使用Elasticsearch7 java api实现pdf全文检索

//定制一个管道,用于将Base64转换为文字形式

PUT _ingest/pipeline/attachment
{
  "description" : "Extract attachment information",  //管道的描述
  "processors" : [
    {
      "attachment" : {
        "field" : "data"        //配置在哪个字段获取Base64数据,然后进行转换
      }
    }
  ]
}


//后面我们索引文档的时候 ?pipeline=attachment,就要指定这个参数,表明索引一个文档的时候要
使用这个管道

PUT my_index/_doc/my_id?pipeline=attachment
{
  "data": "e1xydGYxXGFuc2kNCkxvcmVtIGlwc3VtIGRvbG9yIHNpdCBhbWV0DQpccGFyIH0=" //base64数据
}

"attachment": {
      "content_type": "application/rtf",
      "language": "ro",
      "content": "Lorem ipsum dolor sit amet",
      "content_length": 28
    }

 public static String pdfToBase64(String contentpath) throws IOException {
        InputStream is = null;
        String url = contentpath;
        URL url2 = new URL(url);
        HttpURLConnection conn = (HttpURLConnection) url2.openConnection();
        conn.setDoInput(true);
        conn.connect();
        is =  conn.getInputStream();
        
         // 将图片文件转化为字节数组字符串，并对其进行Base64编码处理
        byte[] data = null;
        // 读取图片字节数组
        try {
            ByteArrayOutputStream swapStream = new ByteArrayOutputStream();
            byte[] buff = new byte[100];
            int rc = 0;
            while ((rc = is.read(buff, 0, 100)) > 0) {
                swapStream.write(buff, 0, rc);
            }
            data = swapStream.toByteArray();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if (is != null) {
                try {
                    is.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
        return new BASE64Encoder().encode(data).replace("\n", "").replace("\r", "");
    }

//将http链接作为参数
String base64Contentpath = Base64Util.pdfToBase64("http://******.pdf");

    RestHighLevelClient esClient = esClient();
    Map<String,Object> jsonMap = new HashMap<>();

    jsonMap.put("base64Contentpath", base64Contentpath);


    IndexRequest request = new IndexRequest("pdf")
                                .setPipeline("管道名称")   //这里就是前面通过json创建的管道
                                .source(jsonMap);  

    esClient.index(request, RequestOptions.DEFAULT);   //执行