@@ -53,7 +53,7 @@ |
||
| 53 | 53 | self::STATUS_REBUTTED |
| 54 | 54 | ]; |
| 55 | 55 | |
| 56 | - public static function isReviewedStatus( $status ) { |
|
| 57 | - return in_array( $status, TranslationStatus::$REVISION_STATUSES ); |
|
| 56 | + public static function isReviewedStatus($status) { |
|
| 57 | + return in_array($status, TranslationStatus::$REVISION_STATUSES); |
|
| 58 | 58 | } |
| 59 | 59 | } |
@@ -50,11 +50,11 @@ discard block |
||
| 50 | 50 | * |
| 51 | 51 | * @return array |
| 52 | 52 | */ |
| 53 | - private static function getInfoFromTmp( $tmp) |
|
| 53 | + private static function getInfoFromTmp($tmp) |
|
| 54 | 54 | { |
| 55 | 55 | try { |
| 56 | 56 | self::checkVersion($tmp); |
| 57 | - } catch ( Exception $ignore) { |
|
| 57 | + } catch (Exception $ignore) { |
|
| 58 | 58 | // do nothing |
| 59 | 59 | // self::$fileType[ 'version' ] is left empty |
| 60 | 60 | } |
@@ -62,10 +62,10 @@ discard block |
||
| 62 | 62 | // run CheckXliffProprietaryPipeline |
| 63 | 63 | $pipeline = self::runPipeline($tmp); |
| 64 | 64 | |
| 65 | - self::$fileType['proprietary' ] = $pipeline['proprietary' ]; |
|
| 66 | - self::$fileType[ 'proprietary_name' ] = $pipeline['proprietary_name' ]; |
|
| 67 | - self::$fileType[ 'proprietary_short_name' ] = $pipeline['proprietary_short_name' ]; |
|
| 68 | - self::$fileType[ 'converter_version' ] = $pipeline['converter_version' ]; |
|
| 65 | + self::$fileType['proprietary'] = $pipeline['proprietary']; |
|
| 66 | + self::$fileType['proprietary_name'] = $pipeline['proprietary_name']; |
|
| 67 | + self::$fileType['proprietary_short_name'] = $pipeline['proprietary_short_name']; |
|
| 68 | + self::$fileType['converter_version'] = $pipeline['converter_version']; |
|
| 69 | 69 | |
| 70 | 70 | return self::$fileType; |
| 71 | 71 | } |
@@ -128,7 +128,7 @@ discard block |
||
| 128 | 128 | } |
| 129 | 129 | |
| 130 | 130 | if (!empty($stringData)) { |
| 131 | - return array( $stringData ); |
|
| 131 | + return array($stringData); |
|
| 132 | 132 | } |
| 133 | 133 | |
| 134 | 134 | return false; |
@@ -142,8 +142,8 @@ discard block |
||
| 142 | 142 | */ |
| 143 | 143 | protected static function checkVersion($tmp) |
| 144 | 144 | { |
| 145 | - if (isset($tmp[ 0 ])) { |
|
| 146 | - self::$fileType[ 'version' ] = XliffVersionDetector::detect($tmp[ 0 ]); |
|
| 145 | + if (isset($tmp[0])) { |
|
| 146 | + self::$fileType['version'] = XliffVersionDetector::detect($tmp[0]); |
|
| 147 | 147 | } |
| 148 | 148 | } |
| 149 | 149 | |
@@ -165,10 +165,10 @@ discard block |
||
| 165 | 165 | // run CheckXliffProprietaryPipeline |
| 166 | 166 | $pipeline = self::runPipeline($tmp); |
| 167 | 167 | |
| 168 | - self::$fileType['proprietary' ] = $pipeline['proprietary' ]; |
|
| 169 | - self::$fileType[ 'proprietary_name' ] = $pipeline['proprietary_name' ]; |
|
| 170 | - self::$fileType[ 'proprietary_short_name' ] = $pipeline['proprietary_short_name' ]; |
|
| 171 | - self::$fileType[ 'converter_version' ] = $pipeline['converter_version' ]; |
|
| 168 | + self::$fileType['proprietary'] = $pipeline['proprietary']; |
|
| 169 | + self::$fileType['proprietary_name'] = $pipeline['proprietary_name']; |
|
| 170 | + self::$fileType['proprietary_short_name'] = $pipeline['proprietary_short_name']; |
|
| 171 | + self::$fileType['converter_version'] = $pipeline['converter_version']; |
|
| 172 | 172 | |
| 173 | 173 | return self::$fileType; |
| 174 | 174 | } |
@@ -197,7 +197,7 @@ discard block |
||
| 197 | 197 | |
| 198 | 198 | //if file is not proprietary AND Enforce is disabled |
| 199 | 199 | //we take it as is |
| 200 | - if (!$fileType[ 'proprietary' ] || $memoryFileType) { |
|
| 200 | + if (!$fileType['proprietary'] || $memoryFileType) { |
|
| 201 | 201 | $convert = false; |
| 202 | 202 | //ok don't convert a standard sdlxliff |
| 203 | 203 | } |
@@ -205,16 +205,16 @@ discard block |
||
| 205 | 205 | //if conversion enforce is active |
| 206 | 206 | //we force all xliff files but not files produced by SDL Studio because we can handle them |
| 207 | 207 | if ( |
| 208 | - $fileType[ 'proprietary_short_name' ] == 'matecat_converter' |
|
| 209 | - || $fileType[ 'proprietary_short_name' ] == 'trados' |
|
| 210 | - || $fileType[ 'proprietary_short_name' ] == 'xliff_v2' |
|
| 208 | + $fileType['proprietary_short_name'] == 'matecat_converter' |
|
| 209 | + || $fileType['proprietary_short_name'] == 'trados' |
|
| 210 | + || $fileType['proprietary_short_name'] == 'xliff_v2' |
|
| 211 | 211 | || $memoryFileType |
| 212 | 212 | ) { |
| 213 | 213 | $convert = false; |
| 214 | 214 | //ok don't convert a standard sdlxliff |
| 215 | 215 | } |
| 216 | 216 | } |
| 217 | - } elseif ($fileType[ 'proprietary' ]) { |
|
| 217 | + } elseif ($fileType['proprietary']) { |
|
| 218 | 218 | |
| 219 | 219 | /** |
| 220 | 220 | * Application misconfiguration. |
@@ -224,7 +224,7 @@ discard block |
||
| 224 | 224 | |
| 225 | 225 | $convert = -1; |
| 226 | 226 | //stop execution |
| 227 | - } elseif (!$fileType[ 'proprietary' ]) { |
|
| 227 | + } elseif (!$fileType['proprietary']) { |
|
| 228 | 228 | $convert = false; |
| 229 | 229 | //ok don't convert a standard sdlxliff |
| 230 | 230 | } |
@@ -13,7 +13,7 @@ discard block |
||
| 13 | 13 | { |
| 14 | 14 | $fileType = []; |
| 15 | 15 | |
| 16 | - if (isset($tmp[ 0 ])) { |
|
| 16 | + if (isset($tmp[0])) { |
|
| 17 | 17 | preg_match('|<xliff.*?\sversion\s?=\s?["\'](.*?)["\']|si', substr($tmp[0], 0, 1000), $versionMatches); |
| 18 | 18 | preg_match('|<xliff.*?\sxmlns\s?=\s?["\']urn:oasis:names:tc:xliff:document:(.*?)["\']|si', substr($tmp[0], 0, 1000), $xmlnsMatches); |
| 19 | 19 | |
@@ -22,10 +22,10 @@ discard block |
||
| 22 | 22 | $xmlns = $xmlnsMatches[1]; |
| 23 | 23 | |
| 24 | 24 | if ($version === $xmlns && $version >= 2) { |
| 25 | - $fileType[ 'proprietary' ] = false; |
|
| 26 | - $fileType[ 'proprietary_name' ] = 'Xliff v'.$version.' File'; |
|
| 27 | - $fileType[ 'proprietary_short_name' ] = 'xliff_v2'; |
|
| 28 | - $fileType[ 'converter_version' ] = '2.0'; |
|
| 25 | + $fileType['proprietary'] = false; |
|
| 26 | + $fileType['proprietary_name'] = 'Xliff v' . $version . ' File'; |
|
| 27 | + $fileType['proprietary_short_name'] = 'xliff_v2'; |
|
| 28 | + $fileType['converter_version'] = '2.0'; |
|
| 29 | 29 | |
| 30 | 30 | return $fileType; |
| 31 | 31 | } |
@@ -16,7 +16,7 @@ discard block |
||
| 16 | 16 | * |
| 17 | 17 | * @param array $map |
| 18 | 18 | */ |
| 19 | - public function __construct( array $map ) { |
|
| 19 | + public function __construct(array $map) { |
|
| 20 | 20 | $this->map = $map; |
| 21 | 21 | } |
| 22 | 22 | |
@@ -31,38 +31,38 @@ discard block |
||
| 31 | 31 | * |
| 32 | 32 | * @return string |
| 33 | 33 | */ |
| 34 | - public function replace( $string ) { |
|
| 34 | + public function replace($string) { |
|
| 35 | 35 | // if map is empty |
| 36 | 36 | // or the string has not a dataRef attribute |
| 37 | 37 | // return string as is |
| 38 | - if ( empty( $this->map ) || !$this->hasAnyDataRefAttribute( $string ) ) { |
|
| 38 | + if (empty($this->map) || !$this->hasAnyDataRefAttribute($string)) { |
|
| 39 | 39 | return $string; |
| 40 | 40 | } |
| 41 | 41 | |
| 42 | 42 | // (recursively) clean string from equiv-text eventually present |
| 43 | - $string = $this->cleanFromEquivText( $string ); |
|
| 43 | + $string = $this->cleanFromEquivText($string); |
|
| 44 | 44 | |
| 45 | - $html = HtmlParser::parse( $string ); |
|
| 45 | + $html = HtmlParser::parse($string); |
|
| 46 | 46 | |
| 47 | 47 | // 1. Replace <ph>|<sc>|<ec> tags |
| 48 | - foreach ( $html as $node ) { |
|
| 49 | - $string = $this->recursiveAddEquivTextToPhTag( $node, $string ); |
|
| 48 | + foreach ($html as $node) { |
|
| 49 | + $string = $this->recursiveAddEquivTextToPhTag($node, $string); |
|
| 50 | 50 | } |
| 51 | 51 | |
| 52 | 52 | // 2. Replace <pc> tags |
| 53 | - $toBeEscaped = Strings::isAnEscapedHTML( $string ); |
|
| 53 | + $toBeEscaped = Strings::isAnEscapedHTML($string); |
|
| 54 | 54 | |
| 55 | - if ( $this->stringContainsPcTags( $string, $toBeEscaped ) ) { |
|
| 55 | + if ($this->stringContainsPcTags($string, $toBeEscaped)) { |
|
| 56 | 56 | |
| 57 | 57 | // replace self-closed <pc /> |
| 58 | - $string = $this->replaceSelfClosedPcTags( $string, $toBeEscaped ); |
|
| 58 | + $string = $this->replaceSelfClosedPcTags($string, $toBeEscaped); |
|
| 59 | 59 | |
| 60 | 60 | // create a dataRefEnd map |
| 61 | 61 | // (needed for correct handling of </pc> closing tags) |
| 62 | - $dataRefEndMap = $this->buildDataRefEndMap( $html ); |
|
| 63 | - $string = $this->replaceOpeningPcTags( $string, $toBeEscaped ); |
|
| 64 | - $string = $this->replaceClosingPcTags( $string, $toBeEscaped, $dataRefEndMap ); |
|
| 65 | - $string = ( $toBeEscaped ) ? Strings::escapeOnlyHTMLTags( $string ) : $string; |
|
| 62 | + $dataRefEndMap = $this->buildDataRefEndMap($html); |
|
| 63 | + $string = $this->replaceOpeningPcTags($string, $toBeEscaped); |
|
| 64 | + $string = $this->replaceClosingPcTags($string, $toBeEscaped, $dataRefEndMap); |
|
| 65 | + $string = ($toBeEscaped) ? Strings::escapeOnlyHTMLTags($string) : $string; |
|
| 66 | 66 | } |
| 67 | 67 | |
| 68 | 68 | return $string; |
@@ -73,17 +73,17 @@ discard block |
||
| 73 | 73 | * |
| 74 | 74 | * @return bool |
| 75 | 75 | */ |
| 76 | - private function hasAnyDataRefAttribute( $string ) { |
|
| 76 | + private function hasAnyDataRefAttribute($string) { |
|
| 77 | 77 | $dataRefTags = [ |
| 78 | 78 | 'dataRef', |
| 79 | 79 | 'dataRefStart', |
| 80 | 80 | 'dataRefEnd', |
| 81 | 81 | ]; |
| 82 | 82 | |
| 83 | - foreach ( $dataRefTags as $tag ) { |
|
| 84 | - preg_match( '/ ' . $tag . '=[\\\\"](.*?)[\\\\"]/', $string, $matches ); |
|
| 83 | + foreach ($dataRefTags as $tag) { |
|
| 84 | + preg_match('/ ' . $tag . '=[\\\\"](.*?)[\\\\"]/', $string, $matches); |
|
| 85 | 85 | |
| 86 | - if ( count( $matches ) > 0 ) { |
|
| 86 | + if (count($matches) > 0) { |
|
| 87 | 87 | return true; |
| 88 | 88 | } |
| 89 | 89 | } |
@@ -94,11 +94,11 @@ discard block |
||
| 94 | 94 | * |
| 95 | 95 | * @return string |
| 96 | 96 | */ |
| 97 | - private function cleanFromEquivText( $string ) { |
|
| 98 | - $html = HtmlParser::parse( $string ); |
|
| 97 | + private function cleanFromEquivText($string) { |
|
| 98 | + $html = HtmlParser::parse($string); |
|
| 99 | 99 | |
| 100 | - foreach ( $html as $node ) { |
|
| 101 | - $string = $this->recursiveCleanFromEquivText( $node, $string ); |
|
| 100 | + foreach ($html as $node) { |
|
| 101 | + $string = $this->recursiveCleanFromEquivText($node, $string); |
|
| 102 | 102 | } |
| 103 | 103 | |
| 104 | 104 | return $string; |
@@ -117,57 +117,57 @@ discard block |
||
| 117 | 117 | * |
| 118 | 118 | * @return string |
| 119 | 119 | */ |
| 120 | - private function recursiveAddEquivTextToPhTag( $node, $string ) { |
|
| 121 | - if ( $node->has_children ) { |
|
| 122 | - foreach ( $node->inner_html as $childNode ) { |
|
| 123 | - $string = $this->recursiveAddEquivTextToPhTag( $childNode, $string ); |
|
| 120 | + private function recursiveAddEquivTextToPhTag($node, $string) { |
|
| 121 | + if ($node->has_children) { |
|
| 122 | + foreach ($node->inner_html as $childNode) { |
|
| 123 | + $string = $this->recursiveAddEquivTextToPhTag($childNode, $string); |
|
| 124 | 124 | } |
| 125 | 125 | } else { |
| 126 | - if ( $node->tagname === 'ph' || $node->tagname === 'sc' || $node->tagname === 'ec' ) { |
|
| 127 | - if ( !isset( $node->attributes[ 'dataRef' ] ) ) { |
|
| 126 | + if ($node->tagname === 'ph' || $node->tagname === 'sc' || $node->tagname === 'ec') { |
|
| 127 | + if (!isset($node->attributes['dataRef'])) { |
|
| 128 | 128 | return $string; |
| 129 | 129 | } |
| 130 | 130 | |
| 131 | - $a = $node->node; // complete match. Eg: <ph id="source1" dataRef="source1"/> |
|
| 132 | - $b = $node->attributes[ 'dataRef' ]; // map identifier. Eg: source1 |
|
| 131 | + $a = $node->node; // complete match. Eg: <ph id="source1" dataRef="source1"/> |
|
| 132 | + $b = $node->attributes['dataRef']; // map identifier. Eg: source1 |
|
| 133 | 133 | |
| 134 | 134 | |
| 135 | 135 | // if isset a value in the map calculate base64 encoded value |
| 136 | 136 | // otherwise skip |
| 137 | - if ( !in_array( $b, array_keys( $this->map ) ) ) { |
|
| 137 | + if (!in_array($b, array_keys($this->map))) { |
|
| 138 | 138 | return $string; |
| 139 | 139 | } |
| 140 | 140 | |
| 141 | 141 | // check if is null, in this case convert it to NULL string |
| 142 | - if ( is_null( $this->map[ $b ] ) ) { |
|
| 143 | - $this->map[ $b ] = 'NULL'; |
|
| 142 | + if (is_null($this->map[$b])) { |
|
| 143 | + $this->map[$b] = 'NULL'; |
|
| 144 | 144 | } |
| 145 | 145 | |
| 146 | - $value = $this->map[ $b ]; |
|
| 147 | - $base64EncodedValue = base64_encode( $value ); |
|
| 146 | + $value = $this->map[$b]; |
|
| 147 | + $base64EncodedValue = base64_encode($value); |
|
| 148 | 148 | |
| 149 | - if ( empty( $base64EncodedValue ) || $base64EncodedValue === '' ) { |
|
| 149 | + if (empty($base64EncodedValue) || $base64EncodedValue === '') { |
|
| 150 | 150 | return $string; |
| 151 | 151 | } |
| 152 | 152 | |
| 153 | 153 | // if there is no id copy it from dataRef |
| 154 | - $id = ( !isset( $node->attributes[ 'id' ] ) ) ? ' id="' . $b . '" removeId="true"' : ''; |
|
| 154 | + $id = (!isset($node->attributes['id'])) ? ' id="' . $b . '" removeId="true"' : ''; |
|
| 155 | 155 | |
| 156 | 156 | // introduce dataType for <ec>/<sc> tag handling |
| 157 | - $dataType = ( $this->isAEcOrScTag( $node ) ) ? ' dataType="' . $node->tagname . '"' : ''; |
|
| 157 | + $dataType = ($this->isAEcOrScTag($node)) ? ' dataType="' . $node->tagname . '"' : ''; |
|
| 158 | 158 | |
| 159 | 159 | // replacement |
| 160 | - $d = str_replace( '/', $id . $dataType . ' equiv-text="base64:' . $base64EncodedValue . '"/', $a ); |
|
| 161 | - $a = str_replace( [ '<', '>', '>', '<' ], '', $a ); |
|
| 162 | - $d = str_replace( [ '<', '>', '>', '<' ], '', $d ); |
|
| 160 | + $d = str_replace('/', $id . $dataType . ' equiv-text="base64:' . $base64EncodedValue . '"/', $a); |
|
| 161 | + $a = str_replace(['<', '>', '>', '<'], '', $a); |
|
| 162 | + $d = str_replace(['<', '>', '>', '<'], '', $d); |
|
| 163 | 163 | |
