feed-rs 2.3.1

A feed parser that handles Atom, RSS 2.0, RSS 1.0, RSS 0.x and JSON Feed
Documentation 
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

use mediatype::{names, MediaType};

use crate::model::{Entry, Feed, FeedType, Image, Link, Person, Text};
use crate::parser;
use crate::util::test;

// Example from the web
#[test]
fn test_example_1() {
    // Parse the feed
    let test_data = test::fixture_as_string("rss1/rss_1.0_example_1.xml");
    let actual = parser::parse(test_data.as_bytes()).unwrap();

    // Expected feed
    let entry0 = actual.entries.first().unwrap();
    let entry1 = actual.entries.get(1).unwrap();
    let expected = Feed::new(FeedType::RSS1)
        .id(actual.id.as_ref()) // not present in the test data
        .title(Text::new("Feed title".into()))
        .link(Link::new("http://www.example.com/main.html", None))
        .description(Text::new("Site description".into()))
        .updated(actual.updated) // not present in the test data
        .published("2017-06-13T09:00:00Z")
        .language("ja")
        .entry(
            Entry::default()
                .id("7d61c42a2d8ecf2289e789e1fb2035d1") // hash of the link
                .updated(entry0.updated) // not present in the test data
                .title(Text::new("記事1のタイトル".into()))
                .link(Link::new("記事1のURL", None))
                .summary(Text::new("記事1の内容".into()))
                .published("2017-06-13T09:00:00Z")
                .author(Person::new("記事1の作者名")),
        )
        .entry(
            Entry::default()
                .id("e342c1b080da9ffbfd10c0a6ba49395f") // hash of the link
                .updated(entry1.updated) // not present in the test data
                .title(Text::new("記事2のタイトル".into()))
                .link(Link::new("記事2のURL", None))
                .summary(Text::new("記事2の内容".into()))
                .author(Person::new("記事2の作者名")),
        );

    // Check
    assert_eq!(actual, expected);
}

// Example with content:encoded from https://planet.freedesktop.org/rss10.xml
#[test]
fn test_example_2() {
    // Parse the feed
    let test_data = test::fixture_as_string("rss1/rss_1.0_example_2.xml");
    let feed = parser::parse(test_data.as_bytes()).unwrap();

    // content:encoded should be mapped to the content field
    assert!(feed.entries[0]
        .content
        .as_ref()
        .unwrap()
        .body
        .as_ref()
        .unwrap()
        .starts_with("This morning I saw two things that were Microsoft "));
    // content media type should be text/html.
    assert_eq!(feed.entries[0].content.as_ref().unwrap().content_type, MediaType::new(names::TEXT, names::HTML));
}

// Example 1 from the spec at https://validator.w3.org/feed/docs/rss1.html
#[test]
fn test_spec_1() {
    // Parse the feed
    let test_data = test::fixture_as_string("rss1/rss_1.0_spec_1.xml");
    let actual = parser::parse(test_data.as_bytes()).unwrap();

    // Expected feed
    let entry0 = actual.entries.first().unwrap();
    let entry1 = actual.entries.get(1).unwrap();
    let expected = Feed::new(FeedType::RSS1)
        .id(actual.id.as_ref())     // not present in the test data
        .title(Text::new("XML.com".into()))
        .link(Link::new("http://xml.com/pub", None))
        .description(Text::new("XML.com features a rich mix of information and services\n            for the XML community.".into()))
        .logo(Image::new("http://xml.com/universal/images/xml_tiny.gif".into())
            .link("http://www.xml.com")
            .title("XML.com"))
        .updated(actual.updated)    // not present in the test data
        .entry(Entry::default()
            .id("958983927af7075ad55f6d2c9b0c24b2")     // hash of the link
            .updated(entry0.updated)            // not present in the test data
            .title(Text::new("Processing Inclusions with XSLT".into()))
            .link(Link::new("http://xml.com/pub/2000/08/09/xslt/xslt.html", None))
            .summary(Text::new("Processing document inclusions with general XML tools can be\n            problematic. This article proposes a way of preserving inclusion\n            information through SAX-based processing.".into())))
        .entry(Entry::default()
            .id("54f62e9fe8901546d7e25c0827e1b8e8")     // hash of the link
            .updated(entry1.updated)            // not present in the test data
            .title(Text::new("Putting RDF to Work".into()))
            .link(Link::new("http://xml.com/pub/2000/08/09/rdfdb/index.html", None))
            .summary(Text::new("Tool and API support for the Resource Description Framework\n            is slowly coming of age. Edd Dumbill takes a look at RDFDB,\n            one of the most exciting new RDF toolkits.".into())));

