Rename to StringUtil methods

calendar-bundle/src/Resources/contao/modules/ModuleEventReader.php

@@ -140,16 +140,16 @@ protected function compile()
 			}
 			elseif ($objEvent->title)
 			{
-				$responseContext->setTitle(StringUtil::getRawDecodedValue($objEvent->title));
+				$responseContext->setTitle(StringUtil::inputEncodedToPlainText($objEvent->title));
 			}
 
 			if ($objEvent->description)
 			{
-				$responseContext->setMetaDescription(StringUtil::getRawDecodedValue($objEvent->description));
+				$responseContext->setMetaDescription(StringUtil::inputEncodedToPlainText($objEvent->description));
 			}
 			elseif ($objEvent->teaser)
 			{
-				$responseContext->setMetaDescription(StringUtil::getRawDecodedValueFromHtml($objEvent->teaser));
+				$responseContext->setMetaDescription(StringUtil::htmlToPlainText($objEvent->teaser));
 			}
 
 			if ($objEvent->robots)

core-bundle/src/Resources/contao/classes/Frontend.php

@@ -568,7 +568,7 @@ public static function getMetaData($strData, $strLanguage)
 	}
 
 	/**
-	 * @deprecated Use StringUtil::getRawDecodedValueFromHtml() instead.
+	 * @deprecated Use StringUtil::htmlToPlainText() instead.
 	 *
 	 * Prepare a text to be used in the meta description tag
 	 *
@@ -578,7 +578,7 @@ public static function getMetaData($strData, $strLanguage)
 	 */
 	protected function prepareMetaDescription($strText)
 	{
-		trigger_deprecation('contao/core-bundle', '4.12', 'Using "Contao\Frontend::prepareMetaDescription()" has been deprecated and will no longer work Contao 5.0. Use the StringUtil::getRawDecodedValueFromHtml() instead.');
+		trigger_deprecation('contao/core-bundle', '4.12', 'Using "Contao\Frontend::prepareMetaDescription()" has been deprecated and will no longer work Contao 5.0. Use the StringUtil::htmlToPlainText() instead.');
 
 		$strText = $this->replaceInsertTags($strText, false);
 		$strText = strip_tags($strText);

core-bundle/src/Resources/contao/library/Contao/StringUtil.php

@@ -975,22 +975,10 @@ public static function ampersand($strString, $blnEncode=true): string
 	/**
 	 * Converts an input-encoded string back to its raw UTF-8 value it originated from.
 	 *
-	 * It handles all Contao input encoding specifics like insert tags, basic entities and encoded entities.
-	 *
-	 * @param bool $blnRemoveInsertTags True to remove insert tags instead of replacing them
+	 * It handles all Contao input encoding specifics like basic entities and encoded entities.
 	 */
-	public static function getRawDecodedValue(string $strValue, bool $blnRemoveInsertTags = false): string
+	public static function revertInputEncoding(string $strValue): string
 	{
-		if ($blnRemoveInsertTags)
-		{
-			$strValue = static::stripInsertTags($strValue);
-		}
-		else
-		{
-			$strValue = Controller::replaceInsertTags($strValue, false);
-		}
-
-		$strValue = strip_tags($strValue);
 		$strValue = static::restoreBasicEntities($strValue);
 		$strValue = static::decodeEntities($strValue);
 
@@ -1005,23 +993,48 @@ public static function getRawDecodedValue(string $strValue, bool $blnRemoveInser
 			mb_substitute_character($substituteCharacter);
 		}
 
+		return $strValue;
+	}
+
+	/**
+	 * Converts an input-encoded string to plain text UTF-8.
+	 *
+	 * Strips or replaces insert tags, strips HTML tags, decodes entities, escapes insert tag braces.
+	 *
+	 * @see StringUtil::revertInputEncoding()
+	 *
+	 * @param bool $blnRemoveInsertTags True to remove insert tags instead of replacing them
+	 */
+	public static function inputEncodedToPlainText(string $strValue, bool $blnRemoveInsertTags = false): string
+	{
+		if ($blnRemoveInsertTags)
+		{
+			$strValue = static::stripInsertTags($strValue);
+		}
+		else
+		{
+			$strValue = Controller::replaceInsertTags($strValue, false);
+		}
+
+		$strValue = strip_tags($strValue);
+		$strValue = static::revertInputEncoding($strValue);
 		$strValue = str_replace(array('{{', '}}'), array('[{]', '[}]'), $strValue);
 
 		return $strValue;
 	}
 
 	/**
-	 * Gets the raw text value of an HTML string with normalized white space.
+	 * Converts an HTML string to plain text with normalized white space.
 	 *
 	 * It handles all Contao input encoding specifics like insert tags, basic
 	 * entities and encoded entities and is meant to be used with content from
 	 * fields that have the allowHtml flag enabled.
 	 *
-	 * @see StringUtil::getRawDecodedValue()
+	 * @see StringUtil::inputEncodedToPlainText()
 	 *
 	 * @param bool $blnRemoveInsertTags True to remove insert tags instead of replacing them
 	 */
-	public static function getRawDecodedValueFromHtml(string $strValue, bool $blnRemoveInsertTags = false): string
+	public static function htmlToPlainText(string $strValue, bool $blnRemoveInsertTags = false): string
 	{
 		if (!$blnRemoveInsertTags)
 		{
@@ -1035,7 +1048,7 @@ public static function getRawDecodedValueFromHtml(string $strValue, bool $blnRem
 			$strValue
 		);
 
