diff options
author | nkozlovskiy <nmk@ydb.tech> | 2023-09-29 12:24:06 +0300 |
---|---|---|
committer | nkozlovskiy <nmk@ydb.tech> | 2023-09-29 12:41:34 +0300 |
commit | e0e3e1717e3d33762ce61950504f9637a6e669ed (patch) | |
tree | bca3ff6939b10ed60c3d5c12439963a1146b9711 /contrib/python/Pygments/py2/pygments/lexers/ruby.py | |
parent | 38f2c5852db84c7b4d83adfcb009eb61541d1ccd (diff) | |
download | ydb-e0e3e1717e3d33762ce61950504f9637a6e669ed.tar.gz |
add ydb deps
Diffstat (limited to 'contrib/python/Pygments/py2/pygments/lexers/ruby.py')
-rw-r--r-- | contrib/python/Pygments/py2/pygments/lexers/ruby.py | 519 |
1 files changed, 519 insertions, 0 deletions
diff --git a/contrib/python/Pygments/py2/pygments/lexers/ruby.py b/contrib/python/Pygments/py2/pygments/lexers/ruby.py new file mode 100644 index 0000000000..8bcbde6714 --- /dev/null +++ b/contrib/python/Pygments/py2/pygments/lexers/ruby.py @@ -0,0 +1,519 @@ +# -*- coding: utf-8 -*- +""" + pygments.lexers.ruby + ~~~~~~~~~~~~~~~~~~~~ + + Lexers for Ruby and related languages. + + :copyright: Copyright 2006-2019 by the Pygments team, see AUTHORS. + :license: BSD, see LICENSE for details. +""" + +import re + +from pygments.lexer import Lexer, RegexLexer, ExtendedRegexLexer, include, \ + bygroups, default, LexerContext, do_insertions, words +from pygments.token import Text, Comment, Operator, Keyword, Name, String, \ + Number, Punctuation, Error, Generic +from pygments.util import shebang_matches + +__all__ = ['RubyLexer', 'RubyConsoleLexer', 'FancyLexer'] + +line_re = re.compile('.*?\n') + + +RUBY_OPERATORS = ( + '*', '**', '-', '+', '-@', '+@', '/', '%', '&', '|', '^', '`', '~', + '[]', '[]=', '<<', '>>', '<', '<>', '<=>', '>', '>=', '==', '===' +) + + +class RubyLexer(ExtendedRegexLexer): + """ + For `Ruby <http://www.ruby-lang.org>`_ source code. + """ + + name = 'Ruby' + aliases = ['rb', 'ruby', 'duby'] + filenames = ['*.rb', '*.rbw', 'Rakefile', '*.rake', '*.gemspec', + '*.rbx', '*.duby', 'Gemfile'] + mimetypes = ['text/x-ruby', 'application/x-ruby'] + + flags = re.DOTALL | re.MULTILINE + + def heredoc_callback(self, match, ctx): + # okay, this is the hardest part of parsing Ruby... + # match: 1 = <<[-~]?, 2 = quote? 3 = name 4 = quote? 5 = rest of line + + start = match.start(1) + yield start, Operator, match.group(1) # <<[-~]? + yield match.start(2), String.Heredoc, match.group(2) # quote ", ', ` + yield match.start(3), String.Delimiter, match.group(3) # heredoc name + yield match.start(4), String.Heredoc, match.group(4) # quote again + + heredocstack = ctx.__dict__.setdefault('heredocstack', []) + outermost = not bool(heredocstack) + heredocstack.append((match.group(1) in ('<<-', '<<~'), match.group(3))) + + ctx.pos = match.start(5) + ctx.end = match.end(5) + # this may find other heredocs + for i, t, v in self.get_tokens_unprocessed(context=ctx): + yield i, t, v + ctx.pos = match.end() + + if outermost: + # this is the outer heredoc again, now we can process them all + for tolerant, hdname in heredocstack: + lines = [] + for match in line_re.finditer(ctx.text, ctx.pos): + if