matecat / subfiltering

src/Filters/XmlToPh.php

Spacing +22 added lines, -22 removed lines

@@ -38,7 +38,7 @@ 
      *
      * @return string The original buffer.
      */
-    protected function _finalizePlainText( string $buffer ): string {
+    protected function _finalizePlainText(string $buffer): string {
         return $buffer;
     }
 
@@ -53,18 +53,18 @@ 
      *
      * @return string The generated <ph> placeholder tag.
      */
-    protected function _finalizeMarkupTag( string $buffer ): string {
+    protected function _finalizeMarkupTag(string $buffer): string {
         // Decode attributes by locking < and > first
         // Because a HTML tag has it's attributes encoded and here we get lt and gt decoded but not other parts of the string
         // Ex:
         // incoming string: <a href="/users/settings?test=123&amp;amp;foobar=1" target="_blank">
         // this should be: <a href="/users/settings?test=123&amp;foobar=1" target="_blank"> with only one ampersand encoding
         //
-        $buffer = str_replace( [ '<', '>' ], [ '#_lt_#', '#_gt_#' ], $buffer );
-        $buffer = html_entity_decode( $buffer, ENT_NOQUOTES | 16 /* ENT_XML1 */, 'UTF-8' );
-        $buffer = str_replace( [ '#_lt_#', '#_gt_#' ], [ '<', '>' ], $buffer );
+        $buffer = str_replace(['<', '>'], ['#_lt_#', '#_gt_#'], $buffer);
+        $buffer = html_entity_decode($buffer, ENT_NOQUOTES | 16 /* ENT_XML1 */, 'UTF-8');
+        $buffer = str_replace(['#_lt_#', '#_gt_#'], ['<', '>'], $buffer);
 
-        return $this->_finalizeTag( $buffer );
+        return $this->_finalizeTag($buffer);
 
     }
 
@@ -76,8 +76,8 @@ 
      *
      * @return string The resulting <ph> tag.
      */
-    protected function _finalizeTag( string $buffer ): string {
-        return '<ph id="' . $this->getPipeline()->getNextId() . '" ctype="' . ( $this->isHTML ? CTypeEnum::HTML : CTypeEnum::XML ) . '" equiv-text="base64:' . base64_encode( htmlentities( $buffer, ENT_NOQUOTES | 16 /* ENT_XML1 */ ) ) . '"/>';
+    protected function _finalizeTag(string $buffer): string {
+        return '<ph id="'.$this->getPipeline()->getNextId().'" ctype="'.($this->isHTML ? CTypeEnum::HTML : CTypeEnum::XML).'" equiv-text="base64:'.base64_encode(htmlentities($buffer, ENT_NOQUOTES | 16 /* ENT_XML1 */)).'"/>';
     }
 
     /**
@@ -87,10 +87,10 @@ 
      *
      * @return string The fixed string with escaped angle brackets.
      */
-    protected function _fixWrongBuffer( string $buffer ): string {
-        $buffer = str_replace( "<", "&lt;", $buffer );
+    protected function _fixWrongBuffer(string $buffer): string {
+        $buffer = str_replace("<", "&lt;", $buffer);
 
-        return str_replace( ">", "&gt;", $buffer );
+        return str_replace(">", "&gt;", $buffer);
     }
 
     /**
@@ -100,8 +100,8 @@ 
      *
      * @return string The generated <ph> placeholder tag.
      */
-    protected function _finalizeScriptTag( string $buffer ): string {
-        return $this->_finalizeTag( $buffer );
+    protected function _finalizeScriptTag(string $buffer): string {
+        return $this->_finalizeTag($buffer);
     }
 
     /**
@@ -118,7 +118,7 @@ 
      *
      * @return bool True if the buffer is a valid tag, false otherwise.
      */
-    protected function _isTagValid( string $buffer ): bool {
+    protected function _isTagValid(string $buffer): bool {
 
