Invalid image: zip:https://t8.docx#word/media/image1.wmf

[yangweijie]

This is:
win i read a docx file ，the code got an exception:
Invalid image: zip:https://t8.docx#word/media/image1.wmf

• [√] a bug report
• a feature request
• not a usage question (ask them on https://stackoverflow.com/questions/tagged/phpword)

Expected Behavior

Please describe the behavior you are expecting.

Current Behavior

What is the current behavior?

Failure Information

Please help provide information about the failure.

How to Reproduce

Please provide a code sample that reproduces the issue.

<?php
$phpWord  = \PhpOffice\PhpWord\IOFactory::load($path);
		$sections = $phpWord->getSections();
		$ph = new PhpWordHelper;
		$to_combines = [];
		foreach ($sections as $key => $section) {
			$headers = $section->getHeaders();
			$htitle  = $ph->get_section_header_text($section);
			foreach ($check_titles as $key => $title) {
				$short_title = str_ireplace(' ', '', $title);
				if(false !== stripos($htitle, $title) || false !== stripos($htitle, $short_title)){
					if(!in_array($title, $to_combines)){
						$to_combines[$title][] = $title;
					}
				}
			}
		}
		return $to_combines;

<?php
namespace util;
use PhpOffice\PhpWord\PhpWord;
use PhpOffice\PhpWord\IOFactory;
use PhpOffice\PhpWord\Style\Font;
use PhpOffice\PhpWord\Shared\ZipArchive;
use PhpOffice\PhpWord\Settings;
use PhpOffice\PhpWord\Reader\Word2007\Styles;
/**
 * 文件压缩解压类
 */
class PhpWordHelper {

    private $currentPage = 0;  // 当前分页
    private $page        = 0; // 插入页数
    private $args        = null; // 文本段样式
    private $tmpFiles    = []; // 临时文件
    private $styles      = [];
    private $breakCount  = 0;


    public function split_by_section($file, $dir = ''){
        $old_phpword = IOFactory::load($file);
        // dump($old_phpword);
        // dump([
        //     $old_phpword->getDefaultFontName(),
        //     $old_phpword->getDefaultFontSize(),
        // ]);
        // die;
        $sections = $old_phpword->getSections();
        $arr      = [];
        foreach ($sections as $section) {
            $elements = $section->getElements();
            // dump($elements);
            // die;
            $phpWord = new PhpWord();
            $headers = $section->getHeaders();
            // dump($headers);
            $htitle = $this->get_section_header_text($section);
            $new_section = $phpWord->addSection();
            // $this->setAttr('section', $new_section, $section);
            $this->copyElement($new_section, $headers);
            // dump($phpWord);
            // 逐级读取／写入节点
            $this->copyElement($new_section, $elements);
            // dump($phpWord);
            $footers = $section->getFooters();
            $this->copyElement($new_section, $footers);
            // dump($phpWord);
            $fwrite = IOFactory::createWriter($phpWord);
            $path = $dir?:dirname($file);
            if(!is_dir($path)) mkdir($path);

            // dump($htitle);
            // $htitle = \mb_convert_encoding($htitle, IS_WIN?'GB2312':'UTF-8', 'UTF-8');
            $filePath = $path . DS . $htitle. '.docx';
            // dump($filePath);
            // $fwrite->save($filePath);
        }
    }

    // 获取分区页眉文本
    public function get_section_header_text($section){
        $headers = $section->getHeaders();
        $text = [];
        foreach ($headers as $key => $header) {
            $elements = $header->getElements();
            foreach ($elements as $key => $element) {
                $type = $this->get_element_type($element);
                if(in_array($type, ['Text', 'TextRun', 'Link', 'Title'])){
                    if($type == 'TextRun'){
                        $textRunElements = $element->getElements();
                        foreach ($textRunElements as $key => $textRunElement) {
                            $text[] = $textRunElement->getText();
                        }
                    }else{
                        $text[] = $element->getText();
                    }
                }
            }
        }
        $str = \implode('', $text);
        return \str_ireplace(' ', '', $str);
    }

