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
|
#include "rss/parser.h"
#include "3rd-party/catch.hpp"
#include "rss/exception.h"
#include "test-helpers/exceptionwithmsg.h"
TEST_CASE("Throws exception if file doesn't exist", "[rsspp::Parser]")
{
using TestHelpers::ExceptionWithMsg;
rsspp::Parser p;
REQUIRE_THROWS_MATCHES(p.parse_file("data/non-existent.xml"),
rsspp::Exception,
ExceptionWithMsg<rsspp::Exception>("could not parse file"));
}
TEST_CASE("Throws exception if file can't be parsed", "[rsspp::Parser]")
{
using TestHelpers::ExceptionWithMsg;
rsspp::Parser p;
REQUIRE_THROWS_MATCHES(p.parse_file("data/empty.xml"),
rsspp::Exception,
ExceptionWithMsg<rsspp::Exception>("could not parse file"));
}
TEST_CASE("Extracts data from RSS 0.91", "[rsspp::Parser]")
{
rsspp::Parser p;
rsspp::Feed f;
REQUIRE_NOTHROW(f = p.parse_file("data/rss091_1.xml"));
REQUIRE(f.rss_version == rsspp::Feed::RSS_0_91);
REQUIRE(f.title == "Example Channel");
REQUIRE(f.description == "an example feed");
REQUIRE(f.link == "http://example.com/");
REQUIRE(f.language == "en");
REQUIRE(f.items.size() == 1u);
REQUIRE(f.items[0].title == "1 < 2");
REQUIRE(f.items[0].link == "http://example.com/1_less_than_2.html");
REQUIRE(f.items[0].description ==
"1 < 2, 3 < 4.\nIn HTML, <b> starts a bold phrase\nand you "
"start a link with <a href=\n");
REQUIRE(f.items[0].author == "");
REQUIRE(f.items[0].guid == "");
}
TEST_CASE("Doesn't crash or garble data if an item in RSS 0.9x contains "
"an empty author tag",
"[rsspp::Parser][issue542]")
{
rsspp::Parser p;
rsspp::Feed f;
const auto check = [&]() {
REQUIRE(f.title == "A Channel with Unnamed Authors");
REQUIRE(f.description == "an example feed");
REQUIRE(f.link == "http://example.com/");
REQUIRE(f.language == "en");
REQUIRE(f.items.size() == 2u);
REQUIRE(f.items[0].title == "This one has en empty author tag");
REQUIRE(f.items[0].link == "http://example.com/test_1.html");
REQUIRE(f.items[0].description == "It doesn't matter.");
REQUIRE(f.items[0].author == "");
REQUIRE(f.items[0].guid == "");
REQUIRE(f.items[1].title == "This one has en empty author tag as well");
REQUIRE(f.items[1].link == "http://example.com/test_2.html");
REQUIRE(f.items[1].description == "Non-empty description though.");
REQUIRE(f.items[1].author == "");
REQUIRE(f.items[1].guid == "");
};
SECTION("RSS 0.91") {
REQUIRE_NOTHROW(f = p.parse_file("data/rss_091_with_empty_author.xml"));
REQUIRE(f.rss_version == rsspp::Feed::RSS_0_91);
check();
}
SECTION("RSS 0.92") {
REQUIRE_NOTHROW(f = p.parse_file("data/rss_092_with_empty_author.xml"));
REQUIRE(f.rss_version == rsspp::Feed::RSS_0_92);
check();
}
SECTION("RSS 0.94") {
REQUIRE_NOTHROW(f = p.parse_file("data/rss_094_with_empty_author.xml"));
REQUIRE(f.rss_version == rsspp::Feed::RSS_0_94);
check();
}
}
TEST_CASE("Extracts data from RSS 0.92", "[rsspp::Parser]")
{
rsspp::Parser p;
rsspp::Feed f;
REQUIRE_NOTHROW(f = p.parse_file("data/rss092_1.xml"));
REQUIRE(f.rss_version == rsspp::Feed::RSS_0_92);
REQUIRE(f.title == "Example Channel");
REQUIRE(f.description == "an example feed");
REQUIRE(f.link == "http://example.com/");
REQUIRE(f.language == "en");
REQUIRE(f.items.size() == 3u);
