trenni 2.0.1 → 2.0.2

data/lib/trenni/fallback/markup.rl

@@ -32,9 +32,16 @@
 	action pcdata_begin {
 		pcdata = ""
 	}
-
+	
 	action pcdata_end {
 	}
+	
+	action text_begin {
+	}
+	
+	action text_end {
+		delegate.text(pcdata)
+	}
 
 	action characters_begin {
 		characters_begin = p
@@ -185,13 +192,6 @@
 		raise ParseError.new("could not parse cdata", buffer, p)
 	}
 
-	action text_begin {
-	}
-
-	action text_end {
-		delegate.text(pcdata)
-	}
-	
 	# This magic ensures that we process bytes.
 	getkey bytes[p];
 	

data/lib/trenni/markup.rb

@@ -51,6 +51,8 @@ module Trenni
 		def initialize(string = nil, escape = true)
 			if string
 				super(string)
+				
+				# self.replace CGI.escapeHTML(self)
 				ESCAPE.gsub!(self) if escape
 			else
 				super()

data/lib/trenni/version.rb

@@ -19,5 +19,5 @@
 # THE SOFTWARE.
 
 module Trenni
-	VERSION = "2.0.1"
+	VERSION = "2.0.2"
 end

data/parsers/trenni/markup.rl

@@ -12,11 +12,11 @@
 	
 	include entities "entities.rl";
 	
-	pcdata_character = (any - [<&]);
-	pcdata_characters = (pcdata_character+) >characters_begin %characters_end;
-	pcdata = (pcdata_characters | entity)+ >pcdata_begin %pcdata_end;
+	pcdata_character = any - [<&];
+	pcdata_characters = pcdata_character+ >characters_begin %characters_end;
+	pcdata = ((pcdata_characters | entity) $(pcdata,2) %(pcdata,1))+ %(pcdata,0) >pcdata_begin %pcdata_end;
 	
-	text = pcdata $(greedy_text,1) >text_begin %text_end;
+	text = pcdata >text_begin %text_end;
 	
 	doctype_text = (any* -- '>');
 	doctype = '<!DOCTYPE' >doctype_begin (doctype_text '>') %doctype_end @err(doctype_error);
@@ -39,5 +39,5 @@
 	
 	tag_closing = '</' >tag_closing_begin (identifier '>') %tag_closing_end @err(tag_error);
 	
-	main := (text >(greedy_text,0) | tag_opening | tag_closing | instruction | comment | doctype | cdata)*;
+	main := (text | tag_opening | tag_closing | instruction | comment | doctype | cdata)**;
 }%%

data/spec/trenni/parsers_performance_spec.rb

@@ -3,6 +3,8 @@ require 'benchmark/ips'
 require 'trenni/parsers'
 require 'trenni/entities'
 
+require 'nokogiri'
+
 require 'ruby-prof'
 
 RSpec.shared_context "profile" do
@@ -28,7 +30,7 @@ RSpec.describe Trenni::Parsers do
 	
 	it "should be fast to parse large documents" do
 		Benchmark.ips do |x|
-			x.report("Large Document") do |times|
+			x.report("Large (Trenni)") do |times|
 				delegate = Trenni::ParseDelegate.new
 				
 				while (times -= 1) >= 0
@@ -38,6 +40,17 @@ RSpec.describe Trenni::Parsers do
 				end
 			end
 			
+			x.report("Large (Nokogiri)") do |times|
+				delegate = Trenni::ParseDelegate.new
+				parser = Nokogiri::HTML::SAX::Parser.new(delegate)
+				
+				while (times -= 1) >= 0
+					parser.parse(xhtml_buffer.read)
+					
+					delegate.events.clear
+				end
+			end
+			
 			x.compare!
 		end
 	end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: trenni
 version: !ruby/object:Gem::Version
-  version: 2.0.1
+  version: 2.0.2
 platform: ruby
 authors:
 - Samuel Williams
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-11-28 00:00:00.000000000 Z
+date: 2016-11-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler