mwilliams-feedzirra 0.0.14
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 +196 -0
- data/Rakefile +56 -0
- data/lib/core_ext/date.rb +21 -0
- data/lib/core_ext/string.rb +9 -0
- data/lib/feedzirra.rb +48 -0
- data/lib/feedzirra/feed.rb +390 -0
- data/lib/feedzirra/feed_entry_utilities.rb +45 -0
- data/lib/feedzirra/feed_utilities.rb +71 -0
- data/lib/feedzirra/parser/atom.rb +26 -0
- data/lib/feedzirra/parser/atom_entry.rb +34 -0
- data/lib/feedzirra/parser/atom_feed_burner.rb +27 -0
- data/lib/feedzirra/parser/atom_feed_burner_entry.rb +35 -0
- data/lib/feedzirra/parser/itunes_rss.rb +50 -0
- data/lib/feedzirra/parser/itunes_rss_item.rb +31 -0
- data/lib/feedzirra/parser/itunes_rss_owner.rb +12 -0
- data/lib/feedzirra/parser/rss.rb +28 -0
- data/lib/feedzirra/parser/rss_entry.rb +40 -0
- data/spec/feedzirra/feed_entry_utilities_spec.rb +52 -0
- data/spec/feedzirra/feed_spec.rb +578 -0
- data/spec/feedzirra/feed_utilities_spec.rb +149 -0
- data/spec/feedzirra/parser/atom_entry_spec.rb +45 -0
- data/spec/feedzirra/parser/atom_feed_burner_entry_spec.rb +42 -0
- data/spec/feedzirra/parser/atom_feed_burner_spec.rb +39 -0
- data/spec/feedzirra/parser/atom_spec.rb +35 -0
- data/spec/feedzirra/parser/itunes_rss_item_spec.rb +48 -0
- data/spec/feedzirra/parser/itunes_rss_owner_spec.rb +18 -0
- data/spec/feedzirra/parser/itunes_rss_spec.rb +50 -0
- data/spec/feedzirra/parser/rss_entry_spec.rb +41 -0
- data/spec/feedzirra/parser/rss_spec.rb +41 -0
- data/spec/spec.opts +2 -0
- data/spec/spec_helper.rb +58 -0
- metadata +132 -0
@@ -0,0 +1,578 @@
|
|
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::Parser::AtomEntry.new.should respond_to(:comment_rss)
|
15
|
+
end
|
16
|
+
|
17
|
+
it "should parse the added element out of RSS feeds" do
|
18
|
+
Feedzirra::Parser::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 as a standard RSS feed" do
|
53
|
+
feed = Feedzirra::Feed.parse(sample_itunes_feed)
|
54
|
+
feed.title.should == "All About Everything"
|
55
|
+
feed.entries.first.published.should == Time.parse("Wed, 15 Jun 2005 19:00:00 GMT")
