diff --git a/test/xml/sax/test_parser.rb b/test/xml/sax/test_parser.rb index de078d6115..69f16d66d2 100644 --- a/test/xml/sax/test_parser.rb +++ b/test/xml/sax/test_parser.rb @@ -2,425 +2,429 @@ require "helper" -module Nokogiri - module XML - module SAX - class TestParser < Nokogiri::SAX::TestCase - def setup - super - @parser = XML::SAX::Parser.new(Doc.new) - end - - def test_parser_context_yielded_io - doc = Doc.new - parser = XML::SAX::Parser.new(doc) - xml = "" - - block_called = false - parser.parse(StringIO.new(xml)) do |ctx| - block_called = true - ctx.replace_entities = true - end - - assert(block_called) - - assert_equal([["foo", [["a", "&b"]]]], doc.start_elements) - end - - def test_parser_context_yielded_in_memory - doc = Doc.new - parser = XML::SAX::Parser.new(doc) - xml = "" - - block_called = false - parser.parse(xml) do |ctx| - block_called = true - ctx.replace_entities = true - end - - assert(block_called) - - assert_equal([["foo", [["a", "&b"]]]], doc.start_elements) - end - - def test_empty_decl - parser = XML::SAX::Parser.new(Doc.new) - - xml = "" - parser.parse(xml) - assert(parser.document.start_document_called, xml) - assert_nil(parser.document.xmldecls, xml) - end - - def test_xml_decl - [ - ['', ["1.0"]], - ['', ["1.0", "UTF-8"]], - ['', ["1.0", "yes"]], - ['', ["1.0", "no"]], - ['', ["1.0", "UTF-8", "no"]], - ['', ["1.0", "ISO-8859-1", "yes"]], - ].each do |decl, value| - parser = XML::SAX::Parser.new(Doc.new) - - xml = "#{decl}\n" - parser.parse(xml) - assert(parser.document.start_document_called, xml) - assert_equal(value, parser.document.xmldecls, xml) - end - end - - def test_parse_empty - assert_raises(RuntimeError) do - @parser.parse("") - end - end - - def test_namespace_declaration_order_is_saved - @parser.parse(<<~eoxml) - - - - eoxml - assert_equal(2, @parser.document.start_elements_namespace.length) - el = @parser.document.start_elements_namespace.first - namespaces = el.last - assert_equal(["foo", "http://foo.example.com/"], namespaces.first) - assert_equal([nil, "http://example.com/"], namespaces.last) - end - - def test_bad_document_calls_error_handler - @parser.parse("") - assert(@parser.document.errors) - assert(@parser.document.errors.length > 0) - end - - def test_namespace_are_super_fun_to_parse - @parser.parse(<<~eoxml) - - - - - - hello world - - eoxml - - assert(@parser.document.start_elements_namespace.length > 0) - el = @parser.document.start_elements_namespace[1] - assert_equal("a", el.first) - assert_equal(1, el[1].length) - - attribute = el[1].first - assert_equal("bar", attribute.localname) - assert_equal("foo", attribute.prefix) - assert_equal("hello", attribute.value) - assert_equal("http://foo.example.com/", attribute.uri) - end - - def test_sax_v1_namespace_attribute_declarations - @parser.parse(<<~eoxml) - - - - - - hello world - - eoxml - assert(@parser.document.start_elements.length > 0) - elm = @parser.document.start_elements.first - assert_equal("root", elm.first) - assert(elm[1].include?(["xmlns:foo", "http://foo.example.com/"])) - assert(elm[1].include?(["xmlns", "http://example.com/"])) - end - - def test_sax_v1_namespace_nodes - @parser.parse(<<~eoxml) - - - - - - hello world - - eoxml - assert_equal(5, @parser.document.start_elements.length) - assert(@parser.document.start_elements.map(&:first).include?("foo:bar")) - assert(@parser.document.end_elements.map(&:first).include?("foo:bar")) - end - - def test_start_is_called_without_namespace - @parser.parse(<<~eoxml) - - - - eoxml - assert_equal(["root", "foo:f", "bar"], - @parser.document.start_elements.map(&:first)) - end - - def test_parser_sets_encoding - parser = XML::SAX::Parser.new(Doc.new, "UTF-8") - assert_equal("UTF-8", parser.encoding) - end - - def test_errors_set_after_parsing_bad_dom - doc = Nokogiri::XML("") - assert(doc.errors) - - @parser.parse("") - assert(@parser.document.errors) - assert(@parser.document.errors.length > 0) - - doc.errors.each do |error| - assert_equal("UTF-8", error.message.encoding.name) - end - - # when using JRuby Nokogiri, more errors will be generated as the DOM - # parser continue to parse an ill formed document, while the sax parser - # will stop at the first error - unless Nokogiri.jruby? - assert_equal(doc.errors.length, @parser.document.errors.length) - end - end - - def test_parse_with_memory_argument - @parser.parse(File.read(XML_FILE)) - assert(@parser.document.cdata_blocks.length > 0) - end - - def test_parse_with_io_argument - File.open(XML_FILE, "rb") do |f| - @parser.parse(f) - end - assert(@parser.document.cdata_blocks.length > 0) - end - - def test_parse_io - call_parse_io_with_encoding("UTF-8") - end - - # issue #828 - def test_parse_io_lower_case_encoding - call_parse_io_with_encoding("utf-8") - end - - def call_parse_io_with_encoding(encoding) - File.open(XML_FILE, "rb") do |f| - @parser.parse_io(f, encoding) - end - assert(@parser.document.cdata_blocks.length > 0) - - called = false - @parser.document.start_elements.flatten.each do |thing| - assert_equal("UTF-8", thing.encoding.name) - called = true - end - assert(called) - - called = false - @parser.document.end_elements.flatten.each do |thing| - assert_equal("UTF-8", thing.encoding.name) - called = true - end - assert(called) - - called = false - @parser.document.data.each do |thing| - assert_equal("UTF-8", thing.encoding.name) - called = true - end - assert(called) - - called = false - @parser.document.comments.flatten.each do |thing| - assert_equal("UTF-8", thing.encoding.name) - called = true - end - assert(called) - - called = false - @parser.document.cdata_blocks.flatten.each do |thing| - assert_equal("UTF-8", thing.encoding.name) - called = true - end - assert(called) - end - - def test_parse_file - @parser.parse_file(XML_FILE) - - assert_raises(ArgumentError) do - @parser.parse_file(nil) - end - - assert_raises(Errno::ENOENT) do - @parser.parse_file("") - end - assert_raises(Errno::EISDIR) do - @parser.parse_file(File.expand_path(File.dirname(__FILE__))) - end - end - - def test_render_parse_nil_param - assert_raises(ArgumentError) { @parser.parse_memory(nil) } - end - - def test_bad_encoding_args - assert_raises(ArgumentError) { XML::SAX::Parser.new(Doc.new, "not an encoding") } - assert_raises(ArgumentError) { @parser.parse_io(StringIO.new(""), "not an encoding") } - end - - def test_ctag - @parser.parse_memory(<<~eoxml) -

