Skip to content

Commit 3b593d1

Browse files
lwindolflwindolf
committed
Add <enclosure> support.
1 parent 72cf275 commit 3b593d1

File tree

7 files changed

+178
-246
lines changed

7 files changed

+178
-246
lines changed

‎tests/rdf.test.js

-63
Original file line numberDiff line numberDiff line change
@@ -54,67 +54,4 @@ test('rss 1.0 parse', () => {
5454
expect(feed.items[0].description).toBe(`Processing document inclusions with general XML tools can be ...`);
5555
expect(feed.items[0].source).toBe('http://xml.com/pub/2000/08/09/xslt/xslt.html');
5656
expect(feed.items[0].time).toBe(1694950440);
57-
});
58-
59-
test('rss Dublin Core', () => {
60-
// XML example from spec https://web.resource.org/rss/1.0/modules/dc/
61-
let feed = RDFParser.parse(`<?xml version="1.0" encoding="utf-8"?>
62-
63-
<rdf:RDF
64-
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
65-
xmlns:dc="http://purl.org/dc/elements/1.1/"
66-
xmlns="http://purl.org/rss/1.0/"
67-
>
68-
69-
<channel rdf:about="http://meerkat.oreillynet.com/?_fl=rss1.0">
70-
<title>Meerkat</title>
71-
<link>http://meerkat.oreillynet.com</link>
72-
<description>Meerkat: An Open Wire Service</description>
73-
<dc:publisher>The O'Reilly Network</dc:publisher>
74-
<dc:creator>Rael Dornfest (mailto:[email protected])</dc:creator>
75-
<dc:rights>Copyright © 2000 O'Reilly &amp; Associates, Inc.</dc:rights>
76-
<dc:date>2000-01-01T12:00+00:00</dc:date>
77-
78-
<image rdf:resource="http://meerkat.oreillynet.com/icons/meerkat-powered.jpg" />
79-
80-
<items>
81-
<rdf:Seq>
82-
<rdf:li resource="http://c.moreover.com/click/here.pl?r123" />
83-
</rdf:Seq>
84-
</items>
85-
86-
<textinput rdf:resource="http://meerkat.oreillynet.com" />
87-
88-
</channel>
89-
90-
<image rdf:about="http://meerkat.oreillynet.com/icons/meerkat-powered.jpg">
91-
<title>Meerkat Powered!</title>
92-
<url>http://meerkat.oreillynet.com/icons/meerkat-powered.jpg</url>
93-
<link>http://meerkat.oreillynet.com</link>
94-
</image>
95-
96-
<item rdf:about="http://c.moreover.com/click/here.pl?r123">
97-
<title>XML: A Disruptive Technology</title>
98-
<link>http://c.moreover.com/click/here.pl?r123</link>
99-
<dc:description>XML is placing increasingly heavy...</dc:description>
100-
<dc:publisher>The O'Reilly Network</dc:publisher>
101-
<dc:creator>Simon St.Laurent (mailto:[email protected])</dc:creator>
102-
<dc:rights>Copyright © 2000 O'Reilly &amp; Associates, Inc.</dc:rights>
103-
<dc:subject>XML</dc:subject>
104-
</item>
105-
106-
<textinput rdf:about="http://meerkat.oreillynet.com">
107-
<title>Search Meerkat</title>
108-
<description>Search Meerkat's RSS Database...</description>
109-
<name>s</name>
110-
<link>http://meerkat.oreillynet.com/</link>
111-
</textinput>
112-
113-
</rdf:RDF>`);
114-
115-
expect(feed.error).toBe(undefined);
116-
expect(feed.items.length).toBe(1);
117-
expect(feed.items[0].description).toBe(`XML is placing increasingly heavy...`);
118-
// with no date given date should be similar to current date
119-
expect(Math.floor(Date.now() / 10000) - Math.floor(feed.items[0].time / 10000)).toBe(0)
12057
});

‎www/assets/js/feed.js

+68-58
Original file line numberDiff line numberDiff line change
@@ -5,74 +5,84 @@
55
import { FeedUpdater } from './feedupdater.js';
66

77
export class Feed {
8-
// state
9-
id;
10-
error;
11-
orig_source;
12-
last_updated;
13-
etag;
8+
// state
9+
id;
10+
error;
11+
orig_source;
12+
last_updated;
13+
etag;
1414

15-
// feed content
16-
title;
17-
source;
18-
description;
19-
icon;
20-
metadata = {};
21-
items = [];
15+
// feed content
16+
title;
17+
source;
18+
description;
19+
icon;
20+
metadata = {};
21+
items = [];
2222

23-
// error code constants
24-
static ERROR_NONE = 0;
25-
static ERROR_AUTH = 1 << 0;
26-
static ERROR_NET = 1 << 1;
27-
static ERROR_DISCOVER = 1 << 2;
28-
static ERROR_XML = 1 << 3;
23+
// error code constants
24+
static ERROR_NONE = 0;
25+
static ERROR_AUTH = 1 << 0;
26+
static ERROR_NET = 1 << 1;
27+
static ERROR_DISCOVER = 1 << 2;
28+
static ERROR_XML = 1 << 3;
2929

