lucene 建立索引的不同方式
1.创建一个简单的索引：
package lia.meetlucene; import java.io.File;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.apache.lucene.analysis.standard.StandardAnalyzer; public class BasicIndexer {
public static void main(String[] args) throws java.io.IOException {
String indexDir = "C:/Users/Administrator/Desktop/xdj"; Directory dir = FSDirectory.open(new File(indexDir));
/*
* writer = new IndexWriter(dir, //3 创建Lucene Index Writer new
* StandardAnalyzer( //3 Version.LUCENE_30),//3 true, //3
* IndexWriter.MaxFieldLength.UNLIMITED); //3
*/
IndexWriter writer = new IndexWriter(dir, // 3 创建Lucene Index Writer
new StandardAnalyzer(Version.LUCENE_30),//
true, //
IndexWriter.MaxFieldLength.UNLIMITED); // 3 // Document
Document doc = new Document(); // Field -title
String title = "i love china";
Field field = new Field("title", title, Field.Store.YES,
Field.Index.ANALYZED);
// add field
doc.add(field); // Field -content
String content = "i love you, my mother land! ";
field = new Field("content", content, Field.Store.YES,
Field.Index.ANALYZED);
// add field
doc.add(field); // add document
writer.addDocument(doc); // close IndexWriter
writer.close(); // message
System.out.println("Index Created!");
}
}
2.创建一个复杂点的索引：
package lia.meetlucene; import java.io.File;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.apache.lucene.analysis.standard.StandardAnalyzer; public class BasicIndexer {
public static void main(String[] args) throws java.io.IOException {
String indexDir = "C:/Users/Administrator/Desktop/xdj"; Directory dir = FSDirectory.open(new File(indexDir));
/*
* writer = new IndexWriter(dir, //3 创建Lucene Index Writer new
* StandardAnalyzer( //3 Version.LUCENE_30),//3 true, //3
* IndexWriter.MaxFieldLength.UNLIMITED); //3
*/
IndexWriter writer = new IndexWriter(dir, // 3 创建Lucene Index Writer
new StandardAnalyzer(Version.LUCENE_30),//
true, //
IndexWriter.MaxFieldLength.UNLIMITED); // 3 // 创建Document--1
Document doc = new Document(); // 创建Field -title
String title = "i love china";
Field field = new Field("title", title, Field.Store.YES,
Field.Index.NOT_ANALYZED);
// 添加add field
doc.add(field); // 创建Field -content
String content = "i love you, my mother land! ";
field = new Field("content", content, Field.Store.YES,
Field.Index.NOT_ANALYZED);
// 添加add field
doc.add(field); // 创建Field -time
String time = "2007-05-31";
field = new Field("time", time, Field.Store.YES, Field.Index.NO);
// 创建add field
doc.add(field); // 添加add document
writer.addDocument(doc); // 创建Document--2
doc = new Document(); // 创建Field -title
title = "i love mom";
field = new Field("title", title, Field.Store.YES,
Field.Index.NOT_ANALYZED);
// add field
doc.add(field); // 创建Field -content
content = "i love you, my mother! ";
field = new Field("content", content, Field.Store.YES,
Field.Index.NOT_ANALYZED);
// 添加add field
doc.add(field); // 创建Field -time
time = "2007-05-31";
field = new Field("time", time, Field.Store.YES, Field.Index.NO);
// 添加add field
doc.add(field); // 添加add document
writer.addDocument(doc); // 创建Document--3
doc = new Document(); // 创建Field -title
title = "i love xiaoyue";
field = new Field("title", title, Field.Store.YES,
Field.Index.NOT_ANALYZED);
// 添加add field
doc.add(field); // 创建Field -content
content = "i love you, my wife! ";
field = new Field("content", content, Field.Store.YES,
Field.Index.NOT_ANALYZED);
// 添加add field
doc.add(field); // 创建Field -time
