bug #9323 [DomCrawler]fix #9321 Crawler::addHtmlContent add gbk encoding support (bronze1man)

fabpot · fabpot · commit e0126d9d39b5 · 2013-12-29T19:30:30.000+01:00
This PR was submitted for the 2.2 branch but it was merged into the 2.3 branch instead (closes #9323). Discussion ---------- [DomCrawler]fix #9321 Crawler::addHtmlContent add gbk encoding support | Q | A | ------------- | --- | Bug fix? | yes | New feature? | no | BC breaks? | no | Deprecations? | no | Tests pass? | yes | Fixed tickets | #9321 | License | MIT | Doc PR | n/a This is solution 1 in #9321 (comment) Commits ------- 30af288 fix some cs 9f20b24 use restore_error_handler instead of set_error_handler($previous) 53cb6ad [DomCrawler]fix #9321 Crawler::addHtmlContent add gbk encoding support
diff --git a/src/Symfony/Component/DomCrawler/Crawler.php b/src/Symfony/Component/DomCrawler/Crawler.php
@@ -147,8 +147,18 @@ public function addHtmlContent($content, $charset = 'UTF-8')
         $dom = new \DOMDocument('1.0', $charset);
         $dom->validateOnParse = true;
 
-        if (function_exists('mb_convert_encoding') && in_array(strtolower($charset), array_map('strtolower', mb_list_encodings()))) {
-            $content = mb_convert_encoding($content, 'HTML-ENTITIES', $charset);
+        if (function_exists('mb_convert_encoding')) {
+            $hasError = false;
+            set_error_handler(function () use (&$hasError) {
+                $hasError = true;
+            });
+            $tmpContent = @mb_convert_encoding($content, 'HTML-ENTITIES', $charset);
+
+            restore_error_handler();
+
+            if (!$hasError) {
+                $content = $tmpContent;
+            }
         }
 
         @$dom->loadHTML($content);
diff --git a/src/Symfony/Component/DomCrawler/Tests/CrawlerTest.php b/src/Symfony/Component/DomCrawler/Tests/CrawlerTest.php
@@ -112,6 +112,18 @@ public function testAddHtmlContentUnsupportedCharset()
         $this->assertEquals('Žťčýů', $crawler->filterXPath('//p')->text());
     }
 
+    /**
+     * @covers Symfony\Component\DomCrawler\Crawler::addHtmlContent
+     */
+    public function testAddHtmlContentCharsetGbk()
+    {
+        $crawler = new Crawler();
+        //gbk encode of <html><p>中文</p></html>
+        $crawler->addHtmlContent(base64_decode('PGh0bWw+PHA+1tDOxDwvcD48L2h0bWw+'), 'gbk');
+
+        $this->assertEquals('中文', $crawler->filterXPath('//p')->text());
+    }
+
     /**
      * @covers Symfony\Component\DomCrawler\Crawler::addHtmlContent
      */
