diff options
Diffstat (limited to 'pygments/lexers/agile.py')
| -rw-r--r-- | pygments/lexers/agile.py | 1717 |
1 files changed, 1110 insertions, 607 deletions
diff --git a/pygments/lexers/agile.py b/pygments/lexers/agile.py index a986c9d6..17e97c3b 100644 --- a/pygments/lexers/agile.py +++ b/pygments/lexers/agile.py @@ -5,27 +5,30 @@ Lexers for agile languages. - :copyright: Copyright 2006-2010 by the Pygments team, see AUTHORS. + :copyright: Copyright 2006-2014 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. """ import re from pygments.lexer import Lexer, RegexLexer, ExtendedRegexLexer, \ - LexerContext, include, combined, do_insertions, bygroups, using + LexerContext, include, combined, do_insertions, bygroups, using, this from pygments.token import Error, Text, Other, \ Comment, Operator, Keyword, Name, String, Number, Generic, Punctuation -from pygments.util import get_bool_opt, get_list_opt, shebang_matches +from pygments.util import get_bool_opt, get_list_opt, shebang_matches, iteritems from pygments import unistring as uni __all__ = ['PythonLexer', 'PythonConsoleLexer', 'PythonTracebackLexer', - 'RubyLexer', 'RubyConsoleLexer', 'PerlLexer', 'LuaLexer', - 'MiniDLexer', 'IoLexer', 'TclLexer', 'ClojureLexer', - 'Python3Lexer', 'Python3TracebackLexer', 'FactorLexer', 'IokeLexer', 'ChaiscriptLexer'] + 'Python3Lexer', 'Python3TracebackLexer', 'RubyLexer', + 'RubyConsoleLexer', 'PerlLexer', 'LuaLexer', 'MoonScriptLexer', + 'CrocLexer', 'MiniDLexer', 'IoLexer', 'TclLexer', 'FactorLexer', + 'FancyLexer', 'DgLexer', 'Perl6Lexer', 'HyLexer', + 'ChaiscriptLexer'] # b/w compatibility from pygments.lexers.functional import SchemeLexer +from pygments.lexers.jvm import IokeLexer, ClojureLexer line_re = re.compile('.*?\n') @@ -36,8 +39,8 @@ class PythonLexer(RegexLexer): """ name = 'Python' - aliases = ['python', 'py'] - filenames = ['*.py', '*.pyw', '*.sc', 'SConstruct', 'SConscript', '*.tac'] + aliases = ['python', 'py', 'sage'] + filenames = ['*.py', '*.pyw', '*.sc', 'SConstruct', 'SConscript', '*.tac', '*.sage'] mimetypes = ['text/x-python', 'application/x-python'] tokens = { @@ -55,8 +58,10 @@ class PythonLexer(RegexLexer): include('keywords'), (r'(def)((?:\s|\\\s)+)', bygroups(Keyword, Text), 'funcname'), (r'(class)((?:\s|\\\s)+)', bygroups(Keyword, Text), 'classname'), - (r'(from)((?:\s|\\\s)+)', bygroups(Keyword.Namespace, Text), 'fromimport'), - (r'(import)((?:\s|\\\s)+)', bygroups(Keyword.Namespace, Text), 'import'), + (r'(from)((?:\s|\\\s)+)', bygroups(Keyword.Namespace, Text), + 'fromimport'), + (r'(import)((?:\s|\\\s)+)', bygroups(Keyword.Namespace, Text), + 'import'), include('builtins'), include('backtick'), ('(?:[rR]|[uU][rR]|[rR][uU])"""', String, 'tdqs'), @@ -73,7 +78,7 @@ class PythonLexer(RegexLexer): 'keywords': [ (r'(assert|break|continue|del|elif|else|except|exec|' r'finally|for|global|if|lambda|pass|print|raise|' - r'return|try|while|yield|as|with)\b', Keyword), + r'return|try|while|yield(\s+from)?|as|with)\b', Keyword), ], 'builtins': [ (r'(?<!\.)(__import__|abs|all|any|apply|basestring|bin|bool|buffer|' @@ -102,12 +107,13 @@ class PythonLexer(RegexLexer): r'WindowsError|ZeroDivisionError)\b', Name.Exception), ], 'numbers': [ - (r'(\d+\.\d*|\d*\.\d+)([eE][+-]?[0-9]+)?', Number.Float), - (r'\d+[eE][+-]?[0-9]+', Number.Float), - (r'0[0-7]+', Number.Oct), + (r'(\d+\.\d*|\d*\.\d+)([eE][+-]?[0-9]+)?j?', Number.Float), + (r'\d+[eE][+-]?[0-9]+j?', Number.Float), + (r'0[0-7]+j?', Number.Oct), + (r'0[bB][01]+', Number.Bin), (r'0[xX][a-fA-F0-9]+', Number.Hex), (r'\d+L', Number.Integer.Long), - (r'\d+', Number.Integer) + (r'\d+j?', Number.Integer) ], 'backtick': [ ('`.*?`', String.Backtick), @@ -123,15 +129,23 @@ class PythonLexer(RegexLexer): ('[a-zA-Z_][a-zA-Z0-9_]*', Name.Class, '#pop') ], 'import': [ - (r'((?:\s|\\\s)+)(as)((?:\s|\\\s)+)', - bygroups(Text, Keyword.Namespace, Text)), + (r'(?:[ \t]|\\\n)+', Text), + (r'as\b', Keyword.Namespace), + (r',', Operator), (r'[a-zA-Z_][a-zA-Z0-9_.]*', Name.Namespace), - (r'(\s*)(,)(\s*)', bygroups(Text, Operator, Text)), (r'', Text, '#pop') # all else: go back ], 'fromimport': [ - (r'((?:\s|\\\s)+)(import)\b', bygroups(Text, Keyword.Namespace), '#pop'), + (r'(?:[ \t]|\\\n)+', Text), + (r'import\b', Keyword.Namespace, '#pop'), + # if None occurs here, it's "raise x from None", since None can + # never be a module name + (r'None\b', Name.Builtin.Pseudo, '#pop'), + # sadly, in "raise x from y" y will be highlighted as namespace too (r'[a-zA-Z_.][a-zA-Z0-9_.]*', Name.Namespace), + # anything else here also means "raise x from y" and is therefore + # not an error + (r'', Text, '#pop'), ], 'stringescape': [ (r'\\([\\abfnrtv"\']|\n|N{.*?}|u[a-fA-F0-9]{4}|' @@ -152,12 +166,12 @@ class PythonLexer(RegexLexer): ], 'dqs': [ (r'"', String, '#pop'), - (r'\\\\|\\"|\\\n', String.Escape), # included here again for raw strings + (r'\\\\|\\"|\\\n', String.Escape), # included here for raw strings include('strings') ], 'sqs': [ (r"'", String, '#pop'), - (r"\\\\|\\'|\\\n", String.Escape), # included here again for raw strings + (r"\\\\|\\'|\\\n", String.Escape), # included here for raw strings include('strings') ], 'tdqs': [ @@ -173,14 +187,15 @@ class PythonLexer(RegexLexer): } def analyse_text(text): - return shebang_matches(text, r'pythonw?(2\.\d)?') + return shebang_matches(text, r'pythonw?(2(\.\d)?)?') or \ + 'import ' in text[:1000] class Python3Lexer(RegexLexer): """ For `Python <http://www.python.org>`_ source code (version 3.0). - *New in Pygments 0.10.* + .. versionadded:: 0.10 """ name = 'Python 3' @@ -195,8 +210,9 @@ class Python3Lexer(RegexLexer): tokens = PythonLexer.tokens.copy() tokens['keywords'] = [ (r'(assert|break|continue|del|elif|else|except|' - r'finally|for|global|if|lambda|pass|raise|' - r'return|try|while|yield|as|with|True|False|None)\b', Keyword), + r'finally|for|global|if|lambda|pass|raise|nonlocal|' + r'return|try|while|yield(\s+from)?|as|with|True|False|None)\b', + Keyword), ] tokens['builtins'] = [ (r'(?<!\.)(__import__|abs|all|any|bin|bool|bytearray|bytes|' @@ -221,7 +237,14 @@ class Python3Lexer(RegexLexer): r'TypeError|UnboundLocalError|UnicodeDecodeError|' r'UnicodeEncodeError|UnicodeError|UnicodeTranslateError|' r'UnicodeWarning|UserWarning|ValueError|VMSError|Warning|' - r'WindowsError|ZeroDivisionError)\b', Name.Exception), + r'WindowsError|ZeroDivisionError|' + # new builtin exceptions from PEP 3151 + r'BlockingIOError|ChildProcessError|ConnectionError|' + r'BrokenPipeError|ConnectionAbortedError|ConnectionRefusedError|' + r'ConnectionResetError|FileExistsError|FileNotFoundError|' + r'InterruptedError|IsADirectoryError|NotADirectoryError|' + r'PermissionError|ProcessLookupError|TimeoutError)\b', + Name.Exception), ] tokens['numbers'] = [ (r'(\d+\.\d*|\d*\.\d+)([eE][+-]?[0-9]+)?', Number.Float), @@ -252,6 +275,7 @@ class Python3Lexer(RegexLexer): (r'(\s+)(import)\b', bygroups(Text, Keyword), '#pop'), (r'\.', Name.Namespace), (uni_name, Name.Namespace), + (r'', Text, '#pop'), ] # don't highlight "%s" substitutions tokens['strings'] = [ @@ -285,7 +309,8 @@ class PythonConsoleLexer(Lexer): `python3` Use Python 3 lexer for code. Default is ``False``. - *New in Pygments 1.0.* + + .. versionadded:: 1.0 """ name = 'Python console session' aliases = ['pycon'] @@ -330,7 +355,7 @@ class PythonConsoleLexer(Lexer): curcode = '' insertions = [] if (line.startswith(u'Traceback (most recent call last):') or - re.match(ur' File "[^"]+", line \d+\n$', line)): + re.match(u' File "[^"]+", line \\d+\\n$', line)): tb = 1 curtb = line tbindex = match.start() @@ -354,7 +379,7 @@ class PythonTracebackLexer(RegexLexer): """ For Python tracebacks. - *New in Pygments 0.7.* + .. versionadded:: 0.7 """ name = 'Python Traceback' @@ -364,7 +389,8 @@ class PythonTracebackLexer(RegexLexer): tokens = { 'root': [ - (r'^Traceback \(most recent call last\):\n', Generic.Traceback, 'intb'), + (r'^Traceback \(most recent call last\):\n', + Generic.Traceback, 'intb'), # SyntaxError starts with this. (r'^(?= File "[^"]+", line \d+)', Generic.Traceback, 'intb'), (r'^.*\n', Other), @@ -376,9 +402,9 @@ class PythonTracebackLexer(RegexLexer): bygroups(Text, Name.Builtin, Text, Number, Text)), (r'^( )(.+)(\n)', bygroups(Text, using(PythonLexer), Text)), - (r'^([ \t]*)(...)(\n)', + (r'^([ \t]*)(\.\.\.)(\n)', bygroups(Text, Comment, Text)), # for doctests... - (r'^(.+)(: )(.+)(\n)', + (r'^([^:]+)(: )(.+)(\n)', bygroups(Generic.Error, Text, Name, Text), '#pop'), (r'^([a-zA-Z_][a-zA-Z0-9_]*)(:?\n)', bygroups(Generic.Error, Text), '#pop') @@ -390,7 +416,7 @@ class Python3TracebackLexer(RegexLexer): """ For Python 3.0 tracebacks, with support for chained exceptions. - *New in Pygments 1.0.