diff options
Diffstat (limited to 'pygments/lexers/esoteric.py')
-rw-r--r-- | pygments/lexers/esoteric.py | 102 |
1 files changed, 100 insertions, 2 deletions
diff --git a/pygments/lexers/esoteric.py b/pygments/lexers/esoteric.py index c9db26b5..26222c9f 100644 --- a/pygments/lexers/esoteric.py +++ b/pygments/lexers/esoteric.py @@ -5,7 +5,7 @@ Lexers for esoteric languages. - :copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ @@ -13,7 +13,8 @@ from pygments.lexer import RegexLexer, include, words from pygments.token import Text, Comment, Operator, Keyword, Name, String, \ Number, Punctuation, Error -__all__ = ['BrainfuckLexer', 'BefungeLexer', 'RedcodeLexer', 'CAmkESLexer'] +__all__ = ['BrainfuckLexer', 'BefungeLexer', 'RedcodeLexer', 'CAmkESLexer', + 'CapDLLexer', 'AheuiLexer'] class BrainfuckLexer(RegexLexer): @@ -143,6 +144,65 @@ class CAmkESLexer(RegexLexer): } +class CapDLLexer(RegexLexer): + """ + Basic lexer for + `CapDL <https://ssrg.nicta.com.au/publications/nictaabstracts/Kuz_KLW_10.abstract.pml>`_. + + The source of the primary tool that reads such specifications is available + at https://github.com/seL4/capdl/tree/master/capDL-tool. Note that this + lexer only supports a subset of the grammar. For example, identifiers can + shadow type names, but these instances are currently incorrectly + highlighted as types. Supporting this would need a stateful lexer that is + considered unnecessarily complex for now. + + .. versionadded:: 2.2 + """ + name = 'CapDL' + aliases = ['capdl'] + filenames = ['*.cdl'] + + tokens = { + 'root': [ + # C pre-processor directive + (r'^\s*#.*\n', Comment.Preproc), + + # Whitespace, comments + (r'\s+', Text), + (r'/\*(.|\n)*?\*/', Comment), + (r'(//|--).*\n', Comment), + + (r'[<>\[(){},:;=\]]', Punctuation), + (r'\.\.', Punctuation), + + (words(('arch', 'arm11', 'caps', 'child_of', 'ia32', 'irq', 'maps', + 'objects'), suffix=r'\b'), Keyword), + + (words(('aep', 'asid_pool', 'cnode', 'ep', 'frame', 'io_device', + 'io_ports', 'io_pt', 'notification', 'pd', 'pt', 'tcb', + 'ut', 'vcpu'), suffix=r'\b'), Keyword.Type), + + # Properties + (words(('asid', 'addr', 'badge', 'cached', 'dom', 'domainID', 'elf', + 'fault_ep', 'G', 'guard', 'guard_size', 'init', 'ip', + 'prio', 'sp', 'R', 'RG', 'RX', 'RW', 'RWG', 'RWX', 'W', + 'WG', 'WX', 'level', 'masked', 'master_reply', 'paddr', + 'ports', 'reply', 'uncached'), suffix=r'\b'), + Keyword.Reserved), + + # Literals + (r'0[xX][\da-fA-F]+', Number.Hex), + (r'\d+(\.\d+)?(k|M)?', Number), + (words(('bits',), suffix=r'\b'), Number), + (words(('cspace', 'vspace', 'reply_slot', 'caller_slot', + 'ipc_buffer_slot'), suffix=r'\b'), Number), + + # Identifiers + (r'[a-zA-Z_][-@\.\w]*', Name), + ], + } + + class RedcodeLexer(RegexLexer): """ A simple Redcode lexer based on ICWS'94. @@ -177,3 +237,41 @@ class RedcodeLexer(RegexLexer): (r'[-+]?\d+', Number.Integer), ], } + + +class AheuiLexer(RegexLexer): + """ + Aheui_ Lexer. + + Aheui_ is esoteric language based on Korean alphabets. + + .. _Aheui: http://aheui.github.io/ + + """ + + name = 'Aheui' + aliases = ['aheui'] + filenames = ['*.aheui'] + + tokens = { + 'root': [ + (u'[' + u'나-낳냐-냫너-넣녀-녛노-놓뇨-눟뉴-닇' + u'다-닿댜-댷더-덯뎌-뎧도-돟됴-둫듀-딓' + u'따-땋땨-떃떠-떻뗘-뗳또-똫뚀-뚷뜌-띟' + u'라-랗랴-럏러-렇려-렿로-롷료-뤃류-릫' + u'마-맣먀-먛머-멓며-몋모-뫃묘-뭏뮤-믷' + u'바-밯뱌-뱧버-벟벼-볗보-봏뵤-붛뷰-빃' + u'빠-빻뺘-뺳뻐-뻫뼈-뼣뽀-뽛뾰-뿧쀼-삏' + u'사-샇샤-샿서-섷셔-셯소-솧쇼-숳슈-싛' + u'싸-쌓쌰-썋써-쎃쎠-쎻쏘-쏳쑈-쑿쓔-씧' + u'자-잫쟈-쟣저-젛져-졓조-좋죠-줗쥬-즿' + u'차-챃챠-챻처-첳쳐-쳫초-촣쵸-춯츄-칗' + u'카-캏캬-컇커-컿켜-켷코-콯쿄-쿻큐-킣' + u'타-탛탸-턓터-텋텨-톃토-톻툐-퉇튜-틯' + u'파-팧퍄-퍟퍼-펗펴-폏포-퐇표-풓퓨-픻' + u'하-핳햐-햫허-헣혀-혛호-홓효-훟휴-힇' + u']', Operator), + ('.', Comment), + ], + } |