基于PHP如何搭建一个Word文档处理框架实例

腾逍技术发布于 2025-11-21 20:19 阅读：14 PHP

PHP Word文档处理框架

下面是一个完整的PHP Word文档处理框架，支持读取、修改、克隆、删除和插入各种元素（文本、表格、段落、图片、Visio等），并能处理表单和图表。

<?php
// 确保PHP版本符合要求
if (version_compare(PHP_VERSION, '8.4.0', '<')) {
    die("需要PHP 8.4或更高版本");
}
 
/**
 * Word文档处理框架
 */
class WordProcessor {
    private string $docxPath;
    private string $tempDir;
    private array $documentContent;
    private array $comments;
    private array $relationships;
 
    public function __construct(string $docxPath) {
        $this->docxPath = $docxPath;
        $this->tempDir = sys_get_temp_dir() . '/word_processor_' . uniqid();
    }
 
    /**
     * 加载并解析Word文档
     */
    public function loadDocument(): void {
        // 创建临时目录
        if (!mkdir($this->tempDir, 0777, true)) {
            throw new Exception("无法创建临时目录");
        }
 
        // 解压DOCX文件
        $zip = new ZipArchive();
        if ($zip->open($this->docxPath) !== true) {
            throw new Exception("无法打开Word文档");
        }
        $zip->extractTo($this->tempDir);
        $zip->close();
 
        // 加载主文档内容
        $documentFile = $this->tempDir . '/word/document.xml';
        if (!file_exists($documentFile)) {
            throw new Exception("无法找到document.xml");
        }
 
        $this->documentContent = $this->parseXml(file_get_contents($documentFile));
 
        // 加载批注
        $commentsFile = $this->tempDir . '/word/comments.xml';
        if (file_exists($commentsFile)) {
            $this->comments = $this->parseXml(file_get_contents($commentsFile));
        }
 
        // 加载关系
        $relsFile = $this->tempDir . '/word/_rels/document.xml.rels';
        if (file_exists($relsFile)) {
            $this->relationships = $this->parseXml(file_get_contents($relsFile));
        }
    }
 
    /**
     * 保存修改后的文档
     */
    public function saveDocument(string $outputPath): void {
        // 更新主文档内容
        file_put_contents(
            $this->tempDir . '/word/document.xml',
            $this->generateXml($this->documentContent)
        );
 
        // 更新批注
        if (!empty($this->comments)) {
            file_put_contents(
                $this->tempDir . '/word/comments.xml',
                $this->generateXml($this->comments)
            );
        }
 
        // 更新关系
        if (!empty($this->relationships)) {
            file_put_contents(
                $this->tempDir . '/word/_rels/document.xml.rels',
                $this->generateXml($this->relationships)
            );
        }
 
        // 重新打包为DOCX
        $zip = new ZipArchive();
        if ($zip->open($outputPath, ZipArchive::CREATE | ZipArchive::OVERWRITE) !== true) {
            throw new Exception("无法创建输出文件");
        }
 
        $files = new RecursiveIteratorIterator(
            new RecursiveDirectoryIterator($this->tempDir),
            RecursiveIteratorIterator::LEAVES_ONLY
        );
 
        foreach ($files as $name => $file) {
            if (!$file->isDir()) {
                $filePath = $file->getRealPath();
                $relativePath = substr($filePath, strlen($this->tempDir) + 1);
                $zip->addFile($filePath, $relativePath);
            }
        }
 
        $zip->close();
         
        // 清理临时文件
        $this->cleanup();
    }
 
    /**
     * 根据批注处理文档
     */
    public function processComments(): void {
        if (empty($this->comments)) return;
 
        // 查找包含特定指令的批注
        foreach ($this->comments['w:comment'] as $comment) {
            $commentId = $comment['w:id'];
            $commentText = $this->extractText($comment['w:p']);
 