30-
constructor(defaults) {
31-
Object.keys(defaults).forEach((k) => { this[k] = defaults[k] });
30+
constructor(defaults) {
31+
Object.keys(defaults).forEach((k) => { this[k] = defaults[k] });
32+
}
33+
34+
async update() {
35+
const f = await FeedUpdater.fetch(this.source);
36+
if (Feed.ERROR_NONE == f.error) {
37+
this.title = f.title;
38+
this.source = f.source;
39+
this.homepage = f.homepage;
40+
this.description = f.description;
41+
this.items = f.items;
42+
this.metadata = f.metadata;
43+
this.items.forEach((i) => {
44+
i.node = this;
45+
})
46+
47+
// feed provided favicon should always win
48+
if (f.icon)
49+
this.icon = f.icon;
3250
}
3351

34-
async update() {
35-
const f = await FeedUpdater.fetch(this.source);
36-
if(Feed.ERROR_NONE == f.error) {
37-
this.title = f.title;
38-
this.source = f.source;
39-
this.homepage = f.homepage;
40-
this.description = f.description;
41-
this.items = f.items;
42-
this.metadata = f.metadata;
43-
this.items.forEach((i) => {
44-
i.node = this;
45-
})
52+
this.last_updated = f.last_updated;
53+
this.error = f.error;
54+
document.dispatchEvent(new CustomEvent('nodeUpdated', { detail: this }));
55+
}
4656

47-
// feed provided favicon should always win
48-
if(f.icon)
49-
this.icon = f.icon;
50-
}
57+
// Return the next unread item after the given id
58+
getNextUnread(id) {
59+
let item, idx = 0;
5160

52-
this.last_updated = f.last_updated;
53-
this.error = f.error;
54-
document.dispatchEvent(new CustomEvent('nodeUpdated', { detail: this }));
61+
// search forward in feed items starting from id
62+
if (id) {
63+
this.items.find((i) => { idx++; return (i.id === id); }); // find current item index
64+
item = this.items.slice(idx).find((i) => !i.read); // find next unread item
65+
if (item)
66+
return item;
5567
}
5668

57-
// Return the next unread item after the given id
58-
getNextUnread(id) {
59-
let item, idx = 0;
69+
// if nothing found search from start of feed
70+
return this.items.find((i) => !i.read);
71+
}
6072

61-
// search forward in feed items starting from id
62-
if(id) {
63-
this.items.find((i) => { idx++; return (i.id === id); }); // find current item index
64-
item = this.items.slice(idx).find((i) => !i.read); // find next unread item
65-
if(item)
66-
return item;
67-
}
73+
getItemById(id) {
74+
let itemsById = {};
75+
this.items.forEach((i) => { itemsById[i.id] = i; });
76+
return itemsById[id];
77+
}
6878

69-
// if nothing found search from start of feed
70-
return this.items.find((i) => !i.read);
71-
}
79+
addItem(item) {
80+
// Finally some guessing
81+
if (!item.time)
82+
item.time = Date.now();
7283

73-
getItemById(id) {
74-
let itemsById = {};
75-
this.items.forEach((i) => { itemsById[i.id] = i; });
76-
return itemsById[id];
77-
}
84+
// FIXME: set an id if sourceId is missing
85+
86+
this.items.push(item);
87+
}
7888
}

‎www/assets/js/item.js

+18-1
Original file line numberDiff line numberDiff line change
@@ -33,6 +33,23 @@ export class Item {
3333
}
3434

3535
addMedia(url, mime, length) {
36-
this.media.push({ url, mime, length });
36+
let l = parseInt(length, 10);
37+
38+
if (Number.isNaN(l))
39+
l = undefined;
40+
41+
if(!url || !mime)
42+
return;
43+
44+
/* gravatars are often supplied as media:content with medium='image'
45+
so we do not treat such occurences as enclosures */
46+
if (-1 !== url.indexOf('www.gravatar.com'))
47+
return;
48+
49+
/* Never add enclosures for images already contained in the description */
50+
if (-1 !== this.description.indexOf(url))
51+
return;
52+
53+
this.media.push({ url, mime, l });
3754
}
3855
}

‎www/assets/js/parsers/atom.js

+4-3
Original file line numberDiff line numberDiff line change
@@ -5,6 +5,7 @@
55
// Specification https://www.ietf.org/rfc/rfc4287.txt
66

77
import { DateParser } from './date.js';
8+
import { NamespaceParser } from './namespace.js'
89
import { XPath } from './xpath.js';
910
import { Feed } from '../feed.js';
1011
import { Item } from '../item.js';
@@ -44,11 +45,11 @@ class AtomParser {
4445
time : DateParser.parse(XPath.lookup(node, 'ns:updated'))
4546
});
4647

47-
if(!item.time)
48-
item.time = DateParser.parse(XPath.lookup(node, 'dc:date'));
48+
NamespaceParser.parseItem(node, ['dc', 'content', 'media'], feed, item);
4949

5050
XPath.foreach(node, 'ns:link', AtomParser.parseEntryLink, item);
51-
feed.items.push(item);
51+
console.log(feed)
52+
feed.addItem(item);
5253
}
5354

