libxml-ruby 0.9.2 → 0.9.3

data/test/tc_input.rb

@@ -0,0 +1,13 @@
+require 'xml'
+require 'test/unit'
+
+class TestInput < Test::Unit::TestCase
+  def test_latin1
+    assert_equal(XML::Input::ISO_8859_1, 10)
+  end
+
+  def test_latin1_to_s
+    encoding_str = XML::Input.encoding_to_s(XML::Input::ISO_8859_1)
+    assert_equal('ISO-8859-1', encoding_str)
+  end
+end

data/test/tc_parser.rb

@@ -90,15 +90,23 @@ class TestParser < Test::Unit::TestCase
       assert_instance_of(XML::Parser, xp)
       assert_equal(io, xp.io)
       assert_equal(io, xp.input.io)
+
+      doc = xp.parse
+      assert_instance_of(XML::Document, doc)
+      assert_instance_of(XML::Parser::Context, xp.context)
     end
   end
 
   def test_string_io
     data = File.read(File.join(File.dirname(__FILE__), 'model/rubynet.xml'))
     string_io = StringIO.new(data)
-    assert_raises(TypeError) do
-      @xp.io = string_io
-    end
+    @xp.io = string_io
+    assert_equal(string_io, @xp.io)
+    assert_equal(string_io, @xp.input.io)
+
+    doc = @xp.parse
+    assert_instance_of(XML::Document, doc)
+    assert_instance_of(XML::Parser::Context, @xp.context)
   end
 
   def test_fd_gc

data/test/tc_reader.rb

@@ -5,14 +5,62 @@ class TextReader < Test::Unit::TestCase
 
   SIMPLE_XML = File.join(File.dirname(__FILE__), 'model/simple.xml')
 
-  def test_new_file
+  def verify_simple(reader)
+    node_types = []
+    19.times do
+      assert_equal(1, reader.read)
+      node_types << reader.node_type
+    end
+    assert_equal(0, reader.read)
+    assert_equal(node_types,
+      [XML::Reader::TYPE_ELEMENT,
+       XML::Reader::TYPE_SIGNIFICANT_WHITESPACE,
+       XML::Reader::TYPE_ELEMENT,
+       XML::Reader::TYPE_TEXT,
+       XML::Reader::TYPE_END_ELEMENT,
+       XML::Reader::TYPE_SIGNIFICANT_WHITESPACE,
+       XML::Reader::TYPE_ELEMENT,
+       XML::Reader::TYPE_SIGNIFICANT_WHITESPACE,
+       XML::Reader::TYPE_ELEMENT,
+       XML::Reader::TYPE_TEXT,
+       XML::Reader::TYPE_END_ELEMENT,
+       XML::Reader::TYPE_SIGNIFICANT_WHITESPACE,
+       XML::Reader::TYPE_ELEMENT,
+       XML::Reader::TYPE_TEXT,
+       XML::Reader::TYPE_END_ELEMENT,
+       XML::Reader::TYPE_SIGNIFICANT_WHITESPACE,
+       XML::Reader::TYPE_END_ELEMENT,
+       XML::Reader::TYPE_SIGNIFICANT_WHITESPACE,
+       XML::Reader::TYPE_END_ELEMENT])
+  end
+
+  def test_file
     reader = XML::Reader.file(SIMPLE_XML)
     verify_simple(reader)
-    assert_raises(RuntimeError) { XML::Reader.file('/does/not/exist') }
   end
 
-  def test_new_data
-    reader = XML::Reader.new(File.read(SIMPLE_XML))
+  def test_invalid_file
+    assert_raises(RuntimeError) do
+      XML::Reader.file('/does/not/exist')
+    end
+  end
+
+  def test_string
+    reader = XML::Reader.string(File.read(SIMPLE_XML))
+    verify_simple(reader)
+  end
+
+  def test_io
+    File.open(SIMPLE_XML, 'rb') do |io|
+      reader = XML::Reader.io(io)
+      verify_simple(reader)
+    end
+  end
+
+  def test_string_io
+    data = File.read(SIMPLE_XML)
+    string_io = StringIO.new(data)
+    reader = XML::Reader.io(string_io)
     verify_simple(reader)
   end
 
