1 # -*- coding: utf-8 -*- |
|
2 """ |
|
3 pygments.lexers.perl |
|
4 ~~~~~~~~~~~~~~~~~~~~ |
|
5 |
|
6 Lexers for Perl, Raku and related languages. |
|
7 |
|
8 :copyright: Copyright 2006-2021 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 <https://www.perl.org>`_ source code. |
|
26 """ |
|
27 |
|
28 name = 'Perl' |
|
29 aliases = ['perl', 'pl'] |
|
30 filenames = ['*.pl', '*.pm', '*.t', '*.perl'] |
|
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 |
|
212 result = 0 |
|
213 |
|
214 if re.search(r'(?:my|our)\s+[$@%(]', text): |
|
215 result += 0.9 |
|
216 |
|
217 if ':=' in text: |
|
218 # := is not valid Perl, but it appears in unicon, so we should |
|
219 # become less confident if we think we found Perl with := |
|
220 result /= 2 |
|
221 |
|
222 return result |
|
223 |
|
224 |
|
225 class Perl6Lexer(ExtendedRegexLexer): |
|
226 """ |
|
227 For `Raku <https://www.raku.org>`_ (a.k.a. Perl 6) source code. |
|
228 |
|
229 .. versionadded:: 2.0 |
|
230 """ |
|
231 |
|
232 name = 'Perl6' |
|
233 aliases = ['perl6', 'pl6', 'raku'] |
|
234 filenames = ['*.pl', '*.pm', '*.nqp', '*.p6', '*.6pl', '*.p6l', '*.pl6', |
|
235 '*.6pm', '*.p6m', '*.pm6', '*.t', '*.raku', '*.rakumod', |
|
236 '*.rakutest', '*.rakudoc'] |
|
237 mimetypes = ['text/x-perl6', 'application/x-perl6'] |
|
238 flags = re.MULTILINE | re.DOTALL | re.UNICODE |
|
239 |
|
240 PERL6_IDENTIFIER_RANGE = r"['\w:-]" |
|
241 |
|
242 PERL6_KEYWORDS = ( |
|
243 #Phasers |
|
244 'BEGIN','CATCH','CHECK','CLOSE','CONTROL','DOC','END','ENTER','FIRST', |
|
245 'INIT','KEEP','LAST','LEAVE','NEXT','POST','PRE','QUIT','UNDO', |
|
246 #Keywords |
|
247 'anon','augment','but','class','constant','default','does','else', |
|
248 'elsif','enum','for','gather','given','grammar','has','if','import', |
|
249 'is','let','loop','made','make','method','module','multi','my','need', |
|
250 'orwith','our','proceed','proto','repeat','require','return', |
|
251 'return-rw','returns','role','rule','state','sub','submethod','subset', |
|
252 'succeed','supersede','token','try','unit','unless','until','use', |
|
253 'when','while','with','without', |
|
254 #Traits |
|
255 'export','native','repr','required','rw','symbol', |
|
256 ) |
|
257 |
|
258 PERL6_BUILTINS = ( |
|
259 'ACCEPTS','abs','abs2rel','absolute','accept','accessed','acos', |
|
260 'acosec','acosech','acosh','acotan','acotanh','acquire','act','action', |
|
261 'actions','add','add_attribute','add_enum_value','add_fallback', |
|
262 'add_method','add_parent','add_private_method','add_role','add_trustee', |
|
263 'adverb','after','all','allocate','allof','allowed','alternative-names', |
|
264 'annotations','antipair','antipairs','any','anyof','app_lifetime', |
|
265 'append','arch','archname','args','arity','Array','asec','asech','asin', |
|
266 'asinh','ASSIGN-KEY','ASSIGN-POS','assuming','ast','at','atan','atan2', |
|
267 'atanh','AT-KEY','atomic-assign','atomic-dec-fetch','atomic-fetch', |
|
268 'atomic-fetch-add','atomic-fetch-dec','atomic-fetch-inc', |
|
269 'atomic-fetch-sub','atomic-inc-fetch','AT-POS','attributes','auth', |
|
270 'await','backtrace','Bag','BagHash','bail-out','base','basename', |
|
271 'base-repeating','batch','BIND-KEY','BIND-POS','bind-stderr', |
|
272 'bind-stdin','bind-stdout','bind-udp','bits','bless','block','Bool', |
|
273 'bool-only','bounds','break','Bridge','broken','BUILD','build-date', |
|
274 'bytes','cache','callframe','calling-package','CALL-ME','callsame', |
|
275 'callwith','can','cancel','candidates','cando','can-ok','canonpath', |
|
276 'caps','caption','Capture','cas','catdir','categorize','categorize-list', |
