diff --git a/typo3/sysext/core/Classes/Charset/CharsetConverter.php b/typo3/sysext/core/Classes/Charset/CharsetConverter.php
index 65ff728200bd458461bcc659e317d06b6f21be5c..6c98ca59c48caca0d5cfb657d52a9b24102ea07a 100644
--- a/typo3/sysext/core/Classes/Charset/CharsetConverter.php
+++ b/typo3/sysext/core/Classes/Charset/CharsetConverter.php
@@ -551,17 +551,14 @@ class CharsetConverter implements SingletonInterface
}
/**
- * Converts numeric entities (UNICODE, eg. decimal (Ӓ) or hexadecimal ()) to UTF-8 multibyte chars
- *
+ * Converts numeric entities (UNICODE, eg. decimal (Ӓ) or hexadecimal ()) to UTF-8 multibyte chars.
+ * All string-HTML entities (like & or £) will be converted as well
* @param string $str Input string, UTF-8
- * @param bool $alsoStdHtmlEnt If set, then all string-HTML entities (like & or £ will be converted as well)
* @return string Output string
*/
- public function entities_to_utf8($str, $alsoStdHtmlEnt = false)
+ public function entities_to_utf8($str)
{
- if ($alsoStdHtmlEnt) {
- $trans_tbl = array_flip(get_html_translation_table(HTML_ENTITIES, ENT_COMPAT, 'UTF-8'));
- }
+ $trans_tbl = array_flip(get_html_translation_table(HTML_ENTITIES, ENT_COMPAT));
$token = md5(microtime());
$parts = explode($token, preg_replace('/(&([#[:alnum:]]*);)/', $token . '${2}' . $token, $str));
foreach ($parts as $k => $v) {
@@ -579,7 +576,7 @@ class CharsetConverter implements SingletonInterface
$v = substr($v, $position);
}
$parts[$k] = $this->UnumberToChar($v);
- } elseif ($alsoStdHtmlEnt && isset($trans_tbl['&' . $v . ';'])) {
+ } elseif (isset($trans_tbl['&' . $v . ';'])) {
// Other entities:
$v = $trans_tbl['&' . $v . ';'];
$parts[$k] = $v;
@@ -592,19 +589,18 @@ class CharsetConverter implements SingletonInterface
}
/**
- * Converts all chars in the input UTF-8 string into integer numbers returned in an array
+ * Converts all chars in the input UTF-8 string into integer numbers returned in an array.
+ * All HTML entities (like & or £ or { or 㽝) will be detected as characters.
+ * Also, instead of integer numbers the real UTF-8 char is returned.
*
* @param string $str Input string, UTF-8
- * @param bool $convEntities If set, then all HTML entities (like & or £ or { or 㽝) will be detected as characters.
- * @param bool $retChar If set, then instead of integer numbers the real UTF-8 char is returned.
* @return array Output array with the char numbers
*/
- public function utf8_to_numberarray($str, $convEntities = false, $retChar = false)
+ public function utf8_to_numberarray($str)
{
- // If entities must be registered as well...:
- if ($convEntities) {
- $str = $this->entities_to_utf8($str, 1);
- }
+ // Entities must be registered as well
+ $str = $this->entities_to_utf8($str);
+
// Do conversion:
$strLen = strlen($str);
$outArr = array();
@@ -631,12 +627,12 @@ class CharsetConverter implements SingletonInterface
break;
}
}
- $outArr[] = $retChar ? $buf : $this->utf8CharToUnumber($buf);
+ $outArr[] = $buf;
} else {
- $outArr[] = $retChar ? chr($this->noCharByteVal) : $this->noCharByteVal;
+ $outArr[] = chr($this->noCharByteVal);
}
} else {
- $outArr[] = $retChar ? chr($ord) : $ord;
+ $outArr[] = chr($ord);
}
}
return $outArr;
diff --git a/typo3/sysext/core/Classes/Imaging/GraphicalFunctions.php b/typo3/sysext/core/Classes/Imaging/GraphicalFunctions.php
index 980c1b4fc8e8e1e6699fb5bea902c0232591e24d..b20f5cf748f4a4f40f07fb00301276f00021a6b6 100644
--- a/typo3/sysext/core/Classes/Imaging/GraphicalFunctions.php
+++ b/typo3/sysext/core/Classes/Imaging/GraphicalFunctions.php
@@ -811,7 +811,7 @@ class GraphicalFunctions
$x += $wordW + $wordSpacing;
}
} else {
- $utf8Chars = $this->csConvObj->utf8_to_numberarray($theText, true, true);
+ $utf8Chars = $this->csConvObj->utf8_to_numberarray($theText);
// For each UTF-8 char, do:
foreach ($utf8Chars as $char) {
$charInf = $this->ImageTTFBBoxWrapper($conf['fontSize'], $conf['angle'], $conf['fontFile'], $char, $conf['splitRendering.'], $sF);
@@ -928,7 +928,7 @@ class GraphicalFunctions
$x += $wordW + $wordSpacing;
}
} else {
- $utf8Chars = $this->csConvObj->utf8_to_numberarray($text, true, true);
+ $utf8Chars = $this->csConvObj->utf8_to_numberarray($text);
// For each UTF-8 char, do:
foreach ($utf8Chars as $char) {
$charInf = $this->ImageTTFBBoxWrapper($fontSize, $angle, $fontFile, $char, $splitRenderingConf, $sF);
@@ -1152,7 +1152,7 @@ class GraphicalFunctions
$currentState = -1;
$bankAccum = '';
// Explode the string value by the word value to highlight:
- $utf8Chars = $this->csConvObj->utf8_to_numberarray($part['str'], true, true);
+ $utf8Chars = $this->csConvObj->utf8_to_numberarray($part['str']);
foreach ($utf8Chars as $utfChar) {
// Find number and evaluate position:
$uNumber = (int)$this->csConvObj->utf8CharToUnumber($utfChar);
diff --git a/typo3/sysext/core/Documentation/Changelog/master/Breaking-74031-CharsetConverterParametersRemoved.rst b/typo3/sysext/core/Documentation/Changelog/master/Breaking-74031-CharsetConverterParametersRemoved.rst
new file mode 100644
index 0000000000000000000000000000000000000000..e88167187f4cb73ba996ade7a28eeb61e3493a3f
--- /dev/null
+++ b/typo3/sysext/core/Documentation/Changelog/master/Breaking-74031-CharsetConverterParametersRemoved.rst
@@ -0,0 +1,32 @@
+======================================================
+Breaking: #74031 - CharsetConverter parameters removed
+======================================================
+
+Description
+===========
+
+The second parameter for the method ``CharsetConverter->entities_to_utf8()`` has been removed.
