Merge branch 'master' into go-scanner

8 files changed, 122 insertions, 84 deletions

diff --git a/lib/coderay/encoders/html/numbering.rb b/lib/coderay/encoders/html/numbering.rb
index 8bc6259..332145b 100644
--- a/lib/coderay/encoders/html/numbering.rb
+++ b/lib/coderay/encoders/html/numbering.rb
@@ -1,15 +1,15 @@
 module CodeRay
 module Encoders
-
+  
   class HTML
-
+    
     module Numbering  # :nodoc:
-
+      
       def self.number! output, mode = :table, options = {}
         return self unless mode
-
+        
         options = DEFAULT_OPTIONS.merge options
-
+        
         start = options[:line_number_start]
         unless start.is_a? Integer
           raise ArgumentError, "Invalid value %p for :line_number_start; Integer expected." % start
@@ -17,7 +17,7 @@ module Encoders
         
         anchor_prefix = options[:line_number_anchors]
         anchor_prefix = 'line' if anchor_prefix == true
-        anchor_prefix = anchor_prefix.to_s[/\w+/] if anchor_prefix
+        anchor_prefix = anchor_prefix.to_s[/[\w-]+/] if anchor_prefix
         anchoring =
           if anchor_prefix
             proc do |line|
@@ -56,12 +56,17 @@ module Encoders
             raise ArgumentError, 'Invalid value %p for :bolding; false or Integer expected.' % bold_every
           end
         
-        line_count = output.count("\n")
-        position_of_last_newline = output.rindex(RUBY_VERSION >= '1.9' ? /\n/ : ?\n)
-        if position_of_last_newline
+        if position_of_last_newline = output.rindex(RUBY_VERSION >= '1.9' ? /\n/ : ?\n)
           after_last_newline = output[position_of_last_newline + 1 .. -1]
           ends_with_newline = after_last_newline[/\A(?:<\/span>)*\z/]
-          line_count += 1 if not ends_with_newline
+          
+          if ends_with_newline
+            line_count = output.count("\n")
+          else
+            line_count = output.count("\n") + 1
+          end
+        else
+          line_count = 1
         end
         
         case mode
@@ -74,30 +79,30 @@ module Encoders
             line_number += 1
             "<span class=\"line-numbers\">#{indent}#{line_number_text}</span>#{line}"
           end
-
+        
         when :table
           line_numbers = (start ... start + line_count).map(&bolding).join("\n")
           line_numbers << "\n"
           line_numbers_table_template = Output::TABLE.apply('LINE_NUMBERS', line_numbers)
-
+          
           output.gsub!(/<\/div>\n/, '</div>')
           output.wrap_in! line_numbers_table_template
           output.wrapped_in = :div
-
+        
         when :list
           raise NotImplementedError, 'The :list option is no longer available. Use :table.'
-
+        
         else
           raise ArgumentError, 'Unknown value %p for mode: expected one of %p' %
             [mode, [:table, :inline]]
         end
-
+        
         output
       end
-
+      
     end
-
+    
   end
-
+  
 end
 end
diff --git a/lib/coderay/encoders/html/output.rb b/lib/coderay/encoders/html/output.rb
index 9132d94..de6f6ea 100644
--- a/lib/coderay/encoders/html/output.rb
+++ b/lib/coderay/encoders/html/output.rb
@@ -124,7 +124,7 @@ module Encoders
 
       TABLE = Template.new <<-TABLE
 <table class="CodeRay"><tr>
-  <td class="line-numbers" title="double click to toggle" ondblclick="with (this.firstChild.style) { display = (display == '') ? 'none' : '' }"><pre><%LINE_NUMBERS%></pre></td>
+  <td class="line-numbers"><pre><%LINE_NUMBERS%></pre></td>
   <td class="code"><pre><%CONTENT%></pre></td>
 </tr></table>
       TABLE
diff --git a/lib/coderay/scanners/diff.rb b/lib/coderay/scanners/diff.rb
index 9e899c3..38efaf4 100644
--- a/lib/coderay/scanners/diff.rb
+++ b/lib/coderay/scanners/diff.rb
@@ -20,7 +20,7 @@ module Scanners
       
       line_kind = nil
       state = :initial
-      deleted_lines = 0
+      deleted_lines_count = 0
       scanners = Hash.new do |h, lang|
         h[lang] = Scanners[lang].new '', :keep_tokens => true, :keep_state => true
       end
@@ -30,7 +30,7 @@ module Scanners
       until eos?
         
