rugments 1.0.0.beta1

data/lib/rugments/lexers/haskell.rb

@@ -0,0 +1,181 @@
+module Rugments
+  module Lexers
+    class Haskell < RegexLexer
+      title 'Haskell'
+      desc 'The Haskell programming language (haskell.org)'
+
+      tag 'haskell'
+      aliases 'hs'
+      filenames '*.hs'
+      mimetypes 'text/x-haskell'
+
+      def self.analyze_text(text)
+        return 1 if text.shebang?('runhaskell')
+      end
+
+      reserved = %w(
+        _ case class data default deriving do else if in
+        infix[lr]? instance let newtype of then type where
+      )
+
+      ascii = %w(
+        NUL SOH [SE]TX EOT ENQ ACK BEL BS HT LF VT FF CR S[OI] DLE
+        DC[1-4] NAK SYN ETB CAN EM SUB ESC [FGRU]S SP DEL
+      )
+
+      state :basic do
+        rule /\s+/m, Text
+        rule /{-#/, Comment::Preproc, :comment_preproc
+        rule /{-/, Comment::Multiline, :comment
+        rule /^--\s+\|.*?$/, Comment::Doc
+        # this is complicated in order to support custom symbols
+        # like -->
+        rule /--(?![!#\$\%&*+.\/<=>?@\^\|_~]).*?$/, Comment::Single
+      end
+
+      # nested commenting
+      state :comment do
+        rule /-}/, Comment::Multiline, :pop!
+        rule /{-/, Comment::Multiline, :comment
+        rule /[^-{}]+/, Comment::Multiline
+        rule /[-{}]/, Comment::Multiline
+      end
+
+      state :comment_preproc do
+        rule /-}/, Comment::Preproc, :pop!
+        rule /{-/, Comment::Preproc, :comment
+        rule /[^-{}]+/, Comment::Preproc
+        rule /[-{}]/, Comment::Preproc
+      end
+
+      state :root do
+        mixin :basic
+
+        rule /\bimport\b/, Keyword::Reserved, :import
+        rule /\bmodule\b/, Keyword::Reserved, :module
+        rule /\berror\b/, Name::Exception
+        rule /\b(?:#{reserved.join('|')})\b/, Keyword::Reserved
+        # not sure why, but ^ doesn't work here
+        # rule /^[_a-z][\w']*/, Name::Function
+        rule /[_a-z][\w']*/, Name
+        rule /[A-Z][\w']*/, Keyword::Type
+
+        # lambda operator
+        rule %r{\\(?![:!#\$\%&*+.\\/<=>?@^\|~-]+)}, Name::Function
+        # special operators
+        rule %r{(<-|::|->|=>|=)(?![:!#\$\%&*+.\\/<=>?@^\|~-]+)}, Operator
+        # constructor/type operators
+        rule %r{:[:!#\$\%&*+.\\/<=>?@^\|~-]*}, Operator
+        # other operators
+        rule %r{[:!#\$\%&*+.\\/<=>?@^\|~-]+}, Operator
+
+        rule /\d+e[+-]?\d+/i, Num::Float
+        rule /\d+\.\d+(e[+-]?\d+)?/i, Num::Float
+        rule /0o[0-7]+/i, Num::Oct
+        rule /0x[\da-f]+/i, Num::Hex
+        rule /\d+/, Num::Integer
+
+        rule /'/, Str::Char, :character
+        rule /"/, Str, :string
+
+        rule /\[\s*\]/, Keyword::Type
+        rule /\(\s*\)/, Name::Builtin
+        rule /[\[\](),;`{}]/, Punctuation
+      end
+
+      state :import do
+        rule /\s+/, Text
+        rule /"/, Str, :string
+        rule /\bqualified\b/, Keyword
+        # import X as Y
+        rule /([A-Z][\w.]*)(\s+)(as)(\s+)([A-Z][a-zA-Z0-9_.]*)/ do
+          groups(
+            Name::Namespace, # X
+            Text, Keyword, # as
+            Text, Name # Y
+          )
+          pop!
+        end
+
+        # import X hiding (functions)
+        rule /([A-Z][\w.]*)(\s+)(hiding)(\s+)(\()/ do
+          groups(
+            Name::Namespace, # X
+            Text, Keyword, # hiding
+            Text, Punctuation # (
+          )
+          goto :funclist
+        end
+
+        # import X (functions)
+        rule /([A-Z][\w.]*)(\s+)(\()/ do
+          groups(
+            Name::Namespace, # X
+            Text,
+            Punctuation # (
+          )
+          goto :funclist
+        end
+
+        rule /[\w.]+/, Name::Namespace, :pop!
+      end
+
+      state :module do
+        rule /\s+/, Text
+        # module Foo (functions)
+        rule /([A-Z][\w.]*)(\s+)(\()/ do
+          groups Name::Namespace, Text, Punctuation
+          push :funclist
+        end
+
+        rule /\bwhere\b/, Keyword::Reserved, :pop!
+
+        rule /[A-Z][a-zA-Z0-9_.]*/, Name::Namespace, :pop!
+      end
+
+      state :funclist do
+        mixin :basic
+        rule /[A-Z]\w*/, Keyword::Type
+        rule /(_[\w\']+|[a-z][\w\']*)/, Name::Function
+        rule /,/, Punctuation
+        rule /[:!#\$\%&*+.\\\/<=>?@^\|~-]+/, Operator
+        rule /\(/, Punctuation, :funclist
+        rule /\)/, Punctuation, :pop!
+      end
+
+      state :character do
+        rule /\\/ do
+          token Str::Escape
+          push :character_end
+          push :escape
+        end
+
+        rule /./ do
+          token Str::Char
+          goto :character_end
+        end
+      end
+
+      state :character_end do
+        rule /'/, Str::Char, :pop!
+        rule /./, Error, :pop!
+      end
+
+      state :string do
+        rule /"/, Str, :pop!
+        rule /\\/, Str::Escape, :escape
+        rule /[^\\"]+/, Str
+      end
+
+      state :escape do
+        rule /[abfnrtv"'&\\]/, Str::Escape, :pop!
+        rule /\^[\]\[A-Z@\^_]/, Str::Escape, :pop!
+        rule /#{ascii.join('|')}/, Str::Escape, :pop!
+        rule /o[0-7]+/i, Str::Escape, :pop!
+        rule /x[\da-f]/i, Str::Escape, :pop!
+        rule /\d+/, Str::Escape, :pop!
+        rule /\s+\\/, Str::Escape, :pop!
+      end
+    end
+  end
+end

data/lib/rugments/lexers/html.rb

@@ -0,0 +1,92 @@
+module Rugments
+  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/rugments/lexers/http.rb

@@ -0,0 +1,78 @@
+module Rugments
+  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/rugments/lexers/ini.rb

@@ -0,0 +1,55 @@
+module Rugments
+  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/rugments/lexers/io.rb

@@ -0,0 +1,66 @@
+module Rugments
+  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/rugments/lexers/java.rb

@@ -0,0 +1,74 @@
+module Rugments
+  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