|
56
|
+
|
57
|
+
# Since the commit 621957879, iTunes feeds will be parsed as standard RSS, so this
|
58
|
+
# entry should now not have a method for itunes_author.
|
59
|
+
feed.entries.first.should_not respond_to(:itunes_author)
|
60
|
+
feed.entries.size.should == 3
|
61
|
+
end
|
62
|
+
end
|
63
|
+
|
64
|
+
context "when there's no available parser" do
|
65
|
+
it "raises Feedzirra::NoParserAvailable" do
|
66
|
+
proc {
|
67
|
+
Feedzirra::Feed.parse("I'm an invalid feed")
|
68
|
+
}.should raise_error(Feedzirra::NoParserAvailable)
|
69
|
+
end
|
70
|
+
end
|
71
|
+
|
72
|
+
it "should parse an feedburner rss feed" do
|
73
|
+
feed = Feedzirra::Feed.parse(sample_rss_feed_burner_feed)
|
74
|
+
feed.title.should == "Sam Harris: Author, Philosopher, Essayist, Atheist"
|
75
|
+
feed.entries.first.published.to_s.should == "Tue Jan 13 17:20:28 UTC 2009"
|
76
|
+
feed.entries.size.should == 10
|
77
|
+
end
|
78
|
+
end
|
79
|
+
|
80
|
+
describe "#determine_feed_parser_for_xml" do
|
81
|
+
it "should return the Feedzirra::Parser::Atom class for an atom feed" do
|
82
|
+
Feedzirra::Feed.determine_feed_parser_for_xml(sample_atom_feed).should == Feedzirra::Parser::Atom
|
83
|
+
end
|
84
|
+
|
85
|
+
it "should return the Feedzirra::Parser::AtomFeedBurner class for an atom feedburner feed" do
|
86
|
+
Feedzirra::Feed.determine_feed_parser_for_xml(sample_feedburner_atom_feed).should == Feedzirra::Parser::AtomFeedBurner
|
87
|
+
end
|
88
|
+
|
89
|
+
it "should return the Feedzirra::Parser::RSS class for an rdf/rss 1.0 feed" do
|
90
|
+
Feedzirra::Feed.determine_feed_parser_for_xml(sample_rdf_feed).should == Feedzirra::Parser::RSS
|
91
|
+
end
|
92
|
+
|
93
|
+
it "should return the Feedzirra::Parser::RSS class for an rss feedburner feed" do
|
94
|
+
Feedzirra::Feed.determine_feed_parser_for_xml(sample_rss_feed_burner_feed).should == Feedzirra::Parser::RSS
|
95
|
+
end
|
96
|
+
|
97
|
+
it "should return the Feedzirra::Parser::RSS object for an rss 2.0 feed" do
|
98
|
+
Feedzirra::Feed.determine_feed_parser_for_xml(sample_rss_feed).should == Feedzirra::Parser::RSS
|
99
|
+
end
|
100
|
+
|
101
|
+
it "should return a Feedzirra::Parser::RSS object for an itunes feed" do
|
102
|
+
Feedzirra::Feed.determine_feed_parser_for_xml(sample_itunes_feed).should == Feedzirra::Parser::RSS
|
103
|
+
end
|
104
|
+
|
105
|
+
end
|
106
|
+
|
107
|
+
describe "when adding feed types" do
|
108
|
+
it "should prioritize added types over the built in ones" do
|
109
|
+
feed_text = "Atom asdf"
|
110
|
+
Feedzirra::Parser::Atom.should be_able_to_parse(feed_text)
|
111
|
+
new_feed_type = Class.new do
|
112
|
+
def self.able_to_parse?(val)
|
113
|
+
true
|
114
|
+
end
|
115
|
+
end
|
116
|
+
|
117
|
+
new_feed_type.should be_able_to_parse(feed_text)
|
118
|
+
Feedzirra::Feed.add_feed_class(new_feed_type)
|
119
|
+
Feedzirra::Feed.determine_feed_parser_for_xml(feed_text).should == new_feed_type
|
120
|
+
|
121
|
+
# this is a hack so that this doesn't break the rest of the tests
|
122
|
+
Feedzirra::Feed.feed_classes.reject! {|o| o == new_feed_type }
|
123
|
+
end
|
124
|
+
end
|
125
|
+
|
126
|
+
describe '#etag_from_header' do
|
127
|
+
before(:each) do
|
128
|
+
@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"
|
129
|
+
end
|
130
|
+
|
131
|
+
it "should return the etag from the header if it exists" do
|
132
|
+
Feedzirra::Feed.etag_from_header(@header).should == "ziEyTl4q9GH04BR4jgkImd0GvSE"
|
133
|
+
end
|
134
|
+
|
135
|
+
it "should return nil if there is no etag in the header" do
|
136
|
+