@@ -84,39 +132,10 @@ class TextReader < Test::Unit::TestCase
     doc.standalone?
   end
 
-  def verify_simple(reader)
-    node_types = []
-    19.times do
-      assert_equal(1, reader.read)
-      node_types << reader.node_type
-    end
-    assert_equal(0, reader.read)
-    assert_equal(node_types,
-      [XML::Reader::TYPE_ELEMENT,
-       XML::Reader::TYPE_SIGNIFICANT_WHITESPACE,
-       XML::Reader::TYPE_ELEMENT,
-       XML::Reader::TYPE_TEXT,
-       XML::Reader::TYPE_END_ELEMENT,
-       XML::Reader::TYPE_SIGNIFICANT_WHITESPACE,
-       XML::Reader::TYPE_ELEMENT,
-       XML::Reader::TYPE_SIGNIFICANT_WHITESPACE,
-       XML::Reader::TYPE_ELEMENT,
-       XML::Reader::TYPE_TEXT,
-       XML::Reader::TYPE_END_ELEMENT,
-       XML::Reader::TYPE_SIGNIFICANT_WHITESPACE,
-       XML::Reader::TYPE_ELEMENT,
-       XML::Reader::TYPE_TEXT,
-       XML::Reader::TYPE_END_ELEMENT,
-       XML::Reader::TYPE_SIGNIFICANT_WHITESPACE,
-       XML::Reader::TYPE_END_ELEMENT,
-       XML::Reader::TYPE_SIGNIFICANT_WHITESPACE,
-       XML::Reader::TYPE_END_ELEMENT])
-  end
-
   def test_mode
     reader = XML::Reader.string('<xml/>')
     assert_equal(XML::Reader::MODE_INITIAL, reader.read_state)
     reader.read
     assert_equal(XML::Reader::MODE_EOF, reader.read_state)
   end
-end
+end

data/test/tc_sax_parser.rb

@@ -59,6 +59,10 @@ class TestSaxParser < Test::Unit::TestCase
     @xp = nil
   end
 
+  def saxtest_file
+    File.join(File.dirname(__FILE__), 'model/saxtest.xml')
+  end
+
   def verify
     assert_equal [1], @xp.callbacks.test[:startdoc]
     assert_equal [[2,'test',{'uga'=>'booga','foo'=>'bar'}],[3,'fixnum',{}],[6,'fixnum',{}]],
@@ -72,26 +76,44 @@ class TestSaxParser < Test::Unit::TestCase
     assert_equal [17], @xp.callbacks.test[:enddoc]
   end
   
-  def test_string_without_callbacks
-    @xp.string = File.read(File.join(File.dirname(__FILE__), 'model/saxtest.xml'))
+  def test_string_no_callbacks
+    @xp.string = File.read(saxtest_file)
     assert_equal true, @xp.parse
   end
 
-  def test_file_without_callbacks
-    @xp.file = File.join(File.dirname(__FILE__), 'model/saxtest.xml')
+  def test_file_no_callbacks
+    @xp.file = File.join(saxtest_file)
     assert_equal true, @xp.parse
   end
 
-  def test_string_with_callbacks
+  def test_string
     @xp.callbacks = TestCaseCallbacks.new
-    @xp.string = File.read(File.join(File.dirname(__FILE__), 'model/saxtest.xml'))
+    @xp.string = File.read(saxtest_file)
     @xp.parse
     verify
   end
 