    // 获取元素的类型
    public function get_element_type($element){
        $class = \get_class($element);
        // dump(explode('\\', $class)[3]);
        return explode('\\', $class)[3];
    }

    public function copyElement(&$container, $elements){
        foreach ($elements as $key => $element) {
            if(!is_null($element)){
                $phpword = $element->getPhpWord();
                $type    = $this->get_element_type($element);
                // dump($type);
                $fun     = "add{$type}";
                // 判断一个元素是否是容器
                if(in_array($type, [
                    'Header',
                    'Footer',
                    'Section'
                ])){
                    if($type == 'Section'){
                        $newEl = $container->$fun();
                    }else{
                        $ptype = $element->getType();
                        // dump('ptype:'.$ptype);
                        // dump("{$type}_{$key}");
                        // dump([$element, $element->getElements()]);
                        // dump($element->getElements());
                        $newEl = $container->$fun($ptype);
                    }
                    // dump($newEl);
                    // if(is_null($newEl)){
                    //     dump($container);
                    // }
                    $this->copyElement($newEl, $element->getElements());
                }elseif(in_array($type, [
                    'Table',
                    'Footnote',
                    'Endnote',
                    'TextRun'
                ])){ // 判断是否复合元素
                    switch ($type) {
                        case 'Table':
                            $tableStyle = $element->getStyle();
                            $newEl      = $container->$fun($tableStyle);
                            $this->setAttr($type, $newEl, $element);
                            $rows = $element->getRows();
                            $this->copyElement($newEl, $rows);
                            break;
                        case 'Footnote':
                            $newEl = $container->$fun();
                            break;
                        case 'Endnote':
                            $newEl = $container->$fun();
                            break;
                        case 'TextRun':
                            dump($text);
                            $paragraphStyle = $element->paragraphStyle();
                            // dump($paragraphStyle);
                            $newEl          = $container->$fun($paragraphStyle);
                            break;
                        default:
                            break;
                    }
                    $this->setAttr($type, $newEl, $element);
                    $sub_elements = $element->getElements();
                    $this->copyElement($newEl, $sub_elements);
                }else{
                    if(\method_exists($element, 'getText')){
                        $text = $element->getText();
                    }else{
                        $text = '';
                    }
                    // dump($type);
                    switch ($type) {
                        case 'Text':
                            // dump([
                            //     $text,
                            //     $element->getFontStyle(),
                            //     $element->getParagraphStyle()
                            // ]);
                            $container->addText($text, $element->getFontStyle(), $element->getParagraphStyle());
                            break;
                        case 'Title':
                            $depth = $element->getDepth();
                            $style = $element->getStyle();
                            $phpWord->addTitleStyle($depth, $style['font'], $style['paragraph']);
                            $container->$fun($text, $depth);
                            break;
                        case 'Link':
                            $linkName       = $text;
                            $linkSrc        = $element->getLinkSrc();
                            $fontStyle      = $element->getFontStyle();
                            $paragraphStyle = $element->getParagraphStyle();
                            $container->$fun($linkSrc, $linkName, $fontStyle, $paragraphStyle);
                            break;
                        case 'PreserveText':
                            $container->$fun();
                            break;
                        case 'TextBreak':
                            $fontStyle      = $element->getFontStyle();
                            $paragraphStyle = $element->getParagraphStyle();
                            $container->$fun($breakCount = 1, $fontStyle, $paragraphStyle);
                            break;
                        case 'PageBreak':
                            $container->$fun();
                            break;
                        case 'Line':
                            $lineStyle = $element->getStyle();
                            $container->$fun($lineStyle);
                            break;
                        case 'Chart':
                            $type       = $element->getType();
                            $series     = $element->getSeries();
                            $style      = $element->getStyle();
                            $categories = array_column($series, 'categories');
                            $chart      = $container->$fun($type, $categories, $style);
                            break;
                        case 'ListItem':
                            $depth          = $element->getDepth();
                            $fontStyle      = $element->getTextObject()->getFontStyle();
                            $paragraphStyle = $element->getTextObject()->getParagraphStyle();
                            $listStyle      = $element->getStyle();
                            $container->$fun($text, $depth, $fontStyle, $listStyle, $paragraphStyle);
                            break;
                        case 'ListItemRun':
                            // TODO
                            break;
                        case 'Shape':
                            $type  = $element->getType();
                            $style = $element->getStyle();
                            $container->$fun($type, $style);
                            break;
                        case 'Image':
                            $source = $element->getSource();
                            $style  = $element->getStyle();
                            if($element->isWatermark() && !$element->isInSection()){
                                if($this->get_element_type($element->getParent()) == 'Header'){
                                    $element->getParent()->addWatermark($source, $style);
                                }
                            }
                            $container->$fun($source, $style);
                            break;
                        case 'OLEObject':
                            $source = $element->getSource();
                            $style  = $element->getStyle();
                            $container->$fun($source, $style);
                            break;
                        case 'Row':
                            $height = $element->getHeight();
                            $style  = $element->getStyle();
                            $row    = $container->$fun($height, $style);
                            $cells  = $row->getCells();
                            if($cells){
                                $this->copyElement($row, $cells);
                            }
                            break;
                        case 'Cell':
                            $width = $element->getWidth();
                            $style = $element->getStyle();
                            $cell  = $container->$fun($width, $style);
                            break;
                        default:
                            // Shape SDT
                            # code...
                            break;
                    }
                }
            }
        }
    }

