kotovalexarian-likes-github/ruby--ruby
1
0
Fork 0
mirror of https://github.com/ruby/ruby.git synced 2022-11-09 12:17:21 -05:00
Code Releases Activity

* lib/rexml/encoding.rb (REXML::Encoding#encoding=): store @encoding

Browse source 
a String which means the name of the encoding.
  this partially revert r29646.

* lib/rexml/document.rb: follow above.

* lib/rexml/output.rb: ditto.

* lib/rexml/parsers/baseparser.rb: ditto.

* lib/rexml/source.rb: ditto.

* lib/rexml/xmldecl.rb: ditto.

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@31008 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
naruse 2011-03-02 15:36:48 +00:00
parent cddcffb8f9
commit f25ff846f6
11 changed files with 114 additions and 147 deletions
Download patch file Download diff file Expand all files Collapse all files

16
ChangeLog
View file

@ -1,3 +1,19 @@
Thu Mar 3 00:36:29 2011 NARUSE, Yui <naruse@ruby-lang.org>
* lib/rexml/encoding.rb (REXML::Encoding#encoding=): store @encoding
a String which means the name of the encoding.
this partially revert r29646.
* lib/rexml/document.rb: follow above.
* lib/rexml/output.rb: ditto.
* lib/rexml/parsers/baseparser.rb: ditto.
* lib/rexml/source.rb: ditto.
* lib/rexml/xmldecl.rb: ditto.
Wed Mar 2 23:19:56 2011 Nobuyoshi Nakada <nobu@ruby-lang.org> Wed Mar 2 23:19:56 2011 Nobuyoshi Nakada <nobu@ruby-lang.org>
* string.c (str_byte_substr): return nil for negative length. * string.c (str_byte_substr): return nil for negative length.

2
lib/rexml/document.rb
View file

@ -184,7 +184,7 @@ module REXML
# that IE's limited abilities can handle. This hack inserts a space # that IE's limited abilities can handle. This hack inserts a space
# before the /> on empty tags. Defaults to false # before the /> on empty tags. Defaults to false
def write( output=$stdout, indent=-1, transitive=false, ie_hack=false ) def write( output=$stdout, indent=-1, transitive=false, ie_hack=false )
if xml_decl.encoding != ::Encoding::UTF_8 && !output.kind_of?(Output) if xml_decl.encoding != 'UTF-8' && !output.kind_of?(Output)
output = Output.new( output, xml_decl.encoding ) output = Output.new( output, xml_decl.encoding )
end end
formatter = if indent > -1 formatter = if indent > -1

42
lib/rexml/encoding.rb
View file

@ -1,8 +1,9 @@
module REXML module REXML
module Encoding module Encoding
# ID ---> Encoding object # ID ---> Encoding name
attr_reader :encoding attr_reader :encoding
def encoding=(encoding) def encoding=(encoding)
encoding = encoding.name if encoding.is_a?(Encoding)
if encoding.is_a?(String) if encoding.is_a?(String)
original_encoding = encoding original_encoding = encoding
encoding = find_encoding(encoding) encoding = find_encoding(encoding)
@ -11,35 +12,25 @@ module REXML
end end
end end
return false if defined?(@encoding) and encoding == @encoding return false if defined?(@encoding) and encoding == @encoding
if encoding and encoding != ::Encoding::UTF_8 if encoding
@encoding = encoding @encoding = encoding.upcase
else else
@encoding = ::Encoding::UTF_8 @encoding = 'UTF-8'
end end
true true
end end
def check_encoding(xml) def check_encoding(xml)
# We have to recognize UTF-16, LSB UTF-16, and UTF-8 # We have to recognize UTF-16BE, UTF-16LE, and UTF-8
if xml[0, 2] == "\xfe\xff" if xml[0, 2] == "\xfe\xff"
xml[0, 2] = "" xml[0, 2] = ""
::Encoding::UTF_16BE return 'UTF-16BE'
elsif xml[0, 2] == "\xff\xfe" elsif xml[0, 2] == "\xff\xfe"
xml[0, 2] = "" xml[0, 2] = ""
::Encoding::UTF_16LE return 'UTF-16LE'
else
if /\A\s*<\?xml\s+version\s*=\s*(['"]).*?\1
\s+encoding\s*=\s*(["'])(.*?)\2/mx =~ xml
encoding_name = $3
if /\Autf-16\z/i =~ encoding_name
::Encoding::UTF_16BE
else
find_encoding(encoding_name)
end
else
::Encoding::UTF_8
end
end end
xml =~ /^\s*<\?xml\s+version\s*=\s*(['"]).*?\1\s+encoding\s*=\s*(["'])(.*?)\2/m
return $3 ? $3.upcase : 'UTF-8'
end end
def encode(string) def encode(string)
@ -53,14 +44,19 @@ module REXML
private private
def find_encoding(name) def find_encoding(name)
case name case name
when "UTF-16"
name = "UTF-16BE"
when /\Ashift-jis\z/i when /\Ashift-jis\z/i
name = "Shift_JIS" return "SHIFT_JIS"
when /\ACP-(\d+)\z/ when /\ACP-(\d+)\z/
name = "CP#{$1}" name = "CP#{$1}"
when /\AUTF-8\z/i
return name
end end
::Encoding.find(name) begin
::Encoding::Converter.search_convpath(name, 'UTF-8')
rescue ::Encoding::ConverterNotFoundError
return nil
end
name
end end
end end
end end

