我已经更新了Lucene in Action第2版书中的Indexer和Searcher示例。
Indexer工作正常，但Searcher不起作用。
我已经索引了一堆txt文件（Indexer过滤器txt文件）。
当我使用单词I搜索Searcher类时，确保txt文件包含（可以用grep验证），它找到0匹配文档。
代码一定有问题。
以下是文件 的pom.xml
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>com.learning</groupId>
<artifactId>lucenebook</artifactId>
<version>1.0-SNAPSHOT</version>
<dependencies>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-core</artifactId>
<version>6.6.0</version>
</dependency>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-queryparser</artifactId>
<version>6.6.0</version>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<configuration>
<source>1.8</source>
<target>1.8</target>
</configuration>
</plugin>
</plugins>
</build>
</project>
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.document.FieldType;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.Directory;
import java.io.File;
import java.io.FileFilter;
import java.io.IOException;
import java.io.FileReader;
import java.nio.file.Paths;
// 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 {
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
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(Paths.get(indexDir));
writer = new IndexWriter(dir, new IndexWriterConfig()); //3
}
public void close() throws IOException {
writer.close(); //4
}
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
}
private static class TextFilesFilter implements FileFilter {
public boolean accept(File path) {
return path.getName().toLowerCase() //6
.endsWith(".txt"); //6
}
}
protected Document getDocument(File f) throws Exception {
Document doc = new Document();
doc.add(new Field("contents", new FileReader(f), new FieldType())); //7
FieldType notAnalyzed = new FieldType();
notAnalyzed.setTokenized(false);
notAnalyzed.setStored(true);
doc.add(new Field("filename", f.getName(), notAnalyzed //8
));//8
doc.add(new Field("fullpath", f.getCanonicalPath(), //9
notAnalyzed));//9
return doc;
}
private void indexFile(File f) throws Exception {
System.out.println("Indexing " + f.getCanonicalPath());
Document doc = getDocument(f);
writer.addDocument(doc); //10
}
}
/*
#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
*/
和Searcher：
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.document.Document;
import org.apache.lucene.index.DirectoryReader;
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.FSDirectory;
import org.apache.lucene.store.Directory;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import java.io.IOException;
import java.nio.file.Paths;
// From chapter 1
/**
* This code was originally written for
* Erik's Lucene intro java.net article
*/
public class Searcher {
public static void main(String[] args) throws IllegalArgumentException,
IOException, ParseException {
if (args.length != 2) {
throw new IllegalArgumentException("Usage: java " + Searcher.class.getName()
+ " <index dir> <query>");
}
String indexDir = args[0]; //1
String q = args[1]; //2
search(indexDir, q);
}
public static void search(String indexDir, String q)
throws IOException, ParseException {
Directory dir = FSDirectory.open(Paths.get(indexDir)); //3
DirectoryReader directoryReader = DirectoryReader.open(dir);
IndexSearcher is = new IndexSearcher(directoryReader); //3
QueryParser parser = new QueryParser( // 4
"f", //4
new StandardAnalyzer( )); //4
Query query = parser.parse(q); //4
long start = System.currentTimeMillis();
TopDocs hits = is.search(query, 10); //5
long end = System.currentTimeMillis();
System.err.println("Found " + hits.totalHits + //6
" document(s) (in " + (end - start) + // 6
" milliseconds) that matched query '" + // 6
q + "':"); // 6
for(ScoreDoc scoreDoc : hits.scoreDocs) {
Document doc = is.doc(scoreDoc.doc); //7
System.out.println(doc.get("fullpath")); //8
}
//9
}
}
/*
#1 Parse provided index directory
#2 Parse provided query string
#3 Open index
#4 Parse query
#5 Search index
#6 Write search stats
#7 Retrieve matching document
#8 Display filename
#9 Close IndexSearcher
*/
答案 0 :(得分：2)
您最大的问题是您如何处理例外。如果你没有把它们扔掉，那么应该看到的例外：
线程中的异常＆＃34; main＆＃34; java.lang.IllegalArgumentException：有一个既没有索引也没有存储的字段是没有意义的 在org.apache.lucene.document.Field。（Field.java:249）
