astro-feedzirra 0.0.8.20090419
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/README.textile +187 -0
- data/Rakefile +53 -0
- data/lib/core_ext/date.rb +21 -0
- data/lib/core_ext/string.rb +9 -0
- data/lib/feedzirra/atom.rb +22 -0
- data/lib/feedzirra/atom_entry.rb +29 -0
- data/lib/feedzirra/atom_feed_burner.rb +22 -0
- data/lib/feedzirra/atom_feed_burner_entry.rb +30 -0
- data/lib/feedzirra/feed.rb +321 -0
- data/lib/feedzirra/feed_entry_utilities.rb +45 -0
- data/lib/feedzirra/feed_utilities.rb +71 -0
- data/lib/feedzirra/itunes_rss.rb +46 -0
- data/lib/feedzirra/itunes_rss_item.rb +28 -0
- data/lib/feedzirra/itunes_rss_owner.rb +8 -0
- data/lib/feedzirra/rss.rb +23 -0
- data/lib/feedzirra/rss_entry.rb +35 -0
- data/lib/feedzirra.rb +36 -0
- data/spec/feedzirra/atom_entry_spec.rb +45 -0
- data/spec/feedzirra/atom_feed_burner_entry_spec.rb +42 -0
- data/spec/feedzirra/atom_feed_burner_spec.rb +39 -0
- data/spec/feedzirra/atom_spec.rb +35 -0
- data/spec/feedzirra/feed_entry_utilities_spec.rb +52 -0
- data/spec/feedzirra/feed_spec.rb +543 -0
- data/spec/feedzirra/feed_utilities_spec.rb +149 -0
- data/spec/feedzirra/itunes_rss_item_spec.rb +48 -0
- data/spec/feedzirra/itunes_rss_owner_spec.rb +18 -0
- data/spec/feedzirra/itunes_rss_spec.rb +50 -0
- data/spec/feedzirra/rss_entry_spec.rb +41 -0
- data/spec/feedzirra/rss_spec.rb +41 -0
- data/spec/spec.opts +2 -0
- data/spec/spec_helper.rb +58 -0
- metadata +142 -0
@@ -0,0 +1,543 @@
|
|
1
|
+
require File.dirname(__FILE__) + '/../spec_helper'
|
2
|
+
|
3
|
+
describe Feedzirra::Feed do
|
4
|
+
describe "#add_common_feed_entry_element" do
|
5
|
+
before(:all) do
|
6
|
+
Feedzirra::Feed.add_common_feed_entry_element("wfw:commentRss", :as => :comment_rss)
|
7
|
+
end
|
8
|
+
|
9
|
+
it "should parse the added element out of Atom feeds" do
|
10
|
+
Feedzirra::Feed.parse(sample_wfw_feed).entries.first.comment_rss.should == "this is the new val"
|
11
|
+
end
|
12
|
+
|
13
|
+
it "should parse the added element out of Atom Feedburner feeds" do
|
14
|
+
Feedzirra::AtomEntry.new.should respond_to(:comment_rss)
|
15
|
+
end
|
16
|
+
|
17
|
+
it "should parse the added element out of RSS feeds" do
|
18
|
+
Feedzirra::RSSEntry.new.should respond_to(:comment_rss)
|
19
|
+
end
|
20
|
+
end
|
21
|
+
|
22
|
+
describe "#parse" do # many of these tests are redundant with the specific feed type tests, but I put them here for completeness
|
23
|
+
context "when there's an available parser" do
|
24
|
+
it "should parse an rdf feed" do
|
25
|
+
feed = Feedzirra::Feed.parse(sample_rdf_feed)
|
26
|
+
feed.title.should == "HREF Considered Harmful"
|
27
|
+
feed.entries.first.published.to_s.should == "Tue Sep 02 19:50:07 UTC 2008"
|
28
|
+
feed.entries.size.should == 10
|
29
|
+
end
|
30
|
+
|
31
|
+
it "should parse an rss feed" do
|
32
|
+
feed = Feedzirra::Feed.parse(sample_rss_feed)
|
33
|
+
feed.title.should == "Tender Lovemaking"
|
34
|
+
feed.entries.first.published.to_s.should == "Thu Dec 04 17:17:49 UTC 2008"
|
35
|
+
feed.entries.size.should == 10
|
36
|
+
end
|
37
|
+
|
38
|
+
it "should parse an atom feed" do
|
39
|
+
feed = Feedzirra::Feed.parse(sample_atom_feed)
|
40
|
+
feed.title.should == "Amazon Web Services Blog"
|
41
|
+
feed.entries.first.published.to_s.should == "Fri Jan 16 18:21:00 UTC 2009"
|
42
|
+
feed.entries.size.should == 10
|
43
|
+
end
|
44
|
+
|
45
|
+
it "should parse an feedburner atom feed" do
|
46
|
+
feed = Feedzirra::Feed.parse(sample_feedburner_atom_feed)
|
47
|
+
feed.title.should == "Paul Dix Explains Nothing"
|
48
|
+
feed.entries.first.published.to_s.should == "Thu Jan 22 15:50:22 UTC 2009"
|
49
|
+
feed.entries.size.should == 5
|
50
|
+
end
|
51
|
+
|
52
|
+
it "should parse an itunes feed" do
|
53
|
+
feed = Feedzirra::Feed.parse(sample_itunes_feed)
|
54
|
+
feed.title.should == "All About Everything"
|
55
|
+
feed.entries.first.published.to_s.should == "Wed, 15 Jun 2005 19:00:00 GMT"
|
56
|
+
feed.entries.first.itunes_author.should == "John Doe"
|
57
|
+
feed.entries.size.should == 3
|
58
|
+
