[WIP] Feature: WPS Writer Support

src/PhpWord/IOFactory.php

@@ -36,7 +36,7 @@ abstract class IOFactory
      */
     public static function createWriter(PhpWord $phpWord, $name = 'Word2007')
     {
-        if ($name !== 'WriterInterface' && !in_array($name, ['ODText', 'RTF', 'Word2007', 'HTML', 'PDF', 'EPub3'], true)) {
+        if ($name !== 'WriterInterface' && !in_array($name, ['ODText', 'RTF', 'Word2007', 'HTML', 'PDF', 'EPub3', 'WPS'], true)) {
             throw new Exception("\"{$name}\" is not a valid writer.");
         }
 

src/PhpWord/Reader/WPS.php

@@ -0,0 +1,132 @@
+<?php
+
+/**
+ * This file is part of PHPWord - A pure PHP library for reading and writing
+ * word processing documents.
+ *
+ * PHPWord is free software distributed under the terms of the GNU Lesser
+ * General Public License version 3 as published by the Free Software Foundation.
+ *
+ * For the full copyright and license information, please read the LICENSE
+ * file that was distributed with this source code. For the full list of
+ * contributors, visit https://github.com/PHPOffice/PHPWord/contributors.
+ *
+ * @see         https://github.com/PHPOffice/PHPWord
+ *
+ * @license     http://www.gnu.org/licenses/lgpl.txt LGPL version 3
+ */
+
+namespace PhpOffice\PhpWord\Reader;
+
+use PhpOffice\PhpWord\PhpWord;
+use PhpOffice\PhpWord\Shared\XMLReader;
+
+/**
+ * Reader for WPS.
+ */
+class WPS extends AbstractReader implements ReaderInterface
+{
+    /**
+     * Magic pattern to identify WPS binary format files.
+     */
+    const WPS_MAGIC_PATTERN = '/(CHNKWKS|CHNKINK)/';
+
+    /**
+     * Loads PhpWord from file.
+     *
+     * @param string $docFile
+     *
+     * @return PhpWord
+     */
+    public function load($docFile)
+    {
+        $phpWord = new PhpWord();
+
+        // Check if this is a binary WPS file
+        if ($this->isBinaryWpsFile($docFile)) {
+            return $this->loadBinaryWps($docFile, $phpWord);
+        }
+
+        // Otherwise process as XML-based WPS file
+        $relationships = $this->readRelationships($docFile);
+        $readerParts = [
+            'content.xml' => 'Content',
+            'meta.xml' => 'Meta',
+        ];
+        foreach ($readerParts as $xmlFile => $partName) {
+            $this->readPart($phpWord, $relationships, $partName, $docFile, $xmlFile);
+        }
+
+        return $phpWord;
+    }
+
+    /**
+     * Check if the file is a binary WPS file.
+     *
+     * @param string $docFile
+     *
+     * @return bool
+     */
+    private function isBinaryWpsFile($docFile)
+    {
+        $fileContent = file_get_contents($docFile, false, null, 0, 1024);
+        if (!is_string($fileContent)) {
+            return false;
+        }
+
+        return preg_match(self::WPS_MAGIC_PATTERN, $fileContent) === 1;
+    }
+
+    /**
+     * Load a binary WPS file.
+     *
+     * @param string $docFile
+     *
+     * @return PhpWord
+     */
+    private function loadBinaryWps($docFile, PhpWord $phpWord)
+    {
+        $reader = new WPSBinaryReader();
+        $text = $reader->extractText($docFile);
+
+        if (!empty($text)) {
+            $section = $phpWord->addSection();
+            $section->addText($text);
+        }
+
+        return $phpWord;
+    }
+
+    /**
+     * Read document part.
+     */
+    private function readPart(PhpWord $phpWord, array $relationships, string $partName, string $docFile, string $xmlFile): void
+    {
+        $partClass = "PhpOffice\\PhpWord\\Reader\\WPS\\{$partName}";
+        if (class_exists($partClass)) {
+            /** @var WPS\AbstractPart $part Type hint */
+            $part = new $partClass($docFile, $xmlFile);
+            $part->setRels($relationships);
+            $part->read($phpWord);
+        }
+    }
+
+    /**
+     * Read all relationship files.
+     */
+    private function readRelationships(string $docFile): array
+    {
+        $rels = [];
+        $xmlFile = 'META-INF/manifest.xml';
+        $xmlReader = new XMLReader();
+        $xmlReader->getDomFromZip($docFile, $xmlFile);
+        $nodes = $xmlReader->getElements('manifest:file-entry');
+        foreach ($nodes as $node) {
+            $type = $xmlReader->getAttribute('manifest:media-type', $node);
+            $target = $xmlReader->getAttribute('manifest:full-path', $node);
+            $rels[] = ['type' => $type, 'target' => $target];
+        }
+
+        return $rels;
+    }
+}

