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

Fill out entries so more; test entry IDs, lang

master
J. King 4 years ago
parent
2f3deb9583
commit
d90af87f96
6 changed files with 151 additions and 14 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. 58
      lib/Parser/XML/Entry.php
  2. 6
      lib/Parser/XML/Feed.php
  3. 4
      lib/Parser/XML/XPath.php
  4. 10
      tests/cases/XML/entry-rss0.yaml
  5. 54
      tests/cases/XML/entry-rss1.yaml
  6. 33
      tests/cases/XML/entry-rss2.yaml

58
lib/Parser/XML/Entry.php
View File

@ -47,19 +47,21 @@ class Entry extends Construct implements \MensBeam\Lax\Parser\Entry {
}
public function getId(): ?string {
return $this->fetchString("atom:id", ".+") // Item identifier
?? $this->fetchString("dc:identifier", ".+") // Dublin Core identifier
?? $this->fetchString("rss2:guid", ".+"); // RSS 2.0 GUID
return $this->fetchString("atom:id", ".+") // Atom identifier
?? $this->fetchString("dc:identifier", ".+") // Dublin Core identifier
?? $this->fetchString("self::rss1:item/@rdf:about") // RSS 1.0 RDF identifier
?? $this->fetchString("rss2:guid", ".+"); // RSS 2.0 GUID, as string
}
public function getLink(): ?Url {
return $this->getLinkAtom() // Atom link
?? $this->getLinkRss1() // RSS 0.90 or RSS 1.0 link
?? $this->getLinkRss2(); // RSS 2.0 link
return $this->getLinkAtom() // Atom link
?? $this->getLinkRss1() // RSS 0.90 or RSS 1.0 link
?? $this->getLinkAndRelatedRss2()[0]; // RSS 2.0 GUID or link, as URL
}
public function getRelatedLink(): ?Url {
return $this->fetchAtomRelation("related", ["text/html", "application/xhtml+xml"]);
return $this->fetchAtomRelation("related", ["text/html", "application/xhtml+xml"]) // Atom related relation
?? $this->getLinkAndRelatedRss2()[1]; // RSS 2.0 link if different from GUID;
}
public function getTitle(): ?Text {
@ -71,11 +73,22 @@ class Entry extends Construct implements \MensBeam\Lax\Parser\Entry {
}
public function getDateModified(): ?Date {
return null;
/* fetching a date works differently from other data as only Atom has
well-defined semantics here. Thus the semantics of all the other
formats are equal, and we want the latest date, whatever it is.
*/
return $this->fetchDate("atom:updated", self::DATE_LATEST) // Atom update date
?? $this->fetchDate("dc:date|rss2:pubDate|rss2:lastBuildDate", self::DATE_LATEST); // Latest other datee
}
public function getDateCreated(): ?Date {
return null;
/* fetching a date works differently from other data as only Atom has
well-defined semantics here. Thus the semantics of all the other
formats are equal, and we want the earliest date, but only if
there are at least two
*/
return $this->fetchDate("atom:created", self::DATE_EARLIEST) // Atom creation date
?? $this->getAssumedDateCreated(); // Earliest other date
}
public function getContent(): ?Text {
@ -101,4 +114,31 @@ class Entry extends Construct implements \MensBeam\Lax\Parser\Entry {
public function getEnclosures(): EnclosureCollection {
return new EnclosureCollection;
}
/** Returns an indexed array containing the entry link (or null)
* and the entry related link (or null)
*
* This follows the suggestion in RSS 2.0 that if the permalink-GUID
* and link differ, then the latter is a related link. For our purposes
* they are considered to differ if they point to different hosts or
* have different schemes
*/
protected function getLinkAndRelatedRss2(): array {
$link = $this->fetchUrl("rss2:link");
$guid = $this->fetchUrl("rss2:guid[not(@isPermalink) or @isPermalink='true']");
if ($link && $guid) {
if ($link->getScheme() !== $guid->getScheme() || $link->getAuthority() !== $guid->getAuthority()) {
return [$guid, $link];
}
}
return [$link ?? $guid, null];
}
protected function getAssumedDateCreated(): ?Date {
$dates = $this->fetchDate("dc:date|rss2:pubDate|rss2:lastBuildDate", self::DATE_ALL);
if (sizeof($dates) > 1) {
return $dates[0];
}
return null;
}
}