end
|
59
|
+
end
|
60
|
+
|
61
|
+
context "when there's no available parser" do
|
62
|
+
it "raises Feedzirra::NoParserAvailable" do
|
63
|
+
proc {
|
64
|
+
Feedzirra::Feed.parse("I'm an invalid feed")
|
65
|
+
}.should raise_error(Feedzirra::NoParserAvailable)
|
66
|
+
end
|
67
|
+
end
|
68
|
+
|
69
|
+
it "should parse an feedburner rss feed" do
|
70
|
+
feed = Feedzirra::Feed.parse(sample_rss_feed_burner_feed)
|
71
|
+
feed.title.should == "Sam Harris: Author, Philosopher, Essayist, Atheist"
|
72
|
+
feed.entries.first.published.to_s.should == "Tue Jan 13 17:20:28 UTC 2009"
|
73
|
+
feed.entries.size.should == 10
|
74
|
+
end
|
75
|
+
end
|
76
|
+
|
77
|
+
describe "#determine_feed_parser_for_xml" do
|
78
|
+
it "should return the Feedzirra::Atom class for an atom feed" do
|
79
|
+
Feedzirra::Feed.determine_feed_parser_for_xml(sample_atom_feed).should == Feedzirra::Atom
|
80
|
+
end
|
81
|
+
|
82
|
+
it "should return the Feedzirra::AtomFeedBurner class for an atom feedburner feed" do
|
83
|
+
Feedzirra::Feed.determine_feed_parser_for_xml(sample_feedburner_atom_feed).should == Feedzirra::AtomFeedBurner
|
84
|
+
end
|
85
|
+
|
86
|
+
it "should return the Feedzirra::RSS class for an rdf/rss 1.0 feed" do
|
87
|
+
Feedzirra::Feed.determine_feed_parser_for_xml(sample_rdf_feed).should == Feedzirra::RSS
|
88
|
+
end
|
89
|
+
|
90
|
+
it "should return the Feedzirra::RSS class for an rss feedburner feed" do
|
91
|
+
Feedzirra::Feed.determine_feed_parser_for_xml(sample_rss_feed_burner_feed).should == Feedzirra::RSS
|
92
|
+
end
|
93
|
+
|
94
|
+
it "should return the Feedzirra::RSS object for an rss 2.0 feed" do
|
95
|
+
Feedzirra::Feed.determine_feed_parser_for_xml(sample_rss_feed).should == Feedzirra::RSS
|
96
|
+
end
|
97
|
+
|
98
|
+
it "should return the Feedzirra::ITunesRSS object for an itunes feed" do
|
99
|
+
Feedzirra::Feed.determine_feed_parser_for_xml(sample_itunes_feed).should == Feedzirra::ITunesRSS
|
100
|
+
end
|
101
|
+
|
102
|
+
end
|
103
|
+
|
104
|
+
describe "when adding feed types" do
|
105
|
+
it "should prioritize added types over the built in ones" do
|
106
|
+
feed_text = "Atom asdf"
|
107
|
+
Feedzirra::Atom.should be_able_to_parse(feed_text)
|
108
|
+
new_feed_type = Class.new do
|
109
|
+
def self.able_to_parse?(val)
|
110
|
+
true
|
111
|
+
end
|
112
|
+
end
|
113
|
+
|
114
|
+
new_feed_type.should be_able_to_parse(feed_text)
|
115
|
+
Feedzirra::Feed.add_feed_class(new_feed_type)
|
116
|
+
Feedzirra::Feed.determine_feed_parser_for_xml(feed_text).should == new_feed_type
|
117
|
+
|
118
|
+
# this is a hack so that this doesn't break the rest of the tests
|
119
|
+
Feedzirra::Feed.feed_classes.reject! {|o| o == new_feed_type }
|
120
|
+
end
|
121
|
+
end
|
122
|
+
|
123
|
+
describe '#etag_from_header' do
|
124
|
+
before(:each) do
|
125
|
+
@header = "HTTP/1.0 200 OK\r\nDate: Thu, 29 Jan 2009 03:55:24 GMT\r\nServer: Apache\r\nX-FB-Host: chi-write6\r\nLast-Modified: Wed, 28 Jan 2009 04:10:32 GMT\r\nETag: ziEyTl4q9GH04BR4jgkImd0GvSE\r\nP3P: CP=\"ALL DSP COR NID CUR OUR NOR\"\r\nConnection: close\r\nContent-Type: text/xml;charset=utf-8\r\n\r\n"
|
126
|
+
end
|
127
|
+
|
128
|
+
it "should return the etag from the header if it exists" do
|
129
|
+
Feedzirra::Feed.etag_from_header(@header).should == "ziEyTl4q9GH04BR4jgkImd0GvSE"
|
130
|
+
end
|
131
|
+
|
132
|
+
it "should return nil if there is no etag in the header" do
|
133
|
+
Feedzirra::Feed.etag_from_header("foo").should be_nil
|
134
|
+
end
|
135
|
+
|
136
|
+
end
|
137
|
+
|
138
|
+
describe '#last_modified_from_header' do
|
139
|
+
before(:each) do
|
140
|
+
@header = "HTTP/1.0 200 OK\r\nDate: Thu, 29 Jan 2009 03:55:24 GMT\r\nServer: Apache\r\nX-FB-Host: chi-write6\r\nLast-Modified: Wed, 28 Jan 2009 04:10:32 GMT\r\nETag: ziEyTl4q9GH04BR4jgkImd0GvSE\r\nP3P: CP=\"ALL DSP COR NID CUR OUR NOR\"\r\nConnection: close\r\nContent-Type: text/xml;charset=utf-8\r\n\r\n"
|
141
|
+
end
|
142
|
+
|
143
|
+
it "should return the last modified date from the header if it exists" do
|
144
|
+
