Java按顺序提取Word内容的方法步骤(文本+数学公式)

 
    /**
     * 提取公式并替换为唯一标识符
     * @param fis 原始Word文档路径
     * @param outputPath 处理后Word文档路径
     * @return 公式与标识符的映射关系
     */
    public Map<String, String> extractAndReplaceFormulas(InputStream fis, String outputPath) {
        Map<String, String> formulaMap = new HashMap<>();
 
        try {
            try (XWPFDocument document = new XWPFDocument(fis)) {
 
                // 遍历所有段落
                for (XWPFParagraph paragraph : document.getParagraphs()) {
                    processParagraphViaXML(paragraph, formulaMap);
                }
 
                // 保存处理后的文档
                try (FileOutputStream fos = new FileOutputStream(outputPath)) {
                    document.write(fos);
                }
            }
        } catch (Exception e) {
            log.error("extractAndReplace Formulas: {0}", e);
        }
 
        return formulaMap;
    }

    /**
     * 通过XML直接处理段落中的公式
     */
    public void processParagraphViaXML(XWPFParagraph paragraph, Map<String, String> formulaMap) {
        try {
            CTP ctp = paragraph.getCTP();
 
            // 获取段落的XML内容
            String originalXml = ctp.xmlText();
 
            // 处理XML，替换公式
            String newXml = parserXML(originalXml, formulaMap);
 
            // 用新的XML替换原来的段落内容
            CTP newCtp = CTP.Factory.parse(newXml);
            paragraph.getCTP().set(newCtp);
        } catch (Exception e) {
            log.error("processParagraphViaXML Error: {0}", e);
        }
    }

    private String parserXML(String originalXml, Map<String, String> formulaMap)
            throws IOException, SAXException, ParserConfigurationException, TransformerException {
        DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
        factory.setNamespaceAware(true); // 启用命名空间支持
        DocumentBuilder builder = factory.newDocumentBuilder();
        org.w3c.dom.Document doc = builder.parse(new ByteArrayInputStream(originalXml.getBytes()));
 
        // 查找m:oMath节点（使用命名空间）
        NodeList oMathNodes = doc.getElementsByTagNameNS("http://schemas.openxmlformats.org/officeDocument/2006/math", "oMath");
 
        Map<Element,Node> map = new HashMap<>();
 
        for (int i = 0; i < oMathNodes.getLength(); i++) {
            Node oMathNode = oMathNodes.item(i);
            Element rElement = doHandleElement(oMathNode, doc);
            map.put(rElement, oMathNode);
        }
 
        map.forEach((rElement, oMathNode) -> oMathNode.getParentNode().replaceChild(rElement, oMathNode));
 
        return docmentToString(doc);
    }

 
    private Element doHandleElement(Node oMathNode, org.w3c.dom.Document doc) throws TransformerException {
        // 保存原始公式内容（简化处理，实际可能需要更复杂的序列化）
        String formulaContent = nodeToString(oMathNode);
 
        if(questionMathReader==null){
            questionMathReader = new QuestionMathReader2();
        }
 
        log.debug("formulaContent:{}", formulaContent);
        String latexContent = questionMathReader.convertFromMmlToLatex(formulaContent);
        log.debug("LatexContent:{}", latexContent);
 
        // 创建新的文本节点
        Text textNode = doc.createTextNode("<KatexText value=\""+latexContent+"\"></KatexText>");
 
        // 创建新的w:r节点（Word中的文本需要包装在r中）
        Element rElement = doc.createElementNS("http://schemas.openxmlformats.org/wordprocessingml/2006/main", "w:r");
        Element tElement = doc.createElementNS("http://schemas.openxmlformats.org/wordprocessingml/2006/main", "w:t");
        tElement.appendChild(textNode);
        rElement.appendChild(tElement);
        return rElement;
    }

 
    // 辅助方法：将 Node 转换为 XML 字符串
    private String nodeToString(Node node) throws TransformerException {
        TransformerFactory tf = TransformerFactory.newInstance();
        Transformer transformer = tf.newTransformer();
        transformer.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION, "yes");
        StringWriter writer = new StringWriter();
        transformer.transform(new DOMSource(node), new StreamResult(writer));
        return writer.toString();
    }

    private static String docmentToString(org.w3c.dom.Document doc) throws TransformerException {
        // 将修改后的DOM转换回XML字符串
        TransformerFactory transformerFactory = TransformerFactory.newInstance();
        Transformer transformer = transformerFactory.newTransformer();
        transformer.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION, "yes");
        transformer.setOutputProperty(OutputKeys.INDENT, "no");
 
        StringWriter writer = new StringWriter();
        transformer.transform(new DOMSource(doc), new StreamResult(writer));
 
        return writer.toString();
    }

            // 处理XML，替换公式
            String newXml = parserXML(originalXml, formulaMap);
 
            // 用新的XML替换原来的段落内容
            CTP newCtp = CTP.Factory.parse(newXml);
            paragraph.getCTP().set(newCtp);

    public static void main(String[] args) throws IOException {
        QuestionMathReplace2 extractor = new QuestionMathReplace2();
 
        // 执行提取并替换公式
        Map<String, String> formulaMap = extractor.extractAndReplaceFormulas(
                Files.newInputStream(Paths.get("F://test_source.docx")),
                "F://test_target.docx"
        );
 
        // 输出映射关系
        for (Map.Entry<String, String> entry : formulaMap.entrySet()) {
            System.out.println(entry.getKey() + " => " + entry.getValue());
        }
    }