diff options
author | Matias Linares <matiaslina@gmail.com> | 2019-01-06 21:11:51 -0300 |
---|---|---|
committer | Matias Linares <matiaslina@gmail.com> | 2019-01-06 21:11:51 -0300 |
commit | 5244d952da00984d226c334b4c1a7d5090b7cda5 (patch) | |
tree | ab532148b719dee5350fa136e633c757b85496f0 | |
download | perl6-pygments-5244d952da00984d226c334b4c1a7d5090b7cda5.tar.gz |
initial commit
-rw-r--r-- | .gitignore | 10 | ||||
-rw-r--r-- | .travis.yml | 12 | ||||
-rw-r--r-- | Changes | 4 | ||||
-rw-r--r-- | LICENSE | 201 | ||||
-rw-r--r-- | META6.json | 23 | ||||
-rw-r--r-- | README.md | 0 | ||||
-rw-r--r-- | dist.ini | 8 | ||||
-rw-r--r-- | lib/Pygments.pm6 | 125 | ||||
-rw-r--r-- | resources/perl.py | 620 | ||||
-rw-r--r-- | t/01-basic.t | 7 |
10 files changed, 1010 insertions, 0 deletions
diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..7431818 --- /dev/null +++ b/.gitignore @@ -0,0 +1,10 @@ +/blib/ +/src/*.o +/src/Makefile +/.panda-work +/resources/*.so +/resources/*.dylib +/resources/*.pyc +/resources/__pyc__/ +.precomp/ +/Pygments-* diff --git a/.travis.yml b/.travis.yml new file mode 100644 index 0000000..e74fe5e --- /dev/null +++ b/.travis.yml @@ -0,0 +1,12 @@ +os: + - linux + - osx +language: perl6 +perl6: + - latest +install: + - rakudobrew build zef + - zef install --deps-only --/test . +script: + - PERL6LIB=$PWD/lib prove -e perl6 -vr t/ +sudo: false @@ -0,0 +1,4 @@ +Revision history for Pygments + +{{$NEXT}} + - Initial version @@ -0,0 +1,201 @@ + The Artistic License 2.0 + + Copyright (c) 2000-2006, The Perl Foundation. + + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + +Preamble + +This license establishes the terms under which a given free software +Package may be copied, modified, distributed, and/or redistributed. +The intent is that the Copyright Holder maintains some artistic +control over the development of that Package while still keeping the +Package available as open source and free software. + +You are always permitted to make arrangements wholly outside of this +license directly with the Copyright Holder of a given Package. If the +terms of this license do not permit the full use that you propose to +make of the Package, you should contact the Copyright Holder and seek +a different licensing arrangement. + +Definitions + + "Copyright Holder" means the individual(s) or organization(s) + named in the copyright notice for the entire Package. + + "Contributor" means any party that has contributed code or other + material to the Package, in accordance with the Copyright Holder's + procedures. + + "You" and "your" means any person who would like to copy, + distribute, or modify the Package. + + "Package" means the collection of files distributed by the + Copyright Holder, and derivatives of that collection and/or of + those files. A given Package may consist of either the Standard + Version, or a Modified Version. + + "Distribute" means providing a copy of the Package or making it + accessible to anyone else, or in the case of a company or + organization, to others outside of your company or organization. + + "Distributor Fee" means any fee that you charge for Distributing + this Package or providing support for this Package to another + party. It does not mean licensing fees. + + "Standard Version" refers to the Package if it has not been + modified, or has been modified only in ways explicitly requested + by the Copyright Holder. + + "Modified Version" means the Package, if it has been changed, and + such changes were not explicitly requested by the Copyright + Holder. + + "Original License" means this Artistic License as Distributed with + the Standard Version of the Package, in its current version or as + it may be modified by The Perl Foundation in the future. + + "Source" form means the source code, documentation source, and + configuration files for the Package. + + "Compiled" form means the compiled bytecode, object code, binary, + or any other form resulting from mechanical transformation or + translation of the Source form. + + +Permission for Use and Modification Without Distribution + +(1) You are permitted to use the Standard Version and create and use +Modified Versions for any purpose without restriction, provided that +you do not Distribute the Modified Version. + + +Permissions for Redistribution of the Standard Version + +(2) You may Distribute verbatim copies of the Source form of the +Standard Version of this Package in any medium without restriction, +either gratis or for a Distributor Fee, provided that you duplicate +all of the original copyright notices and associated disclaimers. At +your discretion, such verbatim copies may or may not include a +Compiled form of the Package. + +(3) You may apply any bug fixes, portability changes, and other +modifications made available from the Copyright Holder. The resulting +Package will still be considered the Standard Version, and as such +will be subject to the Original License. + + +Distribution of Modified Versions of the Package as Source + +(4) You may Distribute your Modified Version as Source (either gratis +or for a Distributor Fee, and with or without a Compiled form of the +Modified Version) provided that you