Elasticsearch入门之（四）使用java全文搜索pdf、word、excel文件

朱雀 2020-10-25 08:25 1252阅读 1赞

一、这里我的思路是，在上传文件时候把数据库对应id存到Elasticsearch对应索引类型的id，然后利用工具类把pdf、word、excel文件内容存到Elasticsearch的id对应json里，返回所有文件id的list

二、这里我封装了一个读取pdf、word、excel文件工具类

package springboot.elasticsearch;
    
    import com.spire.pdf.PdfDocument;
    import com.spire.pdf.PdfPageBase;
    import org.apache.poi.POIXMLDocument;
    import org.apache.poi.POIXMLTextExtractor;
    import org.apache.poi.hssf.extractor.ExcelExtractor;
    import org.apache.poi.hssf.usermodel.HSSFWorkbook;
    import org.apache.poi.hwpf.extractor.WordExtractor;
    import org.apache.poi.openxml4j.opc.OPCPackage;
    import org.apache.poi.poifs.filesystem.POIFSFileSystem;
    import org.apache.poi.xssf.extractor.XSSFExcelExtractor;
    import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
    
    import java.io.File;
    import java.io.FileInputStream;
    import java.io.InputStream;
    
    public class ReadUtil {
    
    	/**
    	 * JSON字符串特殊字符处理
    	 * @param s
    	 * @return String
    	 */
    	public static String stringJson(String s) {
    		StringBuffer sb = new StringBuffer();
    		for (int i = 0; i < s.length(); i++) {
    			char c = s.charAt(i);
    			switch (c) {
    				case '\"':
    					sb.append("\\\"");
    					break;
    				case '\\':
    					sb.append("\\\\");
    					break;
    				case '/':
    					sb.append("\\/");
    					break;
    				case '\b':
    					sb.append("\\b");
    					break;
    				case '\f':
    					sb.append("\\f");
    					break;
    				case '\n':
    					sb.append("\\n");
    					break;
    				case '\r':
    					sb.append("\\r");
    					break;
    				case '\t':
    					sb.append("\\t");
    					break;
    				default:
    					sb.append(c);
    			}
    		}
    		return sb.toString();
    	}
    
    	/**
    	 * word读取工具
    	 * @param path
    	 * @return
    	 */
    	public static String readWord(String path) {
    		String buffer = "";
    		try {
    			if (path.endsWith(".doc")) {
    				InputStream is = new FileInputStream(new File(path));
    				WordExtractor ex = new WordExtractor(is);
    				buffer = ex.getText();
    				ex.close();
    			} else if (path.endsWith(".docx")) {
    				OPCPackage opcPackage = POIXMLDocument.openPackage(path);
    				POIXMLTextExtractor extractor = new XWPFWordExtractor(opcPackage);
    				buffer = extractor.getText();
    				extractor.close();
    			} else {
    				System.out.println("此文件不是word文件！");
    			}
    		} catch (Exception e) {
    			e.printStackTrace();
    		}
    		return stringJson(buffer);
    	}
    
    	/**
    	 * excel读取工具
    	 * @param path
    	 * @return
    	 */
    	public static String readExcel(String path) {
    		String buffer = "";
    		try {
    			InputStream is = new FileInputStream(path);
    			if (path.endsWith(".xls")) {
    				HSSFWorkbook wb = new HSSFWorkbook(new POIFSFileSystem(is));
    				ExcelExtractor extractor = new ExcelExtractor(wb);
    				extractor.setIncludeSheetNames(true);
    				extractor.setFormulasNotResults(true);
    				extractor.setIncludeCellComments(true);
    				buffer = extractor.getText();
    			} else if (path.endsWith(".xlsx")) {
    				OPCPackage opcPackage = POIXMLDocument.openPackage(path);
    				POIXMLTextExtractor extractor = new XSSFExcelExtractor(opcPackage);
    				buffer = extractor.getText();
    				extractor.close();
    			} else {
    				System.out.println("此文件不是excel文件！");
    				return "";
    			}
    		} catch (Exception e) {
    			e.printStackTrace();
    		}
    		return stringJson(buffer);
    	}
    