time = "2007-05-31";
field = new Field("time", time, Field.Store.YES, Field.Index.NO);
// add field
doc.add(field); // 添加add document
writer.addDocument(doc); // 关闭close IndexWriter
writer.close(); // 提示message
System.out.println("Index Three Created!");
}
}
3.文件创建一个索引
package lia.meetlucene; import java.io.File;
import java.io.FileReader; import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.apache.lucene.analysis.standard.StandardAnalyzer; public class BasicIndexer {
public static void main(String[] args) throws java.io.IOException {
String indexDir = "C:/Users/Administrator/Desktop/xdj"; Directory dir = FSDirectory.open(new File(indexDir));
/*
* writer = new IndexWriter(dir, //3 创建Lucene Index Writer new
* StandardAnalyzer( //3 Version.LUCENE_30),//3 true, //3
* IndexWriter.MaxFieldLength.UNLIMITED); //3
*/
IndexWriter writer = new IndexWriter(dir, // 3 创建Lucene Index Writer
new StandardAnalyzer(Version.LUCENE_30),//
true, //
IndexWriter.MaxFieldLength.UNLIMITED); // 3 // 创建Document
Document doc = new Document();
File f = new File(
"E:/xdj/tengxun/a_______________mm/2014-02-19 06.59.53.xml"); // 创建Field -name
String name = f.getName();
Field field = new Field("name", name, Field.Store.YES,
Field.Index.NOT_ANALYZED);
// 添加add field
doc.add(field); // 创建Field -content
field = new Field("content", new FileReader(f)); // FileText.getText(f);
// add field
doc.add(field); // 创建Field -path
String path = f.getPath();
field = new Field("path", path, Field.Store.YES, Field.Index.NO);
// 添加add field
doc.add(field); // 添加add document
writer.addDocument(doc); // 创建**************************************************************/
doc = new Document();
f = new File(
"E:/xdj/tengxun/a_______________mm/2014-02-04 11.43.01.xml"); // 创建Field -name
name = f.getName();
field = new Field("name", name, Field.Store.YES,
Field.Index.NOT_ANALYZED);
// add field
doc.add(field); // 创建Field -content
field = new Field("content", new FileReader(f));
// 添加add field
doc.add(field); // 创建Field -path
path = f.getPath();
field = new Field("path", path, Field.Store.YES, Field.Index.NO);
// 添加add field
doc.add(field); // 添加add document
writer.addDocument(doc); // 关闭close IndexWriter
writer.close(); // 提示message
System.out.println("File Index Created!");
}
}
4.某个文件夹的所有文件创建索引
package lia.meetlucene; /**
* Copyright Manning Publications Co.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific lan
*/ import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.Directory;
import org.apache.lucene.util.Version; import java.io.File;
import java.io.FileFilter;
import java.io.IOException;
import java.io.FileReader; // From chapter 1 /**
* This code was originally written for Erik's Lucene intro java.net article
*/
public class Indexer { public static void main(String[] args) throws Exception {
// args = new String[2];
// args[0] = "E:/xiaodajun/new/lia2e/src/lia/meetlucene";
// args[1] =
// "E:/xiaodajun/new/lia2e/src/lia/meetlucene/data";//"src/lia/meetlucene/data";
// C:/Users/Administrator/Desktop/xdj/data
if (args.length != 2) {
throw new IllegalArgumentException("Usage: java "
+ Indexer.class.getName() + " <index dir> <data dir>");
}
// String indexDir = args[0]; // 1
// String dataDir = args[1]; // String indexDir = "C:/Users/Administrator/Desktop/xdj/suoyin";
String dataDir = "C:/Users/Administrator/Desktop/xdj/data"; // String indexDir =
// "E:/xdj/tengxun";//"C:/Users/Administrator/Desktop/xdj/suoyin";