src/PhpWord/Reader/WPS/AbstractPart.php

@@ -0,0 +1,30 @@
+<?php
+
+/**
+ * This file is part of PHPWord - A pure PHP library for reading and writing
+ * word processing documents.
+ *
+ * PHPWord is free software distributed under the terms of the GNU Lesser
+ * General Public License version 3 as published by the Free Software Foundation.
+ *
+ * For the full copyright and license information, please read the LICENSE
+ * file that was distributed with this source code. For the full list of
+ * contributors, visit https://github.com/PHPOffice/PHPWord/contributors.
+ *
+ * @see         https://github.com/PHPOffice/PHPWord
+ *
+ * @license     http://www.gnu.org/licenses/lgpl.txt LGPL version 3
+ */
+
+namespace PhpOffice\PhpWord\Reader\WPS;
+
+use PhpOffice\PhpWord\Reader\Word2007\AbstractPart as Word2007AbstractPart;
+
+/**
+ * Abstract part reader for WPS format.
+ *
+ * @since 0.18.0
+ */
+abstract class AbstractPart extends Word2007AbstractPart
+{
+}

src/PhpWord/Reader/WPS/Content.php

@@ -0,0 +1,125 @@
+<?php
+
+/**
+ * This file is part of PHPWord - A pure PHP library for reading and writing
+ * word processing documents.
+ *
+ * PHPWord is free software distributed under the terms of the GNU Lesser
+ * General Public License version 3 as published by the Free Software Foundation.
+ *
+ * For the full copyright and license information, please read the LICENSE
+ * file that was distributed with this source code. For the full list of
+ * contributors, visit https://github.com/PHPOffice/PHPWord/contributors.
+ *
+ * @see         https://github.com/PHPOffice/PHPWord
+ *
+ * @license     http://www.gnu.org/licenses/lgpl.txt LGPL version 3
+ */
+
+namespace PhpOffice\PhpWord\Reader\WPS;
+
+use DOMElement;
+use PhpOffice\PhpWord\PhpWord;
+use PhpOffice\PhpWord\Shared\XMLReader;
+
+/**
+ * WPS content reader.
+ *
+ * @since 0.18.0
+ */
+class Content extends AbstractPart
+{
+    /**
+     * Read content.xml.
+     */
+    public function read(PhpWord $phpWord): void
+    {
+        // Prevent using an empty file as ZipArchive to avoid deprecation warnings
+        if (filesize($this->docFile) === 0) {
+            return;
+        }
+
+        $xmlReader = new XMLReader();
+        $xmlReader->getDomFromZip($this->docFile, $this->xmlFile);
+        $nodes = $xmlReader->getElements('office:body/office:text/*');
+        if ($nodes->length > 0) {
+            $section = $phpWord->addSection();
+            foreach ($nodes as $node) {
+                $this->readElement($xmlReader, $node, $section);
+            }
+        }
+    }
+
+    /**
+     * Read element based on node name.
+     */
+    private function readElement(XMLReader $xmlReader, DOMElement $node, \PhpOffice\PhpWord\Element\Section $parent): void
+    {
+        switch ($node->nodeName) {
+            case 'text:p':
+                $this->readParagraph($xmlReader, $node, $parent);
+
+                break;
+            case 'text:h':
+                $this->readHeading($xmlReader, $node, $parent);
+
+                break;
+            case 'table:table':
+                // Implement table reading as needed
+                break;
+        }
+    }
+
+    /**
+     * Read paragraph.
+     */
+    protected function readParagraph(XMLReader $xmlReader, DOMElement $domNode, $parent, $docPart = 'document'): void
+    {
+        $textRun = $parent->addTextRun();
+        $nodes = $xmlReader->getElements('*', $domNode);
+        foreach ($nodes as $textNode) {
+            if ($textNode->nodeName == 'text:span') {
+                $text = $xmlReader->getValue('.', $textNode);
+                if (!empty($text)) {
+                    $textRun->addText($text);
+                }
+            } elseif ($textNode->nodeName == 'text:line-break') {
+                $textRun->addTextBreak();
+            }
+        }
+
+        // If the paragraph has direct text content (not wrapped in spans)
+        $textContent = $this->getDirectTextContent($domNode);
+        if (!empty($textContent)) {
+            $textRun->addText($textContent);
+        }
+    }
+
+    /**
+     * Read heading.
+     */
+    private function readHeading(XMLReader $xmlReader, DOMElement $node, \PhpOffice\PhpWord\Element\Section $parent): void
+    {
+        $text = $xmlReader->getValue('.', $node);
+        $level = $xmlReader->getAttribute('text:outline-level', $node);
+        if (empty($level)) {
+            $level = 1;
+        }
+        $parent->addTitle($text, (int) $level);
+    }
+
+    /**
+     * Get direct text content of a node, excluding child element content.
+     */
+    private function getDirectTextContent(DOMElement $node): string
+    {
+        $textContent = '';
+        foreach ($node->childNodes as $child) {
+            if ($child->nodeType === XML_TEXT_NODE) {
+                $textContent .= $child->nodeValue;
+            }
+        }
+
+        return trim($textContent);
+    }
+}

