diff options
Diffstat (limited to 'pygments')
-rw-r--r-- | pygments/lexers/agile.py | 2 | ||||
-rw-r--r-- | pygments/lexers/jvm.py | 144 | ||||
-rw-r--r-- | pygments/lexers/other.py | 2 | ||||
-rw-r--r-- | pygments/lexers/web.py | 6 |
4 files changed, 53 insertions, 101 deletions
diff --git a/pygments/lexers/agile.py b/pygments/lexers/agile.py index e93cf5a8..3d76abaa 100644 --- a/pygments/lexers/agile.py +++ b/pygments/lexers/agile.py @@ -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'), diff --git a/pygments/lexers/jvm.py b/pygments/lexers/jvm.py index 8b5d5964..e07656a4 100644 --- a/pygments/lexers/jvm.py +++ b/pygments/lexers/jvm.py @@ -15,7 +15,6 @@ from pygments.lexer import Lexer, RegexLexer, include, bygroups, using, \ this from pygments.token import Text, Comment, Operator, Keyword, Name, String, \ Number, Punctuation -from pygments.util import get_choice_opt from pygments import unistring as uni @@ -937,114 +936,65 @@ class CeylonLexer(RegexLexer): class KotlinLexer(RegexLexer): """ - For `Kotlin <http://confluence.jetbrains.net/display/Kotlin/>`_ + For `Kotlin <http://kotlin.jetbrains.org/>`_ source code. - Additional options accepted: - - `unicodelevel` - Determines which Unicode characters this lexer allows for identifiers. - The possible values are: - - * ``none`` -- only the ASCII letters and numbers are allowed. This - is the fastest selection. - * ``basic`` -- all Unicode characters from the specification except - category ``Lo`` are allowed. - * ``full`` -- all Unicode characters as specified in the C# specs - are allowed. Note that this means a considerable slowdown since the - ``Lo`` category has more than 40,000 characters in it! - - The default value is ``basic``. - *New in Pygments 1.5.* """ name = 'Kotlin' aliases = ['kotlin'] filenames = ['*.kt'] - mimetypes = ['text/x-kotlin'] # inferred + mimetypes = ['text/x-kotlin'] flags = re.MULTILINE | re.DOTALL | re.UNICODE - # for the range of allowed unicode characters in identifiers, - # see http://www.ecma-international.org/publications/files/ECMA-ST/Ecma-334.pdf - - levels = { - 'none': '@?[_a-zA-Z][a-zA-Z0-9_]*', - 'basic': ('@?[_' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl + ']' + - '[' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl + - uni.Nd + uni.Pc + uni.Cf + uni.Mn + uni.Mc + ']*'), - 'full': ('@?(?:_|[^' + - uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl') + '])' - + '[^' + uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl', - 'Nd', 'Pc', 'Cf', 'Mn', 'Mc') + ']*'), - } + kt_name = ('@?[_' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl + ']' + + '[' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl + uni.Nd + + uni.Pc + uni.Cf + uni.Mn + uni.Mc + ']*') + kt_id = '(' + kt_name + '|`' + kt_name + '`)' - tokens = {} - token_variants = True - - for levelname, cs_ident in levels.items(): - tokens[levelname] = { - 'root': [ - # method names - (r'^([ \t]*(?:' + cs_ident + r'(?:\[\])?\s+)+?)' # return type - r'(' + cs_ident + ')' # method name - r'(\s*)(\()', # signature start - bygroups(using(this), Name.Function, Text, Punctuation)), - (r'^\s*\[.*?\]', Name.Attribute), - (r'[^\S\n]+', Text), - (r'\\\n', Text), # line continuation - (r'//.*?\n', Comment.Single), - (r'/[*](.|\n)*?[*]/', Comment.Multiline), - (r'\n', Text), - (r'[~!%^&*()+=|\[\]:;,.<>/?-]', Punctuation), - (r'[{}]', Punctuation), - (r'@"(""|[^"])*"', String), - (r'"(\\\\|\\"|[^"\n])*["\n]', String), - (r"'\\.'|'[^\\]'", String.Char), - (r"[0-9](\.[0-9]*)?([eE][+-][0-9]+)?" - r"[flFLdD]?|0[xX][0-9a-fA-F]+[Ll]?", Number), - (r'#[ \t]*(if|endif|else|elif|define|undef|' - r'line|error|warning|region|endregion|pragma)\b.*?