|
277 'catfile','catpath','cause','ceiling','cglobal','changed','Channel', |
|
278 'chars','chdir','child','child-name','child-typename','chmod','chomp', |
|
279 'chop','chr','chrs','chunks','cis','classify','classify-list','cleanup', |
|
280 'clone','close','closed','close-stdin','cmp-ok','code','codes','collate', |
|
281 'column','comb','combinations','command','comment','compiler','Complex', |
|
282 'compose','compose_type','composer','condition','config', |
|
283 'configure_destroy','configure_type_checking','conj','connect', |
|
284 'constraints','construct','contains','contents','copy','cos','cosec', |
|
285 'cosech','cosh','cotan','cotanh','count','count-only','cpu-cores', |
|
286 'cpu-usage','CREATE','create_type','cross','cue','curdir','curupdir','d', |
|
287 'Date','DateTime','day','daycount','day-of-month','day-of-week', |
|
288 'day-of-year','days-in-month','declaration','decode','decoder','deepmap', |
|
289 'default','defined','DEFINITE','delayed','DELETE-KEY','DELETE-POS', |
|
290 'denominator','desc','DESTROY','destroyers','devnull','diag', |
|
291 'did-you-mean','die','dies-ok','dir','dirname','dir-sep','DISTROnames', |
|
292 'do','does','does-ok','done','done-testing','duckmap','dynamic','e', |
|
293 'eager','earlier','elems','emit','enclosing','encode','encoder', |
|
294 'encoding','end','ends-with','enum_from_value','enum_value_list', |
|
295 'enum_values','enums','eof','EVAL','eval-dies-ok','EVALFILE', |
|
296 'eval-lives-ok','exception','excludes-max','excludes-min','EXISTS-KEY', |
|
297 'EXISTS-POS','exit','exitcode','exp','expected','explicitly-manage', |
|
298 'expmod','extension','f','fail','fails-like','fc','feature','file', |
|
299 'filename','find_method','find_method_qualified','finish','first','flat', |
|
300 'flatmap','flip','floor','flunk','flush','fmt','format','formatter', |
|
301 'freeze','from','from-list','from-loop','from-posix','full', |
|
302 'full-barrier','get','get_value','getc','gist','got','grab','grabpairs', |
|
303 'grep','handle','handled','handles','hardware','has_accessor','Hash', |
|
304 'head','headers','hh-mm-ss','hidden','hides','hour','how','hyper','id', |
|
305 'illegal','im','in','indent','index','indices','indir','infinite', |
|
306 'infix','infix:<+>','infix:<->','install_method_cache','Instant', |
|
307 'instead','Int','int-bounds','interval','in-timezone','invalid-str', |
|
308 'invert','invocant','IO','IO::Notification.watch-path','is_trusted', |
|
309 'is_type','isa','is-absolute','isa-ok','is-approx','is-deeply', |
|
310 'is-hidden','is-initial-thread','is-int','is-lazy','is-leap-year', |
|
311 'isNaN','isnt','is-prime','is-relative','is-routine','is-setting', |
|
312 'is-win','item','iterator','join','keep','kept','KERNELnames','key', |
|
313 'keyof','keys','kill','kv','kxxv','l','lang','last','lastcall','later', |
|
314 'lazy','lc','leading','level','like','line','lines','link','List', |
|
315 'listen','live','lives-ok','local','lock','log','log10','lookup','lsb', |
|
316 'made','MAIN','make','Map','match','max','maxpairs','merge','message', |
|
317 'method','method_table','methods','migrate','min','minmax','minpairs', |
|
318 'minute','misplaced','Mix','MixHash','mkdir','mode','modified','month', |
|
319 'move','mro','msb','multi','multiness','my','name','named','named_names', |
|
320 'narrow','nativecast','native-descriptor','nativesizeof','new','new_type', |
|
321 'new-from-daycount','new-from-pairs','next','nextcallee','next-handle', |
|
322 'nextsame','nextwith','NFC','NFD','NFKC','NFKD','nl-in','nl-out', |
|
