1. 程式人生 > >Lucene筆記27-Lucene的使用-自定義QueryParser解決日期和數字範圍問題

Lucene筆記27-Lucene的使用-自定義QueryParser解決日期和數字範圍問題

一、需求說明

Lucene提供的getRangeQuery(String field, String part1, String part2, boolean inclusive)方法支援的是String,假設我們需要對數字範圍查詢,那麼就需要我們自己來改寫了。

二、程式碼實現

重寫getRangeQuery()方法。searchByQuery()方法將傳入的查詢字串進行parse,根據轉化後的樣式,呼叫到了被重寫的getRangeQuery()方法,從而走了裡面的邏輯完成查詢。

package com.wsy;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.*;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

import java.io.File;
import java.io.IOException;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.regex.Pattern;

public class CustomParser extends QueryParser {
    private static Directory directory;
    private static IndexReader indexReader;
    private static Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_35);

    static {
        try {
            directory = FSDirectory.open(new File("E:\\Lucene\\IndexLibrary"));
            indexReader = IndexReader.open(directory);
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    public CustomParser(Version matchVersion, String f, Analyzer a) {
        super(matchVersion, f, a);
    }

    @Override
    protected Query getRangeQuery(String field, String part1, String part2, boolean inclusive) throws ParseException {
        if (field.equals("size")) {
            return NumericRangeQuery.newIntRange(field, Integer.parseInt(part1), Integer.parseInt(part2), inclusive, inclusive);
        } else if (field.equals("date")) {
            Pattern pattern = Pattern.compile("\\d{4}-\\d{2}-\\d{2}");
            if (pattern.matcher(part1).matches() && pattern.matcher(part2).matches()) {
                SimpleDateFormat simpleDateFormat = new SimpleDateFormat("yyyy-MM-dd");
                try {
                    long start = simpleDateFormat.parse(part1).getTime();
                    long end = simpleDateFormat.parse(part2).getTime();
                    return NumericRangeQuery.newLongRange(field, start, end, inclusive, inclusive);
                } catch (java.text.ParseException e) {
                    e.printStackTrace();
                }
            } else {
                throw new ParseException("要檢索的日期格式不對,請使用yyyy-MM-dd格式");
            }
        }
        return super.getRangeQuery(field, part1, part2, inclusive);
    }

    public void searchByQuery(String value) {
        try {
            CustomParser customParser = new CustomParser(Version.LUCENE_35, "content", analyzer);
            Query query = customParser.parse(value);
            System.out.println("query:\t" + query);
            IndexSearcher indexSearcher = new IndexSearcher(indexReader);
            TopDocs topDocs = indexSearcher.search(query, 100);
            ScoreDoc[] scoreDocs = topDocs.scoreDocs;
            SimpleDateFormat simpleDateFormat = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
            for (ScoreDoc scoreDoc : scoreDocs) {
                Document document = indexSearcher.doc(scoreDoc.doc);
                // 依次輸出文件id,文件得分,文件名字,文件路徑,文件大小,文件修改時間
                System.out.println(scoreDoc.doc + "-->" + scoreDoc.score + "-->" + document.get("fileName") + "-->" + document.get("path") + "-->" + document.get("size") + "-->" + simpleDateFormat.format(new Date(Long.valueOf(document.get("date")))));
            }
            indexSearcher.close();
        } catch (IOException e) {
            e.printStackTrace();
        } catch (ParseException e) {
            System.err.println(e.getMessage());
        }
    }

    public static void main(String[] args) {
        CustomParser customParser = new CustomParser(Version.LUCENE_35, "content", analyzer);
        // 查詢size是300到800的
        customParser.searchByQuery("size:[300 TO 800]");
        // 查詢date是2018-01-01到2018-12-31的
        customParser.searchByQuery("date:[2018-01-01 TO 2018-12-31]");
    }
}