\n', - Comment.Preproc), - (r'\b(extern)(\s+)(alias)\b', bygroups(Keyword, Text, - Keyword)), - (r'(abstract|as|break|catch|' - r'fun|continue|default|delegate|' - r'do|else|enum|extern|false|finally|' - r'fixed|for|goto|if|implicit|in|interface|' - r'internal|is|lock|null|' - r'out|override|private|protected|public|readonly|' - r'ref|return|sealed|sizeof|' - r'when|this|throw|true|try|typeof|' - r'unchecked|unsafe|virtual|void|while|' - r'get|set|new|partial|yield|val|var)\b', Keyword), - (r'(global)(::)', bygroups(Keyword, Punctuation)), - (r'(bool|byte|char|decimal|double|dynamic|float|int|long|' - r'short)\b\??', Keyword.Type), - (r'(class|struct)(\s+)', bygroups(Keyword, Text), 'class'), - (r'(package|using)(\s+)', bygroups(Keyword, Text), 'package'), - (cs_ident, Name), - ], - 'class': [ - (cs_ident, Name.Class, '#pop') - ], - 'package': [ - (r'(?=\()', Text, '#pop'), # using (resource) - ('(' + cs_ident + r'|\.)+', Name.Namespace, '#pop') - ] - } - - def __init__(self, **options): - level = get_choice_opt(options, 'unicodelevel', self.tokens.keys(), - 'basic') - if level not in self._all_tokens: - # compile the regexes now - self._tokens = self.__class__.process_tokendef(level) - else: - self._tokens = self._all_tokens[level] - - RegexLexer.__init__(self, **options) + tokens = { + 'root': [ + (r'^\s*\[.*?\]', Name.Attribute), + (r'[^\S\n]+', Text), + (r'\\\n', Text), # line continuation + (r'//.*?\n', Comment.Single), + (r'/[*].*?[*]/', Comment.Multiline), + (r'\n', Text), + (r'::|!!|\?[:.]', Operator), + (r'[~!%^&*()+=|\[\]:;,.<>/?-]', Punctuation), + (r'[{}]', Punctuation), + (r'@"(""|[^"])*"', String), + (r'"(\\\\|\\"|[^"\n])*["\n]', String), + (r"'\\.'|'[^\\]'", String.Char), + (r"[0-9](\.[0-9]*)?([eE][+-][0-9]+)?[flFL]?|" + r"0[xX][0-9a-fA-F]+[Ll]?", Number), + (r'(class)(\s+)(object)', bygroups(Keyword, Text, Keyword)), + (r'(class|trait|object)(\s+)', bygroups(Keyword, Text), 'class'), + (r'(package|import)(\s+)', bygroups(Keyword, Text), 'package'), + (r'(val|var)(\s+)', bygroups(Keyword, Text), 'property'), + (r'(fun)(\s+)', bygroups(Keyword, Text), 'function'), + (r'(abstract|annotation|as|break|by|catch|class|continue|do|else|' + r'enum|false|final|finally|for|fun|get|if|import|in|inner|' + r'internal|is|null|object|open|out|override|package|private|' + r'protected|public|reified|return|set|super|this|throw|trait|' + r'true|try|type|val|var|vararg|when|where|while|This)\b', Keyword), + (kt_id, Name), + ], + 'package': [ + (r'\S+', Name.Namespace, '#pop') + ], + 'class': [ + (kt_id, Name.Class, '#pop') + ], + 'property': [ + (kt_id, Name.Property, '#pop') + ], + 'function': [ + (kt_id, Name.Function, '#pop') + ], + } class XtendLexer(RegexLexer): diff --git a/pygments/lexers/other.py b/pygments/lexers/other.py index 10598fb4..6c5075a3 100644 --- a/pygments/lexers/other.py +++ b/pygments/lexers/other.py @@ -1780,6 +1780,7 @@ class GherkinLexer(RegexLexer): 'examples_table_header': [ (r"\s+\|\s*$", Keyword, "#pop:2"), include('comments'), + (r"\\\|", Name.Variable), (r"\s*\|", Keyword), (r"[^\|]", Name.Variable), ], @@ -1822,6 +1823,7 @@ class GherkinLexer(RegexLexer): 'table_content': [ (r"\s+\|\s*$", Keyword, "#pop"), include('comments'), + (r"\\\|", String), (r"\s*\|", Keyword), include('string'), ], diff --git a/pygments/lexers/web.py b/pygments/lexers/web.py index 142fef57..e2a12046 100644 --- a/pygments/lexers/web.py +++ b/pygments/lexers/web.py @@ -2442,10 +2442,10 @@ class CoffeeScriptLexer(RegexLexer): #(r'^(?=\s|/|<!--)', Text, 'slashstartsregex'), include('commentsandwhitespace'), (r'\+\+|~|&&|\band\b|\bor\b|\bis\b|\bisnt\b|\bnot\b|\?|:|' - r'\|\||\\(?=\n)|(<<|>>>?|==?|!=?|' - r'=(?!>)|-(?!>)|[<>+*`%&\|\^/])=?', + r'\|\||\\(?=\n)|' + r'(<<|>>>?|==?(?!>)|!=?|=(?!>)|-(?!>)|[<>+*`%&\|\^/])=?', Operator, 'slashstartsregex'), - (r'(?:\([^()]+\))?\s*[=-]>', Name.Function), + (r'(?:\([^()]*\))?\s*[=-]>', Name.Function), (r'[{(\[;,]', Punctuation, 'slashstartsregex'), (r'[})\].]', Punctuation), (r'(?<![\.\$])(for|own|in|of|while|until|' |