323 'nodemap','nok','none','norm','not','note','now','nude','Num', |
|
324 'numerator','Numeric','of','offset','offset-in-hours','offset-in-minutes', |
|
325 'ok','old','on-close','one','on-switch','open','opened','operation', |
|
326 'optional','ord','ords','orig','os-error','osname','out-buffer','pack', |
|
327 'package','package-kind','package-name','packages','pair','pairs', |
|
328 'pairup','parameter','params','parent','parent-name','parents','parse', |
|
329 'parse-base','parsefile','parse-names','parts','pass','path','path-sep', |
|
330 'payload','peer-host','peer-port','periods','perl','permutations','phaser', |
|
331 'pick','pickpairs','pid','placeholder','plan','plus','polar','poll', |
|
332 'polymod','pop','pos','positional','posix','postfix','postmatch', |
|
333 'precomp-ext','precomp-target','pred','prefix','prematch','prepend', |
|
334 'print','printf','print-nl','print-to','private','private_method_table', |
|
335 'proc','produce','Promise','prompt','protect','pull-one','push', |
|
336 'push-all','push-at-least','push-exactly','push-until-lazy','put', |
|
337 'qualifier-type','quit','r','race','radix','rand','range','Rat','raw', |
|
338 're','read','readchars','readonly','ready','Real','reallocate','reals', |
|
339 'reason','rebless','receive','recv','redispatcher','redo','reduce', |
|
340 'rel2abs','relative','release','rename','repeated','replacement', |
|
341 'report','reserved','resolve','restore','result','resume','rethrow', |
|
342 'reverse','right','rindex','rmdir','role','roles_to_compose','rolish', |
|
343 'roll','rootdir','roots','rotate','rotor','round','roundrobin', |
|
344 'routine-type','run','rwx','s','samecase','samemark','samewith','say', |
|
345 'schedule-on','scheduler','scope','sec','sech','second','seek','self', |
|
346 'send','Set','set_hidden','set_name','set_package','set_rw','set_value', |
|
347 'SetHash','set-instruments','setup_finalization','shape','share','shell', |
|
348 'shift','sibling','sigil','sign','signal','signals','signature','sin', |
|
349 'sinh','sink','sink-all','skip','skip-at-least','skip-at-least-pull-one', |
|
350 'skip-one','skip-rest','sleep','sleep-timer','sleep-until','Slip','slurp', |
|
351 'slurp-rest','slurpy','snap','snapper','so','socket-host','socket-port', |
|
352 'sort','source','source-package','spawn','SPEC','splice','split', |
|
353 'splitdir','splitpath','sprintf','spurt','sqrt','squish','srand','stable', |
|
354 'start','started','starts-with','status','stderr','stdout','Str', |
|
355 'sub_signature','subbuf','subbuf-rw','subname','subparse','subst', |
|
356 'subst-mutate','substr','substr-eq','substr-rw','subtest','succ','sum', |
|
357 'Supply','symlink','t','tail','take','take-rw','tan','tanh','tap', |
|
358 'target','target-name','tc','tclc','tell','then','throttle','throw', |
|
359 'throws-like','timezone','tmpdir','to','today','todo','toggle','to-posix', |
|
360 'total','trailing','trans','tree','trim','trim-leading','trim-trailing', |
|
361 'truncate','truncated-to','trusts','try_acquire','trying','twigil','type', |
|
362 'type_captures','typename','uc','udp','uncaught_handler','unimatch', |
|
363 'uniname','uninames','uniparse','uniprop','uniprops','unique','unival', |
|
364 'univals','unlike','unlink','unlock','unpack','unpolar','unshift', |
|
365 'unwrap','updir','USAGE','use-ok','utc','val','value','values','VAR', |
|
366 'variable','verbose-config','version','VMnames','volume','vow','w','wait', |
|
367 'warn','watch','watch-path','week','weekday-of-month','week-number', |
|
368 'week-year','WHAT','when','WHERE','WHEREFORE','WHICH','WHO', |
