raldred-coderay 0.9.0 → 0.9.339

data/lib/coderay/scanners/groovy.rb

@@ -0,0 +1,271 @@
+module CodeRay
+module Scanners
+
+  load :java
+
+  class Groovy < Java
+
+    include Streamable
+    register_for :groovy
+    
+    # TODO: Check this!
+    KEYWORDS = Java::KEYWORDS + %w[
+      as assert def in
+    ]
+    KEYWORDS_EXPECTING_VALUE = WordList.new.add %w[
+      case instanceof new return throw typeof while as assert in
+    ]
+    
+    MAGIC_VARIABLES = Java::MAGIC_VARIABLES + %w[ it ]
+    # DIRECTIVES = %w[
+    #   abstract extends final implements native private protected public
+    #   static strictfp synchronized threadsafe throws transient volatile
+    # ]
+    
+    IDENT_KIND = WordList.new(:ident).
+      add(KEYWORDS, :keyword).
+      add(MAGIC_VARIABLES, :local_variable).
+      add(TYPES, :type).
+      add(BuiltinTypes::List, :pre_type).
+      add(DIRECTIVES, :directive)
+    
+    ESCAPE = / [bfnrtv$\n\\'"] | x[a-fA-F0-9]{1,2} | [0-7]{1,3} /x
+    UNICODE_ESCAPE =  / u[a-fA-F0-9]{4} /x  # no 4-byte unicode chars? U[a-fA-F0-9]{8}
+    REGEXP_ESCAPE =  / [bfnrtv\n\\'"] | x[a-fA-F0-9]{1,2} | [0-7]{1,3} | \d | [bBdDsSwW\/] /x
+    
+    # TODO: interpretation inside ', ", /
+    STRING_CONTENT_PATTERN = {
+      "'" => /(?>\\[^\\'\n]+|[^\\'\n]+)+/,
+      '"' => /[^\\$"\n]+/,
+      "'''" => /(?>[^\\']+|'(?!''))+/,
+      '"""' => /(?>[^\\$"]+|"(?!""))+/,
+      '/' => /[^\\$\/\n]+/,
+    }
+    
+    def scan_tokens tokens, options
+
+      state = :initial
+      inline_block_stack = []
+      inline_block_paren_depth = nil
+      string_delimiter = nil
+      import_clause = class_name_follows = last_token = after_def = false
+      value_expected = true
+
+      until eos?
+
+        kind = nil
+        match = nil
+        
+        case state
+
+        when :initial
+
+          if match = scan(/ \s+ | \\\n /x)
+            tokens << [match, :space]
+            if match.index ?\n
+              import_clause = after_def = false
+              value_expected = true unless value_expected
+            end
+            next
+          
+          elsif scan(%r! // [^\n\\]* (?: \\. [^\n\\]* )* | /\* (?: .*? \*/ | .* ) !mx)
+            value_expected = true
+            after_def = false
+            kind = :comment
+          
+          elsif bol? && scan(/ \#!.* /x)
+            kind = :doctype
+          
+          elsif import_clause && scan(/ (?!as) #{IDENT} (?: \. #{IDENT} )* (?: \.\* )? /ox)
+            after_def = value_expected = false
+            kind = :include
+          
+          elsif match = scan(/ #{IDENT} | \[\] /ox)
+            kind = IDENT_KIND[match]
+            value_expected = (kind == :keyword) && KEYWORDS_EXPECTING_VALUE[match]
+            if last_token == '.'
+              kind = :ident
+            elsif class_name_follows
+              kind = :class
+              class_name_follows = false
+            elsif after_def && check(/\s*[({]/)
+              kind = :method
+              after_def = false
+            elsif kind == :ident && last_token != '?' && check(/:/)
+              kind = :key
+            else
+              class_name_follows = true if match == 'class' || (import_clause && match == 'as')
+              import_clause = match == 'import'
+              after_def = true if match == 'def'
+            end
+          
+          elsif scan(/;/)
+            import_clause = after_def = false
+            value_expected = true
+            kind = :operator
+          
+          elsif scan(/\{/)
+            class_name_follows = after_def = false
+            value_expected = true
+            kind = :operator
+            if !inline_block_stack.empty?