         // This is a safeguard against misinterpreting partially processed strings.
         // During filtering, inner tags might be replaced by placeholders (e.g., ##LESSTHAN##).
@@ -126,7 +126,7 @@ 
         // content is not yet restored, so we must not treat it as a valid, final tag.
         // For example, an original string like '&lt;a href="<x/>"&gt;' could become
         // '<a href="##LESSTHAN##x/##GREATERTHAN##">', which should not be converted to a <ph> tag.
-        if ( strpos( $buffer, ConstantEnum::LTPLACEHOLDER ) !== false || strpos( $buffer, ConstantEnum::GTPLACEHOLDER ) !== false ) {
+        if (strpos($buffer, ConstantEnum::LTPLACEHOLDER) !== false || strpos($buffer, ConstantEnum::GTPLACEHOLDER) !== false) {
             return false;
         }
 
@@ -143,7 +143,7 @@ 
         // This regex validates the general structure of an XML/HTML tag.
         // It checks for a valid tag name (not starting with a number), optional attributes
         // (with quoted or unquoted values), and correct opening/closing brackets.
-        if ( preg_match( '#</?(?![0-9]+)[a-z0-9\-._:]+?(?:\s+[:a-z0-9\-._]+(?:=(?:"[^"]*"|\'[^\']*\'|[^\s>]+))?)*\s*/?>#ui', $buffer ) ) {
+        if (preg_match('#</?(?![0-9]+)[a-z0-9\-._:]+?(?:\s+[:a-z0-9\-._]+(?:=(?:"[^"]*"|\'[^\']*\'|[^\s>]+))?)*\s*/?>#ui', $buffer)) {
 
             /**
              * HTML5 Tag Matcher and Global Attribute Parser
@@ -180,7 +180,7 @@ 
              * - This regex is intended for validation and parsing in contexts that allow Unicode and extended characters.
              * - For `dataset` access in JavaScript, `getAttribute` is recommended for attributes with non-ASCII names.
              */
-            if ( preg_match( '#<\s*/?\s*(?:html|head|body|header|footer|main|section|article|nav|aside|h1|h2|h3|h4|h5|h6|p|hr|pre|blockquote|ol|ul|li|dl|dt|dd|figure|figcaption|div|a|em|strong|small|s|cite|q|dfn|abbr|ruby|rt|rp|data|time|code|var|samp|kbd|sub|sup|i|b|u|mark|bdi|bdo|span|br|wbr|form|label|input|button|select|datalist|optgroup|option|textarea|output|fieldset|legend|meter|progress|img|audio|video|source|track|picture|map|area|iframe|embed|object|param|table|caption|colgroup|col|tbody|thead|tfoot|tr|td|th|script|noscript|template|canvas|link|style|meta|base|title|details|summary|dialog|menu|menuitem|slot|portal)\b(?:\s+(?:accesskey|class|contenteditable|data-[^\s=]+|dir|draggable|enterkeyhint|hidden|id|inert|inputmode|lang|popover|spellcheck|style|tabindex|title|translate|xml:lang|xml:base|role|aria-[^\s=]+|on\w+)(?:=(?:"[^"]*"|\'[^\']*\'|[^\s>]+))?)*\s*/?\s*>#ui', $buffer ) ) {
+            if (preg_match('#<\s*/?\s*(?:html|head|body|header|footer|main|section|article|nav|aside|h1|h2|h3|h4|h5|h6|p|hr|pre|blockquote|ol|ul|li|dl|dt|dd|figure|figcaption|div|a|em|strong|small|s|cite|q|dfn|abbr|ruby|rt|rp|data|time|code|var|samp|kbd|sub|sup|i|b|u|mark|bdi|bdo|span|br|wbr|form|label|input|button|select|datalist|optgroup|option|textarea|output|fieldset|legend|meter|progress|img|audio|video|source|track|picture|map|area|iframe|embed|object|param|table|caption|colgroup|col|tbody|thead|tfoot|tr|td|th|script|noscript|template|canvas|link|style|meta|base|title|details|summary|dialog|menu|menuitem|slot|portal)\b(?:\s+(?:accesskey|class|contenteditable|data-[^\s=]+|dir|draggable|enterkeyhint|hidden|id|inert|inputmode|lang|popover|spellcheck|style|tabindex|title|translate|xml:lang|xml:base|role|aria-[^\s=]+|on\w+)(?:=(?:"[^"]*"|\'[^\']*\'|[^\s>]+))?)*\s*/?\s*>#ui', $buffer)) {
                 $this->isHTML = true;
             }
 