|
369 'whole-second','WHY','wordcase','words','workaround','wrap','write', |
|
370 'write-to','x','yada','year','yield','yyyy-mm-dd','z','zip','zip-latest', |
|
371 |
|
372 ) |
|
373 |
|
374 PERL6_BUILTIN_CLASSES = ( |
|
375 #Booleans |
|
376 'False','True', |
|
377 #Classes |
|
378 'Any','Array','Associative','AST','atomicint','Attribute','Backtrace', |
|
379 'Backtrace::Frame','Bag','Baggy','BagHash','Blob','Block','Bool','Buf', |
|
380 'Callable','CallFrame','Cancellation','Capture','CArray','Channel','Code', |
|
381 'compiler','Complex','ComplexStr','Cool','CurrentThreadScheduler', |
|
382 'Cursor','Date','Dateish','DateTime','Distro','Duration','Encoding', |
|
383 'Exception','Failure','FatRat','Grammar','Hash','HyperWhatever','Instant', |
|
384 'Int','int16','int32','int64','int8','IntStr','IO','IO::ArgFiles', |
|
385 'IO::CatHandle','IO::Handle','IO::Notification','IO::Path', |
|
386 'IO::Path::Cygwin','IO::Path::QNX','IO::Path::Unix','IO::Path::Win32', |
|
387 'IO::Pipe','IO::Socket','IO::Socket::Async','IO::Socket::INET','IO::Spec', |
|
388 'IO::Spec::Cygwin','IO::Spec::QNX','IO::Spec::Unix','IO::Spec::Win32', |
|
389 'IO::Special','Iterable','Iterator','Junction','Kernel','Label','List', |
|
390 'Lock','Lock::Async','long','longlong','Macro','Map','Match', |
|
391 'Metamodel::AttributeContainer','Metamodel::C3MRO','Metamodel::ClassHOW', |
|
392 'Metamodel::EnumHOW','Metamodel::Finalization','Metamodel::MethodContainer', |
|
393 'Metamodel::MROBasedMethodDispatch','Metamodel::MultipleInheritance', |
|
394 'Metamodel::Naming','Metamodel::Primitives','Metamodel::PrivateMethodContainer', |
|
395 'Metamodel::RoleContainer','Metamodel::Trusting','Method','Mix','MixHash', |
|
396 'Mixy','Mu','NFC','NFD','NFKC','NFKD','Nil','Num','num32','num64', |
|
397 'Numeric','NumStr','ObjAt','Order','Pair','Parameter','Perl','Pod::Block', |
|
398 'Pod::Block::Code','Pod::Block::Comment','Pod::Block::Declarator', |
|
399 'Pod::Block::Named','Pod::Block::Para','Pod::Block::Table','Pod::Heading', |
|
400 'Pod::Item','Pointer','Positional','PositionalBindFailover','Proc', |
|
401 'Proc::Async','Promise','Proxy','PseudoStash','QuantHash','Range','Rat', |
|
402 'Rational','RatStr','Real','Regex','Routine','Scalar','Scheduler', |
|
403 'Semaphore','Seq','Set','SetHash','Setty','Signature','size_t','Slip', |
|
404 'Stash','Str','StrDistance','Stringy','Sub','Submethod','Supplier', |
|
405 'Supplier::Preserving','Supply','Systemic','Tap','Telemetry', |
|
406 'Telemetry::Instrument::Thread','Telemetry::Instrument::Usage', |
|
407 'Telemetry::Period','Telemetry::Sampler','Thread','ThreadPoolScheduler', |
|
408 'UInt','uint16','uint32','uint64','uint8','Uni','utf8','Variable', |
|
409 'Version','VM','Whatever','WhateverCode','WrapHandle' |
|
410 ) |
|
411 |
|
412 PERL6_OPERATORS = ( |
|
413 'X', 'Z', 'after', 'also', 'and', 'andthen', 'before', 'cmp', 'div', |
|
414 'eq', 'eqv', 'extra', 'ff', 'fff', 'ge', 'gt', 'le', 'leg', 'lt', 'm', |
|
415 'mm', 'mod', 'ne', 'or', 'orelse', 'rx', 's', 'tr', 'x', 'xor', 'xx', |
|
416 '++', '--', '**', '!', '+', '-', '~', '?', '|', '||', '+^', '~^', '?^', |
|
417 '^', '*', '/', '%', '%%', '+&', '+<', '+>', '~&', '~<', '~>', '?&', |
|
418 'gcd', 'lcm', '+', '-', '+|', '+^', '~|', '~^', '?|', '?^', |
|
419 '~', '&', '^', 'but', 'does', '<=>', '..', '..^', '^..', '^..^', |
|
420 '!=', '==', '<', '<=', '>', '>=', '~~', '===', '!eqv', |
|
421 '&&', '||', '^^', '//', 'min', 'max', '??', '!!', 'ff', 'fff', 'so', |
|
422 'not', '<==', '==>', '<<==', '==>>','unicmp', |
|
423 ) |
|
424 |
|