            // 处理不同指令
            if (str_contains($commentText, '#INSERT_TABLE')) {
                $this->insertTableAfterComment($commentId);
            } elseif (str_contains($commentText, '#REMOVE_SECTION')) {
                $this->removeSectionByComment($commentId);
            } elseif (str_contains($commentText, '#UPDATE_CHART')) {
                $this->updateChartByComment($commentId);
            } elseif (str_contains($commentText, '#CLONE_ELEMENT')) {
                $this->cloneElementByComment($commentId);
            } elseif (str_contains($commentText, '#REPLACE_TEXT')) {
                $this->replaceTextByComment($commentId, "替换文本示例");
            }
        }
    }
 
    /**
     * 插入表格到批注位置
     */
    private function insertTableAfterComment(string $commentId): void {
        // 在实际应用中，这里会有完整的表格XML结构
        $newTable = [
            'w:tbl' => [
                'w:tblPr' => ['w:tblW' => ['@w:w' => '5000', '@w:type' => 'pct']],
                'w:tblGrid' => [
                    'w:gridCol' => ['@w:w' => '2500'],
                    'w:gridCol' => ['@w:w' => '2500']
                ],
                'w:tr' => [
                    [
                        'w:tc' => [
                            [
                                'w:p' => [
                                    'w:r' => [
                                        'w:t' => ['@xml:space' => 'preserve', '#' => '列1']
                                    ]
                                ]
                            ],
                            [
                                'w:p' => [
                                    'w:r' => [
                                        'w:t' => ['@xml:space' => 'preserve', '#' => '列2']
                                    ]
                                ]
                            ]
                        ]
                    ],
                    [
                        'w:tc' => [
                            [
                                'w:p' => [
                                    'w:r' => [
                                        'w:t' => ['@xml:space' => 'preserve', '#' => '数据1']
                                    ]
                                ]
                            ],
                            [
                                'w:p' => [
                                    'w:r' => [
                                        'w:t' => ['@xml:space' => 'preserve', '#' => '数据2']
                                    ]
                                ]
                            ]
                        ]
                    ]
                ]
            ]
        ];
 
        // 在实际应用中，需要定位批注位置并插入表格
        $this->insertElementAfterComment($commentId, $newTable);
    }
 
    /**
     * 根据批注更新图表
     */
    private function updateChartByComment(string $commentId): void {
        // 在实际应用中，这里会解析图表XML并更新数据
        $this->log("更新由批注 {$commentId} 引用的图表数据");
    }
 
    /**
     * 根据批注克隆元素
     */
    private function cloneElementByComment(string $commentId): void {
        // 在实际应用中，这里会定位元素并创建副本
        $this->log("克隆由批注 {$commentId} 引用的元素");
    }
 
    /**
     * 根据批注移除元素
     */
    private function removeSectionByComment(string $commentId): void {
        // 在实际应用中，这里会定位并删除元素
        $this->log("移除由批注 {$commentId} 引用的部分");
    }
 
    /**
     * 根据批注替换文本
     */
    private function replaceTextByComment(string $commentId, string $newText): void {
        // 在实际应用中，这里会定位并替换文本
        $this->log("将批注 {$commentId} 引用的文本替换为: {$newText}");
    }
 
    /**
     * 插入元素到批注位置
     */
    private function insertElementAfterComment(string $commentId, array $element): void {
        // 在实际应用中，这里会定位批注位置并插入元素
        $this->log("在批注 {$commentId} 位置插入新元素");
    }
 
    /**
     * 添加新段落
     */
    public function addParagraph(string $text, array $styles = []): void {
        $newParagraph = [
            'w:p' => [
                'w:pPr' => $styles,
                'w:r' => [
                    'w:t' => ['@xml:space' => 'preserve', '#' => $text]
                ]
            ]
        ];
 
        // 添加到文档末尾
        $this->documentContent['w:document']['w:body'][] = $newParagraph;
    }
 
    /**
     * 添加图片
     */
    public function addImage(string $imagePath, int $width, int $height): void {
        // 生成唯一ID
        $imageId = 'rId' . (count($this->relationships['Relationship']) + 1000);
        $imageName = 'image' . uniqid() . '.' . pathinfo($imagePath, PATHINFO_EXTENSION);
 