2
lib/rexml/formatters/default.rb
View file

@ -22,7 +22,7 @@ module REXML
case node case node
when Document when Document
if node.xml_decl.encoding != ::Encoding::UTF_8 && !output.kind_of?(Output) if node.xml_decl.encoding != 'UTF-8' && !output.kind_of?(Output)
output = Output.new( output, node.xml_decl.encoding ) output = Output.new( output, node.xml_decl.encoding )
end end
write_document( node, output ) write_document( node, output )

2
lib/rexml/output.rb
View file

@ -10,7 +10,7 @@ module REXML
@output = real_IO @output = real_IO
self.encoding = encd self.encoding = encd
@to_utf = (@encoding != ::Encoding::UTF_8) @to_utf = encd != 'UTF-8'
end end
def <<( content ) def <<( content )

2
lib/rexml/parsers/baseparser.rb
View file

@ -248,7 +248,7 @@ module REXML
@document_status = :after_doctype @document_status = :after_doctype
@source.read if @source.buffer.size<2 @source.read if @source.buffer.size<2
md = @source.match(/\s*/um, true) md = @source.match(/\s*/um, true)
if @source.encoding == ::Encoding::UTF_8 if @source.encoding == "UTF-8"
@source.buffer.force_encoding(::Encoding::UTF_8) @source.buffer.force_encoding(::Encoding::UTF_8)
end end
end end

6
lib/rexml/source.rb
View file

@ -54,14 +54,12 @@ module REXML
def encoding=(enc) def encoding=(enc)
return unless super return unless super
@line_break = encode( '>' ) @line_break = encode( '>' )
if @encoding != ::Encoding::UTF_8 if @encoding != 'UTF-8'
@buffer = decode(@buffer) @buffer = decode(@buffer)
@to_utf = true @to_utf = true
else else
@to_utf = false @to_utf = false
if @buffer.respond_to? :force_encoding @buffer.force_encoding ::Encoding::UTF_8
@buffer.force_encoding ::Encoding::UTF_8
end
end end
end end

13
lib/rexml/xmldecl.rb
View file

@ -109,20 +109,9 @@ module REXML
end end
private private
def normalized_encoding_name(_encoding)
if _encoding == ::Encoding::UTF_16BE
"UTF-16"
else
return _encoding.name
end
end
def content(enc) def content(enc)
rv = "version='#@version'" rv = "version='#@version'"
if @writeencoding || enc.to_s !~ /\Autf-8\z/i rv << " encoding='#{enc}'" if @writeencoding || enc !~ /utf-8/i
encoding_name = normalized_encoding_name(enc)
rv << " encoding='#{encoding_name}'"
end
rv << " standalone='#@standalone'" if @standalone rv << " standalone='#@standalone'" if @standalone
rv rv
end end