425 # Perl 6 has a *lot* of possible bracketing characters |
|
426 # this list was lifted from STD.pm6 (https://github.com/perl6/std) |
|
427 PERL6_BRACKETS = { |
|
428 '\u0028': '\u0029', '\u003c': '\u003e', '\u005b': '\u005d', |
|
429 '\u007b': '\u007d', '\u00ab': '\u00bb', '\u0f3a': '\u0f3b', |
|
430 '\u0f3c': '\u0f3d', '\u169b': '\u169c', '\u2018': '\u2019', |
|
431 '\u201a': '\u2019', '\u201b': '\u2019', '\u201c': '\u201d', |
|
432 '\u201e': '\u201d', '\u201f': '\u201d', '\u2039': '\u203a', |
|
433 '\u2045': '\u2046', '\u207d': '\u207e', '\u208d': '\u208e', |
|
434 '\u2208': '\u220b', '\u2209': '\u220c', '\u220a': '\u220d', |
|
435 '\u2215': '\u29f5', '\u223c': '\u223d', '\u2243': '\u22cd', |
|
436 '\u2252': '\u2253', '\u2254': '\u2255', '\u2264': '\u2265', |
|
437 '\u2266': '\u2267', '\u2268': '\u2269', '\u226a': '\u226b', |
|
438 '\u226e': '\u226f', '\u2270': '\u2271', '\u2272': '\u2273', |
|
439 '\u2274': '\u2275', '\u2276': '\u2277', '\u2278': '\u2279', |
|
440 '\u227a': '\u227b', '\u227c': '\u227d', '\u227e': '\u227f', |
|
441 '\u2280': '\u2281', '\u2282': '\u2283', '\u2284': '\u2285', |
|
442 '\u2286': '\u2287', '\u2288': '\u2289', '\u228a': '\u228b', |
|
443 '\u228f': '\u2290', '\u2291': '\u2292', '\u2298': '\u29b8', |
|
444 '\u22a2': '\u22a3', '\u22a6': '\u2ade', '\u22a8': '\u2ae4', |
|
445 '\u22a9': '\u2ae3', '\u22ab': '\u2ae5', '\u22b0': '\u22b1', |
|
446 '\u22b2': '\u22b3', '\u22b4': '\u22b5', '\u22b6': '\u22b7', |
|
447 '\u22c9': '\u22ca', '\u22cb': '\u22cc', '\u22d0': '\u22d1', |
|
448 '\u22d6': '\u22d7', '\u22d8': '\u22d9', '\u22da': '\u22db', |
|
449 '\u22dc': '\u22dd', '\u22de': '\u22df', '\u22e0': '\u22e1', |
|
450 '\u22e2': '\u22e3', '\u22e4': '\u22e5', '\u22e6': '\u22e7', |
|
451 '\u22e8': '\u22e9', '\u22ea': '\u22eb', '\u22ec': '\u22ed', |
|
452 '\u22f0': '\u22f1', '\u22f2': '\u22fa', '\u22f3': '\u22fb', |
|
453 '\u22f4': '\u22fc', '\u22f6': '\u22fd', '\u22f7': '\u22fe', |
|
454 '\u2308': '\u2309', '\u230a': '\u230b', '\u2329': '\u232a', |
|
455 '\u23b4': '\u23b5', '\u2768': '\u2769', '\u276a': '\u276b', |
|
456 '\u276c': '\u276d', '\u276e': '\u276f', '\u2770': '\u2771', |
|
457 '\u2772': '\u2773', '\u2774': '\u2775', '\u27c3': '\u27c4', |
|
458 '\u27c5': '\u27c6', '\u27d5': '\u27d6', '\u27dd': '\u27de', |
|
459 '\u27e2': '\u27e3', '\u27e4': '\u27e5', '\u27e6': '\u27e7', |
|
460 '\u27e8': '\u27e9', '\u27ea': '\u27eb', '\u2983': '\u2984', |
|
461 '\u2985': '\u2986', '\u2987': '\u2988', '\u2989': '\u298a', |
|
462 '\u298b': '\u298c', '\u298d': '\u298e', '\u298f': '\u2990', |
|
463 '\u2991': '\u2992', '\u2993': '\u2994', '\u2995': '\u2996', |
|
464 '\u2997': '\u2998', '\u29c0': '\u29c1', '\u29c4': '\u29c5', |
|
465 '\u29cf': '\u29d0', '\u29d1': '\u29d2', '\u29d4': '\u29d5', |
|
466 '\u29d8': '\u29d9', '\u29da': '\u29db', '\u29f8': '\u29f9', |
|
467 '\u29fc': '\u29fd', '\u2a2b': '\u2a2c', '\u2a2d': '\u2a2e', |
|
468 '\u2a34': '\u2a35', '\u2a3c': '\u2a3d', '\u2a64': '\u2a65', |
|
469 '\u2a79': '\u2a7a', '\u2a7d': '\u2a7e', '\u2a7f': '\u2a80', |
|
470 '\u2a81': '\u2a82', '\u2a83': '\u2a84', '\u2a8b': '\u2a8c', |
|
471 '\u2a91': '\u2a92', '\u2a93': '\u2a94', '\u2a95': '\u2a96', |
|
472 '\u2a97': '\u2a98', '\u2a99': '\u2a9a', '\u2a9b': '\u2a9c', |
|
473 '\u2aa1': '\u2aa2', '\u2aa6': '\u2aa7', '\u2aa8': '\u2aa9', |
|
474 '\u2aaa': '\u2aab', '\u2aac': '\u2aad', '\u2aaf': '\u2ab0', |
|
475 '\u2ab3': '\u2ab4', '\u2abb': '\u2abc', '\u2abd': '\u2abe', |
|
476 '\u2abf': '\u2ac0', '\u2ac1': '\u2ac2', '\u2ac3': '\u2ac4', |
|
477 '\u2ac5': '\u2ac6', '\u2acd': '\u2ace', '\u2acf': '\u2ad0', |
|
478 '\u2ad1': '\u2ad2', '\u2ad3': '\u2ad4', '\u2ad5': '\u2ad6', |
