libxml-ruby 2.2.1 → 2.2.2

data/HISTORY

@@ -1,5 +1,31 @@
 = Release History
 
+== 2.2.2 / 2011-08-13 Charlie Savage
+
+* ++API CHANGE+++
+
+Reader#relax_ng_validate now takes a RelaxNG object.  This is
+what the documentation has always said it takes, but it previously
+took a string.  In addition, it now returns true or false instead of 0 or -1.
+
+Reader#schema_validate now takes a Schema object.  This is
+what the documentation has always said it takes, but it previously
+took a string.  In addition, it now returns true or false instead of 0 or -1.
+
+Fixes GitHub issue #30.
+
+* Added Parser::Context#close and HTMLParser::Context#close methods that
+  allow the underlying io stream (file, string, etc) to be closed.  Once a
+  parser is done parsing its data, it now calls one of these methods.
+  This means that if you parse thousands of files at the same time,
+  without running Ruby's garbage colllector, you won't get a too
+  many files open error.  Fixes GitHub issue #29.
+
+* Fixed bug where Node#inner_xml caused an error when it had no child nodes.
+  Fixes GitHub issues #31
+
+* Don't require 'rake' in the gemspec to avoid annoying Bunlder bugs
+
 == 2.2.1 / 2011-08-13 Charlie Savage
 
 * Packaging fix - include the custom .def file in the gem.

data/Rakefile

@@ -5,7 +5,6 @@ require "rake/extensiontask"
 require "rake/testtask"
 require "rubygems/package_task"
 require "rdoc/task"
-require "grancher/task"
 require "yaml"
 
 GEM_NAME = "libxml-ruby"
@@ -76,17 +75,5 @@ Rake::TestTask.new do |t|
   t.verbose = true
 end
 
-# Publish Website to Github
-Grancher::Task.new do |g|
-  # push gh-pages
-  g.branch  = 'gh-pages'
-  # to origin
-  g.push_to = 'origin'
-  # copy the website directory
-  g.directory 'web'
-  # and the rdoc directory
-  g.directory 'doc/libxml-ruby/rdoc', 'rdoc'
-end
-
 desc "Build docs, and publish the website"
 task :publish_with_docs => [:rdoc, :publish]

data/ext/libxml/ruby_xml_html_parser.c

@@ -72,6 +72,8 @@ static VALUE rxml_html_parser_parse(VALUE self)
     rxml_raise(&ctxt->lastError);
   }
 
+  rb_funcall(context, rb_intern("close"), 0);
+
   return rxml_document_wrap(ctxt->myDoc);
 }
 

data/ext/libxml/ruby_xml_html_parser_context.c

@@ -249,6 +249,27 @@ static VALUE rxml_html_parser_context_string(VALUE klass, VALUE string)
   return rxml_html_parser_context_wrap(ctxt);
 }
 
+/*
+ * call-seq:
+ *    context.close -> nil
+ *
+ * Closes the underlying input streams.  This is useful when parsing a large amount of
+ * files and you want to close the files without relying on Ruby's garbage collector
+ * to run.
+ */
+static VALUE rxml_html_parser_context_close(VALUE self)
+{
+  htmlParserCtxtPtr ctxt;
+  xmlParserInputPtr xinput;
+  Data_Get_Struct(self, htmlParserCtxt, ctxt);
+
+  while ((xinput = inputPop(ctxt)) != NULL)
+  {
+	 xmlFreeInputStream(xinput);
+  }
+  return Qnil;
+}
+
 /*
  * call-seq:
  *    context.disable_cdata = (true|false)
@@ -311,6 +332,7 @@ void rxml_init_html_parser_context(void)
   rb_define_singleton_method(cXMLHtmlParserContext, "file", rxml_html_parser_context_file, 1);
   rb_define_singleton_method(cXMLHtmlParserContext, "io", rxml_html_parser_context_io, 1);
   rb_define_singleton_method(cXMLHtmlParserContext, "string", rxml_html_parser_context_string, 1);
+  rb_define_method(cXMLHtmlParserContext, "close", rxml_html_parser_context_close, 0);
   rb_define_method(cXMLHtmlParserContext, "disable_cdata=", rxml_html_parser_context_disable_cdata_set, 1);
   rb_define_method(cXMLHtmlParserContext, "options=", rxml_html_parser_context_options_set, 1);
 }

data/ext/libxml/ruby_xml_parser.c

@@ -74,6 +74,8 @@ static VALUE rxml_parser_parse(VALUE self)
     rxml_raise(&ctxt->lastError);
   }
 