| 164 | 164 | // convert <ec>/<sc> into <ph> |
| 165 | - if ( $this->isAEcOrScTag( $node ) ) { |
|
| 166 | - $d = 'ph' . substr( $d, 2 ); |
|
| 167 | - $d = trim( $d ); |
|
| 165 | + if ($this->isAEcOrScTag($node)) { |
|
| 166 | + $d = 'ph' . substr($d, 2); |
|
| 167 | + $d = trim($d); |
|
| 168 | 168 | } |
| 169 | 169 | |
| 170 | - return str_replace( $a, $d, $string ); |
|
| 170 | + return str_replace($a, $d, $string); |
|
| 171 | 171 | } |
| 172 | 172 | } |
| 173 | 173 | |
@@ -180,11 +180,11 @@ discard block |
||
| 180 | 180 | * |
| 181 | 181 | * @return bool |
| 182 | 182 | */ |
| 183 | - private function stringContainsPcTags( $string, $toBeEscaped ) { |
|
| 184 | - $regex = ( $toBeEscaped ) ? '/<pc (.*?)>/iu' : '/<pc (.*?)>/iu'; |
|
| 185 | - preg_match_all( $regex, $string, $openingPcMatches ); |
|
| 183 | + private function stringContainsPcTags($string, $toBeEscaped) { |
|
| 184 | + $regex = ($toBeEscaped) ? '/<pc (.*?)>/iu' : '/<pc (.*?)>/iu'; |
|
| 185 | + preg_match_all($regex, $string, $openingPcMatches); |
|
| 186 | 186 | |
| 187 | - return ( isset( $openingPcMatches[ 0 ] ) && count( $openingPcMatches[ 0 ] ) > 0 ); |
|
| 187 | + return (isset($openingPcMatches[0]) && count($openingPcMatches[0]) > 0); |
|
| 188 | 188 | } |
| 189 | 189 | |
| 190 | 190 | /** |
@@ -193,28 +193,28 @@ discard block |
||
| 193 | 193 | * |
| 194 | 194 | * @return mixed |
| 195 | 195 | */ |
| 196 | - private function replaceSelfClosedPcTags( $string, $toBeEscaped ) { |
|
| 197 | - if ( $toBeEscaped ) { |
|
| 198 | - $string = str_replace( [ '<', '>' ], [ '<', '>' ], $string ); |
|
| 196 | + private function replaceSelfClosedPcTags($string, $toBeEscaped) { |
|
| 197 | + if ($toBeEscaped) { |
|
| 198 | + $string = str_replace(['<', '>'], ['<', '>'], $string); |
|
| 199 | 199 | } |
| 200 | 200 | |
| 201 | 201 | $regex = '/<pc[^>]+?\/>/iu'; |
| 202 | - preg_match_all( $regex, $string, $selfClosedPcMatches ); |
|
| 202 | + preg_match_all($regex, $string, $selfClosedPcMatches); |
|
| 203 | 203 | |
| 204 | - foreach ( $selfClosedPcMatches[ 0 ] as $match ) { |
|
| 204 | + foreach ($selfClosedPcMatches[0] as $match) { |
|
| 205 | 205 | |
| 206 | - $html = HtmlParser::parse( $match ); |
|
| 207 | - $node = $html[ 0 ]; |
|
| 206 | + $html = HtmlParser::parse($match); |
|
| 207 | + $node = $html[0]; |
|
| 208 | 208 | $attributes = $node->attributes; |
| 209 | 209 | |
| 210 | - if ( isset( $attributes[ 'dataRefStart' ] ) && array_key_exists( $node->attributes[ 'dataRefStart' ], $this->map ) ) { |
|
| 211 | - $replacement = '<ph id="' . $attributes[ 'id' ] . '" dataType="pcSelf" originalData="' . base64_encode( $match ) . '" dataRef="' . $attributes[ 'dataRefStart' ] . '" equiv-text="base64:' . base64_encode( $this->map[ $node->attributes[ 'dataRefStart' ] ] ) . '"/>'; |
|
| 212 | - $string = str_replace( $match, $replacement, $string ); |
|
| 210 | + if (isset($attributes['dataRefStart']) && array_key_exists($node->attributes['dataRefStart'], $this->map)) { |
|
| 211 | + $replacement = '<ph id="' . $attributes['id'] . '" dataType="pcSelf" originalData="' . base64_encode($match) . '" dataRef="' . $attributes['dataRefStart'] . '" equiv-text="base64:' . base64_encode($this->map[$node->attributes['dataRefStart']]) . '"/>'; |
|
| 212 | + $string = str_replace($match, $replacement, $string); |
|
| 213 | 213 | } |
| 214 | 214 | } |
| 215 | 215 | |
| 216 | - if ( $toBeEscaped ) { |
|
| 217 | - $string = str_replace( [ '<', '>' ], [ '<', '>' ], $string ); |
|
| 216 | + if ($toBeEscaped) { |
|
| 217 | + $string = str_replace(['<', '>'], ['<', '>'], $string); |
|
| 218 | 218 | } |
| 219 | 219 | |
| 220 | 220 | return $string; |
@@ -228,12 +228,12 @@ discard block |
||
| 228 | 228 | * |
| 229 | 229 | * @return array |
| 230 | 230 | */ |
| 231 | - private function buildDataRefEndMap( $html ) { |
|
| 231 | + private function buildDataRefEndMap($html) { |
|
| 232 | 232 | $dataRefEndMap = []; |
| 233 | 233 | |
| 234 | - foreach ( $html as $index => $node ) { |
|
| 235 | - if ( $node->tagname === 'pc' ) { |
|
| 236 | - $this->extractDataRefMapRecursively( $node, $dataRefEndMap ); |
|
| 234 | + foreach ($html as $index => $node) { |
|
| 235 | + if ($node->tagname === 'pc') { |
|
| 236 | + $this->extractDataRefMapRecursively($node, $dataRefEndMap); |
|
| 237 | 237 | } |
| 238 | 238 | } |
| 239 | 239 | |
@@ -246,25 +246,25 @@ discard block |
||
| 246 | 246 | * @param object $node |
| 247 | 247 | * @param $dataRefEndMap |
| 248 | 248 | */ |
| 249 | - private function extractDataRefMapRecursively( $node, &$dataRefEndMap ) { |
|
| 250 | - if ( $this->nodeContainsNestedPcTags( $node ) ) { |
|
| 251 | - foreach ( $node->inner_html as $nestedNode ) { |
|
| 252 | - $this->extractDataRefMapRecursively( $nestedNode, $dataRefEndMap ); |
|
| 249 | + private function extractDataRefMapRecursively($node, &$dataRefEndMap) { |
|
| 250 | + if ($this->nodeContainsNestedPcTags($node)) { |
|
| 251 | + foreach ($node->inner_html as $nestedNode) { |
|
| 252 | + $this->extractDataRefMapRecursively($nestedNode, $dataRefEndMap); |
|
| 253 | 253 | } |
| 254 | 254 | } |
| 255 | 255 | |
| 256 | 256 | // EXCLUDE self closed <pc/> |
| 257 | - if ( $node->tagname === 'pc' && $node->self_closed === false ) { |
|
| 258 | - if ( isset( $node->attributes[ 'dataRefEnd' ] ) ) { |
|
| 259 | - $dataRefEnd = $node->attributes[ 'dataRefEnd' ]; |
|
| 260 | - } elseif ( isset( $node->attributes[ 'dataRefStart' ] ) ) { |
|
| 261 | - $dataRefEnd = $node->attributes[ 'dataRefStart' ]; |
|
| 257 | + if ($node->tagname === 'pc' && $node->self_closed === false) { |
|
| 258 | + if (isset($node->attributes['dataRefEnd'])) { |
|
| 259 | + $dataRefEnd = $node->attributes['dataRefEnd']; |
|
| 260 | + } elseif (isset($node->attributes['dataRefStart'])) { |
|
| 261 | + $dataRefEnd = $node->attributes['dataRefStart']; |
|
| 262 | 262 | } else { |
| 263 | 263 | $dataRefEnd = null; |
| 264 | 264 | } |
| 265 | 265 | |
| 266 | 266 | $dataRefEndMap[] = [ |
| 267 | - 'id' => isset( $node->attributes[ 'id' ] ) ? $node->attributes[ 'id' ] : null, |
|
| 267 | + 'id' => isset($node->attributes['id']) ? $node->attributes['id'] : null, |
|
| 268 | 268 | 'dataRefEnd' => $dataRefEnd, |
| 269 | 269 | ]; |
| 270 | 270 | } |
@@ -276,15 +276,15 @@ discard block |
||
| 276 | 276 | * |
| 277 | 277 | * @return string|string[] |
| 278 | 278 | */ |
| 279 | - private function recursiveCleanFromEquivText( $node, $string ) { |
|
| 280 | - if ( $node->has_children ) { |
|
| 281 | - foreach ( $node->inner_html as $childNode ) { |
|
| 282 | - $string = $this->recursiveCleanFromEquivText( $childNode, $string ); |
|
| 279 | + private function recursiveCleanFromEquivText($node, $string) { |
|
| 280 | + if ($node->has_children) { |
|
| 281 | + foreach ($node->inner_html as $childNode) { |
|
| 282 | + $string = $this->recursiveCleanFromEquivText($childNode, $string); |
|
| 283 | 283 | } |
| 284 | 284 | } else { |
| 285 | - if ( isset( $node->attributes[ 'dataRef' ] ) && array_key_exists( $node->attributes[ 'dataRef' ], $this->map ) ) { |
|
| 286 | - $cleaned = preg_replace( '/ equiv-text="(.*?)"/', '', $node->node ); |
|
| 287 | - $string = str_replace( $node->node, $cleaned, $string ); |
|
| 285 | + if (isset($node->attributes['dataRef']) && array_key_exists($node->attributes['dataRef'], $this->map)) { |
|
| 286 | + $cleaned = preg_replace('/ equiv-text="(.*?)"/', '', $node->node); |
|
| 287 | + $string = str_replace($node->node, $cleaned, $string); |
|
| 288 | 288 | } |
| 289 | 289 | } |
| 290 | 290 | |
@@ -299,35 +299,35 @@ discard block |
||
| 299 | 299 | * |
| 300 | 300 | * @return string |
| 301 | 301 | */ |
| 302 | - private function replaceOpeningPcTags( $string, $toBeEscaped ) { |
|
| 303 | - $regex = ( $toBeEscaped ) ? '/<pc (.*?)>/iu' : '/<pc (.*?)>/iu'; |
|
| 304 | - preg_match_all( $regex, $string, $openingPcMatches ); |
|
| 302 | + private function replaceOpeningPcTags($string, $toBeEscaped) { |
|
| 303 | + $regex = ($toBeEscaped) ? '/<pc (.*?)>/iu' : '/<pc (.*?)>/iu'; |
|
| 304 | + preg_match_all($regex, $string, $openingPcMatches); |
|
| 305 | 305 | |
| 306 | - foreach ( $openingPcMatches[ 0 ] as $index => $match ) { |
|
| 307 | - $attr = HtmlParser::getAttributes( $openingPcMatches[ 1 ][ $index ] ); |
|
| 306 | + foreach ($openingPcMatches[0] as $index => $match) { |
|
| 307 | + $attr = HtmlParser::getAttributes($openingPcMatches[1][$index]); |
|
| 308 | 308 | |
| 309 | 309 | // CASE 1 - Missing `dataRefStart` |
| 310 | - if ( isset( $attr[ 'dataRefEnd' ] ) && !isset( $attr[ 'dataRefStart' ] ) ) { |
|
| 311 | - $attr[ 'dataRefStart' ] = $attr[ 'dataRefEnd' ]; |
|
| 310 | + if (isset($attr['dataRefEnd']) && !isset($attr['dataRefStart'])) { |
|
| 311 | + $attr['dataRefStart'] = $attr['dataRefEnd']; |
|
| 312 | 312 | } |
| 313 | 313 | |
| 314 | 314 | // CASE 2 - Missing `dataRefEnd` |
| 315 | - if ( isset( $attr[ 'dataRefStart' ] ) && !isset( $attr[ 'dataRefEnd' ] ) ) { |
|
| 316 | - $attr[ 'dataRefEnd' ] = $attr[ 'dataRefStart' ]; |
|
| 315 | + if (isset($attr['dataRefStart']) && !isset($attr['dataRefEnd'])) { |
|
| 316 | + $attr['dataRefEnd'] = $attr['dataRefStart']; |
|
| 317 | 317 | } |
| 318 | 318 | |
| 319 | - if ( isset( $attr[ 'dataRefStart' ] ) ) { |
|
| 319 | + if (isset($attr['dataRefStart'])) { |
|
| 320 | 320 | $startOriginalData = $match; // opening <pc> |
| 321 | - $startValue = $this->map[ $attr[ 'dataRefStart' ] ] ? $this->map[ $attr[ 'dataRefStart' ] ] : 'NULL'; //handling null values in original data map |
|
| 322 | - $base64EncodedStartValue = base64_encode( $startValue ); |
|
| 323 | - $base64StartOriginalData = base64_encode( $startOriginalData ); |
|
| 321 | + $startValue = $this->map[$attr['dataRefStart']] ? $this->map[$attr['dataRefStart']] : 'NULL'; //handling null values in original data map |
|
| 322 | + $base64EncodedStartValue = base64_encode($startValue); |
|
| 323 | + $base64StartOriginalData = base64_encode($startOriginalData); |
|
| 324 | 324 | |
| 325 | 325 | // conversion for opening <pc> tag |
| 326 | - $openingPcConverted = '<ph ' . ( ( isset( $attr[ 'id' ] ) ) ? 'id="' . $attr[ 'id' ] . '_1"' : '' ) . ' dataType="pcStart" originalData="' . $base64StartOriginalData . '" dataRef="' |
|
| 327 | - . $attr[ 'dataRefStart' ] . '" equiv-text="base64:' |
|
| 326 | + $openingPcConverted = '<ph ' . ((isset($attr['id'])) ? 'id="' . $attr['id'] . '_1"' : '') . ' dataType="pcStart" originalData="' . $base64StartOriginalData . '" dataRef="' |
|
| 327 | + . $attr['dataRefStart'] . '" equiv-text="base64:' |
|
| 328 | 328 | . $base64EncodedStartValue . '"/>'; |
| 329 | 329 | |
| 330 | - $string = str_replace( $startOriginalData, $openingPcConverted, $string ); |
|
| 330 | + $string = str_replace($startOriginalData, $openingPcConverted, $string); |
|
| 331 | 331 | } |
| 332 | 332 | } |
| 333 | 333 | |
@@ -344,34 +344,34 @@ discard block |
||
| 344 | 344 | * |
| 345 | 345 | * @return string |
| 346 | 346 | */ |
| 347 | - private function replaceClosingPcTags( $string, $toBeEscaped, $dataRefEndMap = [] ) { |
|
| 348 | - $regex = ( $toBeEscaped ) ? '/<\/pc>/iu' : '/<\/pc>/iu'; |
|
| 349 | - preg_match_all( $regex, $string, $closingPcMatches, PREG_OFFSET_CAPTURE ); |
|
| 347 | + private function replaceClosingPcTags($string, $toBeEscaped, $dataRefEndMap = []) { |
|
| 348 | + $regex = ($toBeEscaped) ? '/<\/pc>/iu' : '/<\/pc>/iu'; |
|
| 349 | + preg_match_all($regex, $string, $closingPcMatches, PREG_OFFSET_CAPTURE); |
|
| 350 | 350 | $delta = 0; |
| 351 | 351 | |
| 352 | - foreach ( $closingPcMatches[ 0 ] as $index => $match ) { |
|
| 353 | - $offset = $match[ 1 ]; |
|
| 354 | - $length = strlen( $match[ 0 ] ); |
|
| 355 | - $attr = $dataRefEndMap[ $index ]; |
|
| 352 | + foreach ($closingPcMatches[0] as $index => $match) { |
|
| 353 | + $offset = $match[1]; |
|
| 354 | + $length = strlen($match[0]); |
|
| 355 | + $attr = $dataRefEndMap[$index]; |
|
| 356 | 356 | |
| 357 | - if ( !empty( $attr ) && isset( $attr[ 'dataRefEnd' ] ) ) { |
|
| 358 | - $endOriginalData = $match[ 0 ]; // </pc> |
|
| 359 | - $endValue = $this->map[ $attr[ 'dataRefEnd' ] ] ?: 'NULL'; |
|
| 360 | - $base64EncodedEndValue = base64_encode( $endValue ); |
|
| 361 | - $base64EndOriginalData = base64_encode( $endOriginalData ); |
|
| 357 | + if (!empty($attr) && isset($attr['dataRefEnd'])) { |
|
| 358 | + $endOriginalData = $match[0]; // </pc> |
|
| 359 | + $endValue = $this->map[$attr['dataRefEnd']] ?: 'NULL'; |
|
| 360 | + $base64EncodedEndValue = base64_encode($endValue); |
|
| 361 | + $base64EndOriginalData = base64_encode($endOriginalData); |
|
| 362 | 362 | |
| 363 | 363 | // conversion for closing <pc> tag |
| 364 | - $closingPcConverted = '<ph ' . ( ( isset( $attr[ 'id' ] ) ) ? 'id="' . $attr[ 'id' ] . '_2"' : '' ) . ' dataType="pcEnd" originalData="' . $base64EndOriginalData . '" dataRef="' |
|
| 365 | - . $attr[ 'dataRefEnd' ] . '" equiv-text="base64:' . $base64EncodedEndValue . '"/>'; |
|
| 364 | + $closingPcConverted = '<ph ' . ((isset($attr['id'])) ? 'id="' . $attr['id'] . '_2"' : '') . ' dataType="pcEnd" originalData="' . $base64EndOriginalData . '" dataRef="' |
|
| 365 | + . $attr['dataRefEnd'] . '" equiv-text="base64:' . $base64EncodedEndValue . '"/>'; |
|
| 366 | 366 | |
| 367 | - $realOffset = ( $delta === 0 ) ? $offset : ( $offset + $delta ); |
|
| 367 | + $realOffset = ($delta === 0) ? $offset : ($offset + $delta); |
|
| 368 | 368 | |
| 369 | - $string = substr_replace( $string, $closingPcConverted, $realOffset, $length ); |
|
| 370 | - $delta = $delta + strlen( $closingPcConverted ) - $length; |
|
| 369 | + $string = substr_replace($string, $closingPcConverted, $realOffset, $length); |
|
| 370 | + $delta = $delta + strlen($closingPcConverted) - $length; |
|
| 371 | 371 | } |
| 372 | 372 | } |
| 373 | 373 | |
| 374 | - return !is_array( $string ) ? $string : implode( $string ); |
|
| 374 | + return !is_array($string) ? $string : implode($string); |
|
| 375 | 375 | } |
| 376 | 376 | |
| 377 | 377 | /** |
@@ -379,13 +379,13 @@ discard block |
||
| 379 | 379 | * |
| 380 | 380 | * @return bool |
| 381 | 381 | */ |
| 382 | - private function nodeContainsNestedPcTags( $node ) { |
|