16
test/rexml/test_contrib.rb
View file

@ -241,7 +241,7 @@ DELIMITER
end end
doc = REXML::Document.new(source_iso) doc = REXML::Document.new(source_iso)
assert_equal('ISO-8859-1', doc.xml_decl.encoding.to_s) assert_equal('ISO-8859-1', doc.xml_decl.encoding)
assert_equal(koln_utf, doc.root.text) assert_equal(koln_utf, doc.root.text)
doc.write(out="") doc.write(out="")
assert_equal(source_iso, out ) assert_equal(source_iso, out )
@ -255,23 +255,21 @@ DELIMITER
<position><aktuell datum="01-10-11">Technik</aktuell></position> <position><aktuell datum="01-10-11">Technik</aktuell></position>
<hauptspalte> <hauptspalte>
<headline>Technik</headline> <headline>Technik</headline>
Die Technik ist das Rückgrat der meisten Geschäftsprozesse bei Home of the Brave. Deshalb sollen hier alle relevanten technischen Abläufe, Daten und Einrichtungen beschrieben werden, damit jeder im Bedarfsfall die nötigen Informationen, Anweisungen und Verhaltensempfehlungen nachlesen und/oder abrufen kann. Die Technik ist das R\xFCckgrat der meisten Gesch\xFCftsprozesse bei Home of the Brave. Deshalb sollen hier alle relevanten technischen Abl\xFCufe, Daten und Einrichtungen beschrieben werden, damit jeder im Bedarfsfall die n\xFCtigen Informationen, Anweisungen und Verhaltensempfehlungen nachlesen und/oder abrufen kann.
</hauptspalte> </hauptspalte>
<nebenspalte> <nebenspalte>
<link ziel="Flash/">Flash</link><umbruch/> <link ziel="Flash/">Flash</link><umbruch/>
Nützliches von Flashern für Flasher.<umbruch/> N\xFCtzliches von Flashern f\xFCr Flasher.<umbruch/>
<link neu="ja" ziel="Cvs/">CVS-FAQ</link><umbruch/> <link neu="ja" ziel="Cvs/">CVS-FAQ</link><umbruch/>
FAQ zur Benutzung von CVS bei HOB FAQ zur Benutzung von CVS bei HOB
</nebenspalte> </nebenspalte>
</intranet> </intranet>
EOF EOF
tn = XPath.first(doc, "//nebenspalte/text()[2]") tn = XPath.first(doc, "//nebenspalte/text()[2]")
expected_iso = "Nützliches von Flashern für Flasher." expected_iso = "N\xFCtzliches von Flashern f\xFCr Flasher."
expected_utf = expected_iso.unpack('C*').pack('U*') expected_utf = expected_iso.unpack('C*').pack('U*')
if expected_utf.respond_to? :encode expected_iso.force_encoding(::Encoding::ISO_8859_1)
expected_iso.force_encoding("iso-8859-1") expected_utf.force_encoding(::Encoding::UTF_8)
expected_utf.force_encoding(::Encoding::UTF_8)
end
assert_equal(expected_utf, tn.to_s.strip) assert_equal(expected_utf, tn.to_s.strip)
f = REXML::Formatters::Default.new f = REXML::Formatters::Default.new
f.write( tn, Output.new(o = "", "ISO-8859-1") ) f.write( tn, Output.new(o = "", "ISO-8859-1") )

