matecat / xliff-parser

src/XliffParser/AbstractXliffParser.php

Spacing +61 added lines, -61 removed lines

@@ -37,7 +37,7 @@ 
      * @param string|null          $xliffProprietary
      * @param LoggerInterface|null $logger
      */
-    public function __construct( $xliffVersion, $xliffProprietary = null, LoggerInterface $logger = null ) {
+    public function __construct($xliffVersion, $xliffProprietary = null, LoggerInterface $logger = null) {
         $this->xliffVersion     = $xliffVersion;
         $this->logger           = $logger;
         $this->xliffProprietary = $xliffProprietary;
@@ -47,7 +47,7 @@ 
      * @return string
      */
     protected function getTuTagName() {
-        return ( $this->xliffVersion === 1 ) ? 'trans-unit' : 'unit';
+        return ($this->xliffVersion === 1) ? 'trans-unit' : 'unit';
     }
 
     /**
@@ -55,7 +55,7 @@ 
      *
      * @return array
      */
-    abstract public function parse( DOMDocument $dom, $output = [] );
+    abstract public function parse(DOMDocument $dom, $output = []);
 
     /**
      * Extract trans-unit content from the current node
@@ -70,17 +70,17 @@ 
      * @param int          $recursionLevel
      *
      */
-    protected function extractTuFromNode( DOMNode $childNode, &$transUnitIdArrayForUniquenessCheck, DOMDocument $dom, &$output, &$i, &$j, $contextGroups = [], $recursionLevel = 0 ) {
+    protected function extractTuFromNode(DOMNode $childNode, &$transUnitIdArrayForUniquenessCheck, DOMDocument $dom, &$output, &$i, &$j, $contextGroups = [], $recursionLevel = 0) {
 
-        if ( $childNode->nodeType != XML_ELEMENT_NODE ) {
+        if ($childNode->nodeType != XML_ELEMENT_NODE) {
             return;
         }
 
-        if ( $childNode->nodeName === 'group' ) {
+        if ($childNode->nodeName === 'group') {
 
             // add nested context-groups
-            foreach ( $childNode->childNodes as $nestedChildNode ) {
-                if ( $nestedChildNode->nodeName === 'context-group' ) {
+            foreach ($childNode->childNodes as $nestedChildNode) {
+                if ($nestedChildNode->nodeName === 'context-group') {
                     $contextGroups[] = $nestedChildNode;
                 }
             }
@@ -88,23 +88,23 @@ 
             // avoid infinite recursion
             $recursionLevel++;
 
-            foreach ( $childNode->childNodes as $nestedChildNode ) {
+            foreach ($childNode->childNodes as $nestedChildNode) {
 
                 // nested groups
-                if ( $nestedChildNode->nodeName === 'group' ) {
+                if ($nestedChildNode->nodeName === 'group') {
 
-                    if ( $recursionLevel < self::MAX_GROUP_RECURSION_LEVEL ) {
-                        $this->extractTuFromNode( $nestedChildNode, $transUnitIdArrayForUniquenessCheck, $dom, $output, $i, $j, $contextGroups, $recursionLevel );
+                    if ($recursionLevel < self::MAX_GROUP_RECURSION_LEVEL) {
+                        $this->extractTuFromNode($nestedChildNode, $transUnitIdArrayForUniquenessCheck, $dom, $output, $i, $j, $contextGroups, $recursionLevel);
                     } else {
-                        throw new OverflowException( "Maximum tag group nesting level of '" . self::MAX_GROUP_RECURSION_LEVEL . "' reached, aborting!" );
+                        throw new OverflowException("Maximum tag group nesting level of '" . self::MAX_GROUP_RECURSION_LEVEL . "' reached, aborting!");
                     }
 
-                } elseif ( $nestedChildNode->nodeName === $this->getTuTagName() ) {
-                    $this->extractTransUnit( $nestedChildNode, $transUnitIdArrayForUniquenessCheck, $dom, $output, $i, $j, $contextGroups );
+                } elseif ($nestedChildNode->nodeName === $this->getTuTagName()) {
+                    $this->extractTransUnit($nestedChildNode, $transUnitIdArrayForUniquenessCheck, $dom, $output, $i, $j, $contextGroups);
                 }
             }
-        } elseif ( $childNode->nodeName === $this->getTuTagName() ) {
-            $this->extractTransUnit( $childNode, $transUnitIdArrayForUniquenessCheck, $dom, $output, $i, $j, $contextGroups );
+        } elseif ($childNode->nodeName === $this->getTuTagName()) {
+            $this->extractTransUnit($childNode, $transUnitIdArrayForUniquenessCheck, $dom, $output, $i, $j, $contextGroups);
         }
     }
 
