每日一练

pinyinReader:

package jim.pinyinReader;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.IOException;

import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.Field.Index;
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.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.util.Version;
import org.wltea.analyzer.lucene.IKAnalyzer;

public class pinyinReader {
	Document doc = null;
	Field field = null;
	IndexWriter writer = null;
	public void ReadPY(){
		
		BufferedReader myIn = null;
		StringBuffer sb1 = new StringBuffer();
		StringBuffer sb2 = new StringBuffer();
		IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_35, new IKAnalyzer());//选择lucene的版本以及分词器的版本  
		try {
			Directory directory = FSDirectory.open(new File("index"));//创建directory,其储存方式为在
			writer = new IndexWriter(directory,iwc);
		} catch (CorruptIndexException e1) {
			e1.printStackTrace();
		} catch (LockObtainFailedException e1) {
			e1.printStackTrace();
		} catch (IOException e1) {
			e1.printStackTrace();
		}//创建引索器  
		try
		{
			myIn = new BufferedReader(new FileReader("test.txt"));
		}
		catch(FileNotFoundException e)
		{
			System.out.println("File not be found!!");
		}
		int s = 0;
		try {
			while((s = myIn.read()) != -1)
			{
				if(s != '\n')
					if(!((s < 'a'||s>'z')&& (s != ' ')&&(s != '\'')))
					{
						sb1.append((char)s);					//添加拼音
					}
					else
					{
							sb2.append((char)s);				//添加汉字
					}
				else
				{

					System.out.println("换行");
					doc = new Document();//创建索引文件  
					System.out.println("sb1: "+sb1);
					field = new Field("pinyin",sb1.toString(),Field.Store.YES,Index.ANALYZED);//创建索引
					doc.add(field); 
					sb1.delete(0,sb1.capacity()-1);
					System.out.println("sb2: "+sb2);
					field = new Field("ciyu",sb2.toString(),Field.Store.YES,Index.NOT_ANALYZED);//创建索引
					doc.add(field);
					sb2.delete(0,sb2.capacity()-1);
					writer.addDocument(doc);

				}
			}
			 writer.close();//关闭索引器

		} catch (IOException e) {
			System.out.println("Read Error");
			e.printStackTrace();
		}

		try {
			myIn.close();
			
		} catch (IOException e) {
			System.out.println("Close Error");
			e.printStackTrace();
		}

	}
	public void check() throws IOException{						//检查索引是否被正确建立(打印索引)
		Directory directory = FSDirectory.open(new File("index"));//创建directory,其储存方式为在
		directory = FSDirectory.open(new File("index"));
		IndexReader reader = IndexReader.open(directory);
		for(int i = 0;i<reader.numDocs();i++){
			System.out.println(reader.document(i));
		}
	}
	public static void main(String args[]){
		pinyinReader reader = new pinyinReader();
		reader.ReadPY();
//		try {
//			reader.check();
//		} catch (IOException e) {
//			// TODO Auto-generated catch block
//			e.printStackTrace();
//		}
	}
}

Searcher:

package jim.pinyinReader;
import java.io.File;  
import java.io.IOException;  
  
import org.apache.lucene.document.Document;  
import org.apache.lucene.index.CorruptIndexException;  
import org.apache.lucene.index.IndexReader;  
import org.apache.lucene.queryParser.ParseException;  
import org.apache.lucene.queryParser.QueryParser;  
import org.apache.lucene.search.IndexSearcher;  
import org.apache.lucene.search.Query;  
import org.apache.lucene.search.ScoreDoc;  
import org.apache.lucene.search.TopDocs;  
import org.apache.lucene.store.Directory;  
import org.apache.lucene.store.FSDirectory;  
import org.apache.lucene.util.Version;  
import org.wltea.analyzer.lucene.IKAnalyzer;  
  
class Search {  
  
    Directory directory = null;//存储方式  
    String indexPath = "index";//引索存放的目录  
    IndexReader reader = null;//读入引索  
    IndexSearcher searcher = null;//确定搜索对象  
    QueryParser parser = null;//用于确定搜索时的引索的版本以及分词器  
    Query query = null;//记录要搜索的词语  
    TopDocs tds = null;//记录搜索后返回的结果  
    Document document = null;//存放搜索结果以便于提取结果  
    ScoreDoc[] sds = null;//存放TopDocs传来的内容(搜索结果)  
    public Search(String KeyWord){  
        try {  
            directory = FSDirectory.open(new File(indexPath));  
        } catch (IOException e) {  
            System.out.println("创建Directory时发生错误!");  
            e.printStackTrace();  
        }//创建directory,其储存方式为在硬盘上储存  
        try {  
            reader = IndexReader.open(directory);  
        } catch (CorruptIndexException e) {  
            System.out.println("创建IndexReader时发生错误!");  
            e.printStackTrace();  
        } catch (IOException e) {  
            System.out.println("创建IndexReader时发生错误!");  
            e.printStackTrace();  
        }  
        searcher = new IndexSearcher(reader);  
        parser = new QueryParser(Version.LUCENE_35,"pinyin",new IKAnalyzer());  
        try {  
            query = parser.parse(KeyWord);  // 在此输入拼音
        } catch (ParseException e) {  
            System.out.println("query = parser.parse(\"keyword\")时发生错误");  
            e.printStackTrace();  
        }  
        try {  
            tds = searcher.search(query,5);  
        } catch (IOException e) {  
            System.out.println("std = searcher.search(query,5);时发生错误");  
            e.printStackTrace();  
        }   
        sds = tds.scoreDocs;  
        System.out.println("一共搜索到: "+sds.length+" 条");  
        if(sds.length != 0){  
        for( ScoreDoc sd:sds){  
              
            try {  
                document = searcher.doc(sd.doc);  
            } catch (CorruptIndexException e) {  
                System.out.println("document = searcher.doc(sd.doc);时发生错误");  
                e.printStackTrace();  
            } catch (IOException e) {  
                System.out.println("document = searcher.doc(sd.doc);时发生错误");  
                e.printStackTrace();  
            }  
            System.out.println(document.get("pinyin")+"["+document.get("ciyu")+"]");  
              
        }  
    }  
        else  
            System.out.println("The word you enter can't be found!");  
          
        try {  
            reader.close();  
        } catch (IOException e) {  
            System.out.println("关闭reader时发生错误!");  
            e.printStackTrace();  
        }  
          
        System.out.println("Finished");  
    }  
      
}  
public class Searcher {  
    public static void main(String [] args){  
        new Search("wo");  
    }  
}  

今天的收获:

今天把输拼音出汉字搞定了,虽然不是很准确.

今天的不足:

没用弄好汉字转拼音