Feedzirra::Feed.last_modified_from_header(@header).should == Time.parse("Wed, 28 Jan 2009 04:10:32 GMT")
|
145
|
+
end
|
146
|
+
|
147
|
+
it "should return nil if there is no last modified date in the header" do
|
148
|
+
Feedzirra::Feed.last_modified_from_header("foo").should be_nil
|
149
|
+
end
|
150
|
+
end
|
151
|
+
|
152
|
+
describe "fetching feeds" do
|
153
|
+
before(:each) do
|
154
|
+
@paul_feed = { :xml => load_sample("PaulDixExplainsNothing.xml"), :url => "http://feeds.feedburner.com/PaulDixExplainsNothing" }
|
155
|
+
@trotter_feed = { :xml => load_sample("TrotterCashionHome.xml"), :url => "http://feeds2.feedburner.com/trottercashion" }
|
156
|
+
end
|
157
|
+
|
158
|
+
describe "#fetch_raw" do
|
159
|
+
before(:each) do
|
160
|
+
@cmock = stub('cmock', :header_str => '', :body_str => @paul_feed[:xml] )
|
161
|
+
@multi = stub('curl_multi', :add => true, :perform => true)
|
162
|
+
@curl_easy = stub('curl_easy')
|
163
|
+
@curl = stub('curl', :headers => {}, :follow_location= => true, :on_failure => true)
|
164
|
+
@curl.stub!(:on_success).and_yield(@cmock)
|
165
|
+
|
166
|
+
Curl::Multi.stub!(:new).and_return(@multi)
|
167
|
+
Curl::Easy.stub!(:new).and_yield(@curl).and_return(@curl_easy)
|
168
|
+
end
|
169
|
+
|
170
|
+
it "should set user agent if it's passed as an option" do
|
171
|
+
Feedzirra::Feed.fetch_raw(@paul_feed[:url], :user_agent => 'Custom Useragent')
|
172
|
+
@curl.headers['User-Agent'].should == 'Custom Useragent'
|
173
|
+
end
|
174
|
+
|
175
|
+
it "should set user agent to default if it's not passed as an option" do
|
176
|
+
Feedzirra::Feed.fetch_raw(@paul_feed[:url])
|
177
|
+
@curl.headers['User-Agent'].should == Feedzirra::Feed::USER_AGENT
|
178
|
+
end
|
179
|
+
|
180
|
+
it "should set if modified since as an option if passed" do
|
181
|
+
Feedzirra::Feed.fetch_raw(@paul_feed[:url], :if_modified_since => Time.parse("Wed, 28 Jan 2009 04:10:32 GMT"))
|
182
|
+
@curl.headers["If-Modified-Since"].should == 'Wed, 28 Jan 2009 04:10:32 GMT'
|
183
|
+
end
|
184
|
+
|
185
|
+
it "should set if none match as an option if passed" do
|
186
|
+
Feedzirra::Feed.fetch_raw(@paul_feed[:url], :if_none_match => 'ziEyTl4q9GH04BR4jgkImd0GvSE')
|
187
|
+
@curl.headers["If-None-Match"].should == 'ziEyTl4q9GH04BR4jgkImd0GvSE'
|
188
|
+
end
|
189
|
+
|
190
|
+
it 'should set userpwd for http basic authentication if :http_authentication is passed' do
|
191
|
+
@curl.should_receive(:userpwd=).with('username:password')
|
192
|
+
Feedzirra::Feed.fetch_raw(@paul_feed[:url], :http_authentication => ['username', 'password'])
|
193
|
+
end
|
194
|
+
|
195
|
+
it 'should set accepted encodings' do
|
196
|
+
Feedzirra::Feed.fetch_raw(@paul_feed[:url])
|
197
|
+
@curl.headers["Accept-encoding"].should == 'gzip, deflate'
|
198
|
+
end
|
199
|
+
|
200
|
+
it "should return raw xml" do
|
201
|
+
Feedzirra::Feed.fetch_raw(@paul_feed[:url]).should =~ /^#{Regexp.escape('<?xml version="1.0" encoding="UTF-8"?>')}/
|
202
|
+
end
|
203
|
+
|
204
|
+
it "should take multiple feed urls and return a hash of urls and response xml" do
|
205
|
+
multi = stub('curl_multi', :add => true, :perform => true)
|
206
|
+
Curl::Multi.stub!(:new).and_return(multi)
|
207
|
+
|
208
|
+
paul_response = stub('paul_response', :header_str => '', :body_str => @paul_feed[:xml] )
|
209
|
+
trotter_response = stub('trotter_response', :header_str => '', :body_str => @trotter_feed[:xml] )
|
210
|
+
|
211
|
+
paul_curl = stub('paul_curl', :headers => {}, :follow_location= => true, :on_failure => true)
|
212
|
+
paul_curl.stub!(:on_success).and_yield(paul_response)
|
213
|
+
|
214
|
+
trotter_curl = stub('trotter_curl', :headers => {}, :follow_location= => true, :on_failure => true)
|
215
|
+
trotter_curl.stub!(:on_success).and_yield(trotter_response)
|
216
|
+
|
217
|
+
Curl::Easy.should_receive(:new).with(@paul_feed[:url]).ordered.and_yield(paul_curl)
|
218
|
+
Curl::Easy.should_receive(:new).with(@trotter_feed[:url]).ordered.and_yield(trotter_curl)
|
219
|
+
|
220
|
+
results = Feedzirra::Feed.fetch_raw([@paul_feed[:url], @trotter_feed[:url]])