         if match = scan(/\n/)
-          deleted_lines = 0 unless line_kind == :delete
+          deleted_lines_count = 0 unless line_kind == :delete
           if line_kind
             encoder.end_line line_kind
             line_kind = nil
@@ -99,37 +99,59 @@ module Scanners
             end
             next
           elsif match = scan(/-/)
-            deleted_lines += 1
-            encoder.begin_line line_kind = :delete
-            encoder.text_token match, :delete
-            if options[:inline_diff] && deleted_lines == 1 && check(/(?>.*)\n\+(?>.*)$(?!\n\+)/)
-              content_scanner_entry_state = content_scanner.state
-              skip(/(.*)\n\+(.*)$/)
-              head, deletion, insertion, tail = diff self[1], self[2]
-              pre, deleted, post = content_scanner.tokenize [head, deletion, tail], :tokens => Tokens.new
-              encoder.tokens pre
-              unless deleted.empty?
-                encoder.begin_group :eyecatcher
-                encoder.tokens deleted
-                encoder.end_group :eyecatcher
+            deleted_lines_count += 1
+            if options[:inline_diff] && deleted_lines_count == 1 && (changed_lines_count = 1 + check(/.*(?:\n\-.*)*/).count("\n")) && match?(/(?>.*(?:\n\-.*){#{changed_lines_count - 1}}(?:\n\+.*){#{changed_lines_count}})$(?!\n\+)/)
+              deleted_lines  = Array.new(changed_lines_count) { |i| skip(/\n\-/) if i > 0; scan(/.*/) }
+              inserted_lines = Array.new(changed_lines_count) { |i| skip(/\n\+/)         ; scan(/.*/) }
+              
+              deleted_lines_tokenized  = []
+              inserted_lines_tokenized = []
+              for deleted_line, inserted_line in deleted_lines.zip(inserted_lines)
+                pre, deleted_part, inserted_part, post = diff deleted_line, inserted_line
+                content_scanner_entry_state = content_scanner.state
+                deleted_lines_tokenized  << content_scanner.tokenize([pre, deleted_part, post], :tokens => Tokens.new)
+                content_scanner.state = content_scanner_entry_state || :initial
+                inserted_lines_tokenized << content_scanner.tokenize([pre, inserted_part, post], :tokens => Tokens.new)
               end
-              encoder.tokens post
-              encoder.end_line line_kind
-              encoder.text_token "\n", :space
-              encoder.begin_line line_kind = :insert
-              encoder.text_token '+', :insert
-              content_scanner.state = content_scanner_entry_state || :initial
-              pre, inserted, post = content_scanner.tokenize [head, insertion, tail], :tokens => Tokens.new
-              encoder.tokens pre
-              unless inserted.empty?
-                encoder.begin_group :eyecatcher
-                encoder.tokens inserted
-                encoder.end_group :eyecatcher
+              
+              for pre, deleted_part, post in deleted_lines_tokenized
+                encoder.begin_line :delete
+                encoder.text_token '-', :delete
+                encoder.tokens pre
+                unless deleted_part.empty?
+                  encoder.begin_group :eyecatcher
+                  encoder.tokens deleted_part
+                  encoder.end_group :eyecatcher
+                end
+                encoder.tokens post
+                encoder.end_line :delete
+                encoder.text_token "\n", :space
+              end
+              
+              for pre, inserted_part, post in inserted_lines_tokenized
+                encoder.begin_line :insert
+                encoder.text_token '+', :insert
+                encoder.tokens pre
+                unless inserted_part.empty?
+                  encoder.begin_group :eyecatcher
+                  encoder.tokens inserted_part
+                  encoder.end_group :eyecatcher
+                end
+                encoder.tokens post
+                changed_lines_count -= 1
+                if changed_lines_count > 0
+                  encoder.end_line :insert
+                  encoder.text_token "\n", :space
+                end
               end
-              encoder.tokens post
+              
+              line_kind = :insert
+              
             elsif match = scan(/.*/)
+              encoder.begin_line line_kind = :delete
+              encoder.text_token '-', :delete
               if options[:highlight_code]
-                if deleted_lines == 1
+                if deleted_lines_count == 1
                   content_scanner_entry_state = content_scanner.state
                 end
                 content_scanner.tokenize match, :tokens => encoder unless match.empty?
diff --git a/lib/coderay/scanners/html.rb b/lib/coderay/scanners/html.rb
index 733dd6f..3ba3b79 100644
--- a/lib/coderay/scanners/html.rb
+++ b/lib/coderay/scanners/html.rb
@@ -69,6 +69,7 @@ module Scanners
     def setup
       @state = :initial
       @plain_string_content = nil
+      @in_tag = nil
     end
     
