gitlab-rouge 1.9.2

data/lib/rouge/lexers/html.rb

@@ -0,0 +1,94 @@
+# -*- coding: utf-8 -*- #
+
+module Rouge
+  module Lexers
+    class HTML < RegexLexer
+      title "HTML"
+      desc "HTML, the markup language of the web"
+      tag 'html'
+      filenames '*.htm', '*.html', '*.xhtml'
+      mimetypes 'text/html', 'application/xhtml+xml'
+
+      def self.analyze_text(text)
+        return 1 if text.doctype?(/\bhtml\b/i)
+        return 1 if text =~ /<\s*html\b/
+      end
+
+      state :root do
+        rule /[^<&]+/m, Text
+        rule /&\S*?;/, Name::Entity
+        rule /<!DOCTYPE .*?>/im, Comment::Preproc
+        rule /<!\[CDATA\[.*?\]\]>/m, Comment::Preproc
+        rule /<!--/, Comment, :comment
+        rule /<\?.*?\?>/m, Comment::Preproc # php? really?
+
+        rule /<\s*script\s*/m do
+          token Name::Tag
+          push :script_content
+          push :tag
+        end
+
+        rule /<\s*style\s*/m do
+          token Name::Tag
+          push :style_content
+          push :tag
+        end
+
+        rule %r(<\s*[a-zA-Z0-9:-]+), Name::Tag, :tag # opening tags
+        rule %r(<\s*/\s*[a-zA-Z0-9:-]+\s*>), Name::Tag # closing tags
+      end
+
+      state :comment do
+        rule /[^-]+/, Comment
+        rule /-->/, Comment, :pop!
+        rule /-/, Comment
+      end
+
+      state :tag do
+        rule /\s+/m, Text
+        rule /[a-zA-Z0-9_:-]+\s*=/m, Name::Attribute, :attr
+        rule /[a-zA-Z0-9_:-]+/, Name::Attribute
+        rule %r(/?\s*>)m, Name::Tag, :pop!
+      end
+
+      state :attr do
+        # TODO: are backslash escapes valid here?
+        rule /"/ do
+          token Str
+          goto :dq
+        end
+
+        rule /'/ do
+          token Str
+          goto :sq
+        end
+
+        rule /[^\s>]+/, Str, :pop!
+      end
+
+      state :dq do
+        rule /"/, Str, :pop!
+        rule /[^"]+/, Str
+      end
+
+      state :sq do
+        rule /'/, Str, :pop!
+        rule /[^']+/, Str
+      end
+
+      state :script_content do
+        rule %r(<\s*/\s*script\s*>)m, Name::Tag, :pop!
+        rule %r(.*?(?=<\s*/\s*script\s*>))m do
+          delegate Javascript
+        end
+      end
+
+      state :style_content do
+        rule %r(<\s*/\s*style\s*>)m, Name::Tag, :pop!
+        rule %r(.*(?=<\s*/\s*style\s*>))m do
+          delegate CSS
+        end
+      end
+    end
+  end
+end