Feedzirra::Feed.etag_from_header("foo").should be_nil
|
137
|
+
end
|
138
|
+
|
139
|
+
end
|
140
|
+
|
141
|
+
describe '#last_modified_from_header' do
|
142
|
+
before(:each) do
|
143
|
+
@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"
|
144
|
+
end
|
145
|
+
|
146
|
+
it "should return the last modified date from the header if it exists" do
|
147
|
+
Feedzirra::Feed.last_modified_from_header(@header).should == Time.parse("Wed, 28 Jan 2009 04:10:32 GMT")
|
148
|
+
end
|
149
|
+
|
150
|
+
it "should return nil if there is no last modified date in the header" do
|
151
|
+
Feedzirra::Feed.last_modified_from_header("foo").should be_nil
|
152
|
+
end
|
153
|
+
end
|
154
|
+
|
155
|
+
describe "fetching feeds" do
|
156
|
+
before(:each) do
|
157
|
+
@paul_feed = { :xml => load_sample("PaulDixExplainsNothing.xml"), :url => "http://feeds.feedburner.com/PaulDixExplainsNothing" }
|
158
|
+
@trotter_feed = { :xml => load_sample("TrotterCashionHome.xml"), :url => "http://feeds2.feedburner.com/trottercashion" }
|
159
|
+
end
|
160
|
+
|
161
|
+
describe "#fetch_raw" do
|
162
|
+
before(:each) do
|
163
|
+
@cmock = stub('cmock', :header_str => '', :body_str => @paul_feed[:xml] )
|
164
|
+
@multi = stub('curl_multi', :add => true, :perform => true)
|
165
|
+
@curl_easy = stub('curl_easy')
|
166
|
+
@curl = stub('curl', :headers => {}, :follow_location= => true, :on_failure => true)
|
167
|
+
@curl.stub!(:on_success).and_yield(@cmock)
|
168
|
+
|
169
|
+
Curl::Multi.stub!(:new).and_return(@multi)
|
170
|
+
Curl::Easy.stub!(:new).and_yield(@curl).and_return(@curl_easy)
|
171
|
+
end
|
172
|
+
|
173
|
+
it "should set user agent if it's passed as an option" do
|
174
|
+
Feedzirra::Feed.fetch_raw(@paul_feed[:url], :user_agent => 'Custom Useragent')
|
175
|
+
@curl.headers['User-Agent'].should == 'Custom Useragent'
|
176
|
+
end
|
177
|
+
|
178
|
+
it "should set user agent to default if it's not passed as an option" do
|
179
|
+
Feedzirra::Feed.fetch_raw(@paul_feed[:url])
|
180
|
+
@curl.headers['User-Agent'].should == Feedzirra::Feed::USER_AGENT
|
181
|
+
end
|
182
|
+
|
183
|
+
it "should set if modified since as an option if passed" do
|
184
|
+
Feedzirra::Feed.fetch_raw(@paul_feed[:url], :if_modified_since => Time.parse("Wed, 28 Jan 2009 04:10:32 GMT"))
|
185
|
+
@curl.headers["If-Modified-Since"].should == 'Wed, 28 Jan 2009 04:10:32 GMT'
|
186
|
+
end
|
187
|
+
|
188
|
+
it "should set if none match as an option if passed" do
|
189
|
+
Feedzirra::Feed.fetch_raw(@paul_feed[:url], :if_none_match => 'ziEyTl4q9GH04BR4jgkImd0GvSE')
|
190
|
+
@curl.headers["If-None-Match"].should == 'ziEyTl4q9GH04BR4jgkImd0GvSE'
|
191
|
+
end
|
192
|
+
|
193
|
+
it 'should set userpwd for http basic authentication if :http_authentication is passed' do
|
194
|
+
@curl.should_receive(:userpwd=).with('username:password')
|
195
|
+
Feedzirra::Feed.fetch_raw(@paul_feed[:url], :http_authentication => ['username', 'password'])
|
196
|
+
end
|
197
|
+
|
198
|
+
it 'should set accepted encodings' do
|
199
|
+
Feedzirra::Feed.fetch_raw(@paul_feed[:url], :compress => true)
|
200
|
+
@curl.headers["Accept-encoding"].should == 'gzip, deflate'
|
201
|
+
end
|
202
|
+
|
203
|
+
it "should return raw xml" do
|
204
|
+
Feedzirra::Feed.fetch_raw(@paul_feed[:url]).should =~ /^#{Regexp.escape('<?xml version="1.0" encoding="UTF-8"?>')}/
|
205
|
+
end
|
206
|
+
|
207
|
+
it "should take multiple feed urls and return a hash of urls and response xml" do
|
208
|
+
multi = stub('curl_multi', :add => true, :perform => true)
|
209
|
+