5455
static parse(str) {

‎www/assets/js/parsers/namespace.js

+5-23
Original file line numberDiff line numberDiff line change
@@ -63,29 +63,11 @@ export class NamespaceParser {
6363
(example quoted from specification)
6464
*/
6565
XPath.foreach(node, '//media:content', (n) => {
66-
try {
67-
const url = n.lookup('@url');
68-
const mime = n.lookup('@type') || n.lookup('@medium');
69-
let add = true;
70-
let length = parseInt(n.lookup('@duration'), 10);
71-
72-
if (Number.isNaN(length))
73-
length = undefined;
74-
75-
/* gravatars are often supplied as media:content with medium='image'
76-
so we do not treat such occurences as enclosures */
77-
if (-1 !== url.indexOf('www.gravatar.com'))
78-
add = false;
79-
80-
/* Never add enclosures for images already contained in the description */
81-
if (-1 !== item.description.indexOf(url))
82-
add = false;
83-
84-
if (add)
85-
item.addMedia(url, mime, length);
86-
} catch (e) {
87-
console.log(`Failed to parse <media:content> (${e})!`);
88-
}
66+
item.addMedia(
67+
n.lookup('@url'),
68+
n.lookup('@type') || n.lookup('@medium'),
69+
n.lookup('@duration')
70+
);
8971
});
9072
}
9173
}

‎www/assets/js/parsers/rdf.js

+36-50
Original file line numberDiff line numberDiff line change
@@ -2,62 +2,48 @@
22

33
// RSS 1.0 parser
44

5-
import { DateParser } from './date.js';
65
import { NamespaceParser } from './namespace.js'
76
import { XPath } from './xpath.js';
87
import { Feed } from '../feed.js';
98
import { Item } from '../item.js';
109

1110
class RDFParser {
12-
static id = 'rdf';
13-
static autoDiscover = [
14-
'/rdf:RDF/ns:channel'
15-
];
16-
17-
static parseItem(node, feed) {
18-
let item = new Item({
19-
title : XPath.lookup(node, 'ns:title'),
20-
description : XPath.lookup(node, 'ns:description'),
21-
source : XPath.lookup(node, 'ns:link'),
22-
});
23-
24-
// Dublin Core support
25-
if(!item.description)
26-
item.description = XPath.lookup(node, 'dc:description');
27-
if(!item.time)
28-
item.time = DateParser.parse(XPath.lookup(node, 'dc:date'));
29-
30-
// Finally some guessing
31-
if(!item.time)
32-
item.time = Date.now();
33-
// FIXME: set an id
34-
35-
NamespaceParser.parseItem(node, ["dc", "content", "media"], feed, item);
36-
37-
feed.items.push(item);
38-
}
39-
40-
static parse(str) {
41-
const parser = new DOMParser();
42-
const doc = parser.parseFromString(str, 'application/xml');
43-
const root = doc.firstChild;
44-
let feed = new Feed({
45-
error : XPath.lookup(root, '/parsererror'),
46-
});
47-
48-
// RSS 1.0
49-
if(doc.firstChild.nodeName === 'rdf:RDF') {
50-
feed = {...feed, ...{
51-
title : XPath.lookup(root, '/rdf:RDF/ns:channel/ns:title'),
52-
description : XPath.lookup(root, '/rdf:RDF/ns:channel/ns:description'),
53-
homepage : XPath.lookup(root, '/rdf:RDF/ns:channel/ns:link')
54-
}};
55-
56-
XPath.foreach(root, '/rdf:RDF/ns:item', this.parseItem, feed);
57-
}
58-
59-
return feed;
60-
}
11+
static id = 'rdf';
12+
static autoDiscover = [
13+
'/rdf:RDF/ns:channel'
14+
];
15+
16+
static parseItem(node, feed) {
17+
let item = new Item({
18+
title: XPath.lookup(node, 'ns:title'),
19+
description: XPath.lookup(node, 'ns:description'),
20+
source: XPath.lookup(node, 'ns:link'),
21+
});
22+
23+
NamespaceParser.parseItem(node, ['dc', 'content', 'media'], feed, item);
24+
25+
feed.addItem(item);
26+
}
27+
28+
static parse(str) {
29+
const parser = new DOMParser();
30+
const doc = parser.parseFromString(str, 'application/xml');
31+
const root = doc.firstChild;
32+
let feed = new Feed({
33+
error: XPath.lookup(root, '/parsererror'),
34+
});
35+
36+
// RSS 1.0
37+
if (doc.firstChild.nodeName === 'rdf:RDF') {
38+
feed.title = XPath.lookup(root, '/rdf:RDF/ns:channel/ns:title');
39+
feed.description = XPath.lookup(root, '/rdf:RDF/ns:channel/ns:description');
40+
feed.homepage = XPath.lookup(root, '/rdf:RDF/ns:channel/ns:link');
41+
42+
XPath.foreach(root, '/rdf:RDF/ns:item', this.parseItem, feed);
43+
}
44+
45+
return feed;
46+
}
6147
}
6248

6349
export { RDFParser };

0 commit comments

Comments
 (0)