Styjun

I've this issue in my project. I read my .xlsx excel file using Apache Poi and I want to index them in my Solr core. I use SolrInputDocument to index reading file. Here is my java codes

package org.solr;

import org.apache.poi.ss.usermodel.*;
import org.apache.poi.xssf.usermodel.XSSFWorkbook;
import org.apache.poi.ss.usermodel.Cell;
import org.apache.poi.ss.usermodel.Row;
import org.apache.poi.ss.usermodel.Sheet;
import org.apache.poi.ss.usermodel.Workbook;

import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.util.Iterator;
import java.util.ArrayList;
import java.util.List;

import org.apache.solr.client.solrj.SolrClient;
import org.apache.solr.client.solrj.SolrQuery;
import org.apache.solr.client.solrj.SolrQuery.ORDER;
import org.apache.solr.client.solrj.SolrServerException;
import org.apache.solr.client.solrj.impl.HttpSolrClient;
import org.apache.solr.client.solrj.impl.XMLResponseParser;
import org.apache.solr.client.solrj.response.QueryResponse;
import org.apache.solr.client.solrj.response.UpdateResponse;
import org.apache.solr.common.SolrDocumentList;
import org.apache.solr.common.SolrInputDocument;

public class PoiJava 
 private static final String fileName="C:\Users\FTK1187\Desktop\E-Archive - Copy\TableArchive.xlsx";

 public static void main(String Args[]) throws SolrServerException 
 List dataList=getArchiveData();

 

 private static List getArchiveData() throws SolrServerException 
 List dataList =new ArrayList();
 FileInputStream excelFile=null;
 try 
 excelFile = new FileInputStream(new File(fileName));
 Workbook workbook = new XSSFWorkbook(excelFile);
 Sheet datatypeSheet = workbook.getSheetAt(0);
 Iterator<Row> iterator = datatypeSheet.iterator();
 String urlString="http://localhost:8983/solr/archiveCore";
 SolrClient solr=new HttpSolrClient.Builder(urlString).build();
 SolrInputDocument document=new SolrInputDocument();
 if(!document.isEmpty())
 
 solr.deleteByQuery("*");
 solr.commit();
 

 while (iterator.hasNext()) 

 Row currentRow = iterator.next();
 Iterator<Cell> cellIterator = currentRow.iterator();

 while (cellIterator.hasNext()) 

 Cell currentCell = cellIterator.next();
 //getCellTypeEnum shown as deprecated for version 3.15
 //getCellTypeEnum ill be renamed to getCellType starting from version 4.0
 if (currentCell.getCellTypeEnum() == CellType.STRING) 
 //System.out.println(currentCell.getStringCellValue());
 for(int i=0;i<currentRow.getLastCellNum();i++)
 
 if(currentCell.getColumnIndex()==1)
 
 document.addField("NameAdded", currentCell.getStringCellValue());
 
 else if(currentCell.getColumnIndex()==2)
 
 document.addField("DateAdded", currentCell.getStringCellValue());
 
 else if(currentCell.getColumnIndex()==3)
 
 document.addField("NameModified", "");
 
 else if(currentCell.getColumnIndex()==4)
 
 document.addField("DateModified", "");
 
 else if(currentCell.getColumnIndex()==5)
 
 document.addField("strSO", currentCell.getStringCellValue());
 
 else if(currentCell.getColumnIndex()==6)
 
 document.addField("strCust", "");
 
 else if(currentCell.getColumnIndex()==7)
 
 document.addField("strOperator", "");
 
 else if(currentCell.getColumnIndex()==8)
 
 document.addField("PackName", currentCell.getStringCellValue());
 
 else if(currentCell.getColumnIndex()==9)
 
 document.addField("DocName", currentCell.getStringCellValue());
 
 else if(currentCell.getColumnIndex()==10)
 
 document.addField("DocType", currentCell.getStringCellValue());
 
 else if(currentCell.getColumnIndex()==11)
 
 document.addField("extType", currentCell.getStringCellValue());
 
 else if(currentCell.getColumnIndex()==12)
 
 document.addField("FileName", currentCell.getStringCellValue());
 
 else if(currentCell.getColumnIndex()==13)
 
 document.addField("FilePath", currentCell.getStringCellValue());
 
 else if(currentCell.getColumnIndex()==14)
 
 document.addField("NameDeleted", "");
 
 else if(currentCell.getColumnIndex()==15)
 
 document.addField("DateDeleted", "");
 
 else if(currentCell.getColumnIndex()==16)
 
 document.addField("intRev", currentCell.getStringCellValue());
 

 


 else if (currentCell.getCellTypeEnum() == CellType.NUMERIC) 
 //System.out.println(currentCell.getNumericCellValue());
 for(int k=0;k<currentRow.getLastCellNum();k++)
 
 if(currentCell.getColumnIndex()==0)
 
 document.addField("id", currentCell.getNumericCellValue());
 

 

 
 UpdateResponse response=solr.add(document);
 solr.commit();

 
 //System.out.println();
 System.out.println(document.getField("id"));
 
 catch (FileNotFoundException e) 
 e.printStackTrace();
 
 catch(IOException e) 
 e.printStackTrace();
 
 return dataList;
 

So when I'm running my project it gives me this error.

Exception in thread "main" org.apache.solr.client.solrj.impl.HttpSolrClient$RemoteSolrException: Error from server at http://localhost:8983/solr/archiveCore: Document is missing mandatory uniqueKey field: id
 at org.apache.solr.client.solrj.impl.HttpSolrClient.executeMethod(HttpSolrClient.java:610)
 at org.apache.solr.client.solrj.impl.HttpSolrClient.request(HttpSolrClient.java:279)
 at org.apache.solr.client.solrj.impl.HttpSolrClient.request(HttpSolrClient.java:268)
 at org.apache.solr.client.solrj.SolrRequest.process(SolrRequest.java:149)
 at org.apache.solr.client.solrj.SolrClient.add(SolrClient.java:173)
 at org.apache.solr.client.solrj.SolrClient.add(SolrClient.java:138)
 at org.apache.solr.client.solrj.SolrClient.add(SolrClient.java:152)
 at org.solr.PoiJava.getArchiveData(PoiJava.java:148)
 at org.solr.PoiJava.main(PoiJava.java:33)

When I'm indexing files using SimplePostTool there is not error like that but I want to update my core in my web page.

You probably have in your schema a field set as the unique key like this:

<uniqueKey>id</uniqueKey>

The problem is that when you upload a doc, in this case via Apache POI, you are not sending a value for that unique field.

You have a couple options:

1. If you do have a field that will be unique, use it. For example, with a copyField option like:

<copyField source="excel_guaranteed_unique" dest="id"/>

2. As you have the actual document, you could just add a UUID to the "id" field.




3. Create a unique field like a UUID updating your RequestHandlder, like this:

<updateRequestProcessorChain name="uuid" >
 <processor class="solr.UUIDUpdateProcessorFactory">
 <str name="fieldName">id</str>
 </processor>
 ...
</updateRequestProcessorChain>
... 
<requestHandler name="/update" class="solr.UpdateRequestHandler">
 <lst name="defaults">
 <str name="update.chain">uuid</str>
 </lst>
</requestHandler>

You also need to update the extract handler:

 <requestHandler name="/update/extract"
 startup="lazy"
 class="solr.extraction.ExtractingRequestHandler" >
<lst name="defaults">
 ...
 <str name="update.chain">uuid</str>
</lst>