data/lib/rouge/lexers/http.rb

@@ -0,0 +1,80 @@
+# -*- coding: utf-8 -*- #
+
+module Rouge
+  module Lexers
+    class HTTP < RegexLexer
+      tag 'http'
+      title "HTTP"
+      desc 'http requests and responses'
+
+      def self.methods
+        @methods ||= %w(GET POST PUT DELETE HEAD OPTIONS TRACE PATCH)
+      end
+
+      def content_lexer
+        return Lexers::PlainText unless @content_type
+
+        @content_lexer ||= Lexer.guess_by_mimetype(@content_type)
+      rescue Lexer::AmbiguousGuess
+        @content_lexer = Lexers::PlainText
+      end
+
+      start { @content_type = 'text/plain' }
+
+      state :root do
+        # request
+        rule %r(
+          (#{HTTP.methods.join('|')})([ ]+) # method
+          ([^ ]+)([ ]+)                     # path
+          (HTTPS?)(/)(1[.][01])(\r?\n|$)  # http version
+        )ox do
+          groups(
+            Name::Function, Text,
+            Name::Namespace, Text,
+            Keyword, Operator, Num, Text
+          )
+
+          push :headers
+        end
+
+        # response
+        rule %r(
+          (HTTPS?)(/)(1[.][01])([ ]+) # http version
+          (\d{3})([ ]+)               # status
+          ([^\r\n]+)(\r?\n|$)       # status message
+        )x do
+          groups(
+            Keyword, Operator, Num, Text,
+            Num, Text,
+            Name::Exception, Text
+          )
+          push :headers
+        end
+      end
+
+      state :headers do
+        rule /([^\s:]+)( *)(:)( *)([^\r\n]+)(\r?\n|$)/ do |m|
+          key = m[1]
+          value = m[5]
+          if key.strip.downcase == 'content-type'
+            @content_type = value.split(';')[0].downcase
+          end
+
+          groups Name::Attribute, Text, Punctuation, Text, Str, Text
+        end
+
+        rule /([^\r\n]+)(\r?\n|$)/ do
+          groups Str, Text
+        end
+
+        rule /\r?\n/, Text, :content
+      end
+
+      state :content do
+        rule /.+/m do |m|
+          delegate(content_lexer)
+        end
+      end
+    end
+  end
+end

data/lib/rouge/lexers/ini.rb

@@ -0,0 +1,57 @@
+# -*- coding: utf-8 -*- #
+
+module Rouge
+  module Lexers
+    class INI < RegexLexer
+      title "INI"
+      desc 'the INI configuration format'
+      tag 'ini'
+
+      # TODO add more here
+      filenames '*.ini', '*.INI', '*.gitconfig'
+      mimetypes 'text/x-ini'
+
+      def self.analyze_text(text)
+        return 0.1 if text =~ /\A\[[\w.]+\]\s*\w+=\w+/
+      end
+
+      identifier = /[\w.]+/
+
+      state :basic do
+        rule /[;#].*?\n/, Comment
+        rule /\s+/, Text
+        rule /\\\n/, Str::Escape
+      end
+
+      state :root do
+        mixin :basic
+
+        rule /(#{identifier})(\s*)(=)/ do
+          groups Name::Property, Text, Punctuation
+          push :value
+        end
+
+        rule /\[.*?\]/, Name::Namespace
+      end
+
+      state :value do
+        rule /\n/, Text, :pop!
+        mixin :basic
+        rule /"/, Str, :dq
+        rule /'.*?'/, Str
+        mixin :esc_str
+        rule /[^\\\n]+/, Str
+      end
+
+      state :dq do
+        rule /"/, Str, :pop!
+        mixin :esc_str
+        rule /[^\\"]+/m, Str
+      end
+
+      state :esc_str do
+        rule /\\./m, Str::Escape
+      end
+    end
+  end
+end

data/lib/rouge/lexers/io.rb

@@ -0,0 +1,68 @@
+# -*- coding: utf-8 -*- #
+
+module Rouge
+  module Lexers
+    class IO < RegexLexer
+      tag 'io'
+      title "Io"
+      desc 'The IO programming language (http://iolanguage.com)'
+      mimetypes 'text/x-iosrc'
+      filenames '*.io'
+
+      def self.analyze_text(text)
+        return 1 if text.shebang? 'io'
+      end
+
+      def self.constants
+        @constants ||= Set.new %w(nil false true)
+      end
+
+      def self.builtins
+        @builtins ||= Set.new %w(
+          args call clone do doFile doString else elseif for if list
+          method return super then
+        )
+      end
+
+      state :root do
+        rule /\s+/m, Text
+        rule %r(//.*?\n), Comment::Single
+        rule %r(#.*?\n), Comment::Single
+        rule %r(/(\\\n)?[*].*?[*](\\\n)?/)m, Comment::Multiline
+        rule %r(/[+]), Comment::Multiline, :nested_comment
+
+        rule /"(\\\\|\\"|[^"])*"/, Str
+
+        rule %r(:?:=), Keyword
+        rule /[()]/, Punctuation
+
+        rule %r([-=;,*+><!/|^.%&\[\]{}]), Operator
+
+        rule /[A-Z]\w*/, Name::Class
+
+        rule /[a-z_]\w*/ do |m|
+          name = m[0]
+
+          if self.class.constants.include? name
+            token Keyword::Constant
+          elsif self.class.builtins.include? name
+            token Name::Builtin
+          else
+            token Name
+          end
+        end
+
+        rule %r((\d+[.]?\d*|\d*[.]\d+)(e[+-]?[0-9]+)?)i, Num::Float
+        rule /\d+/, Num::Integer
+
+        rule /@@?/, Keyword
+      end
+
+      state :nested_comment do
+        rule %r([^/+]+)m, Comment::Multiline
+        rule %r(/[+]), Comment::Multiline, :nested_comment
+        rule %r([+]/), Comment::Multiline, :pop!
+      end
+    end
+  end
+end

