feedjira 2.2.0 → 3.1.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.github/ISSUE_TEMPLATE/feed-parsing.md +15 -0
- data/.rubocop.yml +32 -8
- data/.rubocop_todo.yml +11 -0
- data/.travis.yml +3 -7
- data/CHANGELOG.md +18 -9
- data/CODE_OF_CONDUCT.md +74 -0
- data/Gemfile +8 -5
- data/README.md +46 -99
- data/Rakefile +8 -6
- data/feedjira.gemspec +31 -20
- data/lib/feedjira.rb +75 -41
- data/lib/feedjira/atom_entry_utilities.rb +51 -0
- data/lib/feedjira/configuration.rb +8 -10
- data/lib/feedjira/core_ext.rb +5 -3
- data/lib/feedjira/core_ext/date.rb +2 -1
- data/lib/feedjira/core_ext/string.rb +2 -1
- data/lib/feedjira/core_ext/time.rb +12 -12
- data/lib/feedjira/date_time_utilities.rb +8 -10
- data/lib/feedjira/date_time_utilities/date_time_epoch_parser.rb +3 -2
- data/lib/feedjira/date_time_utilities/date_time_language_parser.rb +4 -4
- data/lib/feedjira/date_time_utilities/date_time_pattern_parser.rb +11 -15
- data/lib/feedjira/feed.rb +12 -82
- data/lib/feedjira/feed_entry_utilities.rb +14 -7
- data/lib/feedjira/feed_utilities.rb +5 -4
- data/lib/feedjira/parser.rb +6 -1
- data/lib/feedjira/parser/atom.rb +6 -5
- data/lib/feedjira/parser/atom_entry.rb +4 -21
- data/lib/feedjira/parser/atom_feed_burner.rb +7 -6
- data/lib/feedjira/parser/atom_feed_burner_entry.rb +7 -18
- data/lib/feedjira/parser/atom_google_alerts.rb +26 -0
- data/lib/feedjira/parser/atom_google_alerts_entry.rb +21 -0
- data/lib/feedjira/parser/atom_youtube.rb +4 -3
- data/lib/feedjira/parser/atom_youtube_entry.rb +9 -8
- data/lib/feedjira/parser/globally_unique_identifier.rb +21 -0
- data/lib/feedjira/parser/google_docs_atom.rb +6 -6
- data/lib/feedjira/parser/google_docs_atom_entry.rb +3 -19
- data/lib/feedjira/parser/itunes_rss.rb +4 -3
- data/lib/feedjira/parser/itunes_rss_category.rb +6 -5
- data/lib/feedjira/parser/itunes_rss_item.rb +5 -8
- data/lib/feedjira/parser/itunes_rss_owner.rb +2 -1
- data/lib/feedjira/parser/json_feed.rb +41 -0
- data/lib/feedjira/parser/json_feed_item.rb +57 -0
- data/lib/feedjira/parser/podlove_chapter.rb +4 -3
- data/lib/feedjira/parser/rss.rb +5 -3
- data/lib/feedjira/parser/rss_entry.rb +3 -24
- data/lib/feedjira/parser/rss_feed_burner.rb +4 -3
- data/lib/feedjira/parser/rss_feed_burner_entry.rb +6 -26
- data/lib/feedjira/parser/rss_image.rb +2 -0
- data/lib/feedjira/preprocessor.rb +4 -4
- data/lib/feedjira/rss_entry_utilities.rb +53 -0
- data/lib/feedjira/version.rb +3 -1
- data/spec/feedjira/configuration_spec.rb +11 -16
- data/spec/feedjira/date_time_utilities_spec.rb +22 -20
- data/spec/feedjira/feed_entry_utilities_spec.rb +20 -18
- data/spec/feedjira/feed_spec.rb +17 -229
- data/spec/feedjira/feed_utilities_spec.rb +75 -73
- data/spec/feedjira/parser/atom_entry_spec.rb +41 -38
- data/spec/feedjira/parser/atom_feed_burner_entry_spec.rb +22 -20
- data/spec/feedjira/parser/atom_feed_burner_spec.rb +122 -118
- data/spec/feedjira/parser/atom_google_alerts_entry_spec.rb +34 -0
- data/spec/feedjira/parser/atom_google_alerts_spec.rb +62 -0
