diff options
| -rw-r--r-- | AUTHORS | 1 | ||||
| -rw-r--r-- | doc/languages.rst | 1 | ||||
| -rw-r--r-- | pygments/lexers/_mapping.py | 2 | ||||
| -rw-r--r-- | pygments/lexers/functional.py | 171 |
4 files changed, 170 insertions, 5 deletions
@@ -115,6 +115,7 @@ Other contributors, listed alphabetically, are: * Jesper Noehr -- HTML formatter "anchorlinenos" * Mike Nolta -- Julia lexer * Jonas Obrist -- BBCode lexer +* Edward O'Callaghan -- Cryptol lexer * David Oliva -- Rebol lexer * Pat Pannuto -- nesC lexer * Jon Parise -- Protocol buffers lexer diff --git a/doc/languages.rst b/doc/languages.rst index 3b0db5eb..0f98c583 100644 --- a/doc/languages.rst +++ b/doc/languages.rst @@ -25,6 +25,7 @@ Programming languages * ColdFusion * Common Lisp * Coq +* Cryptol (incl. Literate Cryptol) * `Cython <http://cython.org>`_ * `D <http://digitalmars.com/d>`_ * Dart diff --git a/pygments/lexers/_mapping.py b/pygments/lexers/_mapping.py index 339e9cfb..fd170cfe 100644 --- a/pygments/lexers/_mapping.py +++ b/pygments/lexers/_mapping.py @@ -90,6 +90,7 @@ LEXERS = { 'CudaLexer': ('pygments.lexers.compiled', 'CUDA', ('cuda', 'cu'), ('*.cu', '*.cuh'), ('text/x-cuda',)), 'CypherLexer': ('pygments.lexers.graph', 'Cypher', ('cypher',), ('*.cyp', '*.cypher'), ()), 'CythonLexer': ('pygments.lexers.compiled', 'Cython', ('cython', 'pyx', 'pyrex'), ('*.pyx', '*.pxd', '*.pxi'), ('text/x-cython', 'application/x-cython')), + 'CryptolLexer': ('pygments.lexers.functional', 'Cryptol', ('cryptol', 'cry'), ('*.cry',), ('text/x-cryptol',)), 'DLexer': ('pygments.lexers.compiled', 'D', ('d',), ('*.d', '*.di'), ('text/x-dsrc',)), 'DObjdumpLexer': ('pygments.lexers.asm', 'd-objdump', ('d-objdump',), ('*.d-objdump',), ('text/x-d-objdump',)), 'DarcsPatchLexer': ('pygments.lexers.text', 'Darcs Patch', ('dpatch',), ('*.dpatch', '*.darcspatch'), ()), @@ -190,6 +191,7 @@ LEXERS = { 'LighttpdConfLexer': ('pygments.lexers.text', 'Lighttpd configuration file', ('lighty', 'lighttpd'), (), ('text/x-lighttpd-conf',)), 'LimboLexer': ('pygments.lexers.inferno', 'Limbo', ('limbo',), ('*.b',), ('text/limbo',)), 'LiterateAgdaLexer': ('pygments.lexers.functional', 'Literate Agda', ('lagda', 'literate-agda'), ('*.lagda',), ('text/x-literate-agda',)), + 'LiterateCryptolLexer': ('pygments.lexers.functional', 'Literate Cryptol', ('lcry', 'literate-cryptol', 'lcrytol'), ('*.lcry',), ('text/x-literate-cryptol',)), 'LiterateHaskellLexer': ('pygments.lexers.functional', 'Literate Haskell', ('lhs', 'literate-haskell', 'lhaskell'), ('*.lhs',), ('text/x-literate-haskell',)), 'LiterateIdrisLexer': ('pygments.lexers.functional', 'Literate Idris', ('lidr', 'literate-idris', 'lidris'), ('*.lidr',), ('text/x-literate-idris',)), 'LiveScriptLexer': ('pygments.lexers.web', 'LiveScript', ('live-script', 'livescript'), ('*.ls',), ('text/livescript',)), diff --git a/pygments/lexers/functional.py b/pygments/lexers/functional.py index 6d808f7e..2a840694 100644 --- a/pygments/lexers/functional.py +++ b/pygments/lexers/functional.py @@ -16,11 +16,13 @@ from pygments.token import Text, Comment, Operator, Keyword, Name, \ String, Number, Punctuation, Literal, Generic, Error from pygments import unistring as uni -__all__ = ['RacketLexer', 'SchemeLexer', 'CommonLispLexer', 'HaskellLexer', - 'AgdaLexer', 'LiterateHaskellLexer', 'LiterateAgdaLexer', - 'SMLLexer', 'OcamlLexer', 'ErlangLexer', 'ErlangShellLexer', - 'OpaLexer', 'CoqLexer', 'NewLispLexer', 'NixLexer', 'ElixirLexer', - 'ElixirConsoleLexer', 'KokaLexer', 'IdrisLexer', 'LiterateIdrisLexer'] +__all__ = ['RacketLexer', 'SchemeLexer', 'CommonLispLexer', 'CryptolLexer', + 'HaskellLexer', 'AgdaLexer', 'LiterateCryptolLexer', + 'LiterateHaskellLexer', 'LiterateAgdaLexer', 'SMLLexer', + 'OcamlLexer', 'ErlangLexer', 'ErlangShellLexer', 'OpaLexer', + 'CoqLexer', 'NewLispLexer', 'NixLexer', 'ElixirLexer', + 'ElixirConsoleLexer', 'KokaLexer', 'IdrisLexer', + 'LiterateIdrisLexer'] line_re = re.compile('.*?\n') @@ -895,6 +897,142 @@ class CommonLispLexer(RegexLexer): } +class CryptolLexer(RegexLexer): + """ + FIXME: A Cryptol2 lexer based on the lexemes defined in the Haskell 98 Report. + + .. versionadded:: 2.0 + """ + name = 'Cryptol' + aliases = ['cryptol', 'cry'] + filenames = ['*.cry'] + mimetypes = ['text/x-cryptol'] + + reserved = ['Arith','Bit','Cmp','False','Inf','True','else', + 'export','extern','fin','if','import','inf','lg2', + 'max','min','module','newtype','pragma','property', + 'then','type','where','width'] + ascii = ['NUL','SOH','[SE]TX','EOT','ENQ','ACK', + 'BEL','BS','HT','LF','VT','FF','CR','S[OI]','DLE', + 'DC[1-4]','NAK','SYN','ETB','CAN', + 'EM','SUB','ESC','[FGRU]S','SP','DEL'] + + tokens = { + 'root': [ + # Whitespace: + (r'\s+', Text), + #(r'--\s*|.*$', Comment.Doc), + (r'//.*$', Comment.Single), + (r'/\*', Comment.Multiline, 'comment'), + # Lexemes: + # Identifiers + (r'\bimport\b', Keyword.Reserved, 'import'), + (r'\bmodule\b', Keyword.Reserved, 'module'), + (r'\berror\b', Name.Exception), + (r'\b(%s)(?!\')\b' % '|'.join(reserved), Keyword.Reserved), + (r'^[_a-z][\w\']*', Name.Function), + (r"'?[_a-z][\w']*", Name), + (r"('')?[A-Z][\w\']*", Keyword.Type), + # Operators + (r'\\(?![:!#$%&*+.\\/<=>?@^|~-]+)', Name.Function), # lambda operator + (r'(<-|::|->|=>|=)(?![:!#$%&*+.\\/<=>?@^|~-]+)', Operator.Word), # specials + (r':[:!#$%&*+.\\/<=>?@^|~-]*', Keyword.Type), # Constructor operators + (r'[:!#$%&*+.\\/<=>?@^|~-]+', Operator), # Other operators + # Numbers + (r'\d+[eE][+-]?\d+', Number.Float), + (r'\d+\.\d+([eE][+-]?\d+)?', Number.Float), + (r'0[oO][0-7]+', Number.Oct), + (r'0[xX][\da-fA-F]+', Number.Hex), + (r'\d+', Number.Integer), + # Character/String Literals + (r"'", String.Char, 'character'), + (r'"', String, 'string'), + # Special + (r'\[\]', Keyword.Type), + (r'\(\)', Name.Builtin), + (r'[][(),;`{}]', Punctuation), + ], + 'import': [ + # Import statements + (r'\s+', Text), + (r'"', String, 'string'), + # after "funclist" state + (r'\)', Punctuation, '#pop'), + (r'qualified\b', Keyword), + # import X as Y + (r'([A-Z][a-zA-Z0-9_.]*)(\s+)(as)(\s+)([A-Z][a-zA-Z0-9_.]*)', + bygroups(Name.Namespace, Text, Keyword, Text, Name), '#pop'), + # import X hiding (functions) + (r'([A-Z][a-zA-Z0-9_.]