* + .. versionadded:: 1.0 """ name = 'Python 3.0 Traceback' @@ -406,15 +432,18 @@ class Python3TracebackLexer(RegexLexer): r'exception occurred:\n\n', Generic.Traceback), (r'^The above exception was the direct cause of the ' r'following exception:\n\n', Generic.Traceback), + (r'^(?= File "[^"]+", line \d+)', Generic.Traceback, 'intb'), ], 'intb': [ (r'^( File )("[^"]+")(, line )(\d+)(, in )(.+)(\n)', bygroups(Text, Name.Builtin, Text, Number, Text, Name, Text)), + (r'^( File )("[^"]+")(, line )(\d+)(\n)', + bygroups(Text, Name.Builtin, Text, Number, Text)), (r'^( )(.+)(\n)', bygroups(Text, using(Python3Lexer), Text)), - (r'^([ \t]*)(...)(\n)', + (r'^([ \t]*)(\.\.\.)(\n)', bygroups(Text, Comment, Text)), # for doctests... - (r'^(.+)(: )(.+)(\n)', + (r'^([^:]+)(: )(.+)(\n)', bygroups(Generic.Error, Text, Name, Text), '#pop'), (r'^([a-zA-Z_][a-zA-Z0-9_]*)(:?\n)', bygroups(Generic.Error, Text), '#pop') @@ -483,11 +512,11 @@ class RubyLexer(ExtendedRegexLexer): def gen_rubystrings_rules(): def intp_regex_callback(self, match, ctx): - yield match.start(1), String.Regex, match.group(1) # begin + yield match.start(1), String.Regex, match.group(1) # begin nctx = LexerContext(match.group(3), 0, ['interpolated-regex']) for i, t, v in self.get_tokens_unprocessed(context=nctx): yield match.start(3)+i, t, v - yield match.start(4), String.Regex, match.group(4) # end[mixounse]* + yield match.start(4), String.Regex, match.group(4) # end[mixounse]* ctx.pos = match.end() def intp_string_callback(self, match, ctx): @@ -495,17 +524,19 @@ class RubyLexer(ExtendedRegexLexer): nctx = LexerContext(match.group(3), 0, ['interpolated-string']) for i, t, v in self.get_tokens_unprocessed(context=nctx): yield match.start(3)+i, t, v - yield match.start(4), String.Other, match.group(4) # end + yield match.start(4), String.Other, match.group(4) # end ctx.pos = match.end() states = {} states['strings'] = [ # easy ones - (r'\:([a-zA-Z_][\w_]*[\!\?]?|\*\*?|[-+]@?|' + (r'\:@{0,2}([a-zA-Z_]\w*[\!\?]?|\*\*?|[-+]@?|' r'[/%&|^`~]|\[\]=?|<<|>>|<=?>|>=?|===?)', String.Symbol), (r":'(\\\\|\\'|[^'])*'", String.Symbol), (r"'(\\\\|\\'|[^'])*'", String.Single), (r':"', String.Symbol, 'simple-sym'), + (r'([a-zA-Z_][a-zA-Z0-9_]*)(:)(?!:)', + bygroups(String.Symbol, Punctuation)), # Since Ruby 1.9 (r'"', String.Double, 'simple-string'), (r'(?<!\.)`', String.Backtick, 'simple-backtick'), ] @@ -583,14 +614,15 @@ class RubyLexer(ExtendedRegexLexer): tokens = { 'root': [ (r'#.*?$', Comment.Single), - (r'=begin\s.*?\n=end', Comment.Multiline), + (r'=begin\s.*?\n=end.*?$', Comment.Multiline), # keywords (r'(BEGIN|END|alias|begin|break|case|defined\?|' r'do|else|elsif|end|ensure|for|if|in|next|redo|' r'rescue|raise|retry|return|super|then|undef|unless|until|when|' r'while|yield)\b', Keyword), # start of function, class and module names - (r'(module)(\s+)([a-zA-Z_][a-zA-Z0-9_]*(::[a-zA-Z_][a-zA-Z0-9_]*)*)', + (r'(module)(\s+)([a-zA-Z_][a-zA-Z0-9_]*' + r'(?:::[a-zA-Z_][a-zA-Z0-9_]*)*)', bygroups(Keyword, Text, Name.Namespace)), (r'(def)(\s+)', bygroups(Keyword, Text), 'funcname'), (r'def(?=[*%&^`~+-/\[<>=])', Keyword, 'funcname'), @@ -598,18 +630,19 @@ class RubyLexer(ExtendedRegexLexer): # special methods (r'(initialize|new|loop|include|extend|raise|attr_reader|' r'attr_writer|attr_accessor|attr|catch|throw|private|' - r'module_function|public|protected|true|false|nil)\b', Keyword.Pseudo), + r'module_function|public|protected|true|false|nil)\b', + Keyword.Pseudo), (r'(not|and|or)\b', Operator.Word), (r'(autoload|block_given|const_defined|eql|equal|frozen|include|' r'instance_of|is_a|iterator|kind_of|method_defined|nil|' r'private_method_defined|protected_method_defined|' r'public_method_defined|respond_to|tainted)\?', Name.Builtin), (r'(chomp|chop|exit|gsub|sub)!', Name.Builtin), - (r'(?<!\.)(Array|Float|Integer|String|__id__|__send__|abort|ancestors|' - r'at_exit|autoload|binding|callcc|caller|' + (r'(?<!\.)(Array|Float|Integer|String|__id__|__send__|abort|' + r'ancestors|at_exit|autoload|binding|callcc|caller|' r'catch|chomp|chop|class_eval|class_variables|' - r'clone|const_defined\?|const_get|const_missing|const_set|constants|' - r'display|dup|eval|exec|exit|extend|fail|fork|' + r'clone|const_defined\?|const_get|const_missing|const_set|' + r'constants|display|dup|eval|exec|exit|extend|fail|fork|' r'format|freeze|getc|gets|global_variables|gsub|' r'hash|id|included_modules|inspect|instance_eval|' r'instance_method|instance_methods|' @@ -628,12 +661,13 @@ class RubyLexer(ExtendedRegexLexer): r'warn)\b', Name.Builtin), (r'__(FILE|LINE)__\b', Name.Builtin.Pseudo), # normal heredocs - (r'(?<!\w)(<<-?)(["`\']?)([a-zA-Z_]\w*)(\2)(.*?\n)', heredoc_callback), + (r'(?<!\w)(<<-?)(["`\']?)([a-zA-Z_]\w*)(\2)(.*?\n)', + heredoc_callback), # empty string heredocs (r'(<<-?)("|\')()(\2)(.*?\n)', heredoc_callback), (r'__END__', Comment.Preproc, 'end-part'), # multiline regex (after keywords or assignments) - (r'(?:^|(?<=[=<>~!])|' + (r'(?:^|(?<=[=<>~!:])|' r'(?<=(?:\s|;)when\s)|' r'(?<=(?:\s|;)or\s)|' r'(?<=(?:\s|;)and\s)|' @@ -657,10 +691,11 @@ class RubyLexer(ExtendedRegexLexer): r'(?<=^if\s)|' r'(?<=^elsif\s)' r')(\s*)(/)', bygroups(Text, String.Regex), 'multiline-regex'), - # multiline regex (in method calls) - (r'(?<=\(|,)/', String.Regex, 'multiline-regex'), + # multiline regex (in method calls or subscripts) + (r'(?<=\(|,|\[)/', String.Regex, 'multiline-regex'), # multiline regex (this time the funny no whitespace rule) - (r'(\s+)(/[^\s=])', String.Regex, 'multiline-regex'), + (r'(\s+)(/)(?![\s=])', bygroups(Text, String.Regex), + 'multiline-regex'), # lex numbers and ignore following regular expressions which # are division operators in fact (grrrr. i hate that. any # better ideas?) @@ -695,7 +730,7 @@ class RubyLexer(ExtendedRegexLexer): # like keywords (class) or like this: ` ?!? (r'(\.|::)([a-zA-Z_]\w*[\!\?]?|[*%&^`~+-/\[<>=])', bygroups(Operator, Name)), - (r'[a-zA-Z_][\w_]*[\!\?]?', Name), + (r'[a-zA-Z_]\w*[\!\?]?', Name), (r'(\[|\]|\*\*|<<?|>>?|>=|<=|<=>|=~|={3}|' r'!~|&&?|\|\||\.{1,3})', Operator), (r'[-+/*%=<>&!^|~]=?', Operator), @@ -705,7 +740,7 @@ class RubyLexer(ExtendedRegexLexer): 'funcname': [ (r'\(', Punctuation, 'defexpr'), (r'(?:([a-zA-Z_][a-zA-Z0-9_]*)(\.))?' - r'([a-zA-Z_][\w_]*[\!\?]?|\*\*?|[-+]@?|' + r'([a-zA-Z_]\w*[\!\?]?|\*\*?|[-+]@?|' r'[/%&|^`~]|\[\]=?|<<|>>|<=?>|>=?|===?)', bygroups(Name.Class, Operator, Name.Function), '#pop'), (r'', Text, '#pop') @@ -713,7 +748,7 @@ class RubyLexer(ExtendedRegexLexer): 'classname': [ (r'\(', Punctuation, 'defexpr'), (r'<<', Operator, '#pop'), - (r'[A-Z_][\w_]*', Name.Class, '#pop'), + (r'[A-Z_]\w*', Name.Class, '#pop'), (r'', Text, '#pop') ], 'defexpr': [ @@ -732,7 +767,8 @@ class RubyLexer(ExtendedRegexLexer): ], 'string-intp-escaped': [ include('string-intp'), - (r'\\([\\abefnrstv#"\']|x[a-fA-F0-9]{1,2}|[0-7]{1,3})', String.Escape) + (r'\\([\\abefnrstv#"\']|x[a-fA-F0-9]{1,2}|[0-7]{1,3})', + String.Escape) ], 'interpolated-regex': [ include('string-intp'), @@ -815,23 +851,23 @@ class PerlLexer(RegexLexer): name = 'Perl' aliases = ['perl', 'pl'] - filenames = ['*.pl', '*.pm'] + filenames = ['*.pl', '*.pm', '*.t'] mimetypes = ['text/x-perl', 'application/x-perl'] flags = re.DOTALL | re.MULTILINE - # TODO: give this a perl guy who knows how to parse perl... + # 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'), - (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'\#.*?$', Comment.Single), @@ -843,20 +879,26 @@ class PerlLexer(RegexLexer): 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), - (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'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*/(\\\\|\\[^\\]|[^\\/])*/[gcimosx]*', + String.Regex), (r'\s+', Text), (r'(abs|accept|alarm|atan2|bind|binmode|bless|caller|chdir|' r'chmod|chomp|chop|chown|chr|chroot|close|closedir|connect|' @@ -898,9 +940,9 @@ class PerlLexer(RegexLexer): Number.Float), (r'(?i)\d+(_\d*)*e[+-]?\d+(_\d*)*', Number.Float), (r'\d+(_\d+)*', Number.Integer), - (r"'(\\\\|\\'|[^'])*'", String), - (r'"(\\\\|\\"|[^"])*"', String), - (r'`(\\\\|\\`|[^`])*`', String.Backtick), + (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'), @@ -909,7 +951,7 @@ class PerlLexer(RegexLexer): (r'(q|qq|qw|qr|qx)([^a-zA-Z0-9])(.|\n)*?\2', String.Other), (r'package\s+', Keyword, 'modulename'), (r'sub\s+', Keyword, 'funcname'), - (r'(\[\]|\*\*|::|<<|>>|>=|<=|<=>|={3}|!=|=~|' + (r'(\[\]|\*\*|::|<<|>>|>=|<=>|<=|={3}|!=|=~|' r'!~|&&?|\|\||\.{1,3})', Operator), (r'[-+/*%=<>&^|!\\~]=?', Operator), (r'[\(\)\[\]:;,<>/\?\{\}]', Punctuation), # yes, there's no shortage @@ -934,10 +976,10 @@ class PerlLexer(RegexLexer): (r'(?