+  rb_funcall(context, rb_intern("close"), 0);
+
   return rxml_document_wrap(ctxt->myDoc);
 }
 

data/ext/libxml/ruby_xml_parser_context.c

@@ -214,6 +214,26 @@ static VALUE rxml_parser_context_base_uri_set(VALUE self, VALUE url)
   return self;
 }
 
+/*
+ * call-seq:
+ *    context.close -> nil
+ *
+ * Closes the underlying input streams.  This is useful when parsing a large amount of
+ * files and you want to close the files without relying on Ruby's garbage collector
+ * to run.
+ */
+static VALUE rxml_parser_context_close(VALUE self)
+{
+  xmlParserCtxtPtr ctxt;
+  xmlParserInputPtr xinput;
+  Data_Get_Struct(self, xmlParserCtxt, ctxt);
+
+  while ((xinput = inputPop(ctxt)) != NULL)
+  {
+	 xmlFreeInputStream(xinput);
+  }
+  return Qnil;
+}
 
 /*
  * call-seq:
@@ -937,6 +957,7 @@ void rxml_init_parser_context(void)
 
   rb_define_method(cXMLParserContext, "base_uri", rxml_parser_context_base_uri_get, 0);
   rb_define_method(cXMLParserContext, "base_uri=", rxml_parser_context_base_uri_set, 1);
+  rb_define_method(cXMLParserContext, "close", rxml_parser_context_close, 0);
   rb_define_method(cXMLParserContext, "data_directory", rxml_parser_context_data_directory_get, 0);
   rb_define_method(cXMLParserContext, "depth", rxml_parser_context_depth_get, 0);
   rb_define_method(cXMLParserContext, "disable_cdata?", rxml_parser_context_disable_cdata_q, 0);

data/ext/libxml/ruby_xml_reader.c

@@ -562,41 +562,48 @@ static VALUE rxml_reader_read_string(VALUE self)
 
 /*
  * call-seq:
- *    reader.relax_ng_validate(rng) -> code
+ *    reader.relax_ng_validate(rng) -> boolean
  *
  * Use RelaxNG to validate the document as it is processed. Activation is only
  * possible before the first read. If +rng+ is nil, the RelaxNG validation is
  * desactivated.
  *
- * Return 0 in case the RelaxNG validation could be (des)activated and -1 in
+ * Return true in case the RelaxNG validation could be (des)activated and false in
  * case of error.
  */
 static VALUE rxml_reader_relax_ng_validate(VALUE self, VALUE rng)
 {
-  char *xrng = NIL_P(rng) ? NULL : StringValueCStr(rng);
   xmlTextReaderPtr xreader = rxml_text_reader_get(self);
-  return INT2FIX(xmlTextReaderRelaxNGValidate(xreader, xrng));
+  xmlRelaxNGPtr xrelax;
+  int status;
+  Data_Get_Struct(rng, xmlRelaxNG, xrelax);
+  
+  status = xmlTextReaderRelaxNGSetSchema(xreader, xrelax);
+  return (status == 0 ? Qtrue : Qfalse);
 }
 
 #if LIBXML_VERSION >= 20620
 /*
  * call-seq:
- *    reader.schema_validate(schema) -> code
+ *    reader.schema_validate(schema) -> boolean
  *
  * Use W3C XSD schema to validate the document as it is processed. Activation
  * is only possible before the first read. If +schema+ is nil, then XML Schema
- * validation is desactivated.
+ * validation is deactivated.
  *
- * Return 0 in case the schemas validation could be (de)activated and -1 in
- * case of error.
+ * Return false if if the schema's validation could be (de)activated and true
+ * otherwise.
  */
 static VALUE
 rxml_reader_schema_validate(VALUE self, VALUE xsd)
 {
-  char *xxsd = NIL_P(xsd) ? NULL : StringValueCStr(xsd);
   xmlTextReaderPtr xreader = rxml_text_reader_get(self);
-  int status = xmlTextReaderSchemaValidate(xreader, xxsd);
-  return INT2FIX(status);
+  xmlSchemaPtr xschema;
+  int status;
+
+  Data_Get_Struct(xsd, xmlSchema, xschema);
+  status = xmlTextReaderSetSchema(xreader, xschema);
+  return (status == 0 ? Qtrue : Qfalse);
 }
 #endif
 

