我创建了一个自定义的标记生成器，它被admin / analysis.jsp与System.out的日志检查似乎做工精细。 然而，当我进行在使用该自定义标记者现场询问，我看到自定义的标记生成器仅Solr的调用第一个查询字符串（由System.out的日志查询）。 你能不能帮我点什么我错了？ 这是我的代码：
package com.fosp.searchengine;
import java.io.Reader;
import org.apache.lucene.analysis.WhitespaceTokenizer;
import org.apache.solr.analysis.WhitespaceTokenizerFactory;
public class JvnTextProTokenizerFactory extends WhitespaceTokenizerFactory{
@Override
public WhitespaceTokenizer create(Reader input) {
System.out.println("WhitespaceTokenizer create(Reader input)");
Reader processedStringReader = new ProcessedStringReader(input);
return new WhitespaceTokenizer(processedStringReader);
}
}
package com.fosp.searchengine;
import java.io.IOException;
import java.io.Reader;
public class ProcessedStringReader extends java.io.Reader {
private static final int BUFFER_SIZE = 1024 * 8;
private static TextProcess m_textProcess = null;
private char[] m_inputData = null;
private int m_offset = 0;
private int m_length = 0;
public ProcessedStringReader(Reader input){
char[] arr = new char[BUFFER_SIZE];
StringBuffer buf = new StringBuffer();
int numChars;
try {
while ((numChars = input.read(arr, 0, arr.length)) > 0) {
buf.append(arr, 0, numChars);
}
} catch (IOException e) {
e.printStackTrace();
}
if(m_textProcess == null){
try {
m_textProcess = new TextProcess();
} catch (IOException e) {
e.printStackTrace();
}
}
m_inputData = m_textProcess.processText(buf.toString()).toCharArray();
m_offset = 0;
m_length = m_inputData.length;
}
@Override
public int read(char[] cbuf, int off, int len) throws IOException {
int charNumber = 0;
for(int i = m_offset + off;i<m_length && charNumber< len; i++){
cbuf[charNumber] = m_inputData[i];
m_offset ++;
charNumber++;
}
if(charNumber == 0){
return -1;
}
return charNumber;
}
@Override
public void close() throws IOException {
m_inputData = null;
m_offset = 0;
m_length = 0;
}
}
Schema.xml的
<fieldType name="text_jvnTextPro" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="com.fosp.searchengine.JvnTextProTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="com.fosp.searchengine.JvnTextProTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