6
lib/Parser/XML/Feed.php
View File

@ -127,9 +127,9 @@ class Feed extends Construct implements \MensBeam\Lax\Parser\Feed {
}
public function getUrl(): ?Url {
return $this->fetchAtomRelation("self") // Atom 'self' relation URL
?? $this->fetchUrl("self::rss1:channel/@rdf:about") // RDF-about URL from RSS 0.90 or RSS 1.0
?? $this->fetchUrl("apple:new-feed-url"); // iTunes podcast canonical URL
return $this->fetchAtomRelation("self", ["application/atom+xml"]) // Atom 'self' relation URL
?? $this->fetchUrl("self::rss1:channel/@rdf:about") // RDF-about URL from RSS 0.90 or RSS 1.0
?? $this->fetchUrl("apple:new-feed-url"); // iTunes podcast canonical URL
}
public function getLink(): ?Url {

4
lib/Parser/XML/XPath.php
View File

@ -16,8 +16,8 @@ class XPath extends \DOMXpath {
'sched' => "http://purl.org/rss/1.0/modules/syndication/", // Syndication schedule extension http://purl.org/rss/1.0/modules/syndication/
'enc' => "http://purl.org/rss/1.0/modules/content/", // Explicitly encoded content extension http://purl.org/rss/1.0/modules/content/
'media' => "http://search.yahoo.com/mrss/", // Embedded media extension http://www.rssboard.org/media-rss
'rdf' => "http://www.w3.org/1999/02/22-rdf-syntax-ns#", // Resource Description Framework
'xhtml' => "http://www.w3.org/1999/xhtml", // XHTML
'rdf' => "http://www.w3.org/1999/02/22-rdf-syntax-ns#", // Resource Description Framework https://www.w3.org/TR/2014/REC-rdf11-concepts-20140225/
'xhtml' => "http://www.w3.org/1999/xhtml", // XHTML https://html.spec.whatwg.org/
'apple' => "http://www.itunes.com/dtds/podcast-1.0.dtd", // iTunes podcasts https://help.apple.com/itc/podcasts_connect/#/itcb54353390
'gplay' => "http://www.google.com/schemas/play-podcasts/1.0", // Google Play podcasts https://support.google.com/googleplay/podcasts/answer/6260341
];

10
tests/cases/XML/entry-rss0.yaml
View File

@ -0,0 +1,10 @@
Empty entry:
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>
<item/>
</channel>
</rdf:RDF>
output:
format: rdf
version: '0.90'

54
tests/cases/XML/entry-rss1.yaml
View File

@ -0,0 +1,54 @@
# For the purposes of testing Dublin Core metadata is considered a part of RSS 1.0
Empty entry:
input: >
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns="http://purl.org/rss/1.0/">
<channel>
<item/>
</channel>
</rdf:RDF>
output:
format: rdf
version: '1.0'
RDF identifier:
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/">
<channel>
<item rdf:about="blah"/>
</channel>
</rdf:RDF>
output:
format: rdf
version: '1.0'
entries:
- id: blah
Dublin Core identifier:
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/">
<channel>
<item rdf:about="bloo">
<dc:identifier>blah</dc:identifier>
</item>
</channel>
</rdf:RDF>
output:
format: rdf
version: '1.0'
entries:
- id: blah
Dublin Core identifier and language:
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/">
<item rdf:about="blah">
<dc:language>fr</dc:language>
</item>
</rdf:RDF>
output:
format: rdf
version: '1.0'
entries:
- id: blah
lang: fr

33
tests/cases/XML/entry-rss2.yaml
View File

@ -0,0 +1,33 @@
Empty entry:
input: >
<rss><channel>
<item/>
</channel></rss>
output:
format: rss
GUID:
input: >
<rss><channel>
<item>
<guid isPermalink="false">blah</guid>
</item>
</channel></rss>
output:
format: rss
entries:
- id: blah
Language:
input: >
<rss><channel>
<item>
<guid isPermalink="false">blah</guid>
<language>fr</language>
</item>
</channel></rss>
output:
format: rss
entries:
- id: blah
lang: fr
Write Preview
Loading…
Cancel
Save