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
|
#include "rssparser.h"
#include "3rd-party/catch.hpp"
#include "cache.h"
#include "rss/feed.h"
#include "rss/item.h"
#include "rssfeed.h"
#include "rssignores.h"
using namespace newsboat;
TEST_CASE("parse() ignores uninitialized upstream feed", "[RssParser]")
{
ConfigContainer cfg;
Cache rsscache(":memory:", &cfg);
RssIgnores ignores;
RssParser parser("http://example.com", rsscache, cfg, &ignores);
rsspp::Feed upstream_feed;
const auto feed = parser.parse(upstream_feed);
REQUIRE(feed == nullptr);
}
TEST_CASE("parse() with no item GUID falls back to link+pubdate, link, and title",
"[RssParser]")
{
ConfigContainer cfg;
Cache rsscache(":memory:", &cfg);
RssIgnores ignores;
RssParser parser("http://example.com", rsscache, cfg, &ignores);
rsspp::Feed upstream_feed;
upstream_feed.rss_version = rsspp::Feed::ATOM_1_0;
upstream_feed.items.push_back({});
rsspp::Item& upstream_item = upstream_feed.items[0];
upstream_item.guid = "a real GUID";
upstream_item.title = "title of article";
upstream_item.link = "https://example.com/blog/post";
upstream_item.pubDate = "2023-07-31";
SECTION("uses GUID if it is available") {
const auto feed = parser.parse(upstream_feed);
REQUIRE(feed != nullptr);
REQUIRE(feed->items().size() == 1);
REQUIRE(feed->items().front()->guid() == "a real GUID");
}
SECTION("uses link+pubdate if GUID is not available") {
upstream_item.guid.clear();
const auto feed = parser.parse(upstream_feed);
REQUIRE(feed != nullptr);
REQUIRE(feed->items().size() == 1);
REQUIRE(feed->items().front()->guid() == "https://example.com/blog/post2023-07-31");
}
SECTION("uses link if GUID and pubdate are not available") {
upstream_item.guid.clear();
upstream_item.pubDate.clear();
const auto feed = parser.parse(upstream_feed);
REQUIRE(feed != nullptr);
REQUIRE(feed->items().size() == 1);
REQUIRE(feed->items().front()->guid() == "https://example.com/blog/post");
}
SECTION("uses title if other options are not available") {
upstream_item.guid.clear();
upstream_item.pubDate.clear();
upstream_item.link.clear();
const auto feed = parser.parse(upstream_feed);
REQUIRE(feed != nullptr);
REQUIRE(feed->items().size() == 1);
REQUIRE(feed->items().front()->guid() == "title of article");
}
}
TEST_CASE("parse() renders html titles into plaintext if type indicates html",
"[RssParser]")
{
ConfigContainer cfg;
Cache rsscache(":memory:", &cfg);
RssIgnores ignores;
RssParser parser("http://example.com", rsscache, cfg, &ignores);
rsspp::Feed upstream_feed;
upstream_feed.rss_version = rsspp::Feed::ATOM_1_0;
upstream_feed.items.push_back({});
rsspp::Item& upstream_item = upstream_feed.items[0];
upstream_feed.title = "<b>title</b> of feed";
upstream_item.title = "<b>title</b> of article";
SECTION("uses feed title varbatim if no html type is indicated") {
const auto feed = parser.parse(upstream_feed);
REQUIRE(feed != nullptr);
REQUIRE(feed->title() == "<b>title</b> of feed");
}
SECTION("renders out feed title if html type is indicated") {
upstream_feed.title_type = "html";
const auto feed = parser.parse(upstream_feed);
REQUIRE(feed != nullptr);
REQUIRE(feed->title() == "title of feed");
}
SECTION("uses item title varbatim if no html type is indicated") {
const auto feed = parser.parse(upstream_feed);
REQUIRE(feed != nullptr);
REQUIRE(feed->items().size() == 1);
REQUIRE(feed->items().front()->title() == "<b>title</b> of article");
}
SECTION("renders out item title if html type is indicated") {
upstream_item.title_type = "html";
const auto feed = parser.parse(upstream_feed);
REQUIRE(feed != nullptr);
REQUIRE(feed->items().size() == 1);
REQUIRE(feed->items().front()->title() == "title of article");
