Pourquoi un fichier .doc peut-il être indexé via Lucene alors qu'un fichier .docx ne peut pas être indexé?

Question

Je ne peux pas indexer un fichier docx dans java en utilisant lucene. Seul mon fichier doc est indexé. Mais quand je l'ai passé à l'analyseur Doc, il retourne vide et je ne suis pas capable de rechercher le contenu.

---

Here is indexer code. 
package luceneapplication; 

import java.io.File; 
import java.io.FileNotFoundException; 
import java.io.FileReader; 
import java.io.IOException; 
import java.util.Arrays; 
import org.apache.lucene.analysis.standard.StandardAnalyzer; 
import org.apache.lucene.document.Document; 
import org.apache.lucene.document.Field; 
import org.apache.lucene.index.CorruptIndexException; 
import org.apache.lucene.index.IndexReader; 
import org.apache.lucene.index.IndexWriter; 
import org.apache.lucene.index.IndexWriterConfig; 
import org.apache.lucene.queryParser.ParseException; 
import org.apache.lucene.store.FSDirectory; 
import org.apache.lucene.util.Version; 
import parsers.DocFileParser; 
import parsers.PdfFileParser; 

public class Indexer { 

    private final String sourceFilePath = "C:/temp"; //give the location of the source files location here 
    private final String indexFilePath = "C:/com/New folder"; //give the location where you guys want to create index 
    private IndexWriter writer = null; 
    private File indexDirectory = null; 
    private String fileContent; //temporary storer of all the text parsed from doc and pdf 

    /** 
    * 
    * @throws FileNotFoundException 
    * @throws CorruptIndexException 
    * @throws IOException 
    */ 
    private Indexer() throws FileNotFoundException, CorruptIndexException, IOException { 
     try { 
      long start = System.currentTimeMillis(); 
      createIndexWriter(); 
      checkFileValidity(); 
      closeIndexWriter(); 
      long end = System.currentTimeMillis(); 
      System.out.println("Total Document Indexed : " + TotalDocumentsIndexed()); 
      System.out.println("Total time" + (end - start)/(100 * 60)); 
     } catch (Exception e) { 
      System.out.println("Sorry task cannot be completed"); 
     } 
    } 

    /** 
    * IndexWriter writes the data to the index. Its provided by Lucene 
    * 
    * @param analyzer : its a standard analyzer, in this case it filters out 
    * englishStopWords and also analyses TFIDF 
    */ 
    private void createIndexWriter() { 
     try { 
      indexDirectory = new File(indexFilePath); 
      if (!indexDirectory.exists()) { 
       indexDirectory.mkdir(); 
      } 
      FSDirectory dir = FSDirectory.open(indexDirectory); 
      StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_34); 
      IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_34, analyzer); 
      writer = new IndexWriter(dir, config); 
     } catch (Exception ex) { 
      System.out.println("Sorry cannot get the index writer"); 
     } 
    } 

    /** 
    * This function checks whenther the file passed is valid or not 
    */ 
    private void checkFileValidity() { 
     File[] filesToIndex = new File[100]; // suppose there are 100 files at max 
     filesToIndex = new File(sourceFilePath).listFiles(); 
     for (File file : filesToIndex) { 
      try { 
       //to check whenther the file is a readable file or not. 
       if (!file.isDirectory() 
         && !file.isHidden() 
         && file.exists() 
         && file.canRead() 
         && file.length() > 0.0 
         && file.isFile()) { 
        if (file.getName().endsWith(".doc") || file.getName().endsWith(".pdf") 
          || file.getName().endsWith(".docx")) { 
         //different method for indexing doc and pdf file. 
         StartIndex(file); 
        } 
       } 
      } catch (Exception e) { 
       System.out.println("Sorry cannot index " + file.getAbsolutePath()); 
      } 
     } 
    } 

    /** 
    * This method is for indexing pdf file and doc file. The text parsed from 
    * them are indexed along with the filename and filepath 
    * 
    * @param file : the file which you want to index 
    * @throws FileNotFoundException 
    * @throws CorruptIndexException 
    * @throws IOException 
    */ 
    public void StartIndex(File file) throws FileNotFoundException, CorruptIndexException, IOException { 
     fileContent = null; 
     try { 
      Document doc = new Document(); 
      if (file.getName().endsWith(".docx")) { 
       //call the doc file parser and get the content of doc file in txt format 
       String path = file.getCanonicalPath(); 
       System.out.println("Path is:"+path); 
       DocFileParser docParser = new DocFileParser(); 
       System.out.println("DocFileParser contains:"+docParser.toString()); 
       fileContent = ((docParser.DocFileContentParser(path))); 
       System.out.println("file contents :"+fileContent); 
      } 
      doc.add(new Field("content", fileContent,Field.Store.YES,Field.Index.ANALYZED)); 
      doc.add(new Field("filename", file.getName(), 
        Field.Store.YES, Field.Index.ANALYZED)); 
      doc.add(new Field("fullpath", file.getCanonicalPath(), 
        Field.Store.YES, Field.Index.ANALYZED)); 
      if (doc != null) { 
       writer.addDocument(doc); 
      } 
      System.out.println("Indexed" + file.getAbsolutePath()); 
     } catch (Exception e) { 
      System.out.println("error in indexing" + (file.getAbsolutePath())); 
     } 
    } 

