java DiffUtils文本差异对比实现

1、首先引入mvn

<dependency>
  <groupId>io.github.java-diff-utils</groupId>
  <artifactId>java-diff-utils</artifactId>
  <version>4.11</version>
</dependency>
<dependency>
  <groupId>org.apache.poi</groupId>
  <artifactId>poi</artifactId>
  <version>4.0.0</version>
</dependency>
<dependency>
  <groupId>org.apache.poi</groupId>
  <artifactId>poi-ooxml</artifactId>
  <version>4.0.0</version>
</dependency>
<dependency>
  <groupId>org.apache.poi</groupId>
  <artifactId>poi-scratchpad</artifactId>
  <version>4.0.0</version>
</dependency>

2、编写解析word为text函数

public List<String> parseWord(String input){
        try{
            InputStream inputStream = new FileInputStream(input);
            XWPFDocument document = new XWPFDocument(inputStream);

            List<String> pList = new ArrayList<>();
            Map<String, Poi.PraInfo> pMap = new HashMap<>();
            Integer lineNum = 1;
            List<XWPFParagraph> paras = document.getParagraphs();
            if (!CollectionUtils.isEmpty(paras)) {
                for (XWPFParagraph para : paras) {
                    //当前段落的属性
                    //CTPPr pr = para.getCTP().getPPr();
                    String text = para.getText();
                    if (StringUtils.isBlank(text)) {
//                        continue;
                    }
                    pList.add(text);
                }
            }
            return pList;
        }catch (Exception e){
            e.printStackTrace();
        }
        return new ArrayList<>();
    }

3、编写差异函数

public void diff1(){
        try {
            String sourceFile = "D:/java_work_space/test/doc_comparer/2.docx";
            String targetFile = "D:/java_work_space/test/doc_comparer/2-1.docx";
            //原始文件
            List<String> original = parseWord(sourceFile);
            //对比文件
            List<String> revised = parseWord(targetFile);

            //两文件的不同点
            Patch<String> patch = DiffUtils.diff(original, revised);

            //生成统一的差异格式
            List<String> unifiedDiff = UnifiedDiffUtils.generateUnifiedDiff("test1.txt", "test2.txt", original, patch, 0);
            for(int i=2;i<unifiedDiff.size();i++){
                System.out.println(unifiedDiff.get(i));
            }

        }catch (Exception e){
            e.printStackTrace();
        }
    }