138
test/rexml/test_core.rb
View file

@ -20,7 +20,7 @@ class Tester < Test::Unit::TestCase
<?xsl stylesheet="blah.xsl"?> <?xsl stylesheet="blah.xsl"?>
<!-- The first line tests the XMLDecl, the second tests PI. <!-- The first line tests the XMLDecl, the second tests PI.
The next line tests DocType. This line tests comments. --> The next line tests DocType. This line tests comments. -->
<!DOCTYPE xsa PUBLIC <!DOCTYPE xsa PUBLIC
"-//LM Garshol//DTD XML Software Autoupdate 1.0//EN//XML" "-//LM Garshol//DTD XML Software Autoupdate 1.0//EN//XML"
"http://www.garshol.priv.no/download/xsa/xsa.dtd"> "http://www.garshol.priv.no/download/xsa/xsa.dtd">
@ -80,7 +80,7 @@ class Tester < Test::Unit::TestCase
# This because of a reported bug in attribute handling in 1.0a8 # This because of a reported bug in attribute handling in 1.0a8
source = '<a att="A">blah</a>' source = '<a att="A">blah</a>'
doc = Document.new source doc = Document.new source
doc.elements.each do |a| doc.elements.each do |a|
a.attributes['att'] << 'B' a.attributes['att'] << 'B'
assert_equal "AB", a.attributes['att'] assert_equal "AB", a.attributes['att']
a.attributes['att'] = 'C' a.attributes['att'] = 'C'
@ -155,11 +155,11 @@ class Tester < Test::Unit::TestCase
assert_equal 3, doc.root.size assert_equal 3, doc.root.size
assert_equal 1, doc.root.elements.size assert_equal 1, doc.root.elements.size
text = " This is text text = " This is text
with a lot of whitespace " with a lot of whitespace "
source = "<a>#{text}<b>#{text}</b><c>#{text}</c>#{text}</a>" source = "<a>#{text}<b>#{text}</b><c>#{text}</c>#{text}</a>"
doc = Document.new( source, { doc = Document.new( source, {
:respect_whitespace => %w{ a c } :respect_whitespace => %w{ a c }
} ) } )
assert_equal text, doc.elements["//c"].text assert_equal text, doc.elements["//c"].text
@ -207,8 +207,8 @@ class Tester < Test::Unit::TestCase
doc.write(test="") doc.write(test="")
assert_equal(correct, test) assert_equal(correct, test)
multi_line_source = '<!DOCTYPE xsa PUBLIC multi_line_source = '<!DOCTYPE xsa PUBLIC
"-//LM Garshol//DTD XML Software Autoupdate 1.0//EN//XML" "-//LM Garshol//DTD XML Software Autoupdate 1.0//EN//XML"
"http://www.garshol.priv.no/download/xsa/xsa.dtd"> "http://www.garshol.priv.no/download/xsa/xsa.dtd">
<a/>' <a/>'
d = Document.new( multi_line_source ) d = Document.new( multi_line_source )
@ -217,8 +217,8 @@ class Tester < Test::Unit::TestCase
doc.write(test="") doc.write(test="")
assert_equal(correct, test) assert_equal(correct, test)
odd_space_source = ' <!DOCTYPE odd_space_source = ' <!DOCTYPE
xsa PUBLIC "-//LM Garshol//DTD XML Software Autoupdate 1.0//EN//XML" xsa PUBLIC "-//LM Garshol//DTD XML Software Autoupdate 1.0//EN//XML"
"http://www.garshol.priv.no/download/xsa/xsa.dtd"> <a/>' "http://www.garshol.priv.no/download/xsa/xsa.dtd"> <a/>'
d = Document.new( odd_space_source ) d = Document.new( odd_space_source )
dt = d.doctype dt = d.doctype
@ -230,34 +230,12 @@ class Tester < Test::Unit::TestCase
doc = Document.new(docin) doc = Document.new(docin)
doc.write(test="") doc.write(test="")
assert_equal(31, doc.doctype.size) assert_equal(31, doc.doctype.size)
# Here's a little ditty from Tobias...
src = <<-EOL
<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.0//EN"
"http://www.w3.org/TR/SVG/DTD/svg10.dtd"
[
<!-- <!ENTITY % fast-slow "0 0 .5 1">-->
<!--<!ENTITY % slow-fast ".5 0 1 1">-->
<!ENTITY hover_ani
'<animateTransform attributeName="transform"
type="scale" restart="whenNotActive" values="1;0.96"
dur="0.5s" calcMode="spline" keySplines="0 0 .5 1"
fill="freeze" begin="mouseover"/>
<animateTransform attributeName="transform"
type="scale" restart="whenNotActive" values="0.96;1"
dur="0.5s" calcMode="spline" keySplines=".5 0 1 1"
fill="freeze" begin="mouseover+0.5s"/>'
>
]
> <a/>
EOL
end end
def test_document def test_document
# Testing cloning # Testing cloning
source = "<element/>" source = "<element/>"
doc = Document.new source doc = Document.new source
doc2 = Document.new doc
# Testing Root # Testing Root
assert_equal doc.root.name.to_s, "element" assert_equal doc.root.name.to_s, "element"
@ -266,7 +244,7 @@ class Tester < Test::Unit::TestCase
source = @xsa_source source = @xsa_source