- data/spec/feedjira/parser/atom_spec.rb +83 -77
- data/spec/feedjira/parser/atom_youtube_entry_spec.rb +41 -39
- data/spec/feedjira/parser/atom_youtube_spec.rb +21 -19
- data/spec/feedjira/parser/google_docs_atom_entry_spec.rb +10 -8
- data/spec/feedjira/parser/google_docs_atom_spec.rb +25 -21
- data/spec/feedjira/parser/itunes_rss_item_spec.rb +39 -37
- data/spec/feedjira/parser/itunes_rss_owner_spec.rb +7 -5
- data/spec/feedjira/parser/itunes_rss_spec.rb +120 -116
- data/spec/feedjira/parser/json_feed_item_spec.rb +81 -0
- data/spec/feedjira/parser/json_feed_spec.rb +55 -0
- data/spec/feedjira/parser/podlove_chapter_spec.rb +14 -12
- data/spec/feedjira/parser/rss_entry_spec.rb +56 -34
- data/spec/feedjira/parser/rss_feed_burner_entry_spec.rb +36 -34
- data/spec/feedjira/parser/rss_feed_burner_spec.rb +49 -45
- data/spec/feedjira/parser/rss_spec.rb +38 -36
- data/spec/feedjira/preprocessor_spec.rb +9 -7
- data/spec/feedjira_spec.rb +166 -0
- data/spec/sample_feeds.rb +32 -29
- data/spec/sample_feeds/HuffPostCanada.xml +279 -0
- data/spec/sample_feeds/Permalinks.xml +22 -0
- data/spec/sample_feeds/a10.xml +72 -0
- data/spec/sample_feeds/google_alerts_atom.xml +1 -0
- data/spec/sample_feeds/json_feed.json +156 -0
- data/spec/spec_helper.rb +7 -5
- metadata +59 -70
- data/Dangerfile +0 -1
- data/fixtures/vcr_cassettes/fetch_failure.yml +0 -62
- data/fixtures/vcr_cassettes/parse_error.yml +0 -222
- data/fixtures/vcr_cassettes/success.yml +0 -281
@@ -1,4 +1,6 @@
|
|
1
|
-
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "spec_helper"
|
2
4
|
|
3
5
|
describe Feedjira::Parser::AtomFeedBurnerEntry do
|
4
6
|
before(:each) do
|
@@ -10,45 +12,45 @@ describe Feedjira::Parser::AtomFeedBurnerEntry do
|
|
10
12
|
@entry = feed.entries.first
|
11
13
|
end
|
12
14
|
|
13
|
-
it
|
14
|
-
expect(@entry.title).to eq
|
15
|
+
it "should parse the title" do
|
16
|
+
expect(@entry.title).to eq "Making a Ruby C library even faster"
|
15
17
|
end
|
16
18
|
|
17
|
-
it "should be able to fetch a url via the 'alternate' rel if no origLink exists" do
|
18
|
-
xml = File.read("#{File.dirname(__FILE__)}/../../sample_feeds/PaulDixExplainsNothingAlternate.xml")
|
19
|
+
it "should be able to fetch a url via the 'alternate' rel if no origLink exists" do
|
20
|
+
xml = File.read("#{File.dirname(__FILE__)}/../../sample_feeds/PaulDixExplainsNothingAlternate.xml")
|
19
21
|
entry = Feedjira::Parser::AtomFeedBurner.parse(xml).entries.first
|
20
|
-
expect(entry.url).to eq
|
22
|
+
expect(entry.url).to eq("http://feeds.feedburner.com/~r/PaulDixExplainsNothing/~3/519925023/making-a-ruby-c-library-even-faster.html")
|
21
23
|
end
|
22
24
|
|
23
|
-
it
|
24
|
-
expect(@entry.url).to eq
|
25
|
+
it "should parse the url" do
|
26
|
+
expect(@entry.url).to eq "http://www.pauldix.net/2009/01/making-a-ruby-c-library-even-faster.html"
|
25
27
|
end
|
26
28
|
|
27
|
-
it
|
28
|
-
xml = File.read("#{File.dirname(__FILE__)}/../../sample_feeds/FeedBurnerUrlNoAlternate.xml")
|
29
|
+
it "should parse the url when there is no alternate" do
|
30
|
+
