lucene 实现全文检索（二）：创建索引

indexCreate()方法可以对每种类型的文档建立索引

    /***
     * 创建索引
     * @param targetFileDir 源文件夹
     * @param indexSaveDir 索引存放文件夹
     * @throws IOException
     */
    public static void indexCreate(File targetFileDir, File indexSaveDir) throws IOException, InvalidFormatException {
        // 不是目录或不存在则返回
        if (!targetFileDir.isDirectory() || !targetFileDir.exists()) {
            return;
        }
        // 保存Lucene索引文件的路径
        Directory directory = FSDirectory.open(indexSaveDir.toPath());
        // 创建一个简单的分词器,可以对数据进行分词
        Analyzer analyzer = new StandardAnalyzer();
        // 创建索引实例
        IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer);
        IndexWriter indexWriter = new IndexWriter(directory, indexWriterConfig);
        // 获取所有需要建立索引的文件
        File[] files = targetFileDir.listFiles();

        for (int i = 0; i < files.length; i++) {
            // 文件的完整路径 files[i].toString()
            // 获取文件名称
            String fileName = files[i].getName();
            // 获取文件后缀名，将其作为文件类型
            String fileType = fileName.substring(fileName.lastIndexOf(".") + 1, fileName.length()).toLowerCase();
            if(fileType.equals("index")){
                continue;
            }

            Document doc = new Document();
            InputStream in = new FileInputStream(files[i]);
            FieldType fieldType = new FieldType();
            fieldType.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS);
            fieldType.setStored(true);
            fieldType.setTokenized(true);
            
            // 为每种文档类型创建索引 
            if (!fileType.equals("")) {
                switch (fileType) {
                    // doc类型文档
                    case "doc":
                        // 获取doc的word文档
                        WordExtractor wordExtractor = new WordExtractor(in);
                        // 创建Field对象，并放入doc对象中
                        doc.add(new Field("contents", wordExtractor.getText(), fieldType));
                        // 关闭文档
                        wordExtractor.close();
                        break;
                        
                    // docx类型文档    
                    case "docx":
                        // 获取docx的word文档
                        XWPFWordExtractor xwpfWordExtractor = new XWPFWordExtractor(new XWPFDocument(in));
                        // 创建Field对象，并放入doc对象中
                        doc.add(new Field("contents", xwpfWordExtractor.getText(), fieldType));
                        // 关闭文档
                        xwpfWordExtractor.close();
                        break;
                        
                    // pdf类型文档    
                    case "pdf":
                        // 获取pdf文档
                        PDFParser parser = new PDFParser(in);
                        parser.parse();
                        PDDocument pdDocument = parser.getPDDocument();
                        PDFTextStripper stripper = new PDFTextStripper();
                        // 创建Field对象，并放入doc对象中
                        doc.add(new Field("contents", stripper.getText(pdDocument), fieldType));
                        // 关闭文档
                        pdDocument.close();
                        break;
                        
                    // txt类型文档    
                    case "txt":
                        String encodingTxt = "GBK";
                        String txtFile = FileUtils.readFileToString(files[i],encodingTxt);
                        // 创建Field对象，并放入doc对象中
                        //System.out.println(txtFile);
                        System.out.println(txtFile);
                        doc.add(new Field("contents", txtFile, fieldType));
                        //System.out.println(doc);
                        break;
                        
                    // html类型文档    
                    case "html": {
                        StringBuffer sb = new StringBuffer();
                        String str = null;
                        String encoding = "GBK";
                        File file = new File(String.valueOf(files[i]));
                        if (file.isFile() && file.exists()) { //判断文件是否存在
                            InputStreamReader read = new InputStreamReader(
                                    new FileInputStream(file), encoding);//考虑到编码格式
                            BufferedReader bufferedReader = new BufferedReader(read);
                            String lineTxt = null;
                            while ((lineTxt = bufferedReader.readLine()) != null) {
                                sb.append(lineTxt);
                            }
                            str = sb.substring(sb.indexOf("<body>") + 6, sb.indexOf("</body>"));
                            read.close();
                        }
                        doc.add(new Field("contents", str, fieldType));
                        break;
                    }
                    
                    // xml类型文档
                    case "xml": {
                        StringBuffer sb = new StringBuffer();
                        String str = null;
                        String encoding = "UTF-8";
                        File file = new File(String.valueOf(files[i]));
                        if (file.isFile() && file.exists()) { //判断文件是否存在
                            InputStreamReader read = new InputStreamReader(
                                    new FileInputStream(file), encoding);//考虑到编码格式
                            BufferedReader bufferedReader = new BufferedReader(read);
                            String lineTxt = null;
                            while ((lineTxt = bufferedReader.readLine()) != null) {
                                sb.append(lineTxt);
                            }
                            str = sb.substring(sb.indexOf("content"), sb.indexOf("</content>"));
                            read.close();
                        }
                        doc.add(new Field("contents", str, fieldType));
                        break;
                    }
                    
                    // xls类型文档
                    case "xls": {
                        // 工作表
                        Workbook workbook = null;
                        workbook = WorkbookFactory.create(in);
                        StringBuffer sb = new StringBuffer();
                        // 表个数。
                        int numberOfSheets = workbook.getNumberOfSheets();
                        for (int k = 0; k < numberOfSheets; k++) {
                            Sheet sheet = workbook.getSheetAt(k);
                            // 行数。
                            int rowNumbers = sheet.getLastRowNum() + 1;
                            // Excel第一行。
                            Row temp = sheet.getRow(0);
                            if (temp == null) {
                                continue;
                            }
                            int cells = temp.getPhysicalNumberOfCells();
                            // 读数据。
                            for (int row = 0; row < rowNumbers; row++) {
                                Row r = sheet.getRow(row);
                                for (int col = 0; col < cells; col++) {
                                    if (r.getCell(col) == null) {
                                        continue;
                                    }
                                    sb.append(r.getCell(col).toString()).append(" ");
                                }
                            }
                        }
                        doc.add(new Field("contents", String.valueOf(sb), fieldType));
                        workbook.close();
                        break;
                    }
                    
                    // ppt类型文档
                    case "ppt":
                        PowerPointExtractor powerpointExtractor = new PowerPointExtractor(in);
                        doc.add(new Field("contents", powerpointExtractor.getText(), fieldType));
                        break;
                        
                    // 其他非需求类型文档    
                    default:
                        System.out.println("文件类型格式错误！！！");
                        continue;
                }
            }
            // 创建文件名的域，并放入doc对象中
            doc.add(new Field("filename", files[i].getName(), fieldType));
            // 创建时间的域，并放入doc对象中
            doc.add(new Field("indexDate", DateTools.dateToString(new Date(), DateTools.Resolution.DAY), fieldType));
            // 写入IndexWriter
            indexWriter.addDocument(doc);
        }
        // 查看IndexWriter里面有多少个索引
        System.out.println("查看IndexWriter里面有多少个索引:" + indexWriter.numDocs());
        // 关闭索引
        indexWriter.close();
    }