- - Paragraph 1 -

- eoxml - assert_equal([" This is a comment "], @parser.document.cdata_blocks) - end - - def test_comment - @parser.parse_memory(<<~eoxml) -

- - Paragraph 1 -

- eoxml - assert_equal([" This is a comment "], @parser.document.comments) - end - - def test_characters - @parser.parse_memory(<<~eoxml) -

Paragraph 1

- eoxml - assert_equal(["Paragraph 1"], @parser.document.data) - end - - def test_end_document - @parser.parse_memory(<<~eoxml) -

Paragraph 1

- eoxml - assert(@parser.document.end_document_called) - end - - def test_end_element - @parser.parse_memory(<<~eoxml) -

Paragraph 1

- eoxml - assert_equal([["p"]], @parser.document.end_elements) - end - - def test_start_element_attrs - @parser.parse_memory(<<~eoxml) -

Paragraph 1

- eoxml - assert_equal([["p", [["id", "asdfasdf"]]]], @parser.document.start_elements) - end - - def test_start_element_attrs_include_namespaces - @parser.parse_memory(<<~eoxml) -

Paragraph 1

- eoxml - assert_equal([["p", [["xmlns:foo", "http://foo.example.com/"]]]], - @parser.document.start_elements) - end - - def test_processing_instruction - @parser.parse_memory(<<~eoxml) - - - eoxml - assert_equal([["xml-stylesheet", 'href="a.xsl" type="text/xsl"']], - @parser.document.processing_instructions) - end - - def test_parse_document - skip_unless_libxml2("JRuby SAXParser only parses well-formed XML documents") - @parser.parse_memory(<<~eoxml) -