xml = File.read("#{File.dirname(__FILE__)}/../../sample_feeds/FeedBurnerUrlNoAlternate.xml")
|
29
31
|
entry = Feedjira::Parser::AtomFeedBurner.parse(xml).entries.first
|
30
|
-
expect(entry.url).to eq
|
32
|
+
expect(entry.url).to eq "http://example.com/QQQQ.html"
|
31
33
|
end
|
32
34
|
|
33
|
-
it
|
34
|
-
expect(@entry.author).to eq
|
35
|
+
it "should parse the author" do
|
36
|
+
expect(@entry.author).to eq "Paul Dix"
|
35
37
|
end
|
36
38
|
|
37
|
-
it
|
39
|
+
it "should parse the content" do
|
38
40
|
expect(@entry.content).to eq sample_feedburner_atom_entry_content
|
39
41
|
end
|
40
42
|
|
41
|
-
it
|
42
|
-
summary = "Last week I released the first version of a SAX based XML parsing library called SAX-Machine. It uses Nokogiri, which uses libxml, so it's pretty fast. However, I felt that it could be even faster. The only question was how..."
|
43
|
+
it "should provide a summary" do
|
44
|
+
summary = "Last week I released the first version of a SAX based XML parsing library called SAX-Machine. It uses Nokogiri, which uses libxml, so it's pretty fast. However, I felt that it could be even faster. The only question was how..."
|
43
45
|
expect(@entry.summary).to eq summary
|
44
46
|
end
|
45
47
|
|
46
|
-
it
|
47
|
-
published = Time.parse_safely
|
48
|
+
it "should parse the published date" do
|
49
|
+
published = Time.parse_safely "Thu Jan 22 15:50:22 UTC 2009"
|
48
50
|
expect(@entry.published).to eq published
|
49
51
|
end
|
50
52
|
|
51
|
-
it
|
52
|
-
expect(@entry.categories).to eq [
|
53
|
+
it "should parse the categories" do
|
54
|
+
expect(@entry.categories).to eq ["Ruby", "Another Category"]
|
53
55
|
end
|
54
56
|
end
|
@@ -1,124 +1,128 @@
|
|
1
|
-
|
2
|
-
|
3
|
-
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "spec_helper"
|
4
|
+
|
5
|
+
module Feedjira
|
6
|
+
module Parser
|
7
|
+
describe "#will_parse?" do
|
8
|
+
it "should return true for a feedburner atom feed" do
|
9
|
+
expect(AtomFeedBurner).to be_able_to_parse(sample_feedburner_atom_feed)
|
10
|
+
end
|
11
|
+
|
12
|
+
it "should return false for an rdf feed" do
|
13
|
+
expect(AtomFeedBurner).to_not be_able_to_parse(sample_rdf_feed)
|
14
|
+
end
|
15
|
+
|
16
|
+
it "should return false for a regular atom feed" do
|
17
|
+
expect(AtomFeedBurner).to_not be_able_to_parse(sample_atom_feed)
|
18
|
+
end
|
19
|
+
|
20
|
+
it "should return false for an rss feedburner feed" do
|
21
|
+
expect(AtomFeedBurner).to_not be_able_to_parse sample_rss_feed_burner_feed
|
22
|
+
end
|
19
23
|
end
|
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
|
-
|
24
|
+
|
25
|
+
describe "parsing old style feeds" do
|
26
|
+
before(:each) do
|
27
|
+
@feed = AtomFeedBurner.parse(sample_feedburner_atom_feed)
|
28
|
+
end
|
29
|
+
|
30
|
+
it "should parse the title" do
|
31
|
+
expect(@feed.title).to eq "Paul Dix Explains Nothing"
|
32
|
+
end
|
33
|
+
|
34
|
+
it "should parse the description" do
|
35
|
+
description = "Entrepreneurship, programming, software development, politics, NYC, and random thoughts."