-		$strValue = static::getRawDecodedValue($strValue, true);
+		$strValue = static::inputEncodedToPlainText($strValue, true);
 
 		// Remove duplicate line breaks and spaces
 		$strValue = trim(preg_replace(array('/[^\S\n]+/', '/\s*\n\s*/'), array(' ', "\n"), $strValue));

core-bundle/src/Resources/contao/models/PageModel.php

@@ -314,11 +314,11 @@ public function __set($strKey, $varValue)
 				switch ($strKey)
 				{
 					case 'pageTitle':
-						$responseContext->setTitle(StringUtil::getRawDecodedValue($varValue ?? ''));
+						$responseContext->setTitle(StringUtil::inputEncodedToPlainText($varValue ?? ''));
 						break;
 
 					case 'description':
-						$responseContext->setMetaDescription(StringUtil::getRawDecodedValue($varValue ?? ''));
+						$responseContext->setMetaDescription(StringUtil::inputEncodedToPlainText($varValue ?? ''));
 						break;
 
 					case 'robots':

core-bundle/src/Resources/contao/modules/ModuleArticle.php

@@ -171,11 +171,11 @@ protected function compile()
 
 			if ($responseContext instanceof WebpageResponseContext)
 			{
-				$responseContext->setTitle(StringUtil::getRawDecodedValue($this->title ?? ''));
+				$responseContext->setTitle(StringUtil::inputEncodedToPlainText($this->title ?? ''));
 
 				if ($this->teaser)
 				{
-					$responseContext->setMetaDescription(StringUtil::getRawDecodedValueFromHtml($this->teaser));
+					$responseContext->setMetaDescription(StringUtil::htmlToPlainText($this->teaser));
 				}
 			}
 		}

core-bundle/src/Routing/ResponseContext/ContaoWebpageResponseContext.php

@@ -19,11 +19,11 @@ class ContaoWebpageResponseContext extends WebpageResponseContext
 {
     public function __construct(PageModel $pageModel)
     {
-        $title = $pageModel->pageTitle ?: StringUtil::getRawDecodedValue($pageModel->title ?: '');
+        $title = $pageModel->pageTitle ?: StringUtil::inputEncodedToPlainText($pageModel->title ?: '');
 
         $this
             ->setTitle($title ?: '')
-            ->setMetaDescription(StringUtil::getRawDecodedValue($pageModel->description ?: ''))
+            ->setMetaDescription(StringUtil::inputEncodedToPlainText($pageModel->description ?: ''))
         ;
 
         if ($pageModel->robots) {

core-bundle/tests/Contao/StringUtilTest.php

@@ -151,22 +151,48 @@ public function trimsplitProvider(): \Generator
     }
 
     /**
-     * @dataProvider getRawDecodedValueProvider
+     * @dataProvider getRevertInputEncoding
      */
-    public function testGetsRawDecodedValues(string $source, string $expected, bool $removeInsertTags = false): void
+    public function testRevertInputEncoding(string $source, string $expected = null): void
     {
-        $this->assertSame($expected, StringUtil::getRawDecodedValue($source, $removeInsertTags));
+        Input::setGet('value', $source);
+        $inputEncoded = Input::get('value');
+        Input::setGet('value', null);
+
+        // Test input encoding round trip
+        $this->assertSame($expected ?? $source, StringUtil::revertInputEncoding($inputEncoded));
+    }
+
+    public function getRevertInputEncoding(): \Generator
+    {
+        yield ['foobar'];
+        yield ['foo{{email::test@example.com}}bar'];
+        yield ['{{date::...}}'];
+        yield ["<>&\u{A0}<>&\u{A0}"];
+        yield ['I <3 Contao'];
+        yield ['Remove unexpected <span>HTML tags'];
+        yield ['Keep non-HTML <tags> intact'];
+        yield ['Basic [&] entities [nbsp]', "Basic & entities \u{A0}"];
+        yield ["Cont\xE4o invalid UTF-8", "Cont\u{FFFD}o invalid UTF-8"];
+    }
+
+    /**
+     * @dataProvider getInputEncodedToPlainText
+     */
+    public function testInputEncodedToPlainText(string $source, string $expected, bool $removeInsertTags = false): void
+    {
+        $this->assertSame($expected, StringUtil::inputEncodedToPlainText($source, $removeInsertTags));
 
         Input::setGet('value', $expected);
         $inputEncoded = Input::get('value');
         Input::setGet('value', null);
 
         // Test input encoding round trip
-        $this->assertSame($expected, StringUtil::getRawDecodedValue($inputEncoded, true));
-        $this->assertSame($expected, StringUtil::getRawDecodedValue($inputEncoded, false));
+        $this->assertSame($expected, StringUtil::inputEncodedToPlainText($inputEncoded, true));
+        $this->assertSame($expected, StringUtil::inputEncodedToPlainText($inputEncoded, false));
     }
 