| 383 | - if ( !$node->has_children ) { |
|
| 382 | + private function nodeContainsNestedPcTags($node) { |
|
| 383 | + if (!$node->has_children) { |
|
| 384 | 384 | return false; |
| 385 | 385 | } |
| 386 | 386 | |
| 387 | - foreach ( $node->inner_html as $nestedNode ) { |
|
| 388 | - if ( $nestedNode->tagname === 'pc' && ( isset( $node->attributes[ 'dataRefEnd' ] ) || isset( $node->attributes[ 'dataRefStart' ] ) ) ) { |
|
| 387 | + foreach ($node->inner_html as $nestedNode) { |
|
| 388 | + if ($nestedNode->tagname === 'pc' && (isset($node->attributes['dataRefEnd']) || isset($node->attributes['dataRefStart']))) { |
|
| 389 | 389 | return true; |
| 390 | 390 | } |
| 391 | 391 | } |
@@ -398,18 +398,18 @@ discard block |
||
| 398 | 398 | * |
| 399 | 399 | * @return string |
| 400 | 400 | */ |
| 401 | - public function restore( $string ) { |
|
| 401 | + public function restore($string) { |
|
| 402 | 402 | // if map is empty return string as is |
| 403 | - if ( empty( $this->map ) ) { |
|
| 403 | + if (empty($this->map)) { |
|
| 404 | 404 | return $string; |
| 405 | 405 | } |
| 406 | 406 | |
| 407 | 407 | // replace eventual empty equiv-text="" |
| 408 | - $string = str_replace( ' equiv-text=""', '', $string ); |
|
| 409 | - $html = HtmlParser::parse( $string ); |
|
| 408 | + $string = str_replace(' equiv-text=""', '', $string); |
|
| 409 | + $html = HtmlParser::parse($string); |
|
| 410 | 410 | |
| 411 | - foreach ( $html as $node ) { |
|
| 412 | - $string = $this->recursiveRemoveOriginalData( $node, $string ); |
|
| 411 | + foreach ($html as $node) { |
|
| 412 | + $string = $this->recursiveRemoveOriginalData($node, $string); |
|
| 413 | 413 | } |
| 414 | 414 | |
| 415 | 415 | return $string; |
@@ -421,76 +421,76 @@ discard block |
||
| 421 | 421 | * |
| 422 | 422 | * @return string|string[] |
| 423 | 423 | */ |
| 424 | - private function recursiveRemoveOriginalData( $node, $string ) { |
|
| 425 | - if ( $node->has_children ) { |
|
| 426 | - foreach ( $node->inner_html as $childNode ) { |
|
| 427 | - $string = $this->recursiveRemoveOriginalData( $childNode, $string ); |
|
| 424 | + private function recursiveRemoveOriginalData($node, $string) { |
|
| 425 | + if ($node->has_children) { |
|
| 426 | + foreach ($node->inner_html as $childNode) { |
|
| 427 | + $string = $this->recursiveRemoveOriginalData($childNode, $string); |
|
| 428 | 428 | } |
| 429 | 429 | } else { |
| 430 | 430 | |
| 431 | - if ( !isset( $node->attributes[ 'dataRef' ] ) ) { |
|
| 431 | + if (!isset($node->attributes['dataRef'])) { |
|
| 432 | 432 | return $string; |
| 433 | 433 | } |
| 434 | 434 | |
| 435 | - $a = $node->node; // complete match. Eg: <ph id="source1" dataRef="source1"/> |
|
| 436 | - $b = $node->attributes[ 'dataRef' ]; // map identifier. Eg: source1 |
|
| 437 | - $c = $node->terminator; // terminator: Eg: > |
|
| 435 | + $a = $node->node; // complete match. Eg: <ph id="source1" dataRef="source1"/> |
|
| 436 | + $b = $node->attributes['dataRef']; // map identifier. Eg: source1 |
|
| 437 | + $c = $node->terminator; // terminator: Eg: > |
|
| 438 | 438 | |
| 439 | 439 | // if isset a value in the map calculate base64 encoded value |
| 440 | 440 | // or it is an empty string |
| 441 | 441 | // otherwise skip |
| 442 | - if ( !in_array( $b, array_keys( $this->map ) ) ) { |
|
| 442 | + if (!in_array($b, array_keys($this->map))) { |
|
| 443 | 443 | return $string; |
| 444 | 444 | } |
| 445 | 445 | |
| 446 | 446 | // check if is null, in this case convert it to NULL string |
| 447 | - if ( is_null( $this->map[ $b ] ) ) { |
|
| 448 | - $this->map[ $b ] = 'NULL'; |
|
| 447 | + if (is_null($this->map[$b])) { |
|
| 448 | + $this->map[$b] = 'NULL'; |
|
| 449 | 449 | } |
| 450 | 450 | |
| 451 | 451 | // remove id? |
| 452 | - $removeId = ( isset( $node->attributes[ 'removeId' ] ) && $node->attributes[ 'removeId' ] === "true" ) ? ' id="' . $b . '" removeId="true"' : ''; |
|
| 452 | + $removeId = (isset($node->attributes['removeId']) && $node->attributes['removeId'] === "true") ? ' id="' . $b . '" removeId="true"' : ''; |
|
| 453 | 453 | |
| 454 | 454 | // grab dataType attribute for <ec>/<sc> tag handling |
| 455 | - $dataType = ( $this->wasAEcOrScTag( $node ) ) ? ' dataType="' . $node->attributes[ 'dataType' ] . '"' : ''; |
|
| 455 | + $dataType = ($this->wasAEcOrScTag($node)) ? ' dataType="' . $node->attributes['dataType'] . '"' : ''; |
|
| 456 | 456 | |
| 457 | - $d = str_replace( $removeId . $dataType . ' equiv-text="base64:' . base64_encode( $this->map[ $b ] ) . '"/' . $c, '/' . $c, $a ); |
|
| 457 | + $d = str_replace($removeId . $dataType . ' equiv-text="base64:' . base64_encode($this->map[$b]) . '"/' . $c, '/' . $c, $a); |
|
| 458 | 458 | |
| 459 | 459 | // replace original <ec>/<sc> tag |
| 460 | - if ( $this->wasAEcOrScTag( $node ) ) { |
|
| 461 | - $d = $node->attributes[ 'dataType' ] . substr( $d, 3 ); |
|
| 462 | - $d = trim( $d ); |
|
| 460 | + if ($this->wasAEcOrScTag($node)) { |
|
| 461 | + $d = $node->attributes['dataType'] . substr($d, 3); |
|
| 462 | + $d = trim($d); |
|
| 463 | 463 | } |
| 464 | 464 | |
| 465 | 465 | // replace only content tag, no matter if the string is encoded or not |
| 466 | 466 | // in this way we can handle string with mixed tags (encoded and not-encoded) |
| 467 | 467 | // in the same string |
| 468 | - $a = $this->purgeTags( $a ); |
|
| 469 | - $d = $this->purgeTags( $d ); |
|
| 468 | + $a = $this->purgeTags($a); |
|
| 469 | + $d = $this->purgeTags($d); |
|
| 470 | 470 | |
| 471 | - $string = str_replace( $a, $d, $string ); |
|
| 471 | + $string = str_replace($a, $d, $string); |
|
| 472 | 472 | |
| 473 | 473 | // restoring <pc/> self-closed here |
| 474 | - if ( Strings::contains( 'dataType="pcSelf"', $d ) ) { |
|
| 475 | - preg_match( '/\s?originalData="(.*?)"\s?/', $d, $originalDataMatches ); |
|
| 474 | + if (Strings::contains('dataType="pcSelf"', $d)) { |
|
| 475 | + preg_match('/\s?originalData="(.*?)"\s?/', $d, $originalDataMatches); |
|
| 476 | 476 | |
| 477 | - if ( isset( $originalDataMatches[ 1 ] ) ) { |
|
| 478 | - $originalData = base64_decode( $originalDataMatches[ 1 ] ); |
|
| 479 | - $originalData = $this->purgeTags( $originalData ); |
|
| 480 | - $string = str_replace( $d, $originalData, $string ); |
|
| 477 | + if (isset($originalDataMatches[1])) { |
|
| 478 | + $originalData = base64_decode($originalDataMatches[1]); |
|
| 479 | + $originalData = $this->purgeTags($originalData); |
|
| 480 | + $string = str_replace($d, $originalData, $string); |
|
| 481 | 481 | } |
| 482 | 482 | } |
| 483 | 483 | |
| 484 | 484 | // restoring <pc> tags here |
| 485 | 485 | // if <ph> tag has originalData and originalType is pcStart or pcEnd, |
| 486 | 486 | // replace with original data |
| 487 | - if ( Strings::contains( 'dataType="pcStart"', $d ) || Strings::contains( 'dataType="pcEnd"', $d ) ) { |
|
| 488 | - preg_match( '/\s?originalData="(.*?)"\s?/', $d, $originalDataMatches ); |
|
| 487 | + if (Strings::contains('dataType="pcStart"', $d) || Strings::contains('dataType="pcEnd"', $d)) { |
|
| 488 | + preg_match('/\s?originalData="(.*?)"\s?/', $d, $originalDataMatches); |
|
| 489 | 489 | |
| 490 | - if ( isset( $originalDataMatches[ 1 ] ) ) { |
|
| 491 | - $originalData = base64_decode( $originalDataMatches[ 1 ] ); |
|
| 492 | - $originalData = $this->purgeTags( $originalData ); |
|
| 493 | - $string = str_replace( $d, $originalData, $string ); |
|
| 490 | + if (isset($originalDataMatches[1])) { |
|
| 491 | + $originalData = base64_decode($originalDataMatches[1]); |
|
| 492 | + $originalData = $this->purgeTags($originalData); |
|
| 493 | + $string = str_replace($d, $originalData, $string); |
|
| 494 | 494 | } |
| 495 | 495 | } |
| 496 | 496 | } |
@@ -503,8 +503,8 @@ discard block |
||
| 503 | 503 | * |
| 504 | 504 | * @return string |
| 505 | 505 | */ |
| 506 | - private function purgeTags( $string ) { |
|
| 507 | - return str_replace( [ '<', '>', '<', '>' ], '', $string ); |
|
| 506 | + private function purgeTags($string) { |
|
| 507 | + return str_replace(['<', '>', '<', '>'], '', $string); |
|
| 508 | 508 | } |
| 509 | 509 | |
| 510 | 510 | /** |
@@ -514,8 +514,8 @@ discard block |
||
| 514 | 514 | * |
| 515 | 515 | * @return bool |
| 516 | 516 | */ |
| 517 | - private function isAEcOrScTag( $node ) { |
|
| 518 | - return ( $node->tagname === 'ec' || $node->tagname === 'sc' ); |
|
| 517 | + private function isAEcOrScTag($node) { |
|
| 518 | + return ($node->tagname === 'ec' || $node->tagname === 'sc'); |
|
| 519 | 519 | } |
| 520 | 520 | |
| 521 | 521 | /** |
@@ -526,7 +526,7 @@ discard block |
||
| 526 | 526 | * |
| 527 | 527 | * @return bool |
| 528 | 528 | */ |
| 529 | - private function wasAEcOrScTag( $node ) { |
|
| 530 | - return ( isset( $node->attributes[ 'dataType' ] ) && ( $node->attributes[ 'dataType' ] === 'ec' || $node->attributes[ 'dataType' ] === 'sc' ) ); |
|
| 529 | + private function wasAEcOrScTag($node) { |
|
| 530 | + return (isset($node->attributes['dataType']) && ($node->attributes['dataType'] === 'ec' || $node->attributes['dataType'] === 'sc')); |
|
| 531 | 531 | } |
| 532 | 532 | } |
@@ -27,65 +27,65 @@ discard block |
||
| 27 | 27 | * @throws InvalidXmlException When parsing of XML with schema or callable produces any errors unrelated to the XML parsing itself |
| 28 | 28 | * @throws RuntimeException When DOM extension is missing |
| 29 | 29 | */ |
| 30 | - public static function parse( $content, $schemaOrCallable = null ) { |
|
| 31 | - if ( !extension_loaded( 'dom' ) ) { |
|
| 32 | - throw new RuntimeException( 'Extension DOM is required.' ); |
|
| 30 | + public static function parse($content, $schemaOrCallable = null) { |
|
| 31 | + if (!extension_loaded('dom')) { |
|
| 32 | + throw new RuntimeException('Extension DOM is required.'); |
|
| 33 | 33 | } |
| 34 | 34 | |
| 35 | - $internalErrors = libxml_use_internal_errors( true ); |
|
| 36 | - $disableEntities = libxml_disable_entity_loader( true ); |
|
| 35 | + $internalErrors = libxml_use_internal_errors(true); |
|
| 36 | + $disableEntities = libxml_disable_entity_loader(true); |
|
| 37 | 37 | libxml_clear_errors(); |
| 38 | 38 | |
| 39 | - $dom = new DOMDocument( '1.0', 'UTF-8' ); |
|
| 39 | + $dom = new DOMDocument('1.0', 'UTF-8'); |
|
| 40 | 40 | $dom->validateOnParse = true; |
| 41 | - if ( !$dom->loadXML( $content, LIBXML_NONET | ( defined( 'LIBXML_COMPACT' ) ? LIBXML_COMPACT : 0 ) ) ) { |
|
| 42 | - libxml_disable_entity_loader( $disableEntities ); |
|
| 41 | + if (!$dom->loadXML($content, LIBXML_NONET | (defined('LIBXML_COMPACT') ? LIBXML_COMPACT : 0))) { |
|
| 42 | + libxml_disable_entity_loader($disableEntities); |
|
| 43 | 43 | |
| 44 | - throw new XmlParsingException( implode( "\n", static::getXmlErrors( $internalErrors ) ) ); |
|
| 44 | + throw new XmlParsingException(implode("\n", static::getXmlErrors($internalErrors))); |
|
| 45 | 45 | } |
| 46 | 46 | |
| 47 | 47 | $dom->normalizeDocument(); |
| 48 | 48 | |
| 49 | - libxml_use_internal_errors( $internalErrors ); |
|
| 50 | - libxml_disable_entity_loader( $disableEntities ); |
|
| 49 | + libxml_use_internal_errors($internalErrors); |
|
| 50 | + libxml_disable_entity_loader($disableEntities); |
|
| 51 | 51 | |
| 52 | - foreach ( $dom->childNodes as $child ) { |
|
| 53 | - if ( XML_DOCUMENT_TYPE_NODE === $child->nodeType ) { |
|
| 54 | - throw new XmlParsingException( 'Document types are not allowed.' ); |
|
| 52 | + foreach ($dom->childNodes as $child) { |
|
| 53 | + if (XML_DOCUMENT_TYPE_NODE === $child->nodeType) { |
|
| 54 | + throw new XmlParsingException('Document types are not allowed.'); |
|
| 55 | 55 | } |
| 56 | 56 | } |
| 57 | 57 | |
| 58 | - if ( null !== $schemaOrCallable ) { |
|
| 59 | - $internalErrors = libxml_use_internal_errors( true ); |
|
| 58 | + if (null !== $schemaOrCallable) { |
|
| 59 | + $internalErrors = libxml_use_internal_errors(true); |
|
| 60 | 60 | libxml_clear_errors(); |
| 61 | 61 | |
| 62 | 62 | $e = null; |
| 63 | - if ( is_callable( $schemaOrCallable ) ) { |
|
| 63 | + if (is_callable($schemaOrCallable)) { |
|
| 64 | 64 | try { |
| 65 | - $valid = call_user_func( $schemaOrCallable, $dom, $internalErrors ); |
|
| 66 | - } catch ( Exception $e ) { |
|
| 65 | + $valid = call_user_func($schemaOrCallable, $dom, $internalErrors); |
|
| 66 | + } catch (Exception $e) { |
|
| 67 | 67 | $valid = false; |
| 68 | 68 | } |
| 69 | - } elseif ( !is_array( $schemaOrCallable ) && is_file( (string)$schemaOrCallable ) ) { |
|
| 70 | - $schemaSource = file_get_contents( (string)$schemaOrCallable ); |
|
| 71 | - $valid = @$dom->schemaValidateSource( $schemaSource ); |
|
| 69 | + } elseif (!is_array($schemaOrCallable) && is_file((string)$schemaOrCallable)) { |
|
| 70 | + $schemaSource = file_get_contents((string)$schemaOrCallable); |
|
| 71 | + $valid = @$dom->schemaValidateSource($schemaSource); |
|
| 72 | 72 | } else { |
| 73 | - libxml_use_internal_errors( $internalErrors ); |
|
| 73 | + libxml_use_internal_errors($internalErrors); |
|
| 74 | 74 | |
| 75 | - throw new XmlParsingException( 'The schemaOrCallable argument has to be a valid path to XSD file or callable.' ); |
|
| 75 | + throw new XmlParsingException('The schemaOrCallable argument has to be a valid path to XSD file or callable.'); |
|
| 76 | 76 | } |
| 77 | 77 | |
| 78 | - if ( !$valid ) { |
|
| 79 | - $messages = static::getXmlErrors( $internalErrors ); |
|
| 80 | - if ( empty( $messages ) ) { |
|
| 81 | - throw new InvalidXmlException( 'The XML is not valid.', 0, $e ); |
|
| 78 | + if (!$valid) { |
|
| 79 | + $messages = static::getXmlErrors($internalErrors); |
|
| 80 | + if (empty($messages)) { |
|
| 81 | + throw new InvalidXmlException('The XML is not valid.', 0, $e); |
|
| 82 | 82 | } |
| 83 | - throw new XmlParsingException( implode( "\n", $messages ), 0, $e ); |
|
| 83 | + throw new XmlParsingException(implode("\n", $messages), 0, $e); |
|
| 84 | 84 | } |
| 85 | 85 | } |
| 86 | 86 | |
| 87 | 87 | libxml_clear_errors(); |
| 88 | - libxml_use_internal_errors( $internalErrors ); |
|
| 88 | + libxml_use_internal_errors($internalErrors); |
|
| 89 | 89 | |
| 90 | 90 | return $dom; |
| 91 | 91 | } |
@@ -95,14 +95,14 @@ discard block |
||
