diff options
Diffstat (limited to 'pygments/lexers/agile.py')
| -rw-r--r-- | pygments/lexers/agile.py | 189 |
1 files changed, 149 insertions, 40 deletions
diff --git a/pygments/lexers/agile.py b/pygments/lexers/agile.py index 1f81365e..48983ca3 100644 --- a/pygments/lexers/agile.py +++ b/pygments/lexers/agile.py @@ -23,7 +23,7 @@ __all__ = ['PythonLexer', 'PythonConsoleLexer', 'PythonTracebackLexer', 'Python3Lexer', 'Python3TracebackLexer', 'RubyLexer', 'RubyConsoleLexer', 'PerlLexer', 'LuaLexer', 'MoonScriptLexer', 'CrocLexer', 'MiniDLexer', 'IoLexer', 'TclLexer', 'FactorLexer', - 'FancyLexer', 'DgLexer', 'Perl6Lexer'] + 'FancyLexer', 'DgLexer', 'Perl6Lexer', 'HyLexer'] # b/w compatibility from pygments.lexers.functional import SchemeLexer @@ -532,7 +532,7 @@ class RubyLexer(ExtendedRegexLexer): (r":'(\\\\|\\'|[^'])*'", String.Symbol), (r"'(\\\\|\\'|[^'])*'", String.Single), (r':"', String.Symbol, 'simple-sym'), - (r'([a-zA-Z_][a-zA-Z0-9]*)(:)(?!:)', + (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'), @@ -848,7 +848,7 @@ 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 @@ -1848,56 +1848,53 @@ class DgLexer(RegexLexer): tokens = { 'root': [ - # Whitespace: (r'\s+', Text), (r'#.*?$', Comment.Single), - # Lexemes: - # Numbers - (r'0[bB][01]+', Number.Bin), - (r'0[oO][0-7]+', Number.Oct), - (r'0[xX][\da-fA-F]+', Number.Hex), - (r'[+-]?\d+\.\d+([eE][+-]?\d+)?[jJ]?', Number.Float), - (r'[+-]?\d+[eE][+-]?\d+[jJ]?', Number.Float), - (r'[+-]?\d+[jJ]?', Number.Integer), - # Character/String Literals - (r"[br]*'''", String, combined('stringescape', 'tsqs', 'string')), - (r'[br]*"""', String, combined('stringescape', 'tdqs', 'string')), - (r"[br]*'", String, combined('stringescape', 'sqs', 'string')), - (r'[br]*"', String, combined('stringescape', 'dqs', 'string')), - # Operators - (r"`\w+'*`", Operator), # Infix links - # Reserved infix links - (r'\b(or|and|if|else|where|is|in)\b', Operator.Word), + + (r'(?i)0b[01]+', Number.Bin), + (r'(?i)0o[0-7]+', Number.Oct), + (r'(?i)0x[0-9a-f]+', Number.Hex), + (r'(?i)[+-]?[0-9]+\.[0-9]+(e[+-]?[0-9]+)?j?', Number.Float), + (r'(?i)[+-]?[0-9]+e[+-]?\d+j?', Number.Float), + (r'(?i)[+-]?[0-9]+j?', Number.Integer), + + (r"(?i)(br|r?b?)'''", String, combined('stringescape', 'tsqs', 'string')), + (r'(?i)(br|r?b?)"""', String, combined('stringescape', 'tdqs', 'string')), + (r"(?i)(br|r?b?)'", String, combined('stringescape', 'sqs', 'string')), + (r'(?i)(br|r?b?)"', String, combined('stringescape', 'dqs', 'string')), + + (r"`\w+'*`", Operator), + (r'\b(and|in|is|or|where)\b', Operator.Word), (r'[!$%&*+\-./:<-@\\^|~;,]+', Operator), - # Identifiers - # Python 3 types + (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), - # Python 3 builtins + some more (r'(?<!\.)(__import__|abs|all|any|bin|bind|chr|cmp|compile|complex|' - r'delattr|dir|divmod|drop|dropwhile|enumerate|eval|filter|flip|' - r'foldl1?|format|fst|getattr|globals|hasattr|hash|head|hex|id|' - r'init|input|isinstance|issubclass|iter|iterate|last|len|locals|' - r'map|max|min|next|oct|open|ord|pow|print|repr|reversed|round|' - r'setattr|scanl1?|snd|sorted|sum|tail|take|takewhile|vars|zip)' - r"(?!['\w])", Name.Builtin), + 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"(?<!\.)(KeyboardInterrupt|SystemExit|StopIteration|" - r"GeneratorExit)(?!['\w])", Name.Exception), - # Compiler-defined identifiers - (r"(?<![\.\w])(import|inherit|for|while|switch|not|raise|unsafe|" - r"yield|with)(?!['\w])", Keyword.Reserved), - # Other links - (r"[A-Z_']+\b", Name), - (r"[A-Z][\w']*\b", Keyword.Type), + (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), - # Blocks + (r'[()]', Punctuation), + (r'.', Error), ], 'stringescape': [ (r'\\([\\abfnrtv"\']|\n|N{.*?}|u[a-fA-F0-9]{4}|' @@ -1937,7 +1934,7 @@ class Perl6Lexer(ExtendedRegexLexer): name = 'Perl6' aliases = ['perl6', 'pl6'] filenames = ['*.pl', '*.pm', '*.nqp', '*.p6', '*.6pl', '*.p6l', '*.pl6', - '*.6pm', '*.p6m', '*.pm6'] + '*.6pm', '*.p6m', '*.pm6', '*.t'] mimetypes = ['text/x-perl6', 'application/x-perl6'] flags = re.MULTILINE | re.DOTALL | re.UNICODE @@ -2288,3 +2285,115 @@ class Perl6Lexer(ExtendedRegexLexer): def __init__(self, **options): super(Perl6Lexer, self).__init__(**options) self.encoding = options.get('encoding', 'utf-8') + + +class HyLexer(RegexLexer): + """ + Lexer for `Hy <http://hylang.org/>`_ source code. + + *New in Pygments 1.7.* + """ + name = 'Hy' + aliases = ['hy'] + 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'-?\d+\.\d+', Number.Float), + (r'-?\d+', Number.Integer), + (r'0[0-7]+j?', Number.Oct), + (r'0[xX][a-fA-F0-9]+', Number.Hex), + + # 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)), + + # keywords + (r'::?' + valid_name, String.Symbol), + + # special operators + (r'~@|[`\'#^~&@]', Operator), + + 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): + return '(import' in text or '(defn' in text |