1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
|
require 'test/unit'
require 'feed_tools'
require 'feed_tools/helpers/html_helper'
require 'feed_tools/helpers/xml_helper'
require 'feed_tools/helpers/feed_tools_helper'
class HelperTest < Test::Unit::TestCase
include FeedTools::FeedToolsHelper
def setup
FeedTools.reset_configurations
FeedTools.configurations[:tidy_enabled] = false
FeedTools.configurations[:feed_cache] = "FeedTools::DatabaseFeedCache"
FeedTools::FeedToolsHelper.default_local_path =
File.expand_path(
File.expand_path(File.dirname(__FILE__)) + '/../feeds')
end
def test_xpath_case_insensitivity
FEED_TOOLS_NAMESPACES["testnamespace"] = "http://example.com/ns/"
xml = <<-XML
<RoOt>
<ChIlD>Test String #1</ChIlD>
</RoOt>
XML
xml_doc = REXML::Document.new(xml)
test_string = FeedTools::XmlHelper.try_xpaths(xml_doc, [
"ROOT/child/text()"
], :select_result_value => true)
assert_equal("Test String #1", test_string)
xml = <<-XML
<root xmlns:TESTnAmEsPace="http://example.com/ns/">
<TESTnAmEsPace:ChIlD>Test String #2</TESTnAmEsPace:ChIlD>
</root>
XML
xml_doc = REXML::Document.new(xml)
test_string = FeedTools::XmlHelper.try_xpaths(xml_doc, [
"ROOT/testnamespace:child/text()"
], :select_result_value => true)
assert_equal("Test String #2", test_string)
xml = <<-XML
<RoOt>
<ChIlD AttRib="Test String #3" />
</RoOt>
XML
xml_doc = REXML::Document.new(xml)
test_string = FeedTools::XmlHelper.try_xpaths(xml_doc, [
"ROOT/child/@ATTRIB"
], :select_result_value => true)
assert_equal("Test String #3", test_string)
xml = <<-XML
<RoOt xmlns:TESTnAmEsPace="http://example.com/ns/">
<ChIlD TESTnAmEsPace:AttRib="Test String #4" />
</RoOt>
XML
xml_doc = REXML::Document.new(xml)
test_string = FeedTools::XmlHelper.try_xpaths(xml_doc, [
"ROOT/child/@testnamespace:ATTRIB"
], :select_result_value => true)
assert_equal("Test String #4", test_string)
end
def test_escape_entities
end
def test_unescape_entities
end
def test_normalize_url
assert_equal("", FeedTools::UriHelper.normalize_url(""))
assert_equal("http://slashdot.org/",
FeedTools::UriHelper.normalize_url("slashdot.org"))
assert_equal("http://example.com/index.php",
FeedTools::UriHelper.normalize_url("example.com/index.php"))
# Test windows-style file: protocol normalization
assert_equal("file:///c:/windows/My%20Documents%20100%20/foo.txt",
FeedTools::UriHelper.normalize_url("c:\\windows\\My Documents 100%20\\foo.txt"))
assert_equal("file:///c:/windows/My%20Documents%20100%20/foo.txt",
FeedTools::UriHelper.normalize_url(
"file://c:\\windows\\My Documents 100%20\\foo.txt"))
assert_equal("file:///c:/windows/My%20Documents%20100%20/foo.txt",
FeedTools::UriHelper.normalize_url(
"file:///c|/windows/My%20Documents%20100%20/foo.txt"))
assert_equal("file:///c:/windows/My%20Documents%20100%20/foo.txt",
FeedTools::UriHelper.normalize_url(
"file:///c:/windows/My%20Documents%20100%20/foo.txt"))
if FeedTools::UriHelper.idn_enabled?
# Test internationalized domain names
assert_equal(
"http://www.xn--8ws00zhy3a.com/atomtests/iri/everything.atom",
FeedTools::UriHelper.normalize_url(
"http://www.詹姆斯.com/atomtests/iri/everything.atom"))
assert_equal(
"http://www.xn--8ws00zhy3a.com/atomtests/iri/%E8%A9%B9.html",
FeedTools::UriHelper.normalize_url(
"http://www.詹姆斯.com/atomtests/iri/詹.html"))
end
end
def test_tidy_html
FeedTools.configurations[:tidy_enabled] = true
unless FeedTools::HtmlHelper.tidy_enabled?
puts "\nCould not test tidy support. Libtidy couldn't be found."