|
221
|
+
results.keys.should include(@paul_feed[:url])
|
222
|
+
results.keys.should include(@trotter_feed[:url])
|
223
|
+
results[@paul_feed[:url]].should =~ /Paul Dix/
|
224
|
+
results[@trotter_feed[:url]].should =~ /Trotter Cashion/
|
225
|
+
end
|
226
|
+
|
227
|
+
it "should always return a hash when passed an array" do
|
228
|
+
results = Feedzirra::Feed.fetch_raw([@paul_feed[:url]])
|
229
|
+
results.class.should == Hash
|
230
|
+
end
|
231
|
+
end
|
232
|
+
|
233
|
+
describe "#add_url_to_multi" do
|
234
|
+
before(:each) do
|
235
|
+
@multi = Curl::Multi.new(@paul_feed[:url])
|
236
|
+
@multi.stub!(:add)
|
237
|
+
@easy_curl = Curl::Easy.new(@paul_feed[:url])
|
238
|
+
|
239
|
+
Curl::Easy.should_receive(:new).and_yield(@easy_curl)
|
240
|
+
end
|
241
|
+
|
242
|
+
it "should set user agent if it's passed as an option" do
|
243
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, :user_agent => 'My cool application')
|
244
|
+
@easy_curl.headers["User-Agent"].should == 'My cool application'
|
245
|
+
end
|
246
|
+
|
247
|
+
it "should set user agent to default if it's not passed as an option" do
|
248
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
|
249
|
+
@easy_curl.headers["User-Agent"].should == Feedzirra::Feed::USER_AGENT
|
250
|
+
end
|
251
|
+
|
252
|
+
it "should set if modified since as an option if passed" do
|
253
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, :if_modified_since => Time.parse("Jan 25 2009 04:10:32 GMT"))
|
254
|
+
@easy_curl.headers["If-Modified-Since"].should == 'Sun, 25 Jan 2009 04:10:32 GMT'
|
255
|
+
end
|
256
|
+
|
257
|
+
it 'should set follow location to true' do
|
258
|
+
@easy_curl.should_receive(:follow_location=).with(true)
|
259
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
|
260
|
+
end
|
261
|
+
|
262
|
+
it 'should set userpwd for http basic authentication if :http_authentication is passed' do
|
263
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, :http_authentication => ['myusername', 'mypassword'])
|
264
|
+
@easy_curl.userpwd.should == 'myusername:mypassword'
|
265
|
+
end
|
266
|
+
|
267
|
+
it 'should set accepted encodings' do
|
268
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
|
269
|
+
@easy_curl.headers["Accept-encoding"].should == 'gzip, deflate'
|
270
|
+
end
|
271
|
+
|
272
|
+
it "should set if_none_match as an option if passed" do
|
273
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, :if_none_match => 'ziEyTl4q9GH04BR4jgkImd0GvSE')
|
274
|
+
@easy_curl.headers["If-None-Match"].should == 'ziEyTl4q9GH04BR4jgkImd0GvSE'
|
275
|
+
end
|
276
|
+
|
277
|
+
describe 'on success' do
|
278
|
+
before(:each) do
|
279
|
+
@feed = mock('feed', :feed_url= => true, :etag= => true, :last_modified= => true)
|
280
|
+
Feedzirra::Feed.stub!(:decode_content).and_return(@paul_feed[:xml])
|
281
|
+
Feedzirra::Feed.stub!(:determine_feed_parser_for_xml).and_return(Feedzirra::AtomFeedBurner)
|
282
|
+
Feedzirra::AtomFeedBurner.stub!(:parse).and_return(@feed)
|
283
|
+
Feedzirra::Feed.stub!(:etag_from_header).and_return('ziEyTl4q9GH04BR4jgkImd0GvSE')
|
284
|
+
Feedzirra::Feed.stub!(:last_modified_from_header).and_return('Wed, 28 Jan 2009 04:10:32 GMT')
|
285
|
+
end
|
286
|
+
|
287
|
+
it 'should decode the response body' do
|
288
|
+
Feedzirra::Feed.should_receive(:decode_content).with(@easy_curl).and_return(@paul_feed[:xml])
|
289
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
|
290
|
+
@easy_curl.on_success.call(@easy_curl)
|
291
|
+
end
|
292
|
+
|
293
|
+
it 'should determine the xml parser class' do
|
294
|
+
Feedzirra::Feed.should_receive(:determine_feed_parser_for_xml).with(@paul_feed[:xml]).and_return(Feedzirra::AtomFeedBurner)
|
295
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
|
296
|
+
@easy_curl.on_success.call(@easy_curl)
|
297
|
+
end
|
298
|
+
|
299
|
+
it 'should parse the xml' do
|
300
|
+
Feedzirra::AtomFeedBurner.should_receive(:parse).with(@paul_feed[:xml]).and_return(@feed)
|
301
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