@@ -201,16 +201,16 @@ 
      *
      * @return string The transformed segment.
      */
-    public function transform( string $segment ): string {
+    public function transform(string $segment): string {
 
         // restore < e >
-        $segment = str_replace( "&lt;", "<", $segment );
-        $segment = str_replace( "&gt;", ">", $segment );
+        $segment = str_replace("&lt;", "<", $segment);
+        $segment = str_replace("&gt;", ">", $segment);
 
         $parser = new HtmlParser();
-        $parser->registerCallbacksHandler( $this );
+        $parser->registerCallbacksHandler($this);
 
-        return $parser->transform( $segment );
+        return $parser->transform($segment);
     }
 
 }
\ No newline at end of file

src/AbstractFilter.php

Spacing +27 added lines, -27 removed lines

@@ -87,7 +87,7 @@ 
      *
      * @return AbstractFilter The configured instance of the filter.
      */
-    public static function getInstance( FeatureSetInterface $featureSet, ?string $source = null, ?string $target = null, ?array $dataRefMap = [], ?array $handlerClassNamesForLayer0ToLayer1Transition = [] ): ?AbstractFilter {
+    public static function getInstance(FeatureSetInterface $featureSet, ?string $source = null, ?string $target = null, ?array $dataRefMap = [], ?array $handlerClassNamesForLayer0ToLayer1Transition = []): ?AbstractFilter {
         // Create a new instance of the specific filter class (e.g., MateCatFilter).
         $newInstance = new static();
 
@@ -99,17 +99,17 @@ 
         $newInstance->dataRefMap = $dataRefMap ?? [];
 
         // Determine which handlers to use for the Layer 0 to Layer 1 transition.
-        if ( is_array( $handlerClassNamesForLayer0ToLayer1Transition ) && empty( $handlerClassNamesForLayer0ToLayer1Transition ) ) {
+        if (is_array($handlerClassNamesForLayer0ToLayer1Transition) && empty($handlerClassNamesForLayer0ToLayer1Transition)) {
             // If an empty array is passed, load the default set of handlers from the sorter.
-            $handlerClassNamesForLayer0ToLayer1Transition = array_keys( HandlersSorter::getDefaultInjectedHandlers() );
-        } elseif ( is_null( $handlerClassNamesForLayer0ToLayer1Transition ) ) {
+            $handlerClassNamesForLayer0ToLayer1Transition = array_keys(HandlersSorter::getDefaultInjectedHandlers());
+        } elseif (is_null($handlerClassNamesForLayer0ToLayer1Transition)) {
             // If null is passed, use no handlers.
             $handlerClassNamesForLayer0ToLayer1Transition = [];
         }
         // Otherwise, use the custom list of handlers provided.
 
         // Sort the dynamic feature-based handlers.
-        $sorter                                                  = new HandlersSorter( $handlerClassNamesForLayer0ToLayer1Transition );
+        $sorter                                                  = new HandlersSorter($handlerClassNamesForLayer0ToLayer1Transition);
         $newInstance->orderedHandlersForLayer0ToLayer1Transition = $sorter->getOrderedHandlersClassNames();
 
         // Return the fully configured filter instance.
@@ -127,26 +127,26 @@ 
      * @return string The transformed segment in Layer 0 format.
      * @throws Exception If any handler in the pipeline fails.
      */
-    public function fromLayer1ToLayer0( string $segment ): string {
+    public function fromLayer1ToLayer0(string $segment): string {
         // Initialize a new pipeline for this transformation.
-        $channel = new Pipeline( $this->source, $this->target, $this->dataRefMap );
+        $channel = new Pipeline($this->source, $this->target, $this->dataRefMap);
 