doc = Document.new source doc = Document.new source
assert_instance_of XMLDecl, doc.xml_decl assert_instance_of XMLDecl, doc.xml_decl
assert_instance_of DocType, doc.doctype assert_instance_of DocType, doc.doctype
assert_equal doc.version, "1.0" assert_equal doc.version, "1.0"
source = File.new(fixture_path("dash.xml")) source = File.new(fixture_path("dash.xml"))
@ -383,7 +361,7 @@ class Tester < Test::Unit::TestCase
assert_equal(string, text.to_s) assert_equal(string, text.to_s)
string2 = "<a>#{string}</a>" string2 = "<a>#{string}</a>"
doc = Document.new( string2, { doc = Document.new( string2, {
:raw => %w{ a b } :raw => %w{ a b }
} ) } )
f.write(doc,out="") f.write(doc,out="")
@ -463,7 +441,7 @@ class Tester < Test::Unit::TestCase
assert_equal "Datasets", child.name assert_equal "Datasets", child.name
} }
each_test(doc, "Project/Datasets/link", 2 ) each_test(doc, "Project/Datasets/link", 2 )
each_test(doc.root, "/Project/Description", 1) {|child| each_test(doc.root, "/Project/Description", 1) {|child|
assert_equal "Description", child.name assert_equal "Description", child.name
} }
each_test(doc.root, "./Description",1 ) { |child| each_test(doc.root, "./Description",1 ) { |child|
@ -642,11 +620,10 @@ class Tester < Test::Unit::TestCase
end end
def test_line def test_line
doc = Document.new File.new(fixture_path("bad.xml")) Document.new File.new(fixture_path("bad.xml"))
assert_fail "There should have been an error" assert_fail "There should have been an error"
rescue Exception rescue Exception
# We should get here # We should get here
er = $!
assert($!.line == 5, "Should have been an error on line 5, "+ assert($!.line == 5, "Should have been an error on line 5, "+
"but was reported as being on line #{$!.line}" ) "but was reported as being on line #{$!.line}" )
end end
@ -664,13 +641,11 @@ class Tester < Test::Unit::TestCase
def test_exception def test_exception
source = SourceFactory.create_from "<a/>" source = SourceFactory.create_from "<a/>"
p = ParseException.new( "dummy message", source ) p = ParseException.new( "dummy message", source )
s = p.to_s
begin begin
raise "dummy" raise "dummy"
rescue Exception rescue Exception
p.continued_exception = $! p.continued_exception = $!
end end
s = p.to_s
end end
def test_bad_content def test_bad_content
@ -682,7 +657,7 @@ class Tester < Test::Unit::TestCase
assert_equal "content>content", tree_gt.elements[1].text assert_equal "content>content", tree_gt.elements[1].text
# This isn't # This isn't
begin begin
tree_lt = Document.new in_lt Document.new in_lt
assert_fail "Should have gotten a parse error" assert_fail "Should have gotten a parse error"
rescue ParseException rescue ParseException
end end
@ -766,7 +741,7 @@ class Tester < Test::Unit::TestCase
doc.root.each_element_with_text( nil, 0, 'd', &block ) doc.root.each_element_with_text( nil, 0, 'd', &block )
assert_equal 0, arry.size assert_equal 0, arry.size
end end
def test_element_parse_stream def test_element_parse_stream
s = Source.new( "<a>some text</a>" ) s = Source.new( "<a>some text</a>" )
l = Listener.new l = Listener.new
@ -810,7 +785,7 @@ EOL
assert_equal('eeü'.force_encoding("UTF-8"), a.root.text) assert_equal('eeü'.force_encoding("UTF-8"), a.root.text)
end end
def test_element_decl def test_element_decl
element_decl = Source.new("<!DOCTYPE foo [ element_decl = Source.new("<!DOCTYPE foo [
<!ELEMENT bar (#PCDATA)> <!ELEMENT bar (#PCDATA)>
]>") ]>")
@ -824,7 +799,7 @@ EOL
<!DOCTYPE blah [ <!DOCTYPE blah [
<!ATTLIST blah <!ATTLIST blah
xmlns CDATA "foo"> xmlns CDATA "foo">
<!ATTLIST a <!ATTLIST a
bar CDATA "gobble" bar CDATA "gobble"
xmlns:one CDATA "two" xmlns:one CDATA "two"
> >
@ -855,17 +830,15 @@ EOL
def test_attlist_write def test_attlist_write
file=File.new(fixture_path("foo.xml")) file=File.new(fixture_path("foo.xml"))
doc=Document.new file doc=Document.new file
root = doc.root
out = '' out = ''
doc.write(out) doc.write(out)
end end
def test_more_namespaces def test_more_namespaces
assert_raise( REXML::UndefinedNamespaceException, assert_raise( REXML::UndefinedNamespaceException,
%Q{Should have gotten an Undefined Namespace error} ) { %Q{Should have gotten an Undefined Namespace error} ) {
doc1 = Document.new("<r><p><n:c/></p></r>") Document.new("<r><p><n:c/></p></r>")