|
302
|
+
@easy_curl.on_success.call(@easy_curl)
|
303
|
+
end
|
304
|
+
|
305
|
+
describe 'when a compatible xml parser class is found' do
|
306
|
+
it 'should set the last effective url to the feed url' do
|
307
|
+
@easy_curl.should_receive(:last_effective_url).and_return(@paul_feed[:url])
|
308
|
+
@feed.should_receive(:feed_url=).with(@paul_feed[:url])
|
309
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
|
310
|
+
@easy_curl.on_success.call(@easy_curl)
|
311
|
+
end
|
312
|
+
|
313
|
+
it 'should set the etags on the feed' do
|
314
|
+
@feed.should_receive(:etag=).with('ziEyTl4q9GH04BR4jgkImd0GvSE')
|
315
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
|
316
|
+
@easy_curl.on_success.call(@easy_curl)
|
317
|
+
end
|
318
|
+
|
319
|
+
it 'should set the last modified on the feed' do
|
320
|
+
@feed.should_receive(:last_modified=).with('Wed, 28 Jan 2009 04:10:32 GMT')
|
321
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
|
322
|
+
@easy_curl.on_success.call(@easy_curl)
|
323
|
+
end
|
324
|
+
|
325
|
+
it 'should add the feed to the responses' do
|
326
|
+
responses = {}
|
327
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], responses, {})
|
328
|
+
@easy_curl.on_success.call(@easy_curl)
|
329
|
+
|
330
|
+
responses.length.should == 1
|
331
|
+
responses['http://feeds.feedburner.com/PaulDixExplainsNothing'].should == @feed
|
332
|
+
end
|
333
|
+
|
334
|
+
it 'should call proc if :on_success option is passed' do
|
335
|
+
success = lambda { |url, feed| }
|
336
|
+
success.should_receive(:call).with(@paul_feed[:url], @feed)
|
337
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, { :on_success => success })
|
338
|
+
@easy_curl.on_success.call(@easy_curl)
|
339
|
+
end
|
340
|
+
end
|
341
|
+
|
342
|
+
describe 'when no compatible xml parser class is found' do
|
343
|
+
it 'should raise a NoParserAvailable exception'
|
344
|
+
end
|
345
|
+
end
|
346
|
+
|
347
|
+
describe 'on failure' do
|
348
|
+
before(:each) do
|
349
|
+
@headers = "HTTP/1.0 404 Not Found\r\nDate: Thu, 29 Jan 2009 03:55:24 GMT\r\nServer: Apache\r\nX-FB-Host: chi-write6\r\nLast-Modified: Wed, 28 Jan 2009 04:10:32 GMT\r\n"
|
350
|
+
@body = 'Page could not be found.'
|
351
|
+
|
352
|
+
@easy_curl.stub!(:response_code).and_return(404)
|
353
|
+
@easy_curl.stub!(:header_str).and_return(@headers)
|
354
|
+
@easy_curl.stub!(:body_str).and_return(@body)
|
355
|
+
end
|
356
|
+
|
357
|
+
it 'should call proc if :on_failure option is passed' do
|
358
|
+
failure = lambda { |url, feed| }
|
359
|
+
failure.should_receive(:call).with(@paul_feed[:url], 404, @headers, @body)
|
360
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, { :on_failure => failure })
|
361
|
+
@easy_curl.on_failure.call(@easy_curl)
|
362
|
+
end
|
363
|
+
|
364
|
+
it 'should return the http code in the responses' do
|
365
|
+
responses = {}
|
366
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], responses, {})
|
367
|
+
@easy_curl.on_failure.call(@easy_curl)
|
368
|
+
|
369
|
+
responses.length.should == 1
|
370
|
+
responses[@paul_feed[:url]].should == 404
|
371
|
+
end
|
372
|
+
end
|
373
|
+
end
|
374
|
+
|
375
|
+
describe "#add_feed_to_multi" do
|
376
|
+
before(:each) do
|
377
|
+
@multi = Curl::Multi.new(@paul_feed[:url])
|
378
|
+
@multi.stub!(:add)
|
379
|
+
@easy_curl = Curl::Easy.new(@paul_feed[:url])
|
380
|
+
@feed = Feedzirra::Feed.parse(sample_feedburner_atom_feed)
|
381
|
+
|
382
|
+
Curl::Easy.should_receive(:new).and_yield(@easy_curl)
|
383
|
+
end
|
384
|
+
|
385
|
+
it "should set user agent if it's passed as an option" do
|
386
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, :user_agent => 'My cool application')
|
387
|
+
@easy_curl.headers["User-Agent"].should == 'My cool application'
|
388
|
+
end
|
389
|
+
|
390
|
+
it "should set user agent to default if it's not passed as an option" do
|
391
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, {})
|
392
|
+
@easy_curl.headers["User-Agent"].should == Feedzirra::Feed::USER_AGENT
|