@@ -121,7 +121,7 @@ 
      *
      * @return mixed
      */
-    abstract protected function extractTransUnit( DOMElement $transUnit, &$transUnitIdArrayForUniquenessCheck, $dom, &$output, &$i, &$j, $contextGroups = [] );
+    abstract protected function extractTransUnit(DOMElement $transUnit, &$transUnitIdArrayForUniquenessCheck, $dom, &$output, &$i, &$j, $contextGroups = []);
 
     /**
      * @param DOMDocument $dom
@@ -129,10 +129,10 @@ 
      *
      * @return array
      */
-    protected function extractContent( DOMDocument $dom, DOMNode $node ) {
+    protected function extractContent(DOMDocument $dom, DOMNode $node) {
         return [
-                'raw-content' => $this->extractTagContent( $dom, $node ),
-                'attr'        => $this->extractTagAttributes( $node )
+                'raw-content' => $this->extractTagContent($dom, $node),
+                'attr'        => $this->extractTagAttributes($node)
         ];
     }
 
@@ -149,12 +149,12 @@ 
      *
      * @return array
      */
-    protected function extractTagAttributes( DOMNode $element ) {
+    protected function extractTagAttributes(DOMNode $element) {
         $tagAttributes = [];
 
-        if ( $element->hasAttributes() ) {
-            foreach ( $element->attributes as $attr ) {
-                $tagAttributes[ $attr->nodeName ] = $attr->nodeValue;
+        if ($element->hasAttributes()) {
+            foreach ($element->attributes as $attr) {
+                $tagAttributes[$attr->nodeName] = $attr->nodeValue;
             }
         }
 
@@ -169,17 +169,17 @@ 
      *
      * @return string
      */
-    protected function extractTagContent( DOMDocument $dom, DOMNode $element ) {
+    protected function extractTagContent(DOMDocument $dom, DOMNode $element) {
         $childNodes       = $element->hasChildNodes();
         $extractedContent = '';
 
-        if ( !empty( $childNodes ) ) {
-            foreach ( $element->childNodes as $node ) {
-                $extractedContent .= Emoji::toEntity( Strings::fixNonWellFormedXml( $dom->saveXML( $node ) ) );
+        if (!empty($childNodes)) {
+            foreach ($element->childNodes as $node) {
+                $extractedContent .= Emoji::toEntity(Strings::fixNonWellFormedXml($dom->saveXML($node)));
             }
         }
 
-        return str_replace( Placeholder::EMPTY_TAG_PLACEHOLDER, '', $extractedContent );
+        return str_replace(Placeholder::EMPTY_TAG_PLACEHOLDER, '', $extractedContent);
     }
 
     /**
@@ -190,45 +190,45 @@ 
      *
      * @return array
      */
-    protected function extractContentWithMarksAndExtTags( DOMDocument $dom, DOMElement $childNode ) {
+    protected function extractContentWithMarksAndExtTags(DOMDocument $dom, DOMElement $childNode) {
         $source = [];
 
         // example:
         // <g id="1"><mrk mid="0" mtype="seg">An English string with g tags</mrk></g>
-        $raw = $this->extractTagContent( $dom, $childNode );
+        $raw = $this->extractTagContent($dom, $childNode);
 
-        $markers = preg_split( '#<mrk\s#si', $raw, -1 );
+        $markers = preg_split('#<mrk\s#si', $raw, -1);
 
         $mi = 0;
-        while ( isset( $markers[ $mi + 1 ] ) ) {
-            unset( $mid );
+        while (isset($markers[$mi + 1])) {
+            unset($mid);
 
-            preg_match( '|mid\s?=\s?["\'](.*?)["\']|si', $markers[ $mi + 1 ], $mid );
+            preg_match('|mid\s?=\s?["\'](.*?)["\']|si', $markers[$mi + 1], $mid);
 
             // if it's a Trados file the trailing spaces after </mrk> are meaningful
             // so we add them to
             $trailingSpaces = '';
-            if ( $this->xliffProprietary === 'trados' ) {
-                preg_match_all( '/<\/mrk>[\s]+/iu', $markers[ $mi + 1 ], $trailingSpacesMatches );
+            if ($this->xliffProprietary === 'trados') {
+                preg_match_all('/<\/mrk>[\s]+/iu', $markers[$mi + 1], $trailingSpacesMatches);
 
