multisax 0.0.6 → 0.0.6.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 8b40c84bc5076ee64f16e5dba05765e01fd1b17a
-  data.tar.gz: 97f52137ee9171e3c3efd74303fbf784be40ca33
+  metadata.gz: 89ef3e32c76021c3d85738ec9d08e6897dd8ef8a
+  data.tar.gz: 5e76e6c82462ead3333bfec4ccb991c77e00ded0
 SHA512:
-  metadata.gz: 09554bc0d7d6c198b05a2b2a212d506fda00ed7cb81d78d79d3309c4bbe782b00c910be430badc0d64f04c50eba5a72fb800bf8eefcc5d403149c90eee0f8913
-  data.tar.gz: 588370966d1cca05f96ec119d44410e0b3d880fc2e122c0418329ef05c246ab9b387d1e41318c88833b93405e88faf7e6c10fb6688bf3724607c84633d6e2c94
+  metadata.gz: 7fc3c659c2bbd667160ed47a7e479469f065519ee702dcda1c493d72302d5ba8f0bd9426a6d9050e5c8d07289be9c686a1d672f9a6bfc7597000353d5252f125
+  data.tar.gz: 36fb192b9f84bceb2b095d5eb2fd2ccf147e14b5204aef3fabfb9a31016da799b1c9dbf4a8b349b76d3ad47f2a40a04aa6fadb7f59f82b7d49142e4f440f1f1b

data/Xerces.md

@@ -0,0 +1,27 @@
+## Xerces-Ruby support
+
+From 0.0.6.1, multisax supports Xerces-Ruby unofficially. Official support won't be provided unless it is relicensed under permissive(BSD/MIT) or weak-copyleft(MPL) licenses.
+
+Due to license issue, in multisax, you need to `MultiSAX::Sax.open(:xerces)` or `MultiSAX::Sax.open(*MultiSAX::XML_PARSERS_INSTALLABLE+[:xerces]+MultiSAX::XML_PARSERS_DEFAULT)` explicitly.
+
+Here is the instruction to activate Xerces-Ruby.
+
+----
+- Install Xerces-C 2
+  - OSX (MacPorts): `sudo port install xercesc`
+  - Debian: `sudo apt-get install libxerces-c2-dev`
+- Download and extract [xerces-ruby](http://www.geocities.co.jp/SiliconValley-SanJose/9156/xerces-ruby.html)
+- Download [xerces-ruby.patch](https://gist.github.com/cielavenir/8401975)
+- Convert SAXParse.cpp's charcode
+  - `nkf -i -w /Users/tyamada/Downloads/xerces-ruby-2/SAXParse.cpp`
+- Apply patch
+  - `patch < xerces-ruby.patch`
+- Run extconf.rb
+  - `ruby extconf.rb --with-opt-dir=/opt/local`
+- `make`
+- Install libraries
+  - `make install`
+  - `sudo cp Xerces.rb  /Library/Ruby/Site/2.0.0/`
+- Now you can `require 'Xerces'` in your Ruby script.
+
+- Please note currently Xerces-Ruby cannot handle cdata. I (ciel) am NOT going to fix it.

data/lib/multisax.rb

@@ -8,7 +8,16 @@
 
 module MultiSAX
 	# VERSION string
-	VERSION='0.0.6'
+	VERSION='0.0.6.1'
+
+	# Default XML parsers
+	XML_PARSERS_DEFAULT=[:rexmlstream,:rexmlsax2]
+
+	# Installable XML parsers
+	XML_PARSERS_INSTALLABLE=[:ox,:libxml,:xmlparser,:nokogiri,:oga]
+
+	# Installable HTML parsers
+	HTML_PARSERS_INSTALLABLE=[:oxhtml,:nokogirihtml,:ogahtml]
 