|
36
|
+
expect(@feed.description).to eq description
|
37
|
+
end
|
38
|
+
|
39
|
+
it "should parse the url" do
|
40
|
+
expect(@feed.url).to eq "http://www.pauldix.net/"
|
41
|
+
end
|
42
|
+
|
43
|
+
it "should parse the feed_url" do
|
44
|
+
expect(@feed.feed_url).to eq "http://feeds.feedburner.com/PaulDixExplainsNothing"
|
45
|
+
end
|
46
|
+
|
47
|
+
it "should parse no hub urls" do
|
48
|
+
expect(@feed.hubs.count).to eq 0
|
49
|
+
end
|
50
|
+
|
51
|
+
it "should parse hub urls" do
|
52
|
+
AtomFeedBurner.preprocess_xml = false
|
53
|
+
feed_with_hub = AtomFeedBurner.parse(load_sample("TypePadNews.xml"))
|
54
|
+
expect(feed_with_hub.hubs.count).to eq 1
|
55
|
+
end
|
56
|
+
|
57
|
+
it "should parse entries" do
|
58
|
+
expect(@feed.entries.size).to eq 5
|
59
|
+
end
|
60
|
+
|
61
|
+
it "should change url" do
|
62
|
+
new_url = "http://some.url.com"
|
63
|
+
expect { @feed.url = new_url }.not_to raise_error
|
64
|
+
expect(@feed.url).to eq new_url
|
65
|
+
end
|
66
|
+
|
67
|
+
it "should change feed_url" do
|
68
|
+
new_url = "http://some.url.com"
|
69
|
+
expect { @feed.feed_url = new_url }.not_to raise_error
|
70
|
+
expect(@feed.feed_url).to eq new_url
|
71
|
+
end
|
72
|
+
end
|
73
|
+
|
74
|
+
describe "parsing alternate style feeds" do
|
75
|
+
before(:each) do
|
76
|
+
@feed = AtomFeedBurner.parse(sample_feedburner_atom_feed_alternate)
|
77
|
+
end
|
78
|
+
|
79
|
+
it "should parse the title" do
|
80
|
+
expect(@feed.title).to eq "Giant Robots Smashing Into Other Giant Robots"
|
81
|
+
end
|
82
|
+
|
83
|
+
it "should parse the description" do
|
84
|
+
description = "Written by thoughtbot"
|
85
|
+
expect(@feed.description).to eq description
|
86
|
+
end
|
87
|
+
|
88
|
+
it "should parse the url" do
|
89
|
+
expect(@feed.url).to eq "https://robots.thoughtbot.com"
|
90
|
+
end
|
91
|
+
|
92
|
+
it "should parse the feed_url" do
|
93
|
+
expect(@feed.feed_url).to eq "http://feeds.feedburner.com/GiantRobotsSmashingIntoOtherGiantRobots"
|
94
|
+
end
|
95
|
+
|
96
|
+
it "should parse hub urls" do
|
97
|
+
expect(@feed.hubs.count).to eq 1
|
98
|
+
end
|
99
|
+
|
100
|
+
it "should parse entries" do
|
101
|
+
expect(@feed.entries.size).to eq 3
|
102
|
+
end
|
103
|
+
|
104
|
+
it "should change url" do
|
105
|
+
new_url = "http://some.url.com"
|
106
|
+
expect { @feed.url = new_url }.not_to raise_error
|
107
|
+
expect(@feed.url).to eq new_url
|
108
|
+
end
|
109
|
+
|
110
|
+
it "should change feed_url" do
|
111
|
+
new_url = "http://some.url.com"
|
112
|
+
expect { @feed.feed_url = new_url }.not_to raise_error
|
113
|
+
expect(@feed.feed_url).to eq new_url
|
114
|
+
end
|
62
115
|
end
|
63