}
}
TEST_CASE("parse() generates a title when title element is missing",
"[RssParser]")
{
ConfigContainer cfg;
Cache rsscache(":memory:", &cfg);
RssIgnores ignores;
RssParser parser("http://example.com", rsscache, cfg, &ignores);
rsspp::Feed upstream_feed;
upstream_feed.rss_version = rsspp::Feed::ATOM_1_0;
upstream_feed.items.push_back({});
rsspp::Item& upstream_item = upstream_feed.items[0];
upstream_item.description = "<b>Just saying hello</b>";
SECTION("creates a title from the URL") {
upstream_item.link = "http://example.com/2023/08/29/hello-world.html";
const auto feed = parser.parse(upstream_feed);
auto item = feed->items()[0];
REQUIRE(item->title() == "Hello world");
}
SECTION("creates a title from the content if the URL is numeric") {
upstream_item.link = "http://example.com/1234567";
SECTION("title from description") {
const auto feed = parser.parse(upstream_feed);
auto item = feed->items()[0];
REQUIRE(item->title() == "Just saying hello");
}
SECTION("title from content_encoded") {
upstream_item.description.clear();
upstream_item.content_encoded = "<b>article text</b>";
const auto feed = parser.parse(upstream_feed);
auto item = feed->items()[0];
REQUIRE(item->title() == "article text");
}
}
}
TEST_CASE("parse() extracts best enclosure", "[RssParser]")
{
ConfigContainer cfg;
Cache rsscache(":memory:", &cfg);
RssIgnores ignores;
RssParser parser("http://example.com", rsscache, cfg, &ignores);
rsspp::Feed upstream_feed;
upstream_feed.rss_version = rsspp::Feed::ATOM_1_0;
upstream_feed.items.push_back({});
rsspp::Item& upstream_item = upstream_feed.items[0];
const auto make_enclosure = [](
const std::string& url,
const std::string& type,
const std::string& description,
const std::string& mime
) -> rsspp::Enclosure {
rsspp::Enclosure result;
result.url = url;
result.type = type;
result.description = description;
result.description_mime_type = mime;
return result;
};
const auto image_enclosure1 = make_enclosure(
"http://example.com/enclosure1",
"image/png",
"description1",
"text/plain"
);
const auto image_enclosure2 = make_enclosure(
"http://example.com/enclosure2",
"image/jpg",
"description2",
"text/plain"
);
const auto audio_enclosure = make_enclosure(
"http://example.com/enclosure3",
"audio/ogg",
"description3",
"text/plain"
);
SECTION("podcast preferred over non-podcast enclosure") {
const auto run_validation = [&]() {
const auto feed = parser.parse(upstream_feed);
REQUIRE(feed != nullptr);
REQUIRE(feed->items().size() == 1);
REQUIRE(feed->items()[0]->enclosure_url() == "http://example.com/enclosure3");
REQUIRE(feed->items()[0]->enclosure_type() == "audio/ogg");
REQUIRE(feed->items()[0]->enclosure_description() == "description3");
REQUIRE(feed->items()[0]->enclosure_description_mime_type() == "text/plain");
};
SECTION("podcast first") {
upstream_item.enclosures.push_back(audio_enclosure);
upstream_item.enclosures.push_back(image_enclosure1);
run_validation();
}
SECTION("podcast last") {
upstream_item.enclosures.push_back(image_enclosure1);
upstream_item.enclosures.push_back(audio_enclosure);
run_validation();
}
}
SECTION("last enclosure picked if both are non-podcast enclosures") {
upstream_item.enclosures.push_back(image_enclosure1);
upstream_item.enclosures.push_back(image_enclosure2);
const auto feed = parser.parse(upstream_feed);
REQUIRE(feed != nullptr);
REQUIRE(feed->items().size() == 1);
REQUIRE(feed->items()[0]->enclosure_url() == "http://example.com/enclosure2");
REQUIRE(feed->items()[0]->enclosure_type() == "image/jpg");
REQUIRE(feed->items()[0]->enclosure_description() == "description2");
REQUIRE(feed->items()[0]->enclosure_description_mime_type() == "text/plain");
}
}
|