|
479 '\u2aec': '\u2aed', '\u2af7': '\u2af8', '\u2af9': '\u2afa', |
|
480 '\u2e02': '\u2e03', '\u2e04': '\u2e05', '\u2e09': '\u2e0a', |
|
481 '\u2e0c': '\u2e0d', '\u2e1c': '\u2e1d', '\u2e20': '\u2e21', |
|
482 '\u3008': '\u3009', '\u300a': '\u300b', '\u300c': '\u300d', |
|
483 '\u300e': '\u300f', '\u3010': '\u3011', '\u3014': '\u3015', |
|
484 '\u3016': '\u3017', '\u3018': '\u3019', '\u301a': '\u301b', |
|
485 '\u301d': '\u301e', '\ufd3e': '\ufd3f', '\ufe17': '\ufe18', |
|
486 '\ufe35': '\ufe36', '\ufe37': '\ufe38', '\ufe39': '\ufe3a', |
|
487 '\ufe3b': '\ufe3c', '\ufe3d': '\ufe3e', '\ufe3f': '\ufe40', |
|
488 '\ufe41': '\ufe42', '\ufe43': '\ufe44', '\ufe47': '\ufe48', |
|
489 '\ufe59': '\ufe5a', '\ufe5b': '\ufe5c', '\ufe5d': '\ufe5e', |
|
490 '\uff08': '\uff09', '\uff1c': '\uff1e', '\uff3b': '\uff3d', |
|
491 '\uff5b': '\uff5d', '\uff5f': '\uff60', '\uff62': '\uff63', |
|
492 } |
|
493 |
|
494 def _build_word_match(words, boundary_regex_fragment=None, prefix='', suffix=''): |
|
495 if boundary_regex_fragment is None: |
|
496 return r'\b(' + prefix + r'|'.join(re.escape(x) for x in words) + \ |
|
497 suffix + r')\b' |
|
498 else: |
|
499 return r'(?<!' + boundary_regex_fragment + r')' + prefix + r'(' + \ |
|
500 r'|'.join(re.escape(x) for x in words) + r')' + suffix + r'(?!' + \ |
|
501 boundary_regex_fragment + r')' |
|
502 |
|
503 def brackets_callback(token_class): |
|
504 def callback(lexer, match, context): |
|
505 groups = match.groupdict() |
|
506 opening_chars = groups['delimiter'] |
|
507 n_chars = len(opening_chars) |
|
508 adverbs = groups.get('adverbs') |
|
509 |
|
510 closer = Perl6Lexer.PERL6_BRACKETS.get(opening_chars[0]) |
|
511 text = context.text |
|
512 |
|
513 if closer is None: # it's not a mirrored character, which means we |
|
514 # just need to look for the next occurrence |
|
515 |
|
516 end_pos = text.find(opening_chars, match.start('delimiter') + n_chars) |
|
517 else: # we need to look for the corresponding closing character, |
|
518 # keep nesting in mind |
|
519 closing_chars = closer * n_chars |
|
520 nesting_level = 1 |
|
521 |
|
522 search_pos = match.start('delimiter') |
|
523 |
|
524 while nesting_level > 0: |
|
525 next_open_pos = text.find(opening_chars, search_pos + n_chars) |
|
526 next_close_pos = text.find(closing_chars, search_pos + n_chars) |
|
527 |
|
528 if next_close_pos == -1: |
|
529 next_close_pos = len(text) |
|
530 nesting_level = 0 |
|
531 elif next_open_pos != -1 and next_open_pos < next_close_pos: |
|
532 nesting_level += 1 |
|
533 search_pos = next_open_pos |
|
534 else: # next_close_pos < next_open_pos |
|
535 nesting_level -= 1 |
|
536 search_pos = next_close_pos |
|
537 |
|
538 end_pos = next_close_pos |
|
539 |
|
540 if end_pos < 0: # if we didn't find a closer, just highlight the |
|
541 # rest of the text in this class |
|
542 end_pos = len(text) |
|
543 |
|
544 if adverbs is not None and re.search(r':to\b', adverbs): |
|
545 heredoc_terminator = text[match.start('delimiter') + n_chars:end_pos] |
|
546 end_heredoc = re.search(r'^\s*' + re.escape(heredoc_terminator) + |
|
547 r'\s*$', text[end_pos:], re.MULTILINE) |
|
548 |
|
549 if end_heredoc: |
|
550 end_pos += end_heredoc.end() |
|
551 else: |
|
552 end_pos = len(text) |
|
553 |
|
554 yield match.start(), token_class, text[match.start():end_pos + n_chars] |
|
555 context.pos = end_pos + n_chars |
|
556 |
|
557 return callback |
|
558 |
|
559 def opening_brace_callback(lexer, match, context): |
|
560 stack = context.stack |
|
561 |
|
562 yield match.start(), Text, context.text[match.start():match.end()] |