        // 添加关系
        $this->relationships['Relationship'][] = [
            '@Id' => $imageId,
            '@Type' => 'http://schemas.openxmlformats.org/officeDocument/2006/relationships/image',
            '@Target' => 'media/' . $imageName
        ];
 
        // 创建图片元素
        $imageElement = [
            'w:drawing' => [
                'wp:inline' => [
                    'wp:extent' => ['@cx' => $width * 9525, '@cy' => $height * 9525],
                    'wp:docPr' => ['@id' => '1', '@name' => 'Picture'],
                    'a:graphic' => [
                        'a:graphicData' => [
                            '@uri' => 'http://schemas.openxmlformats.org/drawingml/2006/picture',
                            'pic:pic' => [
                                'pic:nvPicPr' => [
                                    'pic:cNvPr' => ['@id' => '0', '@name' => $imageName]
                                ],
                                'pic:blipFill' => [
                                    'a:blip' => ['@r:embed' => $imageId]
                                ],
                                'pic:spPr' => [
                                    'a:xfrm' => ['a:off' => ['@x' => '0', '@y' => '0']],
                                    'a:prstGeom' => ['@prst' => 'rect']
                                ]
                            ]
                        ]
                    ]
                ]
            ]
        ];
 
        // 创建包含图片的段落
        $imageParagraph = [
            'w:p' => [
                'w:r' => $imageElement
            ]
        ];
 
        // 添加到文档末尾
        $this->documentContent['w:document']['w:body'][] = $imageParagraph;
 
        // 复制图片到文档
        copy($imagePath, $this->tempDir . '/word/media/' . $imageName);
    }
 
    /**
     * 清理临时文件
     */
    private function cleanup(): void {
        $files = new RecursiveIteratorIterator(
            new RecursiveDirectoryIterator($this->tempDir, FilesystemIterator::SKIP_DOTS),
            RecursiveIteratorIterator::CHILD_FIRST
        );
 
        foreach ($files as $file) {
            $file->isDir() ? rmdir($file) : unlink($file);
        }
 
        rmdir($this->tempDir);
    }
 
    /**
     * 解析XML为数组
     */
    private function parseXml(string $xml): array {
        $dom = new DOMDocument();
        $dom->loadXML($xml);
        return $this->domToArray($dom->documentElement);
    }
 
    /**
     * 将DOM节点转换为数组
     */
    private function domToArray(DOMNode $node): array {
        $result = [];
        if ($node->hasAttributes()) {
            foreach ($node->attributes as $attribute) {
                $result['@' . $attribute->nodeName] = $attribute->nodeValue;
            }
        }
 
        if ($node->hasChildNodes()) {
            $children = $node->childNodes;
            $textContent = '';
            $hasElements = false;
            $childGroups = [];
 
            foreach ($children as $child) {
                if ($child instanceof DOMText) {
                    $textContent .= $child->nodeValue;
                } elseif ($child instanceof DOMElement) {
                    $hasElements = true;
                    $childArray = $this->domToArray($child);
                    $childName = $child->nodeName;
                     
                    if (!isset($childGroups[$childName])) {
                        $childGroups[$childName] = [];
                    }
                     
                    $childGroups[$childName][] = $childArray;
                }
            }
 
            if ($hasElements) {
                foreach ($childGroups as $name => $children) {
                    $result[$name] = count($children) > 1 ? $children : $children[0];
                }
            } elseif ($textContent !== '') {
                $result['#'] = $textContent;
            }
        }
 
        return $result;
    }
 
    /**
     * 从XML数组生成XML字符串
     */
    private function generateXml(array $data, string $nodeName = ''): string {
        $xml = '';
         
        if (!empty($data['#'])) {
            return htmlspecialchars($data['#']);
        }
         
        foreach ($data as $key => $value) {
            if (str_starts_with($key, '@')) {
                continue; // 属性稍后处理
            }
             