data/ext/libxml/ruby_xml_reader.h

@@ -4,6 +4,9 @@
 #ifndef __RXML_READER__
 #define __RXML_READER__
 
+#include <libxml/xmlreader.h>
+#include <libxml/xmlschemas.h>
+
 extern VALUE cXMLReader;
 
 void rxml_init_reader(void);

data/ext/libxml/ruby_xml_version.h

@@ -1,9 +1,9 @@
 /* Don't nuke this block!  It is used for automatically updating the
  * versions below. VERSION = string formatting, VERNUM = numbered
  * version for inline testing: increment both or none at all.*/
-#define RUBY_LIBXML_VERSION  "2.2.1"
-#define RUBY_LIBXML_VERNUM   221
+#define RUBY_LIBXML_VERSION  "2.2.2"
+#define RUBY_LIBXML_VERNUM   222
 #define RUBY_LIBXML_VER_MAJ   2
 #define RUBY_LIBXML_VER_MIN   2
-#define RUBY_LIBXML_VER_MIC   1
+#define RUBY_LIBXML_VER_MIC   2
 #define RUBY_LIBXML_VER_PATCH 0

data/lib/libxml/node.rb

@@ -32,7 +32,7 @@ module LibXML
           io << xml
         end
 
-        io.string
+        io ? io.string : nil
       end
       
       # :call-seq:

data/libxml-ruby.gemspec

@@ -1,29 +1,8 @@
 # encoding: utf-8
-require 'rake'
 
 # Determine the current version of the software
 version = File.read('ext/libxml/ruby_xml_version.h').match(/\s*RUBY_LIBXML_VERSION\s*['"](\d.+)['"]/)[1]
 
-# ------- Default Package ----------
-FILES = FileList[
-  'HISTORY',
-  'LICENSE',
-  'libxml-ruby.gemspec',
-  'MANIFEST',
-  'Rakefile',
-  'README.rdoc',
-  'setup.rb',
-  'ext/libxml/*.def',
-  'ext/libxml/*.h',
-  'ext/libxml/*.c',
-  'ext/libxml/*.rb',
-  'ext/vc/*.sln',
-  'ext/vc/*.vcprojx',
-  'lib/**/*.rb',
-  'script/**/*',
-  'test/**/*'
-]
-
 Gem::Specification.new do |spec|
   spec.name        = 'libxml-ruby'
   spec.version     = version
@@ -41,9 +20,23 @@ Gem::Specification.new do |spec|
   spec.platform = Gem::Platform::RUBY
   spec.bindir = "bin"
   spec.extensions = ["ext/libxml/extconf.rb"]
-  spec.files = FILES.to_a
+  spec.files = Dir.glob(['HISTORY',
+                         'LICENSE',
+                         'libxml-ruby.gemspec',
+                         'MANIFEST',
+                         'Rakefile',
+                         'README.rdoc',
+                         'setup.rb',
+                         'ext/libxml/*.def',
+                         'ext/libxml/*.h',
+                         'ext/libxml/*.c',
+                         'ext/libxml/*.rb',
+                         'ext/vc/*.sln',
+                         'ext/vc/*.vcprojx',
+                         'lib/**/*.rb',
+                         'script/**/*',
+                         'test/**/*'])
   spec.test_files = Dir.glob("test/tc_*.rb")
-
   spec.required_ruby_version = '>= 1.8.6'
   spec.date = DateTime.now
 end

data/test/model/books.xml

@@ -143,4 +143,12 @@
       environment.
     </description>
   </book>
+  <book id="bk113">
+    <author>Test Mike</author>
+    <title>Test Data with empty nodes</title>
+    <genre/>
+    <price/>
+    <publish_date/>
+    <description/>
+  </book>
 </catalog>

data/test/tc_error.rb

@@ -131,7 +131,7 @@ class TestError < Test::Unit::TestCase
       parser.parse
     end
 