116
|
|
64
|
-
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
-
|
69
|
-
|
70
|
-
|
71
|
-
|
72
|
-
|
73
|
-
@feed = AtomFeedBurner.parse(sample_feedburner_atom_feed_alternate)
|
74
|
-
end
|
75
|
-
|
76
|
-
it 'should parse the title' do
|
77
|
-
expect(@feed.title).to eq 'Giant Robots Smashing Into Other Giant Robots'
|
78
|
-
end
|
79
|
-
|
80
|
-
it 'should parse the description' do
|
81
|
-
description = 'Written by thoughtbot'
|
82
|
-
expect(@feed.description).to eq description
|
83
|
-
end
|
84
|
-
|
85
|
-
it 'should parse the url' do
|
86
|
-
expect(@feed.url).to eq 'https://robots.thoughtbot.com'
|
87
|
-
end
|
88
|
-
|
89
|
-
it 'should parse the feed_url' do
|
90
|
-
expect(@feed.feed_url).to eq 'http://feeds.feedburner.com/GiantRobotsSmashingIntoOtherGiantRobots'
|
91
|
-
end
|
92
|
-
|
93
|
-
it 'should parse hub urls' do
|
94
|
-
expect(@feed.hubs.count).to eq 1
|
95
|
-
end
|
96
|
-
|
97
|
-
it 'should parse entries' do
|
98
|
-
expect(@feed.entries.size).to eq 3
|
99
|
-
end
|
100
|
-
|
101
|
-
it 'should change url' do
|
102
|
-
new_url = 'http://some.url.com'
|
103
|
-
expect { @feed.url = new_url }.not_to raise_error
|
104
|
-
expect(@feed.url).to eq new_url
|
105
|
-
end
|
106
|
-
|
107
|
-
it 'should change feed_url' do
|
108
|
-
new_url = 'http://some.url.com'
|
109
|
-
expect { @feed.feed_url = new_url }.not_to raise_error
|
110
|
-
expect(@feed.feed_url).to eq new_url
|
111
|
-
end
|
112
|
-
end
|
113
|
-
|
114
|
-
describe 'preprocessing' do
|
115
|
-
it 'retains markup in xhtml content' do
|
116
|
-
AtomFeedBurner.preprocess_xml = true
|
117
|
-
|
118
|
-
feed = AtomFeedBurner.parse sample_feed_burner_atom_xhtml_feed
|
119
|
-
entry = feed.entries.first
|
120
|
-
|
121
|
-
expect(entry.content).to match(/\A\<p/)
|
117
|
+
describe "preprocessing" do
|
118
|
+
it "retains markup in xhtml content" do
|
119
|
+
AtomFeedBurner.preprocess_xml = true
|
120
|
+
|
121
|
+
feed = AtomFeedBurner.parse sample_feed_burner_atom_xhtml_feed
|
122
|
+
entry = feed.entries.first
|
123
|
+
|
124
|
+
expect(entry.content).to match(/\A<p/)
|
125
|
+
end
|
122
126
|
end
|
123
127
|
end
|
124
128
|
end
|
@@ -0,0 +1,34 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "spec_helper"
|
4
|
+
|
5
|
+
describe Feedjira::Parser::AtomGoogleAlertsEntry do
|
6
|
+
before(:each) do
|
7
|
+
feed = Feedjira::Parser::AtomGoogleAlerts.parse sample_google_alerts_atom_feed
|
8
|
+
@entry = feed.entries.first
|
9
|
+
end
|
10
|
+
|
11
|
+
it "should parse the title" do
|
12
|
+
expect(@entry.title).to eq "Report offers Prediction of Automotive Slack Market by Top key players like Haldex, Meritor, Bendix ..."