|
563 context.pos = match.end() |
|
564 |
|
565 # if we encounter an opening brace and we're one level |
|
566 # below a token state, it means we need to increment |
|
567 # the nesting level for braces so we know later when |
|
568 # we should return to the token rules. |
|
569 if len(stack) > 2 and stack[-2] == 'token': |
|
570 context.perl6_token_nesting_level += 1 |
|
571 |
|
572 def closing_brace_callback(lexer, match, context): |
|
573 stack = context.stack |
|
574 |
|
575 yield match.start(), Text, context.text[match.start():match.end()] |
|
576 context.pos = match.end() |
|
577 |
|
578 # if we encounter a free closing brace and we're one level |
|
579 # below a token state, it means we need to check the nesting |
|
580 # level to see if we need to return to the token state. |
|
581 if len(stack) > 2 and stack[-2] == 'token': |
|
582 context.perl6_token_nesting_level -= 1 |
|
583 if context.perl6_token_nesting_level == 0: |
|
584 stack.pop() |
|
585 |
|
586 def embedded_perl6_callback(lexer, match, context): |
|
587 context.perl6_token_nesting_level = 1 |
|
588 yield match.start(), Text, context.text[match.start():match.end()] |
|
589 context.pos = match.end() |
|
590 context.stack.append('root') |
|
591 |
|
592 # If you're modifying these rules, be careful if you need to process '{' or '}' |
|
593 # characters. We have special logic for processing these characters (due to the fact |
|
594 # that you can nest Perl 6 code in regex blocks), so if you need to process one of |
|
595 # them, make sure you also process the corresponding one! |
|
596 tokens = { |
|
597 'common': [ |
|
598 (r'#[`|=](?P<delimiter>(?P<first_char>[' + ''.join(PERL6_BRACKETS) + r'])(?P=first_char)*)', |
|
599 brackets_callback(Comment.Multiline)), |
|
600 (r'#[^\n]*$', Comment.Single), |
|
601 (r'^(\s*)=begin\s+(\w+)\b.*?^\1=end\s+\2', Comment.Multiline), |
|
602 (r'^(\s*)=for.*?\n\s*?\n', Comment.Multiline), |
|
603 (r'^=.*?\n\s*?\n', Comment.Multiline), |
|
604 (r'(regex|token|rule)(\s*' + PERL6_IDENTIFIER_RANGE + '+:sym)', |
|
605 bygroups(Keyword, Name), 'token-sym-brackets'), |
|
606 (r'(regex|token|rule)(?!' + PERL6_IDENTIFIER_RANGE + r')(\s*' + PERL6_IDENTIFIER_RANGE + '+)?', |
|
607 bygroups(Keyword, Name), 'pre-token'), |
|
608 # deal with a special case in the Perl 6 grammar (role q { ... }) |
|
609 (r'(role)(\s+)(q)(\s*)', bygroups(Keyword, Text, Name, Text)), |
|
610 (_build_word_match(PERL6_KEYWORDS, PERL6_IDENTIFIER_RANGE), Keyword), |
|
611 (_build_word_match(PERL6_BUILTIN_CLASSES, PERL6_IDENTIFIER_RANGE, suffix='(?::[UD])?'), |
|
612 Name.Builtin), |
|
613 (_build_word_match(PERL6_BUILTINS, PERL6_IDENTIFIER_RANGE), Name.Builtin), |
|
614 # copied from PerlLexer |
|
615 (r'[$@%&][.^:?=!~]?' + PERL6_IDENTIFIER_RANGE + '+(?:<<.*?>>|<.*?>|«.*?»)*', |
|
616 Name.Variable), |
|
617 (r'\$[!/](?:<<.*?>>|<.*?>|«.*?»)*', Name.Variable.Global), |
|
618 (r'::\?\w+', Name.Variable.Global), |
|
619 (r'[$@%&]\*' + PERL6_IDENTIFIER_RANGE + '+(?:<<.*?>>|<.*?>|«.*?»)*', |
|
620 Name.Variable.Global), |
|
621 (r'\$(?:<.*?>)+', Name.Variable), |
|
622 (r'(?:q|qq|Q)[a-zA-Z]?\s*(?P<adverbs>:[\w\s:]+)?\s*(?P<delimiter>(?P<first_char>[^0-9a-zA-Z:\s])' |
|
623 r'(?P=first_char)*)', brackets_callback(String)), |
|
624 # copied from PerlLexer |
|
625 (r'0_?[0-7]+(_[0-7]+)*', Number.Oct), |
|
626 (r'0x[0-9A-Fa-f]+(_[0-9A-Fa-f]+)*', Number.Hex), |
|
627 (r'0b[01]+(_[01]+)*', Number.Bin), |
|
628 (r'(?i)(\d*(_\d*)*\.\d+(_\d*)*|\d+(_\d*)*\.\d+(_\d*)*)(e[+-]?\d+)?', |
|
629 Number.Float), |
|
630 (r'(?i)\d+(_\d*)*e[+-]?\d+(_\d*)*', Number.Float), |
