summaryrefslogtreecommitdiff
path: root/src
diff options
context:
space:
mode:
authorAndres Rey <[email protected]>2017-11-06 18:03:27 +0000
committerAndres Rey <[email protected]>2017-11-06 18:03:27 +0000
commit056921e2450de888a18313610a5303e3edbb2ed4 (patch)
treed1decedb579a50ec446928bcc837bdddb7772a31 /src
parentc1cf2c1a2ea5424797a7d2afe9defdc9c1e6d917 (diff)
Get the article direction
TODO: Make the metadata array an object with getters and setters
Diffstat (limited to 'src')
-rw-r--r--src/HTMLParser.php11
1 files changed, 11 insertions, 0 deletions
diff --git a/src/HTMLParser.php b/src/HTMLParser.php
index f8d2342..fa8a609 100644
--- a/src/HTMLParser.php
+++ b/src/HTMLParser.php
@@ -17,6 +17,7 @@ class HTMLParser
private $dom = null;
/**
+ * TODO Make this an object? Instead of a dumb array
* @var array
*/
private $metadata = [];
@@ -969,6 +970,16 @@ class HTMLParser
$articleContent = $this->prepArticle($articleContent);
if ($hasContent) {
+ // Find out text direction from ancestors of final top candidate.
+ $ancestors = array_merge([$parentOfTopCandidate, $topCandidate], $parentOfTopCandidate->getNodeAncestors());
+ foreach ($ancestors as $ancestor) {
+ $articleDir = $ancestor->getAttribute('dir');
+ if ($articleDir) {
+ $this->metadata['articleDir'] = $articleDir;
+ break;
+ }
+ }
+
return $articleContent;
} else {
return false;