(Keyword, Name), 'pre-token'), | |
| 500 # deal with a special case in the Perl 6 grammar (role q { ... }) | |
| 501 (r'(role)(\s+)(q)(\s*)', bygroups(Keyword, Text, Name, Text)), | |
| 502 (_build_word_match(PERL6_KEYWORDS, PERL6_IDENTIFIER_RANGE), Keyword), | |
| 503 (_build_word_match(PERL6_BUILTIN_CLASSES, PERL6_IDENTIFIER_RANGE, suffix='(?::[UD])?'), | |
| 504 Name.Builtin), | |
| 505 (_build_word_match(PERL6_BUILTINS, PERL6_IDENTIFIER_RANGE), Name.Builtin), | |
| 506 # copied from PerlLexer | |
| 507 (r'[$@%&][.^:?=!~]?' + PERL6_IDENTIFIER_RANGE + u'+(?:<<.*?>>|<.*?>|«.*?»)*', | |
| 508 Name.Variable), | |
| 509 (r'\$[!/](?:<<.*?>>|<.*?>|«.*?»)*', Name.Variable.Global), | |
| 510 (r'::\?\w+', Name.Variable.Global), | |
| 511 (r'[$@%&]\*' + PERL6_IDENTIFIER_RANGE + u'+(?:<<.*?>>|<.*?>|«.*?»)*', | |
| 512 Name.Variable.Global), | |
| 513 (r'\$(?:<.*?>)+', Name.Variable), | |
| 514 (r'(?:q|qq|Q)[a-zA-Z]?\s*(?P<adverbs>:[\w\s:]+)?\s*(?P<delimiter>(?P<first_char>[^0-9a-zA-Z:\s])' | |
| 515 r'(?P=first_char)*)', brackets_callback(String)), | |
| 516 # copied from PerlLexer | |
| 517 (r'0_?[0-7]+(_[0-7]+)*', Number.Oct), | |
| 518 (r'0x[0-9A-Fa-f]+(_[0-9A-Fa-f]+)*', Number.Hex), | |
| 519 (r'0b[01]+(_[01]+)*', Number.Bin), | |
| 520 (r'(?i)(\d*(_\d*)*\.\d+(_\d*)*|\d+(_\d*)*\.\d+(_\d*)*)(e[+-]?\d+)?', | |
| 521 Number.Float), | |
| 522 (r'(?i)\d+(_\d*)*e[+-]?\d+(_\d*)*', Number.Float), | |
| 523 (r'\d+(_\d+)*', Number.Integer), | |
| 524 (r'(?<=~~)\s*/(?:\\\\|\\/|.)*?/', String.Regex), | |
| 525 (r'(?<=[=(,])\s*/(?:\\\\|\\/|.)*?/', String.Regex), | |
| 526 (r'm\w+(?=\()', Name), | |
| 527 (r'(?:m|ms|rx)\s*(?P<adverbs>:[\w\s:]+)?\s*(?P<delimiter>(?P<first_char>[^\w:\s])' | |
| 528 r'(?P=first_char)*)', brackets_callback(String.Regex)), | |
| 529 (r'(?:s|ss|tr)\s*(?::[\w\s:]+)?\s*/(?:\\\\|\\/|.)*?/(?:\\\\|\\/|.)*?/', | |
| 530 String.Regex), | |
| 531 (r'<[^\s=].*?\S>', String), | |
| 532 (_build_word_match(PERL6_OPERATORS), Operator), | |
| 533 (r'\w' + PERL6_IDENTIFIER_RANGE + '*', Name), | |
| 534 (r"'(\\\\|\\[^\\]|[^'\\])*'", String), | |
| 535 (r'"(\\\\|\\[^\\]|[^"\\])*"', String), | |
| 536 ], | |
| 537 'root': [ | |
| 538 include('common'), | |
| 539 (r'\{', opening_brace_callback), | |
| 540 (r'\}', closing_brace_callback), | |
| 541 (r'.+?', Text), | |
| 542 ], | |
| 543 'pre-token': [ | |
| 544 include('common'), | |
| 545 (r'\{', Text, ('#pop', 'token')), | |
| 546 (r'.+?', Text), | |
| 547 ], | |
| 548 'token-sym-brackets': [ | |
| 549 (r'(?P<delimiter>(?P<first_char>[' + ''.join(PERL6_BRACKETS) + '])(?P=first_char)*)', | |