Curl::Multi.stub!(:new).and_return(multi)
|
210
|
+
|
211
|
+
paul_response = stub('paul_response', :header_str => '', :body_str => @paul_feed[:xml] )
|
212
|
+
trotter_response = stub('trotter_response', :header_str => '', :body_str => @trotter_feed[:xml] )
|
213
|
+
|
214
|
+
paul_curl = stub('paul_curl', :headers => {}, :follow_location= => true, :on_failure => true)
|
215
|
+
paul_curl.stub!(:on_success).and_yield(paul_response)
|
216
|
+
|
217
|
+
trotter_curl = stub('trotter_curl', :headers => {}, :follow_location= => true, :on_failure => true)
|
218
|
+
trotter_curl.stub!(:on_success).and_yield(trotter_response)
|
219
|
+
|
220
|
+
Curl::Easy.should_receive(:new).with(@paul_feed[:url]).ordered.and_yield(paul_curl)
|
221
|
+
Curl::Easy.should_receive(:new).with(@trotter_feed[:url]).ordered.and_yield(trotter_curl)
|
222
|
+
|
223
|
+
results = Feedzirra::Feed.fetch_raw([@paul_feed[:url], @trotter_feed[:url]])
|
224
|
+
results.keys.should include(@paul_feed[:url])
|
225
|
+
results.keys.should include(@trotter_feed[:url])
|
226
|
+
results[@paul_feed[:url]].should =~ /Paul Dix/
|
227
|
+
results[@trotter_feed[:url]].should =~ /Trotter Cashion/
|
228
|
+
end
|
229
|
+
|
230
|
+
it "should always return a hash when passed an array" do
|
231
|
+
results = Feedzirra::Feed.fetch_raw([@paul_feed[:url]])
|
232
|
+
results.class.should == Hash
|
233
|
+
end
|
234
|
+
end
|
235
|
+
|
236
|
+
describe "#add_url_to_multi" do
|
237
|
+
before(:each) do
|
238
|
+
@multi = Curl::Multi.new(@paul_feed[:url])
|
239
|
+
@multi.stub!(:add)
|
240
|
+
@easy_curl = Curl::Easy.new(@paul_feed[:url])
|
241
|
+
|
242
|
+
Curl::Easy.should_receive(:new).and_yield(@easy_curl)
|
243
|
+
end
|
244
|
+
|
245
|
+
it "should set user agent if it's passed as an option" do
|
246
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, :user_agent => 'My cool application')
|
247
|
+
@easy_curl.headers["User-Agent"].should == 'My cool application'
|
248
|
+
end
|
249
|
+
|
250
|
+
it "should set user agent to default if it's not passed as an option" do
|
251
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
|
252
|
+
@easy_curl.headers["User-Agent"].should == Feedzirra::Feed::USER_AGENT
|
253
|
+
end
|
254
|
+
|
255
|
+
it "should set if modified since as an option if passed" do
|
256
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, :if_modified_since => Time.parse("Jan 25 2009 04:10:32 GMT"))
|
257
|
+
@easy_curl.headers["If-Modified-Since"].should == 'Sun, 25 Jan 2009 04:10:32 GMT'
|
258
|
+
end
|
259
|
+
|
260
|
+
it 'should set follow location to true' do
|
261
|
+
@easy_curl.should_receive(:follow_location=).with(true)
|
262
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
|
263
|
+
end
|
264
|
+
|
265
|
+
it 'should set userpwd for http basic authentication if :http_authentication is passed' do
|
266
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, :http_authentication => ['myusername', 'mypassword'])
|
267
|
+
@easy_curl.userpwd.should == 'myusername:mypassword'
|
268
|
+
end
|
269
|
+
|
270
|
+
it 'should set accepted encodings' do
|
271
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {:compress => true})
|
272
|
+
@easy_curl.headers["Accept-encoding"].should == 'gzip, deflate'
|
273
|
+
end
|
274
|
+
|
275
|
+
it "should set if_none_match as an option if passed" do
|
276
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, :if_none_match => 'ziEyTl4q9GH04BR4jgkImd0GvSE')
|
277
|
+
@easy_curl.headers["If-None-Match"].should == 'ziEyTl4q9GH04BR4jgkImd0GvSE'
|
278
|
+
end
|
279
|
+
|
280
|
+