} }
doc2 = Document.new("<r xmlns:n='1'><p><n:c/></p></r>") doc2 = Document.new("<r xmlns:n='1'><p><n:c/></p></r>")
es = XPath.match(doc2, '//c') es = XPath.match(doc2, '//c')
@ -916,7 +889,7 @@ EOL
end end
def test_oses_with_bad_EOLs def test_oses_with_bad_EOLs
d = Document.new("\n\n\n<?xml version='1.0'?>\n\n\n<a/>\n\n") Document.new("\n\n\n<?xml version='1.0'?>\n\n\n<a/>\n\n")
end end
# Contributed (with patch to fix bug) by Kouhei # Contributed (with patch to fix bug) by Kouhei
@ -955,25 +928,25 @@ EOL
end end
def test_accents def test_accents
docs = [ docs = [
%Q{<?xml version="1.0" encoding="ISO-8859-1"?> %Q{<?xml version="1.0" encoding="ISO-8859-1"?>
<gnuPod> <gnuPod>
<files> <files>
<file id="57" artist="Coralie Cl\357\277\275ent" /> <file id="57" artist="Coralie Cl\357\277\275ent" />
</files> </files>
</gnuPod>}, </gnuPod>},
'<?xml version="1.0" encoding="ISO-8859-1"?> '<?xml version="1.0" encoding="ISO-8859-1"?>
<gnuPod> <gnuPod>
<files> <files>
<file id="71" album="Astrakan Caf" /> <file id="71" album="Astrakan Caf" />
</files> </files>
</gnuPod>', </gnuPod>',
%Q{<?xml version="1.0" encoding="ISO-8859-1"?> %Q{<?xml version="1.0" encoding="ISO-8859-1"?>
<gnuPod> <gnuPod>
<files> <files>
<file id="71" album="Astrakan Caf\357\277\275eria" /> <file id="71" album="Astrakan Caf\357\277\275eria" />
</files> </files>
</gnuPod>}, </gnuPod>},
%Q{<?xml version="1.0" encoding="ISO-8859-1"?> %Q{<?xml version="1.0" encoding="ISO-8859-1"?>
<gnuPod> <gnuPod>
<files> <files>
@ -1024,7 +997,6 @@ EOL
document.write(s) document.write(s)
end end
def test_write_cdata def test_write_cdata
src = "<a>A</a>" src = "<a>A</a>"
doc = REXML::Document.new( src ) doc = REXML::Document.new( src )
@ -1045,15 +1017,15 @@ EOL
<x:b x:n="foo"/> <x:b x:n="foo"/>
</a> </a>
EOL EOL
d = REXML::Document.new( source ) d = Document.new( source )
assert_equal( 'foo', REXML::XPath.first(d.root, "//x:b/@x:n").value ) assert_equal( 'foo', REXML::XPath.first(d.root, "//x:b/@x:n").value )
assert_equal( nil, REXML::XPath.first(d.root, "//x:b/@x:n", {})) assert_equal( nil, REXML::XPath.first(d.root, "//x:b/@x:n", {}))
end end
def test_null_element_name def test_null_element_name
a = REXML::Document.new a = REXML::Document.new
assert_raise( RuntimeError ) { assert_raise( RuntimeError ) {
a.add_element( nil ) a.add_element( nil )
} }
end end
@ -1095,22 +1067,22 @@ EOL
# Ticket #44 # Ticket #44
t = REXML::Text.new( "&amp;", false, nil, true ) t = REXML::Text.new( "&amp;", false, nil, true )
assert_equal( "&amp;", t.to_s ) assert_equal( "&amp;", t.to_s )
t = REXML::Text.new("&amp;", false, false) t = REXML::Text.new("&amp;", false, false)
assert_equal( "&amp;amp;", t.to_s ) assert_equal( "&amp;amp;", t.to_s )
end end
def test_to_xpath def test_to_xpath
doc = REXML::Document.new( %q{<tag1> doc = REXML::Document.new( %q{<tag1>
<tag2 name="tag2"/> <tag2 name="tag2"/>
<tag2 name="tag2"/> <tag2 name="tag2"/>
</tag1>}) </tag1>})
names = %w{ /tag1/tag2[1] /tag1/tag2[2] } names = %w{ /tag1/tag2[1] /tag1/tag2[2] }
doc.root.elements.each_with_index {|el, i| doc.root.elements.each_with_index {|el, i|
assert_equal( names[i], el.xpath ) assert_equal( names[i], el.xpath )
} }
end end
def test_transitive def test_transitive
doc = REXML::Document.new( "<a/>") doc = REXML::Document.new( "<a/>")
s = "" s = ""
@ -1181,19 +1153,19 @@ EOL
doc = REXML::Document.new doc = REXML::Document.new
doc << REXML::XMLDecl.default doc << REXML::XMLDecl.default
doc << REXML::Element.new("a") doc << REXML::Element.new("a")
str = "" str = ""
doc.write(str) doc.write(str)
assert_equal("<a/>", str) assert_equal("<a/>", str)
doc = REXML::Document.new doc = REXML::Document.new
doc << REXML::XMLDecl.new("1.0", "UTF-8") doc << REXML::XMLDecl.new("1.0", "UTF-8")
doc << REXML::Element.new("a") doc << REXML::Element.new("a")
str = "" str = ""
doc.write(str) doc.write(str)
assert_equal("<?xml version='1.0' encoding='UTF-8'?><a/>", str) assert_equal("<?xml version='1.0' encoding='UTF-8'?><a/>", str)
end end
@ -1212,7 +1184,7 @@ EOL
def test_ticket_52 def test_ticket_52
source = "<!-- this is a single line comment -->" source = "<!-- this is a single line comment -->"
d = REXML::Document.new(source) d = REXML::Document.new(source)
