Skip to content

Improve rel parsing #162

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Mar 25, 2018
Merged

Improve rel parsing #162

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
6b0232b
Add broken test for unique and sorted rel values under rel-urls
Zegnat Mar 22, 2018
ebffee4
Add broken test for merging link information from several elements
Zegnat Mar 22, 2018
f2289a8
Improve parsing of link relationships
Zegnat Mar 22, 2018
31ca035
Test and fix for duplicate URLs in the rels object
Zegnat Mar 22, 2018
108fbf0
Stop using the short array syntax
Zegnat Mar 22, 2018
64e7966
Never do falsy checks on strings
Zegnat Mar 22, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
45 changes: 31 additions & 14 deletions Mf2/Parser.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1250,16 +1250,15 @@ public function parseRelsAndAlternates() {

// Iterate through all a, area and link elements with rel attributes
foreach ($this->xpath->query('//a[@rel and @href] | //link[@rel and @href] | //area[@rel and @href]') as $hyperlink) {
if ($hyperlink->getAttribute('rel') == '') {
// Parse the set of rels for the current link
$linkRels = array_unique(array_filter(preg_split('/[\t\n\f\r ]/', $hyperlink->getAttribute('rel'))));
if (count($linkRels) === 0) {
continue;
}

// Resolve the href
$href = $this->resolveUrl($hyperlink->getAttribute('href'));

// Split up the rel into space-separated values
$linkRels = array_filter(explode(' ', $hyperlink->getAttribute('rel')));

$rel_attributes = array();

if ($hyperlink->hasAttribute('media')) {
Expand All @@ -1278,8 +1277,8 @@ public function parseRelsAndAlternates() {
$rel_attributes['type'] = $hyperlink->getAttribute('type');
}

if ($hyperlink->nodeValue) {
$rel_attributes['text'] = $hyperlink->nodeValue;
if (strlen($hyperlink->textContent) > 0) {
$rel_attributes['text'] = $hyperlink->textContent;
}

if ($this->enableAlternates) {
Expand All @@ -1296,16 +1295,34 @@ public function parseRelsAndAlternates() {
}

foreach ($linkRels as $rel) {
$rels[$rel][] = $href;
if (!array_key_exists($rel, $rels)) {
$rels[$rel] = array($href);
} elseif (!in_array($href, $rels[$rel])) {
$rels[$rel][] = $href;
}
}

if (!in_array($href, $rel_urls)) {
$rel_urls[$href] = array_merge(
$rel_attributes,
array('rels' => $linkRels)
);
if (!array_key_exists($href, $rel_urls)) {
$rel_urls[$href] = array('rels' => array());
}

// Add the attributes collected only if they were not already set
$rel_urls[$href] = array_merge(
$rel_attributes,
$rel_urls[$href]
);

// Merge current rels with those already set
$rel_urls[$href]['rels'] = array_merge(
$rel_urls[$href]['rels'],
$linkRels
);
}

// Alphabetically sort the rels arrays after removing duplicates
foreach ($rel_urls as $href => $object) {
$rel_urls[$href]['rels'] = array_unique($rel_urls[$href]['rels']);
sort($rel_urls[$href]['rels']);
}

if (empty($rels) and $this->jsonMode) {
Expand All @@ -1314,8 +1331,8 @@ public function parseRelsAndAlternates() {

if (empty($rel_urls) and $this->jsonMode) {
$rel_urls = new stdClass();
}
}

return array($rels, $rel_urls, $alternates);
}

Expand Down
43 changes: 43 additions & 0 deletions tests/Mf2/RelTest.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -176,4 +176,47 @@ public function testRelURLs() {
$this->assertArrayHasKey('rels', $output['rel-urls']['http://example.com/articles.atom']);
}

/**
* @see https://github.com/microformats/microformats2-parsing/issues/29
* @see https://github.com/microformats/microformats2-parsing/issues/30
*/
public function testRelURLsRelsUniqueAndSorted() {
$input = '<a href="#" rel="me bookmark"></a>
<a href="#" rel="bookmark archived"></a>';
$parser = new Parser($input);
$output = $parser->parse();
$this->assertEquals($output['rel-urls']['#']['rels'], array('archived', 'bookmark', 'me'));
}

public function testRelURLsInfoMergesCorrectly() {
$input = '<a href="#" rel="a">This nodeValue</a>
<a href="#" rel="a" hreflang="en">Not this nodeValue</a>';
$parser = new Parser($input);
$output = $parser->parse();
$this->assertEquals($output['rel-urls']['#']['hreflang'], 'en');
$this->assertArrayNotHasKey('media', $output['rel-urls']['#']);
$this->assertArrayNotHasKey('title', $output['rel-urls']['#']);
$this->assertArrayNotHasKey('type', $output['rel-urls']['#']);
$this->assertEquals($output['rel-urls']['#']['text'], 'This nodeValue');
}

public function testRelURLsNoDuplicates() {
$input = '<a href="#a" rel="a"></a>
<a href="#b" rel="a"></a>
<a href="#a" rel="a"></a>';
$parser = new Parser($input);
$output = $parser->parse();
$this->assertEquals($output['rels']['a'], array('#a', '#b'));
}

public function testRelURLsFalsyTextVSEmpty() {
$input = '<a href="#a" rel="a">0</a>
<a href="#b" rel="b"></a>';
$parser = new Parser($input);
$output = $parser->parse();
$this->assertArrayHasKey('text', $output['rel-urls']['#a']);
$this->assertEquals($output['rel-urls']['#a']['text'], '0');
$this->assertArrayNotHasKey('text', $output['rel-urls']['#b']);
}

}