 	# The class to handle XML libraries.
 	class SAX
@@ -27,8 +36,8 @@ module MultiSAX
 		#  If multiple selected, MultiSAX will try the libraries one by one and use the first usable one.
 		def open(*list)
 			return @parser if @parser
-			list=[:ox,:libxml,:xmlparser,:nokogiri,:oga,:rexmlstream,:rexmlsax2] if list.empty?||list==[:XML]
-			list=[:oxhtml,:nokogirihtml,:ogahtml] if list==[:HTML]
+			list=XML_PARSERS_INSTALLABLE+XML_PARSERS_DEFAULT if list.empty?||list==[:XML]
+			list=HTML_PARSERS_INSTALLABLE if list==[:HTML]
 			list.each{|e_module|
 				case e_module
 					when :ox,:oxhtml
@@ -115,6 +124,36 @@ module MultiSAX
 							def xmldecl(version,encoding,standalone) @obj.sax_xmldecl(version,encoding,standalone) end
 						}
 						break
+					when :xmlparser
+						begin
+							require 'xml/saxdriver'
+						rescue LoadError;next end
+						@parser=e_module
+						@saxhelper=Class.new(::XML::Parser){
+							def __init__(obj)
+								@obj=obj
+								@cdata=false
+								self
+							end
+							def startElement(tag,attrs) @obj.sax_tag_start(tag,attrs) end
+							def endElement(tag) @obj.sax_tag_end(tag) end
+							def comment(txt) @obj.sax_comment(txt) end
+							def xmlDecl(version,encoding,standalone) @obj.sax_xmldecl(version,encoding,standalone) end
+							def character(txt)
+								if @cdata
+									@obj.sax_cdata(txt)
+								else
+									@obj.sax_text(txt)
+								end
+							end
+							def startCdata
+								@cdata=true
+							end
+							def endCdata
+								@cdata=false
+							end
+						}
+						break
 					when :oga,:ogahtml
 						next if RUBY_VERSION<'1.9'
 						begin
@@ -144,34 +183,35 @@ module MultiSAX
 							end
 						}
 						break
-					when :xmlparser
+					when :xerces
 						begin
-							require 'xml/saxdriver'
+							require 'Xerces'
 						rescue LoadError;next end
 						@parser=e_module
-						@saxhelper=Class.new(::XML::Parser){
+						@saxhelper=Class.new(::XercesR::DocumentHandler){
 							def __init__(obj)
 								@obj=obj
-								@cdata=false
+								#@cdata=false
 								self
 							end
-							def startElement(tag,attrs) @obj.sax_tag_start(tag,attrs) end
+							def startElement(tag,attrs) @obj.sax_tag_start(tag,Hash[*attrs.getLength.times.map{|i|[attrs.getName(i),attrs.getValue(i)]}.flatten(1)]) end
 							def endElement(tag) @obj.sax_tag_end(tag) end
 							def comment(txt) @obj.sax_comment(txt) end
-							def xmlDecl(version,encoding,standalone) @obj.sax_xmldecl(version,encoding,standalone) end
-							def character(txt)
-								if @cdata
+							#def xmlDecl(version,encoding,standalone) @obj.sax_xmldecl(version,encoding,standalone) end
+							#def notationDecl(name, publicId, systemId) end
+							def characters(txt,len)
+								#if @cdata
 									@obj.sax_cdata(txt)
-								else
+								#else
 									@obj.sax_text(txt)
-								end
-							end
-							def startCdata
-								@cdata=true
-							end
-							def endCdata
-								@cdata=false
+								#end
 							end
+							#def startCdata
+							#	@cdata=true
+							#end
+							#def endCdata
+							#	@cdata=false
+							#end
 						}
 						break
 					when :rexmlstream
@@ -242,9 +282,10 @@ module MultiSAX
 					when :libxml       then parser=LibXML::XML::SaxParser.string(source);parser.callbacks=saxhelper;parser.parse
 					when :nokogiri     then parser=Nokogiri::XML::SAX::Parser.new(saxhelper);parser.parse(source)
 					when :nokogirihtml then parser=Nokogiri::HTML::SAX::Parser.new(saxhelper);parser.parse(source)
+					when :xmlparser    then saxhelper.parse(source)
 					when :oga          then parser=Oga::XML::SaxParser.new(saxhelper,source);parser.parse
 					when :ogahtml      then parser=Oga::HTML::SaxParser.new(saxhelper,source);parser.parse
-					when :xmlparser    then saxhelper.parse(source)
+					when :xerces       then parser=XercesR::SAXParser.new;parser.setDocumentHandler(saxhelper);parser.parsebuf(source)
 					when :rexmlstream  then REXML::Parsers::StreamParser.new(source,saxhelper).parse
 					when :rexmlsax2    then parser=REXML::Parsers::SAX2Parser.new(source);parser.listen(saxhelper);parser.parse
 				end
@@ -255,9 +296,10 @@ module MultiSAX
 					when :libxml       then parser=LibXML::XML::SaxParser.io(source);parser.callbacks=saxhelper;parser.parse
 					when :nokogiri     then parser=Nokogiri::XML::SAX::Parser.new(saxhelper);parser.parse(source)
 					when :nokogirihtml then parser=Nokogiri::HTML::SAX::Parser.new(saxhelper);parser.parse(source.read) # fixme: nokogirihtml IO doesn't allow errors.
+					when :xmlparser    then saxhelper.parse(source)
 					when :oga          then parser=Oga::XML::SaxParser.new(saxhelper,source);parser.parse
 					when :ogahtml      then parser=Oga::HTML::SaxParser.new(saxhelper,source);parser.parse
-					when :xmlparser    then saxhelper.parse(source)
+					when :xerces       then parser=XercesR::SAXParser.new;parser.setDocumentHandler(saxhelper);parser.parsebuf(source.read)
 					when :rexmlstream  then REXML::Parsers::StreamParser.new(source,saxhelper).parse
 					when :rexmlsax2    then parser=REXML::Parsers::SAX2Parser.new(source);parser.listen(saxhelper);parser.parse
 				end