+
+The second and the third parameter of ``CharsetConverter->utf8_to_numberarray()`` has been removed.
+
+
+Impact
+======
+
+When calling ``CharsetConverter->entities_to_utf8()``, string-HTML entities (like & or £) will be converted
+to UTF-8 as well at all times. Previously this behaviour was configurable.
+
+When calling ``CharsetConverter->utf8_to_numberarray()``, string-HTML entities (like & or £) will be converted to UTF-8 as well at all times. Additionally instead of integer numbers the real UTF-8 char is returned
+at any times. Previously these behaviours were configurable.
+
+
+Affected Installations
+======================
+
+Installations with custom extensions that used these methods directly in PHP code.
+
+
+Migration
+=========
+
+Remove these parameters from the calling PHP code.
\ No newline at end of file
diff --git a/typo3/sysext/indexed_search/Classes/Controller/SearchController.php b/typo3/sysext/indexed_search/Classes/Controller/SearchController.php
index 937116aa0b2163f950b8bb673683272a29063fbd..c68e1d403e135eb2e0bf1d185f6b600ba7ec780a 100644
--- a/typo3/sysext/indexed_search/Classes/Controller/SearchController.php
+++ b/typo3/sysext/indexed_search/Classes/Controller/SearchController.php
@@ -812,7 +812,7 @@ class SearchController extends \TYPO3\CMS\Extbase\Mvc\Controller\ActionControlle
$searchWords = substr($this->sword, 0, 200);
// Convert to UTF-8 + conv. entities (was also converted during indexing!)
$searchWords = $this->charsetConverter->conv($searchWords, $GLOBALS['TSFE']->metaCharset, 'utf-8');
- $searchWords = $this->charsetConverter->entities_to_utf8($searchWords, true);
+ $searchWords = $this->charsetConverter->entities_to_utf8($searchWords);
$sWordArray = false;
if ($hookObj = $this->hookRequest('getSearchWords')) {
$sWordArray = $hookObj->getSearchWords_splitSWords($searchWords, $defaultOperator);
diff --git a/typo3/sysext/indexed_search/Classes/Controller/SearchFormController.php b/typo3/sysext/indexed_search/Classes/Controller/SearchFormController.php
index 27afe22865c02278659b706b62a06f23014eda06..037c742988df8142e0cc23fb8ef91fdb42acca6f 100755
--- a/typo3/sysext/indexed_search/Classes/Controller/SearchFormController.php
+++ b/typo3/sysext/indexed_search/Classes/Controller/SearchFormController.php
@@ -434,7 +434,7 @@ class SearchFormController extends \TYPO3\CMS\Frontend\Plugin\AbstractPlugin
$inSW = substr($this->piVars['sword'], 0, 200);
// Convert to UTF-8 + conv. entities (was also converted during indexing!)
$inSW = $this->charsetConverter->conv($inSW, $this->frontendController->metaCharset, 'utf-8');
- $inSW = $this->charsetConverter->entities_to_utf8($inSW, true);
+ $inSW = $this->charsetConverter->entities_to_utf8($inSW);
$sWordArray = false;
if ($hookObj = $this->hookRequest('getSearchWords')) {
$sWordArray = $hookObj->getSearchWords_splitSWords($inSW, $defOp);
diff --git a/typo3/sysext/indexed_search/Classes/Indexer.php b/typo3/sysext/indexed_search/Classes/Indexer.php
index c82bd6f68dafee86a2cbc84e1799530e4b64e6c6..18f043190c3dd68735aaf283e368629bfedf3ec8 100644
--- a/typo3/sysext/indexed_search/Classes/Indexer.php
+++ b/typo3/sysext/indexed_search/Classes/Indexer.php
@@ -687,7 +687,7 @@ class Indexer
$content = $this->csObj->conv($content, $charset, 'utf-8');
}
// Convert entities, assuming document is now UTF-8:
- return $this->csObj->entities_to_utf8($content, true);
+ return $this->csObj->entities_to_utf8($content);
}
/**
@@ -1289,7 +1289,7 @@ class Indexer
$contentArr[$key] = $this->csObj->conv($contentArr[$key], $charset, 'utf-8');
}
// decode all numeric / html-entities in the string to real characters:
- $contentArr[$key] = $this->csObj->entities_to_utf8($contentArr[$key], true);
+ $contentArr[$key] = $this->csObj->entities_to_utf8($contentArr[$key]);
}
}
}