From 5ee15661dbc2da70927f588e310315233aff6eea Mon Sep 17 00:00:00 2001
From: murphy <murphy@rubychan.de>
Date: Mon, 10 Apr 2006 03:06:50 +0000
Subject: Large update: Scanners for HTML, RHTML and Nitro-XHTML added.

CSS style changes/enhancments (mainly the new background color for inline code, affects all Ruby code.)
Demos and tests adjusted.

Plugin: new PluginHost::default method.

Scanner:
- New setup method
- ability to re-use a scanner
- ability to keep the tokens
- minor changes to token caching and string flattening

Encoder: Error if token content is neither String nor Symbol.

HTML encoder:
- more warnings for unclosed tokens
- output now UTF-8

Ruby Scanner:
- bug: symbols before => now do not include =; {:foo=>bar} is valid Ruby code
- try to close all open tokens
- constants now all with specific namespace (for speed, I hope)

Styles: new :entity/en class.

Test suite now gives hinted HTML output.
---
 lib/coderay/scanners/html.rb | 57 ++++++++++++++++++++++++++++----------------
 1 file changed, 37 insertions(+), 20 deletions(-)

(limited to 'lib/coderay/scanners/html.rb')

diff --git a/lib/coderay/scanners/html.rb b/lib/coderay/scanners/html.rb
index 62da13b..a1efa9e 100644
--- a/lib/coderay/scanners/html.rb
+++ b/lib/coderay/scanners/html.rb
@@ -1,8 +1,8 @@
-#require 'coderay/common_patterns'
-
 module CodeRay module Scanners
 
 	# HTML Scanner
+	#
+	# $Id$
 	class HTML < Scanner
 
 		include Streamable
@@ -27,10 +27,21 @@ module CodeRay module Scanners
 			;
 		/ox
 
+		PLAIN_STRING_CONTENT = {
+			"'" => /[^&'>\n]+/,
+			'"' => /[^&">\n]+/,
+		}
+
 	private
+		def setup
+			@state = :initial
+			@plain_string_content = nil
+		end
+		
 		def scan_tokens tokens, options
-			
-			state = :initial
+
+			state = @state
+			plain_string_content = @plain_string_content
 			
 			until eos?
 				
@@ -55,17 +66,13 @@ module CodeRay module Scanners
 							kind = :comment
 						elsif scan(/<\/[-\w_.:]*>/m)
 							kind = :tag
-						elsif match = scan(/<[-\w_.:]*/m)
+						elsif match = scan(/<[-\w_.:]*>?/m)
 							kind = :tag
-							if match?(/>/)
-								match << getch
-							else
-								state = :attribute
-							end
+							state = :attribute unless match[-1] == ?>
 						elsif scan(/[^<>&]+/)
 							kind = :plain
 						elsif scan(/#{ENTITY}/ox)
-							kind = :char
+							kind = :entity
 						elsif scan(/>/)
 							kind = :error
 						else
@@ -79,6 +86,8 @@ module CodeRay module Scanners
 						elsif scan(/#{ATTR_NAME}/o)
 							kind = :attribute_name
 							state = :attribute_equal
+						else
+							getch
 						end
 
 					when :attribute_equal
@@ -98,29 +107,32 @@ module CodeRay module Scanners
 						if scan(/#{ATTR_VALUE_UNQUOTED}/o)
 							kind = :attribute_value
 							state = :attribute
-						elsif scan(/"/)
+						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
+							getch
 						end
 
 					when :attribute_value_string
-						if scan(/[^"&\n]+/)
+						if scan(plain_string_content)
 							kind = :content
-						elsif scan(/"/)
-							tokens << ['"', :delimiter]
+						elsif scan(/['"]/)
+							tokens << [matched, :delimiter]
 							tokens << [:close, :string]
 							state = :attribute
 							next
 						elsif scan(/#{ENTITY}/ox)
-							kind = :char
-						elsif match(/\n/)
+							kind = :entity
+						elsif match(/[\n>]/)
 							tokens << [:close, :string]
-							state = :attribute
-							next
+							kind = error
+							state = :initial
 						end
 
 					else
@@ -136,10 +148,15 @@ module CodeRay module Scanners
 					[[match, kind], line], tokens
 				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
 
-- 
cgit v1.2.1