    public static function checkDocumentLinks($file){
        $links       = [];
        try {
            $phpword     = IOFactory::load($file);
        } catch (\Exception $e) {
            ptrace($e->getMessage() . PHP_EOL . $e->getTraceAsString());
            return $links;
        }
        $sections    = $phpword->getSections();

        foreach ($sections as $key => $section) {
            $headers     = $section->getHeaders();
            // dump($headers);
            $ret = self::checkElement($headers, $links);
            if($ret){
                foreach ($ret as $key => $r) {
                    $links[] = $ret;
                }
            }
            // 逐级读取／写入节点
            $ret = self::checkElement($section->getElements(), $links);
            if($ret){
                foreach ($ret as $key => $r) {
                    $links[] = $ret;
                }
            }
            $footers = $section->getFooters();
            $ret = self::checkElement($footers, $links);
            if($ret){
                foreach ($ret as $key => $r) {
                    $links[] = $ret;
                }
            }
        }
        return $links;
    }

    public static function checkElement($elements, &$links){
        foreach ($elements as $key => $element) {
            $class = \get_class($element);
            $type  = explode('\\', $class)[3];
            $ret   = [];
            // dump($type);
            // 判断一个元素是否是容器
            if(in_array($type, [
                'Table',
                'Footnote',
                'Endnote',
                'TextRun'
            ])){ // 判断是否复合元素
                switch ($type) {
                    case 'Table':
                        $rows = $element->getRows();
                        $ret  = self::checkElement($rows, $links);
                        break;
                    case 'Footnote':
                    case 'Endnote':
                        $sub_elements = $element->getElements();
                        $ret = self::checkElement($sub_elements, $links);
                        break;
                    case 'TextRun':
                        $sub_elements = $element->getElements();
                        $ret = self::checkElement($sub_elements, $links);
                        // dump($element);
                        // $text = $element->getText();
                        // $ret  = $text == null?[]:self::check_text_link($text);
                        break;
                    case 'Row':
                        $cells = $element->getCells();
                        $ret  = self::checkElement($cells);
                        break;
                    default:
                        $ret = [];
                        break;
                }
            }elseif(method_exists($element, 'getElements')){
                $sub_elements = $element->getElements();
                $ret = self::checkElement($sub_elements, $links);
            }else{
                if(\method_exists($element, 'getText')){
                    $text = $element->getText();
                }else{
                    $text = '';
                }
                // dump($type);
                switch ($type) {
                    case 'Link':
                        $ret =  [
                            'word'=>$text,
                            'link'=>$element->getLinkSrc()
                        ];
                        break;
                    case 'PreserveText':
                    case 'Text':
                    case 'Title':
                    case 'Cell':
                        if($text){
                            $ret = self::check_text_link($text);
                        }
                        // $ret = self::check_text_link($text);
                        break;
                    case 'TextBreak':
                    case 'PageBreak':
                    case 'Line':
                    case 'Chart':
                    case 'ListItem':
                    case 'ListItemRun':
                    case 'Shape':
                    case 'Image':
                    case 'OLEObject':
                        $ret = [];
                        break;
                    default:
                        // Shape SDT
                        break;
                }
            }
            if($ret){
                $links[] = $ret;
            }
        }
    }

