Allow reading not strictly valid HTML

stloyd · norberttech · commit 85bd82374afd · 2025-11-15T15:41:08.000+01:00
diff --git a/src/core/etl/src/Flow/ETL/Row/Entry/HTMLEntry.php b/src/core/etl/src/Flow/ETL/Row/Entry/HTMLEntry.php
@@ -32,7 +32,7 @@ public function __construct(
         ?Metadata $metadata = null,
     ) {
         if (\is_string($value)) {
-            $this->value = HTMLDocument::createFromString($value);
+            $this->value = HTMLDocument::createFromString($value, \LIBXML_NOERROR);
         } else {
             $this->value = $value;
         }
diff --git a/src/core/etl/tests/Flow/ETL/Tests/Unit/Row/Entry/HTMLEntryTest.php b/src/core/etl/tests/Flow/ETL/Tests/Unit/Row/Entry/HTMLEntryTest.php
@@ -166,6 +166,36 @@ public function test_renames_entry() : void
         self::assertEquals($entry->type(), $newEntry->type());
     }
 
+    public function test_with_non_fully_valid_html_string() : void
+    {
+        $invalidHtml = <<<'HTML'
+<!DOCTYPE html>
+<html lang="en">
+<head></head>
+<body>
+    <div>foo</div>
+    <div><p><span>bar</span></span></p></div>
+</body>
+</html>
+HTML;
+
+        $validHtml = <<<'HTML'
+<!DOCTYPE html>
+<html lang="en">
+<head></head>
+<body>
+    <div>foo</div>
+    <div><p><span>bar</span></p></div>
+</body>
+</html>
+HTML;
+
+        $entry = html_entry('html', $invalidHtml);
+
+        self::assertHtml($invalidHtml, $entry->toString(), false);
+        self::assertHtml($validHtml, $entry->toString(), true);
+    }
+
     public function test_with_value() : void
     {
         $entry = html_entry('html', '<!DOCTYPE html><html lang="en"><head></head><body><div>foobar</div></body></html>');
@@ -178,4 +208,16 @@ public function test_with_value() : void
         self::assertNotEquals($entry->toString(), $newEntry->toString());
         self::assertEquals($html, $newEntry->value());
     }
+
+    private function assertHtml(string $expected, string $html, bool $equals) : void
+    {
+        $expected = \preg_replace('/\s*/', '', $expected);
+        $html = \preg_replace('/\s*/', '', $html);
+
+        if ($equals) {
+            self::assertEquals($expected, $html);
+        } else {
+            self::assertNotEquals($expected, $html);
+        }
+    }
 }
diff --git a/src/lib/types/src/Flow/Types/Type/Logical/HTMLType.php b/src/lib/types/src/Flow/Types/Type/Logical/HTMLType.php
@@ -40,7 +40,7 @@ public function cast(mixed $value) : HTMLDocument
 
         /* @phpstan-ignore-next-line */
         if (\is_string($value)) {
-            return HTMLDocument::createFromString($value);
+            return HTMLDocument::createFromString($value, \LIBXML_NOERROR);
         }
 
         return $value;

Original file line number	Diff line number	Diff line change
`@@ -32,7 +32,7 @@ public function __construct(`
`32`	`32`	`?Metadata $metadata = null,`
`33`	`33`	`) {`
`34`	`34`	`if (\is_string($value)) {`
`35`		`- $this->value = HTMLDocument::createFromString($value);`
	`35`	`+ $this->value = HTMLDocument::createFromString($value, \LIBXML_NOERROR);`
`36`	`36`	`} else {`
`37`	`37`	`$this->value = $value;`
`38`	`38`	`}`
Original file line number	Diff line number	Diff line change
`@@ -40,7 +40,7 @@ public function cast(mixed $value) : HTMLDocument`
`40`	`40`
`41`	`41`	`/* @phpstan-ignore-next-line */`
`42`	`42`	`if (\is_string($value)) {`
`43`		`- return HTMLDocument::createFromString($value);`
	`43`	`+ return HTMLDocument::createFromString($value, \LIBXML_NOERROR);`
`44`	`44`	`}`
`45`	`45`
`46`	`46`	`return $value;`