MensBeam
/
lax
3
0
Fork 0
Code Issues 3 Pull Requests Releases Activity
Browse Source

Feed links

master
J. King 4 years ago
parent
7fd3221599
commit
0ebbd6b7cf
6 changed files with 208 additions and 10 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 12
      lib/Parser/XML/Construct.php
  2. 10
      lib/Parser/XML/Feed.php
  3. 98
      tests/cases/XML/feed-atom.yaml
  4. 14
      tests/cases/XML/feed-rss0.yaml
  5. 16
      tests/cases/XML/feed-rss1.yaml
  6. 68
      tests/cases/XML/feed-rss2.yaml

12
lib/Parser/XML/Construct.php
View File

@ -213,4 +213,16 @@ abstract class Construct {
protected function getLangRss2(): ?string {
return $this->fetchString("language", ".+");
}
protected function getLinkAtom(): ?Url {
return $this->fetchAtomRelation("alternate", ["text/html", "application/xhtml+xml"]);
}
protected function getLinkRss2(): ?Url {
return $this->fetchUrl("link") ?? $this->fetchUrl("guid[not(@isPermalink) or @isPermalink='true']");
}
protected function getLinkRss1(): ?Url {
return $this->fetchUrl("rss1:link|rss0:link");
}
}

10
lib/Parser/XML/Feed.php
View File

@ -85,7 +85,7 @@ class Feed extends Construct implements \MensBeam\Lax\Parser\Feed {
$feed->id = $this->getId();
$feed->lang = $this->getLang();
$feed->url = $this->getUrl();
//$feed->link = $this->getLink();
$feed->link = $this->getLink();
//$feed->title = $this->getTitle();
//$feed->summary = $this->getSummary();
//$feed->dateModified = $this->getDateModified();
@ -123,14 +123,14 @@ class Feed extends Construct implements \MensBeam\Lax\Parser\Feed {
return $this->getUrlAtom() ?? $this->getUrlRss1() ?? $this->getUrlPod();
}
public function getTitle(): ?Text {
return $this->getTitleAtom() ?? $this->getTitleRss1() ?? $this->getTitleRss2() ?? $this->getTitleDC() ?? $this->getTitlePod();
}
public function getLink(): ?Url {
return $this->getLinkAtom() ?? $this->getLinkRss1() ?? $this->getLinkRss2();
}
public function getTitle(): ?Text {
return $this->getTitleAtom() ?? $this->getTitleRss1() ?? $this->getTitleRss2() ?? $this->getTitleDC() ?? $this->getTitlePod();
}
public function getSummary(): ?Text {
// unlike most other data, Atom is not preferred, because Atom doesn't really have feed summaries
return $this->getSummaryDC() ?? $this->getSummaryRss1() ?? $this->getSummaryRss2() ?? $this->getSummaryPod() ?? $this->getSummaryAtom();

98
tests/cases/XML/feed-atom.yaml
View File

@ -65,3 +65,101 @@ Canonical URL:
format: atom
version: '1.0'
url: 'http://example.com/'
Feed link 1:
input: >
<feed xmlns="http://www.w3.org/2005/Atom">
<link rel="alternate" href="http://example.com/"/>
</feed>
output:
format: atom
version: '1.0'
link: 'http://example.com/'
Feed link 2: # default relation is "alternate"
input: >
<feed xmlns="http://www.w3.org/2005/Atom">
<link rel="" href="http://example.com/"/>
</feed>
output:
format: atom
version: '1.0'
link: 'http://example.com/'
Feed link 3: # default relation is "alternate"
input: >
<feed xmlns="http://www.w3.org/2005/Atom">
<link href="http://example.com/"/>
</feed>
output:
format: atom
version: '1.0'
link: 'http://example.com/'
Feed link 4: # other relations are ignored
input: >
<feed xmlns="http://www.w3.org/2005/Atom">
<link rel="bogus" href="http://example.net/"/>
<link href="http://example.com/"/>
</feed>
output:
format: atom
version: '1.0'
link: 'http://example.com/'
Feed link 5: # XHTML is preferred
input: >
<feed xmlns="http://www.w3.org/2005/Atom">
<link href="http://example.net/"/>
<link href="http://example.com/" type="application/xhtml+xml; charset=utf-8"/>
</feed>
output:
format: atom
version: '1.0'
link: 'http://example.com/'
Feed link 6: # HTML is even more preferred
input: >
<feed xmlns="http://www.w3.org/2005/Atom">
<link href="http://example.net/"/>
<link href="http://example.org/" type="application/xhtml+xml; charset=utf-8"/>
<link href="http://example.com/" type="TEXT/HTML; charset=utf-8"/>
</feed>
output:
format: atom
version: '1.0'
link: 'http://example.com/'
Feed link 7: # No type is better than an unacceptable type
input: >
<feed xmlns="http://www.w3.org/2005/Atom">
<link href="http://example.net/" type="image/png"/>
<link href="http://example.org/" type="application/xml"/>
<link href="http://example.com/"/>
</feed>
output:
format: atom
version: '1.0'
link: 'http://example.com/'
Feed link 8: # Bad URLs are ignored
input: >
<feed xmlns="http://www.w3.org/2005/Atom">
<link href="http://example.com/" type="application/xhtml+xml; charset=utf-8"/>
<link href="http://[example.org]/" type="text/html; charset=utf-8"/>
</feed>
output:
format: atom
version: '1.0'
link: 'http://example.com/'
Feed link 9: # The first matching relation wins
input: >
<feed xmlns="http://www.w3.org/2005/Atom">
<link href="http://example.com/" type="text/html"/>
<link href="http://example.org/" type="text/html"/>
</feed>
output:
format: atom
version: '1.0'
link: 'http://example.com/'