393
|
+
end
|
394
|
+
|
395
|
+
it "should set if modified since as an option if passed"
|
396
|
+
|
397
|
+
it 'should set follow location to true' do
|
398
|
+
@easy_curl.should_receive(:follow_location=).with(true)
|
399
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, {})
|
400
|
+
end
|
401
|
+
|
402
|
+
it 'should set userpwd for http basic authentication if :http_authentication is passed' do
|
403
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, :http_authentication => ['myusername', 'mypassword'])
|
404
|
+
@easy_curl.userpwd.should == 'myusername:mypassword'
|
405
|
+
end
|
406
|
+
|
407
|
+
it "should set if_none_match as an option if passed" do
|
408
|
+
@feed.etag = 'ziEyTl4q9GH04BR4jgkImd0GvSE'
|
409
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, {})
|
410
|
+
@easy_curl.headers["If-None-Match"].should == 'ziEyTl4q9GH04BR4jgkImd0GvSE'
|
411
|
+
end
|
412
|
+
|
413
|
+
describe 'on success' do
|
414
|
+
before(:each) do
|
415
|
+
@new_feed = @feed.clone
|
416
|
+
@feed.stub!(:update_from_feed)
|
417
|
+
Feedzirra::Feed.stub!(:decode_content).and_return(@paul_feed[:xml])
|
418
|
+
Feedzirra::Feed.stub!(:determine_feed_parser_for_xml).and_return(Feedzirra::AtomFeedBurner)
|
419
|
+
Feedzirra::AtomFeedBurner.stub!(:parse).and_return(@new_feed)
|
420
|
+
Feedzirra::Feed.stub!(:etag_from_header).and_return('ziEyTl4q9GH04BR4jgkImd0GvSE')
|
421
|
+
Feedzirra::Feed.stub!(:last_modified_from_header).and_return('Wed, 28 Jan 2009 04:10:32 GMT')
|
422
|
+
end
|
423
|
+
|
424
|
+
it 'should process the next feed in the queue'
|
425
|
+
|
426
|
+
it 'should parse the updated feed' do
|
427
|
+
Feedzirra::AtomFeedBurner.should_receive(:parse).and_return(@new_feed)
|
428
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, {})
|
429
|
+
@easy_curl.on_success.call(@easy_curl)
|
430
|
+
end
|
431
|
+
|
432
|
+
it 'should set the last effective url to the feed url' do
|
433
|
+
@easy_curl.should_receive(:last_effective_url).and_return(@paul_feed[:url])
|
434
|
+
@new_feed.should_receive(:feed_url=).with(@paul_feed[:url])
|
435
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, {})
|
436
|
+
@easy_curl.on_success.call(@easy_curl)
|
437
|
+
end
|
438
|
+
|
439
|
+
it 'should set the etags on the feed' do
|
440
|
+
@new_feed.should_receive(:etag=).with('ziEyTl4q9GH04BR4jgkImd0GvSE')
|
441
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, {})
|
442
|
+
@easy_curl.on_success.call(@easy_curl)
|
443
|
+
end
|
444
|
+
|
445
|
+
it 'should set the last modified on the feed' do
|
446
|
+
@new_feed.should_receive(:last_modified=).with('Wed, 28 Jan 2009 04:10:32 GMT')
|
447
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, {})
|
448
|
+
@easy_curl.on_success.call(@easy_curl)
|
449
|
+
end
|
450
|
+
|
451
|
+
it 'should add the feed to the responses' do
|
452
|
+
responses = {}
|
453
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], responses, {})
|
454
|
+
@easy_curl.on_success.call(@easy_curl)
|
455
|
+
|
456
|
+
responses.length.should == 1
|
457
|
+
responses['http://feeds.feedburner.com/PaulDixExplainsNothing'].should == @feed
|
458
|
+
end
|
459
|
+
|
460
|
+
it 'should call proc if :on_success option is passed' do
|
461
|
+
success = lambda { |feed| }
|
462
|
+
success.should_receive(:call).with(@feed)
|
463
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, { :on_success => success })
|
464
|
+
@easy_curl.on_success.call(@easy_curl)
|
465
|
+
end
|
466
|
+
|
467
|
+
it 'should call update from feed on the old feed with the updated feed' do
|
468
|
+
@feed.should_receive(:update_from_feed).with(@new_feed)
|
469
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, {})
|
470
|
+
@easy_curl.on_success.call(@easy_curl)
|
471
|
+
end
|
472
|
+
end
|
473
|
+
|
474
|
+
describe 'on failure' do
|
475
|
+
before(:each) do
|
476
|
+
@headers = "HTTP/1.0 404 Not Found\r\nDate: Thu, 29 Jan 2009 03:55:24 GMT\r\nServer: Apache\r\nX-FB-Host: chi-write6\r\nLast-Modified: Wed, 28 Jan 2009 04:10:32 GMT\r\n"
|
477
|
+
@body = 'Page could not be found.'