| 95 | 95 | * |
| 96 | 96 | * @return array |
| 97 | 97 | */ |
| 98 | - private static function getXmlErrors( $internalErrors ) { |
|
| 98 | + private static function getXmlErrors($internalErrors) { |
|
| 99 | 99 | $errors = []; |
| 100 | - foreach ( libxml_get_errors() as $error ) { |
|
| 100 | + foreach (libxml_get_errors() as $error) { |
|
| 101 | 101 | $errors[] = sprintf( |
| 102 | 102 | '[%s %s] %s (in %s - line %d, column %d)', |
| 103 | 103 | LIBXML_ERR_WARNING == $error->level ? 'WARNING' : 'ERROR', |
| 104 | 104 | $error->code, |
| 105 | - trim( $error->message ), |
|
| 105 | + trim($error->message), |
|
| 106 | 106 | $error->file ?: 'n/a', |
| 107 | 107 | $error->line, |
| 108 | 108 | $error->column |
@@ -110,7 +110,7 @@ discard block |
||
| 110 | 110 | } |
| 111 | 111 | |
| 112 | 112 | libxml_clear_errors(); |
| 113 | - libxml_use_internal_errors( $internalErrors ); |
|
| 113 | + libxml_use_internal_errors($internalErrors); |
|
| 114 | 114 | |
| 115 | 115 | return $errors; |
| 116 | 116 | } |
@@ -19,15 +19,15 @@ discard block |
||
| 19 | 19 | |
| 20 | 20 | // get id |
| 21 | 21 | // trim to first 100 characters because this is the limit on Matecat's DB |
| 22 | - $this->currentTransUnitId = substr($attr[ 'id' ], 0, 100); |
|
| 22 | + $this->currentTransUnitId = substr($attr['id'], 0, 100); |
|
| 23 | 23 | |
| 24 | 24 | // current 'translate' attribute of the current trans-unit |
| 25 | - $this->currentTransUnitTranslate = isset($attr[ 'translate' ]) ? $attr[ 'translate' ] : 'yes'; |
|
| 25 | + $this->currentTransUnitTranslate = isset($attr['translate']) ? $attr['translate'] : 'yes'; |
|
| 26 | 26 | } |
| 27 | 27 | |
| 28 | 28 | // check if we are entering into a <target> |
| 29 | 29 | if ('target' == $name) { |
| 30 | - if($this->currentTransUnitTranslate === 'no'){ |
|
| 30 | + if ($this->currentTransUnitTranslate === 'no') { |
|
| 31 | 31 | $this->inTarget = false; |
| 32 | 32 | } else { |
| 33 | 33 | $this->inTarget = true; |
@@ -64,10 +64,10 @@ discard block |
||
| 64 | 64 | } elseif ('sdl:seg' == $name) { |
| 65 | 65 | |
| 66 | 66 | // write the confidence level for this segment ( Translated, Draft, etc. ) |
| 67 | - if (isset($this->segments[ 'matecat|' . $this->currentTransUnitId ]) && $_sdlStatus_confWritten === false) { |
|
| 67 | + if (isset($this->segments['matecat|' . $this->currentTransUnitId]) && $_sdlStatus_confWritten === false) { |
|
| 68 | 68 | |
| 69 | 69 | // append definition attribute |
| 70 | - $tag .= $this->prepareTargetStatuses($this->lastTransUnit[ $this->markerPos ]); |
|
| 70 | + $tag .= $this->prepareTargetStatuses($this->lastTransUnit[$this->markerPos]); |
|
| 71 | 71 | |
| 72 | 72 | //prepare for an eventual next cycle |
| 73 | 73 | $this->markerPos++; |
@@ -94,15 +94,15 @@ discard block |
||
| 94 | 94 | // is outside current buffer (in the latter case, it's in next buffer to be read by the while loop); |
| 95 | 95 | // this check is necessary because we may have truncated a tag in half with current read, |
| 96 | 96 | // and the other half may be encountered in the next buffer it will be passed |
| 97 | - if (isset($this->currentBuffer[ $idx - $this->offset ])) { |
|
| 97 | + if (isset($this->currentBuffer[$idx - $this->offset])) { |
|
| 98 | 98 | // if this tag entire lenght fitted in the buffer, the last char must be the last |
| 99 | 99 | // symbol before the '>'; if it's an empty tag, it is assumed that it's a '/' |
| 100 | 100 | $tmp_offset = $idx - $this->offset; |
| 101 | - $lastChar = $this->currentBuffer[ $tmp_offset ]; |
|
| 101 | + $lastChar = $this->currentBuffer[$tmp_offset]; |
|
| 102 | 102 | } else { |
| 103 | 103 | //if it's out, simple use the last character of the chunk |
| 104 | 104 | $tmp_offset = $this->len - 1; |
| 105 | - $lastChar = $this->currentBuffer[ $tmp_offset ]; |
|
| 105 | + $lastChar = $this->currentBuffer[$tmp_offset]; |
|
| 106 | 106 | } |
| 107 | 107 | |
| 108 | 108 | // trim last space |
@@ -136,7 +136,7 @@ discard block |
||
| 136 | 136 | } else { |
| 137 | 137 | //these are NOT source/seg-source/value empty tags, THERE IS A CONTENT, write it in buffer |
| 138 | 138 | $this->bufferIsActive = true; |
| 139 | - $this->CDATABuffer .= $tag; |
|
| 139 | + $this->CDATABuffer .= $tag; |
|
| 140 | 140 | } |
| 141 | 141 | } else { |
| 142 | 142 | $this->postProcAndFlush($this->outputFP, $tag); |
@@ -156,11 +156,11 @@ discard block |
||
| 156 | 156 | { |
| 157 | 157 | $endTags = ""; |
| 158 | 158 | |
| 159 | - $segment = Strings::removeDangerousChars($seg [ 'segment' ]); |
|
| 160 | - $translation = Strings::removeDangerousChars($seg [ 'translation' ]); |
|
| 159 | + $segment = Strings::removeDangerousChars($seg ['segment']); |
|
| 160 | + $translation = Strings::removeDangerousChars($seg ['translation']); |
|
| 161 | 161 | $dataRefMap = (isset($seg['data_ref_map']) && $seg['data_ref_map'] !== null) ? Strings::jsonToArray($seg['data_ref_map']) : []; |
| 162 | 162 | |
| 163 | - if (is_null($seg [ 'translation' ]) || $seg [ 'translation' ] == '') { |
|
| 163 | + if (is_null($seg ['translation']) || $seg ['translation'] == '') { |
|
| 164 | 164 | $translation = $segment; |
| 165 | 165 | } else { |
| 166 | 166 | if ($this->callback) { |
@@ -173,20 +173,20 @@ discard block |
||
| 173 | 173 | // for Trados the trailing spaces after </mrk> are meaningful |
| 174 | 174 | // so we trim the translation from Matecat DB and add them after </mrk> |
| 175 | 175 | $trailingSpaces = ''; |
| 176 | - for ($s=0; $s < Strings::getTheNumberOfTrailingSpaces($translation); $s++){ |
|
| 176 | + for ($s = 0; $s < Strings::getTheNumberOfTrailingSpaces($translation); $s++) { |
|
| 177 | 177 | $trailingSpaces .= ' '; |
| 178 | 178 | } |
| 179 | 179 | |
| 180 | - if ($seg[ 'mrk_id' ] !== null && $seg[ 'mrk_id' ] != '') { |
|
| 180 | + if ($seg['mrk_id'] !== null && $seg['mrk_id'] != '') { |
|
| 181 | 181 | if ($this->targetLang === 'ja-JP') { |
| 182 | - $seg[ 'mrk_succ_tags' ] = ltrim($seg[ 'mrk_succ_tags' ]); |
|
| 182 | + $seg['mrk_succ_tags'] = ltrim($seg['mrk_succ_tags']); |
|
| 183 | 183 | } |
| 184 | 184 | |
| 185 | - $translation = "<mrk mid=\"" . $seg[ 'mrk_id' ] . "\" mtype=\"seg\">" . $seg[ 'mrk_prev_tags' ] . rtrim($translation) . $seg[ 'mrk_succ_tags' ] . "</mrk>" . $trailingSpaces; |
|
| 185 | + $translation = "<mrk mid=\"" . $seg['mrk_id'] . "\" mtype=\"seg\">" . $seg['mrk_prev_tags'] . rtrim($translation) . $seg['mrk_succ_tags'] . "</mrk>" . $trailingSpaces; |
|
| 186 | 186 | } |
| 187 | 187 | |
| 188 | 188 | // we need to trim succ_tags here because we already added the trailing spaces after </mrk> |
| 189 | - $transUnitTranslation .= $seg[ 'prev_tags' ] . $translation . $endTags . ltrim($seg[ 'succ_tags' ]); |
|
| 189 | + $transUnitTranslation .= $seg['prev_tags'] . $translation . $endTags . ltrim($seg['succ_tags']); |
|
| 190 | 190 | |
| 191 | 191 | return $transUnitTranslation; |
| 192 | 192 | } |
@@ -206,7 +206,7 @@ discard block |
||
| 206 | 206 | 'REJECTED' => 'RejectedTranslation', |
| 207 | 207 | ]; |
| 208 | 208 | |
| 209 | - return "conf=\"{$statusMap[ $segment[ 'status' ] ]}\" "; |
|
| 209 | + return "conf=\"{$statusMap[$segment['status']]}\" "; |
|
| 210 | 210 | } |
| 211 | 211 | |
| 212 | 212 | /** |
@@ -218,7 +218,7 @@ discard block |
||
| 218 | 218 | */ |
| 219 | 219 | protected function setTransUnitState($seg, $state_prop, $lastMrkState) |
| 220 | 220 | { |
| 221 | - return [ null, null ]; |
|
| 221 | + return [null, null]; |
|
| 222 | 222 | } |
| 223 | 223 | |
| 224 | 224 | /** |
@@ -8,28 +8,28 @@ discard block |
||
| 8 | 8 | abstract class AbstractXliffReplacer { |
| 9 | 9 | protected $originalFP; |
| 10 | 10 | |
| 11 | - protected $tuTagName; // <trans-unit> (forXliff v 1.*) or <unit> (forXliff v 2.*) |
|
| 12 | - protected $inTU = false; // flag to check whether we are in a <trans-unit> |
|
| 13 | - protected $inTarget = false; // flag to check whether we are in a <target>, to ignore everything |
|
| 14 | - protected $isEmpty = false; // flag to check whether we are in an empty tag (<tag/>) |
|
| 15 | - protected $targetWasWritten = false; // flag to check is <target> was written in the current unit |
|
| 16 | - protected $segmentPositionInTu = -1; // the current position of segment in the current <unit> (forXliff v 2.*) |
|
| 17 | - |
|
| 18 | - protected $CDATABuffer = ""; // buffer for special tag |
|
| 19 | - protected $bufferIsActive = false; // buffer for special tag |
|
| 20 | - |
|
| 21 | - protected $offset = 0; // offset for SAX pointer |
|
| 22 | - protected $outputFP; // output stream pointer |
|
| 23 | - protected $currentBuffer; // the current piece of text it's been parsed |
|
| 24 | - protected $len; // length of the currentBuffer |
|
| 25 | - protected $segments; // array of translations |
|
| 11 | + protected $tuTagName; // <trans-unit> (forXliff v 1.*) or <unit> (forXliff v 2.*) |
|
| 12 | + protected $inTU = false; // flag to check whether we are in a <trans-unit> |
|
| 13 | + protected $inTarget = false; // flag to check whether we are in a <target>, to ignore everything |
|
| 14 | + protected $isEmpty = false; // flag to check whether we are in an empty tag (<tag/>) |
|
| 15 | + protected $targetWasWritten = false; // flag to check is <target> was written in the current unit |
|
| 16 | + protected $segmentPositionInTu = -1; // the current position of segment in the current <unit> (forXliff v 2.*) |
|
| 17 | + |
|
| 18 | + protected $CDATABuffer = ""; // buffer for special tag |
|
| 19 | + protected $bufferIsActive = false; // buffer for special tag |
|
| 20 | + |
|
| 21 | + protected $offset = 0; // offset for SAX pointer |
|
| 22 | + protected $outputFP; // output stream pointer |
|
| 23 | + protected $currentBuffer; // the current piece of text it's been parsed |
|
| 24 | + protected $len; // length of the currentBuffer |
|
| 25 | + protected $segments; // array of translations |
|
| 26 | 26 | protected $lastTransUnit = []; |
| 27 | - protected $currentTransUnitId; // id of current <trans-unit> |
|
| 27 | + protected $currentTransUnitId; // id of current <trans-unit> |
|
| 28 | 28 | protected $currentTransUnitTranslate; // 'translate' attribute of current <trans-unit> |
| 29 | - protected $currentSegmentArray = []; // id of current <segment> (forXliff v 2.*) |
|
| 30 | - protected $unitContainsMda = false; // check if <unit> already contains a <mda:metadata> (forXliff v 2.*) |
|
| 31 | - protected $hasWrittenCounts = false; // check if <unit> already wrote segment counts (forXliff v 2.*) |
|
| 32 | - protected $sourceAttributes = []; // current <source> attributes (needed when handling xliff files without <target>) |
|
| 29 | + protected $currentSegmentArray = []; // id of current <segment> (forXliff v 2.*) |
|
| 30 | + protected $unitContainsMda = false; // check if <unit> already contains a <mda:metadata> (forXliff v 2.*) |
|
| 31 | + protected $hasWrittenCounts = false; // check if <unit> already wrote segment counts (forXliff v 2.*) |
|
| 32 | + protected $sourceAttributes = []; // current <source> attributes (needed when handling xliff files without <target>) |
|
| 33 | 33 | |
| 34 | 34 | protected $targetLang; |
| 35 | 35 | |
@@ -76,8 +76,8 @@ discard block |
||
| 76 | 76 | XliffReplacerCallbackInterface $callback = null |
| 77 | 77 | ) { |
| 78 | 78 | self::$INTERNAL_TAG_PLACEHOLDER = $this->getInternalTagPlaceholder(); |
| 79 | - $this->createOutputFileIfDoesNotExist( $outputFilePath ); |
|
| 80 | - $this->setFileDescriptors( $originalXliffPath, $outputFilePath ); |
|
| 79 | + $this->createOutputFileIfDoesNotExist($outputFilePath); |
|
| 80 | + $this->setFileDescriptors($originalXliffPath, $outputFilePath); |
|
| 81 | 81 | $this->xliffVersion = $xliffVersion; |
| 82 | 82 | $this->setTuTagName(); |
| 83 | 83 | $this->segments = $segments; |
@@ -95,19 +95,19 @@ discard block |
||
| 95 | 95 | return "§" . |
| 96 | 96 | substr( |
| 97 | 97 | str_replace( |
| 98 | - [ '+', '/' ], |
|
| 98 | + ['+', '/'], |
|
| 99 | 99 | '', |
| 100 | - base64_encode( openssl_random_pseudo_bytes( 10, $_crypto_strong ) ) |
|
| 100 | + base64_encode(openssl_random_pseudo_bytes(10, $_crypto_strong)) |
|
| 101 | 101 | ), |
| 102 | 102 | 0, |
| 103 | 103 | 4 |
| 104 | 104 | ); |
| 105 | 105 | } |
| 106 | 106 | |
| 107 | - private function createOutputFileIfDoesNotExist( $outputFilePath ) { |
|
| 107 | + private function createOutputFileIfDoesNotExist($outputFilePath) { |
|
| 108 | 108 | // create output file |
| 109 | - if ( !file_exists( $outputFilePath ) ) { |
|
| 110 | - touch( $outputFilePath ); |
|
| 109 | + if (!file_exists($outputFilePath)) { |
|
| 110 | + touch($outputFilePath); |
|
| 111 | 111 | } |
| 112 | 112 | } |
| 113 | 113 | |
@@ -115,13 +115,13 @@ discard block |
||
| 115 | 115 | * @param $originalXliffPath |
| 116 | 116 | * @param $outputFilePath |
| 117 | 117 | */ |
| 118 | - private function setFileDescriptors( $originalXliffPath, $outputFilePath ) { |
|
| 119 | - $this->outputFP = fopen( $outputFilePath, 'w+' ); |
|
| 118 | + private function setFileDescriptors($originalXliffPath, $outputFilePath) { |
|
| 119 | + $this->outputFP = fopen($outputFilePath, 'w+'); |
|
| 120 | 120 | |
| 121 | 121 | $streamArgs = null; |
| 122 | 122 | |
| 123 | - if ( !( $this->originalFP = fopen( $originalXliffPath, "r", false, stream_context_create( $streamArgs ) ) ) ) { |
|
| 124 | - throw new RuntimeException( "could not open XML input" ); |
|
| 123 | + if (!($this->originalFP = fopen($originalXliffPath, "r", false, stream_context_create($streamArgs)))) { |
|
| 124 | + throw new RuntimeException("could not open XML input"); |
|
| 125 | 125 | } |
| 126 | 126 | } |
| 127 | 127 | |
@@ -130,7 +130,7 @@ discard block |
||
| 130 | 130 | * <trans-unit> (xliff v1.*) || <unit> (xliff v2.*) |
| 131 | 131 | */ |
| 132 | 132 | private function setTuTagName() { |
| 133 | - $this->tuTagName = ( $this->xliffVersion === 2 ) ? 'unit' : 'trans-unit'; |
|
| 133 | + $this->tuTagName = ($this->xliffVersion === 2) ? 'unit' : 'trans-unit'; |
|
| 134 | 134 | } |
| 135 | 135 | |
| 136 | 136 | /** |
@@ -139,8 +139,8 @@ discard block |
||
| 139 | 139 | public function __destruct() { |