    	/**
    	 * pdf读取工具
    	 * @param path
    	 * @return
    	 */
    	public static String readPdf(String path) {
    		String buffer = "";
    		try {
    			//创建PdfDocument实例
    			PdfDocument doc= new PdfDocument();
    			//加载PDF文件
    			doc.loadFromFile(path);
    			PdfPageBase page = null;
    			//遍历PDF页面，获取文本
    			for (int i = 0; i < doc.getPages().getCount(); i++) {
    				page = doc.getPages().get(i);
    				buffer += page.extractText(true);
    			}
    		} catch (Exception e) {
    			e.printStackTrace();
    		}
    		return stringJson(buffer);
    	}
    
    	/**
    	 * 根据不同类型，获取内容
    	 * @param path
    	 * @return
    	 */
    	public static String readContent(String path) {
    		String str = "";
    		String[] split = path.split("\\.");
    		String suffix = split[split.length - 1];
    		switch (suffix) {
    			case "doc":
    				str = readWord(path);
    				break;
    			case "docx":
    				str = readWord(path);
    				break;
    			case "xls":
    				str = readExcel(path);
    				break;
    			case "xlsx":
    				str = readExcel(path);
    				break;
    			case "pdf":
    				str = readPdf(path);
    				break;
    			default:
    				break;
    		}
    		return str;
    	}
    
    	public static void main(String[] args) {
    //		String content = readWord("C:\\Users\\dell\\Desktop\\cs123.doc");
    //		String content = readWord("C:\\Users\\dell\\Desktop\\cs.docx");
    //		String content = readExcel("C:\\Users\\dell\\Desktop\\cs1.xls");
    //		String content = readExcel("C:\\Users\\dell\\Desktop\\cs2.xlsx");
    		String content = readPdf("C:\\Users\\dell\\Desktop\\cs3.pdf");
    		System.out.println("content===="+content);
    	}
    }

注：这里读取pdf需要用到[Spire.Pdf.jar][]

三、测试类，这里增删改查调用的工具类参考上一篇[Elasticsearch入门之（三）使用java进行增删改查][Elasticsearch_java]

package springboot.elasticsearch;
    
    import com.alibaba.fastjson.JSON;
    
    import java.text.SimpleDateFormat;
    import java.util.Date;
    import java.util.List;
    import java.util.Map;
    import java.util.UUID;
    
    public class Elasticsearch {
    	public static void main(String[] args) {
    		try {
    			//判断索引是否存在，不存在则创建
    			if (!ElasticsearchUtil.checkIndexExist("cs")) {
    				ElasticsearchUtil.createIndex("cs");
    			}
    			String uuid = UUID.randomUUID().toString().replaceAll("-","");
    			String path = "C:\\Users\\dell\\Desktop\\";
    //			String file_name = "cs123.doc";
    //			String file_name = "cs.docx";
    //			String file_name = "cs1.xls";
    //			String file_name = "cs2.xlsx";
    			String file_name = "cs3.pdf";
    			String[] split = file_name.split("\\.");
    			String suffix = split[split.length - 1];
    			String time = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date());
    			String content = ReadUtil.readContent(path + file_name);
    			String jsonObj = "{" +
    					"\"file_name\":\"" + file_name + "\"," +
    					"\"suffix\":\"" + suffix + "\"," +
    					"\"time\":\"" + time + "\"," +
    					"\"content\":\"" + content + "\"" +
    					"}";
    //			ElasticsearchUtil.insert("cs", "doc", uuid, JSON.parseObject(jsonObj));
    //			ElasticsearchUtil.update("cs", "doc", "3", JSON.parseObject(jsonObj));
    //			ElasticsearchUtil.delete("cs", "doc", "2");
    //			Map<String, Object> source = ElasticsearchUtil.getJson("cs", "doc", "3");
    //			System.out.println(source.get("user"));
    			List<String> list = ElasticsearchUtil.search("cs", "doc", "一个");
    			System.out.println(list);
    		} catch (Exception e) {
    			e.printStackTrace();
    		}finally {
    			ElasticsearchUtil.close();
    		}
    	}
    
    }

四、效果如下

![20200830164507739.png][]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzE1MjYwMzE1_size_16_color_FFFFFF_t_70][]

[Spire.Pdf.jar]: https://www.e-iceblue.cn/Downloads/Free-Spire-PDF-JAVA.html
[20200830164507739.png]: /images/1603614290921.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzE1MjYwMzE1_size_16_color_FFFFFF_t_70]: /images/1603614267417.png