=[^a-zA-Z0-9_])', Text, '#pop'), ], 'modulename': [ - (r'[a-zA-Z_][\w_]*', Name.Namespace, '#pop') + (r'[a-zA-Z_]\w*', Name.Namespace, '#pop') ], 'funcname': [ - (r'[a-zA-Z_][\w_]*[\!\?]?', Name.Function), + (r'[a-zA-Z_]\w*[\!\?]?', Name.Function), (r'\s+', Text), # argument declaration (r'(\([$@%]*\))(\s*)', bygroups(Punctuation, Text)), @@ -980,9 +1022,8 @@ class PerlLexer(RegexLexer): def analyse_text(text): if shebang_matches(text, r'perl'): return True - if 'my $' in text: + if re.search('(?:my|our)\s+[$@%(]', text): return 0.9 - return 0.1 # who knows, might still be perl! class LuaLexer(RegexLexer): @@ -1033,7 +1074,7 @@ class LuaLexer(RegexLexer): # multiline strings (r'(?s)\[(=*)\[.*?\]\1\]', String), - (r'(==|~=|<=|>=|\.\.|\.\.\.|[=+\-*/%^<>#])', Operator), + (r'(==|~=|<=|>=|\.\.\.|\.\.|[=+\-*/%^<>#])', Operator), (r'[\[\]\{\}\(\)\.,:;]', Punctuation), (r'(and|or|not)\b', Operator.Word), @@ -1042,8 +1083,7 @@ class LuaLexer(RegexLexer): (r'(local)\b', Keyword.Declaration), (r'(true|false|nil)\b', Keyword.Constant), - (r'(function)(\s+)', bygroups(Keyword, Text), 'funcname'), - (r'(class)(\s+)', bygroups(Keyword, Text), 'classname'), + (r'(function)\b', Keyword, 'funcname'), (r'[A-Za-z_][A-Za-z0-9_]*(\.[A-Za-z_][A-Za-z0-9_]*)?', Name), @@ -1052,16 +1092,13 @@ class LuaLexer(RegexLexer): ], 'funcname': [ + (r'\s+', Text), ('(?:([A-Za-z_][A-Za-z0-9_]*)(\.))?([A-Za-z_][A-Za-z0-9_]*)', bygroups(Name.Class, Punctuation, Name.Function), '#pop'), # inline function ('\(', Punctuation, '#pop'), ], - 'classname': [ - ('[A-Za-z_][A-Za-z0-9_]*', Name.Class, '#pop') - ], - # if I understand correctly, every character is valid in a lua string, # so this state is only for later corrections 'string': [ @@ -1091,7 +1128,7 @@ class LuaLexer(RegexLexer): self._functions = set() if self.func_name_highlighting: from pygments.lexers._luabuiltins import MODULES - for mod, func in MODULES.iteritems(): + for mod, func in iteritems(MODULES): if mod not in self.disabled_modules: self._functions.update(func) RegexLexer.__init__(self, **options) @@ -1112,15 +1149,80 @@ class LuaLexer(RegexLexer): yield index, token, value -class MiniDLexer(RegexLexer): +class MoonScriptLexer(LuaLexer): """ - For `MiniD <http://www.dsource.org/projects/minid>`_ (a D-like scripting - language) source. + For `MoonScript <http://moonscript.org.org>`_ source code. + + .. versionadded:: 1.5 """ - name = 'MiniD' - filenames = ['*.md'] - aliases = ['minid'] - mimetypes = ['text/x-minidsrc'] + + name = "MoonScript" + aliases = ["moon", "moonscript"] + filenames = ["*.moon"] + mimetypes = ['text/x-moonscript', 'application/x-moonscript'] + + tokens = { + 'root': [ + (r'#!(.*?)$', Comment.Preproc), + (r'', Text, 'base'), + ], + 'base': [ + ('--.*$', Comment.Single), + (r'(?i)(\d*\.\d+|\d+\.\d*)(e[+-]?\d+)?', Number.Float), + (r'(?i)\d+e[+-]?\d+', Number.Float), + (r'(?i)0x[0-9a-f]*', Number.Hex), + (r'\d+', Number.Integer), + (r'\n', Text), + (r'[^\S\n]+', Text), + (r'(?s)\[(=*)\[.*?\]\1\]', String), + (r'(->|=>)', Name.Function), + (r':[a-zA-Z_][a-zA-Z0-9_]*', Name.Variable), + (r'(==|!=|~=|<=|>=|\.\.\.|\.\.|[=+\-*/%^<>#!.\\:])', Operator), + (r'[;,]', Punctuation), + (r'[\[\]\{\}\(\)]', Keyword.Type), + (r'[a-zA-Z_][a-zA-Z0-9_]*:', Name.Variable), + (r"(class|extends|if|then|super|do|with|import|export|" + r"while|elseif|return|for|in|from|when|using|else|" + r"and|or|not|switch|break)\b", Keyword), + (r'(true|false|nil)\b', Keyword.Constant), + (r'(and|or|not)\b', Operator.Word), + (r'(self)\b', Name.Builtin.Pseudo), + (r'@@?([a-zA-Z_][a-zA-Z0-9_]*)?', Name.Variable.Class), + (r'[A-Z]\w*', Name.Class), # proper name + (r'[A-Za-z_][A-Za-z0-9_]*(\.[A-Za-z_][A-Za-z0-9_]*)?', Name), + ("'", String.Single, combined('stringescape', 'sqs')), + ('"', String.Double, combined('stringescape', 'dqs')) + ], + 'stringescape': [ + (r'''\\([abfnrtv\\"']|\d{1,3})''', String.Escape) + ], + 'sqs': [ + ("'", String.Single, '#pop'), + (".", String) + ], + 'dqs': [ + ('"', String.Double, '#pop'), + (".", String) + ] + } + + def get_tokens_unprocessed(self, text): + # set . as Operator instead of Punctuation + for index, token, value in \ + LuaLexer.get_tokens_unprocessed(self, text): + if token == Punctuation and value == ".": + token = Operator + yield index, token, value + + +class CrocLexer(RegexLexer): + """ + For `Croc <http://jfbillingsley.com/croc>`_ source. + """ + name = 'Croc' + filenames = ['*.croc'] + aliases = ['croc'] + mimetypes = ['text/x-crocsrc'] tokens = { 'root': [ @@ -1128,35 +1230,33 @@ class MiniDLexer(RegexLexer): (r'\s+', Text), # Comments (r'//(.*?)\n', Comment.Single), - (r'/(\\\n)?[*](.|\n)*?[*](\\\n)?/', Comment.Multiline), - (r'/\+', Comment.Multiline, 'nestedcomment'), + (r'/\*', Comment.Multiline, 'nestedcomment'), # Keywords - (r'(as|assert|break|case|catch|class|continue|coroutine|default' + (r'(as|assert|break|case|catch|class|continue|default' r'|do|else|finally|for|foreach|function|global|namespace' - r'|if|import|in|is|local|module|return|super|switch' + r'|if|import|in|is|local|module|return|scope|super|switch' r'|this|throw|try|vararg|while|with|yield)\b', Keyword), (r'(false|true|null)\b', Keyword.Constant), # FloatLiteral - (r'([0-9][0-9_]*)?\.[0-9_]+([eE][+\-]?[0-9_]+)?', Number.Float), + (r'([0-9][0-9_]*)(?=[.eE])(\.[0-9][0-9_]*)?([eE][+\-]?[0-9_]+)?', + Number.Float), # IntegerLiteral # -- Binary - (r'0[Bb][01_]+', Number), - # -- Octal - (r'0[Cc][0-7_]+', Number.Oct), + (r'0[bB][01][01_]*', Number), # -- Hexadecimal - (r'0[xX][0-9a-fA-F_]+', Number.Hex), + (r'0[xX][0-9a-fA-F][0-9a-fA-F_]*', Number.Hex), # -- Decimal - (r'(0|[1-9][0-9_]*)', Number.Integer), + (r'([0-9][0-9_]*)(?![.eE])', Number.Integer), # CharacterLiteral - (r"""'(\\['"?\\abfnrtv]|\\x[0-9a-fA-F]{2}|\\[0-9]{1,3}""" + (r"""'(\\['"\\nrt]|\\x[0-9a-fA-F]{2}|\\[0-9]{1,3}""" r"""|\\u[0-9a-fA-F]{4}|\\U[0-9a-fA-F]{8}|.)'""", String.Char ), # StringLiteral # -- WysiwygString - (r'@"(""|.)*"', String), - # -- AlternateWysiwygString - (r'`(``|.)*`', String), + (r'@"(""|[^"])*"', String), + (r'@`(``|[^`])*`', String), + (r"@'(''|[^'])*'", String), # -- DoubleQuotedString (r'"(\\\\|\\"|[^"])*"', String), # Tokens @@ -1169,20 +1269,30 @@ class MiniDLexer(RegexLexer): (r'[a-zA-Z_]\w*', Name), ], 'nestedcomment': [ - (r'[^+/]+', Comment.Multiline), - (r'/\+', Comment.Multiline, '#push'), - (r'\+/', Comment.Multiline, '#pop'), - (r'[+/]', Comment.Multiline), + (r'[^*/]+', Comment.Multiline), + (r'/\*', Comment.Multiline, '#push'), + (r'\*/', Comment.Multiline, '#pop'), + (r'[*/]', Comment.Multiline), ], } +class MiniDLexer(CrocLexer): + """ + For MiniD source. MiniD is now known as Croc. + """ + name = 'MiniD' + filenames = ['*.md'] + aliases = ['minid'] + mimetypes = ['text/x-minidsrc'] + + class IoLexer(RegexLexer): """ For `Io <http://iolanguage.com/>`_ (a small, prototype-based programming language) source. - *New in Pygments 0.10.* + .. versionadded:: 0.10 """ name = 'Io' filenames = ['*.io'] @@ -1208,7 +1318,7 @@ class IoLexer(RegexLexer): # constants (r'(nil|false|true)\b', Name.Constant), # names - ('(Object|list|List|Map|args|Sequence|Coroutine|File)\b', + (r'(Object|list|List|Map|args|Sequence|Coroutine|File)\b', Name.Builtin), ('[a-zA-Z_][a-zA-Z0-9_]*', Name), # numbers @@ -1228,7 +1338,7 @@ class TclLexer(RegexLexer): """ For Tcl source code. - *New in Pygments 0.10.* + .. versionadded:: 0.10 """ keyword_cmds_re = ( @@ -1300,7 +1410,7 @@ class TclLexer(RegexLexer): 'params': [ (r';', Keyword, '#pop'), (r'\n', Text, '#pop'), - (r'(else|elseif|then)', Keyword), + (r'(else|elseif|then)\b', Keyword), include('basic'), include('data'), ], @@ -1354,146 +1464,11 @@ class TclLexer(RegexLexer): return shebang_matches(text, r'(tcl)') -class ClojureLexer(RegexLexer): - """ - Lexer for `Clojure <http://clojure.org/>`_ source code. - - *New in Pygments 0.11.