clearly document how it differs +from the Standard Version, including, but not limited to, documenting +any non-standard features, executables, or modules, and provided that +you do at least ONE of the following: + + (a) make the Modified Version available to the Copyright Holder + of the Standard Version, under the Original License, so that the + Copyright Holder may include your modifications in the Standard + Version. + + (b) ensure that installation of your Modified Version does not + prevent the user installing or running the Standard Version. In + addition, the Modified Version must bear a name that is different + from the name of the Standard Version. + + (c) allow anyone who receives a copy of the Modified Version to + make the Source form of the Modified Version available to others + under + + (i) the Original License or + + (ii) a license that permits the licensee to freely copy, + modify and redistribute the Modified Version using the same + licensing terms that apply to the copy that the licensee + received, and requires that the Source form of the Modified + Version, and of any works derived from it, be made freely + available in that license fees are prohibited but Distributor + Fees are allowed. + + +Distribution of Compiled Forms of the Standard Version +or Modified Versions without the Source + +(5) You may Distribute Compiled forms of the Standard Version without +the Source, provided that you include complete instructions on how to +get the Source of the Standard Version. Such instructions must be +valid at the time of your distribution. If these instructions, at any +time while you are carrying out such distribution, become invalid, you +must provide new instructions on demand or cease further distribution. +If you provide valid instructions or cease distribution within thirty +days after you become aware that the instructions are invalid, then +you do not forfeit any of your rights under this license. + +(6) You may Distribute a Modified Version in Compiled form without +the Source, provided that you comply with Section 4 with respect to +the Source of the Modified Version. + + +Aggregating or Linking the Package + +(7) You may aggregate the Package (either the Standard Version or +Modified Version) with other packages and Distribute the resulting +aggregation provided that you do not charge a licensing fee for the +Package. Distributor Fees are permitted, and licensing fees for other +components in the aggregation are permitted. The terms of this license +apply to the use and Distribution of the Standard or Modified Versions +as included in the aggregation. + +(8) You are permitted to link Modified and Standard Versions with +other works, to embed the Package in a larger work of your own, or to +build stand-alone binary or bytecode versions of applications that +include the Package, and Distribute the result without restriction, +provided the result does not expose a direct interface to the Package. + + +Items That are Not Considered Part of a Modified Version + +(9) Works (including, but not limited to, modules and scripts) that +merely extend or make use of the Package, do not, by themselves, cause +the Package to be a Modified Version. In addition, such works are not +considered parts of the Package itself, and are not subject to the +terms of this license. + + +General Provisions + +(10) Any use, modification, and distribution of the Standard or +Modified Versions is governed by this Artistic License. By using, +modifying or distributing the Package, you accept this license. Do not +use, modify, or distribute the Package, if you do not accept this +license. + +(11) If your Modified Version has been derived from a Modified +Version made by someone other than you, you are nevertheless required +to ensure that your Modified Version complies with the requirements of +this license. + +(12) This license does not grant you the right to use any trademark, +service mark, tradename, or logo of the Copyright Holder. + +(13) This license includes the non-exclusive, worldwide, +free-of-charge patent license to make, have made, use, offer to sell, +sell, import and otherwise transfer the Package with respect to any +patent claims licensable by the Copyright Holder that are necessarily +infringed by the Package. If you institute patent litigation +(including a cross-claim or counterclaim) against any party alleging +that the Package constitutes direct or contributory patent +infringement, then this Artistic License to you shall terminate on the +date that such litigation is filed. + +(14) Disclaimer of Warranty: +THE PACKAGE IS PROVIDED BY THE COPYRIGHT HOLDER AND CONTRIBUTORS "AS +IS" AND WITHOUT ANY EXPRESS OR IMPLIED WARRANTIES. THE IMPLIED +WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, OR +NON-INFRINGEMENT ARE DISCLAIMED TO THE EXTENT PERMITTED BY YOUR LOCAL +LAW. UNLESS REQUIRED BY LAW, NO COPYRIGHT HOLDER OR CONTRIBUTOR WILL +BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES ARISING IN ANY WAY OUT OF THE USE OF THE PACKAGE, EVEN IF +ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. diff --git a/META6.json b/META6.json new file mode 100644 index 0000000..abf75d2 --- /dev/null +++ b/META6.json @@ -0,0 +1,23 @@ +{ + "authors" : [ + "Matias Linares" + ], + "build-depends" : [ ], + "depends" : [ + "Inline::Python" + ], + "description" : "Wrapper to python pygments library.", + "license" : "Artistic-2.0", + "name" : "Pygments", + "perl" : "6.c", + "provides" : { + "Pygments" : "lib/Pygments.pm6" + }, + "resources" : [ + "perl.py" + ], + "source-url" : "", + "tags" : [ ], + "test-depends" : [ ], + "version" : "0.0.1" +} diff --git a/README.md b/README.md new file mode 100644 index 0000000..e69de29 --- /dev/null +++ b/README.md diff --git a/dist.ini b/dist.ini new file mode 100644 index 0000000..aa5c3d5 --- /dev/null +++ b/dist.ini @@ -0,0 +1,8 @@ +name = Pygments + +[ReadmeFromPod] +; enable = false +filename = lib/Pygments.pm6 + +[PruneFiles] +; match = ^ 'xt/' diff --git a/lib/Pygments.pm6 b/lib/Pygments.pm6 new file mode 100644 index 0000000..0244631 --- /dev/null +++ b/lib/Pygments.pm6 @@ -0,0 +1,125 @@ +use v6.d; +unit class Pygments:ver<0.0.1>; + +use Inline::Python; + +my Inline::Python $py; + +INIT { + $py .= new; + $py.run: q:to/SETUP/; + from pygments import highlight + from pygments.lexers import get_lexer_by_name, guess_lexer + from pygments.formatters import get_formatter_by_name + from pygments.styles import STYLE_MAP, get_style_by_name + SETUP + + $py.run: %?RESOURCES<perl.py>.slurp; +} + +method call($name, |c) { + $py.call('__main__', $name, |c) +} + +method highlight(Str $code, $lexer = Any, :$formatter = 'html', *%options) is export { + my $l = do given $lexer { + when 'perl6' { self.call('Perl6Lexer') } + when *.defined { self.call('get_lexer_by_name', $lexer) } + default { self.call('guess_lexer', $code) } + }; + + my $f = $.formatter($formatter, |%options); + $py.call('pygments', 'highlight', $code, $l, $f) +} + +method formatter($name, *%options) is export { + self.call('get_formatter_by_name', $name, |%options) +} + +method style(Str $name = 'default') { + $py.call('pygments.styles', 'get_style_by_name', $name) +} + +method styles { + $py.run('list(STYLE_MAP.keys())', :eval).map: *.decode +} + +=begin pod + +=head1 NAME + +Pygments - Wrapper to python pygments library. + +=head1 SYNOPSIS + + use Pygments; + + my $code = q:to/ENDCODE/; + grammar Parser { + rule TOP { I <love> <lang> } + token love { '♥' | love } + token lang { < Perl Rust Go Python Ruby > } + } + + say Parser.parse: 'I ♥ Perl'; + # OUTPUT: 「I ♥ Perl」 love => 「♥」 lang => 「Perl」 + + say Parser.parse: 'I love Rust'; + # OUTPUT: 「I love Rust」 love => 「love」 lang => 「Rust」 + ENDCODE + + # Get a theme. + my $css = Pygments.css('manni'); + + # Format a full html with line numbers and theme `manni` + my $formatted-code = Pygments.highlight( + $code, "perl6", + :linenos(True), + :style($css), + :full(True) + ); + + say $formatted-code; + +=head1 DESCRIPTION + +Pygments is a wrapper for the L<pygments|http://pygments.org> python library. + +=head1 METHODS + +There's no need to instantiate the C<Pygments> class. All the methods can be called +directly. + +=head2 highlight + +=for code +method highlight(Str $code, $lexer, :$formatter = 'html', *%options) + +Highlight the C<$code> with the lexer passed by paramenter. If no lexer is provided, +pygments will try to guess the lexer that will use. + +=head2 style + +=for code +method style(Str $name = 'default') + +Get a single style with name C<$name> + +=head2 styles + +=for code +method styles + +Return a list of all the available themes. + +=head1 AUTHOR + +Matias Linares <matiaslina@gmail.com> + +=head1 COPYRIGHT AND LICENSE + +Copyright 2019 Matias Linares + +This library is free software; you can redistribute it and/or modify it under the Artistic License 2.0. + +=end pod diff --git a/resources/perl.py b/resources/perl.py new file mode 100644 index 0000000..27e3cc7 --- /dev/null +++ b/resources/perl.py @@ -0,0 +1,620 @@ +# -*- coding: utf-8 -*- +""" + pygments.lexers.perl + ~~~~~~~~~~~~~~~~~~~~ + + Lexers for Perl and related languages. + + :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS. + :license: BSD, see LICENSE for details. +""" + +import re + +from pygments.lexer import RegexLexer, ExtendedRegexLexer, include, bygroups, \ + using, this, default, words +from pygments.token import Text, Comment, Operator, Keyword, Name, String, \ + Number, Punctuation +from pygments.util import shebang_matches + +__all__ = ['PerlLexer', 'Perl6Lexer'] + + +class PerlLexer(RegexLexer): + """ + For `Perl <http://www.perl.org>`_ source code. + """ + + name = 'Perl' + aliases = ['perl', 'pl'] + filenames = ['*.pl', '*.pm', '*.t'] + mimetypes = ['text/x-perl', 'application/x-perl'] + + flags = re.DOTALL | re.MULTILINE + # TODO: give this to a perl guy who knows how to parse perl... + tokens = { + 'balanced-regex': [ + (r'/(\\\\|\\[^\\]|[^\\/])*/[egimosx]*', String.Regex, '#pop'), + (r'!(\\\\|\\[^\\]|[^\\!])*![egimosx]*', String.Regex, '#pop'), + (r'\\(\\\\|[^\\])*\\[egimosx]*', String.Regex, '#pop'), + (r'\{(\\\\|\\[^\\]|[^\\}])*\}[egimosx]*', String.Regex, '#pop'), + (r'<(\\\\|\\[^\\]|[^\\>])*>[egimosx]*', String.Regex, '#pop'), + (r'\[(\\\\|\\[^\\]|[^\\\]])*\][egimosx]*', String.Regex, '#pop'), + (r'\((\\\\|\\[^\\]|[^\\)])*\)[egimosx]*', String.Regex, '#pop'), + (r'@(\\\\|\\[^\\]|[^\\@])*@[egimosx]*', String.Regex, '#pop'), + (r'%(\\\\|\\[^\\]|[^\\%])*%[egimosx]*', String.Regex, '#pop'), + (r'\$(\\\\|\\[^\\]|[^\\$])*\$[egimosx]*', String.Regex, '#pop'), + ], + 'root': [ + (r'\A\#!.