describe 'on success' do
|
281
|
+
before(:each) do
|
282
|
+
@feed = mock('feed', :feed_url= => true, :etag= => true, :last_modified= => true)
|
283
|
+
Feedzirra::Feed.stub!(:decode_content).and_return(@paul_feed[:xml])
|
284
|
+
Feedzirra::Feed.stub!(:determine_feed_parser_for_xml).and_return(Feedzirra::Parser::AtomFeedBurner)
|
285
|
+
Feedzirra::Parser::AtomFeedBurner.stub!(:parse).and_return(@feed)
|
286
|
+
Feedzirra::Feed.stub!(:etag_from_header).and_return('ziEyTl4q9GH04BR4jgkImd0GvSE')
|
287
|
+
Feedzirra::Feed.stub!(:last_modified_from_header).and_return('Wed, 28 Jan 2009 04:10:32 GMT')
|
288
|
+
end
|
289
|
+
|
290
|
+
it 'should decode the response body' do
|
291
|
+
Feedzirra::Feed.should_receive(:decode_content).with(@easy_curl).and_return(@paul_feed[:xml])
|
292
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
|
293
|
+
@easy_curl.on_success.call(@easy_curl)
|
294
|
+
end
|
295
|
+
|
296
|
+
it 'should determine the xml parser class' do
|
297
|
+
Feedzirra::Feed.should_receive(:determine_feed_parser_for_xml).with(@paul_feed[:xml]).and_return(Feedzirra::Parser::AtomFeedBurner)
|
298
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
|
299
|
+
@easy_curl.on_success.call(@easy_curl)
|
300
|
+
end
|
301
|
+
|
302
|
+
it 'should parse the xml' do
|
303
|
+
Feedzirra::Parser::AtomFeedBurner.should_receive(:parse).with(@paul_feed[:xml]).and_return(@feed)
|
304
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
|
305
|
+
@easy_curl.on_success.call(@easy_curl)
|
306
|
+
end
|
307
|
+
|
308
|
+
describe 'when a compatible xml parser class is found' do
|
309
|
+
it 'should set the last effective url to the feed url' do
|
310
|
+
@easy_curl.should_receive(:last_effective_url).and_return(@paul_feed[:url])
|
311
|
+
@feed.should_receive(:feed_url=).with(@paul_feed[:url])
|
312
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
|
313
|
+
@easy_curl.on_success.call(@easy_curl)
|
314
|
+
end
|
315
|
+
|
316
|
+
it 'should set the etags on the feed' do
|
317
|
+
@feed.should_receive(:etag=).with('ziEyTl4q9GH04BR4jgkImd0GvSE')
|
318
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
|
319
|
+
@easy_curl.on_success.call(@easy_curl)
|
320
|
+
end
|
321
|
+
|
322
|
+
it 'should set the last modified on the feed' do
|
323
|
+
@feed.should_receive(:last_modified=).with('Wed, 28 Jan 2009 04:10:32 GMT')
|
324
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
|
325
|
+
@easy_curl.on_success.call(@easy_curl)
|
326
|
+
end
|
327
|
+
|
328
|
+
it 'should add the feed to the responses' do
|
329
|
+
responses = {}
|
330
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], responses, {})
|
331
|
+
@easy_curl.on_success.call(@easy_curl)
|
332
|
+
|
333
|
+
responses.length.should == 1
|
334
|
+
responses['http://feeds.feedburner.com/PaulDixExplainsNothing'].should == @feed
|
335
|
+
end
|
336
|
+
|
337
|
+
it 'should call proc if :on_success option is passed' do
|
338
|
+
success = lambda { |url, feed| }
|
339
|
+
success.should_receive(:call).with(@paul_feed[:url], @feed)
|
340
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, { :on_success => success })
|
341
|
+
@easy_curl.on_success.call(@easy_curl)
|
342
|
+
end
|
343
|
+
end
|
344
|
+
|
345
|
+
describe 'when no compatible xml parser class is found' do
|
346
|
+
it 'should raise a NoParserAvailable exception'
|
347
|
+
end
|
348
|
+
end
|
349
|
+
|
350
|
+
describe 'on failure' do
|
351
|
+
before(:each) do
|
352
|
+
@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"
|
353
|
+
@body = 'Page could not be found.'