-    assert_equal("Fatal error: Document is empty at :1.", error.to_s)
+    assert_equal(" LibXML::XML::Error.", error.to_s)
   end
 
   def test_libxml_parser_empty_string

data/test/tc_html_parser.rb

@@ -144,4 +144,10 @@ class HTMLParserTest < Test::Unit::TestCase
     doc = parser.parse
     assert_equal("<p>#{html}</p>", doc.root.to_s)
   end
+
+  def test_open_many_files
+    1000.times do
+      doc = XML::HTMLParser.file('model/ruby-lang.html').parse
+    end
+  end
 end

data/test/tc_parser.rb

@@ -256,6 +256,11 @@ class TestParser < Test::Unit::TestCase
     XML::Error.reset_handler {|error|}
   end
 
+  def test_open_many_files
+    1000.times do
+      doc = XML::Parser.file('model/atom.xml').parse
+    end
+  end
 
   # -----  Errors  ------
   def test_error

data/test/tc_schema.rb

@@ -18,36 +18,73 @@ class TestSchema < Test::Unit::TestCase
     XML::Schema.document(document)
   end
 
-  def test_from_doc
-    assert_instance_of(XML::Schema, schema)
-  end
-  
-  def test_valid
-    assert(@doc.validate_schema(schema))
-  end
-  
-  def test_invalid
-    new_node = XML::Node.new('invalid', 'this will mess up validation')
-    @doc.root << new_node
-
-    error = assert_raise(XML::Error) do
-      @doc.validate_schema(schema)
-    end
-
+   def check_error(error)
     assert_not_nil(error)
-    assert_kind_of(XML::Error, error)
     assert(error.message.match(/Error: Element 'invalid': This element is not expected. Expected is \( item \)/))
+    assert_kind_of(XML::Error, error)
     assert_equal(XML::Error::SCHEMASV, error.domain)
     assert_equal(XML::Error::SCHEMAV_ELEMENT_CONTENT, error.code)
     assert_equal(XML::Error::ERROR, error.level)
-    assert(error.file.match(/shiporder.xml/))
+    assert(error.file.match(/shiporder.xml/)) if error.file
     assert_nil(error.line)
     assert_nil(error.str1)
     assert_nil(error.str2)
     assert_nil(error.str3)
     assert_equal(0, error.int1)
     assert_equal(0, error.int2)
+  end
+
+  def test_load_from_doc
+    assert_instance_of(XML::Schema, schema)
+  end
+
+  def test_doc_valid
+    assert(@doc.validate_schema(schema))
+  end
+
+  def test_doc_invalid
+    new_node = XML::Node.new('invalid', 'this will mess up validation')
+    @doc.root << new_node
+
+    error = assert_raise(XML::Error) do
+      @doc.validate_schema(schema)
+    end
+
+    check_error(error)
     assert_not_nil(error.node)
     assert_equal('invalid', error.node.name)
   end
-end
+
+  def test_reader_valid
+    reader = XML::Reader.string(@doc.to_s)
+    assert(reader.schema_validate(schema))
+
+    while reader.read
+    end
+  end
+
+  def test_reader_invalid
+    # Set error handler
+    errors = Array.new
+    XML::Error.set_handler do |error|
+      errors << error
+    end
+
+    new_node = XML::Node.new('invalid', 'this will mess up validation')
+    @doc.root << new_node
+    reader = XML::Reader.string(@doc.to_s)
+
+    # Set a schema
+    assert(reader.schema_validate(schema))
+
+    while reader.read
+    end
+
+    assert_equal(1, errors.length)
+
+    error = errors.first
+    check_error(error)
+  ensure
+    XML::Error.set_handler(&LibXML::XML::Error::VERBOSE_HANDLER)
+  end
+end

data/test/tc_traversal.rb

@@ -4,8 +4,8 @@ require './test_helper'
 require 'test/unit'
 
 class TestTranversal < Test::Unit::TestCase
-  ROOT_NODES_LENGTH = 25
-  ROOT_ELEMENTS_LENGTH = 12
+  ROOT_NODES_LENGTH = 27
+  ROOT_ELEMENTS_LENGTH = 13
   
   def setup
     filename = File.join(File.dirname(__FILE__), 'model/books.xml')
@@ -30,7 +30,18 @@ class TestTranversal < Test::Unit::TestCase
     
     assert_equal(ROOT_NODES_LENGTH, nodes.length)
   end
-  
+
+  def test_no_children
+    # Get a node with no children
+    node = @doc.find_first('/catalog/book[@id="bk113"]/price')
+    assert_equal(0, node.children.length)
+  end
+
+  def test_no_children_inner_xml
+    # Get a node with no children
+    node = @doc.find_first('/catalog/book[@id="bk113"]/price')
+    assert_nil(node.inner_xml)
+  end
   def test_each
     # Includes text nodes and such
     nodes = @doc.root.inject([]) do |arr, node|
@@ -131,92 +142,12 @@ class TestTranversal < Test::Unit::TestCase
   