-    public function getRawDecodedValueProvider(): \Generator
+    public function getInputEncodedToPlainText(): \Generator
     {
         yield ['foobar', 'foobar'];
         yield ['foo{{email::test@example.com}}bar', 'footest@example.combar'];
@@ -182,29 +208,29 @@ public function getRawDecodedValueProvider(): \Generator
     }
 
     /**
-     * @dataProvider getRawDecodedValueFromHtmlProvider
+     * @dataProvider getHtmlToPlainText
      */
-    public function testGetsRawDecodedValuesFromHtml(string $source, string $expected, bool $removeInsertTags = false): void
+    public function testHtmlToPlainText(string $source, string $expected, bool $removeInsertTags = false): void
     {
-        $this->assertSame($expected, StringUtil::getRawDecodedValueFromHtml($source, $removeInsertTags));
+        $this->assertSame($expected, StringUtil::htmlToPlainText($source, $removeInsertTags));
 
         Input::setPost('value', str_replace(['&#123;&#123;', '&#125;&#125;'], ['[{]', '[}]'], $source));
         $inputXssStripped = str_replace(['&#123;&#123;', '&#125;&#125;'], ['{{', '}}'], Input::postHtml('value', true));
         Input::setPost('value', null);
 
-        $this->assertSame($expected, StringUtil::getRawDecodedValueFromHtml($inputXssStripped, $removeInsertTags));
+        $this->assertSame($expected, StringUtil::htmlToPlainText($inputXssStripped, $removeInsertTags));
     }
 
-    public function getRawDecodedValueFromHtmlProvider(): \Generator
+    public function getHtmlToPlainText(): \Generator
     {
-        yield from $this->getRawDecodedValueProvider();
+        yield from $this->getInputEncodedToPlainText();
 
         yield ['foo<br>bar{{br}}baz', "foo\nbar\nbaz"];
         yield [" \t\r\nfoo \t\r\n \r\n\t bar \t\r\n", 'foo bar'];
         yield [" \t\r\n<br>foo \t<br>\r\n \r\n\t<br> bar <br>\t\r\n", "foo\nbar"];
         yield [
-            '<h1>Headline</h1>Text<ul><li>List 1</li><li>List 2</li></ul><p>Inline<span>text</span> and <a>link</a></p>',
-            "Headline\nText\nList 1\nList 2\nInlinetext and link",
+            '<h1>Headline</h1>Text<ul><li>List 1</li><li>List 2</li></ul><p>Inline<span>text</span> and <a>link</a></p><div><div><div>single newline',
+            "Headline\nText\nList 1\nList 2\nInlinetext and link\nsingle newline",
         ];
     }
 }

faq-bundle/src/Resources/contao/modules/ModuleFaqReader.php

@@ -121,16 +121,16 @@ protected function compile()
 			}
 			elseif ($objFaq->question)
 			{
-				$responseContext->setTitle(StringUtil::getRawDecodedValue($objFaq->question));
+				$responseContext->setTitle(StringUtil::inputEncodedToPlainText($objFaq->question));
 			}
 
 			if ($objFaq->description)
 			{
-				$responseContext->setMetaDescription(StringUtil::getRawDecodedValue($objFaq->description));
+				$responseContext->setMetaDescription(StringUtil::inputEncodedToPlainText($objFaq->description));
 			}
 			elseif ($objFaq->question)
 			{
-				$responseContext->setMetaDescription(StringUtil::getRawDecodedValue($objFaq->question));
+				$responseContext->setMetaDescription(StringUtil::inputEncodedToPlainText($objFaq->question));
 			}
 
 			if ($objFaq->robots)

news-bundle/src/Resources/contao/modules/ModuleNewsReader.php

@@ -147,16 +147,16 @@ protected function compile()
 			}
 			elseif ($objArticle->headline)
 			{
-				$responseContext->setTitle(StringUtil::getRawDecodedValue($objArticle->headline));
+				$responseContext->setTitle(StringUtil::inputEncodedToPlainText($objArticle->headline));
 			}
 
 			if ($objArticle->description)
 			{
-				$responseContext->setMetaDescription(StringUtil::getRawDecodedValue($objArticle->description));
+				$responseContext->setMetaDescription(StringUtil::inputEncodedToPlainText($objArticle->description));
 			}
 			elseif ($objArticle->teaser)
 			{
-				$responseContext->setMetaDescription(StringUtil::getRawDecodedValueFromHtml($objArticle->teaser));
+				$responseContext->setMetaDescription(StringUtil::htmlToPlainText($objArticle->teaser));
 			}
 
 			if ($objArticle->robots)

newsletter-bundle/src/Resources/contao/modules/ModuleNewsletterReader.php

@@ -113,7 +113,7 @@ protected function compile()
 
 			if ($responseContext instanceof WebpageResponseContext)
 			{
-				$responseContext->setTitle(StringUtil::getRawDecodedValue($objNewsletter->subject));
+				$responseContext->setTitle(StringUtil::inputEncodedToPlainText($objNewsletter->subject));
 			}
 		}