解决数字和英文字母结合检索出现高亮重复问题

问题如下：

数字与英文结合在一起检索，出现高亮重复问题

如：检索“220”则

关于同意220kV佛山变电站#1、#2主变报废的批复 .txt 检索“220kv”则 关于同意220220kV佛山变电站#1、#2主变报废的批复 .txt 高亮采用的是索引时记录Term的位置，高亮处理采用TermPositionVector termFreqVector = (TermPositionVector)ireader.getTermFreqVector(doc, fieldname);方式，其中主要代码如下： QueryParser queryParser = new QueryParser(Version.LUCENE_30,fieldname,queryAnalyzer);
Query query = queryParser.parse(keyWordLc);
Highlighter highlighter = new Highlighter(new SimpleHTMLFormatter(
"<font color=/"red/">", "</font>"), new QueryScorer(
query));
highlighter.setTextFragmenter(new SimpleFragmenter(50));

TermPositionVector termFreqVector = (TermPositionVector)ireader.getTermFreqVector(doc, fieldname);
/**
* 注意这里最好设为true，虽然会影响性能，但是避免出现：
* 文档题名为：索引测试新建文档1.txt
* 查看tokens结果：[(1,8,9), (1.txt,8,13), (文档,6,8), (新建,4,6), (测试,2,4), (索引,0,2), (txt,10,13)]
* 这样高亮显示的时候<font color="red">索引测试新建文档</font>1.txt
* 因为高亮显示的方法里是按位置信息，当当前匹配的term小于前面最大的最后位置时才去高亮，
* 不然则在最后获取到最小匹配的term的首位置到最后匹配的term的末位置的字符串全部高亮起来了。
*/
TokenStream tokenStream = TokenSources.getTokenStream(termFreqVector,true);

String content = hitDoc.get(fieldname);
String result = highlighter.getBestFragments(tokenStream, content, 5,"..."); 通过调试跟踪，paoding分词器对“220kv”会分词为“220 kv 220kv”，而通过Lucene提供的lucene-highlighter-3.0.2.jar、lucene-memory-3.0.2.jar
解决方法是修改lucene-highlighter-3.0.2.jar中Highlighter类，代码如下：

public final TextFragment[] getBestTextFragments(
TokenStream tokenStream,
String text,
boolean mergeContiguousFragments,
int maxNumFragments)
throws IOException, InvalidTokenOffsetsException
{
ArrayList<TextFragment> docFrags = new ArrayList<TextFragment>();
StringBuilder newText=new StringBuilder();

TermAttribute termAtt = tokenStream.addAttribute(TermAttribute.class);
OffsetAttribute offsetAtt = tokenStream.addAttribute(OffsetAttribute.class);
tokenStream.addAttribute(PositionIncrementAttribute.class);
tokenStream.reset();

TextFragment currentFrag = new TextFragment(newText,newText.length(), docFrags.size());
TokenStream newStream = fragmentScorer.init(tokenStream);
if(newStream != null) {
tokenStream = newStream;
}
fragmentScorer.startFragment(currentFrag);
docFrags.add(currentFrag); FragmentQueue fragQueue = new FragmentQueue(maxNumFragments); try
{ String tokenText;
int startOffset;
int endOffset;
int lastEndOffset = 0;
int lastStartOffset = 0; //用来记录当前所取的字符串起点位置 textFragmenter.start(text, tokenStream); TokenGroup tokenGroup=new TokenGroup(tokenStream); for (boolean next = tokenStream.incrementToken(); next && (offsetAtt.startOffset()< maxDocCharsToAnalyze);
next = tokenStream.incrementToken())
{
if( (offsetAtt.endOffset()>text.length())
||
(offsetAtt.startOffset()>text.length())
)
{
throw new InvalidTokenOffsetsException("Token "+ termAtt.term()
+" exceeds length of provided text sized "+text.length());
}
if((tokenGroup.numTokens>0)&&(tokenGroup.isDistinct()))
{
//the current token is distinct from previous tokens -
// markup the cached token group info
startOffset = tokenGroup.matchStartOffset;
endOffset = tokenGroup.matchEndOffset;