         // Add handlers to reverse the sub-filtering process.
-        $channel->addLast( MateCatCustomPHToOriginalValue::class ); // Restore original PH values
-        $channel->addLast( PlaceHoldXliffTags::class );             // Isolate XLIFF tags
-        $channel->addLast( EncodeToRawXML::class );                 // Encode for raw XML storage
-        $channel->addLast( LtGtEncode::class );                     // Encode '<' and '>'
-        $channel->addLast( RestoreXliffTagsContent::class );        // Restore original XLIFF content
-        $channel->addLast( RestorePlaceHoldersToXLIFFLtGt::class ); // Restore placeholders for '<' and '>'
-        $channel->addLast( SplitPlaceholder::class );               // Handle split placeholders
-        $channel->addLast( RestoreEquivText::class );               // Restore equiv-text content
+        $channel->addLast(MateCatCustomPHToOriginalValue::class); // Restore original PH values
+        $channel->addLast(PlaceHoldXliffTags::class); // Isolate XLIFF tags
+        $channel->addLast(EncodeToRawXML::class); // Encode for raw XML storage
+        $channel->addLast(LtGtEncode::class); // Encode '<' and '>'
+        $channel->addLast(RestoreXliffTagsContent::class); // Restore original XLIFF content
+        $channel->addLast(RestorePlaceHoldersToXLIFFLtGt::class); // Restore placeholders for '<' and '>'
+        $channel->addLast(SplitPlaceholder::class); // Handle split placeholders
+        $channel->addLast(RestoreEquivText::class); // Restore equiv-text content
 
         // Allow the current feature set to modify the pipeline (e.g., add or remove handlers).
         /** @var $channel Pipeline */
-        $channel = $this->featureSet->filter( 'fromLayer1ToLayer0', $channel );
+        $channel = $this->featureSet->filter('fromLayer1ToLayer0', $channel);
 
         // Process the segment through the pipeline and return the result.
-        return $channel->transform( $segment );
+        return $channel->transform($segment);
     }
 
 
@@ -162,7 +162,7 @@ 
      *
      * @return string The transformed segment after processing from Layer 0 to Layer 1.
      */
-    public abstract function fromLayer0ToLayer1( string $segment, ?string $cid = null ): string;
+    public abstract function fromLayer0ToLayer1(string $segment, ?string $cid = null): string;
 
     /**
      * Configures the pipeline for transforming content from Layer 0 to Layer 1.
@@ -177,23 +177,23 @@ 
      * @param Pipeline    $channel
      * @param string|null $cid
      */
-    protected function configureFromLayer0ToLayer1Pipeline( Pipeline $channel, ?string $cid = null ): void {
+    protected function configureFromLayer0ToLayer1Pipeline(Pipeline $channel, ?string $cid = null): void {
 
         // Add initial handlers for standard XLIFF and placeholder normalization.
-        $channel->addLast( StandardPHToMateCatCustomPH::class );
-        $channel->addLast( StandardXEquivTextToMateCatCustomPH::class );
-        $channel->addLast( PlaceHoldXliffTags::class );
+        $channel->addLast(StandardPHToMateCatCustomPH::class);
+        $channel->addLast(StandardXEquivTextToMateCatCustomPH::class);
+        $channel->addLast(PlaceHoldXliffTags::class);
 //        $channel->addLast( LtGtDecode::class );
 
         // Add the dynamic feature-based handlers.
-        foreach ( $this->orderedHandlersForLayer0ToLayer1Transition as $handler ) {
-            $channel->addLast( $handler );
+        foreach ($this->orderedHandlersForLayer0ToLayer1Transition as $handler) {
+            $channel->addLast($handler);
         }
 
         // Add final handlers to restore XLIFF content and encode for the target layer.
-        $channel->addLast( RestoreXliffTagsContent::class );
-        $channel->addLast( RestorePlaceHoldersToXLIFFLtGt::class );
-        $channel->addLast( EquivTextToBase64::class );
+        $channel->addLast(RestoreXliffTagsContent::class);
+        $channel->addLast(RestorePlaceHoldersToXLIFFLtGt::class);
+        $channel->addLast(EquivTextToBase64::class);
 
     }