-  def test_file_with_callbacks
+  def test_file
+    @xp.callbacks = TestCaseCallbacks.new
+    @xp.file = saxtest_file
+    @xp.parse
+    verify
+  end
+
+  def test_io
+    File.open(saxtest_file) do |file|
+      @xp.callbacks = TestCaseCallbacks.new
+      @xp.io = file
+      @xp.parse
+      verify
+    end
+  end
+
+  def test_string_io
+    data = File.read(saxtest_file)
+
     @xp.callbacks = TestCaseCallbacks.new
-    @xp.file = File.join(File.dirname(__FILE__), 'model/saxtest.xml')
+    @xp.io = StringIO.new(data)
     @xp.parse
     verify
   end

data/test/test.rb

@@ -0,0 +1,8 @@
+require 'libxml'
+
+x = LibXML::XML::Parser.string("<root />").parse
+r1 = x.find("/root") # if you comment out this line, script will NOT segfault
+puts r1.object_id
+r2 = x.find("/root")#.length  # segfault occurs here
+puts puts r2.object_id
+

data/test/test_suite.rb

@@ -3,7 +3,7 @@ require 'tc_attributes'
 require 'tc_document'
 require 'tc_document_write'
 require 'tc_dtd'
-require 'tc_encoding'
+require 'tc_input'
 require 'tc_html_parser'
 require 'tc_node'
 require 'tc_node_attr'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: libxml-ruby
 version: !ruby/object:Gem::Version 
-  version: 0.9.2
+  version: 0.9.3
 platform: ruby
 authors: 
 - Charlie Savage
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2008-11-19 00:00:00 -07:00
+date: 2008-11-22 00:00:00 -07:00
 default_executable: 
 dependencies: []
 
@@ -40,8 +40,6 @@ files:
 - ext/libxml/ruby_xml_document.h
 - ext/libxml/ruby_xml_dtd.c
 - ext/libxml/ruby_xml_dtd.h
-- ext/libxml/ruby_xml_encoding.c
-- ext/libxml/ruby_xml_encoding.h
 - ext/libxml/ruby_xml_error.c
 - ext/libxml/ruby_xml_error.h
 - ext/libxml/ruby_xml_html_parser.c
@@ -136,9 +134,9 @@ files:
 - test/tc_document.rb
 - test/tc_document_write.rb
 - test/tc_dtd.rb
-- test/tc_encoding.rb
 - test/tc_error.rb
 - test/tc_html_parser.rb
+- test/tc_input.rb
 - test/tc_node.rb
 - test/tc_node_attr.rb
 - test/tc_node_cdata.rb
@@ -163,6 +161,7 @@ files:
 - test/tc_xpath_context.rb
 - test/tc_xpath_expression.rb
 - test/tc_xpointer.rb
+- test/test.rb
 - test/test_suite.rb
 has_rdoc: true
 homepage: http://libxml.rubyforge.org/
@@ -197,9 +196,9 @@ test_files:
 - test/tc_document.rb
 - test/tc_document_write.rb
 - test/tc_dtd.rb
-- test/tc_encoding.rb
 - test/tc_error.rb
 - test/tc_html_parser.rb
+- test/tc_input.rb
 - test/tc_node.rb
 - test/tc_node_attr.rb
 - test/tc_node_cdata.rb

