rugments 1.0.0.beta1

data/lib/rugments/lexers/go.rb

@@ -0,0 +1,176 @@
+module Rugments
+  module Lexers
+    class Go < RegexLexer
+      title 'Go'
+      desc 'The Go programming language (http://golang.org)'
+      tag 'go'
+      aliases 'go', 'golang'
+      filenames '*.go'
+
+      mimetypes 'text/x-go', 'application/x-go'
+
+      def self.analyze_text(_text)
+        0
+      end
+
+      # Characters
+
+      WHITE_SPACE            = /[\s\t\r\n]+/
+
+      NEWLINE                = /\n/
+      UNICODE_CHAR           = /[^\n]/
+      UNICODE_LETTER         = /[[:alpha:]]/
+      UNICODE_DIGIT          = /[[:digit:]]/
+
+      # Letters and digits
+
+      LETTER                 = /#{UNICODE_LETTER}|_/
+      DECIMAL_DIGIT          = /[0-9]/
+      OCTAL_DIGIT            = /[0-7]/
+      HEX_DIGIT              = /[0-9A-Fa-f]/
+
+      # Comments
+
+      LINE_COMMENT           = /\/\/(?:(?!#{NEWLINE}).)*/
+      GENERAL_COMMENT        = /\/\*(?:(?!\*\/).)*\*\//m
+      COMMENT                = /#{LINE_COMMENT}|#{GENERAL_COMMENT}/
+
+      # Keywords
+
+      KEYWORD                = /\b(?:
+                                 break       | default     | func
+                               | interface   | select      | case
+                               | defer       | go          | map
+                               | struct      | chan        | else
+                               | goto        | package     | switch
+                               | const       | fallthrough | if
+                               | range       | type        | continue
+                               | for         | import      | return
+                               | var
+                               )\b/x
+
+      # Identifiers
+
+      IDENTIFIER             = / (?!#{KEYWORD})
+                                 #{LETTER}(?:#{LETTER}|#{UNICODE_DIGIT})* /x
+
+      # Operators and delimiters
+
+      OPERATOR               = / \+=    | \+\+   | \+     | &\^=   | &\^
+                               | &=     | &&     | &      | ==     | =
+                               | \!=    | \!     | -=     | --     | -
+                               | \|=    | \|\|   | \|     | <=     | <-
+                               | <<=    | <<     | <      | \*=    | \*
+                               | \^=    | \^     | >>=    | >>     | >=
+                               | >      | \/     | \/=    | :=     | %
+                               | %=     | \.\.\. | \.     | :
+                               /x
+
+      SEPARATOR              = / \(     | \)     | \[     | \]     | \{
+                               | \}     | ,      | ;
+                               /x
+
+      # Integer literals
+
+      DECIMAL_LIT            = /[0-9]#{DECIMAL_DIGIT}*/
+      OCTAL_LIT              = /0#{OCTAL_DIGIT}*/
+      HEX_LIT                = /0[xX]#{HEX_DIGIT}+/
+      INT_LIT                = /#{HEX_LIT}|#{DECIMAL_LIT}|#{OCTAL_LIT}/
+
+      # Floating-point literals
+
+      DECIMALS               = /#{DECIMAL_DIGIT}+/
+      EXPONENT               = /[eE][+\-]?#{DECIMALS}/
+      FLOAT_LIT              = / #{DECIMALS} \. #{DECIMALS}? #{EXPONENT}?
+                               | #{DECIMALS} #{EXPONENT}
+                               | \. #{DECIMALS} #{EXPONENT}?