Paragraph 1

-

Paragraph 2

- eoxml - end - - def test_parser_attributes - xml = <<~eoxml - - eoxml - - block_called = false - @parser.parse(xml) do |ctx| - block_called = true - ctx.replace_entities = true - end - - assert(block_called) - - assert_equal([["root", []], ["foo", [["a", "&b"], ["c", ">d"]]]], @parser.document.start_elements) - end - - def test_recovery_from_incorrect_xml - xml = <<~eoxml - heyhey yourself - eoxml - - block_called = false - @parser.parse(xml) do |ctx| - block_called = true - ctx.recovery = true - end - - assert(block_called) - - assert_equal([["Root", []], ["Data", []], ["Item", []], ["Data", []], ["Item", []]], - @parser.document.start_elements) - end - - def test_square_bracket_in_text # issue 1261 - xml = <<~eoxml - - en:#:home_page:#:stories:#:[6]:#:name - Sandy S. - - eoxml - @parser.parse(xml) - assert_includes(@parser.document.data, "en:#:home_page:#:stories:#:[6]:#:name") - end - - def test_large_cdata_is_handled - # see #2132 and https://gitlab.gnome.org/GNOME/libxml2/-/issues/200 - skip("Upstream libxml2 <= 2.9.10 needs to be patched") if Nokogiri::VersionInfo.instance.libxml2_using_system? - - template = <<~EOF - - - - - gorilla - secret - - - - - - - - - EOF - - factor = 10 - huge_data = "a" * (1024 * 1024 * factor) - xml = StringIO.new(template % (huge_data)) - - handler = Nokogiri::SAX::TestCase::Doc.new - parser = Nokogiri::XML::SAX::Parser.new(handler) - parser.parse(xml) - - assert_predicate(handler.errors, :empty?) - end +class Nokogiri::SAX::TestCase + describe Nokogiri::XML::SAX::Parser do + let(:parser) { Nokogiri::XML::SAX::Parser.new(Doc.new) } + + it :test_parser_context_yielded_io do + doc = Doc.new + parser = Nokogiri::XML::SAX::Parser.new(doc) + xml = "" + + block_called = false + parser.parse(StringIO.new(xml)) do |ctx| + block_called = true + ctx.replace_entities = true end + + assert(block_called) + + assert_equal([["foo", [["a", "&b"]]]], doc.start_elements) + end + + it :test_parser_context_yielded_in_memory do + doc = Doc.new + parser = Nokogiri::XML::SAX::Parser.new(doc) + xml = "" + + block_called = false + parser.parse(xml) do |ctx| + block_called = true + ctx.replace_entities = true + end + + assert(block_called) + + assert_equal([["foo", [["a", "&b"]]]], doc.start_elements) + end + + it :test_empty_decl do + parser = Nokogiri::XML::SAX::Parser.new(Doc.new) + + xml = "" + parser.parse(xml) + assert(parser.document.start_document_called, xml) + assert_nil(parser.document.xmldecls, xml) + end + + it :test_xml_decl do + [ + ['', ["1.0"]], + ['', ["1.0", "UTF-8"]], + ['', ["1.0", "yes"]], + ['', ["1.0", "no"]], + ['', ["1.0", "UTF-8", "no"]], + ['', ["1.0", "ISO-8859-1", "yes"]], + ].each do |decl, value| + parser = Nokogiri::XML::SAX::Parser.new(Doc.new) + + xml = "#{decl}\n" + parser.parse(xml) + assert(parser.document.start_document_called, xml) + assert_equal(value, parser.document.xmldecls, xml) + end + end + + it :test_parse_empty do + assert_raises(RuntimeError) do + parser.parse("") + end + end + + it :test_namespace_declaration_order_is_saved do + parser.parse(<<~EOF) + +
+ + EOF + assert_equal(2, parser.document.start_elements_namespace.length) + el = parser.document.start_elements_namespace.first + namespaces = el.last + assert_equal(["foo", "http://foo.example.com/"], namespaces.first) + assert_equal([nil, "http://example.com/"], namespaces.last) + end + + it :test_bad_document_calls_error_handler do + parser.parse("") + assert(parser.document.errors) + assert(parser.document.errors.length > 0) + end + + it :test_namespace_are_super_fun_to_parse do + parser.parse(<<~EOF) + + + + + + hello world + + EOF + + assert(parser.document.start_elements_namespace.length > 0) + el = parser.document.start_elements_namespace[1] + assert_equal("a", el.first) + assert_equal(1, el[1].length) + + attribute = el[1].first + assert_equal("bar", attribute.localname) + assert_equal("foo", attribute.prefix) + assert_equal("hello", attribute.value) + assert_equal("http://foo.example.com/", attribute.uri) + end + + it :test_sax_v1_namespace_attribute_declarations do + parser.parse(<<~EOF) + + + + + + hello world + + EOF + assert(parser.document.start_elements.length > 0) + elm = parser.document.start_elements.first + assert_equal("root", elm.first) + assert(elm[1].include?