|
631 (r'\d+(_\d+)*', Number.Integer), |
|
632 (r'(?<=~~)\s*/(?:\\\\|\\/|.)*?/', String.Regex), |
|
633 (r'(?<=[=(,])\s*/(?:\\\\|\\/|.)*?/', String.Regex), |
|
634 (r'm\w+(?=\()', Name), |
|
635 (r'(?:m|ms|rx)\s*(?P<adverbs>:[\w\s:]+)?\s*(?P<delimiter>(?P<first_char>[^\w:\s])' |
|
636 r'(?P=first_char)*)', brackets_callback(String.Regex)), |
|
637 (r'(?:s|ss|tr)\s*(?::[\w\s:]+)?\s*/(?:\\\\|\\/|.)*?/(?:\\\\|\\/|.)*?/', |
|
638 String.Regex), |
|
639 (r'<[^\s=].*?\S>', String), |
|
640 (_build_word_match(PERL6_OPERATORS), Operator), |
|
641 (r'\w' + PERL6_IDENTIFIER_RANGE + '*', Name), |
|
642 (r"'(\\\\|\\[^\\]|[^'\\])*'", String), |
|
643 (r'"(\\\\|\\[^\\]|[^"\\])*"', String), |
|
644 ], |
|
645 'root': [ |
|
646 include('common'), |
|
647 (r'\{', opening_brace_callback), |
|
648 (r'\}', closing_brace_callback), |
|
649 (r'.+?', Text), |
|
650 ], |
|
651 'pre-token': [ |
|
652 include('common'), |
|
653 (r'\{', Text, ('#pop', 'token')), |
|
654 (r'.+?', Text), |
|
655 ], |
|
656 'token-sym-brackets': [ |
|
657 (r'(?P<delimiter>(?P<first_char>[' + ''.join(PERL6_BRACKETS) + '])(?P=first_char)*)', |
|
658 brackets_callback(Name), ('#pop', 'pre-token')), |
|
659 default(('#pop', 'pre-token')), |
|
660 ], |
|
661 'token': [ |
|
662 (r'\}', Text, '#pop'), |
|
663 (r'(?<=:)(?:my|our|state|constant|temp|let).*?;', using(this)), |
|
664 # make sure that quotes in character classes aren't treated as strings |
|
665 (r'<(?:[-!?+.]\s*)?\[.*?\]>', String.Regex), |
|
666 # make sure that '#' characters in quotes aren't treated as comments |
|
667 (r"(?<!\\)'(\\\\|\\[^\\]|[^'\\])*'", String.Regex), |
|
668 (r'(?<!\\)"(\\\\|\\[^\\]|[^"\\])*"', String.Regex), |
|
669 (r'#.*?$', Comment.Single), |
|
670 (r'\{', embedded_perl6_callback), |
|
671 ('.+?', String.Regex), |
|
672 ], |
|
673 } |
|
674 |
|
675 def analyse_text(text): |
|
676 def strip_pod(lines): |
|
677 in_pod = False |
|
678 stripped_lines = [] |
|
679 |
|
680 for line in lines: |
|
681 if re.match(r'^=(?:end|cut)', line): |
|
682 in_pod = False |
|
683 elif re.match(r'^=\w+', line): |
|
684 in_pod = True |
|
685 elif not in_pod: |
|
686 stripped_lines.append(line) |
|
687 |
|
688 return stripped_lines |
|
689 |
|
690 # XXX handle block comments |
|
691 lines = text.splitlines() |
|
692 lines = strip_pod(lines) |
|
693 text = '\n'.join(lines) |
|
694 |
|
695 if shebang_matches(text, r'perl6|rakudo|niecza|pugs'): |
|
696 return True |
|
697 |
|
698 saw_perl_decl = False |
|
699 rating = False |
|
700 |
|
701 # check for my/our/has declarations |
|
702 if re.search(r"(?:my|our|has)\s+(?:" + Perl6Lexer.PERL6_IDENTIFIER_RANGE + |
|
703 r"+\s+)?[$@%&(]", text): |
|
704 rating = 0.8 |
|
705 saw_perl_decl = True |
|
706 |
|
707 for line in lines: |
|
708 line = re.sub('#.*', '', line) |
|
709 if re.match(r'^\s*$', line): |
|
710 continue |
|
711 |
|
712 # match v6; use v6; use v6.0; use v6.0.0; |
|
713 if re.match(r'^\s*(?:use\s+)?v6(?:\.\d(?:\.\d)?)?;', line): |
|
714 return True |
|
715 # match class, module, role, enum, grammar declarations |
|
716 class_decl = re.match(r'^\s*(?:(?P<scope>my|our)\s+)?(?:module|class|role|enum|grammar)', line) |
|
717 if class_decl: |
|
718 if saw_perl_decl or class_decl.group('scope') is not None: |
|
719 return True |
|
720 rating = 0.05 |
|
721 continue |
|
722 break |
|
723 |
|
724 if ':=' in text: |
|
725 # Same logic as above for PerlLexer |
|
726 rating /= 2 |
|
727 |
|
728 return rating |
|
729 |
|
730 def __init__(self, **options): |
|
731 super().__init__(**options) |
|
732 self.encoding = options.get('encoding', 'utf-8') |
|