* - """ - name = 'Clojure' - aliases = ['clojure', 'clj'] - filenames = ['*.clj'] - mimetypes = ['text/x-clojure', 'application/x-clojure'] - - keywords = [ - 'fn', 'def', 'defn', 'defmacro', 'defmethod', 'defmulti', 'defn-', - 'defstruct', - 'if', 'cond', - 'let', 'for' - ] - builtins = [ - '.', '..', - '*', '+', '-', '->', '..', '/', '<', '<=', '=', '==', '>', '>=', - 'accessor', 'agent', 'agent-errors', 'aget', 'alength', 'all-ns', - 'alter', 'and', 'append-child', 'apply', 'array-map', 'aset', - 'aset-boolean', 'aset-byte', 'aset-char', 'aset-double', 'aset-float', - 'aset-int', 'aset-long', 'aset-short', 'assert', 'assoc', 'await', - 'await-for', 'bean', 'binding', 'bit-and', 'bit-not', 'bit-or', - 'bit-shift-left', 'bit-shift-right', 'bit-xor', 'boolean', 'branch?', - 'butlast', 'byte', 'cast', 'char', 'children', 'class', - 'clear-agent-errors', 'comment', 'commute', 'comp', 'comparator', - 'complement', 'concat', 'conj', 'cons', 'constantly', - 'construct-proxy', 'contains?', 'count', 'create-ns', 'create-struct', - 'cycle', 'dec', 'deref', 'difference', 'disj', 'dissoc', 'distinct', - 'doall', 'doc', 'dorun', 'doseq', 'dosync', 'dotimes', 'doto', - 'double', 'down', 'drop', 'drop-while', 'edit', 'end?', 'ensure', - 'eval', 'every?', 'false?', 'ffirst', 'file-seq', 'filter', 'find', - 'find-doc', 'find-ns', 'find-var', 'first', 'float', 'flush', - 'fnseq', 'frest', 'gensym', 'get', 'get-proxy-class', - 'hash-map', 'hash-set', 'identical?', 'identity', 'if-let', 'import', - 'in-ns', 'inc', 'index', 'insert-child', 'insert-left', 'insert-right', - 'inspect-table', 'inspect-tree', 'instance?', 'int', 'interleave', - 'intersection', 'into', 'into-array', 'iterate', 'join', 'key', 'keys', - 'keyword', 'keyword?', 'last', 'lazy-cat', 'lazy-cons', 'left', - 'lefts', 'line-seq', 'list', 'list*', 'load', 'load-file', - 'locking', 'long', 'loop', 'macroexpand', 'macroexpand-1', - 'make-array', 'make-node', 'map', 'map-invert', 'map?', 'mapcat', - 'max', 'max-key', 'memfn', 'merge', 'merge-with', 'meta', 'min', - 'min-key', 'name', 'namespace', 'neg?', 'new', 'newline', 'next', - 'nil?', 'node', 'not', 'not-any?', 'not-every?', 'not=', 'ns-imports', - 'ns-interns', 'ns-map', 'ns-name', 'ns-publics', 'ns-refers', - 'ns-resolve', 'ns-unmap', 'nth', 'nthrest', 'or', 'parse', 'partial', - 'path', 'peek', 'pop', 'pos?', 'pr', 'pr-str', 'print', 'print-str', - 'println', 'println-str', 'prn', 'prn-str', 'project', 'proxy', - 'proxy-mappings', 'quot', 'rand', 'rand-int', 'range', 're-find', - 're-groups', 're-matcher', 're-matches', 're-pattern', 're-seq', - 'read', 'read-line', 'reduce', 'ref', 'ref-set', 'refer', 'rem', - 'remove', 'remove-method', 'remove-ns', 'rename', 'rename-keys', - 'repeat', 'replace', 'replicate', 'resolve', 'rest', 'resultset-seq', - 'reverse', 'rfirst', 'right', 'rights', 'root', 'rrest', 'rseq', - 'second', 'select', 'select-keys', 'send', 'send-off', 'seq', - 'seq-zip', 'seq?', 'set', 'short', 'slurp', 'some', 'sort', - 'sort-by', 'sorted-map', 'sorted-map-by', 'sorted-set', - 'special-symbol?', 'split-at', 'split-with', 'str', 'string?', - 'struct', 'struct-map', 'subs', 'subvec', 'symbol', 'symbol?', - 'sync', 'take', 'take-nth', 'take-while', 'test', 'time', 'to-array', - 'to-array-2d', 'tree-seq', 'true?', 'union', 'up', 'update-proxy', - 'val', 'vals', 'var-get', 'var-set', 'var?', 'vector', 'vector-zip', - 'vector?', 'when', 'when-first', 'when-let', 'when-not', - 'with-local-vars', 'with-meta', 'with-open', 'with-out-str', - 'xml-seq', 'xml-zip', 'zero?', 'zipmap', 'zipper'] - - # valid names for identifiers - # well, names can only not consist fully of numbers - # but this should be good enough for now - valid_name = r'[a-zA-Z0-9!$%&*+,/:<=>?@^_~-]+' - - tokens = { - 'root' : [ - # the comments - always starting with semicolon - # and going to the end of the line - (r';.*$', Comment.Single), - - # whitespaces - usually not relevant - (r'\s+', Text), - - # numbers - (r'-?\d+\.\d+', Number.Float), - (r'-?\d+', Number.Integer), - # support for uncommon kinds of numbers - - # have to figure out what the characters mean - #(r'(#e|#i|#b|#o|#d|#x)[\d.]+', Number), - - # strings, symbols and characters - (r'"(\\\\|\\"|[^"])*"', String), - (r"'" + valid_name, String.Symbol), - (r"\\([()/'\".'_!§$%& ?;=#+-]{1}|[a-zA-Z0-9]+)", String.Char), - - # constants - (r'(#t|#f)', Name.Constant), - - # special operators - (r"('|#|`|,@|,|\.)", Operator), - - # highlight the keywords - ('(%s)' % '|'.join([ - re.escape(entry) + ' ' for entry in keywords]), - Keyword - ), - - # first variable in a quoted string like - # '(this is syntactic sugar) - (r"(?<='\()" + valid_name, Name.Variable), - (r"(?<=#\()" + valid_name, Name.Variable), - - # highlight the builtins - ("(?<=\()(%s)" % '|'.join([ - re.escape(entry) + ' ' for entry in builtins]), - Name.Builtin - ), - - # the remaining functions - (r'(?<=\()' + valid_name, Name.Function), - # find the remaining variables - (valid_name, Name.Variable), - - # Clojure accepts vector notation - (r'(\[|\])', Punctuation), - - # Clojure accepts map notation - (r'(\{|\})', Punctuation), - - # the famous parentheses! - (r'(\(|\))', Punctuation), - ], - } - - class FactorLexer(RegexLexer): """ Lexer for the `Factor <http://factorcode.org>`_ language. - *New in Pygments 1.4.* + .. versionadded:: 1.4 """ name = 'Factor' aliases = ['factor'] @@ -1503,229 +1478,276 @@ class FactorLexer(RegexLexer): flags = re.MULTILINE | re.UNICODE builtin_kernel = ( - r'(?:or|2bi|2tri|while|wrapper|nip|4dip|wrapper\\?|bi\\*|' - r'callstack>array|both\\?|hashcode|die|dupd|callstack|' - r'callstack\\?|3dup|tri@|pick|curry|build|\\?execute|3bi|' - r'prepose|>boolean|\\?if|clone|eq\\?|tri\\*|\\?|=|swapd|' - r'2over|2keep|3keep|clear|2dup|when|not|tuple\\?|dup|2bi\\*|' - r'2tri\\*|call|tri-curry|object|bi@|do|unless\\*|if\\*|loop|' - r'bi-curry\\*|drop|when\\*|assert=|retainstack|assert\\?|-rot|' - r'execute|2bi@|2tri@|boa|with|either\\?|3drop|bi|curry\\?|' - r'datastack|until|3dip|over|3curry|tri-curry\\*|tri-curry@|swap|' - r'and|2nip|throw|bi-curry|\\(clone\\)|hashcode\\*|compose|2dip|if|3tri|' - r'unless|compose\\?|tuple|keep|2curry|equal\\?|assert|tri|2drop|' - r'most|<wrapper>|boolean\\?|identity-hashcode|identity-tuple\\?|' - r'null|new|dip|bi-curry@|rot|xor|identity-tuple|boolean)\s' - ) + r'(?:-rot|2bi|2bi@|2bi\*|2curry|2dip|2drop|2dup|2keep|2nip|' + r'2over|2tri|2tri@|2tri\*|3bi|3curry|3dip|3drop|3dup|3keep|' + r'3tri|4dip|4drop|4dup|4keep|<wrapper>|=|>boolean|\(clone\)|' + r'\?|\?execute|\?if|and|assert|assert=|assert\?|bi|bi-curry|' + r'bi-curry@|bi-curry\*|bi@|bi\*|boa|boolean|boolean\?|both\?|' + r'build|call|callstack|callstack>array|callstack\?|clear|clone|' + r'compose|compose\?|curry|curry\?|datastack|die|dip|do|drop|' + r'dup|dupd|either\?|eq\?|equal\?|execute|hashcode|hashcode\*|' + r'identity-hashcode|identity-tuple|identity-tuple\?|if|if\*|' + r'keep|loop|most|new|nip|not|null|object|or|over|pick|prepose|' + r'retainstack|rot|same\?|swap|swapd|throw|tri|tri-curry|' + r'tri-curry@|tri-curry\*|tri@|tri\*|tuple|tuple\?|unless|' + r'unless\*|until|when|when\*|while|with|wrapper|wrapper\?|xor)\s' + ) builtin_assocs = ( - r'(?:\\?at|assoc\\?|assoc-clone-like|assoc=|delete-at\\*|' - r'assoc-partition|extract-keys|new-assoc|value\\?|assoc-size|' - r'map>assoc|push-at|assoc-like|key\\?|assoc-intersect|' - r'assoc-refine|update|assoc-union|assoc-combine|at\\*|' - r'assoc-empty\\?|at\\+|set-at|assoc-all\\?|assoc-subset\\?|' - r'assoc-hashcode|change-at|assoc-each|assoc-diff|zip|values|' - r'value-at|rename-at|inc-at|enum\\?|at|cache|assoc>map|<enum>|' - r'assoc|assoc-map|enum|value-at\\*|assoc-map-as|>alist|' - r'assoc-filter-as|clear-assoc|assoc-stack|maybe-set-at|' - r'substitute|assoc-filter|2cache|delete-at|assoc-find|keys|' - r'assoc-any\\?|unzip)\s' - ) + r'(?:2cache|<enum>|>alist|\?at|\?of|assoc|assoc-all\?|' + r'assoc-any\?|assoc-clone-like|assoc-combine|assoc-diff|' + r'assoc-diff!|assoc-differ|assoc-each|assoc-empty\?|' + r'assoc-filter|assoc-filter!|assoc-filter-as|assoc-find|' + r'assoc-hashcode|assoc-intersect|assoc-like|assoc-map|' + r'assoc-map-as|assoc-partition|assoc-refine|assoc-size|' + r'assoc-stack|assoc-subset\?|assoc-union|assoc-union!|' + r'assoc=|assoc>map|assoc\?|at|at+|at\*|cache|change-at|' + r'clear-assoc|delete-at|delete-at\*|enum|enum\?|extract-keys|' + r'inc-at|key\?|keys|map>assoc|maybe-set-at|new-assoc|of|' + r'push-at|rename-at|set-at|sift-keys|sift-values|substitute|' + r'unzip|value-at|value-at\*|value\?|values|zip)\s' + ) builtin_combinators = ( - r'(?:case|execute-effect|no-cond|no-case\\?|3cleave>quot|2cleave|' - r'cond>quot|wrong-values\\?|no-cond\\?|cleave>quot|no-case|' - r'case>quot|3cleave|wrong-values|to-fixed-point|alist>quot|' - r'case-find|cond|cleave|call-effect|2cleave>quot|recursive-hashcode|' - r'linear-case-quot|spread|spread>quot)\s' - ) + r'(?:2cleave|2cleave>quot|3cleave|3cleave>quot|4cleave|' + r'4cleave>quot|alist>quot|call-effect|case|case-find|' + r'case>quot|cleave|cleave>quot|cond|cond>quot|deep-spread>quot|' + r'execute-effect|linear-case-quot|no-case|no-case\?|no-cond|' + r'no-cond\?|recursive-hashcode|shallow-spread>quot|spread|' + r'to-fixed-point|wrong-values|wrong-values\?)\s' + ) builtin_math = ( - r'(?:number=|if-zero|next-power-of-2|each-integer|\\?1\\+|' - r'fp-special\\?|imaginary-part|unless-zero|float>bits|number\\?|' - r'fp-infinity\\?|bignum\\?|fp-snan\\?|denominator|fp-bitwise=|\\*|' - r'\\+|power-of-2\\?