            if (is_array($value)) {
                if (is_numeric($key)) {
                    $xml .= $this->generateXml($value, $nodeName);
                } else {
                    if (isset($value[0]) && is_array($value[0])) {
                        foreach ($value as $item) {
                            $xml .= "<$key";
                            if (isset($item['@'])) {
                                foreach ($item['@'] as $attr => $val) {
                                    $xml .= " $attr="" . htmlspecialchars($val) . """;
                                }
                                unset($item['@']);
                            }
                            $xml .= ">" . $this->generateXml($item, $key) . "</$key>";
                        }
                    } else {
                        $xml .= "<$key";
                        if (isset($value['@'])) {
                            foreach ($value['@'] as $attr => $val) {
                                $xml .= " $attr="" . htmlspecialchars($val) . """;
                            }
                            unset($value['@']);
                        }
                        $xml .= ">" . $this->generateXml($value, $key) . "</$key>";
                    }
                }
            } else {
                $xml .= "<$key>" . htmlspecialchars($value) . "</$key>";
            }
        }
         
        return $xml;
    }
 
    /**
     * 从XML节点提取文本
     */
    private function extractText(array $element): string {
        if (isset($element['w:r']['w:t'])) {
            return $element['w:r']['w:t']['#'] ?? '';
        }
         
        $text = '';
        foreach ($element as $part) {
            if (is_array($part) {
                $text .= $this->extractText($part);
            }
        }
         
        return $text;
    }
 
    /**
     * 记录操作日志
     */
    private function log(string $message): void {
        echo "[LOG] " . $message . PHP_EOL;
    }
}
 
// 示例使用
try {
    // 创建Word处理器实例
    $processor = new WordProcessor('input.docx');
     
    // 加载文档
    $processor->loadDocument();
     
    // 处理批注
    $processor->processComments();
     
    // 添加新段落
    $processor->addParagraph("这是通过PHP添加的新段落。");
     
    // 添加图片
    $processor->addImage('example.png', 300, 200);
     
    // 保存修改后的文档
    $processor->saveDocument('output.docx');
     
    echo "Word文档处理完成！输出文件: output.docx" . PHP_EOL;
     
} catch (Exception $e) {
    die("处理错误: " . $e->getMessage());
}
?>

框架功能说明

这个PHP Word处理框架具有以下核心功能：

1.文档加载与解析：

解压DOCX文件
解析主文档XML
提取批注和关系信息

2.批注处理：

识别特定指令的批注（如#INSERT_TABLE, #REMOVE_SECTION等）
根据批注执行相应操作

3.文档元素操作：

插入表格
添加段落和文本
插入图片
更新图表数据
克隆元素
删除指定部分
替换文本

4.文档保存：

更新XML内容
重新打包为DOCX文件
清理临时文件

技术特点

1.PHP原生实现：

使用PHP 8.4特性
不依赖外部库

2.XML处理：

DOM解析与操作
XML到数组的转换
智能XML生成

3.批注驱动处理：

通过批注标记文档修改点
支持多种指令类型

4.资源管理：

自动处理图片等资源
管理文档内部关系

使用示例

// 创建Word处理器实例
$processor = new WordProcessor('input.docx');
 
// 加载文档
$processor->loadDocument();
 
// 处理批注
$processor->processComments();
 
// 添加新段落
$processor->addParagraph("这是通过PHP添加的新段落。");
 
// 添加图片
$processor->addImage('example.png', 300, 200);
 
// 保存修改后的文档
$processor->saveDocument('output.docx');

注意事项

1.此框架为概念实现，实际应用中需要：

完善XML处理逻辑
增强错误处理
优化性能
添加更多元素支持

2.使用前确保：

PHP版本≥8.4
启用Zip扩展
有足够的临时存储空间

3.对于复杂的文档操作，建议：

分阶段处理
添加详细日志
进行充分测试

此框架提供了一个强大的基础，可用于构建自定义Word文档处理解决方案。

到此这篇关于基于PHP搭建一个Word文档处理框架的文章就介绍到这了,更多相关PHP Word处理内容请搜索腾逍技术以前的文章或继续浏览下面的相关文章希望大家以后多多支持腾逍技术！

Word文档