主题：使用开源组件搭建搜索引擎

//http://www.iteye.com/topic/93119


在开发中小型搜索引擎的过程中，我使用由Java开发的开源软件：jspider,htmlparser,lucence,IKAnalyzer，下面我一一道来。

lucence很著名啦，不必多说，我写的这个引擎就是在它自带的demo基础上重构的。

jspider顾名思义，是一个用Java开发的爬虫。

htmlparser是解析html页面的，因为lucene自带的html解析器不够健壮，所以用了这个。

IKAnalyzer是为lucence定做的中文分词组件，在使用中我发现效果不错。

具体的编码下次再说吧，呵呵
接着说。
用jspider从新浪和163开始爬了大约200M的材料，作为构建搜索引擎的基础，我开始了自己的搜索引擎之路。
剩下的工作就是建立索引和利用索引提供查询服务。

建立索引
我首先分析了
lucene-2.1.0\src\demo\org\apache\lucene\demo\IndexHtml.java
这个文件提供了很好的实例，我简单重构了一下就可以用了

import org.mira.lucene.analysis.MIK_CAnalyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.demo.HTMLDocument;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.TermEnum;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

import java.io.File;
import java.util.Date;
import java.util.Arrays;

/** Indexer for HTML files. */
public class IndexHTML {
private IndexHTML() {}

private static boolean deleting = false; // true during deletion pass
private static IndexReader reader; // existing index
private static IndexWriter writer; // new index being built
private static TermEnum uidIter; // document id iterator

/** Indexer for HTML files.*/
public static void main(String[] argv) {
try {
String index = "index";
boolean create = true;
File root = null;


String usage = "IndexHTML [-create] [-index <index>] <root_directory>";
/*
if (argv.length == 0) {
System.err.println("Usage: " + usage);
return;
}

for (int i = 0; i < argv.length; i++) {
if (argv[i].equals("-index")) { // parse -index option
index = argv[++i];
} else if (argv[i].equals("-create")) { // parse -create option
create = true;
} else if (i != argv.length-1) {
System.err.println("Usage: " + usage);
return;
} else
root = new File(argv[i]);
}
*/
Date start = new Date();
root = new File("c://tes1");
index = "c://index1";
if (!create) { // delete stale docs
deleting = true;
indexDocs(root, index, create);
}
writer = new IndexWriter(index, new MIK_CAnalyzer(), create);
writer.setMaxBufferedDocs(30);
writer.setMergeFactor(100);
writer.setMaxFieldLength(1000000);
indexDocs(root, index, create); // add new docs

System.out.println("Optimizing index...");

writer.optimize();
writer.close();

Date end = new Date();

System.out.print(end.getTime() - start.getTime());
System.out.println(" total milliseconds");

} catch (Exception e) {
System.out.println(" caught a " + e.getClass() +
"\n with message: " + e.getMessage());
}
}

/* Walk directory hierarchy in uid order, while keeping uid iterator from
/* existing index in sync. Mismatches indicate one of: (a) old documents to
/* be deleted; (b) unchanged documents, to be left alone; or (c) new
/* documents, to be indexed.
*/

private static void indexDocs(File file, String index, boolean create)
throws Exception {
if (!create) { // incrementally update

reader = IndexReader.open(index); // open existing index
uidIter = reader.terms(new Term("uid", "")); // init uid iterator

indexDocs(file);

if (deleting) { // delete rest of stale docs
while (uidIter.term() != null && uidIter.term().field() == "uid") {
System.out.println("deleting " +
HTMLDocument.uid2url(uidIter.term().text()));
reader.deleteDocuments(uidIter.term());
uidIter.next();
}
deleting = false;
}

uidIter.close(); // close uid iterator
reader.close(); // close existing index

} else // don't have exisiting
indexDocs(file);
}

private static void indexDocs(File file) throws Exception {
if (file.isDirectory()) { // if a directory
String[] files = file.list(); // list its files
Arrays.sort(files); // sort the files
for (int i = 0; i < files.length; i++) // recursively index them
indexDocs(new File(file, files[i]));

} else if (file.getPath().endsWith(".html") || // index .html files
file.getPath().endsWith(".htm") || // index .htm files
file.getPath().endsWith(".txt")) { // index .txt files

if (uidIter != null) {
String uid = HTMLDocument.uid(file); // construct uid for doc

while (uidIter.term() != null && uidIter.term().field() == "uid" &&
uidIter.term().text().compareTo(uid) < 0) {
if (deleting) { // delete stale docs
System.out.println("deleting " +
HTMLDocument.uid2url(uidIter.term().text()));
reader.deleteDocuments(uidIter.term());
}
uidIter.next();
}
if (uidIter.term() != null && uidIter.term().field() == "uid" &&
uidIter.term().text().compareTo(uid) == 0) {
uidIter.next(); // keep matching docs
} else if (!deleting) { // add new docs
Document doc = HTMLDocument.Document(file);
System.out.println("adding " + doc.get("path"));
writer.addDocument(doc);
}
} else { // creating a new index
Document doc = HTMLDocument.Document(file);
System.out.println("adding " + doc.get("path"));
writer.addDocument(doc); // add docs unconditionally
}
}
}
}

从源代码可以看到，中文分词已经加进去了，
而索引HTML的关键工作是由 HTMLDocument这个类完成的，需要对它进行重构


这个时候，htmlparser闪亮登场
请说jspider只能是对HTML的url进行检索，
是嘛，
不知道Heritrix这个怎么样呢，对比起来！！