|-|u>=|/|>=|bitand|log2-expects-positive|<|' - r'log2|>|integer\\?|number|bits>double|2/|zero\\?|(find-integer)|' - r'bits>float|float\\?|shift|ratio\\?|even\\?|ratio|fp-sign|bitnot|' - r'>fixnum|complex\\?|/i|/f|byte-array>bignum|when-zero|sgn|>bignum|' - r'next-float|u<|u>|mod|recip|rational|find-last-integer|>float|' - r'(all-integers\\?)|2^|times|integer|fixnum\\?|neg|fixnum|sq|' - r'bignum|(each-integer)|bit\\?|fp-qnan\\?|find-integer|complex|' - r'<fp-nan>|real|double>bits|bitor|rem|fp-nan-payload|all-integers\\?|' - r'real-part|log2-expects-positive\\?|prev-float|align|unordered\\?|' - r'float|fp-nan\\?|abs|bitxor|u<=|odd\\?|<=|/mod|rational\\?|>integer|' - r'real\\?|numerator)\s' - ) + r'(?:-|/|/f|/i|/mod|2/|2\^|<|<=|<fp-nan>|>|>=|>bignum|' + r'>fixnum|>float|>integer|\(all-integers\?\)|' + r'\(each-integer\)|\(find-integer\)|\*|\+|\?1\+|' + r'abs|align|all-integers\?|bignum|bignum\?|bit\?|bitand|' + r'bitnot|bitor|bits>double|bits>float|bitxor|complex|' + r'complex\?|denominator|double>bits|each-integer|even\?|' + r'find-integer|find-last-integer|fixnum|fixnum\?|float|' + r'float>bits|float\?|fp-bitwise=|fp-infinity\?|fp-nan-payload|' + r'fp-nan\?|fp-qnan\?|fp-sign|fp-snan\?|fp-special\?|' + r'if-zero|imaginary-part|integer|integer>fixnum|' + r'integer>fixnum-strict|integer\?|log2|log2-expects-positive|' + r'log2-expects-positive\?|mod|neg|neg\?|next-float|' + r'next-power-of-2|number|number=|number\?|numerator|odd\?|' + r'out-of-fixnum-range|out-of-fixnum-range\?|power-of-2\?|' + r'prev-float|ratio|ratio\?|rational|rational\?|real|' + r'real-part|real\?|recip|rem|sgn|shift|sq|times|u<|u<=|u>|' + r'u>=|unless-zero|unordered\?|when-zero|zero\?)\s' + ) builtin_sequences = ( - r'(?:member-eq\\?|append|assert-sequence=|find-last-from|trim-head-slice|' - r'clone-like|3sequence|assert-sequence\\?|map-as|last-index-from|' - r'reversed|index-from|cut\\*|pad-tail|remove-eq!|concat-as|' - r'but-last|snip|trim-tail|nths|nth|2selector|sequence|slice\\?|' - r'<slice>|partition|remove-nth|tail-slice|empty\\?|tail\\*|' - r'if-empty|find-from|virtual-sequence\\?|member\\?|set-length|' - r'drop-prefix|unclip|unclip-last-slice|iota|map-sum|' - r'bounds-error\\?|sequence-hashcode-step|selector-for|' - r'accumulate-as|map|start|midpoint@|\\(accumulate\\)|rest-slice|' - r'prepend|fourth|sift|accumulate!|new-sequence|follow|map!|' - r'like|first4|1sequence|reverse|slice|unless-empty|padding|' - r'virtual@|repetition\\?|set-last|index|4sequence|max-length|' - r'set-second|immutable-sequence|first2|first3|replicate-as|' - r'reduce-index|unclip-slice|supremum|suffix!|insert-nth|' - r'trim-tail-slice|tail|3append|short|count|suffix|concat|' - r'flip|filter|sum|immutable\\?|reverse!|2sequence|map-integers|' - r'delete-all|start\\*|indices|snip-slice|check-slice|sequence\\?|' - r'head|map-find|filter!|append-as|reduce|sequence=|halves|' - r'collapse-slice|interleave|2map|filter-as|binary-reduce|' - r'slice-error\\?|product|bounds-check\\?|bounds-check|harvest|' - r'immutable|virtual-exemplar|find|produce|remove|pad-head|last|' - r'replicate|set-fourth|remove-eq|shorten|reversed\\?|' - r'map-find-last|3map-as|2unclip-slice|shorter\\?|3map|find-last|' - r'head-slice|pop\\*|2map-as|tail-slice\\*|but-last-slice|' - r'2map-reduce|iota\\?|collector-for|accumulate|each|selector|' - r'append!|new-resizable|cut-slice|each-index|head-slice\\*|' - r'2reverse-each|sequence-hashcode|pop|set-nth|\\?nth|' - r'<flat-slice>|second|join|when-empty|collector|' - r'immutable-sequence\\?|<reversed>|all\\?|3append-as|' - r'virtual-sequence|subseq\\?|remove-nth!|push-either|new-like|' - r'length|last-index|push-if|2all\\?|lengthen|assert-sequence|' - r'copy|map-reduce|move|third|first|3each|tail\\?|set-first|' - r'prefix|bounds-error|any\\?|<repetition>|trim-slice|exchange|' - r'surround|2reduce|cut|change-nth|min-length|set-third|produce-as|' - r'push-all|head\\?|delete-slice|rest|sum-lengths|2each|head\\*|' - r'infimum|remove!|glue|slice-error|subseq|trim|replace-slice|' - r'push|repetition|map-index|trim-head|unclip-last|mismatch)\s' - ) + r'(?:1sequence|2all\?|2each|2map|2map-as|2map-reduce|2reduce|' + r'2selector|2sequence|3append|3append-as|3each|3map|3map-as|' + r'3sequence|4sequence|<repetition>|<reversed>|<slice>|\?first|' + r'\?last|\?nth|\?second|\?set-nth|accumulate|accumulate!|' + r'accumulate-as|all\?|any\?|append|append!|append-as|' + r'assert-sequence|assert-sequence=|assert-sequence\?|' + r'binary-reduce|bounds-check|bounds-check\?|bounds-error|' + r'bounds-error\?|but-last|but-last-slice|cartesian-each|' + r'cartesian-map|cartesian-product|change-nth|check-slice|' + r'check-slice-error|clone-like|collapse-slice|collector|' + r'collector-for|concat|concat-as|copy|count|cut|cut-slice|' + r'cut\*|delete-all|delete-slice|drop-prefix|each|each-from|' + r'each-index|empty\?|exchange|filter|filter!|filter-as|find|' + r'find-from|find-index|find-index-from|find-last|find-last-from|' + r'first|first2|first3|first4|flip|follow|fourth|glue|halves|' + r'harvest|head|head-slice|head-slice\*|head\*|head\?|' + r'if-empty|immutable|immutable-sequence|immutable-sequence\?|' + r'immutable\?|index|index-from|indices|infimum|infimum-by|' + r'insert-nth|interleave|iota|iota-tuple|iota-tuple\?|join|' + r'join-as|last|last-index|last-index-from|length|lengthen|' + r'like|longer|longer\?|longest|map|map!|map-as|map-find|' + r'map-find-last|map-index|map-integers|map-reduce|map-sum|' + r'max-length|member-eq\?|member\?|midpoint@|min-length|' + r'mismatch|move|new-like|new-resizable|new-sequence|' + r'non-negative-integer-expected|non-negative-integer-expected\?|' + r'nth|nths|pad-head|pad-tail|padding|partition|pop|pop\*|' + r'prefix|prepend|prepend-as|produce|produce-as|product|push|' + r'push-all|push-either|push-if|reduce|reduce-index|remove|' + r'remove!|remove-eq|remove-eq!|remove-nth|remove-nth!|repetition|' + r'repetition\?|replace-slice|replicate|replicate-as|rest|' + r'rest-slice|reverse|reverse!|reversed|reversed\?|second|' + r'selector|selector-for|sequence|sequence-hashcode|sequence=|' + r'sequence\?|set-first|set-fourth|set-last|set-length|set-nth|' + r'set-second|set-third|short|shorten|shorter|shorter\?|' + r'shortest|sift|slice|slice-error|slice-error\?|slice\?|' + r'snip|snip-slice|start|start\*|subseq|subseq\?|suffix|' + r'suffix!|sum|sum-lengths|supremum|supremum-by|surround|tail|' + r'tail-slice|tail-slice\*|tail\*|tail\?|third|trim|' + r'trim-head|trim-head-slice|trim-slice|trim-tail|trim-tail-slice|' + r'unclip|unclip-last|unclip-last-slice|unclip-slice|unless-empty|' + r'virtual-exemplar|virtual-sequence|virtual-sequence\?|virtual@|' + r'when-empty)\s' + ) builtin_namespaces = ( - r'(?:global|\\+@|change|set-namestack|change-global|init-namespaces|' - r'on|off|set-global|namespace|set|with-scope|bind|with-variable|' - r'inc|dec|counter|initialize|namestack|get|get-global|make-assoc)\s' - ) + r'(?:\+@|change|change-global|counter|dec|get|get-global|' + r'global|inc|init-namespaces|initialize|is-global|make-assoc|' + r'namespace|namestack|off|on|set|set-global|set-namestack|' + r'toggle|with-global|with-scope|with-variable|with-variables)\s' + ) builtin_arrays = ( - r'(?:<array>|2array|3array|pair|>array|1array|4array|pair\\?|' - r'array|resize-array|array\\?)\s' - ) + r'(?:1array|2array|3array|4array|<array>|>array|array|array\?|' + r'pair|pair\?|resize-array)\s' + ) builtin_io = ( - r'(?:\\+character\\+|bad-seek-type\\?|readln|each-morsel|stream-seek|' - r'read|print|with-output-stream|contents|write1|stream-write1|' - r'stream-copy|stream-element-type|with-input-stream|' - r'stream-print|stream-read|stream-contents|stream-tell|' - r'tell-output|bl|seek-output|bad-seek-type|nl|stream-nl|write|' - r'flush|stream-lines|\\+byte\\+|stream-flush|read1|' - r'seek-absolute\\?|stream-read1|lines|stream-readln|' - r'stream-read-until|each-line|seek-end|with-output-stream\\*|' - r'seek-absolute|with-streams|seek-input|seek-relative\\?|' - r'input-stream|stream-write|read-partial|seek-end\\?|' - r'seek-relative|error-stream|read-until|with-input-stream\\*|' - r'with-streams\\*|tell-input|each-block|output-stream|' - r'stream-read-partial|each-stream-block|each-stream-line)\s' - ) + r'(?:\(each-stream-block-slice\)|\(each-stream-block\)|' + r'\(stream-contents-by-block\)|\(stream-contents-by-element\)|' + r'\(stream-contents-by-length-or-block\)|' + r'\(stream-contents-by-length\)|\+byte\+|\+character\+|' + r'bad-seek-type|bad-seek-type\?|bl|contents|each-block|' + r'each-block-size|each-block-slice|each-line|each-morsel|' + r'each-stream-block|each-stream-block-slice|each-stream-line|' + r'error-stream|flush|input-stream|input-stream\?