data/ext/libxml/ruby_xml_encoding.c

@@ -1,164 +0,0 @@
-/* $Id: ruby_xml_ns.c 524 2008-08-20 08:59:54Z cfis $ */
-
-/* Please see the LICENSE file for copyright and distribution information */
-
-#include "ruby_libxml.h"
-#include "ruby_xml_encoding.h"
-
-VALUE mXMLEncoding;
-
-/*
-* Document-module: LibXML::XML::Encoding
-*
-* LibXML converts all data sources to UTF8 internally before 
-* processing them.  By default, LibXML will determine a data
-* source's encoding using the algorithm described on its
-* website[* http://xmlsoft.org/encoding.html].
-*
-* However, its some cases it is possible to tell LibXML
-* the data source's encoding via the constants defined in
-* the Encoding module.
-*
-* Example 1:
-* 
-*   parser = XML::Parser.new
-*   parser.input.encoding = XML::Encoding::ISO_8859_1
-*   parser.io = File.open('some_file', 'rb')
-*   doc = parser.parse
-*
-* Example 2:
-* 
-*   parser = XML::HTMLParser.new
-*   parser.encoding = XML::Encoding::ISO_8859_1
-*   parser.file = "some_file"
-*   doc = parser.parse
-*
-* Example 3:
-* 
-*   document = XML::Document.new
-*   encoding_string =  XML::Encoding.encoding_to_s(XML::Encoding::ISO_8859_1)
-*   document.encoding = document
-*   doc << XML::Node.new */
-
-VALUE
-ruby_xml_encoding_to_s(VALUE self, VALUE encoding)
-{
-  char* encodingStr = NULL;
-
-  switch (NUM2INT(encoding))
-  {
-    case XML_CHAR_ENCODING_ERROR:
-      encodingStr = "Error";
-      break;
-    case XML_CHAR_ENCODING_NONE:
-      encodingStr = "None";
-      break;
-    case XML_CHAR_ENCODING_UTF8:
-      encodingStr = "UTF-8";
-      break;
-    case XML_CHAR_ENCODING_UTF16LE:
-      encodingStr = "UTF-16LE";
-      break;
-    case XML_CHAR_ENCODING_UTF16BE:
-      encodingStr = "UTF-16BE";
-      break;
-    case XML_CHAR_ENCODING_UCS4LE:
-      encodingStr = "UCS-4LE";
-      break;
-    case XML_CHAR_ENCODING_UCS4BE:
-      encodingStr = "UCS-4BE";
-      break;
-    case XML_CHAR_ENCODING_EBCDIC:
-      encodingStr = "EBCDIC";
-      break;
-    case XML_CHAR_ENCODING_UCS4_2143:
-      encodingStr = "UCS-4";
-      break;
-    case XML_CHAR_ENCODING_UCS4_3412:
-      encodingStr = "UCS-4";
-      break;
-    case XML_CHAR_ENCODING_UCS2:
-      encodingStr = "UCS-2";
-      break;
-    case XML_CHAR_ENCODING_8859_1:
-      encodingStr = "ISO-8859-1";
-      break;
-    case XML_CHAR_ENCODING_8859_2:
-      encodingStr = "ISO-8859-2";
-      break;
-    case XML_CHAR_ENCODING_8859_3:
-      encodingStr = "ISO-8859-3";
-      break;
-    case XML_CHAR_ENCODING_8859_4:
-      encodingStr = "ISO-8859-4";
-      break;
-    case XML_CHAR_ENCODING_8859_5:
-      encodingStr = "ISO-8859-5";
-      break;
-    case XML_CHAR_ENCODING_8859_6:
-      encodingStr = "ISO-8859-6";
-      break;
-    case XML_CHAR_ENCODING_8859_7:
-      encodingStr = "ISO-8859-7";
-      break;
-    case XML_CHAR_ENCODING_8859_8:
-      encodingStr = "ISO-8859-8";
-      break;
-    case XML_CHAR_ENCODING_8859_9:
-      encodingStr = "ISO-8859-9";
-      break;
-    case XML_CHAR_ENCODING_2022_JP:
-      encodingStr = "ISO-2022-JP";
-      break;
-    case XML_CHAR_ENCODING_SHIFT_JIS:
-      encodingStr = "Shift_JIS";
-      break;