| 140 | 140 | //this stream can be closed outside the class |
| 141 | 141 | //to permit multiple concurrent downloads, so suppress warnings |
| 142 | - @fclose( $this->originalFP ); |
|
| 143 | - fclose( $this->outputFP ); |
|
| 142 | + @fclose($this->originalFP); |
|
| 143 | + fclose($this->outputFP); |
|
| 144 | 144 | } |
| 145 | 145 | |
| 146 | 146 | abstract public function replaceTranslation(); |
@@ -151,11 +151,11 @@ discard block |
||
| 151 | 151 | * @return resource |
| 152 | 152 | */ |
| 153 | 153 | protected function initSaxParser() { |
| 154 | - $xmlSaxParser = xml_parser_create( 'UTF-8' ); |
|
| 155 | - xml_set_object( $xmlSaxParser, $this ); |
|
| 156 | - xml_parser_set_option( $xmlSaxParser, XML_OPTION_CASE_FOLDING, false ); |
|
| 157 | - xml_set_element_handler( $xmlSaxParser, 'tagOpen', 'tagClose' ); |
|
| 158 | - xml_set_character_data_handler( $xmlSaxParser, 'characterData' ); |
|
| 154 | + $xmlSaxParser = xml_parser_create('UTF-8'); |
|
| 155 | + xml_set_object($xmlSaxParser, $this); |
|
| 156 | + xml_parser_set_option($xmlSaxParser, XML_OPTION_CASE_FOLDING, false); |
|
| 157 | + xml_set_element_handler($xmlSaxParser, 'tagOpen', 'tagClose'); |
|
| 158 | + xml_set_character_data_handler($xmlSaxParser, 'characterData'); |
|
| 159 | 159 | |
| 160 | 160 | return $xmlSaxParser; |
| 161 | 161 | } |
@@ -163,8 +163,8 @@ discard block |
||
| 163 | 163 | /** |
| 164 | 164 | * @param resource $xmlSaxParser |
| 165 | 165 | */ |
| 166 | - protected function closeSaxParser( $xmlSaxParser ) { |
|
| 167 | - xml_parser_free( $xmlSaxParser ); |
|
| 166 | + protected function closeSaxParser($xmlSaxParser) { |
|
| 167 | + xml_parser_free($xmlSaxParser); |
|
| 168 | 168 | } |
| 169 | 169 | |
| 170 | 170 | /** |
@@ -174,7 +174,7 @@ discard block |
||
| 174 | 174 | * |
| 175 | 175 | * @return mixed |
| 176 | 176 | */ |
| 177 | - abstract protected function tagOpen( $parser, $name, $attr ); |
|
| 177 | + abstract protected function tagOpen($parser, $name, $attr); |
|
| 178 | 178 | |
| 179 | 179 | /** |
| 180 | 180 | * @param $parser |
@@ -182,7 +182,7 @@ discard block |
||
| 182 | 182 | * |
| 183 | 183 | * @return mixed |
| 184 | 184 | */ |
| 185 | - abstract protected function tagClose( $parser, $name ); |
|
| 185 | + abstract protected function tagClose($parser, $name); |
|
| 186 | 186 | |
| 187 | 187 | /** |
| 188 | 188 | * @param $parser |
@@ -190,7 +190,7 @@ discard block |
||
| 190 | 190 | * |
| 191 | 191 | * @return mixed |
| 192 | 192 | */ |
| 193 | - abstract protected function characterData( $parser, $data ); |
|
| 193 | + abstract protected function characterData($parser, $data); |
|
| 194 | 194 | |
| 195 | 195 | /** |
| 196 | 196 | * postprocess escaped data and write to disk |
@@ -199,18 +199,18 @@ discard block |
||
| 199 | 199 | * @param string $data |
| 200 | 200 | * @param bool $treatAsCDATA |
| 201 | 201 | */ |
| 202 | - protected function postProcAndFlush( $fp, $data, $treatAsCDATA = false ) { |
|
| 202 | + protected function postProcAndFlush($fp, $data, $treatAsCDATA = false) { |
|
| 203 | 203 | //postprocess string |
| 204 | - $data = preg_replace( "/" . self::$INTERNAL_TAG_PLACEHOLDER . '(.*?)' . self::$INTERNAL_TAG_PLACEHOLDER . "/", '&$1;', $data ); |
|
| 205 | - $data = str_replace( ' ', ' ', $data ); |
|
| 206 | - if ( !$treatAsCDATA ) { |
|
| 204 | + $data = preg_replace("/" . self::$INTERNAL_TAG_PLACEHOLDER . '(.*?)' . self::$INTERNAL_TAG_PLACEHOLDER . "/", '&$1;', $data); |
|
| 205 | + $data = str_replace(' ', ' ', $data); |
|
| 206 | + if (!$treatAsCDATA) { |
|
| 207 | 207 | //unix2dos |
| 208 | - $data = str_replace( "\r\n", "\r", $data ); |
|
| 209 | - $data = str_replace( "\n", "\r", $data ); |
|
| 210 | - $data = str_replace( "\r", "\r\n", $data ); |
|
| 208 | + $data = str_replace("\r\n", "\r", $data); |
|
| 209 | + $data = str_replace("\n", "\r", $data); |
|
| 210 | + $data = str_replace("\r", "\r\n", $data); |
|
| 211 | 211 | } |
| 212 | 212 | |
| 213 | 213 | //flush to disk |
| 214 | - fwrite( $fp, $data ); |
|
| 214 | + fwrite($fp, $data); |
|
| 215 | 215 | } |
| 216 | 216 | } |
@@ -31,17 +31,17 @@ discard block |
||
| 31 | 31 | ]; |
| 32 | 32 | |
| 33 | 33 | public function replaceTranslation() { |
| 34 | - fwrite( $this->outputFP, '<?xml version="1.0" encoding="UTF-8"?>' ); |
|
| 34 | + fwrite($this->outputFP, '<?xml version="1.0" encoding="UTF-8"?>'); |
|
| 35 | 35 | |
| 36 | 36 | //create Sax parser |
| 37 | 37 | $xmlParser = $this->initSaxParser(); |
| 38 | 38 | |
| 39 | - while ( $this->currentBuffer = fread( $this->originalFP, 4096 ) ) { |
|
| 39 | + while ($this->currentBuffer = fread($this->originalFP, 4096)) { |
|
| 40 | 40 | /* |
| 41 | 41 | preprocess file |
| 42 | 42 | */ |
| 43 | 43 | // obfuscate entities because sax automatically does html_entity_decode |
| 44 | - $temporary_check_buffer = preg_replace( "/&(.*?);/", self::$INTERNAL_TAG_PLACEHOLDER . '$1' . self::$INTERNAL_TAG_PLACEHOLDER, $this->currentBuffer ); |
|
| 44 | + $temporary_check_buffer = preg_replace("/&(.*?);/", self::$INTERNAL_TAG_PLACEHOLDER . '$1' . self::$INTERNAL_TAG_PLACEHOLDER, $this->currentBuffer); |
|
| 45 | 45 | |
| 46 | 46 | //avoid cutting entities in half: |
| 47 | 47 | //the last fread could have truncated an entity (say, '<' in '&l'), thus invalidating the escaping |
@@ -53,84 +53,84 @@ discard block |
||
| 53 | 53 | // add 9 Bytes and substitute the entities, if the & is present, and it is not at the end |
| 54 | 54 | //it can't be an entity, exit the loop |
| 55 | 55 | |
| 56 | - while ( true ) { |
|
| 57 | - $_ampPos = strpos( $temporary_check_buffer, '&' ); |
|
| 56 | + while (true) { |
|
| 57 | + $_ampPos = strpos($temporary_check_buffer, '&'); |
|
| 58 | 58 | |
| 59 | 59 | //check for real entity or escape it to safely exit from the loop!!! |
| 60 | - if ( $_ampPos === false || strlen( substr( $temporary_check_buffer, $_ampPos ) ) > 9 ) { |
|
| 60 | + if ($_ampPos === false || strlen(substr($temporary_check_buffer, $_ampPos)) > 9) { |
|
| 61 | 61 | $escape_AMP = true; |
| 62 | 62 | break; |
| 63 | 63 | } |
| 64 | 64 | |
| 65 | 65 | //if an entity is still present, fetch some more and repeat the escaping |
| 66 | - $this->currentBuffer .= fread( $this->originalFP, 9 ); |
|
| 67 | - $temporary_check_buffer = preg_replace( "/&(.*?);/", self::$INTERNAL_TAG_PLACEHOLDER . '$1' . self::$INTERNAL_TAG_PLACEHOLDER, $this->currentBuffer ); |
|
| 66 | + $this->currentBuffer .= fread($this->originalFP, 9); |
|
| 67 | + $temporary_check_buffer = preg_replace("/&(.*?);/", self::$INTERNAL_TAG_PLACEHOLDER . '$1' . self::$INTERNAL_TAG_PLACEHOLDER, $this->currentBuffer); |
|
| 68 | 68 | } |
| 69 | 69 | |
| 70 | 70 | //free stuff outside the loop |
| 71 | - unset( $temporary_check_buffer ); |
|
| 71 | + unset($temporary_check_buffer); |
|
| 72 | 72 | |
| 73 | - $this->currentBuffer = preg_replace( "/&(.*?);/", self::$INTERNAL_TAG_PLACEHOLDER . '$1' . self::$INTERNAL_TAG_PLACEHOLDER, $this->currentBuffer ); |
|
| 74 | - if ( $escape_AMP ) { |
|
| 75 | - $this->currentBuffer = str_replace( "&", self::$INTERNAL_TAG_PLACEHOLDER . 'amp' . self::$INTERNAL_TAG_PLACEHOLDER, $this->currentBuffer ); |
|
| 73 | + $this->currentBuffer = preg_replace("/&(.*?);/", self::$INTERNAL_TAG_PLACEHOLDER . '$1' . self::$INTERNAL_TAG_PLACEHOLDER, $this->currentBuffer); |
|
| 74 | + if ($escape_AMP) { |
|
| 75 | + $this->currentBuffer = str_replace("&", self::$INTERNAL_TAG_PLACEHOLDER . 'amp' . self::$INTERNAL_TAG_PLACEHOLDER, $this->currentBuffer); |
|
| 76 | 76 | } |
| 77 | 77 | |
| 78 | 78 | //get length of chunk |
| 79 | - $this->len = strlen( $this->currentBuffer ); |
|
| 79 | + $this->len = strlen($this->currentBuffer); |
|
| 80 | 80 | |
| 81 | 81 | //parse chunk of text |
| 82 | - if ( !xml_parse( $xmlParser, $this->currentBuffer, feof( $this->originalFP ) ) ) { |
|
| 82 | + if (!xml_parse($xmlParser, $this->currentBuffer, feof($this->originalFP))) { |
|
| 83 | 83 | //if unable, raise an exception |
| 84 | - throw new RuntimeException( sprintf( |
|
| 84 | + throw new RuntimeException(sprintf( |
|
| 85 | 85 | "XML error: %s at line %d", |
| 86 | - xml_error_string( xml_get_error_code( $xmlParser ) ), |
|
| 87 | - xml_get_current_line_number( $xmlParser ) |
|
| 88 | - ) ); |
|
| 86 | + xml_error_string(xml_get_error_code($xmlParser)), |
|
| 87 | + xml_get_current_line_number($xmlParser) |
|
| 88 | + )); |
|
| 89 | 89 | } |
| 90 | 90 | //get accumulated this->offset in document: as long as SAX pointer advances, we keep track of total bytes it has seen so far; this way, we can translate its global pointer in an address local to the current buffer of text to retrieve last char of tag |
| 91 | 91 | $this->offset += $this->len; |
| 92 | 92 | } |
| 93 | 93 | |
| 94 | 94 | // close Sax parser |
| 95 | - $this->closeSaxParser( $xmlParser ); |
|
| 95 | + $this->closeSaxParser($xmlParser); |
|
| 96 | 96 | |
| 97 | 97 | } |
| 98 | 98 | |
| 99 | 99 | /** |
| 100 | 100 | * @inheritDoc |
| 101 | 101 | */ |
| 102 | - protected function tagOpen( $parser, $name, $attr ) { |
|
| 102 | + protected function tagOpen($parser, $name, $attr) { |
|
| 103 | 103 | // check if we are entering into a <trans-unit> (xliff v1.*) or <unit> (xliff v2.*) |
| 104 | - if ( $this->tuTagName === $name ) { |
|
| 104 | + if ($this->tuTagName === $name) { |
|
| 105 | 105 | $this->inTU = true; |
| 106 | 106 | |
| 107 | 107 | // get id |
| 108 | 108 | // trim to first 100 characters because this is the limit on Matecat's DB |
| 109 | - $this->currentTransUnitId = substr( $attr[ 'id' ], 0, 100 ); |
|
| 109 | + $this->currentTransUnitId = substr($attr['id'], 0, 100); |
|
| 110 | 110 | |
| 111 | 111 | // `translate` attribute can be only yes or no |
| 112 | - if ( isset( $attr[ 'translate' ] ) && $attr[ 'translate' ] === 'no' ) { |
|
| 113 | - $attr[ 'translate' ] = 'no'; |
|
| 112 | + if (isset($attr['translate']) && $attr['translate'] === 'no') { |
|
| 113 | + $attr['translate'] = 'no'; |
|
| 114 | 114 | } else { |
| 115 | - $attr[ 'translate' ] = 'yes'; |
|
| 115 | + $attr['translate'] = 'yes'; |
|
| 116 | 116 | } |
| 117 | 117 | |
| 118 | 118 | // current 'translate' attribute of the current trans-unit |
| 119 | - $this->currentTransUnitTranslate = $attr[ 'translate' ]; |
|
| 119 | + $this->currentTransUnitTranslate = $attr['translate']; |
|
| 120 | 120 | } |
| 121 | 121 | |
| 122 | - if ( 'source' === $name ) { |
|
| 122 | + if ('source' === $name) { |
|
| 123 | 123 | $this->sourceAttributes = $attr; |
| 124 | 124 | } |
| 125 | 125 | |
| 126 | - if ( 'mda:metadata' === $name ) { |
|
| 126 | + if ('mda:metadata' === $name) { |
|
| 127 | 127 | $this->unitContainsMda = true; |
| 128 | 128 | } |
| 129 | 129 | |
| 130 | 130 | // check if we are entering into a <target> |
| 131 | - if ( 'target' === $name ) { |
|
| 131 | + if ('target' === $name) { |
|
| 132 | 132 | |
| 133 | - if ( $this->currentTransUnitTranslate === 'no' ) { |
|
| 133 | + if ($this->currentTransUnitTranslate === 'no') { |
|
| 134 | 134 | $this->inTarget = false; |
| 135 | 135 | } else { |
| 136 | 136 | $this->inTarget = true; |
@@ -139,7 +139,7 @@ discard block |
||
| 139 | 139 | |
| 140 | 140 | // check if we are inside a <target>, obviously this happen only if there are targets inside the trans-unit |
| 141 | 141 | // <target> must be stripped to be replaced, so this check avoids <target> reconstruction |
| 142 | - if ( !$this->inTarget ) { |
|
| 142 | + if (!$this->inTarget) { |
|
| 143 | 143 | |
| 144 | 144 | $tag = ''; |
| 145 | 145 | |
@@ -161,14 +161,14 @@ discard block |
||
| 161 | 161 | // |
| 162 | 162 | // http://docs.oasis-open.org/xliff/xliff-core/v2.0/os/xliff-core-v2.0-os.html#unit |
| 163 | 163 | // |
| 164 | - if ( $this->xliffVersion === 2 && ( $name === 'notes' || $name === 'originalData' || $name === 'segment' || $name === 'ignorable' ) && $this->unitContainsMda === false ) { |
|
| 165 | - if ( isset( $this->transUnits[ $this->currentTransUnitId ] ) && !empty( $this->transUnits[ $this->currentTransUnitId ] ) && !$this->hasWrittenCounts ) { |
|
| 164 | + if ($this->xliffVersion === 2 && ($name === 'notes' || $name === 'originalData' || $name === 'segment' || $name === 'ignorable') && $this->unitContainsMda === false) { |
|
| 165 | + if (isset($this->transUnits[$this->currentTransUnitId]) && !empty($this->transUnits[$this->currentTransUnitId]) && !$this->hasWrittenCounts) { |
|
| 166 | 166 | |
| 167 | 167 | // we need to update counts here |
| 168 | 168 | $this->updateCounts(); |
| 169 | 169 | $this->hasWrittenCounts = true; |
| 170 | 170 | |
| 171 | - $tag .= $this->getWordCountGroupForXliffV2( $this->counts[ 'raw_word_count' ], $this->counts[ 'eq_word_count' ] ); |
|
| 171 | + $tag .= $this->getWordCountGroupForXliffV2($this->counts['raw_word_count'], $this->counts['eq_word_count']); |
|
| 172 | 172 | $this->unitContainsMda = true; |
| 173 | 173 | } |
| 174 | 174 | } |
@@ -179,88 +179,88 @@ discard block |
||
| 179 | 179 | $lastMrkState = null; |
| 180 | 180 | $stateProp = ''; |
| 181 | 181 | |
| 182 | - foreach ( $attr as $k => $v ) { |
|
| 182 | + foreach ($attr as $k => $v) { |
|
| 183 | 183 | |
| 184 | 184 | //if tag name is file, we must replace the target-language attribute |
| 185 | - if ( $name === 'file' && $k === 'target-language' && !empty( $this->targetLang ) ) { |
|
| 185 | + if ($name === 'file' && $k === 'target-language' && !empty($this->targetLang)) { |
|
| 186 | 186 | //replace Target language with job language provided from constructor |
| 187 | 187 | $tag .= "$k=\"$this->targetLang\" "; |
| 188 | 188 | } else { |
| 189 | 189 | $pos = 0; |
| 190 | - if ( $this->currentTransUnitId ) { |
|
| 191 | - $pos = current( $this->transUnits[ $this->currentTransUnitId ] ); |
|
| 190 | + if ($this->currentTransUnitId) { |
|
| 191 | + $pos = current($this->transUnits[$this->currentTransUnitId]); |
|
| 192 | 192 | } |
| 193 | 193 | |
| 194 | - if ( $name === $this->tuTagName ) { |
|
| 194 | + if ($name === $this->tuTagName) { |
|
| 195 | 195 | |
| 196 | - $sid = $this->segments[ $pos ][ 'sid' ]; |
|
| 196 | + $sid = $this->segments[$pos]['sid']; |
|
| 197 | 197 | |
| 198 | 198 | // add `help-id` to xliff v.1* |
| 199 | 199 | // add `mtc:segment-id` to xliff v.2* |