|' + r'invalid-read-buffer|invalid-read-buffer\?|lines|nl|' + r'output-stream|output-stream\?|print|read|read-into|' + r'read-partial|read-partial-into|read-until|read1|readln|' + r'seek-absolute|seek-absolute\?|seek-end|seek-end\?|' + r'seek-input|seek-output|seek-relative|seek-relative\?|' + r'stream-bl|stream-contents|stream-contents\*|stream-copy|' + r'stream-copy\*|stream-element-type|stream-flush|' + r'stream-length|stream-lines|stream-nl|stream-print|' + r'stream-read|stream-read-into|stream-read-partial|' + r'stream-read-partial-into|stream-read-partial-unsafe|' + r'stream-read-unsafe|stream-read-until|stream-read1|' + r'stream-readln|stream-seek|stream-seekable\?|stream-tell|' + r'stream-write|stream-write1|tell-input|tell-output|' + r'with-error-stream|with-error-stream\*|with-error>output|' + r'with-input-output\+error-streams|' + r'with-input-output\+error-streams\*|with-input-stream|' + r'with-input-stream\*|with-output-stream|with-output-stream\*|' + r'with-output>error|with-output\+error-stream|' + r'with-output\+error-stream\*|with-streams|with-streams\*|' + r'write|write1)\s' + ) builtin_strings = ( - r'(?:resize-string|>string|<string>|1string|string|string\\?)\s' - ) + r'(?:1string|<string>|>string|resize-string|string|string\?)\s' + ) builtin_vectors = ( - r'(?:vector\\?|<vector>|\\?push|vector|>vector|1vector)\s' - ) + r'(?:1vector|<vector>|>vector|\?push|vector|vector\?)\s' + ) builtin_continuations = ( - r'(?:with-return|restarts|return-continuation|with-datastack|' - r'recover|rethrow-restarts|<restart>|ifcc|set-catchstack|' - r'>continuation<|cleanup|ignore-errors|restart\\?|' - r'compute-restarts|attempt-all-error|error-thread|continue|' - r'<continuation>|attempt-all-error\\?|condition\\?|' - r'<condition>|throw-restarts|error|catchstack|continue-with|' - r'thread-error-hook|continuation|rethrow|callcc1|' - r'error-continuation|callcc0|attempt-all|condition|' - r'continuation\\?|restart|return)\s' - ) + r'(?:<condition>|<continuation>|<restart>|attempt-all|' + r'attempt-all-error|attempt-all-error\?|callback-error-hook|' + r'callcc0|callcc1|cleanup|compute-restarts|condition|' + r'condition\?|continuation|continuation\?|continue|' + r'continue-restart|continue-with|current-continuation|' + r'error|error-continuation|error-in-thread|error-thread|' + r'ifcc|ignore-errors|in-callback\?|original-error|recover|' + r'restart|restart\?|restarts|rethrow|rethrow-restarts|' + r'return|return-continuation|thread-error-hook|throw-continue|' + r'throw-restarts|with-datastack|with-return)\s' + ) tokens = { 'root': [ - # TODO: (( inputs -- outputs )) - # TODO: << ... >> + # factor allows a file to start with a shebang + (r'#!.*$', Comment.Preproc), + (r'', Text, 'base'), + ], + 'base': [ + (r'\s+', Text), # defining words - (r'(\s*)(:|::|MACRO:|MEMO:)(\s+)(\S+)', - bygroups(Text, Keyword, Text, Name.Function)), - (r'(\s*)(M:)(\s+)(\S+)(\s+)(\S+)', - bygroups(Text, Keyword, Text, Name.Class, Text, Name.Function)), - (r'(\s*)(GENERIC:)(\s+)(\S+)', - bygroups(Text, Keyword, Text, Name.Function)), - (r'(\s*)(HOOK:|GENERIC#)(\s+)(\S+)(\s+)(\S+)', - bygroups(Text, Keyword, Text, Name.Function, Text, Name.Function)), - (r'(\()(\s+)', bygroups(Name.Function, Text), 'stackeffect'), - (r'\;\s', Keyword), + (r'((?:MACRO|MEMO|TYPED)?:[:]?)(\s+)(\S+)', + bygroups(Keyword, Text, Name.Function)), + (r'(M:[:]?)(\s+)(\S+)(\s+)(\S+)', + bygroups(Keyword, Text, Name.Class, Text, Name.Function)), + (r'(C:)(\s+)(\S+)(\s+)(\S+)', + bygroups(Keyword, Text, Name.Function, Text, Name.Class)), + (r'(GENERIC:)(\s+)(\S+)', + bygroups(Keyword, Text, Name.Function)), + (r'(HOOK:|GENERIC#)(\s+)(\S+)(\s+)(\S+)', + bygroups(Keyword, Text, Name.Function, Text, Name.Function)), + (r'\(\s', Name.Function, 'stackeffect'), + (r';\s', Keyword), # imports and namespaces - (r'(USING:)((?:\s|\\\s)+)', bygroups(Keyword.Namespace, Text), 'import'), - (r'(USE:)(\s+)(\S+)', bygroups(Keyword.Namespace, Text, Name.Namespace)), - (r'(UNUSE:)(\s+)(\S+)', bygroups(Keyword.Namespace, Text, Name.Namespace)), - (r'(QUALIFIED:)(\s+)(\S+)', - bygroups(Keyword.Namespace, Text, Name.Namespace)), - (r'(QUALIFIED-WITH:)(\s+)(\S+)', - bygroups(Keyword.Namespace, Text, Name.Namespace)), - (r'(FROM:|EXCLUDE:)(\s+)(\S+)(\s+)(=>)', - bygroups(Keyword.Namespace, Text, Name.Namespace, Text, Text)), - (r'(IN:)(\s+)(\S+)', bygroups(Keyword.Namespace, Text, Name.Namespace)), - (r'(?:ALIAS|DEFER|FORGET|POSTPONE):', Keyword.Namespace), + (r'(USING:)(\s+)', + bygroups(Keyword.Namespace, Text), 'vocabs'), + (r'(USE:|UNUSE:|IN:|QUALIFIED:)(\s+)(\S+)', + bygroups(Keyword.Namespace, Text, Name.Namespace)), + (r'(QUALIFIED-WITH:)(\s+)(\S+)(\s+)(\S+)', + bygroups(Keyword.Namespace, Text, Name.Namespace, Text, Name.Namespace)), + (r'(FROM:|EXCLUDE:)(\s+)(\S+)(\s+=>\s)', + bygroups(Keyword.Namespace, Text, Name.Namespace, Text), 'words'), + (r'(RENAME:)(\s+)(\S+)(\s+)(\S+)(\s+=>\s+)(\S+)', + bygroups(Keyword.Namespace, Text, Name.Function, Text, Name.Namespace, Text, Name.Function)), + (r'(ALIAS:|TYPEDEF:)(\s+)(\S+)(\s+)(\S+)', + bygroups(Keyword.Namespace, Text, Name.Function, Text, Name.Function)), + (r'(DEFER:|FORGET:|POSTPONE:)(\s+)(\S+)', + bygroups(Keyword.Namespace, Text, Name.Function)), # tuples and classes - (r'(TUPLE:)(\s+)(\S+)(\s+<\s+)(\S+)', - bygroups(Keyword, Text, Name.Class, Text, Name.Class), 'slots'), - (r'(TUPLE:)(\s+)(\S+)', bygroups(Keyword, Text, Name.Class), 'slots'), - (r'(UNION:)(\s+)(\S+)', bygroups(Keyword, Text, Name.Class)), - (r'(INTERSECTION:)(\s+)(\S+)', bygroups(Keyword, Text, Name.Class)), + (r'(TUPLE:|ERROR:)(\s+)(\S+)(\s+<\s+)(\S+)', + bygroups(Keyword, Text, Name.Class, Text, Name.Class), 'slots'), + (r'(TUPLE:|ERROR:|BUILTIN:)(\s+)(\S+)', + bygroups(Keyword, Text, Name.Class), 'slots'), + (r'(MIXIN:|UNION:|INTERSECTION:)(\s+)(\S+)', + bygroups(Keyword, Text, Name.Class)), (r'(PREDICATE:)(\s+)(\S+)(\s+<\s+)(\S+)', - bygroups(Keyword, Text, Name.Class, Text, Name.Class)), + bygroups(Keyword, Text, Name.Class, Text, Name.Class)), (r'(C:)(\s+)(\S+)(\s+)(\S+)', - bygroups(Keyword, Text, Name.Function, Text, Name.Class)), - (r'INSTANCE:', Keyword), - (r'SLOT:', Keyword), - (r'MIXIN:', Keyword), - (r'(?:SINGLETON|SINGLETONS):', Keyword), + bygroups(Keyword, Text, Name.Function, Text, Name.Class)), + (r'(INSTANCE:)(\s+)(\S+)(\s+)(\S+)', + bygroups(Keyword, Text, Name.Class, Text, Name.Class)), + (r'(SLOT:)(\s+)(\S+)', bygroups(Keyword, Text, Name.Function)), + (r'(SINGLETON:)(\s+)(\S+)', bygroups(Keyword, Text, Name.Class)), + (r'SINGLETONS:', Keyword, 'classes'), # other syntax - (r'CONSTANT:', Keyword), - (r'(?:SYMBOL|SYMBOLS):', Keyword), - (r'ERROR:', Keyword), - (r'SYNTAX:', Keyword), - (r'(HELP:)(\s+)(\S+)', bygroups(Keyword, Text, Name.Function)), - (r'(MAIN:)(\s+)(\S+)', bygroups(Keyword.Namespace, Text, Name.Function)), - (r'(?:ALIEN|TYPEDEF|FUNCTION|STRUCT):', Keyword), + (r'(CONSTANT:|SYMBOL:|MAIN:|HELP:)(\s+)(\S+)', + bygroups(Keyword, Text, Name.Function)), + (r'SYMBOLS:\s', Keyword, 'words'), + (r'SYNTAX:\s', Keyword), + (r'ALIEN:\s', Keyword), + (r'(STRUCT:)(\s+)(\S+)', bygroups(Keyword, Text, Name.Class)), + (r'(FUNCTION:)(\s+\S+\s+)(\S+)(\s+\(\s+[^\)]+\)\s)', + bygroups(Keyword.Namespace, Text, Name.Function, Text)), + (r'(FUNCTION-ALIAS:)(\s+)(\S+)(\s+\S+\s+)(\S+)(\s+\(\s+[^\)]+\)\s)', + bygroups(Keyword.Namespace, Text, Name.Function, Text, Name.Function, Text)), # vocab.private - # TODO: words inside vocab.private should have red names? - (r'(?:<PRIVATE|PRIVATE>)', Keyword.Namespace), + (r'(?:<PRIVATE|PRIVATE>)\s', Keyword.Namespace), # strings (r'"""\s+(?:.|\n)*?\s+"""', String), (r'"(?:\\\\|\\"|[^"])*"', String), - (r'CHAR:\s+(\\[\\abfnrstv]*|\S)\s', String.Char), + (r'\S+"\s+(?:\\\\|\\"|[^"])*"', String), + (r'CHAR:\s+(?:\\[\\abfnrstv]|[^\\]\S*)\s', String.Char), # comments - (r'\!\s+.*$', Comment), - (r'#\!\s+.*$', Comment), + (r'!\s+.*$', Comment), + (r'#!\s+.*$', Comment), + (r'/\*\s+(?:.|\n)*?\s\*/\s', Comment), # boolean constants - (r'(t|f)\s', Name.Constant), + (r'[tf]\s', Name.Constant), - # numbers - (r'-?\d+\.\d+\s', Number.Float), - (r'-?\d+\s', Number.Integer), - (r'HEX:\s+[a-fA-F\d]+\s', Number.Hex), - (r'BIN:\s+[01]+\s', Number.Integer), - (r'OCT:\s+[0-7]+\s', Number.Oct), + # symbols and literals + (r'[\\$]\s+\S+', Name.Constant), + (r'M\\\s+\S+\s+\S+', Name.Constant), - # operators - (r'[-+/*=<>^]\s', Operator), + # numbers + (r'[+-]?(?:[\d,]*\d)?\.(?:\d([\d,]*\d)?)?(?:[eE][+-]?\d+)?\s', Number), + (r'[+-]?\d(?:[\d,]*\d)?(?:[eE][+-]?\d+)?\s', Number), + (r'0x[a-fA-F\d](?:[a-fA-F\d,]*[a-fA-F\d])?(?:p\d([\d,]*\d)?)?\s', Number), + (r'NAN:\s+[a-fA-F\d](?:[a-fA-F\d,]*[a-fA-F\d])?