bug #10983 [DomCrawler] Fixed charset detection in html5 meta charset tag (77web)
This PR was squashed before being merged into the 2.3 branch (closes #10983).
Discussion
----------
[DomCrawler] Fixed charset detection in html5 meta charset tag
| Q | A
| ------------- | ---
| Bug fix? | yes
| New feature? | no
| BC breaks? | no
| Deprecations? | no
| Tests pass? | yes
| Fixed tickets | N/A
| License | MIT
It may be minor to folks with ascii-charactered language, but is critical for us Japanese.
Many Japanese websites with SJIS encoding have "Shift_JIS" as their encoding declaration.
Commits
-------
172e752
[DomCrawler] Fixed charset detection in html5 meta charset tag
This commit is contained in:
commit
cff410507f
@ -108,8 +108,10 @@ class Crawler extends \SplObjectStorage
|
||||
}
|
||||
}
|
||||
|
||||
// http://www.w3.org/TR/encoding/#encodings
|
||||
// http://www.w3.org/TR/REC-xml/#NT-EncName
|
||||
if (null === $charset &&
|
||||
preg_match('/\<meta[^\>]+charset *= *["\']?([a-zA-Z\-0-9]+)/i', $content, $matches)) {
|
||||
preg_match('/\<meta[^\>]+charset *= *["\']?([a-zA-Z\-0-9_:.]+)/i', $content, $matches)) {
|
||||
$charset = $matches[1];
|
||||
}
|
||||
|
||||
|
@ -232,6 +232,10 @@ EOF
|
||||
$crawler = new Crawler();
|
||||
$crawler->addContent('<html><meta http-equiv="Content-Type" content="text/html; charset=utf-8" /><span>中文</span></html>');
|
||||
$this->assertEquals('中文', $crawler->filterXPath('//span')->text(), '->addContent() guess wrong charset');
|
||||
|
||||
$crawler = new Crawler();
|
||||
$crawler->addContent(mb_convert_encoding('<html><head><meta charset="Shift_JIS"></head><body>日本語</body></html>', 'SJIS', 'UTF-8'));
|
||||
$this->assertEquals('日本語', $crawler->filterXPath('//body')->text(), '->addContent() can recognize "Shift_JIS" in html5 meta charset tag');
|
||||
}
|
||||
|
||||
/**
|
||||
|
Reference in New Issue
Block a user