|
354
|
+
|
355
|
+
@easy_curl.stub!(:response_code).and_return(404)
|
356
|
+
@easy_curl.stub!(:header_str).and_return(@headers)
|
357
|
+
@easy_curl.stub!(:body_str).and_return(@body)
|
358
|
+
end
|
359
|
+
|
360
|
+
it 'should call proc if :on_failure option is passed' do
|
361
|
+
failure = lambda { |url, feed| }
|
362
|
+
failure.should_receive(:call).with(@paul_feed[:url], 404, @headers, @body)
|
363
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, { :on_failure => failure })
|
364
|
+
@easy_curl.on_failure.call(@easy_curl)
|
365
|
+
end
|
366
|
+
|
367
|
+
it 'should return the http code in the responses' do
|
368
|
+
responses = {}
|
369
|
+
Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], responses, {})
|
370
|
+
@easy_curl.on_failure.call(@easy_curl)
|
371
|
+
|
372
|
+
responses.length.should == 1
|
373
|
+
responses[@paul_feed[:url]].should == 404
|
374
|
+
end
|
375
|
+
end
|
376
|
+
end
|
377
|
+
|
378
|
+
describe "#add_feed_to_multi" do
|
379
|
+
before(:each) do
|
380
|
+
@multi = Curl::Multi.new(@paul_feed[:url])
|
381
|
+
@multi.stub!(:add)
|
382
|
+
@easy_curl = Curl::Easy.new(@paul_feed[:url])
|
383
|
+
@feed = Feedzirra::Feed.parse(sample_feedburner_atom_feed)
|
384
|
+
|
385
|
+
Curl::Easy.should_receive(:new).and_yield(@easy_curl)
|
386
|
+
end
|
387
|
+
|
388
|
+
it "should set user agent if it's passed as an option" do
|
389
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, :user_agent => 'My cool application')
|
390
|
+
@easy_curl.headers["User-Agent"].should == 'My cool application'
|
391
|
+
end
|
392
|
+
|
393
|
+
it "should set user agent to default if it's not passed as an option" do
|
394
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, {})
|
395
|
+
@easy_curl.headers["User-Agent"].should == Feedzirra::Feed::USER_AGENT
|
396
|
+
end
|
397
|
+
|
398
|
+
it "should set if modified since as an option if passed"
|
399
|
+
|
400
|
+
it 'should set follow location to true' do
|
401
|
+
@easy_curl.should_receive(:follow_location=).with(true)
|
402
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, {})
|
403
|
+
end
|
404
|
+
|
405
|
+
it 'should set userpwd for http basic authentication if :http_authentication is passed' do
|
406
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, :http_authentication => ['myusername', 'mypassword'])
|
407
|
+
@easy_curl.userpwd.should == 'myusername:mypassword'
|
408
|
+
end
|
409
|
+
|
410
|
+
it "should set if_none_match as an option if passed" do
|
411
|
+
@feed.etag = 'ziEyTl4q9GH04BR4jgkImd0GvSE'
|
412
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, {})
|
413
|
+
@easy_curl.headers["If-None-Match"].should == 'ziEyTl4q9GH04BR4jgkImd0GvSE'
|
414
|
+
end
|
415
|
+
|
416
|
+
describe 'on success' do
|
417
|
+
before(:each) do
|
418
|
+
@new_feed = @feed.clone
|
419
|
+
@feed.stub!(:update_from_feed)
|
420
|
+
Feedzirra::Feed.stub!(:decode_content).and_return(@paul_feed[:xml])
|
421
|
+
Feedzirra::Feed.stub!(:determine_feed_parser_for_xml).and_return(Feedzirra::Parser::AtomFeedBurner)
|
422
|
+
Feedzirra::Parser::AtomFeedBurner.stub!(:parse).and_return(@new_feed)
|
423
|
+
Feedzirra::Feed.stub!(:etag_from_header).and_return('ziEyTl4q9GH04BR4jgkImd0GvSE')
|
424
|
+
Feedzirra::Feed.stub!(:last_modified_from_header).and_return('Wed, 28 Jan 2009 04:10:32 GMT')
|
425
|
+
end
|
426
|
+
|
427
|
+
it 'should process the next feed in the queue'
