bug #47175 [DowCrawler] Fix locale-sensitivity of whitespace normalization (nicolas-grekas)

nicolas-grekas · nicolas-grekas · commit fcd9c2d6153a · 2022-08-03T15:04:20.000+02:00
This PR was merged into the 4.4 branch. Discussion ---------- [DowCrawler] Fix locale-sensitivity of whitespace normalization | Q | A | ------------- | --- | Branch? | 4.4 | Bug fix? | yes | New feature? | no | Deprecations? | no | Tickets | Fix #46822 | License | MIT | Doc PR | - Also aligning with https://infra.spec.whatwg.org/#ascii-whitespace Commits ------- a632fe2 [DowCrawler] Fix locale-sensitivity of whitespace normalization
diff --git a/src/Symfony/Component/DomCrawler/Crawler.php b/src/Symfony/Component/DomCrawler/Crawler.php
@@ -620,15 +620,15 @@ public function text(/* string $default = null, bool $normalizeWhitespace = true
         $text = $this->getNode(0)->nodeValue;
 
         if (\func_num_args() <= 1) {
-            if (trim(preg_replace('/(?:\s{2,}+|[^\S ])/', ' ', $text)) !== $text) {
+            if (trim(preg_replace("/(?:[ \n\r\t\x0C]{2,}+|[\n\r\t\x0C])/", ' ', $text), " \n\r\t\x0C") !== $text) {
                 @trigger_error(sprintf('"%s()" will normalize whitespaces by default in Symfony 5.0, set the second "$normalizeWhitespace" argument to false to retrieve the non-normalized version of the text.', __METHOD__), \E_USER_DEPRECATED);
             }
 
             return $text;
         }
 
         if (\func_num_args() > 1 && func_get_arg(1)) {
-            return trim(preg_replace('/(?:\s{2,}+|[^\S ])/', ' ', $text));
+            return trim(preg_replace("/(?:[ \n\r\t\x0C]{2,}+|[\n\r\t\x0C])/", ' ', $text), " \n\r\t\x0C");
         }
 
         return $text;

Original file line number	Diff line number	Diff line change
`@@ -620,15 +620,15 @@ public function text(/* string $default = null, bool $normalizeWhitespace = true`
`620`	`620`	`$text = $this->getNode(0)->nodeValue;`
`621`	`621`
`622`	`622`	`if (\func_num_args() <= 1) {`
`623`		`- if (trim(preg_replace('/(?:\s{2,}+\|[^\S ])/', ' ', $text)) !== $text) {`
	`623`	`+ if (trim(preg_replace("/(?:[ \n\r\t\x0C]{2,}+\|[\n\r\t\x0C])/", ' ', $text), " \n\r\t\x0C") !== $text) {`
`624`	`624`	`@trigger_error(sprintf('"%s()" will normalize whitespaces by default in Symfony 5.0, set the second "$normalizeWhitespace" argument to false to retrieve the non-normalized version of the text.', __METHOD__), \E_USER_DEPRECATED);`
`625`	`625`	`}`
`626`	`626`
`627`	`627`	`return $text;`
`628`	`628`	`}`
`629`	`629`
`630`	`630`	`if (\func_num_args() > 1 && func_get_arg(1)) {`
`631`		`- return trim(preg_replace('/(?:\s{2,}+\|[^\S ])/', ' ', $text));`
	`631`	`+ return trim(preg_replace("/(?:[ \n\r\t\x0C]{2,}+\|[\n\r\t\x0C])/", ' ', $text), " \n\r\t\x0C");`
`632`	`632`	`}`
`633`	`633`
`634`	`634`	`return $text;`