(["xmlns:foo", "http://foo.example.com/"])) + assert(elm[1].include?(["xmlns", "http://example.com/"])) + end + + it :test_sax_v1_namespace_nodes do + parser.parse(<<~EOF) + + + + + + hello world + + EOF + assert_equal(5, parser.document.start_elements.length) + assert(parser.document.start_elements.map(&:first).include?("foo:bar")) + assert(parser.document.end_elements.map(&:first).include?("foo:bar")) + end + + it :test_start_is_called_without_namespace do + parser.parse(<<~EOF) + + + + EOF + assert_equal( + ["root", "foo:f", "bar"], + parser.document.start_elements.map(&:first) + ) + end + + it :test_parser_sets_encoding do + parser = Nokogiri::XML::SAX::Parser.new(Doc.new, "UTF-8") + assert_equal("UTF-8", parser.encoding) + end + + it :test_errors_set_after_parsing_bad_dom do + doc = Nokogiri::XML("") + assert(doc.errors) + + parser.parse("") + assert(parser.document.errors) + assert(parser.document.errors.length > 0) + + doc.errors.each do |error| + assert_equal("UTF-8", error.message.encoding.name) + end + + # when using JRuby Nokogiri, more errors will be generated as the DOM + # parser continue to parse an ill formed document, while the sax parser + # will stop at the first error + unless Nokogiri.jruby? + assert_equal(doc.errors.length, parser.document.errors.length) + end + end + + it :test_parse_with_memory_argument do + parser.parse(File.read(XML_FILE)) + assert(parser.document.cdata_blocks.length > 0) + end + + it :test_parse_with_io_argument do + File.open(XML_FILE, "rb") do |f| + parser.parse(f) + end + assert(parser.document.cdata_blocks.length > 0) + end + + it :test_parse_io do + call_parse_io_with_encoding("UTF-8") + end + + # issue #828 + it :test_parse_io_lower_case_encoding do + call_parse_io_with_encoding("utf-8") + end + + def call_parse_io_with_encoding(encoding) + File.open(XML_FILE, "rb") do |f| + parser.parse_io(f, encoding) + end + assert(parser.document.cdata_blocks.length > 0) + + called = false + parser.document.start_elements.flatten.each do |thing| + assert_equal("UTF-8", thing.encoding.name) + called = true + end + assert(called) + + called = false + parser.document.end_elements.flatten.each do |thing| + assert_equal("UTF-8", thing.encoding.name) + called = true + end + assert(called) + + called = false + parser.document.data.each do |thing| + assert_equal("UTF-8", thing.encoding.name) + called = true + end + assert(called) + + called = false + parser.document.comments.flatten.each do |thing| + assert_equal("UTF-8", thing.encoding.name) + called = true + end + assert(called) + + called = false + parser.document.cdata_blocks.flatten.each do |thing| + assert_equal("UTF-8", thing.encoding.name) + called = true + end + assert(called) + end + + it :test_parse_file do + parser.parse_file(XML_FILE) + + assert_raises(ArgumentError) do + parser.parse_file(nil) + end + + assert_raises(Errno::ENOENT) do + parser.parse_file("") + end + assert_raises(Errno::EISDIR) do + parser.parse_file(File.expand_path(File.dirname(__FILE__))) + end + end + + it :test_render_parse_nil_param do + assert_raises(ArgumentError) { parser.parse_memory(nil) } + end + + it :test_bad_encoding_args do + assert_raises(ArgumentError) { Nokogiri::XML::SAX::Parser.new(Doc.new, "not an encoding") } + assert_raises(ArgumentError) { parser.parse_io(StringIO.new(""), "not an encoding") } + end + + it :test_ctag do + parser.parse_memory(<<~EOF) +