data/spec/multisax_spec.rb

@@ -87,6 +87,17 @@ describe "[XML] MultiSAX::Sax.parse(String)" do
 		listener.attrib.should eq 'foo'
 		listener.xmlencoding.should eq 'UTF-8'
 	end
+	it "uses :xmlparser" do
+		pending 'xmlparser is not supported by jruby' if defined?(RUBY_ENGINE)&&RUBY_ENGINE=='jruby'
+		pending 'xmlparser is not supported by rubinius' if defined?(RUBY_ENGINE)&&RUBY_ENGINE=='rbx'
+		MultiSAX::Sax.reset
+		MultiSAX::Sax.open(:xmlparser)
+		MultiSAX::Sax.parser.should eq :xmlparser
+		listener=MultiSAX::Sax.parse(input_xml,MultiSAXTester.new)
+		listener.result.should eq xml_answer
+		listener.attrib.should eq 'foo'
+		listener.xmlencoding.should eq 'UTF-8'
+	end
 	it "uses :oga" do
 		pending 'oga requires Ruby >=1.9.3' if RUBY_VERSION<'1.9.3'
 		MultiSAX::Sax.reset
@@ -97,16 +108,16 @@ describe "[XML] MultiSAX::Sax.parse(String)" do
 		listener.attrib.should eq 'foo'
 		listener.xmlencoding.should eq 'UTF-8'
 	end
-	it "uses :xmlparser" do
-		pending 'xmlparser is not supported by jruby' if defined?(RUBY_ENGINE)&&RUBY_ENGINE=='jruby'
-		pending 'xmlparser is not supported by rubinius' if defined?(RUBY_ENGINE)&&RUBY_ENGINE=='rbx'
+	it "uses :xerces" do
+		pending 'xerces is not supported by jruby' if defined?(RUBY_ENGINE)&&RUBY_ENGINE=='jruby'
+		pending 'xerces will not be supported officially'
 		MultiSAX::Sax.reset
-		MultiSAX::Sax.open(:xmlparser)
-		MultiSAX::Sax.parser.should eq :xmlparser
+		MultiSAX::Sax.open(:xerces)
+		MultiSAX::Sax.parser.should eq :xerces
 		listener=MultiSAX::Sax.parse(input_xml,MultiSAXTester.new)
 		listener.result.should eq xml_answer
 		listener.attrib.should eq 'foo'
-		listener.xmlencoding.should eq 'UTF-8'
+		#listener.xmlencoding.should eq 'UTF-8'
 	end
 end
 
@@ -158,6 +169,17 @@ describe "[XML] MultiSAX::Sax.parse(IO)" do
 		listener.attrib.should eq 'foo'
 		listener.xmlencoding.should eq 'UTF-8'
 	end
+	it "uses :xmlparser" do
+		pending 'xmlparser is not supported by jruby' if defined?(RUBY_ENGINE)&&RUBY_ENGINE=='jruby'
+		pending 'xmlparser is not supported by rubinius' if defined?(RUBY_ENGINE)&&RUBY_ENGINE=='rbx'
+		MultiSAX::Sax.reset
+		MultiSAX::Sax.open(:xmlparser)
+		MultiSAX::Sax.parser.should eq :xmlparser
+		listener=MultiSAX::Sax.parse(StringIO.new(input_xml),MultiSAXTester.new)
+		listener.result.should eq xml_answer
+		listener.attrib.should eq 'foo'
+		listener.xmlencoding.should eq 'UTF-8'
+	end
 	it "uses :oga" do
 		pending 'oga requires Ruby >=1.9.3' if RUBY_VERSION<'1.9.3'
 		MultiSAX::Sax.reset
@@ -168,16 +190,16 @@ describe "[XML] MultiSAX::Sax.parse(IO)" do
 		listener.attrib.should eq 'foo'
 		listener.xmlencoding.should eq 'UTF-8'
 	end
-	it "uses :xmlparser" do
-		pending 'xmlparser is not supported by jruby' if defined?(RUBY_ENGINE)&&RUBY_ENGINE=='jruby'
-		pending 'xmlparser is not supported by rubinius' if defined?(RUBY_ENGINE)&&RUBY_ENGINE=='rbx'
+	it "uses :xerces" do
+		pending 'xerces is not supported by jruby' if defined?(RUBY_ENGINE)&&RUBY_ENGINE=='jruby'
+		pending 'xerces will not be supported officially'
 		MultiSAX::Sax.reset
-		MultiSAX::Sax.open(:xmlparser)
-		MultiSAX::Sax.parser.should eq :xmlparser
+		MultiSAX::Sax.open(:xerces)
+		MultiSAX::Sax.parser.should eq :xerces
 		listener=MultiSAX::Sax.parse(StringIO.new(input_xml),MultiSAXTester.new)
 		listener.result.should eq xml_answer
 		listener.attrib.should eq 'foo'
-		listener.xmlencoding.should eq 'UTF-8'
+		#listener.xmlencoding.should eq 'UTF-8'
 	end
 end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: multisax
 version: !ruby/object:Gem::Version
-  version: 0.0.6
+  version: 0.0.6.1
 platform: ruby
 authors:
 - cielavenir
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-11-19 00:00:00.000000000 Z
+date: 2014-11-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -67,6 +67,7 @@ files:
 - LICENSE.txt
 - README.md
 - Rakefile
+- Xerces.md
 - lib/multisax.rb
 - multisax.gemspec
 - spec/multisax_spec.rb