Mercurial Repositories > eric / file comparison
comparison: ThirdParty/Pygments/pygments/lexers/grammar_notation.py
ThirdParty/Pygments/pygments/lexers/grammar_notation.py
- changeset 4697
- c2e9bf425554
- child 5713
- 6762afd9f963
equal
deleted
inserted
replaced
| 4696:bf4d19a7cade | 4697:c2e9bf425554 |
|---|---|
| 1 # -*- coding: utf-8 -*- | |
| 2 """ | |
| 3 pygments.lexers.grammar_notation | |
| 4 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ | |
| 5 | |
| 6 Lexers for grammer notations like BNF. | |
| 7 | |
| 8 :copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS. | |
| 9 :license: BSD, see LICENSE for details. | |
| 10 """ | |
| 11 | |
| 12 from pygments.lexer import RegexLexer, bygroups, words | |
| 13 from pygments.token import Punctuation, Text, Comment, Operator, \ | |
| 14 Keyword, Name, Literal | |
| 15 | |
| 16 __all__ = ['BnfLexer', 'AbnfLexer'] | |
| 17 | |
| 18 | |
| 19 class BnfLexer(RegexLexer): | |
| 20 """ | |
| 21 This lexer is for grammer notations which are similar to | |
| 22 original BNF. | |
| 23 | |
| 24 In order to maximize a number of targets of this lexer, | |
| 25 let's decide some designs: | |
| 26 | |
| 27 * We don't distinguish `Terminal Symbol`. | |
| 28 | |
| 29 * We do assume that `NonTerminal Symbol` are always enclosed | |
| 30 with arrow brackets. | |
| 31 | |
| 32 * We do assume that `NonTerminal Symbol` may include | |
| 33 any printable characters except arrow brackets and ASCII 0x20. | |
| 34 This assumption is for `RBNF <http://www.rfc-base.org/txt/rfc-5511.txt>`_. | |
| 35 | |
| 36 * We do assume that target notation doesn't support comment. | |
| 37 | |
| 38 * We don't distinguish any operators and punctuation except | |
| 39 `::=`. | |
| 40 | |
| 41 Though these desision making might cause too minimal highlighting | |
| 42 and you might be disappointed, but it is reasonable for us. | |
| 43 | |
| 44 .. versionadded:: 2.1 | |
| 45 """ | |
| 46 | |
| 47 name = 'BNF' | |
| 48 aliases = ['bnf'] | |
| 49 filenames = ['*.bnf'] | |
| 50 mimetypes = ['text/x-bnf'] | |
| 51 | |
| 52 tokens = { | |
| 53 'root': [ | |
| 54 (r'(<)([ -;=?-~]+)(>)', | |
| 55 bygroups(Punctuation, Name.Class, Punctuation)), | |
| 56 | |
| 57 # an only operator | |
| 58 (r'::=', Operator), | |
| 59 | |
| 60 # fallback | |
| 61 (r'[^<>:]+', Text), # for performance | |
| 62 (r'.', Text), | |
| 63 ], | |
| 64 } | |
| 65 | |
| 66 | |
| 67 class AbnfLexer(RegexLexer): | |
| 68 """ | |
| 69 Lexer for `IETF 7405 ABNF | |
| 70 <http://www.ietf.org/rfc/rfc7405.txt>`_ | |
| 71 (Updates `5234 <http://www.ietf.org/rfc/rfc5234.txt>`_) | |
| 72 grammars. | |
| 73 | |
| 74 .. versionadded:: 2.1 | |
| 75 """ | |
| 76 | |
| 77 name = 'ABNF' | |
| 78 aliases = ['abnf'] | |
| 79 filenames = ['*.abnf'] | |
| 80 mimetypes = ['text/x-abnf'] | |
| 81 | |
| 82 _core_rules = ( | |
| 83 'ALPHA', 'BIT', 'CHAR', 'CR', 'CRLF', 'CTL', 'DIGIT', | |
| 84 'DQUOTE', 'HEXDIG', 'HTAB', 'LF', 'LWSP', 'OCTET', | |
| 85 'SP', 'VCHAR', 'WSP') | |
| 86 | |
| 87 tokens = { | |
| 88 'root': [ | |
| 89 # comment | |
| 90 (r';.*$', Comment.Single), | |
| 91 | |
| 92 # quoted | |
| 93 # double quote itself in this state, it is as '%x22'. | |
| 94 (r'(%[si])?"[^"]*"', Literal), | |
| 95 | |
| 96 # binary (but i have never seen...) | |
| 97 (r'%b[01]+\-[01]+\b', Literal), # range | |
| 98 (r'%b[01]+(\.[01]+)*\b', Literal), # concat | |
| 99 | |
| 100 # decimal | |
| 101 (r'%d[0-9]+\-[0-9]+\b', Literal), # range | |
| 102 (r'%d[0-9]+(\.[0-9]+)*\b', Literal), # concat | |
| 103 | |
| 104 # hexadecimal | |
| 105 (r'%x[0-9a-fA-F]+\-[0-9a-fA-F]+\b', Literal), # range | |
| 106 (r'%x[0-9a-fA-F]+(\.[0-9a-fA-F]+)*\b', Literal), # concat | |
| 107 | |
| 108 # repetition (<a>*<b>element) including nRule | |
| 109 (r'\b[0-9]+\*[0-9]+', Operator), | |
| 110 (r'\b[0-9]+\*', Operator), | |
| 111 (r'\b[0-9]+', Operator), | |
| 112 (r'\*', Operator), | |
| 113 | |
| 114 # Strictly speaking, these are not keyword but | |
| 115 # are called `Core Rule'. | |
| 116 (words(_core_rules, suffix=r'\b'), Keyword), | |
| 117 | |
| 118 # nonterminals (ALPHA *(ALPHA / DIGIT / "-")) | |
| 119 (r'[a-zA-Z][a-zA-Z0-9-]+\b', Name.Class), | |
| 120 | |
| 121 # operators | |
| 122 (r'(=/|=|/)', Operator), | |
| 123 | |
| 124 # punctuation | |
| 125 (r'[\[\]()]', Punctuation), | |
| 126 | |
| 127 # fallback | |
| 128 (r'\s+', Text), | |
| 129 (r'.', Text), | |
| 130 ], | |
| 131 } |