tolerant: + check = match.group().strip() + else: + check = match.group().rstrip() + if check == hdname: + for amatch in lines: + yield amatch.start(), String.Heredoc, amatch.group() + yield match.start(), String.Delimiter, match.group() + ctx.pos = match.end() + break + else: + lines.append(match) + else: + # end of heredoc not found -- error! + for amatch in lines: + yield amatch.start(), Error, amatch.group() + ctx.end = len(ctx.text) + del heredocstack[:] + + def gen_rubystrings_rules(): + def intp_regex_callback(self, match, ctx): + 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]* + ctx.pos = match.end() + + def intp_string_callback(self, match, ctx): + yield match.start(1), String.Other, match.group(1) + 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 + ctx.pos = match.end() + + states = {} + states['strings'] = [ + # easy ones + (r'\:@{0,2}[a-zA-Z_]\w*[!?]?', String.Symbol), + (words(RUBY_OPERATORS, prefix=r'\:@{0,2}'), String.Symbol), + (r":'(\\\\|\\'|[^'])*'", String.Symbol), + (r"'(\\\\|\\'|[^'])*'", String.Single), + (r':"', String.Symbol, 'simple-sym'), + (r'([a-zA-Z_]\w*)(:)(?!:)', + bygroups(String.Symbol, Punctuation)), # Since Ruby 1.9 + (r'"', String.Double, 'simple-string'), + (r'(?<!\.)`', String.Backtick, 'simple-backtick'), + ] + + # double-quoted string and symbol + for name, ttype, end in ('string', String.Double, '"'), \ + ('sym', String.Symbol, '"'), \ + ('backtick', String.Backtick, '`'): + states['simple-'+name] = [ + include('string-intp-escaped'), + (r'[^\\%s#]+' % end, ttype), + (r'[\\#]', ttype), + (end, ttype, '#pop'), + ] + + # braced quoted strings + for lbrace, rbrace, bracecc, name in \ + ('\\{', '\\}', '{}', 'cb'), \ + ('\\[', '\\]', '\\[\\]', 'sb'), \ + ('\\(', '\\)', '()', 'pa'), \ + ('<', '>', '<>', 'ab'): + states[name+'-intp-string'] = [ + (r'\\[\\' + bracecc + ']', String.Other), + (lbrace, String.Other, '#push'), + (rbrace, String.Other, '#pop'), + include('string-intp-escaped'), + (r'[\\#' + bracecc + ']', String.Other), + (r'[^\\#' + bracecc + ']+', String.Other), + ] + states['strings'].append((r'%[QWx]?' + lbrace, String.Other, + name+'-intp-string')) + states[name+'-string'] = [ + (r'\\[\\' + bracecc + ']', String.Other), + (lbrace, String.Other, '#push'), + (rbrace, String.Other, '#pop'), + (r'[\\#' + bracecc + ']', String.Other), + (r'[^\\#' + bracecc + ']+', String.Other), + ] + states['strings'].append((r'%[qsw]' + lbrace, String.Other, + name+'-string')) + states[name+'-regex'] = [ + (r'\\[\\' + bracecc + ']', String.Regex), + (lbrace, String.Regex, '#push'), + (rbrace + '[mixounse]*', String.Regex, '#pop'), + include('string-intp'), + (r'[\\#' + bracecc + ']', String.Regex), + (r'[^\\#' + bracecc + ']+', String.Regex), + ] + states['strings'].append((r'%r' + lbrace, String.Regex, + name+'-regex')) + + # these must come after %<brace>! + states['strings'] += [ + # %r regex + (r'(%r([\W_]))((?:\\\2|(?!\2).)*)(\2[mixounse]*)', + intp_regex_callback), + # regular fancy strings with qsw + (r'%[qsw]([\W_])((?:\\\1|(?!\1).)