14
tests/cases/XML/feed-rss0.yaml
View File

@ -54,3 +54,17 @@ Canonical URL: # this is not actually a feature of RSS 0.90, but is consistent w
format: rdf
version: '0.90'
url: 'http://example.com/'
Feed link:
input: >
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns="http://channel.netscape.com/rdf/simple/0.9/">
<channel>
<link/>
<link>http://[example.net]/</link>
<link>http://example.com/</link>
</channel>
</rdf:RDF>
output:
format: rdf
version: '0.90'
link: 'http://example.com/'

16
tests/cases/XML/feed-rss1.yaml
View File

@ -182,10 +182,24 @@ DC language:
Canonical URL:
input: >
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns="http://purl.org/rss/1.0/" xmlns:dc="http://purl.org/dc/elements/1.1/">
<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://example.com/"/>
</rdf:RDF>
output:
format: rdf
version: '1.0'
url: 'http://example.com/'
Feed link:
input: >
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns="http://purl.org/rss/1.0/">
<channel>
<link/>
<link>http://[example.net]/</link>
<link>http://example.com/</link>
</channel>
</rdf:RDF>
output:
format: rdf
version: '1.0'
link: 'http://example.com/'

68
tests/cases/XML/feed-rss2.yaml
View File

@ -9,7 +9,7 @@ Channel GUID:
input: >
<rss>
<channel>
<guid>http://example.com/</guid>
<guid isPermalink="false">http://example.com/</guid>
</channel>
</rss>
output:
@ -20,7 +20,7 @@ Channel GUID with whitespace:
input: >
<rss>
<channel>
<guid>
<guid isPermalink="false">
http://example.com/
</guid>
</channel>
@ -33,7 +33,7 @@ Root GUID: # Any elements on the RSS2 root element should be ignored
input: >
<rss>
<channel/>
<guid>http://example.com/</guid>
<guid isPermalink="false">http://example.com/</guid>
</rss>
output:
format: rss
@ -43,7 +43,7 @@ Bogus GUID before good:
<rss>
<channel>
<guid/>
<guid>http://example.com/</guid>
<guid isPermalink="false">http://example.com/</guid>
</channel>
</rss>
output:
@ -230,3 +230,63 @@ Feed language:
output:
format: rss
lang: ja
Feed link:
input: >
<rss><channel>
<link/>
<link>http://[example.net]/</link>
<link>http://example.com/</link>
</channel></rss>
output:
format: rss
link: 'http://example.com/'
Feed link via GUID 1:
input: >
<rss><channel>
<guid>http://example.com/</guid>
</channel></rss>
output:
format: rss
id: 'http://example.com/'
link: 'http://example.com/'
Feed link via GUID 2:
input: >
<rss><channel>
<guid isPermalink='true'>http://example.com/</guid>
</channel></rss>
output:
format: rss
id: 'http://example.com/'
link: 'http://example.com/'
GUID not a link:
input: >
<rss><channel>
<guid isPermalink='maybe not'>http://example.com/</guid>
</channel></rss>
output:
format: rss
id: 'http://example.com/'
Explicit link preferred:
input: >
<rss><channel>
<guid>http://example.net/</guid>
<link>http://example.com/</link>
</channel></rss>
output:
format: rss
id: 'http://example.net/'
link: 'http://example.com/'
GUID not a url:
input: >
<rss><channel>
<guid>http://[example.com]/</guid>
</channel></rss>
output:
format: rss
id: 'http://[example.com]/'

Write Preview
Loading…
Cancel
Save