| 200 | - if ( $this->xliffVersion === 1 && strpos( $tag, 'help-id' ) === false ) { |
|
| 201 | - if ( !empty( $sid ) ) { |
|
| 200 | + if ($this->xliffVersion === 1 && strpos($tag, 'help-id') === false) { |
|
| 201 | + if (!empty($sid)) { |
|
| 202 | 202 | $tag .= "help-id=\"$sid\" "; |
| 203 | 203 | } |
| 204 | - } elseif ( $this->xliffVersion === 2 && strpos( $tag, 'mtc:segment-id' ) === false ) { |
|
| 205 | - if ( !empty( $sid ) ) { |
|
| 204 | + } elseif ($this->xliffVersion === 2 && strpos($tag, 'mtc:segment-id') === false) { |
|
| 205 | + if (!empty($sid)) { |
|
| 206 | 206 | $tag .= "mtc:segment-id=\"$sid\" "; |
| 207 | 207 | } |
| 208 | 208 | } |
| 209 | 209 | |
| 210 | - } elseif ( 'segment' === $name && $this->xliffVersion === 2 ) { // add state to segment in Xliff v2 |
|
| 211 | - list( $stateProp, $lastMrkState ) = $this->setTransUnitState( $this->segments[ $pos ], $stateProp, $lastMrkState ); |
|
| 210 | + } elseif ('segment' === $name && $this->xliffVersion === 2) { // add state to segment in Xliff v2 |
|
| 211 | + list($stateProp, $lastMrkState) = $this->setTransUnitState($this->segments[$pos], $stateProp, $lastMrkState); |
|
| 212 | 212 | } |
| 213 | 213 | |
| 214 | 214 | //normal tag flux, put attributes in it |
| 215 | 215 | $tag .= "$k=\"$v\" "; |
| 216 | 216 | |
| 217 | 217 | // replace state for xliff v2 |
| 218 | - if ( $stateProp ) { |
|
| 218 | + if ($stateProp) { |
|
| 219 | 219 | $pattern = '/state=\"(.*)\"/i'; |
| 220 | - $tag = preg_replace( $pattern, $stateProp, $tag ); |
|
| 220 | + $tag = preg_replace($pattern, $stateProp, $tag); |
|
| 221 | 221 | } |
| 222 | 222 | } |
| 223 | 223 | } |
| 224 | 224 | |
| 225 | 225 | // add oasis xliff 20 namespace |
| 226 | - if ( $this->xliffVersion === 2 && $name === 'xliff' && !array_key_exists( 'xmlns:mda', $attr ) ) { |
|
| 226 | + if ($this->xliffVersion === 2 && $name === 'xliff' && !array_key_exists('xmlns:mda', $attr)) { |
|
| 227 | 227 | $tag .= 'xmlns:mda="urn:oasis:names:tc:xliff:metadata:2.0"'; |
| 228 | 228 | } |
| 229 | 229 | |
| 230 | 230 | // add MateCat specific namespace, we want maybe add non-XLIFF attributes |
| 231 | - if ( $name === 'xliff' && !array_key_exists( 'xmlns:mtc', $attr ) ) { |
|
| 231 | + if ($name === 'xliff' && !array_key_exists('xmlns:mtc', $attr)) { |
|
| 232 | 232 | $tag .= ' xmlns:mtc="https://www.matecat.com" '; |
| 233 | 233 | } |
| 234 | 234 | |
| 235 | 235 | // trgLang |
| 236 | - if ( $name === 'xliff' ) { |
|
| 237 | - $tag = preg_replace( '/trgLang="(.*?)"/', 'trgLang="' . $this->targetLang . '"', $tag ); |
|
| 236 | + if ($name === 'xliff') { |
|
| 237 | + $tag = preg_replace('/trgLang="(.*?)"/', 'trgLang="' . $this->targetLang . '"', $tag); |
|
| 238 | 238 | } |
| 239 | 239 | |
| 240 | 240 | //this logic helps detecting empty tags |
| 241 | 241 | //get current position of SAX pointer in all the stream of data is has read so far: |
| 242 | 242 | //it points at the end of current tag |
| 243 | - $idx = xml_get_current_byte_index( $parser ); |
|
| 243 | + $idx = xml_get_current_byte_index($parser); |
|
| 244 | 244 | |
| 245 | 245 | //check whether the bounds of current tag are entirely in current buffer or the end of the current tag |
| 246 | 246 | //is outside current buffer (in the latter case, it's in next buffer to be read by the while loop); |
| 247 | 247 | //this check is necessary because we may have truncated a tag in half with current read, |
| 248 | 248 | //and the other half may be encountered in the next buffer it will be passed |
| 249 | - if ( isset( $this->currentBuffer[ $idx - $this->offset ] ) ) { |
|
| 249 | + if (isset($this->currentBuffer[$idx - $this->offset])) { |
|
| 250 | 250 | //if this tag entire lenght fitted in the buffer, the last char must be the last |
| 251 | 251 | //symbol before the '>'; if it's an empty tag, it is assumed that it's a '/' |
| 252 | - $lastChar = $this->currentBuffer[ $idx - $this->offset ]; |
|
| 252 | + $lastChar = $this->currentBuffer[$idx - $this->offset]; |
|
| 253 | 253 | } else { |
| 254 | 254 | //if it's out, simple use the last character of the chunk |
| 255 | - $lastChar = $this->currentBuffer[ $this->len - 1 ]; |
|
| 255 | + $lastChar = $this->currentBuffer[$this->len - 1]; |
|
| 256 | 256 | } |
| 257 | 257 | |
| 258 | 258 | //trim last space |
| 259 | - $tag = rtrim( $tag ); |
|
| 259 | + $tag = rtrim($tag); |
|
| 260 | 260 | |
| 261 | 261 | //detect empty tag |
| 262 | - $this->isEmpty = ( $lastChar == '/' || $name == 'x' ); |
|
| 263 | - if ( $this->isEmpty ) { |
|
| 262 | + $this->isEmpty = ($lastChar == '/' || $name == 'x'); |
|
| 263 | + if ($this->isEmpty) { |
|
| 264 | 264 | $tag .= '/'; |
| 265 | 265 | } |
| 266 | 266 | |
@@ -268,29 +268,29 @@ discard block |
||
| 268 | 268 | $tag .= ">"; |
| 269 | 269 | |
| 270 | 270 | //set a a Buffer for the segSource Source tag |
| 271 | - if ( $this->bufferIsActive || in_array( $name, $this->nodesToCopy ) ) { // we are opening a critical CDATA section |
|
| 271 | + if ($this->bufferIsActive || in_array($name, $this->nodesToCopy)) { // we are opening a critical CDATA section |
|
| 272 | 272 | |
| 273 | 273 | //WARNING BECAUSE SOURCE AND SEG-SOURCE TAGS CAN BE EMPTY IN SOME CASES!!!!! |
| 274 | 274 | //so check for isEmpty also in conjunction with name |
| 275 | - if ( $this->isEmpty && ( 'source' === $name || 'seg-source' === $name ) ) { |
|
| 276 | - $this->postProcAndFlush( $this->outputFP, $tag ); |
|
| 275 | + if ($this->isEmpty && ('source' === $name || 'seg-source' === $name)) { |
|
| 276 | + $this->postProcAndFlush($this->outputFP, $tag); |
|
| 277 | 277 | } else { |
| 278 | 278 | //these are NOT source/seg-source/value empty tags, THERE IS A CONTENT, write it in buffer |
| 279 | 279 | $this->bufferIsActive = true; |
| 280 | - $this->CDATABuffer .= $tag; |
|
| 280 | + $this->CDATABuffer .= $tag; |
|
| 281 | 281 | } |
| 282 | 282 | } else { |
| 283 | - $this->postProcAndFlush( $this->outputFP, $tag ); |
|
| 283 | + $this->postProcAndFlush($this->outputFP, $tag); |
|
| 284 | 284 | } |
| 285 | 285 | } |
| 286 | 286 | |
| 287 | 287 | // update segmentPositionInTu |
| 288 | 288 | |
| 289 | - if ( $this->xliffVersion === 1 && $this->inTU && $name === 'source' ) { |
|
| 289 | + if ($this->xliffVersion === 1 && $this->inTU && $name === 'source') { |
|
| 290 | 290 | $this->segmentPositionInTu++; |
| 291 | 291 | } |
| 292 | 292 | |
| 293 | - if ( $this->xliffVersion === 2 && $this->inTU && $name === 'segment' ) { |
|
| 293 | + if ($this->xliffVersion === 2 && $this->inTU && $name === 'segment') { |
|
| 294 | 294 | $this->segmentPositionInTu++; |
| 295 | 295 | } |
| 296 | 296 | } |
@@ -298,7 +298,7 @@ discard block |
||
| 298 | 298 | /** |
| 299 | 299 | * @inheritDoc |
| 300 | 300 | */ |
| 301 | - protected function tagClose( $parser, $name ) { |
|
| 301 | + protected function tagClose($parser, $name) { |
|
| 302 | 302 | $tag = ''; |
| 303 | 303 | |
| 304 | 304 | /** |
@@ -307,26 +307,26 @@ discard block |
||
| 307 | 307 | * |
| 308 | 308 | * self::tagOpen method |
| 309 | 309 | */ |
| 310 | - if ( !$this->isEmpty && !( $this->inTarget && $name !== 'target' ) ) { |
|
| 310 | + if (!$this->isEmpty && !($this->inTarget && $name !== 'target')) { |
|
| 311 | 311 | |
| 312 | - if ( !$this->inTarget ) { |
|
| 312 | + if (!$this->inTarget) { |
|
| 313 | 313 | $tag = "</$name>"; |
| 314 | 314 | } |
| 315 | 315 | |
| 316 | - if ( 'target' == $name ) { |
|
| 316 | + if ('target' == $name) { |
|
| 317 | 317 | |
| 318 | - if ( $this->currentTransUnitTranslate === 'no' ) { |
|
| 318 | + if ($this->currentTransUnitTranslate === 'no') { |
|
| 319 | 319 | // do nothing |
| 320 | - } elseif ( isset( $this->transUnits[ $this->currentTransUnitId ] ) ) { |
|
| 320 | + } elseif (isset($this->transUnits[$this->currentTransUnitId])) { |
|
| 321 | 321 | |
| 322 | 322 | // get translation of current segment, by indirect indexing: id -> positional index -> segment |
| 323 | 323 | // actually there may be more that one segment to that ID if there are two mrk of the same source segment |
| 324 | 324 | |
| 325 | - $listOfSegmentsIds = $this->transUnits[ $this->currentTransUnitId ]; |
|
| 325 | + $listOfSegmentsIds = $this->transUnits[$this->currentTransUnitId]; |
|
| 326 | 326 | |
| 327 | 327 | // $currentSegmentId |
| 328 | - if ( !empty( $listOfSegmentsIds ) ) { |
|
| 329 | - $this->setCurrentSegmentArray( $listOfSegmentsIds ); |
|
| 328 | + if (!empty($listOfSegmentsIds)) { |
|
| 329 | + $this->setCurrentSegmentArray($listOfSegmentsIds); |
|
| 330 | 330 | } |
| 331 | 331 | |
| 332 | 332 | /* |
@@ -343,12 +343,12 @@ discard block |
||
| 343 | 343 | $this->lastTransUnit = []; |
| 344 | 344 | |
| 345 | 345 | $last_value = null; |
| 346 | - $segmentsCount = count( $listOfSegmentsIds ); |
|
| 347 | - for ( $i = 0; $i < $segmentsCount; $i++ ) { |
|
| 348 | - $id = $listOfSegmentsIds[ $i ]; |
|
| 349 | - if ( isset( $this->segments[ $id ] ) && ( $i == 0 || $last_value + 1 == $listOfSegmentsIds[ $i ] ) ) { |
|
| 350 | - $last_value = $listOfSegmentsIds[ $i ]; |
|
| 351 | - $this->lastTransUnit[] = $this->segments[ $id ]; |
|
| 346 | + $segmentsCount = count($listOfSegmentsIds); |
|
| 347 | + for ($i = 0; $i < $segmentsCount; $i++) { |
|
| 348 | + $id = $listOfSegmentsIds[$i]; |
|
| 349 | + if (isset($this->segments[$id]) && ($i == 0 || $last_value + 1 == $listOfSegmentsIds[$i])) { |
|
| 350 | + $last_value = $listOfSegmentsIds[$i]; |
|
| 351 | + $this->lastTransUnit[] = $this->segments[$id]; |
|
| 352 | 352 | } |
| 353 | 353 | } |
| 354 | 354 | |
@@ -360,27 +360,27 @@ discard block |
||
| 360 | 360 | // we must reset the lastMrkId found because this is a new segment. |
| 361 | 361 | $lastMrkId = -1; |
| 362 | 362 | |
| 363 | - if ( $this->xliffVersion === 2 ) { |
|
| 364 | - $seg = $this->segments[ $this->currentSegmentArray[ 'sid' ] ]; |
|
| 363 | + if ($this->xliffVersion === 2) { |
|
| 364 | + $seg = $this->segments[$this->currentSegmentArray['sid']]; |
|
| 365 | 365 | |
| 366 | 366 | // update counts |
| 367 | - if ( !$this->hasWrittenCounts && !empty( $seg ) ) { |
|
| 368 | - $this->updateSegmentCounts( $seg ); |
|
| 367 | + if (!$this->hasWrittenCounts && !empty($seg)) { |
|
| 368 | + $this->updateSegmentCounts($seg); |
|
| 369 | 369 | } |
| 370 | 370 | |
| 371 | 371 | // delete translations so the prepareSegment |
| 372 | 372 | // will put source content in target tag |
| 373 | - if ( $this->sourceInTarget ) { |
|
| 374 | - $seg[ 'translation' ] = ''; |
|
| 373 | + if ($this->sourceInTarget) { |
|
| 374 | + $seg['translation'] = ''; |
|
| 375 | 375 | $this->resetCounts(); |
| 376 | 376 | } |
| 377 | 377 | |
| 378 | 378 | // append $translation |
| 379 | - $translation = $this->prepareTranslation( $seg, $translation ); |
|
| 379 | + $translation = $this->prepareTranslation($seg, $translation); |
|
| 380 | 380 | |
| 381 | - list( $stateProp, $lastMrkState ) = $this->setTransUnitState( $seg, $stateProp, $lastMrkState ); |
|
| 381 | + list($stateProp, $lastMrkState) = $this->setTransUnitState($seg, $stateProp, $lastMrkState); |
|
| 382 | 382 | } else { |
| 383 | - foreach ( $listOfSegmentsIds as $pos => $id ) { |
|
| 383 | + foreach ($listOfSegmentsIds as $pos => $id) { |
|
| 384 | 384 | |
| 385 | 385 | /* |
| 386 | 386 | * This routine works to respect the positional orders of markers. |
@@ -393,8 +393,8 @@ discard block |
||
| 393 | 393 | * pre-assign zero to the new mrk if this is the first one ( in this segment ) |
| 394 | 394 | * If it is null leave it NULL |
| 395 | 395 | */ |
| 396 | - if ( (int)$this->segments[ $id ][ "mrk_id" ] < 0 && $this->segments[ $id ][ "mrk_id" ] !== null ) { |
|
| 397 | - $this->segments[ $id ][ "mrk_id" ] = 0; |
|
| 396 | + if ((int)$this->segments[$id]["mrk_id"] < 0 && $this->segments[$id]["mrk_id"] !== null) { |
|
| 397 | + $this->segments[$id]["mrk_id"] = 0; |
|
| 398 | 398 | } |
| 399 | 399 | |
| 400 | 400 | /* |
@@ -403,65 +403,65 @@ discard block |
||
| 403 | 403 | * ( null <= -1 ) === true |
| 404 | 404 | * so, cast to int |
| 405 | 405 | */ |
| 406 | - if ( (int)$this->segments[ $id ][ "mrk_id" ] <= $lastMrkId ) { |
|
| 406 | + if ((int)$this->segments[$id]["mrk_id"] <= $lastMrkId) { |
|
| 407 | 407 | break; |
| 408 | 408 | } |
| 409 | 409 | |
| 410 | 410 | // set $this->currentSegment |
| 411 | - $seg = $this->segments[ $id ]; |
|
| 411 | + $seg = $this->segments[$id]; |
|
| 412 | 412 | |
| 413 | 413 | // update counts |
| 414 | - if ( !empty( $seg ) ) { |
|
| 415 | - $this->updateSegmentCounts( $seg ); |
|
| 414 | + if (!empty($seg)) { |
|
| 415 | + $this->updateSegmentCounts($seg); |
|
| 416 | 416 | } |
| 417 | 417 | |
| 418 | 418 | // delete translations so the prepareSegment |
| 419 | 419 | // will put source content in target tag |
| 420 | - if ( $this->sourceInTarget ) { |
|
| 421 | - $seg[ 'translation' ] = ''; |
|
| 420 | + if ($this->sourceInTarget) { |
|
| 421 | + $seg['translation'] = ''; |
|
| 422 | 422 | $this->resetCounts(); |
| 423 | 423 | } |
| 424 | 424 | |
| 425 | 425 | // append $translation |
| 426 | - $translation = $this->prepareTranslation( $seg, $translation ); |
|
| 426 | + $translation = $this->prepareTranslation($seg, $translation); |
|
| 427 | 427 | |
| 428 | 428 | // for xliff 2 we need $this->transUnits[ $this->currentId ] [ $pos ] for populating metadata |
| 429 | 429 | |
| 430 | - unset( $this->transUnits[ $this->currentTransUnitId ] [ $pos ] ); |
|
| 430 | + unset($this->transUnits[$this->currentTransUnitId] [$pos]); |
|
| 431 | 431 | |
| 432 | - $lastMrkId = $this->segments[ $id ][ "mrk_id" ]; |
|
| 432 | + $lastMrkId = $this->segments[$id]["mrk_id"]; |
|
| 433 | 433 | |
| 434 | - list( $stateProp, $lastMrkState ) = $this->setTransUnitState( $seg, $stateProp, $lastMrkState ); |
|
| 434 | + list($stateProp, $lastMrkState) = $this->setTransUnitState($seg, $stateProp, $lastMrkState); |
|
| 435 | 435 | } |
| 436 | 436 | } |
| 437 | 437 | |
| 438 | 438 | //append translation |
| 439 | 439 | $targetLang = ''; |
| 440 | - if ( $this->xliffVersion === 1 ) { |
|
| 440 | + if ($this->xliffVersion === 1) { |
|
| 441 | 441 | $targetLang = ' xml:lang="' . $this->targetLang . '"'; |
| 442 | 442 | } |
| 443 | 443 | |