+              inline_block_paren_depth += 1
+            end
+          
+          # TODO: ~'...', ~"..." and ~/.../ style regexps
+          elsif match = scan(/ \.\.<? | \*?\.(?!\d)@? | \.& | \?:? | [,?:(\[] | -[->] | \+\+ |
+              && | \|\| | \*\*=? | ==?~ | <=?>? | [-+*%^~&|>=!]=? | <<<?=? | >>>?=? /x)
+            value_expected = true
+            value_expected = :regexp if match == '~'
+            after_def = false
+            kind = :operator
+          
+          elsif match = scan(/ [)\]}] /x)
+            value_expected = after_def = false
+            if !inline_block_stack.empty? && match == '}'
+              inline_block_paren_depth -= 1
+              if inline_block_paren_depth == 0  # closing brace of inline block reached
+                tokens << [match, :inline_delimiter]
+                tokens << [:close, :inline]
+                state, string_delimiter, inline_block_paren_depth = inline_block_stack.pop
+                next
+              end
+            end
+          
+          elsif check(/[\d.]/)
+            after_def = value_expected = false
+            if scan(/0[xX][0-9A-Fa-f]+/)
+              kind = :hex
+            elsif scan(/(?>0[0-7]+)(?![89.eEfF])/)
+              kind = :oct
+            elsif scan(/\d+[fFdD]|\d*\.\d+(?:[eE][+-]?\d+)?[fFdD]?|\d+[eE][+-]?\d+[fFdD]?/)
+              kind = :float
+            elsif scan(/\d+[lLgG]?/)
+              kind = :integer
+            end
+
+          elsif match = scan(/'''|"""/)
+            after_def = value_expected = false
+            state = :multiline_string
+            tokens << [:open, :string]
+            string_delimiter = match
+            kind = :delimiter
+          
+          # TODO: record.'name'
+          elsif match = scan(/["']/)
+            after_def = value_expected = false
+            state = match == '/' ? :regexp : :string
+            tokens << [:open, state]
+            string_delimiter = match
+            kind = :delimiter
+
+          elsif value_expected && (match = scan(/\//))
+            after_def = value_expected = false
+            tokens << [:open, :regexp]
+            state = :regexp
+            string_delimiter = '/'
+            kind = :delimiter
+
+          elsif scan(/ @ #{IDENT} /ox)
+            after_def = value_expected = false
+            kind = :annotation
+
+          elsif scan(/\//)
+            after_def = false
+            value_expected = true
+            kind = :operator
+          
+          else
+            getch
+            kind = :error
+
+          end
+
+        when :string, :regexp, :multiline_string
+          if scan(STRING_CONTENT_PATTERN[string_delimiter])
+            kind = :content
+            
+          elsif match = scan(state == :multiline_string ? /'''|"""/ : /["'\/]/)
+            tokens << [match, :delimiter]
+            if state == :regexp
+              # TODO: regexp modifiers? s, m, x, i?
+              modifiers = scan(/[ix]+/)
+              tokens << [modifiers, :modifier] if modifiers && !modifiers.empty?
+            end
+            state = :string if state == :multiline_string
+            tokens << [:close, state]
+            string_delimiter = nil
+            after_def = value_expected = false
+            state = :initial
+            next
+          
+          elsif (state == :string || state == :multiline_string) &&
+              (match = scan(/ \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) /mox))
+            if string_delimiter[0] == ?' && !(match == "\\\\" || match == "\\'")
+              kind = :content
+            else
+              kind = :char
+            end
+          elsif state == :regexp && scan(/ \\ (?: #{REGEXP_ESCAPE} | #{UNICODE_ESCAPE} ) /mox)
+            kind = :char
+          
+          elsif match = scan(/ \$ #{IDENT} /mox)
+            tokens << [:open, :inline]
+            tokens << ['$', :inline_delimiter]
+            match = match[1..-1]
+            tokens << [match, IDENT_KIND[match]]
+            tokens << [:close, :inline]
+            next
+          elsif match = scan(/ \$ \{ /x)
+            tokens << [:open, :inline]
+            tokens << ['${', :inline_delimiter]
+            inline_block_stack << [state, string_delimiter, inline_block_paren_depth]
+            inline_block_paren_depth = 1
+            state = :initial
+            next
+          
+          elsif scan(/ \$ /mx)
+            kind = :content
+          
+          elsif scan(/ \\. /mx)
+            kind = :content
+          
+          elsif scan(/ \\ | \n /x)
+            tokens << [:close, state]
+            kind = :error
+            after_def = value_expected = false
+            state = :initial
+          
+          else
+            raise_inspect "else case \" reached; %p not handled." % peek(1), tokens
+          end
+
+        else
+          raise_inspect 'Unknown state', tokens
+
+        end
+
+        match ||= matched
+        if $DEBUG and not kind
+          raise_inspect 'Error token %p in line %d' %
+            [[match, kind], line], tokens
+        end
+        raise_inspect 'Empty token', tokens unless match
+        
+        last_token = match unless [:space, :comment, :doctype].include? kind
+        
+        tokens << [match, kind]
+
+      end
+
+      if [:multiline_string, :string, :regexp].include? state
+        tokens << [:close, state]
+      end
+
+      tokens
+    end
+
+  end
+
+end
+end

data/lib/coderay/scanners/html.rb

@@ -0,0 +1,175 @@
+module CodeRay
+module Scanners
+
+  # HTML Scanner
+  class HTML < Scanner
+
+    include Streamable
+    register_for :html
+
+    ATTR_NAME = /[\w.:-]+/
+    ATTR_VALUE_UNQUOTED = ATTR_NAME
+    TAG_END = /\/?>/
+    HEX = /[0-9a-fA-F]/
+    ENTITY = /
+      &
+      (?:
+        \w+
+      |
+        \#
+        (?:
+          \d+
+        |
+          x#{HEX}+
+        )
+      )
+      ;
+    /ox
+
+    PLAIN_STRING_CONTENT = {
+      "'" => /[^&'>\n]+/,
+      '"' => /[^&">\n]+/,
+    }
+
+    def reset
+      super
+      @state = :initial
+    end
+
+  private
+    def setup
+      @state = :initial
+      @plain_string_content = nil
+    end
+
+    def scan_tokens tokens, options
+
+      state = @state
+      plain_string_content = @plain_string_content
+
+      until eos?