     def scan_java_script encoder, code
@@ -83,7 +84,8 @@ module Scanners
     def scan_tokens encoder, options
       state = options[:state] || @state
       plain_string_content = @plain_string_content
-      in_tag = in_attribute = nil
+      in_tag = @in_tag
+      in_attribute = nil
       
       encoder.begin_group :string if state == :attribute_value_string
       
@@ -99,7 +101,7 @@ module Scanners
           when :initial
             if match = scan(/<!--(?:.*?-->|.*)/m)
               encoder.text_token match, :comment
-            elsif match = scan(/<!DOCTYPE(?:.*?>|.*)/m)
+            elsif match = scan(/<!(\w+)(?:.*?>|.*)|\]>/m)
               encoder.text_token match, :doctype
             elsif match = scan(/<\?xml(?:.*?\?>|.*)/m)
               encoder.text_token match, :preprocessor
@@ -237,6 +239,7 @@ module Scanners
       if options[:keep_state]
         @state = state
         @plain_string_content = plain_string_content
+        @in_tag = in_tag
       end
       
       encoder.end_group :string if state == :attribute_value_string
diff --git a/lib/coderay/scanners/php.rb b/lib/coderay/scanners/php.rb
index 8acfff5..6c68834 100644
--- a/lib/coderay/scanners/php.rb
+++ b/lib/coderay/scanners/php.rb
@@ -1,4 +1,4 @@
-# encoding: ASCII-8BIT
+# encoding: utf-8
 module CodeRay
 module Scanners
   
@@ -11,7 +11,6 @@ module Scanners
     
     register_for :php
     file_extension 'php'
-    encoding 'BINARY'
     
     KINDS_NOT_LOC = HTML::KINDS_NOT_LOC
     
@@ -211,7 +210,7 @@ module Scanners
       
       HTML_INDICATOR = /<!DOCTYPE html|<(?:html|body|div|p)[> ]/i
       
-      IDENTIFIER = /[a-z_\x7f-\xFF][a-z0-9_\x7f-\xFF]*/i
+      IDENTIFIER = 'ä'[/[[:alpha:]]/] == 'ä' ? Regexp.new('[[:alpha:]_[^\0-\177]][[:alnum:]_[^\0-\177]]*') : Regexp.new('[a-z_\x7f-\xFF][a-z0-9_\x7f-\xFF]*', true)
       VARIABLE = /\$#{IDENTIFIER}/
       
