java获取word文件中的字符数量

最新推荐文章于 2024-02-21 13:59:24 发布

danjiawei

最新推荐文章于 2024-02-21 13:59:24 发布

阅读量1.8k

点赞数 1

CC 4.0 BY-SA版权

文章标签： java poi

本文链接：https://blog.youkuaiyun.com/danjiawei/article/details/103669631

相关依赖

        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi</artifactId>
            <version>3.9</version>
        </dependency>

        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml</artifactId>
            <version>3.9</version>
        </dependency>

        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml-schemas</artifactId>
            <version>3.9</version>
        </dependency>
       
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-scratchpad</artifactId>
            <version>3.9</version>
        </dependency>

实现代码

/**
     * 获取word中的字数
     *
     * @param file
     * @return
     */
    public static int getWordCount(File file) {
        try {
            FileInputStream fis = new FileInputStream(file);
            //获取文件后缀名
            String suffix = file.getName().substring(file.getName().lastIndexOf(".") + 1);
            //定义word内容
            String content = "";
            switch (suffix) {
                case "doc":
                    WordExtractor wordExtractor = new WordExtractor(fis);
                    content = wordExtractor.getText();
                    break;
                case "docx":
                    XWPFDocument document = new XWPFDocument(fis);
                    XWPFWordExtractor extractor = new XWPFWordExtractor(document);
                    content = extractor.getText();
                    break;
                default:
                    break;
            }
            fis.close();
            //中文单词
            String cnWords = content.replaceAll("[^(\\u4e00-\\u9fa5，。《》？；’‘：“”【】、）（……￥！·)]", "");
            int cnWordsCount = cnWords.length();
            //非中文单词
            String noCnWords = content.replaceAll("[^(a-zA-Z0-9`\\-=\';.,/~!@#$%^&*()_+|}{\":><?\\[\\])]", " ");
            int noCnWordsCount = 0;
            String[] ss = noCnWords.split(" ");
            for (String s : ss) {
                if (s.trim().length() != 0) {
                    noCnWordsCount++;
                }
            }
            //中文和非中文单词合计
            return cnWordsCount + noCnWordsCount;
        } catch (IOException e) {
            e.printStackTrace();
        }
        return 0;
    }