// String dataDir =
// "E:/xdj/tengxunsuoying";//"C:/Users/Administrator/Desktop/xdj/weibohanzi"; long start = System.currentTimeMillis();
// ///////////////////////////////////////////////////////////////////////////////////////////
Indexer indexer = new Indexer(indexDir);
int numIndexed;
try {
numIndexed = indexer.index(dataDir, new TextFilesFilter());
} finally {
indexer.close();
}
long end = System.currentTimeMillis();
// /////////////////////////////////////////////////////////////////////////////////////////////
System.out.println("Indexing " + numIndexed + " files took "
+ (end - start) + " milliseconds");
} private IndexWriter writer; public Indexer(String indexDir) throws IOException {
Directory dir = FSDirectory.open(new File(indexDir)); /*
* writer = new IndexWriter(dir, //3 创建Lucene Index Writer new
* StandardAnalyzer( //3 Version.LUCENE_30),//3 true, //3
* IndexWriter.MaxFieldLength.UNLIMITED); //3
*/
writer = new IndexWriter(dir, // 3 创建Lucene Index Writer
new SmartChineseAnalyzer(Version.LUCENE_20),//
true, //
IndexWriter.MaxFieldLength.UNLIMITED); //
} public void close() throws IOException {
writer.close(); // 4 关闭Lucene Index Writer
} public int index(String dataDir, FileFilter filter) throws Exception { File[] files = new File(dataDir).listFiles(); for (File f : files) {
if (!f.isDirectory() && !f.isHidden() && f.exists() && f.canRead()
&& (filter == null || filter.accept(f))) {
indexFile(f);
}
} return writer.numDocs(); // 5返沪被索引文档数
} private static class TextFilesFilter implements FileFilter {
public boolean accept(File path) {
return path.getName().toLowerCase() // 6只索引.txt文件，采用FileFilter
.endsWith(".txt"); //
}
} protected Document getDocument(File f) throws Exception {
Document doc = new Document();
doc.add(new Field("contents", new FileReader(f))); // 7索引文件内容
doc.add(new Field("filename", f.getName(), // 8索引文件名
Field.Store.YES, Field.Index.NOT_ANALYZED));//
doc.add(new Field("fullpath", f.getCanonicalPath(), // 9索引文件完整路径
Field.Store.YES, Field.Index.NOT_ANALYZED));//
return doc;
} // Store.是否存储 yes no compress(压缩之后再存)
// Index。是否进行索引 Index.ANALYZED 分词后进行索引,NOT_ANALYZED 不索引，NOT_ANALYZED 不分词直接索引 private void indexFile(File f) throws Exception {
System.out.println("Indexing " + f.getCanonicalPath());
Document doc = getDocument(f);
writer.addDocument(doc); // 10向Lucene索引中添加文档
}
} /*
* #1 Create index in this directory #2 Index *.txt files from this directory #3
* Create Lucene IndexWriter #4 Close IndexWriter #5 Return number of documents
* indexed #6 Index .txt files only, using FileFilter #7 Index file content #8
* Index file name #9 Index file full path #10 Add document to Lucene index
*/
5.<Lucene in action>第二版索引demo
package lia.meetlucene; /**
* Copyright Manning Publications Co.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific lan
*/ import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.Directory;
import org.apache.lucene.util.Version; import java.io.File;
import java.io.FileFilter;
import java.io.IOException;
import java.io.FileReader; // From chapter 1 /**
* This code was originally written for Erik's Lucene intro java.net article
*/
public class Indexer { public static void main(String[] args) throws Exception {
// args = new String[2];
// args[0] = "E:/xiaodajun/new/lia2e/src/lia/meetlucene";
// args[1] =
// "E:/xiaodajun/new/lia2e/src/lia/meetlucene/data";//"src/lia/meetlucene/data";