|
428
|
+
|
429
|
+
it 'should parse the updated feed' do
|
430
|
+
Feedzirra::Parser::AtomFeedBurner.should_receive(:parse).and_return(@new_feed)
|
431
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, {})
|
432
|
+
@easy_curl.on_success.call(@easy_curl)
|
433
|
+
end
|
434
|
+
|
435
|
+
it 'should set the last effective url to the feed url' do
|
436
|
+
@easy_curl.should_receive(:last_effective_url).and_return(@paul_feed[:url])
|
437
|
+
@new_feed.should_receive(:feed_url=).with(@paul_feed[:url])
|
438
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, {})
|
439
|
+
@easy_curl.on_success.call(@easy_curl)
|
440
|
+
end
|
441
|
+
|
442
|
+
it 'should set the etags on the feed' do
|
443
|
+
@new_feed.should_receive(:etag=).with('ziEyTl4q9GH04BR4jgkImd0GvSE')
|
444
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, {})
|
445
|
+
@easy_curl.on_success.call(@easy_curl)
|
446
|
+
end
|
447
|
+
|
448
|
+
it 'should set the last modified on the feed' do
|
449
|
+
@new_feed.should_receive(:last_modified=).with('Wed, 28 Jan 2009 04:10:32 GMT')
|
450
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, {})
|
451
|
+
@easy_curl.on_success.call(@easy_curl)
|
452
|
+
end
|
453
|
+
|
454
|
+
it 'should add the feed to the responses' do
|
455
|
+
responses = {}
|
456
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], responses, {})
|
457
|
+
@easy_curl.on_success.call(@easy_curl)
|
458
|
+
|
459
|
+
responses.length.should == 1
|
460
|
+
responses['http://feeds.feedburner.com/PaulDixExplainsNothing'].should == @feed
|
461
|
+
end
|
462
|
+
|
463
|
+
it 'should call proc if :on_success option is passed' do
|
464
|
+
success = lambda { |feed| }
|
465
|
+
success.should_receive(:call).with(@feed)
|
466
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, { :on_success => success })
|
467
|
+
@easy_curl.on_success.call(@easy_curl)
|
468
|
+
end
|
469
|
+
|
470
|
+
it 'should call update from feed on the old feed with the updated feed' do
|
471
|
+
@feed.should_receive(:update_from_feed).with(@new_feed)
|
472
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, {})
|
473
|
+
@easy_curl.on_success.call(@easy_curl)
|
474
|
+
end
|
475
|
+
end
|
476
|
+
|
477
|
+
describe 'on failure' do
|
478
|
+
before(:each) do
|
479
|
+
@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"
|
480
|
+
@body = 'Page could not be found.'
|
481
|
+
|
482
|
+
@easy_curl.stub!(:response_code).and_return(404)
|
483
|
+
@easy_curl.stub!(:header_str).and_return(@headers)
|
484
|
+
@easy_curl.stub!(:body_str).and_return(@body)
|
485
|
+
end
|
486
|
+
|
487
|
+
it 'should call on success callback if the response code is 304' do
|
488
|
+
success = lambda { |feed| }
|
489
|
+
success.should_receive(:call).with(@feed)
|
490
|
+
@easy_curl.should_receive(:response_code).and_return(304)
|
491
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, { :on_success => success })
|
492
|
+
@easy_curl.on_failure.call(@easy_curl)
|
493
|
+
end
|
494
|
+
|
495
|
+
it 'should return the http code in the responses' do
|
496
|
+
responses = {}
|
497
|
+
Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], responses, {})
|
498
|
+
@easy_curl.on_failure.call(@easy_curl)
|
499
|
+
|
500
|
+
responses.length.should == 1
|
501
|
+
responses['http://www.pauldix.net/'].should == 404
|
502
|
+
end
|
503
|
+
end
|
504
|
+
end
|
505
|
+
|
506
|
+