+?$', Comment.Hashbang), + (r'\#.*?$', Comment.Single), + (r'^=[a-zA-Z0-9]+\s+.*?\n=cut', Comment.Multiline), + (words(( + 'case', 'continue', 'do', 'else', 'elsif', 'for', 'foreach', + 'if', 'last', 'my', 'next', 'our', 'redo', 'reset', 'then', + 'unless', 'until', 'while', 'print', 'new', 'BEGIN', + 'CHECK', 'INIT', 'END', 'return'), suffix=r'\b'), + Keyword), + (r'(format)(\s+)(\w+)(\s*)(=)(\s*\n)', + bygroups(Keyword, Text, Name, Text, Punctuation, Text), 'format'), + (r'(eq|lt|gt|le|ge|ne|not|and|or|cmp)\b', Operator.Word), + # common delimiters + (r's/(\\\\|\\[^\\]|[^\\/])*/(\\\\|\\[^\\]|[^\\/])*/[egimosx]*', + String.Regex), + (r's!(\\\\|\\!|[^!])*!(\\\\|\\!|[^!])*![egimosx]*', String.Regex), + (r's\\(\\\\|[^\\])*\\(\\\\|[^\\])*\\[egimosx]*', String.Regex), + (r's@(\\\\|\\[^\\]|[^\\@])*@(\\\\|\\[^\\]|[^\\@])*@[egimosx]*', + String.Regex), + (r's%(\\\\|\\[^\\]|[^\\%])*%(\\\\|\\[^\\]|[^\\%])*%[egimosx]*', + String.Regex), + # balanced delimiters + (r's\{(\\\\|\\[^\\]|[^\\}])*\}\s*', String.Regex, 'balanced-regex'), + (r's<(\\\\|\\[^\\]|[^\\>])*>\s*', String.Regex, 'balanced-regex'), + (r's\[(\\\\|\\[^\\]|[^\\\]])*\]\s*', String.Regex, + 'balanced-regex'), + (r's\((\\\\|\\[^\\]|[^\\)])*\)\s*', String.Regex, + 'balanced-regex'), + + (r'm?/(\\\\|\\[^\\]|[^\\/\n])*/[gcimosx]*', String.Regex), + (r'm(?=[/!\\{<\[(@%$])', String.Regex, 'balanced-regex'), + (r'((?<==~)|(?<=\())\s*/(\\\\|\\[^\\]|[^\\/])*/[gcimosx]*', + String.Regex), + (r'\s+', Text), + (words(( + 'abs', 'accept', 'alarm', 'atan2', 'bind', 'binmode', 'bless', 'caller', 'chdir', + 'chmod', 'chomp', 'chop', 'chown', 'chr', 'chroot', 'close', 'closedir', 'connect', + 'continue', 'cos', 'crypt', 'dbmclose', 'dbmopen', 'defined', 'delete', 'die', + 'dump', 'each', 'endgrent', 'endhostent', 'endnetent', 'endprotoent', + 'endpwent', 'endservent', 'eof', 'eval', 'exec', 'exists', 'exit', 'exp', 'fcntl', + 'fileno', 'flock', 'fork', 'format', 'formline', 'getc', 'getgrent', 'getgrgid', + 'getgrnam', 'gethostbyaddr', 'gethostbyname', 'gethostent', 'getlogin', + 'getnetbyaddr', 'getnetbyname', 'getnetent', 'getpeername', 'getpgrp', + 'getppid', 'getpriority', 'getprotobyname', 'getprotobynumber', + 'getprotoent', 'getpwent', 'getpwnam', 'getpwuid', 'getservbyname', + 'getservbyport', 'getservent', 'getsockname', 'getsockopt', 'glob', 'gmtime', + 'goto', 'grep', 'hex', 'import', 'index', 'int', 'ioctl', 'join', 'keys', 'kill', 'last', + 'lc', 'lcfirst', 'length', 'link', 'listen', 'local', 'localtime', 'log', 'lstat', + 'map', 'mkdir', 'msgctl', 'msgget', 'msgrcv', 'msgsnd', 'my', 'next', 'oct', 'open', + 'opendir', 'ord', 'our', 'pack', 'pipe', 'pop', 'pos', 'printf', + 'prototype', 'push', 'quotemeta', 'rand', 'read', 'readdir', + 'readline', 'readlink', 'readpipe', 'recv', 'redo', 'ref', 'rename', + 'reverse', 'rewinddir', 'rindex', 'rmdir', 'scalar', 'seek', 'seekdir', + 'select', 'semctl', 'semget', 'semop', 'send', 'setgrent', 'sethostent', 'setnetent', + 'setpgrp', 'setpriority', 'setprotoent', 'setpwent', 'setservent', + 'setsockopt', 'shift', 'shmctl', 'shmget', 'shmread', 'shmwrite', 'shutdown', + 'sin', 'sleep', 'socket', 'socketpair', 'sort', 'splice', 'split', 'sprintf', 'sqrt', + 'srand', 'stat', 'study', 'substr', 'symlink', 'syscall', 'sysopen', 'sysread', + 'sysseek', 'system', 'syswrite', 'tell', 'telldir', 'tie', 'tied', 'time', 'times', 'tr', + 'truncate', 'uc', 'ucfirst', 'umask', 'undef', 'unlink', 'unpack', 'unshift', 'untie', + 'utime', 'values', 'vec', 'wait', 'waitpid', 'wantarray', 'warn', 'write'), suffix=r'\b'), + Name.Builtin), + (r'((__(DATA|DIE|WARN)__)|(STD(IN|OUT|ERR)))\b', Name.Builtin.Pseudo), + (r'(<<)([\'"]?)([a-zA-Z_]\w*)(\2;?\n.*?\n)(\3)(\n)', + bygroups(String, String, String.Delimiter, String, String.Delimiter, Text)), + (r'__END__', Comment.Preproc, 'end-part'), + (r'\$\^[ADEFHILMOPSTWX]', Name.Variable.Global), + (r"\$[\\\"\[\]'&`+*.,;=%~?@$!<>(^|/-](?!\w)", Name.Variable.Global), + (r'[$@%#]+', Name.Variable, 'varname'), + (r'0_?[0-7]+(_[0-7]+)*', Number.Oct), + (r'0x[0-9A-Fa-f]+(_[0-9A-Fa-f]+)*', Number.Hex), + (r'0b[01]+(_[01]+)*', Number.Bin), + (r'(?i)(\d*(_\d*)*\.\d+(_\d*)*|\d+(_\d*)*\.\d+(_\d*)*)(e[+-]?\d+)?', + Number.Float), + (r'(?i)\d+(_\d*)*e[+-]?\d+(_\d*)*', Number.Float), + (r'\d+(_\d+)*', Number.Integer), + (r"'(\\\\|\\[^\\]|[^'\\])*'", String), + (r'"(\\\\|\\[^\\]|[^"\\])*"', String), + (r'`(\\\\|\\[^\\]|[^`\\])*`', String.Backtick), + (r'<([^\s>]+)>', String.Regex), + (r'(q|qq|qw|qr|qx)\{', String.Other, 'cb-string'), + (r'(q|qq|qw|qr|qx)\(', String.Other, 'rb-string'), + (r'(q|qq|qw|qr|qx)\[', String.Other, 'sb-string'), + (r'(q|qq|qw|qr|qx)\<', String.Other, 'lt-string'), + (r'(q|qq|qw|qr|qx)([\W_])(.|\n)*?\2', String.Other), + (r'(package)(\s+)([a-zA-Z_]\w*(?:::[a-zA-Z_]\w*)*)', + bygroups(Keyword, Text, Name.Namespace)), + (r'(use|require|no)(\s+)([a-zA-Z_]\w*(?:::[a-zA-Z_]\w*)*)', + bygroups(Keyword, Text, Name.Namespace)), + (r'(sub)(\s+)', bygroups(Keyword, Text), 'funcname'), + (words(( + 'no', 'package', 'require', 'use'), suffix=r'\b'), + Keyword), + (r'(\[\]|\*\*|::|<<|>>|>=|<=>|<=|={3}|!