|
13
|
+
expect(@entry.raw_title).to eq "Report offers Prediction of Automotive <b>Slack</b> Market by Top key players like Haldex, Meritor, Bendix ..."
|
14
|
+
expect(@entry.title_type).to eq "html"
|
15
|
+
end
|
16
|
+
|
17
|
+
it "should parse the url" do
|
18
|
+
expect(@entry.url).to eq "https://www.aglobalmarketresearch.com/report-offers-prediction-of-automotive-slack-market-by-top-key-players-like-haldex-meritor-bendix-mei-wabco-accuride-stemco-tbk-febi-aydinsan/"
|
19
|
+
end
|
20
|
+
|
21
|
+
it "should parse the content" do
|
22
|
+
expect(@entry.content).to eq "Automotive <b>Slack</b> Market reports provides a comprehensive overview of the global market size and share. It provides strategists, marketers and senior ..."
|
23
|
+
end
|
24
|
+
|
25
|
+
it "should parse the published date" do
|
26
|
+
published = Time.parse_safely "2019-07-10T11:53:37Z"
|
27
|
+
expect(@entry.published).to eq published
|
28
|
+
end
|
29
|
+
|
30
|
+
it "should parse the updated date" do
|
31
|
+
updated = Time.parse_safely "2019-07-10T11:53:37Z"
|
32
|
+
expect(@entry.updated).to eq updated
|
33
|
+
end
|
34
|
+
end
|
@@ -0,0 +1,62 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "spec_helper"
|
4
|
+
|
5
|
+
module Feedjira
|
6
|
+
module Parser
|
7
|
+
describe "#able_to_parse?" do
|
8
|
+
it "should return true for a Google Alerts atom feed" do
|
9
|
+
expect(AtomGoogleAlerts).to be_able_to_parse(sample_google_alerts_atom_feed)
|
10
|
+
end
|
11
|
+
|
12
|
+
it "should return false for an rdf feed" do
|
13
|
+
expect(AtomGoogleAlerts).to_not be_able_to_parse(sample_rdf_feed)
|
14
|
+
end
|
15
|
+
|
16
|
+
it "should return false for a regular atom feed" do
|
17
|
+
expect(AtomGoogleAlerts).to_not be_able_to_parse(sample_atom_feed)
|
18
|
+
end
|
19
|
+
|
20
|
+
it "should return false for a feedburner atom feed" do
|
21
|
+
expect(AtomGoogleAlerts).to_not be_able_to_parse(sample_feedburner_atom_feed)
|
22
|
+
end
|
23
|
+
end
|
24
|
+
|
25
|
+
describe "parsing" do
|
26
|
+
before(:each) do
|
27
|
+
@feed = AtomGoogleAlerts.parse(sample_google_alerts_atom_feed)
|
28
|
+
end
|
29
|
+
|
30
|
+
it "should parse the title" do
|
31
|
+
expect(@feed.title).to eq "Google Alert - Slack"
|
32
|
+
end
|
33
|
+
|
34
|
+
it "should parse the descripton" do
|
35
|
+
expect(@feed.description).to be_nil
|
36
|
+
end
|
37
|
+
|
38
|
+
it "should parse the url" do
|
39
|
+