     assert_equal(@doc.root.children, next_nodes)
   end
-  
-  #    node = @doc.find_first('book')
-   # node.children.each do |node|
-    #  puts 1
-    #end
-   # @doc.root.children do |node|
-    #  if node.node_type == XML::Node::ELEMENT_NODE
-     #   puts node.name
-      #end
-    #end
-    #assert_equal(12,nodes.length)
-  #end
-
-  #def test_doc_class
-    #assert_instance_of(XML::Document, @doc)
-  #end
-  
-  #def test_root_class
-    #assert_instance_of(XML::Node, @doc.root)
-  #end
-  
-  #def test_node_class
-    #for n in nodes
-      #assert_instance_of(XML::Node, n)
-    #end
-  #end
-
-  #def test_find_class
-    #set = @doc.find('/ruby_array/fixnum')
-    #assert_instance_of(XML::XPath::Object, set)
-  #end
 
-  #def test_node_child_get
-    #assert_instance_of(TrueClass, @doc.root.child?)
-    #assert_instance_of(XML::Node, @doc.root.child)
-    #assert_equal('fixnum', @doc.root.child.name)
-  #end
-
-  #def test_node_doc
-    #for n in nodes
-      #assert_instance_of(XML::Document, n.doc) if n.document?
-    #end
-  #end
-
-  #def test_node_type_name
-    #assert_equal('element', nodes[0].node_type_name)
-    #assert_equal('element', nodes[1].node_type_name)
-  #end
-
-  #def test_node_find
-    #set = @doc.root.find('./fixnum').set
-    #assert_instance_of(XML::Node::Set, set)
-    #for node in set
-      #assert_instance_of(XML::Node, node)
-    #end
-  #end
-  
-  #def test_equality
-    #node_a = @doc.find('/ruby_array/fixnum').first
-    #node_b = @doc.root.child
-    #assert(node_a == node_b)
-    #assert(node_a.eql?(node_b))
-    #assert(node_a.equal?(node_b))
-    
-    #xp2 = XML::Parser.new()
-    #xp2.string = '<ruby_array uga="booga" foo="bar"><fixnum>one</fixnum><fixnum>two</fixnum></ruby_array>'
-    #doc2 = xp2.parse
-
-    #node_a2 = doc2.find('/ruby_array/fixnum').first
-    
-    #assert(node_a.to_s == node_a2.to_s)
-    #assert(node_a == node_a2)
-    #assert(node_a.eql?(node_a2))
-    #assert(!node_a.equal?(node_a2))
-  #end
-      
-  #def test_content()
-    #assert_equal('onetwo', @doc.root.content)
-    
-    #first = @doc.root.child
-    #assert_equal('one', first.content)
-    #assert_equal('two', first.next.content)
-  #end
+  def test_doc_class
+    assert_instance_of(XML::Document, @doc)
+  end
   
-  #def test_base
-    #doc = XML::Parser.string('<person />').parse
-    #assert_nil(doc.root.base)
-  #end
+  def test_root_class
+    assert_instance_of(XML::Node, @doc.root)
+  end
 end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: libxml-ruby
 version: !ruby/object:Gem::Version 
-  hash: 5
+  hash: 3
   prerelease: 
   segments: 
   - 2
   - 2
-  - 1
-  version: 2.2.1
+  - 2
+  version: 2.2.2
 platform: ruby
 authors: 
 - Ross Bamform
@@ -20,7 +20,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-08-14 00:00:00 Z
+date: 2011-08-29 00:00:00 Z
 dependencies: []
 
 description: "    The Libxml-Ruby project provides Ruby language bindings for the GNOME\n    Libxml2 XML toolkit. It is free software, released under the MIT License.\n    Libxml-ruby's primary advantage over REXML is performance - if speed\n    is your need, these are good libraries to consider, as demonstrated\n    by the informal benchmark below.\n"
@@ -227,7 +227,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.8.6
+rubygems_version: 1.7.2
 signing_key: 
 specification_version: 3
 summary: Ruby Bindings for LibXML2