我正在尝试从Lucene获取术语文档矩阵。似乎大多数SO问题都针对具有不同类的过时API。我尝试将这两个问题的见解相结合,以从每个文档中获取术语向量:


Term Vector Frequency in Lucene 4.0
Is it possible to iterate through documents stored in Lucene Index?


相关代码,但在当前API中无法识别DocEnum。如何获得每个文档的术语向量或所有术语的计数?

IndexReader reader = DirectoryReader.open(index);

for (int i = 0;  i < reader.maxDoc(); i++) {
    Document doc = reader.document(i);
    Terms terms = reader.getTermVector(i, "country_text");

    if (terms != null && terms.size() > 0) {
        // access the terms for this field
        TermsEnum termsEnum = terms.iterator();
        BytesRef term = null;

        // explore the terms for this field
        while ((term = termsEnum.next()) != null) {
            // enumerate through documents, in this case only one
            DocsEnum docsEnum = termsEnum.docs(null, null);
            int docIdEnum;
            while ((docIdEnum = docsEnum.nextDoc()) != DocIdSetIterator.NO_MORE_DOCS) {
                // get the term frequency in the document
                System.out.println(term.utf8ToString()+ " " + docIdEnum + " " + docsEnum.freq());
            }
        }
    }
}


完整代码:

import java.io.*;
import java.util.Iterator;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.Terms;
import org.apache.lucene.index.TermsEnum;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.FuzzyQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.BytesRef;
import org.json.simple.JSONArray;
import org.json.simple.JSONObject;
import org.json.simple.JSONValue;
import org.json.simple.parser.JSONParser;

public class LuceneIndex {

    public static void main(String[] args) throws IOException, ParseException {

        String jsonFilePath = "wiki_data.json";
        JSONParser parser = new JSONParser();
        // Specify the analyzer for tokenizing text.
        StandardAnalyzer analyzer = new StandardAnalyzer();
        // create the index
        Directory index = new RAMDirectory();
        IndexWriterConfig config = new IndexWriterConfig(analyzer);
        IndexWriter w = new IndexWriter(index, config);

        try {
            JSONArray a = (JSONArray) parser.parse(new FileReader(jsonFilePath));

            for (Object o : a) {
                JSONObject country = (JSONObject) o;
                String countryName = (String) country.get("country_name");
                String cityName = (String) country.get("city_name");
                String countryText = (String) country.get("country_text");
                String cityText = (String) country.get("city_text");
                System.out.println(cityName);
                addDoc(w, countryName, cityName, countryText, cityText);
            }
            w.close();

            IndexReader reader = DirectoryReader.open(index);

            for (int i = 0;  i < reader.maxDoc(); i++) {
                Document doc = reader.document(i);
                Terms terms = reader.getTermVector(i, "country_text");

                if (terms != null && terms.size() > 0) {
                    // access the terms for this field
                    TermsEnum termsEnum = terms.iterator();
                    BytesRef term = null;

                    // explore the terms for this field
                    while ((term = termsEnum.next()) != null) {
                        // enumerate through documents, in this case only one
                        DocsEnum docsEnum = termsEnum.docs(null, null);
                        int docIdEnum;
                        while ((docIdEnum = docsEnum.nextDoc()) != DocIdSetIterator.NO_MORE_DOCS) {
                            // get the term frequency in the document
                            System.out.println(term.utf8ToString()+ " " + docIdEnum + " " + docsEnum.freq());
                        }
                    }
                }
            }

            // reader can be closed when there
            // is no need to access the documents any more.
            reader.close();

        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } catch (org.json.simple.parser.ParseException e) {
            e.printStackTrace();
        }
    }

    private static void addDoc(IndexWriter w, String countryName, String cityName,
            String countryText, String cityText) throws IOException {
        Document doc = new Document();
        doc.add(new StringField("country_name", countryName, Field.Store.YES));
        doc.add(new StringField("city_name", cityName, Field.Store.YES));
        doc.add(new TextField("country_text", countryText, Field.Store.YES));
        doc.add(new TextField("city_text", cityText, Field.Store.YES));

        w.addDocument(doc);
    }

}

最佳答案

根据此question,您不应将TextField用于词频。因为它不计算。
使用“字段”。

关于java - Lucene中的术语文档矩阵,我们在Stack Overflow上找到一个类似的问题:https://stackoverflow.com/questions/47321816/

10-15 20:22