*)\1', String.Other), + (r'(%[QWx]([\W_]))((?:\\\2|(?!\2).)*)(\2)', + intp_string_callback), + # special forms of fancy strings after operators or + # in method calls with braces + (r'(?<=[-+/*%=<>&!^|~,(])(\s*)(%([\t ])(?:(?:\\\3|(?!\3).)*)\3)', + bygroups(Text, String.Other, None)), + # and because of fixed width lookbehinds the whole thing a + # second time for line startings... + (r'^(\s*)(%([\t ])(?:(?:\\\3|(?!\3).)*)\3)', + bygroups(Text, String.Other, None)), + # all regular fancy strings without qsw + (r'(%([^a-zA-Z0-9\s]))((?:\\\2|(?!\2).)*)(\2)', + intp_string_callback), + ] + + return states + + tokens = { + 'root': [ + (r'\A#!.+?$', Comment.Hashbang), + (r'#.*?$', Comment.Single), + (r'=begin\s.*?\n=end.*?$', Comment.Multiline), + # keywords + (words(( + 'BEGIN', 'END', 'alias', 'begin', 'break', 'case', 'defined?', + 'do', 'else', 'elsif', 'end', 'ensure', 'for', 'if', 'in', 'next', 'redo', + 'rescue', 'raise', 'retry', 'return', 'super', 'then', 'undef', + 'unless', 'until', 'when', 'while', 'yield'), suffix=r'\b'), + Keyword), + # start of function, class and module names + (r'(module)(\s+)([a-zA-Z_]\w*' + r'(?:::[a-zA-Z_]\w*)*)', + bygroups(Keyword, Text, Name.Namespace)), + (r'(def)(\s+)', bygroups(Keyword, Text), 'funcname'), + (r'def(?=[*%&^`~+-/\[<>=])', Keyword, 'funcname'), + (r'(class)(\s+)', bygroups(Keyword, Text), 'classname'), + # special methods + (words(( + 'initialize', 'new', 'loop', 'include', 'extend', 'raise', 'attr_reader', + 'attr_writer', 'attr_accessor', 'attr', 'catch', 'throw', 'private', + 'module_function', 'public', 'protected', 'true', 'false', 'nil'), + suffix=r'\b'), + Keyword.Pseudo), + (r'(not|and|or)\b', Operator.Word), + (words(( + 'autoload', 'block_given', 'const_defined', 'eql', 'equal', 'frozen', 'include', + 'instance_of', 'is_a', 'iterator', 'kind_of', 'method_defined', 'nil', + 'private_method_defined', 'protected_method_defined', + 'public_method_defined', 'respond_to', 'tainted'), suffix=r'\?'), + Name.Builtin), + (r'(chomp|chop|exit|gsub|sub)!', Name.Builtin), + (words(( + 'Array', 'Float', 'Integer', 'String', '__id__', '__send__', 'abort', + 'ancestors', 'at_exit', 'autoload', 'binding', 'callcc', 'caller', + 'catch', 'chomp', 'chop', 'class_eval', 'class_variables', + 'clone', 'const_defined?', 'const_get', 'const_missing', 'const_set', + 'constants', 'display', 'dup', 'eval', 'exec', 'exit', 'extend', 'fail', 'fork', + 'format', 'freeze', 'getc', 'gets', 'global_variables', 'gsub', + 'hash', 'id', 'included_modules', 'inspect', 'instance_eval', + 'instance_method', 'instance_methods', + 'instance_variable_get', 'instance_variable_set', 'instance_variables', + 'lambda', 'load', 'local_variables', 'loop', + 'method', 'method_missing', 'methods', 'module_eval', 'name', + 'object_id', 'open', 'p', 'print', 'printf', 'private_class_method', + 'private_instance_methods', + 'private_methods', 'proc', 'protected_instance_methods', + 'protected_methods', 'public_class_method', + 'public_instance_methods', 'public_methods', + 'putc', 'puts', 'raise', 'rand', 'readline', 'readlines', 'require', + 'scan', 'select', 'self', 'send', 'set_trace_func', 'singleton_methods', 'sleep', + 'split', 'sprintf', 'srand', 'sub', 'syscall', 'system', 'taint', + 'test', 'throw', 'to_a', 'to_s', 'trace_var', 'trap', 'untaint', + 'untrace_var', 'warn'), prefix=r'(?