+                               /x
+
+      # Imaginary literals
+
+      IMAGINARY_LIT          = /(?:#{DECIMALS}|#{FLOAT_LIT})i/
+
+      # Rune literals
+
+      ESCAPED_CHAR           = /\\[abfnrtv\\'"]/
+      LITTLE_U_VALUE         = /\\u#{HEX_DIGIT}{4}/
+      BIG_U_VALUE            = /\\U#{HEX_DIGIT}{8}/
+      UNICODE_VALUE          = / #{UNICODE_CHAR} | #{LITTLE_U_VALUE}
+                               | #{BIG_U_VALUE}  | #{ESCAPED_CHAR}
+                               /x
+      OCTAL_BYTE_VALUE       = /\\#{OCTAL_DIGIT}{3}/
+      HEX_BYTE_VALUE         = /\\x#{HEX_DIGIT}{2}/
+      BYTE_VALUE             = /#{OCTAL_BYTE_VALUE}|#{HEX_BYTE_VALUE}/
+      CHAR_LIT               = /'(?:#{UNICODE_VALUE}|#{BYTE_VALUE})'/
+      ESCAPE_SEQUENCE        = / #{ESCAPED_CHAR}
+                               | #{LITTLE_U_VALUE}
+                               | #{BIG_U_VALUE}
+                               | #{HEX_BYTE_VALUE}
+                               /x
+
+      # String literals
+
+      RAW_STRING_LIT         = /`(?:#{UNICODE_CHAR}|#{NEWLINE})*`/
+      INTERPRETED_STRING_LIT = / "(?: (?!")
+                                      (?: #{UNICODE_VALUE} | #{BYTE_VALUE} )
+                                  )*" /x
+      STRING_LIT             = /#{RAW_STRING_LIT}|#{INTERPRETED_STRING_LIT}/
+
+      # Predeclared identifiers
+
+      PREDECLARED_TYPES      = /\b(?:
+                                 bool       | byte       | complex64
+                               | complex128 | error      | float32
+                               | float64    | int8       | int16
+                               | int32      | int64      | int
+                               | rune       | string     | uint8
+                               | uint16     | uint32     | uint64
+                               | uintptr    | uint
+                               )\b/x
+
+      PREDECLARED_CONSTANTS  = /\b(?:true|false|iota|nil)\b/
+
+      PREDECLARED_FUNCTIONS  = /\b(?:
+                                 append  | cap     | close   | complex
+                               | copy    | delete  | imag    | len
+                               | make    | new     | panic   | print
+                               | println | real    | recover
+                               )\b/x
+
+      state :simple_tokens do
+        rule(COMMENT,               Comment)
+        rule(KEYWORD,               Keyword)
+        rule(PREDECLARED_TYPES,     Keyword::Type)
+        rule(PREDECLARED_FUNCTIONS, Name::Builtin)
+        rule(PREDECLARED_CONSTANTS, Name::Constant)
+        rule(IMAGINARY_LIT,         Num)
+        rule(FLOAT_LIT,             Num)
+        rule(INT_LIT,               Num)
+        rule(CHAR_LIT,              Str::Char)
+        rule(OPERATOR,              Operator)
+        rule(SEPARATOR,             Punctuation)
+        rule(IDENTIFIER,            Name)
+        rule(WHITE_SPACE,           Other)
+      end
+
+      state :root do
+        mixin :simple_tokens
+
+        rule(/`/,             Str, :raw_string)
+        rule(/"/,             Str, :interpreted_string)
+      end
+
+      state :interpreted_string do
+        rule(ESCAPE_SEQUENCE, Str::Escape)
+        rule(/\\./,           Error)
+        rule(/"/,             Str, :pop!)
+        rule(/[^"\\]+/,       Str)
+      end
+
+      state :raw_string do
+        rule(/`/,             Str, :pop!)
