aboutsummaryrefslogtreecommitdiffhomepage
path: root/reader/rdf/parser_test.go
blob: bad3ed78ab5f6471860dd4eb702cc1b237ffa2c6 (plain)
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
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
// Copyright 2017 Frédéric Guillot. All rights reserved.
// Use of this source code is governed by the Apache 2.0
// license that can be found in the LICENSE file.

package rdf

import (
	"bytes"
	"strings"
	"testing"
	"time"

	"github.com/miniflux/miniflux2/errors"
)

func TestParseRDFSample(t *testing.T) {
	data := `
	<?xml version="1.0"?>

	<rdf:RDF
	  xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
	  xmlns="http://purl.org/rss/1.0/"
	>

	  <channel rdf:about="http://www.xml.com/xml/news.rss">
		<title>XML.com</title>
		<link>http://xml.com/pub</link>
		<description>
		  XML.com features a rich mix of information and services
		  for the XML community.
		</description>

		<image rdf:resource="http://xml.com/universal/images/xml_tiny.gif" />

		<items>
		  <rdf:Seq>
			<rdf:li resource="http://xml.com/pub/2000/08/09/xslt/xslt.html" />
			<rdf:li resource="http://xml.com/pub/2000/08/09/rdfdb/index.html" />
		  </rdf:Seq>
		</items>

		<textinput rdf:resource="http://search.xml.com" />

	  </channel>

	  <image rdf:about="http://xml.com/universal/images/xml_tiny.gif">
		<title>XML.com</title>
		<link>http://www.xml.com</link>
		<url>http://xml.com/universal/images/xml_tiny.gif</url>
	  </image>

	  <item rdf:about="http://xml.com/pub/2000/08/09/xslt/xslt.html">
		<title>Processing Inclusions with XSLT</title>
		<link>http://xml.com/pub/2000/08/09/xslt/xslt.html</link>
		<description>
		 Processing document inclusions with general XML tools can be
		 problematic. This article proposes a way of preserving inclusion
		 information through SAX-based processing.
		</description>
	  </item>

	  <item rdf:about="http://xml.com/pub/2000/08/09/rdfdb/index.html">
		<title>Putting RDF to Work</title>
		<link>http://xml.com/pub/2000/08/09/rdfdb/index.html</link>
		<description>
		 Tool and API support for the Resource Description Framework
		 is slowly coming of age. Edd Dumbill takes a look at RDFDB,
		 one of the most exciting new RDF toolkits.
		</description>
	  </item>

	  <textinput rdf:about="http://search.xml.com">
		<title>Search XML.com</title>
		<description>Search XML.com's XML collection</description>
		<name>s</name>
		<link>http://search.xml.com</link>
	  </textinput>

	</rdf:RDF>`

	feed, err := Parse(bytes.NewBufferString(data))
	if err != nil {
		t.Error(err)
	}

	if feed.Title != "XML.com" {
		t.Errorf("Incorrect title, got: %s", feed.Title)
	}

	if feed.FeedURL != "" {
		t.Errorf("Incorrect feed URL, got: %s", feed.FeedURL)
	}

	if feed.SiteURL != "http://xml.com/pub" {
		t.Errorf("Incorrect site URL, got: %s", feed.SiteURL)
	}

	if len(feed.Entries) != 2 {
		t.Errorf("Incorrect number of entries, got: %d", len(feed.Entries))
	}

	if feed.Entries[1].Hash != "8aaeee5d3ab50351422fbded41078ee88c73bf1441085b16a8c09fd90a7db321" {
		t.Errorf("Incorrect entry hash, got: %s", feed.Entries[0].Hash)
	}

	if feed.Entries[1].URL != "http://xml.com/pub/2000/08/09/rdfdb/index.html" {
		t.Errorf("Incorrect entry URL, got: %s", feed.Entries[0].URL)
	}

	if feed.Entries[1].Title != "Putting RDF to Work" {
		t.Errorf("Incorrect entry title, got: %s", feed.Entries[0].Title)
	}

	if strings.HasSuffix(feed.Entries[1].Content, "Tool and API support") {
		t.Errorf("Incorrect entry content, got: %s", feed.Entries[0].Content)
	}

	if feed.Entries[1].Date.Year() != time.Now().Year() {
		t.Errorf("Entry date should not be empty")
	}
}

func TestParseRDFSampleWithDublinCore(t *testing.T) {
	data := `<?xml version="1.0" encoding="utf-8"?>