REQUIRE(f.items[0].title == "1 < 2");
REQUIRE(f.items[0].link == "http://example.com/1_less_than_2.html");
REQUIRE(f.items[0].base == "http://example.com/feed/rss_testing.html");
REQUIRE(f.items[1].title == "A second item");
REQUIRE(f.items[1].link == "http://example.com/a_second_item.html");
REQUIRE(f.items[1].description == "no description");
REQUIRE(f.items[1].author == "");
REQUIRE(f.items[1].guid == "");
REQUIRE(f.items[1].base == "http://example.com/item/rss_testing.html");
REQUIRE(f.items[2].title == "A third item");
REQUIRE(f.items[2].link == "http://example.com/a_third_item.html");
REQUIRE(f.items[2].description == "no description");
REQUIRE(f.items[2].base == "http://example.com/desc/rss_testing.html");
}
TEST_CASE("Extracts data fro RSS 2.0", "[rsspp::Parser]")
{
rsspp::Parser p;
rsspp::Feed f;
REQUIRE_NOTHROW(f = p.parse_file("data/rss20_1.xml"));
REQUIRE(f.title == "my weblog");
REQUIRE(f.link == "http://example.com/blog/");
REQUIRE(f.description == "my description");
REQUIRE(f.items.size() == 1u);
REQUIRE(f.items[0].title == "this is an item");
REQUIRE(f.items[0].link ==
"http://example.com/blog/this_is_an_item.html");
REQUIRE(f.items[0].author == "Andreas Krennmair");
REQUIRE(f.items[0].author_email == "blog@synflood.at");
REQUIRE(f.items[0].content_encoded == "oh well, this is the content.");
REQUIRE(f.items[0].pubDate == "Fri, 12 Dec 2008 02:36:10 +0100");
REQUIRE(f.items[0].guid ==
"http://example.com/blog/this_is_an_item.html");
REQUIRE_FALSE(f.items[0].guid_isPermaLink);
}
TEST_CASE("Extracts data from RSS 1.0", "[rsspp::Parser]")
{
rsspp::Parser p;
rsspp::Feed f;
REQUIRE_NOTHROW(f = p.parse_file("data/rss10_1.xml"));
REQUIRE(f.rss_version == rsspp::Feed::RSS_1_0);
REQUIRE(f.title == "Example Dot Org");
REQUIRE(f.link == "http://www.example.org");
REQUIRE(f.description == "the Example Organization web site");
REQUIRE(f.items.size() == 1u);
REQUIRE(f.items[0].title == "New Status Updates");
REQUIRE(f.items[0].link == "http://www.example.org/status/foo");
REQUIRE(f.items[0].guid == "http://www.example.org/status/");
REQUIRE(f.items[0].description == "News about the Example project");
REQUIRE(f.items[0].pubDate == "Tue, 30 Dec 2008 07:20:00 +0000");
}
TEST_CASE("Extracts data from Atom 1.0", "[rsspp::Parser]")
{
rsspp::Parser p;
rsspp::Feed f;
REQUIRE_NOTHROW(f = p.parse_file("data/atom10_1.xml"));
REQUIRE(f.rss_version == rsspp::Feed::ATOM_1_0);
REQUIRE(f.title == "test atom");
REQUIRE(f.title_type == "text");
REQUIRE(f.description == "atom description!");
REQUIRE(f.pubDate == "Tue, 30 Dec 2008 18:26:15 +0000");
REQUIRE(f.link == "http://example.com/");
REQUIRE(f.items.size() == 3u);
REQUIRE(f.items[0].title == "A gentle introduction to Atom testing");
REQUIRE(f.items[0].title_type == "html");
REQUIRE(f.items[0].link == "http://example.com/atom_testing.html");
REQUIRE(f.items[0].guid == "tag:example.com,2008-12-30:/atom_testing");
REQUIRE(f.items[0].description == "some content");
REQUIRE(f.items[0].base == "http://example.com/feed/atom_testing.html");
REQUIRE(f.items[0].author == "A Person");
REQUIRE(f.items[1].title == "A missing rel attribute");
REQUIRE(f.items[1].title_type == "html");