       OPERATOR = /
diff --git a/lib/coderay/scanners/ruby.rb b/lib/coderay/scanners/ruby.rb
index 2be98a6..c5cf1e2 100644
--- a/lib/coderay/scanners/ruby.rb
+++ b/lib/coderay/scanners/ruby.rb
@@ -94,18 +94,27 @@ module Scanners
             if !method_call_expected &&
                match = scan(unicode ? /#{patterns::METHOD_NAME}/uo :
                                       /#{patterns::METHOD_NAME}/o)
-              value_expected = false
+              
               kind = patterns::IDENT_KIND[match]
-              if kind == :ident
-                if match[/\A[A-Z]/] && !(match[/[!?]$/] || match?(/\(/))
-                  kind = :constant
+              if kind == :ident && value_expected != :colon_expected && scan(/:(?!:)/)
+                value_expected = true
+                encoder.text_token match, :key
+                encoder.text_token ':',   :operator
+              else
+                value_expected = false
+                if kind == :ident
+                  if match[/\A[A-Z]/] && !(match[/[!?]$/] || match?(/\(/))
+                    kind = :constant
+                  end
+                elsif kind == :keyword
+                  state = patterns::KEYWORD_NEW_STATE[match]
+                  if patterns::KEYWORDS_EXPECTING_VALUE[match]
+                    value_expected = match == 'when' ? :colon_expected : true
+                  end
                 end
-              elsif kind == :keyword
-                state = patterns::KEYWORD_NEW_STATE[match]
-                value_expected = true if patterns::KEYWORDS_EXPECTING_VALUE[match]
+                value_expected = true if !value_expected && check(/#{patterns::VALUE_FOLLOWS}/o)
+                encoder.text_token match, kind
               end
-              value_expected = true if !value_expected && check(/#{patterns::VALUE_FOLLOWS}/o)
-              encoder.text_token match, kind
               
             elsif method_call_expected &&
                match = scan(unicode ? /#{patterns::METHOD_AFTER_DOT}/uo :
@@ -119,9 +128,9 @@ module Scanners
               value_expected = check(/#{patterns::VALUE_FOLLOWS}/o)
               
             # OPERATORS #
-            elsif !method_call_expected && match = scan(/ (\.(?!\.)|::) | (?: \.\.\.? | ==?=? | [,\(\[\{] )() | [\)\]\}] /x)
+            elsif !method_call_expected && match = scan(/ (\.(?!\.)|::) | ( \.\.\.? | ==?=? | [,\(\[\{] ) | [\)\]\}] /x)
               method_call_expected = self[1]
-              value_expected = !method_call_expected && self[2]
+              value_expected = !method_call_expected && !!self[2]
               if inline_block_stack
                 case match
                 when '{'
@@ -213,7 +222,7 @@ module Scanners
               encoder.text_token match, :integer
               
             elsif match = scan(/ %=? | <(?:<|=>?)? | \? /x)
-              value_expected = true
+              value_expected = match == '?' ? :colon_expected : true
               encoder.text_token match, :operator
               