expect(@feed.url).to eq "https://www.google.com/alerts/feeds/04175468913983673025/4428013283581841004"
|
40
|
+
end
|
41
|
+
|
42
|
+
it "should parse the feed_url" do
|
43
|
+
expect(@feed.feed_url).to eq "https://www.google.com/alerts/feeds/04175468913983673025/4428013283581841004"
|
44
|
+
end
|
45
|
+
|
46
|
+
it "should parse entries" do
|
47
|
+
expect(@feed.entries.size).to eq 20
|
48
|
+
end
|
49
|
+
end
|
50
|
+
|
51
|
+
describe "preprocessing" do
|
52
|
+
it "retains markup in xhtml content" do
|
53
|
+
AtomGoogleAlerts.preprocess_xml = true
|
54
|
+
|
55
|
+
feed = AtomGoogleAlerts.parse sample_google_alerts_atom_feed
|
56
|
+
entry = feed.entries.first
|
57
|
+
|
58
|
+
expect(entry.content).to include("<b>Slack</b>")
|
59
|
+
end
|
60
|
+
end
|
61
|
+
end
|
62
|
+
end
|
@@ -1,104 +1,110 @@
|
|
1
|
-
|
1
|
+
# frozen_string_literal: true
|
2
2
|
|
3
|
-
|
4
|
-
describe '#will_parse?' do
|
5
|
-
it 'should return true for an atom feed' do
|
6
|
-
expect(Atom).to be_able_to_parse(sample_atom_feed)
|
7
|
-
end
|
3
|
+
require "spec_helper"
|
8
4
|
|
9
|
-
|
10
|
-
|
11
|
-
|
5
|
+
module Feedjira
|
6
|
+
module Parser
|
7
|
+
describe "#will_parse?" do
|
8
|
+
it "should return true for an atom feed" do
|
9
|
+
expect(Atom).to be_able_to_parse(sample_atom_feed)
|
10
|
+
end
|
12
11
|
|
13
|
-
|
14
|
-
|
15
|
-
|
12
|
+
it "should return false for an rdf feed" do
|
13
|
+
expect(Atom).to_not be_able_to_parse(sample_rdf_feed)
|
14
|
+
end
|
16
15
|
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
end
|
16
|
+
it "should return false for an rss feedburner feed" do
|
17
|
+
expect(Atom).to_not be_able_to_parse(sample_rss_feed_burner_feed)
|
18
|
+
end
|
21
19
|
|
22
|
-
|
23
|
-
|
24
|
-
|
20
|
+
it "should return true for an atom feed that has line breaks in between attributes in the <feed> node" do
|
21
|
+
expect(Atom).to be_able_to_parse(sample_atom_feed_line_breaks)
|
22
|
+
end
|
25
23
|
end
|
26
24
|
|
27
|
-
|
28
|
-
|
29
|
-
|
25
|
+
describe "parsing" do
|
26
|
+
before(:each) do
|
27
|
+
@feed = Atom.parse(sample_atom_feed)
|
28
|
+
end
|
30
29
|
|
31
|
-
|
32
|
-
|
33
|
-
|
34
|
-
end
|
30
|
+
it "should parse the title" do
|
31
|
+
expect(@feed.title).to eq "Amazon Web Services Blog"
|
32
|
+
end
|
35
33
|
|
36
|
-
|
37
|
-
|
38
|
-
|
34
|
+
it "should parse the description" do
|
35
|
+
description = "Amazon Web Services, Products, Tools, and Developer Information..."