//用下面两行替代代码tokenText = text.substring(startOffset, endOffset);
//解决“数字+英文或英文+数字”格式关键词出现高亮重复问题，如：检索“220KV”会高亮“220220KV”
lastStartOffset = Math.max(startOffset, lastEndOffset);
tokenText = text.substring(lastStartOffset, endOffset);

String markedUpText=formatter.highlightTerm(encoder.encodeText(tokenText), tokenGroup);
//store any whitespace etc from between this and last group
if (startOffset > lastEndOffset)
newText.append(encoder.encodeText(text.substring(lastEndOffset, startOffset)));
newText.append(markedUpText);
lastEndOffset=Math.max(endOffset, lastEndOffset);

tokenGroup.clear(); //check if current token marks the start of a new fragment
if(textFragmenter.isNewFragment())
{
currentFrag.setScore(fragmentScorer.getFragmentScore());
//record stats for a new fragment
currentFrag.textEndPos = newText.length();
currentFrag =new TextFragment(newText, newText.length(), docFrags.size());
fragmentScorer.startFragment(currentFrag);
docFrags.add(currentFrag);
}
} tokenGroup.addToken(fragmentScorer.getTokenScore());// if(lastEndOffset>maxDocBytesToAnalyze)
// {
// break;
// }
}
currentFrag.setScore(fragmentScorer.getFragmentScore()); if(tokenGroup.numTokens>0)
{
//flush the accumulated text (same code as in above loop)
startOffset = tokenGroup.matchStartOffset;
endOffset = tokenGroup.matchEndOffset;
tokenText = text.substring(startOffset, endOffset);
String markedUpText=formatter.highlightTerm(encoder.encodeText(tokenText), tokenGroup);
//store any whitespace etc from between this and last group
if (startOffset > lastEndOffset)
newText.append(encoder.encodeText(text.substring(lastEndOffset, startOffset)));
newText.append(markedUpText);
lastEndOffset=Math.max(lastEndOffset,endOffset);
} //Test what remains of the original text beyond the point where we stopped analyzing
if (
// if there is text beyond the last token considered..
(lastEndOffset < text.length())
&&
// and that text is not too large...
(text.length()<= maxDocCharsToAnalyze)
)
{
//append it to the last fragment
newText.append(encoder.encodeText(text.substring(lastEndOffset)));
} currentFrag.textEndPos = newText.length(); //sort the most relevant sections of the text
for (Iterator<TextFragment> i = docFrags.iterator(); i.hasNext();)
{
currentFrag = i.next(); //If you are running with a version of Lucene before 11th Sept 03
// you do not have PriorityQueue.insert() - so uncomment the code below
/*
if (currentFrag.getScore() >= minScore)
{
fragQueue.put(currentFrag);
if (fragQueue.size() > maxNumFragments)
{ // if hit queue overfull
fragQueue.pop(); // remove lowest in hit queue
minScore = ((TextFragment) fragQueue.top()).getScore(); // reset minScore
}
}
*/
//The above code caused a problem as a result of Christoph Goller's 11th Sept 03
//fix to PriorityQueue. The correct method to use here is the new "insert" method
// USE ABOVE CODE IF THIS DOES NOT COMPILE!
fragQueue.insertWithOverflow(currentFrag);
} //return the most relevant fragments
TextFragment frag[] = new TextFragment[fragQueue.size()];
for (int i = frag.length - 1; i >= 0; i--)
{
frag[i] = fragQueue.pop();
} //merge any contiguous fragments to improve readability
if(mergeContiguousFragments)
{
mergeContiguousFragments(frag);
ArrayList<TextFragment> fragTexts = new ArrayList<TextFragment>();
for (int i = 0; i < frag.length; i++)
{
if ((frag[i] != null) && (frag[i].getScore() > 0))
{
fragTexts.add(frag[i]);
}
}
frag= fragTexts.toArray(new TextFragment[0]);
} return frag; }
finally
{
if (tokenStream != null)
{
try
{
tokenStream.close();
}
catch (Exception e)
{
}
}
}
}