-                if ( isset( $trailingSpacesMatches[ 0 ] ) && count( $trailingSpacesMatches[ 0 ] ) > 0 ) {
-                    foreach ( $trailingSpacesMatches[ 0 ] as $match ) {
-                        $trailingSpaces = str_replace( '</mrk>', '', $match );
+                if (isset($trailingSpacesMatches[0]) && count($trailingSpacesMatches[0]) > 0) {
+                    foreach ($trailingSpacesMatches[0] as $match) {
+                        $trailingSpaces = str_replace('</mrk>', '', $match);
                     }
                 }
             }
 
             //re-build the mrk tag after the split
-            $originalMark = trim( '<mrk ' . $markers[ $mi + 1 ] );
+            $originalMark = trim('<mrk ' . $markers[$mi + 1]);
 
-            $mark_string  = preg_replace( '#^<mrk\s[^>]+>(.*)#', '$1', $originalMark ); // at this point we have: ---> 'Test </mrk> </g>>'
-            $mark_content = preg_split( '#</mrk>#si', $mark_string );
+            $mark_string  = preg_replace('#^<mrk\s[^>]+>(.*)#', '$1', $originalMark); // at this point we have: ---> 'Test </mrk> </g>>'
+            $mark_content = preg_split('#</mrk>#si', $mark_string);
 
             $sourceArray = [
-                    'mid'           => ( isset( $mid[ 1 ] ) ) ? $mid[ 1 ] : $mi,
-                    'ext-prec-tags' => ( $mi == 0 ? $markers[ 0 ] : "" ),
-                    'raw-content'   => ( isset( $mark_content[ 0 ] ) ) ? $mark_content[ 0 ] . $trailingSpaces : '',
-                    'ext-succ-tags' => ( isset( $mark_content[ 1 ] ) ) ? $mark_content[ 1 ] : '',
+                    'mid'           => (isset($mid[1])) ? $mid[1] : $mi,
+                    'ext-prec-tags' => ($mi == 0 ? $markers[0] : ""),
+                    'raw-content'   => (isset($mark_content[0])) ? $mark_content[0] . $trailingSpaces : '',
+                    'ext-succ-tags' => (isset($mark_content[1])) ? $mark_content[1] : '',
             ];
 
             $source[] = $sourceArray;
@@ -244,12 +244,12 @@ 
      *
      * @return array
      */
-    protected function getDataRefMap( $originalData ) {
+    protected function getDataRefMap($originalData) {
         // dataRef map
         $dataRefMap = [];
-        foreach ( $originalData as $datum ) {
-            if ( isset( $datum[ 'attr' ][ 'id' ] ) ) {
-                $dataRefMap[ $datum[ 'attr' ][ 'id' ] ] = $datum[ 'raw-content' ];
+        foreach ($originalData as $datum) {
+            if (isset($datum['attr']['id'])) {
+                $dataRefMap[$datum['attr']['id']] = $datum['raw-content'];
             }
         }
 
@@ -261,10 +261,10 @@ 
      *
      * @return bool
      */
-    protected function stringContainsMarks( $raw ) {
-        $markers = preg_split( '#<mrk\s#si', $raw, -1 );
+    protected function stringContainsMarks($raw) {
+        $markers = preg_split('#<mrk\s#si', $raw, -1);
 
-        return isset( $markers[ 1 ] );
+        return isset($markers[1]);
     }
 
     /**
@@ -274,7 +274,7 @@ 
      * @return array
      * @throws \Exception
      */
-    protected function JSONOrRawContentArray( $noteValue, $escapeStrings = true ) {
+    protected function JSONOrRawContentArray($noteValue, $escapeStrings = true) {
         //
         // convert double escaped entites
         //
@@ -284,17 +284,17 @@ 
         // &amp;amp; ---> &amp;
         // &amp;apos ---> &apos;
         //
-        if ( Strings::isADoubleEscapedEntity( $noteValue ) ) {
-            $noteValue = Strings::htmlspecialchars_decode( $noteValue, true );
+        if (Strings::isADoubleEscapedEntity($noteValue)) {
+            $noteValue = Strings::htmlspecialchars_decode($noteValue, true);
         } else {
             // for non escaped entities $escapeStrings is always true for security reasons
             $escapeStrings = true;
         }
 
-        if ( Strings::isJSON( $noteValue ) ) {
-            return [ 'json' => Strings::cleanCDATA( $noteValue ) ];
+        if (Strings::isJSON($noteValue)) {
+            return ['json' => Strings::cleanCDATA($noteValue)];
         }
 
-        return [ 'raw-content' => Strings::fixNonWellFormedXml( $noteValue, $escapeStrings ) ];
+        return ['raw-content' => Strings::fixNonWellFormedXml($noteValue, $escapeStrings)];
     }
 }