diff options
Diffstat (limited to 'pygments/lexers/jvm.py')
| -rw-r--r-- | pygments/lexers/jvm.py | 154 |
1 files changed, 52 insertions, 102 deletions
diff --git a/pygments/lexers/jvm.py b/pygments/lexers/jvm.py index ed4d257c..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 @@ -38,11 +37,6 @@ class JavaLexer(RegexLexer): tokens = { 'root': [ - # method names - (r'^(\s*(?:[a-zA-Z_][a-zA-Z0-9_\.\[\]<>]*\s+)+?)' # return arguments - r'([a-zA-Z_][a-zA-Z0-9_]*)' # method name - r'(\s*)(\()', # signature start - bygroups(using(this), Name.Function, Text, Operator)), (r'[^\S\n]+', Text), (r'//.*?\n', Comment.Single), (r'/\*.*?\*/', Comment.Multiline), @@ -55,6 +49,11 @@ class JavaLexer(RegexLexer): r'transient|volatile)\b', Keyword.Declaration), (r'(boolean|byte|char|double|float|int|long|short|void)\b', Keyword.Type), + # method names + (r'^(\s*(?:[a-zA-Z_][a-zA-Z0-9_\.\[\]<>]*\s+)+?)' # return arguments + r'([a-zA-Z_][a-zA-Z0-9_]*)' # method name + r'(\s*)(\()', # signature start + bygroups(using(this), Name.Function, Text, Operator)), (r'(package)(\s+)', bygroups(Keyword.Namespace, Text)), (r'(true|false|null)\b', Keyword.Constant), (r'(class|interface)(\s+)', bygroups(Keyword.Declaration, Text), 'class'), @@ -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): |