    // { HYPERLINK &quot;https://baike.baidu.com/item/%E5%BB%BA%E7%AD%91&quot; \t &quot;_blank&quot; }
    public static function check_text_link($text){
        if(is_array($text)){
            $text = implode('', $text);
            $text = trim($text);
        }elseif(is_numeric($text)){
            return [];
        }
        if(stripos($text, '{ HYPERLINK ') === false && stripos($text, 'quot; }') === false){
            return [];
        }else{
            ptrace($text);
            $arr      = explode('&quot;', $text);
            $link     = $arr[1];
            $new_link = urldecode($link);
            $word     = getChinese($new_link)?:$new_link;
            return [
                    'word'=>$word == false?'':$word,
                    'link'=>$new_link,
            ];
        }
    }

    private function setAttr($elName, &$newEl, $element)
    {
        switch (strtolower($elName)) {
            case 'section':
                $orders = [
                    'getOrientation'        => 'setOrientation',
                    'getGutter'             => 'setGutter',
                    'getBreakType'          => 'setBreakType',
                    'getPaperSize'          => 'setPaperSize',
                    'getMarginTop'          => 'setMarginTop',
                    'getMarginLeft'         => 'setMarginLeft',
                    'getMarginBottom'       => 'setMarginBottom',
                    'getHeaderHeight'       => 'setHeaderHeight',
                    'getFooterHeight'       => 'setFooterHeight',
                    'getColsNum'            => 'setColsNum',
                    'getColsSpace'          => 'setColsSpace',
                    'getLineNumbering'      => 'setLineNumbering',
                    'getPageSizeW'          => 'setPageSizeW',
                    'getPageSizeH'          => 'setPageSizeH',
                    'getPageNumberingStart' => 'setPageNumberingStart',
                ];
                foreach ($orders as $get => $set) {
                    $newEl->$set($element->$get());
                }
                break;
            case 'footnote':
                $newEl->setReferenceId($element->getReferenceId());
                break;
            case 'formfield':
                $newEl->setName($element->getName());
                $newEl->setDefault($element->getDefault());
                $newEl->setValue($element->getValue());
                $newEl->setEntries($element->getEntries());
                break;
            case 'object':
                $newEl->setImageRelationId($element->getImageRelationId());
                $newEl->setObjectId($element->getObjectId());
                break;
            case 'sdt':
                $newEl->setValue($element->getValue());
                $newEl->setListItems($element->getListItems());
                break;
            case 'table':
                $newEl->setWidth($element->getWidth());
                break;
        }
    }
}

Context

t8.docx

• PHP version:
• PHPWord version: dev-develop 1534dc2

[JieAnthony]

解决了么

[yangweijie]

解决了么

没 后来改为用 win 服务器执行宏来 做格式化 提取内容了 拦截了一些异常 不支持word里 特殊的图片 只支持jpg png 之类的

[JieAnthony]

解决了么

没后来后来用win服务器执行宏来做格式化格式化提取内容了拦截了一些异常不支持word里特殊的图片只支持jpg png之类的

那得估计要翻一下源码看看哪里限制了。如果你是word转html的话还有一种办法就是用libreoffice

[thomasb88]

Same issue as #1480 (also add WMF support).