// C:/Users/Administrator/Desktop/xdj/data
if (args.length != 2) {
throw new IllegalArgumentException("Usage: java "
+ Indexer.class.getName() + " <index dir> <data dir>");
}
// String indexDir = args[0]; // 1
// String dataDir = args[1]; // 2 // String indexDir = "C:/Users/Administrator/Desktop/xdj/suoyin";
// String dataDir = "C:/Users/Administrator/Desktop/xdj/data"; String indexDir = "C:/Users/Administrator/Desktop/xdj/suoyin";
String dataDir = "C:/Users/Administrator/Desktop/xdj/tengxun/A__Vae"; long start = System.currentTimeMillis();
// ///////////////////////////////////////////////////////////////////////////////////////////
Indexer indexer = new Indexer(indexDir);
int numIndexed;
try {
numIndexed = indexer.index(dataDir, new TextFilesFilter());
} finally {
indexer.close();
}
long end = System.currentTimeMillis();
// /////////////////////////////////////////////////////////////////////////////////////////////
System.out.println("Indexing " + numIndexed + " files took "
+ (end - start) + " milliseconds");
} private IndexWriter writer; public Indexer(String indexDir) throws IOException {
Directory dir = FSDirectory.open(new File(indexDir)); /*
* writer = new IndexWriter(dir, //3 创建Lucene Index Writer new
* StandardAnalyzer( //3 Version.LUCENE_30),//3 true, //3
* IndexWriter.MaxFieldLength.UNLIMITED); //3
*/
writer = new IndexWriter(dir, // 3 创建Lucene Index Writer
new SmartChineseAnalyzer(Version.LUCENE_20),// 3
// new StandardAnalyzer(Version.LUCENE_30),
true, //
IndexWriter.MaxFieldLength.UNLIMITED); //
} public void close() throws IOException {
writer.close(); // 4 关闭Lucene Index Writer
} public int index(String dataDir, FileFilter filter) throws Exception { File[] files = new File(dataDir).listFiles(); for (File f : files) {
if (!f.isDirectory() && !f.isHidden() && f.exists() && f.canRead()
&& (filter == null || filter.accept(f))) { indexFile(f);
}
} return writer.numDocs(); // 5返沪被索引文档数
} private static class TextFilesFilter implements FileFilter {
public boolean accept(File path) {
return path.getName().toLowerCase() // 6只索引.txt文件，采用FileFilter
.endsWith(".xml"); //
}
} protected Document getDocument(File f) throws Exception {
Document doc = new Document();
doc.add(new Field("contents", new FileReader(f))); // 7索引文件内容
doc.add(new Field("filename", f.getName(), // 8索引文件名
Field.Store.YES, Field.Index.NOT_ANALYZED));//
doc.add(new Field("fullpath", f.getCanonicalPath(), // 9索引文件完整路径
Field.Store.YES, Field.Index.NOT_ANALYZED));//
return doc;
} // Store.是否存储 yes no compress(压缩之后再存)
// Index。是否进行索引 Index.ANALYZED 分词后进行索引,NOT_ANALYZED 不索引，NOT_ANALYZED 不分词直接索引 private void indexFile(File f) throws Exception {
System.out.println("Indexing " + f.getCanonicalPath());
Document doc = getDocument(f);
writer.addDocument(doc); // 10向Lucene索引中添加文档
}
} /*
* #1 Create index in this directory #2 Index *.txt files from this directory #3
* Create Lucene IndexWriter #4 Close IndexWriter #5 Return number of documents
* indexed #6 Index .txt files only, using FileFilter #7 Index file content #8
* Index file name #9 Index file full path #10 Add document to Lucene index
*/
lucene 建立索引的不同方式的更多相关文章
- Lucene建立索引搜索入门实例
第一部分:Lucene建立索引 Lucene建立索引主要有以下两步:第一步:建立索引器第二步:添加索引文件准备在f盘建立lucene文件夹,然后 ...
- 【转】Lucene不同版本中Field的Keyword、UnIndex，导致lucene 建立索引总是报错 急！！
lucene 建立索引 总是报错 急!! http://zhidao.baidu.com/link?url=iaVs9JH4DfN6iwaWImt7VMJENWCWGGaWFGPjqhUw_jz7Fs ...