             elsif match = scan(/`/)
diff --git a/lib/coderay/scanners/ruby/patterns.rb b/lib/coderay/scanners/ruby/patterns.rb
index a52198e..ed071d2 100644
--- a/lib/coderay/scanners/ruby/patterns.rb
+++ b/lib/coderay/scanners/ruby/patterns.rb
@@ -1,9 +1,9 @@
 # encoding: utf-8
 module CodeRay
 module Scanners
-
+  
   module Ruby::Patterns  # :nodoc: all
-
+    
     KEYWORDS = %w[
       and def end in or unless begin
       defined? ensure module redo super until
@@ -12,7 +12,7 @@ module Scanners
       while alias class elsif if not return
       undef yield
     ]
-
+    
     # See http://murfy.de/ruby-constants.
     PREDEFINED_CONSTANTS = %w[
       nil true false self
@@ -24,19 +24,19 @@ module Scanners
       RUBY_PLATFORM RUBY_RELEASE_DATE RUBY_REVISION RUBY_VERSION
       __FILE__ __LINE__ __ENCODING__
     ]
-
+    
     IDENT_KIND = WordList.new(:ident).
       add(KEYWORDS, :keyword).
       add(PREDEFINED_CONSTANTS, :predefined_constant)
-
+    
     KEYWORD_NEW_STATE = WordList.new(:initial).
       add(%w[ def ], :def_expected).
       add(%w[ undef ], :undef_expected).
       add(%w[ alias ], :alias_expected).
       add(%w[ class module ], :module_expected)
-
-    IDENT = 'ä'[/[[:alpha:]]/] == 'ä' ? /[[:alpha:]_][[:alnum:]_]*/ : /[^\W\d]\w*/
-
+    
+    IDENT = 'ä'[/[[:alpha:]]/] == 'ä' ? Regexp.new('[[:alpha:]_[^\0-\177]][[:alnum:]_[^\0-\177]]*') : /[^\W\d]\w*/
+    
     METHOD_NAME = / #{IDENT} [?!]? /ox
     METHOD_NAME_OPERATOR = /
       \*\*?           # multiplication and power
@@ -57,25 +57,25 @@ module Scanners
     GLOBAL_VARIABLE = / \$ (?: #{IDENT} | [1-9]\d* | 0\w* | [~&+`'=\/,;_.<>!@$?*":\\] | -[a-zA-Z_0-9] ) /ox
     PREFIX_VARIABLE = / #{GLOBAL_VARIABLE} | #{OBJECT_VARIABLE} /ox
     VARIABLE = / @?@? #{IDENT} | #{GLOBAL_VARIABLE} /ox
-
+    
     QUOTE_TO_TYPE = {
       '`' => :shell,
       '/'=> :regexp,
     }
     QUOTE_TO_TYPE.default = :string
-
+    
     REGEXP_MODIFIERS = /[mousenix]*/
-
+    
     DECIMAL = /\d+(?:_\d+)*/
     OCTAL = /0_?[0-7]+(?:_[0-7]+)*/
     HEXADECIMAL = /0x[0-9A-Fa-f]+(?:_[0-9A-Fa-f]+)*/
     BINARY = /0b[01]+(?:_[01]+)*/
-
+    
     EXPONENT = / [eE] [+-]? #{DECIMAL} /ox
     FLOAT_SUFFIX = / #{EXPONENT} | \. #{DECIMAL} #{EXPONENT}? /ox
     FLOAT_OR_INT = / #{DECIMAL} (?: #{FLOAT_SUFFIX} () )? /ox
     NUMERIC = / (?: (?=0) (?: #{OCTAL} | #{HEXADECIMAL} | #{BINARY} ) | #{FLOAT_OR_INT} ) /ox
-
+    
     SYMBOL = /
       :
       (?:
@@ -85,7 +85,7 @@ module Scanners
       )
     /ox
     METHOD_NAME_OR_SYMBOL = / #{METHOD_NAME_EX} | #{SYMBOL} /ox
-
+    
     SIMPLE_ESCAPE = /
         [abefnrstv]
       |  [0-7]{1,3}
@@ -110,7 +110,7 @@ module Scanners
       | \\ #{ESCAPE}
       )
     /mox
-
+    
     # NOTE: This is not completely correct, but
     # nobody needs heredoc delimiters ending with \n.
     HEREDOC_OPEN = /
@@ -122,13 +122,13 @@ module Scanners
         ( [^\n]*? ) \3     # $4 = delim
       )
     /mx
-
+    
     RUBYDOC = /
       =begin (?!\S)
       .*?
       (?: \Z | ^=end (?!\S) [^\n]* )
     /mx
-
+    
     DATA = /
       __END__$
       .*?
@@ -136,7 +136,7 @@ module Scanners
     /mx
     
     RUBYDOC_OR_DATA = / #{RUBYDOC} | #{DATA} /xo
-
+    
     # Checks for a valid value to follow. This enables
     # value_expected in method calls without parentheses.
     VALUE_FOLLOWS = /
diff --git a/lib/coderay/version.rb b/lib/coderay/version.rb
index 620e703..bfb5f24 100644
--- a/lib/coderay/version.rb
+++ b/lib/coderay/version.rb
@@ -1,3 +1,3 @@
 module CodeRay
-  VERSION = '1.0.7'
+  VERSION = '1.0.9'
 end