	<rdf:RDF
	  xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
	  xmlns:dc="http://purl.org/dc/elements/1.1/"
	  xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	  xmlns:co="http://purl.org/rss/1.0/modules/company/"
	  xmlns:ti="http://purl.org/rss/1.0/modules/textinput/"
	  xmlns="http://purl.org/rss/1.0/"
	>

	  <channel rdf:about="http://meerkat.oreillynet.com/?_fl=rss1.0">
		<title>Meerkat</title>
		<link>http://meerkat.oreillynet.com</link>
		<description>Meerkat: An Open Wire Service</description>
		<dc:publisher>The O'Reilly Network</dc:publisher>
		<dc:creator>Rael Dornfest (mailto:rael@oreilly.com)</dc:creator>
		<dc:rights>Copyright &#169; 2000 O'Reilly &amp; Associates, Inc.</dc:rights>
		<dc:date>2000-01-01T12:00+00:00</dc:date>
		<sy:updatePeriod>hourly</sy:updatePeriod>
		<sy:updateFrequency>2</sy:updateFrequency>
		<sy:updateBase>2000-01-01T12:00+00:00</sy:updateBase>

		<image rdf:resource="http://meerkat.oreillynet.com/icons/meerkat-powered.jpg" />

		<items>
		  <rdf:Seq>
			<rdf:li resource="http://c.moreover.com/click/here.pl?r123" />
		  </rdf:Seq>
		</items>

		<textinput rdf:resource="http://meerkat.oreillynet.com" />

	  </channel>

	  <image rdf:about="http://meerkat.oreillynet.com/icons/meerkat-powered.jpg">
		<title>Meerkat Powered!</title>
		<url>http://meerkat.oreillynet.com/icons/meerkat-powered.jpg</url>
		<link>http://meerkat.oreillynet.com</link>
	  </image>

	  <item rdf:about="http://c.moreover.com/click/here.pl?r123">
		<title>XML: A Disruptive Technology</title>
		<link>http://c.moreover.com/click/here.pl?r123</link>
		<dc:description>
		  XML is placing increasingly heavy loads on the existing technical
		  infrastructure of the Internet.
		</dc:description>
		<dc:publisher>The O'Reilly Network</dc:publisher>
		<dc:creator>Simon St.Laurent (mailto:simonstl@simonstl.com)</dc:creator>
		<dc:rights>Copyright &#169; 2000 O'Reilly &amp; Associates, Inc.</dc:rights>
		<dc:subject>XML</dc:subject>
		<co:name>XML.com</co:name>
		<co:market>NASDAQ</co:market>
		<co:symbol>XML</co:symbol>
	  </item>

	  <textinput rdf:about="http://meerkat.oreillynet.com">
		<title>Search Meerkat</title>
		<description>Search Meerkat's RSS Database...</description>
		<name>s</name>
		<link>http://meerkat.oreillynet.com/</link>
		<ti:function>search</ti:function>
		<ti:inputType>regex</ti:inputType>
	  </textinput>