data/lib/rouge/lexers/java.rb

@@ -0,0 +1,76 @@
+# -*- coding: utf-8 -*- #
+
+module Rouge
+  module Lexers
+    class Java < RegexLexer
+      title "Java"
+      desc "The Java programming language (java.com)"
+
+      tag 'java'
+      filenames '*.java'
+      mimetypes 'text/x-java'
+
+      keywords = %w(
+        assert break case catch continue default do else finally for
+        if goto instanceof new return switch this throw try while
+      )
+
+      declarations = %w(
+        abstract const enum extends final implements native private protected
+        public static strictfp super synchronized throws transient volatile
+      )
+
+      types = %w(boolean byte char double float int long short void)
+
+      id = /[a-zA-Z_][a-zA-Z0-9_]*/
+
+      state :root do
+        rule %r(^
+          (\s*(?:[a-zA-Z_][a-zA-Z0-9_.\[\]]*\s+)+?) # return arguments
+          ([a-zA-Z_][a-zA-Z0-9_]*)                  # method name
+          (\s*)(\()                                 # signature start
+        )mx do |m|
+          # TODO: do this better, this shouldn't need a delegation
+          delegate Java, m[1]
+          token Name::Function, m[2]
+          token Text, m[3]
+          token Punctuation, m[4]
+        end
+
+        rule /\s+/, Text
+        rule %r(//.*?$), Comment::Single
+        rule %r(/\*.*?\*/)m, Comment::Multiline
+        rule /@#{id}/, Name::Decorator
+        rule /(?:#{keywords.join('|')})\b/, Keyword
+        rule /(?:#{declarations.join('|')})\b/, Keyword::Declaration
+        rule /(?:#{types.join('|')})\b/, Keyword::Type
+        rule /package\b/, Keyword::Namespace
+        rule /(?:true|false|null)\b/, Keyword::Constant
+        rule /(?:class|interface)\b/, Keyword::Declaration, :class
+        rule /import\b/, Keyword::Namespace, :import
+        rule /"(\\\\|\\"|[^"])*"/, Str
+        rule /'(?:\\.|[^\\]|\\u[0-9a-f]{4})'/, Str::Char
+        rule /(\.)(#{id})/ do
+          groups Operator, Name::Attribute
+        end
+        rule /#{id}:/, Name::Label
+        rule /\$?#{id}/, Name
+        rule /[~^*!%&\[\](){}<>\|+=:;,.\/?-]/, Operator
+        rule /[0-9][0-9]*\.[0-9]+([eE][0-9]+)?[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+/m, Text
+        rule id, Name::Class, :pop!
+      end
+
+      state :import do
+        rule /\s+/m, Text
+        rule /[a-z0-9_.]+\*?/i, Name::Namespace, :pop!
+      end
+    end
+  end
+end