    /** 
    * This method returns the total number of documents indexed. 
    * 
    * @return total number of documents indexed. 
    */ 
    private int TotalDocumentsIndexed() { 
     try { 
      IndexReader reader = IndexReader.open(FSDirectory.open(indexDirectory)); 
      return reader.maxDoc(); 
     } catch (Exception ex) { 
      System.out.println("Sorry no index found"); 
     } 
     return 0; 
    } 

    /** 
    * closes the IndexWriter 
    */ 
    private void closeIndexWriter() { 
     try { 
      writer.optimize(); 
      writer.close(); 
     } catch (Exception e) { 
      System.out.println("Indexer Cannot be closed"); 
     } 
    } 

    /** 
    * Main method. 
    * 
    * @param arg 
    */ 
    public static void main(String arg[]) throws ParseException { 
     try { 
      new Indexer(); 
      new Searcher().searchIndex("Program"); 
     } catch (IOException ex) { 
      System.out.println("Cannot Start :("); 
     } 
    } 
} 

---

Searcher code 
public class Searcher { 

    public void searchIndex(String instring) throws IOException, ParseException { 
     System.out.println("Searching for ' " + instring + " '"); 
     IndexSearcher searcher = new IndexSearcher(FSDirectory.open(new File("C:\\com\\New folder"))); 
     Analyzer analyzer1 = new StandardAnalyzer(Version.LUCENE_34); 
     QueryParser queryParser = new QueryParser(Version.LUCENE_34, "content", analyzer1); 
     QueryParser queryParserfilename = new QueryParser(Version.LUCENE_34, "fullpath", analyzer1); 
     Query query = queryParser.parse(instring); 
     // Query queryfilename = queryParserfilename.parse(instring); 
     TopDocs hits = searcher.search(query, 100); 
     ScoreDoc[] document = hits.scoreDocs; 

     System.out.println("Total no of hits for content: " + hits.totalHits); 
     for (int i = 0; i < document.length; i++) { 
      Document doc = searcher.doc(document[i].doc); 
      String filePath = doc.get("fullpath"); 
      System.out.println(filePath); 
     } 

//  TopDocs hitfilename = searcher.search(queryfilename, 100); 
//  ScoreDoc[] documentfilename = hitfilename.scoreDocs; 
//  System.out.println("Total no of hits according to file name" + hitfilename.totalHits); 
//  for (int i = 0; i < documentfilename.length; i++) { 
//   Document doc = searcher.doc(documentfilename[i].doc); 
//   String filename = doc.get("filename"); 
//   System.out.println(filename); 
//  } 
    } 

---

and my DocParser code 
public class DocFileParser { 

    /** 
    * This method parses the content of the .doc file. i.e. this method will 
    * return all the text of the file passed to it. 
    * 
    * @param fileName : file name of which you want the conent of. 
    * @return : returns the content of the file 
    */ 
    public String DocFileContentParser(String fileName)throws Exception { 
     System.out.println("Filename in DocParser:" + fileName); 
     POIFSFileSystem fs = null; 
     //try 
     { 

//   if (fileName.endsWith(".xls")) { //if the file is excel file 
//    ExcelExtractor ex = new ExcelExtractor(fs); 
//    return ex.getText(); //returns text of the excel file 
//   } else if (fileName.endsWith(".ppt")) { //if the file is power point file 
//    PowerPointExtractor extractor = new PowerPointExtractor(fs); 
//    return extractor.getText(); //returns text of the power point file 
// 


      //else for .doc file 
      FileInputStream inputstream = new FileInputStream(new File(fileName)); 
      fs = new POIFSFileSystem(inputstream); 
      System.out.println("POIFSFileSystem:" + fs); 
      HWPFDocument doc = new HWPFDocument(fs); 
//   System.out.println("HWPFDocument:" + doc); 
      WordExtractor we = new WordExtractor(fs); 
      System.out.println("WordExtractor:" + we); 
      String content = we.getTextFromPieces(); 
      return content;//if the extension is .doc 
     } 
//   catch (Exception e) { 
//   e.getMessage(); 
//  } 
     //return ""; 
    } 
} 

i m retourner le contenu mais je ne reçois pas. Il me montre vide j'ai SYSO il après l'appel fucntion est retourné.S'il vous plaît laissez-moi savoir que je suis coincé pendant 3 jours. Merci

Answer 1

Promouvoir un commentaire à une réponse:

La raison pour laquelle votre code fonctionne uniquement avec .doc fichiers est que vous avez seulement le code écrit pour gérer .doc fichiers! Comme le Apache POI components page explains, HWPF (que vous avez utilisé) poignées .doc fichiers, qui .docx fichiers ont besoin XWPF

Cependant, vous certainement ne voulez pas d'écrire votre propre code contre POI pour l'extraction de texte simple. Des trucs avancés, avec des règles spéciales - bien sûr! Mais basique "s'il vous plaît donnez-moi du texte" choses, il ya des bibliothèques de niveau supérieur qui font tout pour vous

Je vous suggère fortement de passer à l'aide de Apache Tika à la place. Tika est construit sur un tas de bibliothèques open source, y compris les POI. Il peut générer du texte brut pour l'indexation pour Word .doc et .docx, tous en utilisant les mêmes lignes de code. Il prend en charge un large and growing number of file formats. Beaucoup plus facile à utiliser, et tout ce dont vous avez besoin est déjà là!