MsDoc Reader: Support for UTF-8 characters (#2664)

Author: Progi1984

docs/changes/1.x/1.3.0.md

@@ -11,6 +11,7 @@
 - Word2007 Reader : Support for FormFields by [@vincentKool](https://github.com/vincentKool) in [#2653](https://github.com/PHPOffice/PHPWord/pull/2653)
 - RTF Writer : Support for Table Border Style fixing [#345](https://github.com/PHPOffice/PHPWord/issues/345) by [@Progi1984](https://github.com/Progi1984) in [#2656](https://github.com/PHPOffice/PHPWord/pull/2656)
 - Word2007 Reader: Support the page break (<w:lastRenderedPageBreak/>) by [@stanolacko](https://github.com/stanolacko) in [#2662](https://github.com/PHPOffice/PHPWord/pull/2662)
+- MsDoc Reader: Support for UTF-8 characters by [@Progi1984] fixing [#881](https://github.com/PHPOffice/PHPWord/issues/881), [#1454](https://github.com/PHPOffice/PHPWord/issues/1454), [#1817](https://github.com/PHPOffice/PHPWord/issues/1817), [#1927](https://github.com/PHPOffice/PHPWord/issues/1927), [#2383](https://github.com/PHPOffice/PHPWord/issues/2383), [#2565](https://github.com/PHPOffice/PHPWord/issues/2565) in [#2664](https://github.com/PHPOffice/PHPWord/pull/2664)
 
 ### Bug fixes
 

src/PhpWord/Reader/MsDoc.php

@@ -1279,10 +1279,12 @@ private function readRecordPlcfBtePapx(): void
                     break;
                 }
                 $strLen = $arrayRGFC[$key + 1] - $arrayRGFC[$key] - 1;
-                for ($inc = 0; $inc < $strLen; ++$inc) {
-                    $byte = self::getInt1d($this->dataWorkDocument, $arrayRGFC[$key] + $inc);
+                for ($inc = 0; $inc < ($strLen * 2); ++$inc) {
+                    $byte = self::getInt2d($this->dataWorkDocument, $arrayRGFC[$key] + ($inc * 2));
                     if ($byte > 0) {
-                        $string .= chr($byte);
+                        $string .= mb_chr($byte, 'UTF-8');
+                    } else {
+                        break;
                     }
                 }
             }
@@ -2331,7 +2333,7 @@ private function generatePhpWord(): void
             foreach ($this->arrayParagraphs as $itmParagraph) {
                 $textPara = $itmParagraph;
                 foreach ($this->arrayCharacters as $oCharacters) {
-                    $subText = substr($textPara, $oCharacters->pos_start, $oCharacters->pos_len);
+                    $subText = mb_substr($textPara, $oCharacters->pos_start, $oCharacters->pos_len);
                     $subText = str_replace(chr(13), PHP_EOL, $subText);
                     $arrayText = explode(PHP_EOL, $subText);
                     if (end($arrayText) == '') {

tests/PhpWordTests/Reader/MsDocTest.php

@@ -18,7 +18,9 @@
 namespace PhpOffice\PhpWordTests\Reader;
 
 use Exception;
+use PhpOffice\PhpWord\Element\Text;
 use PhpOffice\PhpWord\IOFactory;
+use PhpOffice\PhpWord\PhpWord;
 use PhpOffice\PhpWord\Reader\MsDoc;
 
 /**
@@ -50,14 +52,20 @@ public function testCanReadFailed(): void
         self::assertFalse($object->canRead($filename));
     }
 
-    /**
-     * Load.
-     */
-    public function testLoad(): void
+    public function testLoadBasic(): void
     {
         $filename = __DIR__ . '/../_files/documents/reader.doc';
         $phpWord = IOFactory::load($filename, 'MsDoc');
-        self::assertInstanceOf('PhpOffice\\PhpWord\\PhpWord', $phpWord);
+        self::assertInstanceOf(PhpWord::class, $phpWord);
+
+        $sections = $phpWord->getSections();
+        self::assertCount(1, $sections);
+        $elements = $sections[0]->getElements();
+        self::assertArrayHasKey(0, $elements);
+        /** @var Text $element0 */
+        $element0 = $elements[0];
+        self::assertInstanceOf(Text::class, $element0);
+        self::assertEquals('Welcome to PhpWord', $element0->getText());
     }
 
     public function testLoadHalfPointFont(): void
@@ -76,6 +84,54 @@ public function testLoadHalfPointFont(): void
         }
     }
 
+    public function testLoadChinese(): void
+    {
+        $filename = __DIR__ . '/../_files/documents/docChinese.doc';
+        $phpWord = IOFactory::load($filename, 'MsDoc');
+        self::assertInstanceOf(PhpWord::class, $phpWord);
+
+        $sections = $phpWord->getSections();
+        self::assertCount(1, $sections);
+        $elements = $sections[0]->getElements();
+        self::assertArrayHasKey(0, $elements);
+        /** @var Text $element0 */
+        $element0 = $elements[0];
+        self::assertInstanceOf(Text::class, $element0);
+        self::assertEquals('OKKI AI 客户案例', $element0->getText());
+    }
+
+    public function testLoadCzech(): void
+    {
+        $filename = __DIR__ . '/../_files/documents/docCzech.doc';
+        $phpWord = IOFactory::load($filename, 'MsDoc');
+        self::assertInstanceOf(PhpWord::class, $phpWord);
+
+        $sections = $phpWord->getSections();
+        self::assertCount(1, $sections);
+        $elements = $sections[0]->getElements();
+        self::assertArrayHasKey(0, $elements);
+        /** @var Text $element0 */
+        $element0 = $elements[0];
+        self::assertInstanceOf(Text::class, $element0);
+        self::assertEquals('Příliš žluťoučký kůň pěl ďábelské ódy', $element0->getText());
+    }
+
+    public function testLoadSlovak(): void
+    {
+        $filename = __DIR__ . '/../_files/documents/docSlovak.doc';
+        $phpWord = IOFactory::load($filename, 'MsDoc');
+        self::assertInstanceOf(PhpWord::class, $phpWord);
+
+        $sections = $phpWord->getSections();
+        self::assertCount(1, $sections);
+        $elements = $sections[0]->getElements();
+        self::assertArrayHasKey(0, $elements);
+        /** @var Text $element0 */
+        $element0 = $elements[0];
+        self::assertInstanceOf(Text::class, $element0);
+        self::assertEquals('Pondelok', $element0->getText());
+    }
+
     /**
      * Test exception on not existing file.
      */