<!\.)', suffix=r'\b'), + Name.Builtin), + (r'__(FILE|LINE)__\b', Name.Builtin.Pseudo), + # normal heredocs + (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'(?<=(?:\s|;)when\s)|' + r'(?<=(?:\s|;)or\s)|' + r'(?<=(?:\s|;)and\s)|' + r'(?<=\.index\s)|' + r'(?<=\.scan\s)|' + r'(?<=\.sub\s)|' + r'(?<=\.sub!\s)|' + r'(?<=\.gsub\s)|' + r'(?<=\.gsub!\s)|' + r'(?<=\.match\s)|' + r'(?<=(?:\s|;)if\s)|' + r'(?<=(?:\s|;)elsif\s)|' + r'(?<=^when\s)|' + r'(?<=^index\s)|' + r'(?<=^scan\s)|' + r'(?<=^sub\s)|' + r'(?<=^gsub\s)|' + r'(?<=^sub!\s)|' + r'(?<=^gsub!\s)|' + r'(?<=^match\s)|' + r'(?<=^if\s)|' + r'(?<=^elsif\s)' + r')(\s*)(/)', bygroups(Text, 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=])', 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?) + # since pygments 0.7 we also eat a "?" operator after numbers + # so that the char operator does not work. Chars are not allowed + # there so that you can use the ternary operator. + # stupid example: + # x>=0?n[x]:"" + (r'(0_?[0-7]+(?:_[0-7]+)*)(\s*)([/?])?', + bygroups(Number.Oct, Text, Operator)), + (r'(0x[0-9A-Fa-f]+(?:_[0-9A-Fa-f]+)*)(\s*)([/?])?', + bygroups(Number.Hex, Text, Operator)), + (r'(0b[01]+(?:_[01]+)*)(\s*)([/?])?', + bygroups(Number.Bin, Text, Operator)), + (r'([\d]+(?:_\d+)*)(\s*)([/?])?', + bygroups(Number.Integer, Text, Operator)), + # Names + (r'@@[a-zA-Z_]\w*', Name.Variable.Class), + (r'@[a-zA-Z_]\w*', Name.Variable.Instance), + (r'\$\w+', Name.Variable.Global), + (r'\$[!@&`\'+~=/\\,;.<>_*$?:"^-]', Name.Variable.Global), + (r'\$-[0adFiIlpvw]', Name.Variable.Global), + (r'::', Operator), + include('strings'), + # chars + (r'\?(\\[MC]-)*' # modifiers + r'(\\([\\abefnrstv#"\']|x[a-fA-F0-9]{1,2}|[0-7]{1,3})|\S)' + r'(?!\w)', + String.Char), + (r'[A-Z]\w+', Name.Constant), + # this is needed because ruby attributes can look + # like keywords (class) or like this: ` ?!? + (words(RUBY_OPERATORS, prefix=r'(\.|::)'), + bygroups(Operator, Name.Operator)), + (r'(\.|::)([a-zA-Z_]\w*[!?]?|[*%&^`~+\-/\[<>=])', + bygroups(Operator, Name)), + (r'[a-zA-Z_]\w*[!?]?', Name), + (r'(\[|\]|\*\*|<<?|>>?|>=|<=|<=>|=~|={3}|' + r'!~|&&?|\|\||\.{1,3})', Operator), + (r'[-+/*%=<>&!^|~]=?', Operator), + (r'[(){};,/?:\\]', Punctuation), + (r'\s+', Text) + ], + 'funcname': [ + (r'\(', Punctuation, 'defexpr'), + (r'(?:([a-zA-Z_]\w*)(\.))?' + r'([a-zA-Z_]\w*[!?]?|\*\*?|[-+]@?|' + r'[/%&|^`~]|\[\]=?|<<|>>|<=?>|>=?|===?)', + bygroups(Name.Class, Operator, Name.Function), '#pop'), + default('#pop') + ], + 'classname': [ + (r'\(', Punctuation, 'defexpr'), + (r'<<', Operator, '#pop'), + (r'[A-Z_]\w*', Name.Class, '#pop'), + default('#pop') + ], + 'defexpr': [ + (r'(\))(\.