d.write(k="") d.write(k="")
assert_equal( source, k ) assert_equal( source, k )
@ -1233,17 +1205,17 @@ EOL
def test_ticket_21 def test_ticket_21
src = "<foo bar=value/>" src = "<foo bar=value/>"
assert_raise( ParseException, "invalid XML should be caught" ) { assert_raise( ParseException, "invalid XML should be caught" ) {
d = REXML::Document.new(src) Document.new(src)
} }
begin begin
d = REXML::Document.new(src) Document.new(src)
rescue rescue
assert_match( /missing attribute quote/, $!.message ) assert_match( /missing attribute quote/, $!.message )
end end
end end
def test_ticket_63 def test_ticket_63
d = REXML::Document.new(File.new(fixture_path("t63-1.xml"))) Document.new(File.new(fixture_path("t63-1.xml")))
end end
def test_ticket_75 def test_ticket_75
@ -1256,7 +1228,7 @@ EOL
#- rexml sanity check (bugs in ruby 1.8.4, ruby 1.8.6) #- rexml sanity check (bugs in ruby 1.8.4, ruby 1.8.6)
xmldoc = Document.new("<test/>") xmldoc = Document.new("<test/>")
xmldoc << XMLDecl.new(XMLDecl::DEFAULT_VERSION, "UTF-8") xmldoc << XMLDecl.new(XMLDecl::DEFAULT_VERSION, "UTF-8")
content = ['61c3a927223c3e26'].pack("H*") content = ['61c3a927223c3e26'].pack("H*")
content.force_encoding('UTF-8') if content.respond_to?(:force_encoding) content.force_encoding('UTF-8') if content.respond_to?(:force_encoding)
#- is some UTF-8 text but just to make sure my editor won't magically convert.. #- is some UTF-8 text but just to make sure my editor won't magically convert..
xmldoc.root.add_attribute('attr', content) xmldoc.root.add_attribute('attr', content)
@ -1272,14 +1244,14 @@ EOL
assert_equal( sanity1, sanity2 ) assert_equal( sanity1, sanity2 )
end end
def test_ticket_88 def test_ticket_88
doc = REXML::Document.new("<?xml version=\"1.0\" encoding=\"shift_jis\"?>") doc = REXML::Document.new("<?xml version=\"1.0\" encoding=\"shift_jis\"?>")
assert_equal("<?xml version='1.0' encoding='Shift_JIS'?>", doc.to_s) assert_equal("<?xml version='1.0' encoding='SHIFT_JIS'?>", doc.to_s)
doc = REXML::Document.new("<?xml version = \"1.0\" encoding = \"shift_jis\"?>") doc = REXML::Document.new("<?xml version = \"1.0\" encoding = \"shift_jis\"?>")
assert_equal("<?xml version='1.0' encoding='Shift_JIS'?>", doc.to_s) assert_equal("<?xml version='1.0' encoding='SHIFT_JIS'?>", doc.to_s)
end end
def test_ticket_85 def test_ticket_85
xml = <<ENDXML xml = <<ENDXML
<foo> <foo>
@ -1295,8 +1267,6 @@ ENDXML
</bar> </bar>
</foo>" </foo>"
zml = "<foo><bar><bob name='jimmy'/></bar></foo>"
# The pretty printer ignores all whitespace, anyway so output1 == output2 # The pretty printer ignores all whitespace, anyway so output1 == output2
f = REXML::Formatters::Pretty.new( 2 ) f = REXML::Formatters::Pretty.new( 2 )
d = Document.new( xml, :ignore_whitespace_nodes=>:all ) d = Document.new( xml, :ignore_whitespace_nodes=>:all )
@ -1311,7 +1281,7 @@ ENDXML
# The base case. # The base case.
d = Document.new(yml) d = Document.new(yml)
f.write( d, output3="" ) f.write( d, output3="" )
assert_equal( output3.strip, output2.strip ) assert_equal( output3.strip, output2.strip )
d = Document.new(yml) d = Document.new(yml)
@ -1355,10 +1325,10 @@ ENDXML
end end
def test_ticket_14 def test_ticket_14
# Per .2.5 Node Tests of XPath spec # Per .2.5 Node Tests of XPath spec
assert_raise( REXML::UndefinedNamespaceException, assert_raise( REXML::UndefinedNamespaceException,
%Q{Should have gotten an Undefined Namespace error} ) { %Q{Should have gotten an Undefined Namespace error} ) {
d = Document.new("<a><n:b/></a>") Document.new("<a><n:b/></a>")
} }
end end
@ -1395,7 +1365,7 @@ ENDXML
doc.add_element(bean_element) doc.add_element(bean_element)
REXML::Formatters::Pretty.new(3).write( doc, out = "" ) REXML::Formatters::Pretty.new(3).write( doc, out = "" )
assert_equal "<bean>\n <prop key='filter'>\n (&amp;#38;(|(memberof=CN=somegroupabcdefgh,OU=OUsucks,DC=hookemhorns,DC=com)(mail=*someco.com))(acct=%u)(!(extraparameter:2.2.222.222222.2.2.222:=2)))\n </prop>\n</bean>", out assert_equal "<bean>\n <prop key='filter'>\n (&amp;#38;(|(memberof=CN=somegroupabcdefgh,OU=OUsucks,DC=hookemhorns,DC=com)(mail=*someco.com))(acct=%u)(!(extraparameter:2.2.222.222222.2.2.222:=2)))\n </prop>\n</bean>", out
end end