(?:p\d([\d,]*\d)?)?\s', Number), + (r'0b[01]+\s', Number), + (r'0o[0-7]+\s', Number), + (r'(?:\d([\d,]*\d)?)?\+\d(?:[\d,]*\d)?/\d(?:[\d,]*\d)?\s', Number), + (r'(?:\-\d([\d,]*\d)?)?\-\d(?:[\d,]*\d)?/\d(?:[\d,]*\d)?\s', Number), # keywords - (r'(?:deprecated|final|foldable|flushable|inline|recursive)\s', Keyword), + (r'(?:deprecated|final|foldable|flushable|inline|recursive)\s', + Keyword), # builtins (builtin_kernel, Name.Builtin), @@ -1740,224 +1762,706 @@ class FactorLexer(RegexLexer): (builtin_vectors, Name.Builtin), (builtin_continuations, Name.Builtin), - # whitespaces - usually not relevant - (r'\s+', Text), - # everything else is text (r'\S+', Text), ], - 'stackeffect': [ - (r'\s*\(', Name.Function, 'stackeffect'), - (r'\)', Name.Function, '#pop'), - (r'\-\-', Name.Function), (r'\s+', Text), + (r'\(\s+', Name.Function, 'stackeffect'), + (r'\)\s', Name.Function, '#pop'), + (r'--\s', Name.Function), (r'\S+', Name.Variable), ], - 'slots': [ (r'\s+', Text), (r';\s', Keyword, '#pop'), + (r'({\s+)(\S+)(\s+[^}]+\s+}\s)', + bygroups(Text, Name.Variable, Text)), (r'\S+', Name.Variable), ], - - 'import': [ - (r';', Keyword, '#pop'), + 'vocabs': [ + (r'\s+', Text), + (r';\s', Keyword, '#pop'), (r'\S+', Name.Namespace), + ], + 'classes': [ (r'\s+', Text), + (r';\s', Keyword, '#pop'), + (r'\S+', Name.Class), + ], + 'words': [ + (r'\s+', Text), + (r';\s', Keyword, '#pop'), + (r'\S+', Name.Function), ], } -class IokeLexer(RegexLexer): +class FancyLexer(RegexLexer): """ - For `Ioke <http://ioke.org/>`_ (a strongly typed, dynamic, - prototype based programming language) source. + Pygments Lexer For `Fancy <http://www.fancy-lang.org/>`_. + + Fancy is a self-hosted, pure object-oriented, dynamic, + class-based, concurrent general-purpose programming language + running on Rubinius, the Ruby VM. - *New in Pygments 1.4.* + .. versionadded:: 1.5 """ - name = 'Ioke' - filenames = ['*.ik'] - aliases = ['ioke', 'ik'] - mimetypes = ['text/x-iokesrc'] + name = 'Fancy' + filenames = ['*.fy', '*.fancypack'] + aliases = ['fancy', 'fy'] + mimetypes = ['text/x-fancysrc'] + tokens = { - 'interpolatableText': [ - (r'(\\b|\\e|\\t|\\n|\\f|\\r|\\"|\\\\|\\#|\\\Z|\\u[0-9a-fA-F]{1,4}' - r'|\\[0-3]?[0-7]?[0-7])', String.Escape), - (r'#{', Punctuation, 'textInterpolationRoot') - ], - - 'text': [ - (r'(?<!\\)"', String, '#pop'), - include('interpolatableText'), - (r'[^"]', String) - ], - - 'documentation': [ - (r'(?<!\\)"', String.Doc, '#pop'), - include('interpolatableText'), - (r'[^"]', String.Doc) - ], - - 'textInterpolationRoot': [ - (r'}', Punctuation, '#pop'), - include('root') - ], + # copied from PerlLexer: + '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'\s+', Text), - 'slashRegexp': [ - (r'(?<!\\)/[oxpniums]*', String.Regex, '#pop'), - include('interpolatableText'), - (r'\\/', String.Regex), - (r'[^/]', String.Regex) - ], - - 'squareRegexp': [ - (r'(?<!\\)][oxpniums]*', String.Regex, '#pop'), - include('interpolatableText'), - (r'\\]', String.Regex), - (r'[^\]]', String.Regex) - ], - - 'squareText': [ - (r'(?<!\\)]', String, '#pop'), - include('interpolatableText'), - (r'[^\]]', String) - ], + # balanced delimiters (copied from PerlLexer): + (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'), + # Comments + (r'#(.*?)\n', Comment.Single), + # Symbols + (r'\'([^\'\s\[\]\(\)\{\}]+|\[\])', String.Symbol), + # Multi-line DoubleQuotedString + (r'"""(\\\\|\\"|[^"])*"""', String), + # DoubleQuotedString + (r'"(\\\\|\\"|[^"])*"', String), + # keywords + (r'(def|class|try|catch|finally|retry|return|return_local|match|' + r'case|->|=>)\b', Keyword), + # constants + (r'(self|super|nil|false|true)\b', Name.Constant), + (r'[(){};,/?\|:\\]', Punctuation), + # names + (r'(Object|Array|Hash|Directory|File|Class|String|Number|' + r'Enumerable|FancyEnumerable|Block|TrueClass|NilClass|' + r'FalseClass|Tuple|Symbol|Stack|Set|FancySpec|Method|Package|' + r'Range)\b', Name.Builtin), + # functions + (r'[a-zA-Z]([a-zA-Z0-9_]|[-+?!=*/^><%])*:', Name.Function), + # operators, must be below functions + (r'[-+*/~,<>=&!?%^\[\]\.$]+', Operator), + ('[A-Z][a-zA-Z0-9_]*', Name.Constant), + ('@[a-zA-Z_][a-zA-Z0-9_]*', Name.Variable.Instance), + ('@@[a-zA-Z_][a-zA-Z0-9_]*', Name.Variable.Class), + ('@@?', Operator), + ('[a-zA-Z_][a-zA-Z0-9_]*', Name), + # numbers - / checks are necessary to avoid mismarking regexes, + # see comment in RubyLexer + (r'(0[oO]?[0-7]+(?:_[0-7]+)*)(\s*)([/?])?', + bygroups(Number.Oct, Text, Operator)), + (r'(0[xX][0-9A-Fa-f]+(?:_[0-9A-Fa-f]+)*)(\s*)([/?])?', + bygroups(Number.Hex, Text, Operator)), + (r'(0[bB][01]+(?:_[01]+)*)(\s*)([/?])?', + bygroups(Number.Bin, Text, Operator)), + (r'([\d]+(?:_\d+)*)(\s*)([/?])?', + bygroups(Number.Integer, Text, Operator)), + (r'\d+([eE][+-]?[0-9]+)|\d+\.\d+([eE][+-]?[0-9]+)?', Number.Float), + (r'\d+', Number.Integer) + ] + } + + +class DgLexer(RegexLexer): + """ + Lexer for `dg <http://pyos.github.com/dg>`_, + a functional and object-oriented programming language + running on the CPython 3 VM. + + .. versionadded:: 1.6 + """ + name = 'dg' + aliases = ['dg'] + filenames = ['*.dg'] + mimetypes = ['text/x-dg'] + + tokens = { 'root': [ - (r'\n', Text), (r'\s+', Text), + (r'#.*?$', Comment.Single), - # Comments - (r';(.*?)\n', Comment), - (r'\A#!(.*?)\n', Comment), + (r'(?i)0b[01]+', Number.Bin), + (r'(?i)0o[0-7]+', Number.Oct), + (r'(?i)0x[0-9a-f]+', Number.Hex), + (r'(?i)[+-]?[0-9]+\.[0-9]+(e[+-]?[0-9]+)?j?', Number.Float), + (r'(?i)[+-]?[0-9]+e[+-]?\d+j?', Number.Float), + (r'(?i)[+-]?[0-9]+j?', Number.Integer), + + (r"(?i)(br|r?b?)'''", String, combined('stringescape', 'tsqs', 'string')), + (r'(?i)(br|r?b?)"""', String, combined('stringescape', 'tdqs', 'string')), + (r"(?i)(br|r?b?)'", String, combined('stringescape', 'sqs', 'string')), + (r'(?i)(br|r?b?)"', String, combined('stringescape', 'dqs', 'string')), + + (r"`\w+'*`", Operator), + (r'\b(and|in|is|or|where)\b', Operator.Word), + (r'[!$%&*+\-./:<-@\\^|~;,]+', Operator), + + (r"(?<!\.)(bool|bytearray|bytes|classmethod|complex|dict'?|" + r"float|frozenset|int|list'?|memoryview|object|property|range|" + r"set'?|slice|staticmethod|str|super|tuple'?|type)" + r"(?!['\w])", Name.Builtin), + (r'(?<!\.)(__import__|abs|all|any|bin|bind|chr|cmp|compile|complex|' + r'delattr|dir|divmod|drop|dropwhile|enumerate|eval|exhaust|' + r'filter|flip|foldl1?|format|fst|getattr|globals|hasattr|hash|' + r'head|hex|id|init|input|isinstance|issubclass|iter|iterate|last|' + r'len|locals|map|max|min|next|oct|open|ord|pow|print|repr|' + r'reversed|round|setattr|scanl1?|snd|sorted|sum|tail|take|' + r"takewhile|vars|zip)(?!['\w])", Name.Builtin), + (r"(?<!\.)(self|Ellipsis|NotImplemented|None|True|False)(?!['\w])", + Name.Builtin.Pseudo), + + (r"(?<!\.)[A-Z]\w*(Error|Exception|Warning)'*(?!['\w])", + Name.Exception), + (r"(?<!\.)(Exception|GeneratorExit|KeyboardInterrupt|StopIteration|" + r"SystemExit)(?!['\w])", Name.Exception), + + (r"(?<![\.\w])(except|finally|for|if|import|not|otherwise|raise|" + r"subclass|while|with|yield)(?!['\w])", Keyword.Reserved), + + (r"[A-Z_]+'*(?!['\w])", Name), + (r"[A-Z]\w+'*(?!['\w])", Keyword.Type), + (r"\w+'*", Name), + + (r'[()]', Punctuation), + (r'.', Error), + ], + 'stringescape': [ + (r'\\([\\abfnrtv"\']|\n|N{.*?}|u[a-fA-F0-9]{4}|' + r'U[a-fA-F0-9]{8}|x[a-fA-F0-9]{2}|[0-7]{1,3})', String.Escape) + ], + 'string': [ + (r'%(\([a-zA-Z0-9_]+\))?[-#0 +]*([0-9]+|[*])?(\.([0-9]+|[*]))?' + '[hlL]?[diouxXeEfFgGcrs%]', String.Interpol), + (r'[^\\\'"%\n]+', String), + # quotes, percents and backslashes must be parsed one at a time + (r'[\'"\\]', String), + # unhandled string formatting sign + (r'%', String), + (r'\n', String) + ], + 'dqs': [ + (r'"', String, '#pop') + ], + 'sqs': [ + (r"'", String, '#pop') + ], + 'tdqs': [ + (r'"""', String, '#pop') + ], + 'tsqs': [ + (r"'''", String, '#pop') + ], + } - #Regexps - (r'#/', String.Regex, 'slashRegexp'), - (r'#r\[', String.Regex, 'squareRegexp'), - #Symbols - (r':[a-zA-Z0-9_!:?]+', String.Symbol), - (r'[a-zA-Z0-9_!:?]+:(?![a-zA-Z0-9_!?])', String.Other), - (r':"(\\\\|\\"|[^"])*"', String.Symbol), +class Perl6Lexer(ExtendedRegexLexer): + """ + For `Perl 6 <http://www.perl6.org>`_ source code. - #Documentation - (r'((?<=fn\()|(?<=fnx\()|(?<=method\()|(?<=macro\()|(?<=lecro\()' - r'|(?<=syntax\()|(?<=dmacro\()|(?<=dlecro\()|(?<=dlecrox\()' - r'|(?<=dsyntax\())[\s\n\r]*"', String.Doc, 'documentation'), + .. versionadded:: 2.0 + """ - #Text - (r'"', String, 'text'), - (r'#\[', String, 'squareText'), + 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 = "['a-zA-Z0-9_:-]" # if you alter this, search for a copy made of it below + + 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', + } - #Mimic - (r'[a-zA-Z0-9_][a-zA-Z0-9!?