+        rule(/[^`]+/m,        Str)
+      end
+    end
+  end
+end

data/lib/rugments/lexers/groovy.rb

@@ -0,0 +1,102 @@
+module Rugments
+  module Lexers
+    class Groovy < RegexLexer
+      title 'Groovy'
+      desc 'The Groovy programming language (groovy.codehaus.org)'
+      tag 'groovy'
+      filenames '*.groovy'
+      mimetypes 'text/x-groovy'
+
+      ws = %r{(?:\s|//.*?\n|/[*].*?[*]/)+}
+
+      def self.keywords
+        @keywords ||= Set.new %w(
+          assert break case catch continue default do else finally for
+          if goto instanceof new return switch this throw try while in as
+        )
+      end
+
+      def self.declarations
+        @declarations ||= Set.new %w(
+          abstract const enum extends final implements native private
+          protected public static strictfp super synchronized throws
+          transient volatile
+        )
+      end
+
+      def self.types
+        @types ||= Set.new %w(
+          def boolean byte char double float int long short void
+        )
+      end
+
+      def self.constants
+        @constants ||= Set.new %w(true false null)
+      end
+
+      state :root do
+        rule %r{^
+          (\s*(?:\w[\w\d.\[\]]*\s+)+?) # return arguments
+          (\w[\w\d]*) # method name
+          (\s*) (\() # signature start
+                }x do |m|
+          delegate clone, m[1]
+          token Name::Function, m[2]
+          token Text, m[3]
+          token Operator, m[4]
+        end
+
+        # whitespace
+        rule /[^\S\n]+/, Text
+        rule %r{//.*?\n}, Comment::Single
+        rule %r{/[*].*?[*]/}m, Comment::Multiline
+        rule /@\w[\w\d.]*/, Name::Decorator
+        rule /(class|interface)\b/,  Keyword::Declaration, :class
+        rule /package\b/, Keyword::Namespace, :import
+        rule /import\b/, Keyword::Namespace, :import
+
+        rule /"(\\\\|\\"|[^"])*"/, Str::Double
+        rule /'(\\\\|\\'|[^'])*'/, Str::Single
+        rule %r{\$/((?!/\$).)*/\$}, Str
+        rule %r{/(\\\\|\\"|[^/])*/}, Str
+        rule /'\\.'|'[^\\]'|'\\u[0-9a-f]{4}'/, Str::Char
+        rule /(\.)([a-zA-Z_][a-zA-Z0-9_]*)/ do
+          groups Operator, Name::Attribute
+        end
+
+        rule /[a-zA-Z_][a-zA-Z0-9_]*:/, Name::Label
+        rule /[a-zA-Z_\$][a-zA-Z0-9_]*/ do |m|
+          if self.class.keywords.include? m[0]
+            token Keyword
+          elsif self.class.declarations.include? m[0]
+            token Keyword::Declaration
+          elsif self.class.types.include? m[0]
+            token Keyword::Type
+          elsif self.class.constants.include? m[0]
+            token Keyword::Constant
+          else
+            token Name
+          end
+        end
+
+        rule %r([~^*!%&\[\](){}<>\|+=:;,./?-]), Operator
+
+        # numbers
+        rule /\d+\.\d+([eE]\d+)?[fd]?/, Num::Float
+        rule /0x[0-9a-f]+/, Num::Hex
+        rule /[0-9]+L?/, Num::Integer
+        rule /\n/, Text
+      end
+
+      state :class do
+        rule /\s+/, Text
+        rule /\w[\w\d]*/, Name::Class, :pop!
+      end
+
+      state :import do
+        rule /\s+/, Text
+        rule /[\w\d.]+[*]?/, Name::Namespace, :pop!
+      end
+    end
+  end
+end

data/lib/rugments/lexers/haml.rb

@@ -0,0 +1,226 @@
+module Rugments
+  module Lexers
+    # A lexer for the Haml templating system for Ruby.
+    # @see http://haml.info
+    class Haml < RegexLexer
+      include Indentation
+
+      title 'Haml'
+      desc 'The Haml templating system for Ruby (haml.info)'
+
+      tag 'haml'
+      aliases 'HAML'
+
+      filenames '*.haml'
+      mimetypes 'text/x-haml'
+
+      def self.analyze_text(text)
+        return 0.1 if text.start_with? '!!!'
+      end
+
+      # @option opts :filters
+      #   A hash of filter name to lexer of how various filters should be
+      #   highlighted.  By default, :javascript, :css, :ruby, and :erb
+      #   are supported.