    // Check
    assert_eq!(actual, expected);
}

// Example 2 from the spec at https://validator.w3.org/feed/docs/rss1.html
#[test]
fn test_spec_2() {
    // Parse the feed
    let test_data = test::fixture_as_string("rss1/rss_1.0_spec_2.xml");
    let actual = parser::parse(test_data.as_bytes()).unwrap();

    // Expected feed
    let entry0 = actual.entries.first().unwrap();
    let expected = Feed::new(FeedType::RSS1)
        .id(actual.id.as_ref()) // not present in the test data
        .title(Text::new("Meerkat".into()))
        .link(Link::new("http://meerkat.oreillynet.com", None))
        .description(Text::new("Meerkat: An Open Wire Service".into()))
        .logo(
            Image::new("http://meerkat.oreillynet.com/icons/meerkat-powered.jpg".into())
                .link("http://meerkat.oreillynet.com")
                .title("Meerkat Powered!"),
        )
        .updated(actual.updated) // not present in the test data
        .author(Person::new("Rael Dornfest (mailto:rael@oreilly.com)"))
        .rights(Text::new("Copyright © 2000 O'Reilly & Associates, Inc.".into()))
        .entry(
            Entry::default()
                .id("acf7c86547d5d594af6d8f3327e84b06") // hash of the link
                .updated(entry0.updated) // not present in the test data
                .title(Text::new("XML: A Disruptive Technology".into()))
                .link(Link::new("http://c.moreover.com/click/here.pl?r123", None))
                .summary(Text::new(
                    "XML is placing increasingly heavy loads on the existing technical\n            infrastructure of the Internet.".into(),
                ))
                .author(Person::new("Simon St.Laurent (mailto:simonstl@simonstl.com)"))
                .rights(Text::new("Copyright © 2000 O'Reilly & Associates, Inc.".into())),
        );

    // Check
    assert_eq!(actual, expected);
}

// Verifies that publish date is set
#[test]
fn test_debian() {
    let test_data = test::fixture_as_string("rss1/rss_1.0_debian.xml");
    let actual = parser::parse(test_data.as_bytes()).unwrap();
    let entry = actual.entries.first().expect("feed has 1 entry");

    assert!(entry.published.is_some());
}

// Verifies ISO8859 decoding works correctly
#[test]
fn test_iso8859() {
    let test_data = test::fixture_as_raw("rss1/rss_1.0_iso8859.xml");
    let actual = parser::parse(test_data.as_slice()).unwrap();
    let entry = actual.entries.first().expect("feed has 1 entry");

    let expected = "Ab April soll es wieder Förderung für den Ausbau von Glasfaser geben.";
    let summary = &entry.summary.as_ref().unwrap().content;
    assert!(summary.starts_with(expected));
    let content = entry.content.as_ref().unwrap().body.as_ref().unwrap();
    assert!(content.contains(expected));
}

// Verifies bioRxiv titles are extracted correctly
#[test]
fn test_bio_rxiv() {
    let test_data = test::fixture_as_raw("rss1/rss_1.0_biorxiv.xml");
    let actual = parser::parse(test_data.as_slice()).unwrap();
    for entry in actual.entries {
        assert!(!entry.title.unwrap().content.is_empty())
    }
}