+
+        kind = nil
+        match = nil
+
+        if scan(/\s+/m)
+          kind = :space
+
+        else
+
+          case state
+
+          when :initial
+            if scan(/<!--.*?-->/m)
+              kind = :comment
+            elsif scan(/<!DOCTYPE.*?>/m)
+              kind = :doctype
+            elsif scan(/<\?xml.*?\?>/m)
+              kind = :preprocessor
+            elsif scan(/<\?.*?\?>|<%.*?%>/m)
+              kind = :comment
+            elsif scan(/<\/[-\w_.:]*>/m)
+              kind = :tag
+            elsif match = scan(/<[-\w_.:]+>?/m)
+              kind = :tag
+              state = :attribute unless match[-1] == ?>
+            elsif scan(/[^<>&]+/)
+              kind = :plain
+            elsif scan(/#{ENTITY}/ox)
+              kind = :entity
+            elsif scan(/[<>&]/)
+              kind = :error
+            else
+              raise_inspect '[BUG] else-case reached with state %p' % [state], tokens
+            end
+
+          when :attribute
+            if scan(/#{TAG_END}/)
+              kind = :tag
+              state = :initial
+            elsif scan(/#{ATTR_NAME}/o)
+              kind = :attribute_name
+              state = :attribute_equal
+            else
+              kind = :error
+              getch
+            end
+
+          when :attribute_equal
+            if scan(/=/)
+              kind = :operator
+              state = :attribute_value
+            elsif scan(/#{ATTR_NAME}/o)
+              kind = :attribute_name
+            elsif scan(/#{TAG_END}/o)
+              kind = :tag
+              state = :initial
+            elsif scan(/./)
+              kind = :error
+              state = :attribute
+            end
+
+          when :attribute_value
+            if scan(/#{ATTR_VALUE_UNQUOTED}/o)
+              kind = :attribute_value
+              state = :attribute
+            elsif match = scan(/["']/)
+              tokens << [:open, :string]
+              state = :attribute_value_string
+              plain_string_content = PLAIN_STRING_CONTENT[match]
+              kind = :delimiter
+            elsif scan(/#{TAG_END}/o)
+              kind = :tag
+              state = :initial
+            else
+              kind = :error
+              getch
+            end
+
+          when :attribute_value_string
+            if scan(plain_string_content)
+              kind = :content
+            elsif scan(/['"]/)
+              tokens << [matched, :delimiter]
+              tokens << [:close, :string]
+              state = :attribute
+              next
+            elsif scan(/#{ENTITY}/ox)
+              kind = :entity
+            elsif scan(/&/)
+              kind = :content
+            elsif scan(/[\n>]/)
+              tokens << [:close, :string]
+              kind = :error
+              state = :initial
+            end
+
+          else
+            raise_inspect 'Unknown state: %p' % [state], tokens
+
+          end
+
+        end
+
+        match ||= matched
+        if $DEBUG and not kind
+          raise_inspect 'Error token %p in line %d' %
+            [[match, kind], line], tokens, state
+        end
+        raise_inspect 'Empty token', tokens unless match
+
+        tokens << [match, kind]
+      end
+
+      if options[:keep_state]
+        @state = state
+        @plain_string_content = plain_string_content
+      end
+
+      tokens
+    end
+
+  end
+
+end
+end

data/lib/coderay/scanners/java.rb

@@ -0,0 +1,173 @@
+module CodeRay
+module Scanners
+
+  class Java < Scanner
+
+    include Streamable
+    register_for :java
+    helper :builtin_types
+    
+    # TODO: Check this!
+    KEYWORDS = %w[
+      break case catch continue default do else
+      false finally for if instanceof new null
+      return switch throw true try typeof while
+      debugger export import package
+    ]
+    
+    MAGIC_VARIABLES = %w[ this super ]
+    TYPES = %w[
+      boolean byte char class interface double enum float String int long short void
+    ] << '[]'
+    DIRECTIVES = %w[
+      abstract extends final implements native private protected public
+      static strictfp synchronized threadsafe throws transient volatile
+    ]
+    
+    # Reserved for future use.