|
478
|
+
|
479
|
+
@easy_curl.stub!(:response_code).and_return(404)
|
480
|
+
@easy_curl.stub!(:header_str).and_return(@headers)
|
481
|
+
@easy_curl.stub!(:body_str).and_return(@body)
|
482
|
+
end
|
483
|
+
|
484
|
+
it 'should call on success callback if the response code is 304' do
|
485
|
+
success = lambda { |feed| }
|
486
|
+
success.should_receive(:call).with(@feed)
|
487
|
+
@easy_curl.should_receive(:response_code).and_return(304)
|
488
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, { :on_success => success })
|
489
|
+
@easy_curl.on_failure.call(@easy_curl)
|
490
|
+
end
|
491
|
+
|
492
|
+
it 'should return the http code in the responses' do
|
493
|
+
responses = {}
|
494
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], responses, {})
|
495
|
+
@easy_curl.on_failure.call(@easy_curl)
|
496
|
+
|
497
|
+
responses.length.should == 1
|
498
|
+
responses['http://www.pauldix.net/'].should == 404
|
499
|
+
end
|
500
|
+
end
|
501
|
+
end
|
502
|
+
|
503
|
+
describe "#fetch_and_parse" do
|
504
|
+
it 'should initiate the fetching and parsing using multicurl'
|
505
|
+
it "should pass any request options through to add_url_to_multi"
|
506
|
+
it 'should slice the feeds into groups of thirty for processing'
|
507
|
+
it "should return a feed object if a single feed is passed in"
|
508
|
+
it "should return an return an array of feed objects if multiple feeds are passed in"
|
509
|
+
end
|
510
|
+
|
511
|
+
describe "#decode_content" do
|
512
|
+
before(:each) do
|
513
|
+
@curl_easy = mock('curl_easy', :body_str => '<xml></xml>')
|
514
|
+
end
|
515
|
+
|
516
|
+
it 'should decode the response body using gzip if the Content-Encoding: is gzip' do
|
517
|
+
@curl_easy.stub!(:header_str).and_return('Content-Encoding: gzip')
|
518
|
+
string_io = mock('stringio', :read => @curl_easy.body_str, :close => true)
|
519
|
+
StringIO.should_receive(:new).and_return(string_io)
|
520
|
+
Zlib::GzipReader.should_receive(:new).with(string_io).and_return(string_io)
|
521
|
+
Feedzirra::Feed.decode_content(@curl_easy)
|
522
|
+
end
|
523
|
+
|
524
|
+
it 'should deflate the response body using inflate if the Content-Encoding: is deflate' do
|
525
|
+
@curl_easy.stub!(:header_str).and_return('Content-Encoding: deflate')
|
526
|
+
Zlib::Inflate.should_receive(:inflate).with(@curl_easy.body_str)
|
527
|
+
Feedzirra::Feed.decode_content(@curl_easy)
|
528
|
+
end
|
529
|
+
|
530
|
+
it 'should return the response body if it is not encoded' do
|
531
|
+
@curl_easy.stub!(:header_str).and_return('')
|
532
|
+
Feedzirra::Feed.decode_content(@curl_easy).should == '<xml></xml>'
|
533
|
+
end
|
534
|
+
end
|
535
|
+
|
536
|
+
describe "#update" do
|
537
|
+
it 'should perform the updating using multicurl'
|
538
|
+
it "should pass any request options through to add_feed_to_multi"
|
539
|
+
it "should return a feed object if a single feed is passed in"
|
540
|
+
it "should return an return an array of feed objects if multiple feeds are passed in"
|
541
|
+
end
|
542
|
+
end
|
543
|
+
end
|
@@ -0,0 +1,149 @@
|
|
1
|
+
require File.dirname(__FILE__) + '/../spec_helper'
|
2
|
+
|
3
|
+
describe Feedzirra::FeedUtilities do
|
4
|
+
before(:each) do
|
5
|
+
@klass = Class.new do
|
6
|
+
include Feedzirra::FeedUtilities
|
7
|
+
end
|
8
|
+
end
|
9
|
+
|
10
|
+
describe "instance methods" do
|
11
|
+
it "should provide an updated? accessor" do
|
12
|
+
feed = @klass.new
|
13
|
+
feed.should_not be_updated
|
14
|
+
feed.updated = true
|
15
|
+
feed.should be_updated
|
16
|
+
end
|
17
|
+
|
18
|
+
it "should provide a new_entries accessor" do
|
19
|
+
feed = @klass.new
|
20
|
+
feed.new_entries.should == []
|
21
|
+
feed.new_entries = [:foo]
|
22
|
+
feed.new_entries.should == [:foo]
|
23
|
+
end
|
24
|
+
|
25
|
+
it "should provide an etag accessor" do
|
26
|
+
feed = @klass.new
|
27
|
+
feed.etag = "foo"
|
28
|
+
feed.etag.should == "foo"
|
29
|
+
end
|
30
|
+
|
31
|
+
it "should provide a last_modified accessor" do
|
32
|
+
feed = @klass.new
|
33
|
+
time = Time.now
|
34
|
+
feed.last_modified = time
|
35
|
+
feed.last_modified.should == time
|
36
|
+
end
|
37
|
+
|
38
|
+
it "should return new_entries? as true when entries are put into new_entries" do
|
39
|
+
feed = @klass.new
|
40
|
+
feed.new_entries << :foo
|
41
|
+
feed.should have_new_entries
|
42
|
+
end
|
43
|
+
|
44
|
+
it "should return a last_modified value from the entry with the most recent published date if the last_modified date hasn't been set" do
|
45
|
+
feed = Feedzirra::Atom.new
|
46
|
+
entry =Feedzirra::AtomEntry.new
|
47
|
+
entry.published = Time.now.to_s
|
48
|
+
feed.entries << entry
|
49
|
+
feed.last_modified.should == entry.published
|
50
|
+
end
|
51
|
+
|
52
|
+
it "should not throw an error if one of the entries has published date of nil" do