	</rdf:RDF>`

	feed, err := Parse(bytes.NewBufferString(data))
	if err != nil {
		t.Error(err)
	}

	if feed.Title != "Meerkat" {
		t.Errorf("Incorrect title, got: %s", feed.Title)
	}

	if feed.FeedURL != "" {
		t.Errorf("Incorrect feed URL, got: %s", feed.FeedURL)
	}

	if feed.SiteURL != "http://meerkat.oreillynet.com" {
		t.Errorf("Incorrect site URL, got: %s", feed.SiteURL)
	}

	if len(feed.Entries) != 1 {
		t.Errorf("Incorrect number of entries, got: %d", len(feed.Entries))
	}

	if feed.Entries[0].Hash != "fa4ef7c300b175ca66f92f226b5dba5caa2a9619f031101bf56e5b884b02cd97" {
		t.Errorf("Incorrect entry hash, got: %s", feed.Entries[0].Hash)
	}

	if feed.Entries[0].URL != "http://c.moreover.com/click/here.pl?r123" {
		t.Errorf("Incorrect entry URL, got: %s", feed.Entries[0].URL)
	}

	if feed.Entries[0].Title != "XML: A Disruptive Technology" {
		t.Errorf("Incorrect entry title, got: %s", feed.Entries[0].Title)
	}

	if strings.HasSuffix(feed.Entries[0].Content, "XML is placing increasingly") {
		t.Errorf("Incorrect entry content, got: %s", feed.Entries[0].Content)
	}

	if feed.Entries[0].Author != "Simon St.Laurent (mailto:simonstl@simonstl.com)" {
		t.Errorf("Incorrect entry author, got: %s", feed.Entries[0].Author)
	}
}

func TestParseItemWithOnlyFeedAuthor(t *testing.T) {
	data := `<?xml version="1.0" encoding="utf-8"?>

	<rdf:RDF
	  xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
	  xmlns:dc="http://purl.org/dc/elements/1.1/"
	  xmlns="http://purl.org/rss/1.0/"
	>

	  <channel rdf:about="http://meerkat.oreillynet.com/?_fl=rss1.0">
		<title>Meerkat</title>
		<link>http://meerkat.oreillynet.com</link>
		<dc:creator>Rael Dornfest (mailto:rael@oreilly.com)</dc:creator>
	  </channel>

	  <item rdf:about="http://c.moreover.com/click/here.pl?r123">
		<title>XML: A Disruptive Technology</title>
		<link>http://c.moreover.com/click/here.pl?r123</link>
		<dc:description>
		  XML is placing increasingly heavy loads on the existing technical
		  infrastructure of the Internet.
		</dc:description>
	  </item>
	</rdf:RDF>`

	feed, err := Parse(bytes.NewBufferString(data))
	if err != nil {
		t.Error(err)
	}

	if feed.Entries[0].Author != "Rael Dornfest (mailto:rael@oreilly.com)" {
		t.Errorf("Incorrect entry author, got: %s", feed.Entries[0].Author)
	}
}

func TestParseItemWithoutLink(t *testing.T) {
	data := `<?xml version="1.0" encoding="utf-8"?>

	<rdf:RDF
	  xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
	  xmlns="http://purl.org/rss/1.0/"
	>

	  <channel rdf:about="http://meerkat.oreillynet.com/?_fl=rss1.0">
		<title>Meerkat</title>
		<link>http://meerkat.oreillynet.com</link>
	  </channel>

	  <item rdf:about="http://c.moreover.com/click/here.pl?r123">
		<title>Title</title>
		<description>Test</description>
	  </item>
	</rdf:RDF>`

	feed, err := Parse(bytes.NewBufferString(data))
	if err != nil {
		t.Error(err)
	}

	if feed.Entries[0].Hash != "37f5223ebd58639aa62a49afbb61df960efb7dc5db5181dfb3cedd9a49ad34c6" {
		t.Errorf("Incorrect entry hash, got: %s", feed.Entries[0].Hash)
	}

	if feed.Entries[0].URL != "http://meerkat.oreillynet.com" {
		t.Errorf("Incorrect entry url, got: %s", feed.Entries[0].URL)
	}
}

func TestParseInvalidXml(t *testing.T) {
	data := `garbage`
	_, err := Parse(bytes.NewBufferString(data))
	if err == nil {
		t.Error("Parse should returns an error")
	}

	if _, ok := err.(errors.LocalizedError); !ok {
		t.Error("The error returned must be a LocalizedError")
	}
}