=|=~|' + r'!~|&&?|\|\||\.{1,3})', Operator), + (r'[-+/*%=<>&^|!\\~]=?', Operator), + (r'[()\[\]:;,<>/?{}]', Punctuation), # yes, there's no shortage + # of punctuation in Perl! + (r'(?=\w)', Name, 'name'), + ], + 'format': [ + (r'\.\n', String.Interpol, '#pop'), + (r'[^\n]*\n', String.Interpol), + ], + 'varname': [ + (r'\s+', Text), + (r'\{', Punctuation, '#pop'), # hash syntax? + (r'\)|,', Punctuation, '#pop'), # argument specifier + (r'\w+::', Name.Namespace), + (r'[\w:]+', Name.Variable, '#pop'), + ], + 'name': [ + (r'[a-zA-Z_]\w*(::[a-zA-Z_]\w*)*(::)?(?=\s*->)', Name.Namespace, '#pop'), + (r'[a-zA-Z_]\w*(::[a-zA-Z_]\w*)*::', Name.Namespace, '#pop'), + (r'[\w:]+', Name, '#pop'), + (r'[A-Z_]+(?=\W)', Name.Constant, '#pop'), + (r'(?=\W)', Text, '#pop'), + ], + 'funcname': [ + (r'[a-zA-Z_]\w*[!?]?', Name.Function), + (r'\s+', Text), + # argument declaration + (r'(\([$@%]*\))(\s*)', bygroups(Punctuation, Text)), + (r';', Punctuation, '#pop'), + (r'.*?\{', Punctuation, '#pop'), + ], + 'cb-string': [ + (r'\\[{}\\]', String.Other), + (r'\\', String.Other), + (r'\{', String.Other, 'cb-string'), + (r'\}', String.Other, '#pop'), + (r'[^{}\\]+', String.Other) + ], + 'rb-string': [ + (r'\\[()\\]', String.Other), + (r'\\', String.Other), + (r'\(', String.Other, 'rb-string'), + (r'\)', String.Other, '#pop'), + (r'[^()]+', String.Other) + ], + 'sb-string': [ + (r'\\[\[\]\\]', String.Other), + (r'\\', String.Other), + (r'\[', String.Other, 'sb-string'), + (r'\]', String.Other, '#pop'), + (r'[^\[\]]+', String.Other) + ], + 'lt-string': [ + (r'\\[<>\\]', String.Other), + (r'\\', String.Other), + (r'\<', String.Other, 'lt-string'), + (r'\>', String.Other, '#pop'), + (r'[^<>]+', String.Other) + ], + 'end-part': [ + (r'.+', Comment.Preproc, '#pop') + ] + } + + def analyse_text(text): + if shebang_matches(text, r'perl'): + return True + if re.search(r'(?:my|our)\s+[$@%(]', text): + return 0.9 + + +class Perl6Lexer(ExtendedRegexLexer): + """ + For `Perl 6 <http://www.perl6.org>`_ source code. + + .. versionadded:: 2.0 + """ + + name = 'Perl6' + aliases = ['perl6', 'pl6'] + filenames = ['*.pl', '*.pm', '*.nqp', '*.p6', '*.6pl', '*.p6l', '*.pl6', + '*.6pm', '*.p6m', '*.pm6', '*.t'] + mimetypes = ['text/x-perl6', 'application/x-perl6'] + flags = re.MULTILINE | re.DOTALL | re.UNICODE + + PERL6_IDENTIFIER_RANGE = r"['\w:-]" + + PERL6_KEYWORDS = ( + 'BEGIN', 'CATCH', 'CHECK', 'CONTROL', 'END', 'ENTER', 'FIRST', 'INIT', + 'KEEP', 'LAST', 'LEAVE', 'NEXT', 'POST', 'PRE', 'START', 'TEMP', + 'UNDO', 'as', 'assoc', 'async', 'augment', 'binary', 'break', 'but', + 'cached', 'category', 'class', 'constant', 'contend', 'continue', + 'copy', 'deep', 'default', 'defequiv', 'defer', 'die', 'do', 'else', + 'elsif', 'enum', 'equiv', 'exit', 'export', 'fail', 'fatal', 'for', + 'gather', 'given', 'goto', 'grammar', 'handles', 'has', 'if', 'inline', + 'irs', 'is', 'last', 'leave', 'let', 'lift', 'loop', 'looser', 'macro', + 'make', 'maybe', 'method', 'module', 'multi', 'my', 'next', 'of', + 'ofs', 'only', 'oo', 'ors', 'our', 'package', 'parsed', 'prec', + 'proto', 'readonly', 'redo', 'ref', 'regex', 'reparsed', 'repeat', + 'require', 'required', 'return', 'returns', 'role', 'rule', 'rw', + 'self', 'slang', 'state', 'sub', 'submethod', 'subset', 'supersede', + 'take', 'temp', 'tighter', 'token', 'trusts', 'try', 'unary', + 'unless', 'until', 'use', 'warn', 'when', 'where', 'while', 'will', + ) + + PERL6_BUILTINS = ( + 'ACCEPTS', 'HOW', 'REJECTS', 'VAR', 'WHAT', 'WHENCE', 'WHERE', 'WHICH', + 'WHO', 'abs', 'acos', 'acosec', 'acosech', 'acosh', 'acotan', 'acotanh', + 'all', 'any', 'approx', 'arity', 'asec', 'asech', 'asin', 'asinh', + 'assuming', 'atan', 'atan2', 'atanh', 'attr', 'bless', 'body', 'by', + 'bytes', 'caller', 'callsame', 'callwith', 'can', 'capitalize', 'cat', + 'ceiling', 'chars', 'chmod', 'chomp', 'chop', 'chr', 'chroot', + 'circumfix', 'cis', 'classify', 'clone', 'close', 'cmp_ok', 'codes', + 'comb', 'connect', 'contains', 'context', 'cos', 'cosec', 'cosech', + 'cosh', 'cotan', 'cotanh', 'count', 'defined', 'delete', 'diag', + 'dies_ok', 'does', 'e', 'each', 'eager', 'elems', 'end', 'eof', 'eval', + 'eval_dies_ok', 'eval_elsewhere', 'eval_lives_ok', 'evalfile', 'exists', + 'exp', 'first', 'flip', 'floor', 'flunk', 'flush', 'fmt', 'force_todo', + 'fork', 'from', 'getc', 'gethost', 'getlogin', 'getpeername', 'getpw', + 'gmtime', 'graphs', 'grep', 'hints', 'hyper', 'im', 'index', 'infix', + 'invert', 'is_approx', 'is_deeply', 'isa', 'isa_ok', 'isnt', 'iterator', + 'join', 'key', 'keys', 'kill', 'kv', 'lastcall', 'lazy', 'lc', 'lcfirst', + 'like', 'lines', 'link', 'lives_ok', 'localtime', 'log', 'log10', 'map', + 'max', 'min', 'minmax', 'name', 'new', 'nextsame', 'nextwith', 'nfc', + 'nfd', 'nfkc', 'nfkd', 'nok_error', 'nonce', 'none', 'normalize', 'not', + 'nothing', 'ok', 'once', 'one', 'open', 'opendir', 'operator', 'ord', + 'p5chomp', 'p5chop', 'pack', 'pair', 'pairs', 'pass', 'perl', 'pi', + 'pick', 'plan', 'plan_ok', 'polar', 'pop', 'pos', 'postcircumfix', + 'postfix', 'pred', 'prefix', 'print', 'printf', 'push', 'quasi', + 'quotemeta', 