| 550 brackets_callback(Name), ('#pop', 'pre-token')), | |
| 551 default(('#pop', 'pre-token')), | |
| 552 ], | |
| 553 'token': [ | |
| 554 (r'\}', Text, '#pop'), | |
| 555 (r'(?<=:)(?:my|our|state|constant|temp|let).*?;', using(this)), | |
| 556 # make sure that quotes in character classes aren't treated as strings | |
| 557 (r'<(?:[-!?+.]\s*)?\[.*?\]>', String.Regex), | |
| 558 # make sure that '#' characters in quotes aren't treated as comments | |
| 559 (r"(?<!\\)'(\\\\|\\[^\\]|[^'\\])*'", String.Regex), | |
| 560 (r'(?<!\\)"(\\\\|\\[^\\]|[^"\\])*"', String.Regex), | |
| 561 (r'#.*?$', Comment.Single), | |
| 562 (r'\{', embedded_perl6_callback), | |
| 563 ('.+?', String.Regex), | |
| 564 ], | |
| 565 } | |
| 566 | |
| 567 def analyse_text(text): | |
| 568 def strip_pod(lines): | |
| 569 in_pod = False | |
| 570 stripped_lines = [] | |
| 571 | |
| 572 for line in lines: | |
| 573 if re.match(r'^=(?:end|cut)', line): | |
| 574 in_pod = False | |
| 575 elif re.match(r'^=\w+', line): | |
| 576 in_pod = True | |
| 577 elif not in_pod: | |
| 578 stripped_lines.append(line) | |
| 579 | |
| 580 return stripped_lines | |
| 581 | |
| 582 # XXX handle block comments | |
| 583 lines = text.splitlines() | |
| 584 lines = strip_pod(lines) | |
| 585 text = '\n'.join(lines) | |
| 586 | |
| 587 if shebang_matches(text, r'perl6|rakudo|niecza|pugs'): | |
| 588 return True | |
| 589 | |
| 590 saw_perl_decl = False | |
| 591 rating = False | |
| 592 | |
| 593 # check for my/our/has declarations | |
| 594 if re.search(r"(?:my|our|has)\s+(?:" + Perl6Lexer.PERL6_IDENTIFIER_RANGE + | |
| 595 r"+\s+)?[$@%&(]", text): | |
| 596 rating = 0.8 | |
| 597 saw_perl_decl = True | |
| 598 | |
| 599 for line in lines: | |
| 600 line = re.sub('#.*', '', line) | |
| 601 if re.match(r'^\s*$', line): | |
| 602 continue | |
| 603 | |
| 604 # match v6; use v6; use v6.0; use v6.0.0; | |
| 605 if re.match(r'^\s*(?:use\s+)?v6(?:\.\d(?:\.\d)?)?;', line): | |
| 606 return True | |
| 607 # match class, module, role, enum, grammar declarations | |
| 608 class_decl = re.match(r'^\s*(?:(?P<scope>my|our)\s+)?(?:module|class|role|enum|grammar)', line) | |
| 609 if class_decl: | |
| 610 if saw_perl_decl or class_decl.group('scope') is not None: | |
| 611 return True | |
| 612 rating = 0.05 | |
| 613 continue | |
| 614 break | |
| 615 | |
| 616 return rating | |
| 617 | |
| 618 def __init__(self, **options): | |
| 619 super(Perl6Lexer, self).__init__(**options) | |
| 620 self.encoding = options.get('encoding', 'utf-8') |