else
illegal_pre = <<-EOF
<pre>
require 'net/http'
module Net
class HTTPIO < HTTP
def request(req, body = nil, &block)
begin_transport req
req.exec @socket, @curr_http_version, edit_path(req.path), body
begin
res = HTTPResponse.read_new(@socket)
end while HTTPContinue === res
res.instance_eval do
def read len = nil; ... end
def body; true end
def close
req, res = @req, self
@http.instance_eval do
end_transport req, res
finish
end
end
def size; 0 end
def is_a? klass; klass == IO ? true : super(klass); end
end
res
end
end
</pre>
EOF
illegal_pre_after_tidy = FeedTools::HtmlHelper.tidy_html(illegal_pre)
assert_not_equal(nil, illegal_pre_after_tidy =~ /class HTTPIO < HTTP/,
"Tidy failed to clean up illegal chars in <pre> block.")
unescaped_utf8_characters = <<-EOF
\302\240
EOF
unescaped_utf8_characters_after_tidy =
FeedTools::HtmlHelper.tidy_html(unescaped_utf8_characters)
assert_not_equal(" ", unescaped_utf8_characters_after_tidy,
"Tidy failed to escape the unicode characters correctly.")
assert_not_equal("Â ", unescaped_utf8_characters_after_tidy,
"Tidy failed to escape the unicode characters correctly.")
end
FeedTools.configurations[:tidy_enabled] = false
end
def test_build_urn_uri
assert_equal("urn:uuid:fa6d0b87-3f36-517d-b9b7-1349f8c3fc6b",
FeedTools::UriHelper.build_urn_uri('http://sporkmonger.com/'))
end
def test_build_merged_feed
if FeedTools::FEED_TOOLS_VERSION::MINOR == 2 &&
FeedTools::FEED_TOOLS_VERSION::TINY <= 26
merged_feed = FeedTools.build_merged_feed([
"http://rss.slashdot.org/Slashdot/slashdot"
])
end
end
def test_extract_xhtml
FeedTools.configurations[:tidy_enabled] = false
xml = <<-XML
<content>
<div xmlns='http://www.w3.org/1999/xhtml'><em>Testing.</em></div>
</content>
XML
doc = REXML::Document.new(xml)
assert_equal(
"<div><em>Testing.</em></div>",
FeedTools::HtmlHelper.extract_xhtml(doc.root))
xml = <<-XML
<content xmlns:xhtml='http://www.w3.org/1999/xhtml'>
<xhtml:div><xhtml:em>Testing.</xhtml:em></xhtml:div>
</content>
XML
doc = REXML::Document.new(xml)
assert_equal(
"<div><em>Testing.</em></div>",
FeedTools::HtmlHelper.extract_xhtml(doc.root))
xml = <<-XML
<content type="xhtml" xmlns:xhtml='http://www.w3.org/1999/xhtml'>
<xhtml:div xmlns='http://hsivonen.iki.fi/FooML'>
<xhtml:ul>
<xhtml:li>XHTML List Item</xhtml:li>
</xhtml:ul>
<ul>
<li>FooML List Item</li>
</ul>
</xhtml:div>
</content>
XML
doc = REXML::Document.new(xml)
xhtml = FeedTools::HtmlHelper.extract_xhtml(doc.root)
assert((xhtml =~ /<div>/) && (xhtml =~ /<\/div>/),
"XHTML divs were not normalized properly.")
assert((xhtml =~ /hsivonen\.iki\.fi/),
"FooML namespace was not preserved.")
assert((xhtml =~ /<foo:ul xmlns:foo=/),
"Namespace was not placed correctly.")
FeedTools.configurations[:tidy_enabled] = true
xml = <<-XML
<content type="xhtml" xmlns:xhtml='http://www.w3.org/1999/xhtml'>
<xhtml:div xmlns='http://hsivonen.iki.fi/FooML'>
<xhtml:ul>
<xhtml:li>XHTML List Item</xhtml:li>
</xhtml:ul>
<ul>
<li>FooML List Item</li>
</ul>
</xhtml:div>
</content>
XML
doc = REXML::Document.new(xml)
xhtml = FeedTools::HtmlHelper.extract_xhtml(doc.root)
assert((xhtml =~ /<div>/) && (xhtml =~ /<\/div>/),
"XHTML divs were not normalized properly.")
assert((xhtml =~ /hsivonen\.iki\.fi/),
"FooML namespace was not preserved.")
assert((xhtml =~ /<foo:ul xmlns:foo=/),
"Namespace was not placed correctly.")
end
end
|