+ + Paragraph 1 +

+ EOF + assert_equal([" This is a comment "], parser.document.cdata_blocks) + end + + it :test_comment do + parser.parse_memory(<<~EOF) +

+ + Paragraph 1 +

+ EOF + assert_equal([" This is a comment "], parser.document.comments) + end + + it :test_characters do + parser.parse_memory(<<~EOF) +

Paragraph 1

+ EOF + assert_equal(["Paragraph 1"], parser.document.data) + end + + it :test_end_document do + parser.parse_memory(<<~EOF) +

Paragraph 1

+ EOF + assert(parser.document.end_document_called) + end + + it :test_end_element do + parser.parse_memory(<<~EOF) +

Paragraph 1

+ EOF + assert_equal([["p"]], parser.document.end_elements) + end + + it :test_start_element_attrs do + parser.parse_memory(<<~EOF) +

Paragraph 1

+ EOF + assert_equal([["p", [["id", "asdfasdf"]]]], parser.document.start_elements) + end + + it :test_start_element_attrs_include_namespaces do + parser.parse_memory(<<~EOF) +

Paragraph 1

+ EOF + assert_equal( + [["p", [["xmlns:foo", "http://foo.example.com/"]]]], + parser.document.start_elements + ) + end + + it :test_processing_instruction do + parser.parse_memory(<<~EOF) + + + EOF + assert_equal( + [["xml-stylesheet", 'href="a.xsl" type="text/xsl"']], + parser.document.processing_instructions + ) + end + + it :test_parse_document do + skip_unless_libxml2("JRuby SAXParser only parses well-formed XML documents") + parser.parse_memory(<<~EOF) +