-    case XML_CHAR_ENCODING_EUC_JP:
-      encodingStr = "EUC-JP";
-      break;
-    case XML_CHAR_ENCODING_ASCII:
-      encodingStr = "ASCII";
-      break;
-  }
-
-  return rb_str_new2(encodingStr);
-}
-
-// Rdoc needs to know 
-#ifdef RDOC_NEVER_DEFINED
-  mLibXML = rb_define_module("LibXML");
-  mXML = rb_define_module_under(mLibXML, "XML");
-#endif
-
-void
-ruby_init_xml_encoding(void) {
-  mXMLEncoding = rb_define_module_under(mXML, "Encoding");
-
-  rb_define_module_function(mXMLEncoding, "encoding_to_s", ruby_xml_encoding_to_s, 1);
-
-  rb_define_const(mXMLEncoding, "UNDEFINED", INT2NUM(XPATH_UNDEFINED));
-  rb_define_const(mXMLEncoding, "ERROR", INT2NUM(XML_CHAR_ENCODING_ERROR));         /* No char encoding detected */
-  rb_define_const(mXMLEncoding, "NONE", INT2NUM(XML_CHAR_ENCODING_NONE));           /* No char encoding detected */
-  rb_define_const(mXMLEncoding, "UTF8", INT2NUM(XML_CHAR_ENCODING_UTF8));	          /* UTF-8 */
-  rb_define_const(mXMLEncoding, "UTF16LE", INT2NUM(XML_CHAR_ENCODING_UTF16LE));	    /* UTF-16 little endian */
-  rb_define_const(mXMLEncoding, "UTF16BE", INT2NUM(XML_CHAR_ENCODING_UTF16BE));	    /* UTF-16 big endian */
-  rb_define_const(mXMLEncoding, "UCS4LE", INT2NUM(XML_CHAR_ENCODING_UCS4LE));	      /* UCS-4 little endian */
-  rb_define_const(mXMLEncoding, "UCS4BE", INT2NUM(XML_CHAR_ENCODING_UCS4BE));	      /* UCS-4 big endian */
-  rb_define_const(mXMLEncoding, "EBCDIC", INT2NUM(XML_CHAR_ENCODING_EBCDIC));	      /* EBCDIC uh! */
-  rb_define_const(mXMLEncoding, "UCS4_2143", INT2NUM(XML_CHAR_ENCODING_UCS4_2143)); /* UCS-4 unusual ordering */
-  rb_define_const(mXMLEncoding, "UCS4_3412", INT2NUM(XML_CHAR_ENCODING_UCS4_3412)); /* UCS-4 unusual ordering */
-  rb_define_const(mXMLEncoding, "UCS2", INT2NUM(XML_CHAR_ENCODING_UCS2));	          /* UCS-2 */
-  rb_define_const(mXMLEncoding, "ISO_8859_1", INT2NUM(XML_CHAR_ENCODING_8859_1));	      /* ISO-8859-1 ISO Latin 1 */
-  rb_define_const(mXMLEncoding, "ISO_8859_2", INT2NUM(XML_CHAR_ENCODING_8859_2));	      /* ISO-8859-2 ISO Latin 2 */
-  rb_define_const(mXMLEncoding, "ISO_8859_3", INT2NUM(XML_CHAR_ENCODING_8859_3));	      /* ISO-8859-3 */
-  rb_define_const(mXMLEncoding, "ISO_8859_4", INT2NUM(XML_CHAR_ENCODING_8859_4));	      /* ISO-8859-4 */
-  rb_define_const(mXMLEncoding, "ISO_8859_5", INT2NUM(XML_CHAR_ENCODING_8859_5));	      /* ISO-8859-5 */
-  rb_define_const(mXMLEncoding, "ISO_8859_6", INT2NUM(XML_CHAR_ENCODING_8859_6));	      /* ISO-8859-6 */
-  rb_define_const(mXMLEncoding, "ISO_8859_7", INT2NUM(XML_CHAR_ENCODING_8859_7));	      /* ISO-8859-7 */
-  rb_define_const(mXMLEncoding, "ISO_8859_8", INT2NUM(XML_CHAR_ENCODING_8859_8));	      /* ISO-8859-8 */
-  rb_define_const(mXMLEncoding, "ISO_8859_9", INT2NUM(XML_CHAR_ENCODING_8859_9));	      /* ISO-8859-9 */
-  rb_define_const(mXMLEncoding, "ISO_2022_JP", INT2NUM(XML_CHAR_ENCODING_2022_JP));     /* ISO-2022-JP */
-  rb_define_const(mXMLEncoding, "SHIFT_JIS", INT2NUM(XML_CHAR_ENCODING_SHIFT_JIS)); /* Shift_JIS */
-  rb_define_const(mXMLEncoding, "EUC_JP", INT2NUM(XML_CHAR_ENCODING_EUC_JP));       /* EUC-JP */
-  rb_define_const(mXMLEncoding, "ASCII", INT2NUM(XML_CHAR_ENCODING_ASCII));         /* pure ASCII */
-}