data/lib/rouge/lexers/javascript.rb

@@ -0,0 +1,297 @@
+# -*- coding: utf-8 -*- #
+
+module Rouge
+  module Lexers
+    class Javascript < RegexLexer
+      title "JavaScript"
+      desc "JavaScript, the browser scripting language"
+
+      tag 'javascript'
+      aliases 'js'
+      filenames '*.js'
+      mimetypes 'application/javascript', 'application/x-javascript',
+                'text/javascript', 'text/x-javascript'
+
+      def self.analyze_text(text)
+        return 1 if text.shebang?('node')
+        return 1 if text.shebang?('jsc')
+        # TODO: rhino, spidermonkey, etc
+      end
+
+      state :comments_and_whitespace do
+        rule /\s+/, Text
+        rule /<!--/, Comment # really...?
+        rule %r(//.*?$), Comment::Single
+        rule %r(/\*.*?\*/)m, Comment::Multiline
+      end
+
+      state :expr_start do
+        mixin :comments_and_whitespace
+
+        rule %r(/) do
+          token Str::Regex
+          goto :regex
+        end
+
+        rule /[{]/, Punctuation, :object
+
+        rule //, Text, :pop!
+      end
+
+      state :regex do
+        rule %r(/) do
+          token Str::Regex
+          goto :regex_end
+        end
+
+        rule %r([^/]\n), Error, :pop!
+
+        rule /\n/, Error, :pop!
+        rule /\[\^/, Str::Escape, :regex_group
+        rule /\[/, Str::Escape, :regex_group
+        rule /\\./, Str::Escape
+        rule %r{[(][?][:=<!]}, Str::Escape
+        rule /[{][\d,]+[}]/, Str::Escape
+        rule /[()?]/, Str::Escape
+        rule /./, Str::Regex
+      end
+
+      state :regex_end do
+        rule /[gim]+/, Str::Regex, :pop!
+        rule(//) { pop! }
+      end
+
+      state :regex_group do
+        # specially highlight / in a group to indicate that it doesn't
+        # close the regex
+        rule /\//, Str::Escape
+
+        rule %r([^/]\n) do
+          token Error
+          pop! 2
+        end
+
+        rule /\]/, Str::Escape, :pop!
+        rule /\\./, Str::Escape
+        rule /./, Str::Regex
+      end
+
+      state :bad_regex do
+        rule /[^\n]+/, Error, :pop!
+      end
+
+      def self.keywords
+        @keywords ||= Set.new %w(
+          for in while do break return continue switch case default
+          if else throw try catch finally new delete typeof instanceof
+          void this yield
+        )
+      end
+
+      def self.declarations
+        @declarations ||= Set.new %w(var let with function)
+      end
+
+      def self.reserved
+        @reserved ||= Set.new %w(
+          abstract boolean byte char class const debugger double enum
+          export extends final float goto implements import int interface
+          long native package private protected public short static
+          super synchronized throws transient volatile
+        )
+      end
+
+      def self.constants
+        @constants ||= Set.new %w(true false null NaN Infinity undefined)
+      end
+
+      def self.builtins
+        @builtins ||= %w(
+          Array Boolean Date Error Function Math netscape
+          Number Object Packages RegExp String sun decodeURI
+          decodeURIComponent encodeURI encodeURIComponent
+          Error eval isFinite isNaN parseFloat parseInt document this
+          window
+        )
+      end
+
+      id = /[$a-zA-Z_][a-zA-Z0-9_]*/
+
+      state :root do
+        rule /\A\s*#!.*?\n/m, Comment::Preproc, :statement
+        rule /\n/, Text, :statement
+        rule %r((?<=\n)(?=\s|/|<!--)), Text, :expr_start
+        mixin :comments_and_whitespace
+        rule %r(\+\+ | -- | ~ | && | \|\| | \\(?=\n) | << | >>>? | ===
+               | !== )x,
+          Operator, :expr_start
+        rule %r([-<>+*%&|\^/!=]=?), Operator, :expr_start
+        rule /[(\[,]/, Punctuation, :expr_start
+        rule /;/, Punctuation, :statement
+        rule /[)\].]/, Punctuation
+
+        rule /[?]/ do
+          token Punctuation
+          push :ternary
+          push :expr_start
+        end
+
+        rule /[{}]/, Punctuation, :statement
+
+        rule id do |m|
+          if self.class.keywords.include? m[0]
+            token Keyword