| 444 | - $tag = $this->buildTranslateTag( $targetLang, $stateProp, $translation, $this->counts[ 'raw_word_count' ], $this->counts[ 'eq_word_count' ] ); |
|
| 444 | + $tag = $this->buildTranslateTag($targetLang, $stateProp, $translation, $this->counts['raw_word_count'], $this->counts['eq_word_count']); |
|
| 445 | 445 | } |
| 446 | 446 | |
| 447 | 447 | // signal we are leaving a target |
| 448 | 448 | $this->targetWasWritten = true; |
| 449 | 449 | $this->inTarget = false; |
| 450 | - $this->postProcAndFlush( $this->outputFP, $tag, $treatAsCDATA = true ); |
|
| 451 | - } elseif ( in_array( $name, $this->nodesToCopy ) ) { // we are closing a critical CDATA section |
|
| 450 | + $this->postProcAndFlush($this->outputFP, $tag, $treatAsCDATA = true); |
|
| 451 | + } elseif (in_array($name, $this->nodesToCopy)) { // we are closing a critical CDATA section |
|
| 452 | 452 | |
| 453 | 453 | $this->bufferIsActive = false; |
| 454 | 454 | |
| 455 | 455 | // only for Xliff 2.* |
| 456 | 456 | // write here <mda:metaGroup> and <mda:meta> if already present in the <unit> |
| 457 | - if ( 'mda:metadata' === $name && $this->unitContainsMda && $this->xliffVersion === 2 && !$this->hasWrittenCounts ) { |
|
| 457 | + if ('mda:metadata' === $name && $this->unitContainsMda && $this->xliffVersion === 2 && !$this->hasWrittenCounts) { |
|
| 458 | 458 | |
| 459 | 459 | // we need to update counts here |
| 460 | 460 | $this->updateCounts(); |
| 461 | 461 | $this->hasWrittenCounts = true; |
| 462 | 462 | |
| 463 | 463 | $tag = $this->CDATABuffer; |
| 464 | - $tag .= $this->getWordCountGroupForXliffV2( $this->counts[ 'raw_word_count' ], $this->counts[ 'eq_word_count' ], false ); |
|
| 464 | + $tag .= $this->getWordCountGroupForXliffV2($this->counts['raw_word_count'], $this->counts['eq_word_count'], false); |
|
| 465 | 465 | $tag .= " </mda:metadata>"; |
| 466 | 466 | |
| 467 | 467 | } else { |
@@ -471,59 +471,59 @@ discard block |
||
| 471 | 471 | $this->CDATABuffer = ""; |
| 472 | 472 | |
| 473 | 473 | //flush to pointer |
| 474 | - $this->postProcAndFlush( $this->outputFP, $tag ); |
|
| 475 | - } elseif ( 'segment' === $name ) { |
|
| 474 | + $this->postProcAndFlush($this->outputFP, $tag); |
|
| 475 | + } elseif ('segment' === $name) { |
|
| 476 | 476 | |
| 477 | 477 | // only for Xliff 2.* |
| 478 | 478 | // if segment has no <target> add it BEFORE </segment> |
| 479 | - if ( $this->xliffVersion === 2 && !$this->targetWasWritten ) { |
|
| 479 | + if ($this->xliffVersion === 2 && !$this->targetWasWritten) { |
|
| 480 | 480 | |
| 481 | 481 | $seg = $this->getCurrentSegment(); |
| 482 | 482 | |
| 483 | 483 | // copy attr from <source> |
| 484 | 484 | $tag = '<target'; |
| 485 | - foreach ( $this->sourceAttributes as $k => $v ) { |
|
| 485 | + foreach ($this->sourceAttributes as $k => $v) { |
|
| 486 | 486 | $tag .= " $k=\"$v\""; |
| 487 | 487 | } |
| 488 | 488 | |
| 489 | - $tag .= '>' . $seg[ 'translation' ] . '</target></segment>'; |
|
| 489 | + $tag .= '>' . $seg['translation'] . '</target></segment>'; |
|
| 490 | 490 | } |
| 491 | 491 | |
| 492 | - $this->postProcAndFlush( $this->outputFP, $tag ); |
|
| 492 | + $this->postProcAndFlush($this->outputFP, $tag); |
|
| 493 | 493 | |
| 494 | 494 | // we are leaving <segment>, reset $segmentHasTarget |
| 495 | 495 | $this->targetWasWritten = false; |
| 496 | 496 | |
| 497 | - } elseif ( $name === 'trans-unit' ) { |
|
| 497 | + } elseif ($name === 'trans-unit') { |
|
| 498 | 498 | |
| 499 | 499 | // only for Xliff 1.* |
| 500 | 500 | // handling </trans-unit> closure |
| 501 | - if ( !$this->targetWasWritten ) { |
|
| 501 | + if (!$this->targetWasWritten) { |
|
| 502 | 502 | $seg = $this->getCurrentSegment(); |
| 503 | 503 | $lastMrkState = null; |
| 504 | 504 | $stateProp = ''; |
| 505 | 505 | $tag = ''; |
| 506 | 506 | |
| 507 | 507 | // if there is translation available insert <target> BEFORE </trans-unit> |
| 508 | - if ( isset( $seg[ 'translation' ] ) ) { |
|
| 509 | - list( $stateProp, $lastMrkState ) = $this->setTransUnitState( $seg, $stateProp, $lastMrkState ); |
|
| 510 | - $tag .= $this->createTargetTag( $seg[ 'translation' ], $stateProp ); |
|
| 508 | + if (isset($seg['translation'])) { |
|
| 509 | + list($stateProp, $lastMrkState) = $this->setTransUnitState($seg, $stateProp, $lastMrkState); |
|
| 510 | + $tag .= $this->createTargetTag($seg['translation'], $stateProp); |
|
| 511 | 511 | } |
| 512 | 512 | |
| 513 | 513 | $tag .= '</trans-unit>'; |
| 514 | - $this->postProcAndFlush( $this->outputFP, $tag ); |
|
| 514 | + $this->postProcAndFlush($this->outputFP, $tag); |
|
| 515 | 515 | } else { |
| 516 | - $this->postProcAndFlush( $this->outputFP, '</trans-unit>' ); |
|
| 516 | + $this->postProcAndFlush($this->outputFP, '</trans-unit>'); |
|
| 517 | 517 | } |
| 518 | - } elseif ( $this->bufferIsActive ) { // this is a tag ( <g | <mrk ) inside a seg or seg-source tag |
|
| 518 | + } elseif ($this->bufferIsActive) { // this is a tag ( <g | <mrk ) inside a seg or seg-source tag |
|
| 519 | 519 | $this->CDATABuffer .= "</$name>"; |
| 520 | 520 | // Do NOT Flush |
| 521 | 521 | } else { //generic tag closure do Nothing |
| 522 | 522 | // flush to pointer |
| 523 | - $this->postProcAndFlush( $this->outputFP, $tag ); |
|
| 523 | + $this->postProcAndFlush($this->outputFP, $tag); |
|
| 524 | 524 | } |
| 525 | - } elseif ( $this->CDATABuffer === '<note/>' && $this->bufferIsActive === true ) { |
|
| 526 | - $this->postProcAndFlush( $this->outputFP, '<note/>' ); |
|
| 525 | + } elseif ($this->CDATABuffer === '<note/>' && $this->bufferIsActive === true) { |
|
| 526 | + $this->postProcAndFlush($this->outputFP, '<note/>'); |
|
| 527 | 527 | $this->bufferIsActive = false; |
| 528 | 528 | $this->CDATABuffer = ''; |
| 529 | 529 | $this->isEmpty = false; |
@@ -533,7 +533,7 @@ discard block |
||
| 533 | 533 | } |
| 534 | 534 | |
| 535 | 535 | // check if we are leaving a <trans-unit> (xliff v1.*) or <unit> (xliff v2.*) |
| 536 | - if ( $this->tuTagName === $name ) { |
|
| 536 | + if ($this->tuTagName === $name) { |
|
| 537 | 537 | $this->currentTransUnitTranslate = null; |
| 538 | 538 | $this->inTU = false; |
| 539 | 539 | $this->segmentPositionInTu = -1; |
@@ -548,21 +548,21 @@ discard block |
||
| 548 | 548 | * |
| 549 | 549 | * @param array $listOfSegmentsIds |
| 550 | 550 | */ |
| 551 | - private function setCurrentSegmentArray( array $listOfSegmentsIds = [] ) { |
|
| 551 | + private function setCurrentSegmentArray(array $listOfSegmentsIds = []) { |
|
| 552 | 552 | // $currentSegmentId |
| 553 | - if ( empty( $this->currentSegmentArray ) ) { |
|
| 553 | + if (empty($this->currentSegmentArray)) { |
|
| 554 | 554 | $this->currentSegmentArray = [ |
| 555 | - 'sid' => $listOfSegmentsIds[ 0 ], |
|
| 555 | + 'sid' => $listOfSegmentsIds[0], |
|
| 556 | 556 | 'tid' => $this->currentTransUnitId, |
| 557 | 557 | ]; |
| 558 | 558 | } else { |
| 559 | - if ( $this->currentSegmentArray[ 'tid' ] === $this->currentTransUnitId ) { |
|
| 560 | - $key = array_search( $this->currentSegmentArray[ 'sid' ], $listOfSegmentsIds ); |
|
| 561 | - $this->currentSegmentArray[ 'sid' ] = $listOfSegmentsIds[ $key + 1 ]; |
|
| 562 | - $this->currentSegmentArray[ 'tid' ] = $this->currentTransUnitId; |
|
| 559 | + if ($this->currentSegmentArray['tid'] === $this->currentTransUnitId) { |
|
| 560 | + $key = array_search($this->currentSegmentArray['sid'], $listOfSegmentsIds); |
|
| 561 | + $this->currentSegmentArray['sid'] = $listOfSegmentsIds[$key + 1]; |
|
| 562 | + $this->currentSegmentArray['tid'] = $this->currentTransUnitId; |
|
| 563 | 563 | } else { |
| 564 | 564 | $this->currentSegmentArray = [ |
| 565 | - 'sid' => $listOfSegmentsIds[ 0 ], |
|
| 565 | + 'sid' => $listOfSegmentsIds[0], |
|
| 566 | 566 | 'tid' => $this->currentTransUnitId, |
| 567 | 567 | ]; |
| 568 | 568 | } |
@@ -574,23 +574,23 @@ discard block |
||
| 574 | 574 | */ |
| 575 | 575 | private function updateCounts() { |
| 576 | 576 | // populate counts |
| 577 | - $listOfSegmentsIds = $this->transUnits[ $this->currentTransUnitId ]; |
|
| 577 | + $listOfSegmentsIds = $this->transUnits[$this->currentTransUnitId]; |
|
| 578 | 578 | |
| 579 | 579 | // $currentSegmentId |
| 580 | - if ( !empty( $listOfSegmentsIds ) ) { |
|
| 581 | - $this->setCurrentSegmentArray( $listOfSegmentsIds ); |
|
| 580 | + if (!empty($listOfSegmentsIds)) { |
|
| 581 | + $this->setCurrentSegmentArray($listOfSegmentsIds); |
|
| 582 | 582 | } |
| 583 | 583 | |
| 584 | - if ( $this->xliffVersion === 2 ) { |
|
| 585 | - $seg = $this->segments[ $this->currentSegmentArray[ 'sid' ] ]; |
|
| 586 | - if ( !empty( $seg ) ) { |
|
| 587 | - $this->updateSegmentCounts( $seg ); |
|
| 584 | + if ($this->xliffVersion === 2) { |
|
| 585 | + $seg = $this->segments[$this->currentSegmentArray['sid']]; |
|
| 586 | + if (!empty($seg)) { |
|
| 587 | + $this->updateSegmentCounts($seg); |
|
| 588 | 588 | } |
| 589 | 589 | } else { |
| 590 | - foreach ( $listOfSegmentsIds as $pos => $id ) { |
|
| 591 | - $seg = $this->segments[ $id ]; |
|
| 592 | - if ( !empty( $seg ) ) { |
|
| 593 | - $this->updateSegmentCounts( $seg ); |
|
| 590 | + foreach ($listOfSegmentsIds as $pos => $id) { |
|
| 591 | + $seg = $this->segments[$id]; |
|
| 592 | + if (!empty($seg)) { |
|
| 593 | + $this->updateSegmentCounts($seg); |
|
| 594 | 594 | } |
| 595 | 595 | } |
| 596 | 596 | } |
@@ -601,14 +601,14 @@ discard block |
||
| 601 | 601 | /** |
| 602 | 602 | * @param array $seg |
| 603 | 603 | */ |
| 604 | - private function updateSegmentCounts( array $seg = [] ) { |
|
| 605 | - $this->counts[ 'raw_word_count' ] += $seg[ 'raw_word_count' ]; |
|
| 606 | - $this->counts[ 'eq_word_count' ] += ( floor( $seg[ 'eq_word_count' ] * 100 ) / 100 ); |
|
| 604 | + private function updateSegmentCounts(array $seg = []) { |
|
| 605 | + $this->counts['raw_word_count'] += $seg['raw_word_count']; |
|
| 606 | + $this->counts['eq_word_count'] += (floor($seg['eq_word_count'] * 100) / 100); |
|
| 607 | 607 | } |
| 608 | 608 | |
| 609 | 609 | private function resetCounts() { |
| 610 | - $this->counts[ 'raw_word_count' ] = 0; |
|
| 611 | - $this->counts[ 'eq_word_count' ] = 0; |
|
| 610 | + $this->counts['raw_word_count'] = 0; |
|
| 611 | + $this->counts['eq_word_count'] = 0; |
|
| 612 | 612 | } |
| 613 | 613 | |
| 614 | 614 | /** |
@@ -619,37 +619,37 @@ discard block |
||
| 619 | 619 | * |
| 620 | 620 | * @return string |
| 621 | 621 | */ |
| 622 | - protected function prepareTranslation( $seg, $transUnitTranslation = "" ) { |
|
| 622 | + protected function prepareTranslation($seg, $transUnitTranslation = "") { |
|
| 623 | 623 | $endTags = ""; |
| 624 | 624 | |
| 625 | - $segment = Strings::removeDangerousChars( $seg [ 'segment' ] ); |
|
| 626 | - $translation = Strings::removeDangerousChars( $seg [ 'translation' ] ); |
|
| 627 | - $dataRefMap = ( isset( $seg[ 'data_ref_map' ] ) && $seg[ 'data_ref_map' ] !== null ) ? Strings::jsonToArray( $seg[ 'data_ref_map' ] ) : []; |
|
| 625 | + $segment = Strings::removeDangerousChars($seg ['segment']); |
|
| 626 | + $translation = Strings::removeDangerousChars($seg ['translation']); |
|
| 627 | + $dataRefMap = (isset($seg['data_ref_map']) && $seg['data_ref_map'] !== null) ? Strings::jsonToArray($seg['data_ref_map']) : []; |
|
| 628 | 628 | |
| 629 | - if ( is_null( $seg [ 'translation' ] ) || $seg [ 'translation' ] == '' ) { |
|
| 629 | + if (is_null($seg ['translation']) || $seg ['translation'] == '') { |
|
| 630 | 630 | $translation = $segment; |
| 631 | 631 | } else { |
| 632 | - if ( $this->callback ) { |
|
| 633 | - if ( $this->callback->thereAreErrors( $seg[ 'sid' ], $segment, $translation, $dataRefMap ) ) { |
|
| 632 | + if ($this->callback) { |
|
| 633 | + if ($this->callback->thereAreErrors($seg['sid'], $segment, $translation, $dataRefMap)) { |
|
| 634 | 634 | $translation = '|||UNTRANSLATED_CONTENT_START|||' . $segment . '|||UNTRANSLATED_CONTENT_END|||'; |
| 635 | 635 | } |
| 636 | 636 | } |
| 637 | 637 | } |
| 638 | 638 | |
| 639 | 639 | // for xliff v2 we ignore the marks on purpose |
| 640 | - if ( $this->xliffVersion === 2 ) { |
|
| 640 | + if ($this->xliffVersion === 2) { |
|
| 641 | 641 | return $translation; |
| 642 | 642 | } |
| 643 | 643 | |
| 644 | - if ( $seg[ 'mrk_id' ] !== null && $seg[ 'mrk_id' ] != '' ) { |
|
| 645 | - if ( $this->targetLang === 'ja-JP' ) { |
|
| 646 | - $seg[ 'mrk_succ_tags' ] = ltrim( $seg[ 'mrk_succ_tags' ] ); |
|
| 644 | + if ($seg['mrk_id'] !== null && $seg['mrk_id'] != '') { |
|
| 645 | + if ($this->targetLang === 'ja-JP') { |
|
| 646 | + $seg['mrk_succ_tags'] = ltrim($seg['mrk_succ_tags']); |
|
| 647 | 647 | } |
| 648 | 648 | |
| 649 | - $translation = "<mrk mid=\"" . $seg[ 'mrk_id' ] . "\" mtype=\"seg\">" . $seg[ 'mrk_prev_tags' ] . $translation . $seg[ 'mrk_succ_tags' ] . "</mrk>"; |
|
| 649 | + $translation = "<mrk mid=\"" . $seg['mrk_id'] . "\" mtype=\"seg\">" . $seg['mrk_prev_tags'] . $translation . $seg['mrk_succ_tags'] . "</mrk>"; |
|
| 650 | 650 | } |
| 651 | 651 | |
| 652 | - $transUnitTranslation .= $seg[ 'prev_tags' ] . $translation . $endTags . $seg[ 'succ_tags' ]; |
|
| 652 | + $transUnitTranslation .= $seg['prev_tags'] . $translation . $endTags . $seg['succ_tags']; |
|
| 653 | 653 | |
| 654 | 654 | return $transUnitTranslation; |
| 655 | 655 | } |
@@ -663,15 +663,15 @@ discard block |
||
| 663 | 663 | * |
| 664 | 664 | * @return string |
| 665 | 665 | */ |
| 666 | - private function buildTranslateTag( $targetLang, $stateProp, $translation, $rawWordCount, $eqWordCount ) { |
|
| 667 | - switch ( $this->xliffVersion ) { |
|
| 666 | + private function buildTranslateTag($targetLang, $stateProp, $translation, $rawWordCount, $eqWordCount) { |
|
| 667 | + switch ($this->xliffVersion) { |
|
| 668 | 668 | case 1: |
| 669 | 669 | default: |
| 670 | 670 | $tag = "<target $targetLang $stateProp>$translation</target>"; |
| 671 | 671 | |
| 672 | 672 | // if it's a Trados file don't append count group |
| 673 | - if ( get_class( $this ) !== SdlXliffSAXTranslationReplacer::class ) { |
|
| 674 | - $tag .= $this->getWordCountGroup( $rawWordCount, $eqWordCount ); |
|
| 673 | + if (get_class($this) !== SdlXliffSAXTranslationReplacer::class) { |