如果您想弄清楚您的计划有什么问题，请不要抛弃所有例外情况！这些是帮助您找到并处理问题的工具！
该异常告诉您的是，您的某个字段（＆＃34; content＆＃34;，具体而言）既未编入索引也未存储。您永远不应该使用FieldType所有默认值。您需要使用该字段的相应值进行设置。在这种情况下，仅使用TextField可能是有意义的。
PS - Lucene in Action第二版。是7岁，它的代码是Lucene 3.0。它已经过时了，你可能会更好地尝试the current lucene demo。
答案 1 :(得分：0)
问题在于搜索者没有使用索引的字段，它被命名为“内容”，它使用的是“f”并且它没有匹配。 以下是更正的代码，Searcher仅将“f”更改为“contents”，Indexer使用TextField并更好地捕获异常（对于Indexer的更改由femtoRgon提交的答案建议）。 请注意，最好使用当前的Lucene演示，正如femtoRgon所建议的那样，实际上将它与代码进行比较是解决方案的路径。 更正了Indexer.java：
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.document.FieldType;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.Directory;
import java.io.File;
import java.io.FileFilter;
import java.io.IOException;
import java.io.FileReader;
import java.nio.file.Paths;
// 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) {
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
Indexer indexer = null;
long start = System.currentTimeMillis();
int numIndexed = 0;
try {
indexer = new Indexer(indexDir);
numIndexed = indexer.index(dataDir, new TextFilesFilter());
} catch(Exception e) {
e.printStackTrace();
} finally {
if (indexer != null)
try {
indexer.close();
} catch (IOException e) {
// ignored
}
}
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(Paths.get(indexDir));
writer = new IndexWriter(dir, new IndexWriterConfig()); //3
}
public void close() throws IOException {
writer.close(); //4
}
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
}
private static class TextFilesFilter implements FileFilter {
public boolean accept(File path) {
return path.getName().toLowerCase() //6
.endsWith(".txt"); //6
}
}
protected Document getDocument(File f) throws Exception {
Document doc = new Document();
doc.add(new TextField("contents", new FileReader(f))); //7
FieldType notAnalyzed = new FieldType();
notAnalyzed.setTokenized(false);
notAnalyzed.setStored(true);
doc.add(new Field("filename", f.getName(), notAnalyzed //8
));//8
doc.add(new Field("fullpath", f.getCanonicalPath(), //9
notAnalyzed));//9
return doc;
}
private void indexFile(File f) throws Exception {
System.out.println("Indexing " + f.getCanonicalPath());
Document doc = getDocument(f);
writer.addDocument(doc); //10
}
}
/*
#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
*/
和Searcher.java：
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.document.Document;
import org.apache.lucene.index.DirectoryReader;
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.FSDirectory;
import org.apache.lucene.store.Directory;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import java.io.IOException;
import java.nio.file.Paths;
// From chapter 1
/**
* This code was originally written for
* Erik's Lucene intro java.net article
*/
public class Searcher {
public static void main(String[] args) throws IllegalArgumentException,
IOException, ParseException {
if (args.length != 2) {
throw new IllegalArgumentException("Usage: java " + Searcher.class.getName()
+ " <index dir> <query>");
}
String indexDir = args[0]; //1
String q = args[1]; //2
search(indexDir, q);
}
public static void search(String indexDir, String q)
throws IOException, ParseException {
Directory dir = FSDirectory.open(Paths.get(indexDir)); //3
DirectoryReader directoryReader = DirectoryReader.open(dir);
IndexSearcher is = new IndexSearcher(directoryReader); //3
QueryParser parser = new QueryParser( // 4
"contents", //4
new StandardAnalyzer( )); //4
Query query = parser.parse(q); //4
long start = System.currentTimeMillis();
TopDocs hits = is.search(query, 10); //5
long end = System.currentTimeMillis();
System.err.println("Found " + hits.totalHits + //6
" document(s) (in " + (end - start) + // 6
" milliseconds) that matched query '" + // 6
q + "':"); // 6
for(ScoreDoc scoreDoc : hits.scoreDocs) {
Document doc = is.doc(scoreDoc.doc); //7
System.out.println(doc.get("fullpath")); //8
}
//9
}
}
/*
#1 Parse provided index directory
#2 Parse provided query string
#3 Open index
#4 Parse query
#5 Search index
#6 Write search stats
#7 Retrieve matching document
#8 Display filename
#9 Close IndexSearcher
*/