*)(\s+)(hiding)(\s+)(\()', + bygroups(Name.Namespace, Text, Keyword, Text, Punctuation), 'funclist'), + # import X (functions) + (r'([A-Z][a-zA-Z0-9_.]*)(\s+)(\()', + bygroups(Name.Namespace, Text, Punctuation), 'funclist'), + # import X + (r'[a-zA-Z0-9_.]+', Name.Namespace, '#pop'), + ], + 'module': [ + (r'\s+', Text), + (r'([A-Z][a-zA-Z0-9_.]*)(\s+)(\()', + bygroups(Name.Namespace, Text, Punctuation), 'funclist'), + (r'[A-Z][a-zA-Z0-9_.]*', Name.Namespace, '#pop'), + ], + 'funclist': [ + (r'\s+', Text), + (r'[A-Z][a-zA-Z0-9_]*', Keyword.Type), + (r'(_[\w\']+|[a-z][\w\']*)', Name.Function), + (r'--(?![!#$%&*+./<=>?@\^|_~:\\]).*?$', Comment.Single), + (r'{-', Comment.Multiline, 'comment'), + (r',', Punctuation), + (r'[:!#$%&*+.\\/<=>?@^|~-]+', Operator), + # (HACK, but it makes sense to push two instances, believe me) + (r'\(', Punctuation, ('funclist', 'funclist')), + (r'\)', Punctuation, '#pop:2'), + ], + 'comment': [ + # Multiline Comments + (r'[^/\*]+', Comment.Multiline), + (r'/\*', Comment.Multiline, '#push'), + (r'\*/', Comment.Multiline, '#pop'), + (r'[\*/]', Comment.Multiline), + ], + 'character': [ + # Allows multi-chars, incorrectly. + (r"[^\\']'", String.Char, '#pop'), + (r"\\", String.Escape, 'escape'), + ("'", String.Char, '#pop'), + ], + 'string': [ + (r'[^\\"]+', String), + (r"\\", String.Escape, 'escape'), + ('"', String, '#pop'), + ], + 'escape': [ + (r'[abfnrtv"\'&\\]', String.Escape, '#pop'), + (r'\^[][A-Z@\^_]', String.Escape, '#pop'), + ('|'.join(ascii), String.Escape, '#pop'), + (r'o[0-7]+', String.Escape, '#pop'), + (r'x[\da-fA-F]+', String.Escape, '#pop'), + (r'\d+', String.Escape, '#pop'), + (r'\s+\\', String.Escape, '#pop'), + ], + } + + EXTRA_KEYWORDS = ['join', 'split', 'reverse', 'transpose', 'width', + 'length', 'tail', '<<', '>>', '<<<', '>>>', 'const', + 'reg', 'par', 'seq', 'ASSERT', 'undefined', 'error', + 'trace'] + + def get_tokens_unprocessed(self, text): + stack = ['root'] + for index, token, value in \ + RegexLexer.get_tokens_unprocessed(self, text, stack): + if token is Name and value in self.EXTRA_KEYWORDS: + yield index, Name.Builtin, value + else: + yield index, token, value + + class HaskellLexer(RegexLexer): """ A Haskell lexer based on the lexemes defined in the Haskell 98 Report. @@ -1262,6 +1400,29 @@ class LiterateLexer(Lexer): yield item +class LiterateCryptolLexer(LiterateLexer): + """ + For Literate Cryptol (Bird-style or LaTeX) source. + + Additional options accepted: + + `litstyle` + If given, must be ``"bird"`` or ``"latex"``. If not given, the style + is autodetected: if the first non-whitespace character in the source + is a backslash or percent character, LaTeX is assumed, else Bird. + + .. versionadded:: 0.9 + """ + name = 'Literate Cryptol' + aliases = ['lcry', 'literate-cryptol', 'lcryptol'] + filenames = ['*.lcry'] + mimetypes = ['text/x-literate-cryptol'] + + def __init__(self, **options): + crylexer = CryptolLexer(**options) + LiterateLexer.__init__(self, crylexer, **options) + + class LiterateHaskellLexer(LiterateLexer): """ For Literate Haskell (Bird-style or LaTeX) source. |