Paragraph 1

+

Paragraph 2

+ EOF + end + + it :test_parser_attributes do + xml = <<~EOF + + EOF + + block_called = false + parser.parse(xml) do |ctx| + block_called = true + ctx.replace_entities = true + end + + assert(block_called) + + assert_equal( + [["root", []], ["foo", [["a", "&b"], ["c", ">d"]]]], parser.document.start_elements + ) + end + + it :test_recovery_from_incorrect_xml do + xml = <<~EOF + heyhey yourself + EOF + + block_called = false + parser.parse(xml) do |ctx| + block_called = true + ctx.recovery = true + end + + assert(block_called) + + assert_equal( + [["Root", []], ["Data", []], ["Item", []], ["Data", []], ["Item", []]], + parser.document.start_elements + ) + end + + it :test_square_bracket_in_text do + # issue 1261 + xml = <<~EOF + + en:#:home_page:#:stories:#:[6]:#:name + Sandy S. + + EOF + parser.parse(xml) + assert_includes(parser.document.data, "en:#:home_page:#:stories:#:[6]:#:name") + end + + it :test_large_cdata_is_handled do + # see #2132 and https://gitlab.gnome.org/GNOME/libxml2/-/issues/200 + skip("Upstream libxml2 <= 2.9.10 needs to be patched") if Nokogiri::VersionInfo.instance.libxml2_using_system? + + template = <<~EOF + + + + + gorilla + secret + + + + + + + + + EOF + + factor = 10 + huge_data = "a" * (1024 * 1024 * factor) + xml = StringIO.new(template % huge_data) + + handler = Nokogiri::SAX::TestCase::Doc.new + parser = Nokogiri::XML::SAX::Parser.new(handler) + parser.parse(xml) + + assert_predicate(handler.errors, :empty?) end end end diff --git a/test/xml/sax/test_push_parser.rb b/test/xml/sax/test_push_parser.rb index 587bd54a1a..dfab1793fa 100644 --- a/test/xml/sax/test_push_parser.rb +++ b/test/xml/sax/test_push_parser.rb @@ -1,266 +1,243 @@ # -*- coding: utf-8 -*- +# frozen_string_literal: true require "helper" -module Nokogiri - module XML - module SAX - class TestPushParser < Nokogiri::SAX::TestCase - def setup - super - @parser = XML::SAX::PushParser.new(Doc.new) - end - - def test_exception - assert_raises(SyntaxError) do - @parser << "" - end - - assert_raises(SyntaxError) do - @parser << nil - end - end +class Nokogiri::SAX::TestCase + describe Nokogiri::XML::SAX::PushParser do + let(:parser) { Nokogiri::XML::SAX::PushParser.new(Doc.new) } - def test_early_finish - @parser << "" - assert_raises(SyntaxError) do - @parser.finish - end - end + it :test_exception do + assert_raises(Nokogiri::XML::SyntaxError) do + parser << "" + end - def test_write_last_chunk - @parser << "" - @parser.write "", true - assert_equal [["foo", []]], @parser.document.start_elements - assert_equal [["foo"]], @parser.document.end_elements - end + assert_raises(Nokogiri::XML::SyntaxError) do + parser << nil + end + end - def test_empty_doc - @parser.options |= XML::ParseOptions::RECOVER - @parser.write "", true - assert_nil @parser.document.start_elements - assert_nil @parser.document.end_elements - end + it :test_early_finish do + parser << "" + assert_raises(Nokogiri::XML::SyntaxError) do + parser.finish + end + end + it :test_write_last_chunk do + parser << "" + parser.write("", true) + assert_equal [["foo", []]], parser.document.start_elements + assert_equal [["foo"]], parser.document.end_elements + end - def test_finish_should_rethrow_last_error - begin - @parser << "" - rescue => e - expected = e - end + it :test_empty_doc do + parser.options |= Nokogiri::XML::ParseOptions::RECOVER + parser.write("", true) + assert_nil parser.document.start_elements + assert_nil parser.document.end_elements + end - begin - @parser.finish - rescue => e - actual = e - end + it :test_finish_should_rethrow_last_error do + expected = assert_raise(Nokogiri::XML::SyntaxError) { parser << "" } + actual = assert_raise(Nokogiri::XML::SyntaxError) { parser.finish } + assert_equal actual.message, expected.message + end - assert_equal actual.message, expected.message + it :test_should_throw_error_returned_by_document do + doc = Doc.new + class << doc + def error(msg) + raise "parse error" end + end + parser = Nokogiri::XML::SAX::PushParser.new(doc) - def test_should_throw_error_returned_by_document - doc = Doc.new - class << doc - def error msg - raise "parse error" - end - end - - @parser = XML::SAX::PushParser.new(doc) - begin - @parser << "" - rescue => e - actual = e - end - fail 'PushParser should throw error when fed ill-formed data' if actual.nil? - - assert_equal actual.message, "parse error" - end + exception = assert_raise(RuntimeError) { parser << "" } + assert_equal exception.message, "parse error" + end - def test_writing_nil - assert_equal @parser.write(nil), @parser - end + it :test_writing_nil do + assert_equal parser.write(nil), parser + end - def test_end_document_called - @parser.<<(<<-eoxml) -

- - Paragraph 1 -

- eoxml - assert ! @parser.document.end_document_called - @parser.finish - assert @parser.document.end_document_called - end + it :test_end_document_called do + parser.<<(<<~EOF) +