|
36
|
+
expect(@feed.description).to eq description
|
37
|
+
end
|
39
38
|
|
40
|
-
|
41
|
-
|
42
|
-
|
43
|
-
expect(feed.url).to eq 'http://www.innoq.com/planet/'
|
44
|
-
end
|
39
|
+
it "should parse the url" do
|
40
|
+
expect(@feed.url).to eq "http://aws.typepad.com/aws/"
|
41
|
+
end
|
45
42
|
|
46
|
-
|
47
|
-
|
48
|
-
|
49
|
-
|
43
|
+
it "should parse the url even when it doesn't have the type='text/html' attribute" do
|
44
|
+
xml = load_sample "atom_with_link_tag_for_url_unmarked.xml"
|
45
|
+
feed = Atom.parse xml
|
46
|
+
expect(feed.url).to eq "http://www.innoq.com/planet/"
|
47
|
+
end
|
50
48
|
|
51
|
-
|
52
|
-
|
53
|
-
|
49
|
+
it "should parse the feed_url even when it doesn't have the type='application/atom+xml' attribute" do
|
50
|
+
feed = Atom.parse(load_sample("atom_with_link_tag_for_url_unmarked.xml"))
|
51
|
+
expect(feed.feed_url).to eq "http://www.innoq.com/planet/atom.xml"
|
52
|
+
end
|
54
53
|
|
55
|
-
|
56
|
-
|
57
|
-
|
54
|
+
it "should parse the feed_url" do
|
55
|
+
expect(@feed.feed_url).to eq "http://aws.typepad.com/aws/atom.xml"
|
56
|
+
end
|
58
57
|
|
59
|
-
|
60
|
-
|
61
|
-
|
62
|
-
expect(feed_with_hub.hubs.first).to eq 'http://pubsubhubbub.appspot.com/'
|
63
|
-
end
|
58
|
+
it "should parse no hub urls" do
|
59
|
+
expect(@feed.hubs.count).to eq 0
|
60
|
+
end
|
64
61
|
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
-
|
62
|
+
it "should parse the hub urls" do
|
63
|
+
feed_with_hub = Atom.parse(load_sample("SamRuby.xml"))
|
64
|
+
expect(feed_with_hub.hubs.count).to eq 1
|
65
|
+
expect(feed_with_hub.hubs.first).to eq "http://pubsubhubbub.appspot.com/"
|
66
|
+
end
|
69
67
|
|
70
|
-
|
71
|
-
|
72
|
-
|
68
|
+
it "should parse entries" do
|
69
|
+
expect(@feed.entries.size).to eq 10
|
70
|
+
end
|
71
|
+
end
|
73
72
|
|
74
|
-
|
75
|
-
|
73
|
+
describe "preprocessing" do
|
74
|
+
it "retains markup in xhtml content" do
|
75
|
+
Atom.preprocess_xml = true
|
76
76
|
|
77
|
-
|
78
|
-
|
79
|
-
expect(entry.content).to match(/\A\<p/)
|
80
|
-
end
|
77
|
+
feed = Atom.parse sample_atom_xhtml_feed
|
78
|
+
entry = feed.entries.first
|
81
79
|
|
82
|
-
|
83
|
-
|
80
|
+
expect(entry.raw_title).to match(/<i/)
|
81
|
+
expect(entry.title).to eq("Sentry Calming Collar for dogs")
|
82
|
+
expect(entry.title_type).to eq("xhtml")
|
83
|
+
expect(entry.summary).to match(/<b/)
|
84
|
+
expect(entry.content).to match(/\A<p/)
|
85
|
+
end
|
84
86
|
|
85
|
-
|
86
|
-
|
87
|
-
expect(content.css('img').length).to eq 11
|
88
|
-
end
|
89
|
-
end
|
87
|
+
it "should not duplicate content when there are divs in content" do
|
88
|
+
Atom.preprocess_xml = true
|
90
89
|
|
91
|
-
|
92
|
-
|
93
|
-
|
90
|
+
feed = Atom.parse sample_duplicate_content_atom_feed
|
91
|
+
content = Nokogiri::HTML(feed.entries[1].content)
|
92
|
+
expect(content.css("img").length).to eq 11
|
93
|
+
end
|
94
94
|
end
|
95
95
|
|
96
|
-
|
97
|
-
|
98
|
-
|
96
|
+
describe "parsing url and feed url based on rel attribute" do
|
97
|
+
before :each do
|
98
|
+
@feed = Atom.parse(sample_atom_middleman_feed)
|
99
|
+
end
|
99
100
|
|
100
|
-
|
101
|
-
|
101
|
+
it "should parse url" do
|
102
|
+
expect(@feed.url).to eq "http://feedjira.com/blog"
|
103
|
+
end
|
104
|
+
|
105
|
+
it "should parse feed url" do
|
106
|
+
expect(@feed.feed_url).to eq "http://feedjira.com/blog/feed.xml"
|
107
|
+
end
|
102
108
|
end
|
103
109
|
end
|
104
110
|
end
|