+      def initialize(opts = {})
+        (opts.delete(:filters) || {}).each do |name, lexer|
+          unless lexer.respond_to? :lex
+            lexer = Lexer.find(lexer) or fail "unknown lexer: #{lexer}"
+            lexer = lexer.new(options)
+          end
+
+          filters[name.to_s] = lexer
+        end
+
+        super(opts)
+      end
+
+      def ruby
+        @ruby ||= Ruby.new(options)
+      end
+
+      def html
+        @html ||= HTML.new(options)
+      end
+
+      def filters
+        @filters ||= {
+          'javascript' => Javascript.new(options),
+          'css' => CSS.new(options),
+          'ruby' => ruby,
+          'erb' => ERB.new(options),
+          'markdown' => Markdown.new(options),
+          # TODO
+          # 'sass' => Sass.new(options),
+          # 'textile' => Textile.new(options),
+          # 'maruku' => Maruku.new(options),
+        }
+      end
+
+      start { ruby.reset!; html.reset! }
+
+      identifier = /[\w:-]+/
+      ruby_var = /[a-z]\w*/
+
+      # Haml can include " |\n" anywhere,
+      # which is ignored and used to wrap long lines.
+      # To accomodate this, use this custom faux dot instead.
+      dot = /[ ]\|\n(?=.*[ ]\|)|./
+
+      # In certain places, a comma at the end of the line
+      # allows line wrapping as well.
+      comma_dot = /,\s*\n|#{dot}/
+
+      state :root do
+        rule /\s*\n/, Text
+        rule(/\s*/) { |m| token Text; indentation(m[0]) }
+      end
+
+      state :content do
+        mixin :css
+        rule(/%#{identifier}/) { token Name::Tag; goto :tag }
+        rule /!!!#{dot}*\n/, Name::Namespace, :pop!
+        rule %r{
+          (/) (\[#{dot}*?\]) (#{dot}*\n)
+                }x do
+          groups Comment, Comment::Special, Comment
+          pop!
+        end
+
+        rule %r{/#{dot}*\n} do
+          token Comment
+          pop!
+          starts_block :html_comment_block
+        end
+
+        rule /-##{dot}*\n/ do
+          token Comment
+          pop!
+          starts_block :haml_comment_block
+        end
+
+        rule /-/ do
+          token Punctuation
+          reset_stack
+          push :ruby_line
+        end
+
+        # filters
+        rule /:(#{dot}*)\n/ do |m|
+          token Name::Decorator
+          pop!
+          starts_block :filter_block
+
+          filter_name = m[1].strip
+
+          @filter_lexer = filters[filter_name]
+          @filter_lexer.reset! unless @filter_lexer.nil?
+
+          puts "    haml: filter #{filter_name.inspect} #{@filter_lexer.inspect}" if @debug
+        end
+
+        mixin :eval_or_plain
+      end
+
+      state :css do
+        rule(/\.#{identifier}/) { token Name::Class; goto :tag }
+        rule(/##{identifier}/) { token Name::Function; goto :tag }
+      end
+
+      state :tag do
+        mixin :css
+        rule(/\{#{comma_dot}*?\}/) { delegate ruby }
+        rule(/\[#{dot}*?\]/) { delegate ruby }
+        rule /\(/, Punctuation, :html_attributes
+        rule /\s*\n/, Text, :pop!
+
+        # whitespace chompers
+        rule /[<>]{1,2}(?=[ \t=])/, Punctuation
+
+        mixin :eval_or_plain
+      end
+
+      state :plain do
+        rule(/([^#\n]|#[^{\n]|(\\\\)*\\#\{)+/) { delegate html }
+        mixin :interpolation
+        rule(/\n/) { token Text; reset_stack }
+      end
+
+      state :eval_or_plain do
+        rule /[&!]?==/, Punctuation, :plain
+        rule /[&!]?[=!]/ do
+          token Punctuation
+          reset_stack
+          push :ruby_line
+        end
+
+        rule(//) { push :plain }
+      end
+
+      state :ruby_line do
+        rule /\n/, Text, :pop!
+        rule(/,[ \t]*\n/) { delegate ruby }
+        rule /[ ]\|[ \t]*\n/, Str::Escape
+        rule(/.*?(?=(,$| \|)?[ \t]*$)/) { delegate ruby }
+      end
+
+      state :html_attributes do
+        rule /\s+/, Text
+        rule /#{identifier}\s*=/, Name::Attribute, :html_attribute_value
+        rule identifier, Name::Attribute
+        rule /\)/, Text, :pop!