+ + Paragraph 1 +

+ EOF + assert !parser.document.end_document_called + parser.finish + assert parser.document.end_document_called + end - def test_start_element - @parser.<<(<<-eoxml) -

- eoxml - - assert_equal [["p", [["id", "asdfasdf"]]]], - @parser.document.start_elements - - @parser.<<(<<-eoxml) - - Paragraph 1 -

- eoxml - assert_equal [' This is a comment '], @parser.document.comments - @parser.finish - end + it :test_start_element do + parser.<<(<<~EOF) +

+ EOF + + assert_equal [["p", [["id", "asdfasdf"]]]], + parser.document.start_elements + + parser.<<(<<~EOF) + + Paragraph 1 +

+ EOF + assert_equal [" This is a comment "], parser.document.comments + parser.finish + end - def test_start_element_with_namespaces - @parser.<<(<<-eoxml) -

- eoxml - - assert_equal [["p", [["xmlns:foo", "http://foo.example.com/"]]]], - @parser.document.start_elements - - @parser.<<(<<-eoxml) - - Paragraph 1 -

- eoxml - assert_equal [' This is a comment '], @parser.document.comments - @parser.finish - end + it :test_start_element_with_namespaces do + parser.<<(<<~EOF) +

+ EOF + + assert_equal [["p", [["xmlns:foo", "http://foo.example.com/"]]]], + parser.document.start_elements + + parser.<<(<<~EOF) + + Paragraph 1 +

+ EOF + assert_equal [" This is a comment "], parser.document.comments + parser.finish + end - def test_start_element_ns - @parser.<<(<<-eoxml) - - eoxml + it :test_start_element_ns do + parser.<<(<<~EOF) + + EOF - assert_equal 1, @parser.document.start_elements_namespace.length - el = @parser.document.start_elements_namespace.first + assert_equal 1, parser.document.start_elements_namespace.length + el = parser.document.start_elements_namespace.first - assert_equal 'stream', el.first - assert_equal 2, el[1].length - assert_equal [['version', '1.0'], ['size', 'large']], - el[1].map { |x| [x.localname, x.value] } + assert_equal "stream", el.first + assert_equal 2, el[1].length + assert_equal [["version", "1.0"], ["size", "large"]], + el[1].map { |x| [x.localname, x.value] } - assert_equal 'stream', el[2] - assert_equal 'http://etherx.jabber.org/streams', el[3] - @parser.finish - end + assert_equal "stream", el[2] + assert_equal "http://etherx.jabber.org/streams", el[3] + parser.finish + end - def test_end_element_ns - @parser.<<(<<-eoxml) - - eoxml + it :test_end_element_ns do + parser.<<(<<~EOF) + + EOF - assert_equal [['stream', 'stream', 'http://etherx.jabber.org/streams']], - @parser.document.end_elements_namespace - @parser.finish - end + assert_equal [["stream", "stream", "http://etherx.jabber.org/streams"]], + parser.document.end_elements_namespace + parser.finish + end - def test_chevron_partial_xml - @parser.<<(<<-eoxml) -

- eoxml - - @parser.<<(<<-eoxml) - - Paragraph 1 -

- eoxml - assert_equal [' This is a comment '], @parser.document.comments - @parser.finish - end + it :test_chevron_partial_xml do + parser.<<(<<~EOF) +

+ EOF + + parser.<<(<<~EOF) + + Paragraph 1 +

+ EOF + assert_equal [" This is a comment "], parser.document.comments + parser.finish + end - def test_chevron - @parser.<<(<<-eoxml) -

- - Paragraph 1 -

- eoxml - @parser.finish - assert_equal [' This is a comment '], @parser.document.comments - end + it :test_chevron do + parser.<<(<<~EOF) +

+ + Paragraph 1 +

+ EOF + parser.finish + assert_equal [" This is a comment "], parser.document.comments + end - def test_default_options - assert_equal 0, @parser.options - end + it :test_default_options do + assert_equal 0, parser.options + end - def test_recover - @parser.options |= XML::ParseOptions::RECOVER - @parser.<<(<<-eoxml) -