_:]+(?=\s*=.*mimic\s)', Name.Entity), + 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 + ')' + prefix + '(' + \ + r'|'.join([ re.escape(x) for x in words]) + r')' + suffix + '(?!' + boundary_regex_fragment + ')' + + 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.Singleline), + (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 + ')(\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])(?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>[^0-9a-zA-Z_:\s])(?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'[0-9a-zA-Z_]' + 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')), + (r'', Name, ('#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'#.*?$', Comment.Singleline), + (r'\{', embedded_perl6_callback), + ('.+?', String.Regex), + ], + } - #Assignment - (r'[a-zA-Z_][a-zA-Z0-9_!:?]*(?=[\s]*[+*/-]?=[^=].*($|\.))', Name.Variable), + 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 - # keywords - (r'(break|cond|continue|do|ensure|for|for:dict|for:set|if|let|' - r'loop|p:for|p:for:dict|p:for:set|return|unless|until|while|' - r'with)(?![a-zA-Z0-9!:_?])', Keyword.Reserved), - - # Origin - (r'(eval|mimic|print|println)(?![a-zA-Z0-9!:_?])', Keyword), - - # Base - (r'(cell\?|cellNames|cellOwner\?|cellOwner|cells|cell|' - r'documentation|hash|identity|mimic|removeCell\!|undefineCell\!)' - r'(?![a-zA-Z0-9!:_?])', Keyword), - - # Ground - (r'(stackTraceAsText)(?![a-zA-Z0-9!:_?])', Keyword), - - #DefaultBehaviour Literals - (r'(dict|list|message|set)(?![a-zA-Z0-9!:_?])', Keyword.Reserved), - - #DefaultBehaviour Case - (r'(case|case:and|case:else|case:nand|case:nor|case:not|case:or|' - r'case:otherwise|case:xor)(?![a-zA-Z0-9!:_?])', Keyword.Reserved), - - #DefaultBehaviour Reflection - (r'(asText|become\!|derive|freeze\!|frozen\?|in\?|is\?|kind\?|' - r'mimic\!|mimics|mimics\?|prependMimic\!|removeAllMimics\!|' - r'removeMimic\!|same\?|send|thaw\!|uniqueHexId)' - r'(?![a-zA-Z0-9!:_?])', Keyword), - - #DefaultBehaviour Aspects - (r'(after|around|before)(?![a-zA-Z0-9!:_?])', Keyword.Reserved), - - # DefaultBehaviour - (r'(kind|cellDescriptionDict|cellSummary|genSym|inspect|notice)' - r'(?![a-zA-Z0-9!:_?])', Keyword), - (r'(use|destructuring)', Keyword.Reserved), - - #DefaultBehavior BaseBehavior - (r'(cell\?|cellOwner\?|cellOwner|cellNames|cells|cell|' - r'documentation|identity|removeCell!|undefineCell)' - r'(?![a-zA-Z0-9!:_?])', Keyword), - - #DefaultBehavior Internal - (r'(internal:compositeRegexp|internal:concatenateText|' - r'internal:createDecimal|internal:createNumber|' - r'internal:createRegexp|internal:createText)' - r'(?![a-zA-Z0-9!:_?])', Keyword.Reserved), - - #DefaultBehaviour Conditions - (r'(availableRestarts|bind|error\!|findRestart|handle|' - r'invokeRestart|rescue|restart|signal\!|warn\!)' - r'(?![a-zA-Z0-9!:_?])', Keyword.Reserved), + saw_perl_decl = False + rating = False + + # check for my/our/has declarations + # copied PERL6_IDENTIFIER_RANGE from above; not happy about that + if re.search("(?:my|our|has)\s+(?:['a-zA-Z0-9_:-]+\s+)?[$@%&(]", text): + rating = 0.8 + saw_perl_decl = True + + for line in lines: + line = re.sub('#.*', '', line) + if re.match('^\s*$', line): + continue + + # match v6; use v6; use v6.0; use v6.0.0; + if re.match('^\s*(?:use\s+)?v6(?:\.\d(?:\.\d)?)?;', line): + return True + # match class, module, role, enum, grammar declarations + class_decl = re.match('^\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 - # constants - (r'(nil|false|true)(?![a-zA-Z0-9!:_?])', Name.Constant), + def __init__(self, **options): + super(Perl6Lexer, self).__init__(**options) + self.encoding = options.get('encoding', 'utf-8') - # names - (r'(Arity|Base|Call|Condition|DateTime|Aspects|Pointcut|' - r'Assignment|BaseBehavior|Boolean|Case|AndCombiner|Else|' - r'NAndCombiner|NOrCombiner|NotCombiner|OrCombiner|XOrCombiner|' - r'Conditions|Definitions|FlowControl|Internal|Literals|' - r'Reflection|DefaultMacro|DefaultMethod|DefaultSyntax|Dict|' - r'FileSystem|Ground|Handler|Hook|IO|IokeGround|Struct|' - r'LexicalBlock|LexicalMacro|List|Message|Method|Mixins|' - r'NativeMethod|Number|Origin|Pair|Range|Reflector|Regexp Match|' - r'Regexp|Rescue|Restart|Runtime|Sequence|Set|Symbol|' - r'System|Text|Tuple)(?![a-zA-Z0-9!:_?])', Name.Builtin), - # functions - (ur'(generateMatchMethod|aliasMethod|\u03bb|\u028E|fnx|fn|method|' - ur'dmacro|dlecro|syntax|macro|dlecrox|lecrox|lecro|syntax)' - ur'(?![a-zA-Z0-9!:_?])', Name.Function), +class HyLexer(RegexLexer): + """ + Lexer for `Hy <http://hylang.org/>`_ source code. + + .. versionadded:: 2.0 + """ + name = 'Hy' + aliases = ['hylang'] + filenames = ['*.hy'] + mimetypes = ['text/x-hy', 'application/x-hy'] + + special_forms = [ + 'cond', 'for', '->', '->>', 'car', + 'cdr', 'first', 'rest', 'let', 'when', 'unless', + 'import', 'do', 'progn', 'get', 'slice', 'assoc', 'with-decorator', + ',', 'list_comp', 'kwapply', '~', 'is', 'in', 'is-not', 'not-in', + 'quasiquote', 'unquote', 'unquote-splice', 'quote', '|', '<<=', '>>=', + 'foreach', 'while', + 'eval-and-compile', 'eval-when-compile' + ] + + declarations = [ + 'def' 'defn', 'defun', 'defmacro', 'defclass', 'lambda', 'fn', 'setv' + ] + + hy_builtins = [] + + hy_core = [ + 'cycle', 'dec', 'distinct', 'drop', 'even?', 'filter', 'inc', + 'instance?', 'iterable?', 'iterate', 'iterator?', 'neg?', + 'none?', 'nth', 'numeric?', 'odd?', 'pos?', 'remove', 'repeat', + 'repeatedly', 'take', 'take_nth', 'take_while', 'zero?' + ] + + builtins = hy_builtins + hy_core + + # valid names for identifiers + # well, names can only not consist fully of numbers + # but this should be good enough for now + valid_name = r'(?!#)[\w!$%*+<=>?/.#-]+' + + def _multi_escape(entries): + return '(%s)' % ('|'.join(re.escape(entry) + ' ' for entry in entries)) + + tokens = { + 'root': [ + # the comments - always starting with semicolon + # and going to the end of the line + (r';.*$', Comment.Single), + + # whitespaces - usually not relevant + (r'[,\s]+', Text), - # Numbers - (r'-?0[xX][0-9a-fA-F]+', Number.Hex), - (r'-?(\d+\.?\d*|\d*\.\d+)([eE][+-]?[0-9]+)?', Number.Float), + # numbers + (r'-?\d+\.\d+', Number.Float), (r'-?\d+', Number.Integer), + (r'0[0-7]+j?', Number.Oct), + (r'0[xX][a-fA-F0-9]+', Number.Hex), - (r'#\(', Punctuation), - - # Operators - (ur'(&&>>|\|\|>>|\*\*>>|:::|::|\.\.\.|===|\*\*>|\*\*=|&&>|&&=|' - ur'\|\|>|\|\|=|\->>|\+>>|!>>|<>>>|<>>|&>>|%>>|#>>|@>>|/>>|\*>>|' - ur'\?>>|\|>>|\^>>|~>>|\$>>|=>>|<<=|>>=|<=>|<\->|=~|!~|=>|\+\+|' - ur'\-\-|<=|>=|==|!=|&&|\.\.|\+=|\-=|\*=|\/=|%=|&=|\^=|\|=|<\-|' - ur'\+>|!>|<>|&>|%>|#>|\@>|\/>|\*>|\?>|\|>|\^>|~>|\$>|<\->|\->|' - ur'<<|>>|\*\*|\?\||\?&|\|\||>|<|\*|\/|%|\+|\-|&|\^|\||=|\$|!|~|' - ur'\?|#|\u2260|\u2218|\u2208|\u2209)', Operator), - (r'(and|nand|or|xor|nor|return|import)(?![a-zA-Z0-9_!?])', - Operator), + # strings, symbols and characters + (r'"(\\\\|\\"|[^"])*"', String), + (r"'" + valid_name, String.Symbol), + (r"\\(.|[a-z]+)", String.Char), + (r'^(\s*)([rRuU]{,2}"""(?:.|\n)*?""")', bygroups(Text, String.Doc)), + (r"^(\s*)([rRuU]{,2}'''(?:.|\n)*?''')", bygroups(Text, String.Doc)), - # Punctuation - (r'(\`\`|\`|\'\'|\'|\.|\,|@|@@|\[|\]|\(|\)|{|})', Punctuation), + # keywords + (r'::?' + valid_name, String.Symbol), - #kinds - (r'[A-Z][a-zA-Z0-9_!:?]*', Name.Class), + # special operators + (r'~@|[`\'#^~&@]', Operator), - #default cellnames - (r'[a-z_][a-zA-Z0-9_!:?]*', Name) - ] + include('py-keywords'), + include('py-builtins'), + + # highlight the special forms + (_multi_escape(special_forms), Keyword), + + # Technically, only the special forms are 'keywords'. The problem + # is that only treating them as keywords means that things like + # 'defn' and 'ns' need to be highlighted as builtins. This is ugly + # and weird for most styles. So, as a compromise we're going to + # highlight them as Keyword.Declarations. + (_multi_escape(declarations), Keyword.Declaration), + + # highlight the builtins + (_multi_escape(builtins), Name.Builtin), + + # the remaining functions + (r'(?<=\()' + valid_name, Name.Function), + + # find the remaining variables + (valid_name, Name.Variable), + + # Hy accepts vector notation + (r'(\[|\])', Punctuation), + + # Hy accepts map notation + (r'(\{|\})', Punctuation), + + # the famous parentheses! + (r'(\(|\))', Punctuation), + + ], + 'py-keywords': PythonLexer.tokens['keywords'], + 'py-builtins': PythonLexer.tokens['builtins'], } + def analyse_text(text): + if '(import ' in text or '(defn ' in text: + return 0.9 class ChaiscriptLexer(RegexLexer): @@ -2012,4 +2516,3 @@ class ChaiscriptLexer(RegexLexer): (r"'(\\\\|\\'|[^'])*'", String.Single), ] } - |