src/PhpWord/Reader/WPS/Meta.php

@@ -0,0 +1,83 @@
+<?php
+
+/**
+ * This file is part of PHPWord - A pure PHP library for reading and writing
+ * word processing documents.
+ *
+ * PHPWord is free software distributed under the terms of the GNU Lesser
+ * General Public License version 3 as published by the Free Software Foundation.
+ *
+ * For the full copyright and license information, please read the LICENSE
+ * file that was distributed with this source code. For the full list of
+ * contributors, visit https://github.com/PHPOffice/PHPWord/contributors.
+ *
+ * @see         https://github.com/PHPOffice/PHPWord
+ *
+ * @license     http://www.gnu.org/licenses/lgpl.txt LGPL version 3
+ */
+
+namespace PhpOffice\PhpWord\Reader\WPS;
+
+use PhpOffice\PhpWord\PhpWord;
+use PhpOffice\PhpWord\Shared\XMLReader;
+
+/**
+ * WPS meta reader.
+ *
+ * @since 0.18.0
+ */
+class Meta extends AbstractPart
+{
+    /**
+     * Read meta.xml.
+     */
+    public function read(PhpWord $phpWord): void
+    {
+        $xmlReader = new XMLReader();
+        $xmlReader->getDomFromZip($this->docFile, $this->xmlFile);
+
+        $docProps = $phpWord->getDocInfo();
+
+        // Title
+        $title = $xmlReader->getValue('office:meta/dc:title');
+        if (!empty($title)) {
+            $docProps->setTitle($title);
+        }
+
+        // Subject
+        $subject = $xmlReader->getValue('office:meta/dc:subject');
+        if (!empty($subject)) {
+            $docProps->setSubject($subject);
+        }
+
+        // Creator
+        $creator = $xmlReader->getValue('office:meta/meta:initial-creator');
+        if (!empty($creator)) {
+            $docProps->setCreator($creator);
+        }
+
+        // Keywords
+        $keywords = $xmlReader->getValue('office:meta/meta:keyword');
+        if (!empty($keywords)) {
+            $docProps->setKeywords($keywords);
+        }
+
+        // Description
+        $description = $xmlReader->getValue('office:meta/dc:description');
+        if (!empty($description)) {
+            $docProps->setDescription($description);
+        }
+
+        // Category
+        $category = $xmlReader->getValue('office:meta/meta:user-defined[@meta:name="Category"]');
+        if (!empty($category)) {
+            $docProps->setCategory($category);
+        }
+
+        // Company
+        $company = $xmlReader->getValue('office:meta/meta:user-defined[@meta:name="Company"]');
+        if (!empty($company)) {
+            $docProps->setCompany($company);
+        }
+    }
+}