+            push :expr_start
+          elsif self.class.declarations.include? m[0]
+            token Keyword::Declaration
+            push :expr_start
+          elsif self.class.reserved.include? m[0]
+            token Keyword::Reserved
+          elsif self.class.constants.include? m[0]
+            token Keyword::Constant
+          elsif self.class.builtins.include? m[0]
+            token Name::Builtin
+          else
+            token Name::Other
+          end
+        end
+
+        rule /[0-9][0-9]*\.[0-9]+([eE][0-9]+)?[fd]?/, Num::Float
+        rule /0x[0-9a-fA-F]+/, Num::Hex
+        rule /[0-9]+/, Num::Integer
+        rule /"(\\\\|\\"|[^"])*"/, Str::Double
+        rule /'(\\\\|\\'|[^'])*'/, Str::Single
+      end
+
+      # braced parts that aren't object literals
+      state :statement do
+        rule /(#{id})(\s*)(:)/ do
+          groups Name::Label, Text, Punctuation
+        end
+
+        rule /[{}]/, Punctuation
+
+        mixin :expr_start
+      end
+
+      # object literals
+      state :object do
+        mixin :comments_and_whitespace
+        rule /[}]/ do
+          token Punctuation
+          goto :statement
+        end
+
+        rule /(#{id})(\s*)(:)/ do
+          groups Name::Attribute, Text, Punctuation
+          push :expr_start
+        end
+
+        rule /:/, Punctuation
+        mixin :root
+      end
+
+      # ternary expressions, where <id>: is not a label!
+      state :ternary do
+        rule /:/ do
+          token Punctuation
+          goto :expr_start
+        end
+
+        mixin :root
+      end
+    end
+
+    class JSON < RegexLexer
+      desc "JavaScript Object Notation (json.org)"
+      tag 'json'
+      filenames '*.json'
+      mimetypes 'application/json', 'application/vnd.api+json'
+
+      # TODO: is this too much of a performance hit?  JSON is quite simple,
+      # so I'd think this wouldn't be too bad, but for large documents this
+      # could mean doing two full lexes.
+      def self.analyze_text(text)
+        return 0.8 if text =~ /\A\s*{/m && text.lexes_cleanly?(self)
+      end
+
+      string = /"(\\.|[^"])*"/
+
+      state :root do
+        mixin :whitespace
+        rule /(?:true|false|null)\b/, Keyword::Constant
+        rule /{/,  Punctuation, :object_key_initial
+        rule /\[/, Punctuation, :array
+        rule /-?(?:0|[1-9]\d*)\.\d+(?:e[+-]\d+)?/i, Num::Float
+        rule /-?(?:0|[1-9]\d*)(?:e[+-]\d+)?/i, Num::Integer
+        mixin :has_string
+      end
+
+      state :whitespace do
+        rule /\s+/m, Text::Whitespace
+      end
+
+      state :has_string do
+        rule string, Str::Double
+      end
+
+      # in object_key_initial it's allowed to immediately close the object again
+      state :object_key_initial do
+        mixin :whitespace
+        rule string do
+          token Name::Tag
+          goto :object_key
+        end
+        rule /}/, Punctuation, :pop!
+      end
+
+      # in object_key at least one more name/value pair is required
+      state :object_key do
+        mixin :whitespace
+        rule string, Name::Tag
+        rule /:/, Punctuation, :object_val
+        rule /}/, Error, :pop!
+      end
+
+      state :object_val do
+        rule /,/, Punctuation, :pop!
+        rule(/}/) { token Punctuation; pop!(2) }
+        mixin :root
+      end
+
+      state :array do
+        rule /\]/, Punctuation, :pop!
+        rule /,/, Punctuation
+        mixin :root
+      end
+    end
+
+    class JSONDOC < JSON
+      desc "JavaScript Object Notation with extenstions for documentation"
+      tag 'json-doc'
+
+      prepend :root do
+        mixin :comments
+        rule /(\.\.\.)/, Comment::Single
+      end
+
+      prepend :object_key_initial do
+        mixin :comments
+        rule /(\.\.\.)/, Comment::Single
+      end
+
+      prepend :object_key do
+        mixin :comments
+        rule /(\.\.\.)/ do
+          token Comment::Single
+          goto :object_key_initial
+        end
+      end
+
+      state :comments do
+        rule %r(//.*?$), Comment::Single
+      end
+    end
+
+  end
+end