+      end
+
+      state :html_attribute_value do
+        rule /\s+/, Text
+        rule ruby_var, Name::Variable, :pop!
+        rule /@#{ruby_var}/, Name::Variable::Instance, :pop!
+        rule /\$#{ruby_var}/, Name::Variable::Global, :pop!
+        rule /'(\\\\|\\'|[^'\n])*'/, Str, :pop!
+        rule /"(\\\\|\\"|[^"\n])*"/, Str, :pop!
+      end
+
+      state :html_comment_block do
+        rule /#{dot}+/, Comment
+        mixin :indented_block
+      end
+
+      state :haml_comment_block do
+        rule /#{dot}+/, Comment::Preproc
+        mixin :indented_block
+      end
+
+      state :filter_block do
+        rule /([^#\n]|#[^{\n]|(\\\\)*\\#\{)+/ do
+          if @filter_lexer
+            delegate @filter_lexer
+          else
+            token Name::Decorator
+          end
+        end
+
+        mixin :interpolation
+        mixin :indented_block
+      end
+
+      state :interpolation do
+        rule /#[{]/, Str::Interpol, :ruby
+      end
+
+      state :ruby do
+        rule /[}]/, Str::Interpol, :pop!
+        mixin :ruby_inner
+      end
+
+      state :ruby_inner do
+        rule(/[{]/) { delegate ruby; push :ruby_inner }
+        rule(/[}]/) { delegate ruby; pop! }
+        rule(/[^{}]+/) { delegate ruby }
+      end
+
+      state :indented_block do
+        rule(/\n/) { token Text; reset_stack }
+      end
+    end
+  end
+end

data/lib/rugments/lexers/handlebars.rb

@@ -0,0 +1,77 @@
+module Rugments
+  module Lexers
+    class Handlebars < TemplateLexer
+      title 'Handlebars'
+      desc 'the Handlebars and Mustache templating languages'
+      tag 'handlebars'
+      aliases 'hbs', 'mustache'
+      filenames '*.handlebars', '*.hbs', '*.mustache'
+      mimetypes 'text/x-handlebars', 'text/x-mustache'
+
+      id = %r{[\w$-]+}
+
+      state :root do
+        # escaped slashes
+        rule(/\\{+/) { delegate parent }
+
+        # block comments
+        rule /{{!--/, Comment, :comment
+        rule /{{!.*?}}/, Comment
+
+        rule /{{{?/ do
+          token Keyword
+          push :stache
+          push :open_sym
+        end
+
+        rule(/(.+?)(?=\\|{{)/m) { delegate parent }
+
+        # if we get here, there's no more mustache tags, so we eat
+        # the rest of the doc
+        rule(/.+/m) { delegate parent }
+      end
+
+      state :comment do
+        rule(/{{/) { token Comment; push }
+        rule(/}}/) { token Comment; pop! }
+        rule(/[^{}]+/m) { token Comment }
+        rule(/[{}]/) { token Comment }
+      end
+
+      state :stache do
+        rule /}}}?/, Keyword, :pop!
+        rule /\s+/m, Text
+        rule /[=]/, Operator
+        rule /[\[\]]/, Punctuation
+        rule /[.](?=[}\s])/, Name::Variable
+        rule /[.][.]/, Name::Variable
+        rule %r{[/.]}, Punctuation
+        rule /"(\\.|.)*?"/, Str::Double
+        rule /'(\\.|.)*?'/, Str::Single
+        rule /\d+(?=}\s)/, Num
+        rule /(true|false)(?=[}\s])/, Keyword::Constant
+        rule /else(?=[}\s])/, Keyword
+        rule /this(?=[}\s])/, Name::Builtin::Pseudo
+        rule /@#{id}/, Name::Attribute
+        rule id, Name::Variable
+      end
+
+      state :open_sym do
+        rule %r{[#/]} do
+          token Keyword
+          goto :block_name
+        end
+
+        rule /[>^&]/, Keyword
+
+        rule(//) { pop! }
+      end
+
+      state :block_name do
+        rule /if(?=[}\s])/, Keyword
+        rule id, Name::Namespace, :pop!
+        rule(//) { pop! }
+      end
+    end
+  end
+end