|
53
|
+
feed = Feedzirra::Atom.new
|
54
|
+
entry = Feedzirra::AtomEntry.new
|
55
|
+
entry.published = Time.now.to_s
|
56
|
+
feed.entries << entry
|
57
|
+
feed.entries << Feedzirra::AtomEntry.new
|
58
|
+
feed.last_modified.should == entry.published
|
59
|
+
end
|
60
|
+
end
|
61
|
+
|
62
|
+
describe "#update_from_feed" do
|
63
|
+
describe "updating feed attributes" do
|
64
|
+
before(:each) do
|
65
|
+
# I'm using the Atom class when I know I should be using a different one. However, this update_from_feed
|
66
|
+
# method would only be called against a feed item.
|
67
|
+
@feed = Feedzirra::Atom.new
|
68
|
+
@feed.title = "A title"
|
69
|
+
@feed.url = "http://pauldix.net"
|
70
|
+
@feed.feed_url = "http://feeds.feedburner.com/PaulDixExplainsNothing"
|
71
|
+
@feed.updated = false
|
72
|
+
@updated_feed = @feed.dup
|
73
|
+
end
|
74
|
+
|
75
|
+
it "should update the title if changed" do
|
76
|
+
@updated_feed.title = "new title"
|
77
|
+
@feed.update_from_feed(@updated_feed)
|
78
|
+
@feed.title.should == @updated_feed.title
|
79
|
+
@feed.should be_updated
|
80
|
+
end
|
81
|
+
|
82
|
+
it "should not update the title if the same" do
|
83
|
+
@feed.update_from_feed(@updated_feed)
|
84
|
+
@feed.should_not be_updated
|
85
|
+
end
|
86
|
+
|
87
|
+
it "should update the feed_url if changed" do
|
88
|
+
@updated_feed.feed_url = "a new feed url"
|
89
|
+
@feed.update_from_feed(@updated_feed)
|
90
|
+
@feed.feed_url.should == @updated_feed.feed_url
|
91
|
+
@feed.should be_updated
|
92
|
+
end
|
93
|
+
|
94
|
+
it "should not update the feed_url if the same" do
|
95
|
+
@feed.update_from_feed(@updated_feed)
|
96
|
+
@feed.should_not be_updated
|
97
|
+
end
|
98
|
+
|
99
|
+
it "should update the url if changed" do
|
100
|
+
@updated_feed.url = "a new url"
|
101
|
+
@feed.update_from_feed(@updated_feed)
|
102
|
+
@feed.url.should == @updated_feed.url
|
103
|
+
end
|
104
|
+
|
105
|
+
it "should not update the url if not changed" do
|
106
|
+
@feed.update_from_feed(@updated_feed)
|
107
|
+
@feed.should_not be_updated
|
108
|
+
end
|
109
|
+
end
|
110
|
+
|
111
|
+
describe "updating entries" do
|
112
|
+
before(:each) do
|
113
|
+
# I'm using the Atom class when I know I should be using a different one. However, this update_from_feed
|
114
|
+
# method would only be called against a feed item.
|
115
|
+
@feed = Feedzirra::Atom.new
|
116
|
+
@feed.title = "A title"
|
117
|
+
@feed.url = "http://pauldix.net"
|
118
|
+
@feed.feed_url = "http://feeds.feedburner.com/PaulDixExplainsNothing"
|
119
|
+
@feed.updated = false
|
120
|
+
@updated_feed = @feed.dup
|
121
|
+
@old_entry = Feedzirra::AtomEntry.new
|
122
|
+
@old_entry.url = "http://pauldix.net/old.html"
|
123
|
+
@old_entry.published = Time.now.to_s
|
124
|
+
@new_entry = Feedzirra::AtomEntry.new
|
125
|
+
@new_entry.url = "http://pauldix.net/new.html"
|
126
|
+
@new_entry.published = (Time.now + 10).to_s
|
127
|
+
@feed.entries << @old_entry
|
128
|
+
@updated_feed.entries << @new_entry
|
129
|
+
@updated_feed.entries << @old_entry
|
130
|
+
end
|
131
|
+
|
132
|
+
it "should update last-modified from the latest entry date" do
|
133
|
+
@feed.update_from_feed(@updated_feed)
|
134
|
+
@feed.last_modified.should == @new_entry.published
|
135
|
+
end
|
136
|
+
|
137
|
+
it "should put new entries into new_entries" do
|
138
|
+
@feed.update_from_feed(@updated_feed)
|
139
|
+
@feed.new_entries.should == [@new_entry]
|
140
|
+
end
|
141
|
+
|
142
|
+
it "should also put new entries into the entries collection" do
|
143
|
+
@feed.update_from_feed(@updated_feed)
|
144
|
+
@feed.entries.should include(@new_entry)
|
145
|
+
@feed.entries.should include(@old_entry)
|
146
|
+
end
|
147
|
+
end
|
148
|
+
end
|
149
|
+
end
|