- lucene 建立索引的过程
时间 -- :: CSDN博客 原文 http://blog.csdn.net/caohaicheng/article/details/ 看lucene主页(http://lucene.apach ...
- Lucene4.9学习笔记——Lucene建立索引
基本上创建索引需要三个步骤: 1.创建索引库IndexWriter对象 2.根据文件创建文档Document 3.向索引库中写入文档内容 这其中主要涉及到了IndexWriter(索引的核心组件,用于 ...
- lucene建立索引的过程
建立索引过程 用户提交数据=>solr建立索引=>调用lucene包建立索引 官方建立索引和查询索引的例子如下: http://lucene.apache.org/core/4_10_3/ ...
- html抽取文本信息-java版（适合lucene建立索引）
import org.htmlparser.NodeFilter; import org.htmlparser.Parser; import org.htmlparser.beans.StringBe ...
- 利用Lucene将被索引文件目录中的所有文件建立索引
1.新建两个文件夹htm和index,其中htm中存放被索引的文件,index文件中存放建立的索引文件. 2.新建解析目录中所有文件的类,用来解析指定目录下的所有文件. import java.io. ...
- Lucene实现索引和查询
0引言 随着万维网的发展和大数据时代的到来,每天都有大量的数字化信息在生产.存储.传递和转化,如何从大量的信息中以一定的方式找到满足自己需求的信息,使之有序化并加以利用成为一大难题.全文检索技术是现如 ...
- 和我一起打造个简单搜索之Logstash实时同步建立索引
用过 Solr 的朋友都知道,Solr 可以直接在配置文件中配置数据库连接从而完成索引的同步创建,但是 ElasticSearch 本身并不具备这样的功能,那如何建立索引呢?方法其实很多,可以使用 J ...
随机推荐
- Java for LeetCode 146 LRU Cache 【HARD】
Design and implement a data structure for Least Recently Used (LRU) cache. It should support the fol ...
- July 12th, Week 29th Tuesday, 2016
When the traveler goes alone he gets acquainted with himself. 独自旅行可以让人更好地了解自己. With other's company, ...
- 【读书笔记】读《JavaScript设计模式》之装饰者模式
一.定义 装饰者模式可用来透明地把对象包装在具有同样接口的另一个对象之中.这样一来,你可以给一个方法添加一些行为,然后将方法调用传递给原始对象.相对于创建子类来说,使用装饰者对象是一种更灵活的选择(装 ...
- 学习 BigInteger
以下是摘抄与其他人的: JAVA之BigInteger 用Java来处理高精度问题,相信对很多ACMer来说都是一件很happy的事,简单易懂.用Java刷了一些题,感觉Java还不错,在处理高精度和 ...
- sina发现并不会去导入qq使用的
看问题需要多角度,为之不能实现也是有可能没有完善的.确实是由于短时间发布过多,还是bky好点好像有30S
- ctrl + z fg bg
[root@bass ~]# jobs [1]+ Stopped vncviewer 192.168.1.17:5904 [root@bass ~]# #ctrl + z [root@bass ~]# ...
- asp.net获取客户端IP方法(转载)
最近web获取客户端ip,看到下面这篇文章,转载过来,一起分享(转载地址:http://www.cnblogs.com/yejun/archive/2008/02/26/1082485.html) 通 ...
- javascript字典数据结构常用功能实现
必知必会啊. function Dictionary(){ var items = {}; this.has = function (key) { return key in items; }; th ...
- 浅析十三种常用的数据挖掘的技术&五个免费开源的数据挖掘软件
一.前 沿 数据挖掘就是从大量的.不完全的.有噪声的.模糊的.随机的数据中,提取隐含在其中的.人们事先不知道的但又是潜在有用的信息和知识的过程.数据挖掘的任务是从数据集中发现模式,可以发现的模式有很多 ...
- PHP GBK UTF8互转
function gbk_to_utf8($str){ return mb_convert_encoding($str, 'utf-8', 'gbk'); } function utf8_ ...