22
test/rexml/test_encoding.rb
View file

@ -18,7 +18,7 @@ class EncodingTester < Test::Unit::TestCase
def test_encoded_in_encoded_out def test_encoded_in_encoded_out
doc = Document.new( @encoded ) doc = Document.new( @encoded )
doc.write( out="" ) doc.write( out="" )
out.force_encoding('binary') if out.respond_to? :force_encoding out.force_encoding(::Encoding::ASCII_8BIT)
assert_equal( @encoded, out ) assert_equal( @encoded, out )
end end
@ -26,12 +26,12 @@ class EncodingTester < Test::Unit::TestCase
def test_encoded_in_change_out def test_encoded_in_change_out
doc = Document.new( @encoded ) doc = Document.new( @encoded )
doc.xml_decl.encoding = "UTF-8" doc.xml_decl.encoding = "UTF-8"
assert_equal( ::Encoding::UTF_8, doc.encoding ) assert_equal("UTF-8", doc.encoding)
REXML::Formatters::Default.new.write( doc.root, out="" ) REXML::Formatters::Default.new.write( doc.root, out="" )
out.force_encoding('binary') if out.respond_to? :force_encoding out.force_encoding(::Encoding::ASCII_8BIT)
assert_equal( @not_encoded, out ) assert_equal( @not_encoded, out )
char = XPath.first( doc, "/a/b/text()" ).to_s char = XPath.first( doc, "/a/b/text()" ).to_s
char.force_encoding('binary') if char.respond_to? :force_encoding char.force_encoding(::Encoding::ASCII_8BIT)
assert_equal( "ĉ", char ) assert_equal( "ĉ", char )
end end
@ -39,7 +39,7 @@ class EncodingTester < Test::Unit::TestCase
def test_encoded_in_different_out def test_encoded_in_different_out
doc = Document.new( @encoded ) doc = Document.new( @encoded )
REXML::Formatters::Default.new.write( doc.root, Output.new( out="", "UTF-8" ) ) REXML::Formatters::Default.new.write( doc.root, Output.new( out="", "UTF-8" ) )
out.force_encoding('binary') if out.respond_to? :force_encoding out.force_encoding(::Encoding::ASCII_8BIT)
assert_equal( @not_encoded, out ) assert_equal( @not_encoded, out )
end end
@ -47,9 +47,9 @@ class EncodingTester < Test::Unit::TestCase
def test_in_change_out def test_in_change_out
doc = Document.new( @not_encoded ) doc = Document.new( @not_encoded )
doc.xml_decl.encoding = "ISO-8859-3" doc.xml_decl.encoding = "ISO-8859-3"
assert_equal( ::Encoding::ISO_8859_3, doc.encoding ) assert_equal("ISO-8859-3", doc.encoding)
doc.write( out="" ) doc.write( out="" )
out.force_encoding('binary') if out.respond_to? :force_encoding out.force_encoding(::Encoding::ASCII_8BIT)
assert_equal( @encoded, out ) assert_equal( @encoded, out )
end end
@ -57,7 +57,7 @@ class EncodingTester < Test::Unit::TestCase
def test_in_different_out def test_in_different_out
doc = Document.new( @not_encoded ) doc = Document.new( @not_encoded )
doc.write( Output.new( out="", "ISO-8859-3" ) ) doc.write( Output.new( out="", "ISO-8859-3" ) )
out.force_encoding('binary') if out.respond_to? :force_encoding out.force_encoding(::Encoding::ASCII_8BIT)
assert_equal( @encoded, out ) assert_equal( @encoded, out )
end end
@ -66,10 +66,10 @@ class EncodingTester < Test::Unit::TestCase
def test_in_different_access def test_in_different_access
doc = Document.new <<-EOL doc = Document.new <<-EOL
<?xml version='1.0' encoding='ISO-8859-1'?> <?xml version='1.0' encoding='ISO-8859-1'?>
<a a="ÿ">ÿ</a> <a a="\xFF">\xFF</a>
EOL EOL
expect = "\303\277" expect = "\303\277"
expect.force_encoding('UTF-8') if expect.respond_to? :force_encoding expect.force_encoding(::Encoding::UTF_8)
assert_equal( expect, doc.elements['a'].attributes['a'] ) assert_equal( expect, doc.elements['a'].attributes['a'] )
assert_equal( expect, doc.elements['a'].text ) assert_equal( expect, doc.elements['a'].text )
end end
@ -86,7 +86,7 @@ class EncodingTester < Test::Unit::TestCase
def test_ticket_110 def test_ticket_110
utf16 = REXML::Document.new(File.new(fixture_path("ticket_110_utf16.xml"))) utf16 = REXML::Document.new(File.new(fixture_path("ticket_110_utf16.xml")))
assert_equal( ::Encoding::UTF_16BE, utf16.encoding ) assert_equal(utf16.encoding, "UTF-16")
assert( utf16[0].kind_of?(REXML::XMLDecl)) assert( utf16[0].kind_of?(REXML::XMLDecl))
end end
end end