'rand', 're', 'read', 'readdir', 'readline', 'reduce', + 'reverse', 'rewind', 'rewinddir', 'rindex', 'roots', 'round', + 'roundrobin', 'run', 'runinstead', 'sameaccent', 'samecase', 'say', + 'sec', 'sech', 'sech', 'seek', 'shape', 'shift', 'sign', 'signature', + 'sin', 'sinh', 'skip', 'skip_rest', 'sleep', 'slurp', 'sort', 'splice', + 'split', 'sprintf', 'sqrt', 'srand', 'strand', 'subst', 'substr', 'succ', + 'sum', 'symlink', 'tan', 'tanh', 'throws_ok', 'time', 'times', 'to', + 'todo', 'trim', 'trim_end', 'trim_start', 'true', 'truncate', 'uc', + 'ucfirst', 'undef', 'undefine', 'uniq', 'unlike', 'unlink', 'unpack', + 'unpolar', 'unshift', 'unwrap', 'use_ok', 'value', 'values', 'vec', + 'version_lt', 'void', 'wait', 'want', 'wrap', 'write', 'zip', + ) + + PERL6_BUILTIN_CLASSES = ( + 'Abstraction', 'Any', 'AnyChar', 'Array', 'Associative', 'Bag', 'Bit', + 'Blob', 'Block', 'Bool', 'Buf', 'Byte', 'Callable', 'Capture', 'Char', 'Class', + 'Code', 'Codepoint', 'Comparator', 'Complex', 'Decreasing', 'Exception', + 'Failure', 'False', 'Grammar', 'Grapheme', 'Hash', 'IO', 'Increasing', + 'Int', 'Junction', 'KeyBag', 'KeyExtractor', 'KeyHash', 'KeySet', + 'KitchenSink', 'List', 'Macro', 'Mapping', 'Match', 'Matcher', 'Method', + 'Module', 'Num', 'Object', 'Ordered', 'Ordering', 'OrderingPair', + 'Package', 'Pair', 'Positional', 'Proxy', 'Range', 'Rat', 'Regex', + 'Role', 'Routine', 'Scalar', 'Seq', 'Set', 'Signature', 'Str', 'StrLen', + 'StrPos', 'Sub', 'Submethod', 'True', 'UInt', 'Undef', 'Version', 'Void', + 'Whatever', 'bit', 'bool', 'buf', 'buf1', 'buf16', 'buf2', 'buf32', + 'buf4', 'buf64', 'buf8', 'complex', 'int', 'int1', 'int16', 'int2', + 'int32', 'int4', 'int64', 'int8', 'num', 'rat', 'rat1', 'rat16', 'rat2', + 'rat32', 'rat4', 'rat64', 'rat8', 'uint', 'uint1', 'uint16', 'uint2', + 'uint32', 'uint4', 'uint64', 'uint8', 'utf16', 'utf32', 'utf8', + ) + + PERL6_OPERATORS = ( + 'X', 'Z', 'after', 'also', 'and', 'andthen', 'before', 'cmp', 'div', + 'eq', 'eqv', 'extra', 'ff', 'fff', 'ge', 'gt', 'le', 'leg', 'lt', 'm', + 'mm', 'mod', 'ne', 'or', 'orelse', 'rx', 's', 'tr', 'x', 'xor', 'xx', + '++', '--', '**', '!', '+', '-', '~', '?', '|', '||', '+^', '~^', '?^', + '^', '*', '/', '%', '%%', '+&', '+<', '+>', '~&', '~<', '~>', '?&', + 'gcd', 'lcm', '+', '-', '+|', '+^', '~|', '~^', '?|', '?^', + '~', '&', '^', 'but', 'does', '<=>', '..', '..^', '^..', '^..^', + '!=', '==', '<', '<=', '>', '>=', '~~', '===', '!eqv', + '&&', '||', '^^', '//', 'min', 'max', '??', '!!', 'ff', 'fff', 'so', + 'not', '<==', '==>', '<<==', '==>>', + ) + + # Perl 6 has a *lot* of possible bracketing characters + # this list was lifted from STD.pm6 (https://github.com/perl6/std) + PERL6_BRACKETS = { + u'\u0028': u'\u0029', u'\u003c': u'\u003e', u'\u005b': u'\u005d', + u'\u007b': u'\u007d', u'\u00ab': u'\u00bb', u'\u0f3a': u'\u0f3b', + u'\u0f3c': u'\u0f3d', u'\u169b': u'\u169c', u'\u2018': u'\u2019', + u'\u201a': u'\u2019', u'\u201b': u'\u2019', u'\u201c': u'\u201d', + u'\u201e': u'\u201d', u'\u201f': u'\u201d', u'\u2039': u'\u203a', + u'\u2045': u'\u2046', u'\u207d': u'\u207e', u'\u208d': u'\u208e', + u'\u2208': u'\u220b', u'\u2209': u'\u220c', u'\u220a': u'\u220d', + u'\u2215': u'\u29f5', u'\u223c': u'\u223d', u'\u2243': u'\u22cd', + u'\u2252': u'\u2253', u'\u2254': u'\u2255', u'\u2264': u'\u2265', + u'\u2266': u'\u2267', u'\u2268': u'\u2269', u'\u226a': u'\u226b', + u'\u226e': u'\u226f', u'\u2270': u'\u2271', u'\u2272': u'\u2273', + u'\u2274': u'\u2275', u'\u2276': u'\u2277', u'\u2278': u'\u2279', + u'\u227a': u'\u227b', u'\u227c': u'\u227d', u'\u227e': u'\u227f', + u'\u2280': u'\u2281', u'\u2282': u'\u2283', u'\u2284': u'\u2285', + u'\u2286': u'\u2287', u'\u2288': u'\u2289', u'\u228a': u'\u228b', + u'\u228f': u'\u2290', u'\u2291': u'\u2292', u'\u2298': u'\u29b8', + u'\u22a2': u'\u22a3', u'\u22a6': u'\u2ade', u'\u22a8': u'\u2ae4', + u'\u22a9': u'\u2ae3', u'\u22ab': u'\u2ae5', u'\u22b0': u'\u22b1', + u'\u22b2': u'\u22b3', u'\u22b4': u'\u22b5', u'\u22b6': u'\u22b7', + u'\u22c9': u'\u22ca', u'\u22cb': u'\u22cc', u'\u22d0': u'\u22d1', + u'\u22d6': u'\u22d7', u'\u22d8': u'\u22d9', u'\u22da': u'\u22db', + u'\u22dc': u'\u22dd', u'\u22de': u'\u22df', u'\u22e0': u'\u22e1', + u'\u22e2': u'\u22e3', u'\u22e4': u'\u22e5', u'\u22e6': u'\u22e7', + u'\u22e8': u'\u22e9', u'\u22ea': u'\u22eb', u'\u22ec': u'\u22ed', + u'\u22f0': u'\u22f1', u'\u22f2': u'\u22fa', u'\u22f3': u'\u22fb', + u'\u22f4': u'\u22fc', u'\u22f6': u'\u22fd', u'\u22f7': u'\u22fe', + u'\u2308': u'\u2309', u'\u230a': u'\u230b', u'\u2329': u'\u232a', + u'\u23b4': u'\u23b5', u'\u2768': u'\u2769', u'\u276a': u'\u276b', + u'\u276c': u'\u276d', u'\u276e': u'\u276f', u'\u2770': u'\u2771', + u'\u2772': u'\u2773', u'\u2774': u'\u2775', u'\u27c3': u'\u27c4', + u'\u27c5': u'\u27c6', u'\u27d5': u'\u27d6', u'\u27dd': u'\u27de', + u'\u27e2': u'\u27e3', u'\u27e4': u'\u27e5', u'\u27e6': u'\u27e7', + u'\u27e8': u'\u27e9', u'\u27ea': u'\u27eb', u'\u2983': u'\u2984', + u'\u2985': u'\u2986', u'\u2987': u'\u2988', u'\u2989': u'\u298a', + u'\u298b': u'\u298c', u'\u298d': u'\u298e', u'\u298f': u'\u2990', + u'\u2991': u'\u2992', u'\u2993': u'\u2994', u'\u2995': u'\u2996', + u'\u2997': u'\u2998', u'\u29c0': u'\u29