|
| 674 | + $tag .= $this->getWordCountGroup($rawWordCount, $eqWordCount); |
|
| 675 | 675 | } |
| 676 | 676 | |
| 677 | 677 | return $tag; |
@@ -687,7 +687,7 @@ discard block |
||
| 687 | 687 | * |
| 688 | 688 | * @return string |
| 689 | 689 | */ |
| 690 | - private function getWordCountGroup( $raw_word_count, $eq_word_count ) { |
|
| 690 | + private function getWordCountGroup($raw_word_count, $eq_word_count) { |
|
| 691 | 691 | return "\n<count-group name=\"$this->currentTransUnitId\"><count count-type=\"x-matecat-raw\">$raw_word_count</count><count count-type=\"x-matecat-weighted\">$eq_word_count</count></count-group>"; |
| 692 | 692 | } |
| 693 | 693 | |
@@ -695,11 +695,11 @@ discard block |
||
| 695 | 695 | * @return array |
| 696 | 696 | */ |
| 697 | 697 | private function getCurrentSegment() { |
| 698 | - if ( $this->currentTransUnitTranslate === 'yes' && isset( $this->transUnits[ $this->currentTransUnitId ] ) ) { |
|
| 699 | - $index = $this->transUnits[ $this->currentTransUnitId ][ $this->segmentPositionInTu ]; |
|
| 698 | + if ($this->currentTransUnitTranslate === 'yes' && isset($this->transUnits[$this->currentTransUnitId])) { |
|
| 699 | + $index = $this->transUnits[$this->currentTransUnitId][$this->segmentPositionInTu]; |
|
| 700 | 700 | |
| 701 | - if ( isset( $this->segments[ $index ] ) ) { |
|
| 702 | - return $this->segments[ $index ]; |
|
| 701 | + if (isset($this->segments[$index])) { |
|
| 702 | + return $this->segments[$index]; |
|
| 703 | 703 | } |
| 704 | 704 | } |
| 705 | 705 | |
@@ -714,10 +714,10 @@ discard block |
||
| 714 | 714 | * |
| 715 | 715 | * @return string |
| 716 | 716 | */ |
| 717 | - private function createTargetTag( $translation, $stateProp ) { |
|
| 717 | + private function createTargetTag($translation, $stateProp) { |
|
| 718 | 718 | $targetLang = 'xml:lang="' . $this->targetLang . '"'; |
| 719 | 719 | |
| 720 | - return $this->buildTranslateTag( $targetLang, $stateProp, $translation, $this->counts[ 'raw_word_count' ], $this->counts[ 'eq_word_count' ] ); |
|
| 720 | + return $this->buildTranslateTag($targetLang, $stateProp, $translation, $this->counts['raw_word_count'], $this->counts['eq_word_count']); |
|
| 721 | 721 | } |
| 722 | 722 | |
| 723 | 723 | /** |
@@ -727,11 +727,11 @@ discard block |
||
| 727 | 727 | * |
| 728 | 728 | * @return string |
| 729 | 729 | */ |
| 730 | - private function getWordCountGroupForXliffV2( $raw_word_count, $eq_word_count, $withMetadataTag = true ) { |
|
| 730 | + private function getWordCountGroupForXliffV2($raw_word_count, $eq_word_count, $withMetadataTag = true) { |
|
| 731 | 731 | $this->mdaGroupCounter++; |
| 732 | 732 | $id = 'word_count_tu_' . $this->mdaGroupCounter; |
| 733 | 733 | |
| 734 | - if ( $withMetadataTag === false ) { |
|
| 734 | + if ($withMetadataTag === false) { |
|
| 735 | 735 | return " <mda:metaGroup id=\"" . $id . "\" category=\"row_xml_attribute\"> |
| 736 | 736 | <mda:meta type=\"x-matecat-raw\">$raw_word_count</mda:meta> |
| 737 | 737 | <mda:meta type=\"x-matecat-weighted\">$eq_word_count</mda:meta> |
@@ -754,19 +754,19 @@ discard block |
||
| 754 | 754 | * |
| 755 | 755 | * @return array |
| 756 | 756 | */ |
| 757 | - private function setTransUnitState( $seg, $state_prop, $lastMrkState ) { |
|
| 758 | - switch ( $seg[ 'status' ] ) { |
|
| 757 | + private function setTransUnitState($seg, $state_prop, $lastMrkState) { |
|
| 758 | + switch ($seg['status']) { |
|
| 759 | 759 | |
| 760 | 760 | case TranslationStatus::STATUS_FIXED: |
| 761 | 761 | case TranslationStatus::STATUS_APPROVED: |
| 762 | - if ( $lastMrkState == null || $lastMrkState == TranslationStatus::STATUS_APPROVED ) { |
|
| 763 | - $state_prop = ( $this->xliffVersion === 2 ) ? "state=\"reviewed\"" : "state=\"signed-off\""; |
|
| 762 | + if ($lastMrkState == null || $lastMrkState == TranslationStatus::STATUS_APPROVED) { |
|
| 763 | + $state_prop = ($this->xliffVersion === 2) ? "state=\"reviewed\"" : "state=\"signed-off\""; |
|
| 764 | 764 | $lastMrkState = TranslationStatus::STATUS_APPROVED; |
| 765 | 765 | } |
| 766 | 766 | break; |
| 767 | 767 | |
| 768 | 768 | case TranslationStatus::STATUS_TRANSLATED: |
| 769 | - if ( $lastMrkState == null || $lastMrkState == TranslationStatus::STATUS_TRANSLATED || $lastMrkState == TranslationStatus::STATUS_APPROVED ) { |
|
| 769 | + if ($lastMrkState == null || $lastMrkState == TranslationStatus::STATUS_TRANSLATED || $lastMrkState == TranslationStatus::STATUS_APPROVED) { |
|
| 770 | 770 | $state_prop = "state=\"translated\""; |
| 771 | 771 | $lastMrkState = TranslationStatus::STATUS_TRANSLATED; |
| 772 | 772 | } |
@@ -774,15 +774,15 @@ discard block |
||
| 774 | 774 | |
| 775 | 775 | case TranslationStatus::STATUS_REJECTED: // if there is a mark REJECTED and there is not a DRAFT, all the trans-unit is REJECTED. In V2 there is no way to mark |
| 776 | 776 | case TranslationStatus::STATUS_REBUTTED: |
| 777 | - if ( ( $lastMrkState == null ) || ( $lastMrkState != TranslationStatus::STATUS_NEW || $lastMrkState != TranslationStatus::STATUS_DRAFT ) ) { |
|
| 778 | - $state_prop = ( $this->xliffVersion === 2 ) ? "state=\"initial\"" : "state=\"needs-review-translation\""; |
|
| 777 | + if (($lastMrkState == null) || ($lastMrkState != TranslationStatus::STATUS_NEW || $lastMrkState != TranslationStatus::STATUS_DRAFT)) { |
|
| 778 | + $state_prop = ($this->xliffVersion === 2) ? "state=\"initial\"" : "state=\"needs-review-translation\""; |
|
| 779 | 779 | $lastMrkState = TranslationStatus::STATUS_REJECTED; |
| 780 | 780 | } |
| 781 | 781 | break; |
| 782 | 782 | |
| 783 | 783 | case TranslationStatus::STATUS_NEW: |
| 784 | - if ( ( $lastMrkState == null ) || $lastMrkState != TranslationStatus::STATUS_DRAFT ) { |
|
| 785 | - $state_prop = ( $this->xliffVersion === 2 ) ? "state=\"initial\"" : "state=\"new\""; |
|
| 784 | + if (($lastMrkState == null) || $lastMrkState != TranslationStatus::STATUS_DRAFT) { |
|
| 785 | + $state_prop = ($this->xliffVersion === 2) ? "state=\"initial\"" : "state=\"new\""; |
|
| 786 | 786 | $lastMrkState = TranslationStatus::STATUS_NEW; |
| 787 | 787 | } |
| 788 | 788 | break; |
@@ -795,7 +795,7 @@ discard block |
||
| 795 | 795 | // this is the case when a segment is not showed in cattool, so the row in |
| 796 | 796 | // segment_translations does not exists and |
| 797 | 797 | // ---> $seg[ 'status' ] is NULL |
| 798 | - if ( $lastMrkState == null ) { //this is the first MRK ID |
|
| 798 | + if ($lastMrkState == null) { //this is the first MRK ID |
|
| 799 | 799 | $state_prop = "state=\"translated\""; |
| 800 | 800 | $lastMrkState = TranslationStatus::STATUS_TRANSLATED; |
| 801 | 801 | } else { |
@@ -804,17 +804,17 @@ discard block |
||
| 804 | 804 | break; |
| 805 | 805 | } |
| 806 | 806 | |
| 807 | - return [ $state_prop, $lastMrkState ]; |
|
| 807 | + return [$state_prop, $lastMrkState]; |
|
| 808 | 808 | } |
| 809 | 809 | |
| 810 | 810 | /** |
| 811 | 811 | * @inheritDoc |
| 812 | 812 | */ |
| 813 | - protected function characterData( $parser, $data ) { |
|
| 813 | + protected function characterData($parser, $data) { |
|
| 814 | 814 | // don't write <target> data |
| 815 | - if ( !$this->inTarget && !$this->bufferIsActive ) { |
|
| 816 | - $this->postProcAndFlush( $this->outputFP, $data ); |
|
| 817 | - } elseif ( $this->bufferIsActive ) { |
|
| 815 | + if (!$this->inTarget && !$this->bufferIsActive) { |
|
| 816 | + $this->postProcAndFlush($this->outputFP, $data); |
|
| 817 | + } elseif ($this->bufferIsActive) { |
|
| 818 | 818 | $this->CDATABuffer .= $data; |
| 819 | 819 | } |
| 820 | 820 | } |
@@ -64,22 +64,22 @@ discard block |
||
| 64 | 64 | * @throws Exception\NotValidFileException |
| 65 | 65 | * @throws Exception\XmlParsingException |
| 66 | 66 | */ |
| 67 | - public function xliffToArray( $xliffContent, $collapseEmptyTags = false) |
|
| 67 | + public function xliffToArray($xliffContent, $collapseEmptyTags = false) |
|
| 68 | 68 | { |
| 69 | 69 | $xliff = []; |
| 70 | 70 | $xliffContent = self::forceUft8Encoding($xliffContent, $xliff); |
| 71 | 71 | $xliffVersion = XliffVersionDetector::detect($xliffContent); |
| 72 | 72 | $info = XliffProprietaryDetect::getInfoFromXliffContent($xliffContent); |
| 73 | 73 | |
| 74 | - if($xliffVersion === 1){ |
|
| 74 | + if ($xliffVersion === 1) { |
|
| 75 | 75 | $xliffContent = self::removeInternalFileTagFromContent($xliffContent, $xliff); |
| 76 | 76 | } |
| 77 | 77 | |
| 78 | - if($xliffVersion === 2){ |
|
| 78 | + if ($xliffVersion === 2) { |
|
| 79 | 79 | $xliffContent = self::escapeDataInOriginalMap($xliffContent); |
| 80 | 80 | } |
| 81 | 81 | |
| 82 | - if($collapseEmptyTags === false){ |
|
| 82 | + if ($collapseEmptyTags === false) { |
|
| 83 | 83 | $xliffContent = self::insertPlaceholderInEmptyTags($xliffContent); |
| 84 | 84 | } |
| 85 | 85 | |
@@ -104,8 +104,8 @@ discard block |
||
| 104 | 104 | $enc = mb_detect_encoding($xliffContent); |
| 105 | 105 | |
| 106 | 106 | if ($enc !== 'UTF-8') { |
| 107 | - $xliff[ 'parser-warnings' ][] = "Input identified as $enc ans converted UTF-8. May not be a problem if the content is English only"; |
|
| 108 | - $s = iconv( $enc, 'UTF-8', $xliffContent ); |
|
| 107 | + $xliff['parser-warnings'][] = "Input identified as $enc ans converted UTF-8. May not be a problem if the content is English only"; |
|
| 108 | + $s = iconv($enc, 'UTF-8', $xliffContent); |
|
| 109 | 109 | $xliffContent = $s !== false ? $s : ""; |
| 110 | 110 | } |
| 111 | 111 | |
@@ -125,22 +125,22 @@ discard block |
||
| 125 | 125 | private static function removeInternalFileTagFromContent($xliffContent, &$xliff) |
| 126 | 126 | { |
| 127 | 127 | $index = 1; |
| 128 | - $a = Strings::preg_split( '|<internal-file[\s>]|si', $xliffContent ); |
|
| 128 | + $a = Strings::preg_split('|<internal-file[\s>]|si', $xliffContent); |
|
| 129 | 129 | |
| 130 | 130 | // no match, return original string |
| 131 | - if(count($a) === 1){ |
|
| 131 | + if (count($a) === 1) { |
|
| 132 | 132 | return $a[0]; |
| 133 | 133 | } |
| 134 | 134 | |
| 135 | - $b = Strings::preg_split( '|</internal-file>|si', $a[1] ); |
|
| 136 | - $strippedContent = $a[0].$b[1]; |
|
| 137 | - $xliff['files'][$index][ 'reference' ][] = self::extractBase64($b[0]); |
|
| 135 | + $b = Strings::preg_split('|</internal-file>|si', $a[1]); |
|
| 136 | + $strippedContent = $a[0] . $b[1]; |
|
| 137 | + $xliff['files'][$index]['reference'][] = self::extractBase64($b[0]); |
|
| 138 | 138 | $index++; |
| 139 | 139 | |
| 140 | - if(isset($a[2])){ |
|
| 141 | - $c = Strings::preg_split( '|</internal-file[\s>]|si', $a[2] ); |
|
| 140 | + if (isset($a[2])) { |
|
| 141 | + $c = Strings::preg_split('|</internal-file[\s>]|si', $a[2]); |
|
| 142 | 142 | $strippedContent .= $c[1]; |
| 143 | - $xliff['files'][$index][ 'reference' ][] = self::extractBase64($c[0]); |
|
| 143 | + $xliff['files'][$index]['reference'][] = self::extractBase64($c[0]); |
|
| 144 | 144 | } |
| 145 | 145 | |
| 146 | 146 | return $strippedContent; |
@@ -177,8 +177,8 @@ discard block |
||
| 177 | 177 | */ |
| 178 | 178 | private static function escapeDataInOriginalMap($xliffContent) |
| 179 | 179 | { |
| 180 | - $xliffContent = preg_replace_callback('/<data(.*?)>(.*?)<\/data>/iU', [XliffParser::class, 'replaceSpace' ], $xliffContent); |
|
| 181 | - $xliffContent = preg_replace_callback('/<data(.*?)>(.*?)<\/data>/iU', [XliffParser::class, 'replaceXliffTags' ], $xliffContent); |
|
| 180 | + $xliffContent = preg_replace_callback('/<data(.*?)>(.*?)<\/data>/iU', [XliffParser::class, 'replaceSpace'], $xliffContent); |
|
| 181 | + $xliffContent = preg_replace_callback('/<data(.*?)>(.*?)<\/data>/iU', [XliffParser::class, 'replaceXliffTags'], $xliffContent); |
|
| 182 | 182 | |
| 183 | 183 | return $xliffContent; |
| 184 | 184 | } |
@@ -201,11 +201,11 @@ discard block |
||
| 201 | 201 | { |
| 202 | 202 | preg_match_all('/<([a-zA-Z0-9._-]+)[^>]*><\/\1>/sm', $xliffContent, $emptyTagMatches); |
| 203 | 203 | |
| 204 | - if(!empty($emptyTagMatches[0])){ |
|
| 205 | - foreach ($emptyTagMatches[0] as $index => $emptyTagMatch){ |
|
| 204 | + if (!empty($emptyTagMatches[0])) { |
|
| 205 | + foreach ($emptyTagMatches[0] as $index => $emptyTagMatch) { |
|
| 206 | 206 | $matchedTag = $emptyTagMatches[1][$index]; |
| 207 | - $subst = Placeholder::EMPTY_TAG_PLACEHOLDER.'</'.$matchedTag.'>'; |
|
| 208 | - $replacedTag = str_replace('</'.$matchedTag.'>', $subst, $emptyTagMatch); |
|
| 207 | + $subst = Placeholder::EMPTY_TAG_PLACEHOLDER . '</' . $matchedTag . '>'; |
|
| 208 | + $replacedTag = str_replace('</' . $matchedTag . '>', $subst, $emptyTagMatch); |
|
| 209 | 209 | $xliffContent = str_replace($emptyTagMatch, $replacedTag, $xliffContent); |
| 210 | 210 | } |
| 211 | 211 | } |
@@ -226,7 +226,7 @@ discard block |
||
| 226 | 226 | $content = str_replace('\n', Placeholder::NEW_LINE_PLACEHOLDER, $content); |
| 227 | 227 | $content = str_replace('\t', Placeholder::TAB_PLACEHOLDER, $content); |
| 228 | 228 | |
| 229 | - return '<data'.$matches[1].'>'.$content.'</data>'; |
|
| 229 | + return '<data' . $matches[1] . '>' . $content . '</data>'; |
|
| 230 | 230 | } |
| 231 | 231 | |
| 232 | 232 | /** |
@@ -239,11 +239,11 @@ discard block |
||
| 239 | 239 | $xliffTags = XliffTags::$tags; |
| 240 | 240 | $content = $matches[2]; |
| 241 | 241 | |
| 242 | - foreach ($xliffTags as $xliffTag){ |
|
| 243 | - $content = preg_replace( '|<('.$xliffTag.'.*?)>|si', Placeholder::LT_PLACEHOLDER . "$1" . Placeholder::GT_PLACEHOLDER, $content ); |
|
| 244 | - $content = preg_replace( '|<(/'.$xliffTag.')>|si', Placeholder::LT_PLACEHOLDER . "$1" . Placeholder::GT_PLACEHOLDER, $content ); |
|
| 242 | + foreach ($xliffTags as $xliffTag) { |
|
| 243 | + $content = preg_replace('|<(' . $xliffTag . '.*?)>|si', Placeholder::LT_PLACEHOLDER . "$1" . Placeholder::GT_PLACEHOLDER, $content); |
|
| 244 | + $content = preg_replace('|<(/' . $xliffTag . ')>|si', Placeholder::LT_PLACEHOLDER . "$1" . Placeholder::GT_PLACEHOLDER, $content); |
|
| 245 | 245 | } |
| 246 | 246 | |
| 247 | - return '<data'.$matches[1].'>'.$content.'</data>'; |
|
| 247 | + return '<data' . $matches[1] . '>' . $content . '</data>'; |
|
| 248 | 248 | } |
| 249 | 249 | } |