describe "#fetch_and_parse" do
|
507
|
+
describe "with curl" do
|
508
|
+
before(:each) do
|
509
|
+
Feedzirra.should_receive(:use_curb?).and_return(true)
|
510
|
+
end
|
511
|
+
it 'should initiate the fetching and parsing using multicurl' do
|
512
|
+
@curl_multi = mock('curl_multi')
|
513
|
+
@curl_multi.should_receive(:perform)
|
514
|
+
Curl::Multi.should_receive(:new).and_return(@curl_multi)
|
515
|
+
Feedzirra::Feed.fetch_and_parse('')
|
516
|
+
end
|
517
|
+
it "should pass any request options through to add_url_to_multi"
|
518
|
+
it 'should slice the feeds into groups of thirty for processing'
|
519
|
+
it "should return a feed object if a single feed is passed in"
|
520
|
+
it "should return an return an array of feed objects if multiple feeds are passed in"
|
521
|
+
end
|
522
|
+
describe "without curl" do
|
523
|
+
before(:each) do
|
524
|
+
Feedzirra.should_receive(:use_curb?).and_return(false)
|
525
|
+
end
|
526
|
+
it 'should initiate the fetching and parsing using Net::HTTP' do
|
527
|
+
url = 'http://engadget.com/rss.xml'
|
528
|
+
responses = Feedzirra::Feed.fetch_and_parse(url)
|
529
|
+
responses.should_not == nil
|
530
|
+
end
|
531
|
+
it "should return a feed object if a single feed is passed in" do
|
532
|
+
url = 'http://engadget.com/rss.xml'
|
533
|
+
responses = Feedzirra::Feed.fetch_and_parse(url)
|
534
|
+
responses.title.should == 'Engadget'
|
535
|
+
responses.entries.length.should == 40
|
536
|
+
end
|
537
|
+
it "should return an return an hash of feed objects if multiple feeds are passed in" do
|
538
|
+
responses = Feedzirra::Feed.fetch_and_parse(
|
539
|
+
['http://engadget.com/rss.xml', 'http://gizmodo.com/index.xml']
|
540
|
+
)
|
541
|
+
responses.length.should == 2
|
542
|
+
end
|
543
|
+
end
|
544
|
+
end
|
545
|
+
|
546
|
+
describe "#decode_content" do
|
547
|
+
before(:each) do
|
548
|
+
@curl_easy = mock('curl_easy', :body_str => '<xml></xml>')
|
549
|
+
end
|
550
|
+
|
551
|
+
it 'should decode the response body using gzip if the Content-Encoding: is gzip' do
|
552
|
+
@curl_easy.stub!(:header_str).and_return('Content-Encoding: gzip')
|
553
|
+
string_io = mock('stringio', :read => @curl_easy.body_str, :close => true)
|
554
|
+
StringIO.should_receive(:new).and_return(string_io)
|
555
|
+
Zlib::GzipReader.should_receive(:new).with(string_io).and_return(string_io)
|
556
|
+
Feedzirra::Feed.decode_content(@curl_easy)
|
557
|
+
end
|
558
|
+
|
559
|
+
it 'should deflate the response body using inflate if the Content-Encoding: is deflate' do
|
560
|
+
@curl_easy.stub!(:header_str).and_return('Content-Encoding: deflate')
|
561
|
+
Zlib::Inflate.should_receive(:inflate).with(@curl_easy.body_str)
|
562
|
+
Feedzirra::Feed.decode_content(@curl_easy)
|
563
|
+
end
|
564
|
+
|
565
|
+
it 'should return the response body if it is not encoded' do
|
566
|
+
@curl_easy.stub!(:header_str).and_return('')
|
567
|
+
Feedzirra::Feed.decode_content(@curl_easy).should == '<xml></xml>'
|
568
|
+
end
|
569
|
+
end
|
570
|
+
|
571
|
+
describe "#update" do
|
572
|
+
it 'should perform the updating using multicurl'
|
573
|
+
it "should pass any request options through to add_feed_to_multi"
|
574
|
+
it "should return a feed object if a single feed is passed in"
|
575
|
+
it "should return an return an array of feed objects if multiple feeds are passed in"
|
576
|
+
end
|
577
|
+
end
|
578
|
+
end
|