c1', u'\u29c4': u'\u29c5', + u'\u29cf': u'\u29d0', u'\u29d1': u'\u29d2', u'\u29d4': u'\u29d5', + u'\u29d8': u'\u29d9', u'\u29da': u'\u29db', u'\u29f8': u'\u29f9', + u'\u29fc': u'\u29fd', u'\u2a2b': u'\u2a2c', u'\u2a2d': u'\u2a2e', + u'\u2a34': u'\u2a35', u'\u2a3c': u'\u2a3d', u'\u2a64': u'\u2a65', + u'\u2a79': u'\u2a7a', u'\u2a7d': u'\u2a7e', u'\u2a7f': u'\u2a80', + u'\u2a81': u'\u2a82', u'\u2a83': u'\u2a84', u'\u2a8b': u'\u2a8c', + u'\u2a91': u'\u2a92', u'\u2a93': u'\u2a94', u'\u2a95': u'\u2a96', + u'\u2a97': u'\u2a98', u'\u2a99': u'\u2a9a', u'\u2a9b': u'\u2a9c', + u'\u2aa1': u'\u2aa2', u'\u2aa6': u'\u2aa7', u'\u2aa8': u'\u2aa9', + u'\u2aaa': u'\u2aab', u'\u2aac': u'\u2aad', u'\u2aaf': u'\u2ab0', + u'\u2ab3': u'\u2ab4', u'\u2abb': u'\u2abc', u'\u2abd': u'\u2abe', + u'\u2abf': u'\u2ac0', u'\u2ac1': u'\u2ac2', u'\u2ac3': u'\u2ac4', + u'\u2ac5': u'\u2ac6', u'\u2acd': u'\u2ace', u'\u2acf': u'\u2ad0', + u'\u2ad1': u'\u2ad2', u'\u2ad3': u'\u2ad4', u'\u2ad5': u'\u2ad6', + u'\u2aec': u'\u2aed', u'\u2af7': u'\u2af8', u'\u2af9': u'\u2afa', + u'\u2e02': u'\u2e03', u'\u2e04': u'\u2e05', u'\u2e09': u'\u2e0a', + u'\u2e0c': u'\u2e0d', u'\u2e1c': u'\u2e1d', u'\u2e20': u'\u2e21', + u'\u3008': u'\u3009', u'\u300a': u'\u300b', u'\u300c': u'\u300d', + u'\u300e': u'\u300f', u'\u3010': u'\u3011', u'\u3014': u'\u3015', + u'\u3016': u'\u3017', u'\u3018': u'\u3019', u'\u301a': u'\u301b', + u'\u301d': u'\u301e', u'\ufd3e': u'\ufd3f', u'\ufe17': u'\ufe18', + u'\ufe35': u'\ufe36', u'\ufe37': u'\ufe38', u'\ufe39': u'\ufe3a', + u'\ufe3b': u'\ufe3c', u'\ufe3d': u'\ufe3e', u'\ufe3f': u'\ufe40', + u'\ufe41': u'\ufe42', u'\ufe43': u'\ufe44', u'\ufe47': u'\ufe48', + u'\ufe59': u'\ufe5a', u'\ufe5b': u'\ufe5c', u'\ufe5d': u'\ufe5e', + u'\uff08': u'\uff09', u'\uff1c': u'\uff1e', u'\uff3b': u'\uff3d', + u'\uff5b': u'\uff5d', u'\uff5f': u'\uff60', u'\uff62': u'\uff63', + } + + def _build_word_match(words, boundary_regex_fragment=None, prefix='', suffix=''): + if boundary_regex_fragment is None: + return r'\b(' + prefix + r'|'.join(re.escape(x) for x in words) + \ + suffix + r')\b' + else: + return r'(?<!' + boundary_regex_fragment + r')' + prefix + r'(' + \ + r'|'.join(re.escape(x) for x in words) + r')' + suffix + r'(?!' + \ + boundary_regex_fragment + r')' + + def brackets_callback(token_class): + def callback(lexer, match, context): + groups = match.groupdict() + opening_chars = groups['delimiter'] + n_chars = len(opening_chars) + adverbs = groups.get('adverbs') + + closer = Perl6Lexer.PERL6_BRACKETS.get(opening_chars[0]) + text = context.text + + if closer is None: # it's not a mirrored character, which means we + # just need to look for the next occurrence + + end_pos = text.find(opening_chars, match.start('delimiter') + n_chars) + else: # we need to look for the corresponding closing character, + # keep nesting in mind + closing_chars = closer * n_chars + nesting_level = 1 + + search_pos = match.start('delimiter') + + while nesting_level > 0: + next_open_pos = text.find(opening_chars, search_pos + n_chars) + next_close_pos = text.find(closing_chars, search_pos + n_chars) + + if next_close_pos == -1: + next_close_pos = len(text) + nesting_level = 0 + elif next_open_pos != -1 and next_open_pos < next_close_pos: + nesting_level += 1 + search_pos = next_open_pos + else: # next_close_pos < next_open_pos + nesting_level -= 1 + search_pos = next_close_pos + + end_pos = next_close_pos + + if end_pos < 0: # if we didn't find a closer, just highlight the + # rest of the text in this class + end_pos = len(text) + + if adverbs is not None and re.search(r':to\b', adverbs): + heredoc_terminator = text[match.start('delimiter') + n_chars:end_pos] + end_heredoc = re.search(r'^\s*' + re.escape(heredoc_terminator) + + r'\s*$', text[end_pos:], re.MULTILINE) + + if end_heredoc: + end_pos += end_heredoc.end() + else: + end_pos = len(text) + + yield match.start(), token_class, text[match.start():end_pos + n_chars] + context.pos = end_pos + n_chars + + return callback + + def opening_brace_callback(lexer, match, context): + stack = context.stack + + yield match.start(), Text, context.text[match.start():match.end()] + context.pos = match.end() + + # if we encounter an opening brace and we're one level + # below a token state, it means we need to increment + # the nesting level for braces so we know later when + # we should return to the token rules. + if len(stack) > 2 and stack[-2] == 'token': + context.perl6_token_nesting_level += 1 + + def closing_brace_callback(lexer, match, context): + stack = context.stack + + yield match.start(), Text, context.text[match.start():match.end()] + context.pos = match.end() + + # if we encounter a free closing brace and we're one level + # below a token state, it means we need to check the nesting + # level to see if we need to return to the token state. + if len(stack) > 2 and stack[-2] == 'token': + context.perl6_token_nesting_level -= 1 + if context.perl6_token_nesting_level == 0: + stack.pop() + + def embedded_perl6_callback(lexer, match, context): + context.perl6_token_nesting_level = 1 + yield match.start(), Text, context.text[match.start():match.end()] + context.pos = match.end() + context.stack.append('root') + + # If you're modifying these rules, be careful if you need to process '{' or '}' + # characters. We have special logic for processing these characters (due to the fact + # that you can nest Perl 6 code in regex blocks), so if you need to process one of + # them, make sure you also process the corresponding one! + tokens = { + 'common': [ + (r'#[`|=](?P<delimiter>(?P<first_char>[' + ''.join(PERL6_BRACKETS) + r'])(?P=first_char)*)', + brackets_callback(Comment.Multiline)), + (r'#[^\n]*$', Comment.Single), + (r'^(\s*)=begin\s+(\w+)\b.