+    
+    IDENT_KIND = WordList.new(:ident).
+      add(KEYWORDS, :keyword).
+      add(MAGIC_VARIABLES, :local_variable).
+      add(TYPES, :type).
+      add(BuiltinTypes::List, :pre_type).
+      add(DIRECTIVES, :directive)
+
+    ESCAPE = / [bfnrtv\n\\'"] | x[a-fA-F0-9]{1,2} | [0-7]{1,3} /x
+    UNICODE_ESCAPE =  / u[a-fA-F0-9]{4} | U[a-fA-F0-9]{8} /x
+    STRING_CONTENT_PATTERN = {
+      "'" => /[^\\']+/,
+      '"' => /[^\\"]+/,
+      '/' => /[^\\\/]+/,
+    }
+    IDENT = /[a-zA-Z_][A-Za-z_0-9]*/
+    
+    def scan_tokens tokens, options
+
+      state = :initial
+      string_delimiter = nil
+      import_clause = class_name_follows = last_token_dot = false
+
+      until eos?
+
+        kind = nil
+        match = nil
+        
+        case state
+
+        when :initial
+
+          if match = scan(/ \s+ | \\\n /x)
+            tokens << [match, :space]
+            next
+          
+          elsif match = scan(%r! // [^\n\\]* (?: \\. [^\n\\]* )* | /\* (?: .*? \*/ | .* ) !mx)
+            tokens << [match, :comment]
+            next
+          
+          elsif import_clause && scan(/ #{IDENT} (?: \. #{IDENT} )* /ox)
+            kind = :include
+          
+          elsif match = scan(/ #{IDENT} | \[\] /ox)
+            kind = IDENT_KIND[match]
+            if last_token_dot
+              kind = :ident
+            elsif class_name_follows
+              kind = :class
+              class_name_follows = false
+            else
+              import_clause = true if match == 'import'
+              class_name_follows = true if match == 'class' || match == 'interface'
+            end
+          
+          elsif scan(/ \.(?!\d) | [,?:()\[\]}] | -- | \+\+ | && | \|\| | \*\*=? | [-+*\/%^~&|<>=!]=? | <<<?=? | >>>?=? /x)
+            kind = :operator
+          
+          elsif scan(/;/)
+            import_clause = false
+            kind = :operator
+          
+          elsif scan(/\{/)
+            class_name_follows = false
+            kind = :operator
+          
+          elsif check(/[\d.]/)
+            if scan(/0[xX][0-9A-Fa-f]+/)
+              kind = :hex
+            elsif scan(/(?>0[0-7]+)(?![89.eEfF])/)
+              kind = :oct
+            elsif scan(/\d+[fFdD]|\d*\.\d+(?:[eE][+-]?\d+)?[fFdD]?|\d+[eE][+-]?\d+[fFdD]?/)
+              kind = :float
+            elsif scan(/\d+[lL]?/)
+              kind = :integer
+            end
+
+          elsif match = scan(/["']/)
+            tokens << [:open, :string]
+            state = :string
+            string_delimiter = match
+            kind = :delimiter
+
+          elsif scan(/ @ #{IDENT} /ox)
+            kind = :annotation
+
+          else
+            getch
+            kind = :error
+
+          end
+
+        when :string
+          if scan(STRING_CONTENT_PATTERN[string_delimiter])
+            kind = :content
+          elsif match = scan(/["'\/]/)
+            tokens << [match, :delimiter]
+            tokens << [:close, state]
+            string_delimiter = nil
+            state = :initial
+            next
+          elsif state == :string && (match = scan(/ \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) /mox))
+            if string_delimiter == "'" && !(match == "\\\\" || match == "\\'")
+              kind = :content
+            else
+              kind = :char
+            end
+          elsif scan(/\\./m)
+            kind = :content
+          elsif scan(/ \\ | $ /x)
+            tokens << [:close, :delimiter]
+            kind = :error
+            state = :initial
+          else
+            raise_inspect "else case \" reached; %p not handled." % peek(1), tokens
+          end
+
+        else
+          raise_inspect 'Unknown state', tokens
+
+        end
+
+        match ||= matched
+        if $DEBUG and not kind
+          raise_inspect 'Error token %p in line %d' %
+            [[match, kind], line], tokens
+        end
+        raise_inspect 'Empty token', tokens unless match
+        
+        last_token_dot = match == '.'
+        
+        tokens << [match, kind]
+
+      end
+
+      if state == :string
+        tokens << [:close, state]
+      end
+
+      tokens
+    end
+
+  end
+
+end
+end