|::)?', bygroups(Punctuation, Operator), '#pop'), + (r'\(', Operator, '#push'), + include('root') + ], + 'in-intp': [ + (r'\{', String.Interpol, '#push'), + (r'\}', String.Interpol, '#pop'), + include('root'), + ], + 'string-intp': [ + (r'#\{', String.Interpol, 'in-intp'), + (r'#@@?[a-zA-Z_]\w*', String.Interpol), + (r'#\$[a-zA-Z_]\w*', String.Interpol) + ], + 'string-intp-escaped': [ + include('string-intp'), + (r'\\([\\abefnrstv#"\']|x[a-fA-F0-9]{1,2}|[0-7]{1,3})', + String.Escape) + ], + 'interpolated-regex': [ + include('string-intp'), + (r'[\\#]', String.Regex), + (r'[^\\#]+', String.Regex), + ], + 'interpolated-string': [ + include('string-intp'), + (r'[\\#]', String.Other), + (r'[^\\#]+', String.Other), + ], + 'multiline-regex': [ + include('string-intp'), + (r'\\\\', String.Regex), + (r'\\/', String.Regex), + (r'[\\#]', String.Regex), + (r'[^\\/#]+', String.Regex), + (r'/[mixounse]*', String.Regex, '#pop'), + ], + 'end-part': [ + (r'.+', Comment.Preproc, '#pop') + ] + } + tokens.update(gen_rubystrings_rules()) + + def analyse_text(text): + return shebang_matches(text, r'ruby(1\.\d)?') + + +class RubyConsoleLexer(Lexer): + """ + For Ruby interactive console (**irb**) output like: + + .. sourcecode:: rbcon + + irb(main):001:0> a = 1 + => 1 + irb(main):002:0> puts a + 1 + => nil + """ + name = 'Ruby irb session' + aliases = ['rbcon', 'irb'] + mimetypes = ['text/x-ruby-shellsession'] + + _prompt_re = re.compile(r'irb\([a-zA-Z_]\w*\):\d{3}:\d+[>*"\'] ' + r'|>> |\?> ') + + def get_tokens_unprocessed(self, text): + rblexer = RubyLexer(**self.options) + + curcode = '' + insertions = [] + for match in line_re.finditer(text): + line = match.group() + m = self._prompt_re.match(line) + if m is not None: + end = m.end() + insertions.append((len(curcode), + [(0, Generic.Prompt, line[:end])])) + curcode += line[end:] + else: + if curcode: + for item in do_insertions( + insertions, rblexer.get_tokens_unprocessed(curcode)): + yield item + curcode = '' + insertions = [] + yield match.start(), Generic.Output, line + if curcode: + for item in do_insertions( + insertions, rblexer.get_tokens_unprocessed(curcode)): + yield item + + +class FancyLexer(RegexLexer): + """ + 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. + + .. versionadded:: 1.5 + """ + name = 'Fancy' + filenames = ['*.fy', '*.fancypack'] + aliases = ['fancy', 'fy'] + mimetypes = ['text/x-fancysrc'] + + tokens = { + # 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), + + # 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 + (words(( + 'Object', 'Array', 'Hash', 'Directory', 'File', 'Class', 'String', + 'Number', 'Enumerable', 'FancyEnumerable', 'Block', 'TrueClass', + 'NilClass', 'FalseClass', 'Tuple', 'Symbol', 'Stack', 'Set', + 'FancySpec', 'Method', 'Package', 'Range'), suffix=r'\b'), + Name.Builtin), + # functions + (r'[a-zA-Z](\w|[-+?!=*/^><%])*:', Name.Function), + # operators, must be below functions + (r'[-+*/~,<>=&!?%^\[\].$]+', Operator), + (r'[A-Z]\w*', Name.Constant), + (r'@[a-zA-Z_]\w*', Name.Variable.Instance), + (r'@@[a-zA-Z_]\w*', Name.Variable.Class), + ('@@?', Operator), + (r'[a-zA-Z_]\w*', 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) + ] + } |