*?^\1=end\s+\2', Comment.Multiline), + (r'^(\s*)=for.*?\n\s*?\n', Comment.Multiline), + (r'^=.*?\n\s*?\n', Comment.Multiline), + (r'(regex|token|rule)(\s*' + PERL6_IDENTIFIER_RANGE + '+:sym)', + bygroups(Keyword, Name), 'token-sym-brackets'), + (r'(regex|token|rule)(?!' + PERL6_IDENTIFIER_RANGE + r')(\s*' + PERL6_IDENTIFIER_RANGE + '+)?', + bygroups(Keyword, Name), 'pre-token'), + # deal with a special case in the Perl 6 grammar (role q { ... }) + (r'(role)(\s+)(q)(\s*)', bygroups(Keyword, Text, Name, Text)), + (_build_word_match(PERL6_KEYWORDS, PERL6_IDENTIFIER_RANGE), Keyword), + (_build_word_match(PERL6_BUILTIN_CLASSES, PERL6_IDENTIFIER_RANGE, suffix='(?::[UD])?'), + Name.Builtin), + (_build_word_match(PERL6_BUILTINS, PERL6_IDENTIFIER_RANGE), Name.Builtin), + # copied from PerlLexer + (r'[$@%&][.^:?=!~]?' + PERL6_IDENTIFIER_RANGE + u'+(?:<<.*?>>|<.*?>|«.*?»)*', + Name.Variable), + (r'\$[!/](?:<<.*?>>|<.*?>|«.*?»)*', Name.Variable.Global), + (r'::\?\w+', Name.Variable.Global), + (r'[$@%&]\*' + PERL6_IDENTIFIER_RANGE + u'+(?:<<.*?>>|<.*?>|«.*?»)*', + Name.Variable.Global), + (r'\$(?:<.*?>)+', Name.Variable), + (r'(?:q|qq|Q)[a-zA-Z]?\s*(?P<adverbs>:[\w\s:]+)?\s*(?P<delimiter>(?P<first_char>[^0-9a-zA-Z:\s])' + r'(?P=first_char)*)', brackets_callback(String)), + # copied from PerlLexer + (r'0_?[0-7]+(_[0-7]+)*', Number.Oct), + (r'0x[0-9A-Fa-f]+(_[0-9A-Fa-f]+)*', Number.Hex), + (r'0b[01]+(_[01]+)*', Number.Bin), + (r'(?i)(\d*(_\d*)*\.\d+(_\d*)*|\d+(_\d*)*\.\d+(_\d*)*)(e[+-]?\d+)?', + Number.Float), + (r'(?i)\d+(_\d*)*e[+-]?\d+(_\d*)*', Number.Float), + (r'\d+(_\d+)*', Number.Integer), + (r'(?<=~~)\s*/(?:\\\\|\\/|.)*?/', String.Regex), + (r'(?<=[=(,])\s*/(?:\\\\|\\/|.)*?/', String.Regex), + (r'm\w+(?=\()', Name), + (r'(?:m|ms|rx)\s*(?P<adverbs>:[\w\s:]+)?\s*(?P<delimiter>(?P<first_char>[^\w:\s])' + r'(?P=first_char)*)', brackets_callback(String.Regex)), + (r'(?:s|ss|tr)\s*(?::[\w\s:]+)?\s*/(?:\\\\|\\/|.)*?/(?:\\\\|\\/|.)*?/', + String.Regex), + (r'<[^\s=].*?\S>', String), + (_build_word_match(PERL6_OPERATORS), Operator), + (r'\w' + PERL6_IDENTIFIER_RANGE + '*', Name), + (r"'(\\\\|\\[^\\]|[^'\\])*'", String), + (r'"(\\\\|\\[^\\]|[^"\\])*"', String), + ], + 'root': [ + include('common'), + (r'\{', opening_brace_callback), + (r'\}', closing_brace_callback), + (r'.+?', Text), + ], + 'pre-token': [ + include('common'), + (r'\{', Text, ('#pop', 'token')), + (r'.+?', Text), + ], + 'token-sym-brackets': [ + (r'(?P<delimiter>(?P<first_char>[' + ''.join(PERL6_BRACKETS) + '])(?P=first_char)*)', + brackets_callback(Name), ('#pop', 'pre-token')), + default(('#pop', 'pre-token')), + ], + 'token': [ + (r'\}', Text, '#pop'), + (r'(?<=:)(?:my|our|state|constant|temp|let).*?;', using(this)), + # make sure that quotes in character classes aren't treated as strings + (r'<(?:[-!?+.]\s*)?\[.*?\]>', String.Regex), + # make sure that '#' characters in quotes aren't treated as comments + (r"(?<!\\)'(\\\\|\\[^\\]|[^'\\])*'", String.Regex), + (r'(?<!\\)"(\\\\|\\[^\\]|[^"\\])*"', String.Regex), + (r'#.*?$', Comment.Single), + (r'\{', embedded_perl6_callback), + ('.+?', String.Regex), + ], + } + + def analyse_text(text): + def strip_pod(lines): + in_pod = False + stripped_lines = [] + + for line in lines: + if re.match(r'^=(?:end|cut)', line): + in_pod = False + elif re.match(r'^=\w+', line): + in_pod = True + elif not in_pod: + stripped_lines.append(line) + + return stripped_lines + + # XXX handle block comments + lines = text.splitlines() + lines = strip_pod(lines) + text = '\n'.join(lines) + + if shebang_matches(text, r'perl6|rakudo|niecza|pugs'): + return True + + saw_perl_decl = False + rating = False + + # check for my/our/has declarations + if re.search(r"(?:my|our|has)\s+(?:" + Perl6Lexer.PERL6_IDENTIFIER_RANGE + + r"+\s+)?[$@%&(]", text): + rating = 0.8 + saw_perl_decl = True + + for line in lines: + line = re.sub('#.*', '', line) + if re.match(r'^\s*$', line): + continue + + # match v6; use v6; use v6.0; use v6.0.0; + if re.match(r'^\s*(?:use\s+)?v6(?:\.\d(?:\.\d)?)?;', line): + return True + # match class, module, role, enum, grammar declarations + class_decl = re.match(r'^\s*(?:(?P<scope>my|our)\s+)?(?:module|class|role|enum|grammar)', line) + if class_decl: + if saw_perl_decl or class_decl.group('scope') is not None: + return True + rating = 0.05 + continue + break + + return rating + + def __init__(self, **options): + super(Perl6Lexer, self).__init__(**options) + self.encoding = options.get('encoding', 'utf-8') diff --git a/t/01-basic.t b/t/01-basic.t new file mode 100644 index 0000000..91781c8 --- /dev/null +++ b/t/01-basic.t @@ -0,0 +1,7 @@ +use v6.c; +use Test; +use Pygments; + +pass "replace me"; + +done-testing; |