- Foo - - Bar -

- eoxml - @parser.finish - assert(@parser.document.errors.size >= 1) - assert_equal [["p", []], ["bar", []]], @parser.document.start_elements - assert_equal "FooBar", @parser.document.data.map { |x| - x.gsub(/\s/, '') - }.join - end + it :test_recover do + parser.options |= Nokogiri::XML::ParseOptions::RECOVER + parser.<<(<<~EOF) +

+ Foo + + Bar +

+ EOF + parser.finish + assert(parser.document.errors.size >= 1) + assert_equal [["p", []], ["bar", []]], parser.document.start_elements + assert_equal "FooBar", parser.document.data.map { |x| + x.gsub(/\s/, "") + }.join + end - def test_broken_encoding - skip_unless_libxml2("ultra hard to fix for pure Java version") - @parser.options |= XML::ParseOptions::RECOVER - # This is ISO_8859-1: - @parser.<< "Gau\337" - @parser.finish - assert(@parser.document.errors.size >= 1) - assert_equal "Gau\337", @parser.document.data.join - assert_equal [["r"]], @parser.document.end_elements - end + it :test_broken_encoding do + skip_unless_libxml2("ultra hard to fix for pure Java version") + parser.options |= Nokogiri::XML::ParseOptions::RECOVER + # This is ISO_8859-1: + parser.<< "Gau\337" + parser.finish + assert(parser.document.errors.size >= 1) + assert_equal "Gau\337", parser.document.data.join + assert_equal [["r"]], parser.document.end_elements + end - def test_replace_entities_attribute_behavior - if Nokogiri.uses_libxml? - # initially false - assert_equal false, @parser.replace_entities - - # can be set to true - @parser.replace_entities = true - assert_equal true, @parser.replace_entities - - # can be set to false - @parser.replace_entities = false - assert_equal false, @parser.replace_entities - else - # initially true - assert_equal true, @parser.replace_entities - - # ignore attempts to set to false - @parser.replace_entities = false # TODO: should we raise an exception here? - assert_equal true, @parser.replace_entities - end - end + it :test_replace_entities_attribute_behavior do + if Nokogiri.uses_libxml? + # initially false + assert_equal false, parser.replace_entities + + # can be set to true + parser.replace_entities = true + assert_equal true, parser.replace_entities + + # can be set to false + parser.replace_entities = false + assert_equal false, parser.replace_entities + else + # initially true + assert_equal true, parser.replace_entities + + # ignore attempts to set to false + parser.replace_entities = false # TODO: should we raise an exception here? + assert_equal true, parser.replace_entities + end + end - def test_untouched_entities - skip_unless_libxml2("entities are always replaced in pure Java version") - @parser.<<(<<-eoxml) -

- - Paragraph 1 & 2 -

- eoxml - @parser.finish - assert_equal [["p", [["id", "asdf&asdf"]]]], @parser.document.start_elements - assert_equal "Paragraph 1 & 2", @parser.document.data.join.strip - end + it :test_untouched_entities do + skip_unless_libxml2("entities are always replaced in pure Java version") + parser.<<(<<~EOF) +

+ + Paragraph 1 & 2 +

+ EOF + parser.finish + assert_equal [["p", [["id", "asdf&asdf"]]]], parser.document.start_elements + assert_equal "Paragraph 1 & 2", parser.document.data.join.strip + end - def test_replaced_entities - @parser.replace_entities = true - @parser.<<(<<-eoxml) -

- - Paragraph 1 & 2 -

- eoxml - @parser.finish - assert_equal [["p", [["id", "asdf&asdf"]]]], @parser.document.start_elements - assert_equal "Paragraph 1 & 2", @parser.document.data.join.strip - end - end + it :test_replaced_entities do + parser.replace_entities = true + parser.<<(<<~EOF) +

+ + Paragraph 1 & 2 +

+ EOF + parser.finish + assert_equal [["p", [["id", "asdf&asdf"]]]], parser.document.start_elements + assert_equal "Paragraph 1 & 2", parser.document.data.join.strip end end end