REQUIRE(f.items[1].link == "http://example.com/atom_testing.html");
REQUIRE(f.items[1].guid == "tag:example.com,2008-12-30:/atom_testing1");
REQUIRE(f.items[1].description == "some content");
REQUIRE(f.items[1].base ==
"http://example.com/entry/atom_testing.html");
REQUIRE(f.items[1].author == "A different Person");
REQUIRE(f.items[2].title == "alternate link isn't first");
REQUIRE(f.items[2].title_type == "html");
REQUIRE(f.items[2].link == "http://example.com/atom_testing.html");
REQUIRE(f.items[2].guid == "tag:example.com,2008-12-30:/atom_testing2");
REQUIRE(f.items[2].description == "some content");
REQUIRE(f.items[2].base ==
"http://example.com/content/atom_testing.html");
REQUIRE(f.items[2].author == "Person A, Person B");
}
TEST_CASE("Extracts data from media:... tags in atom feed", "[rsspp::Parser]")
{
rsspp::Parser p;
rsspp::Feed f;
REQUIRE_NOTHROW(f = p.parse_file("data/atom10_2.xml"));
REQUIRE(f.rss_version == rsspp::Feed::ATOM_1_0);
REQUIRE(f.title == "Media test feed");
REQUIRE(f.title_type == "text");
REQUIRE(f.pubDate == "Tue, 30 Dec 2008 18:26:15 +0000");
REQUIRE(f.link == "http://example.com/");
REQUIRE(f.items.size() == 5u);
REQUIRE(f.items[0].title == "using regular content");
REQUIRE(f.items[0].description == "regular html content");
REQUIRE(f.items[0].description_mime_type == "text/html");
REQUIRE(f.items[1].title == "using media:description");
REQUIRE(f.items[1].description == "media plaintext content");
REQUIRE(f.items[1].description_mime_type == "text/plain");
REQUIRE(f.items[2].title == "using multiple media tags");
REQUIRE(f.items[2].description == "media html content");
REQUIRE(f.items[2].description_mime_type == "text/html");
REQUIRE(f.items[2].link == "http://example.com/player.html");
REQUIRE(f.items[3].title ==
"using multiple media tags nested in group/content");
REQUIRE(f.items[3].description == "nested media html content");
REQUIRE(f.items[3].description_mime_type == "text/html");
REQUIRE(f.items[3].link == "http://example.com/player.html");
SECTION("media:{title,description,player} does not overwrite regular title, description, and link if they exist") {
REQUIRE(f.items[4].title == "regular title");
REQUIRE(f.items[4].description == "regular content");
REQUIRE(f.items[4].description_mime_type == "text/html");
REQUIRE(f.items[4].link == "http://example.com/regular-link");
}
}
TEST_CASE("Extracts data from media:... tags in RSS 2.0 feeds",
"[rsspp::Parser]")
{
rsspp::Parser p;
rsspp::Feed f;
REQUIRE_NOTHROW(f = p.parse_file("data/rss20_2.xml"));
REQUIRE(f.title == "my weblog");
REQUIRE(f.link == "http://example.com/blog/");
REQUIRE(f.description == "my description");
REQUIRE(f.items.size() == 2u);
REQUIRE(f.items[0].title == "using multiple media tags");
REQUIRE(f.items[0].description == "media html content");
REQUIRE(f.items[0].description_mime_type == "text/html");
REQUIRE(f.items[0].link == "http://example.com/player.html");
REQUIRE(f.items[1].title ==
"using multiple media tags nested in group/content");
REQUIRE(f.items[1].description == "nested media html content");
REQUIRE(f.items[1].description_mime_type == "text/html");
REQUIRE(f.items[1].link == "http://example.com/player.html");
}
|
