lucene-java-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Erik Hatcher <>
Subject Re: Hypenated word
Date Mon, 13 Jun 2005 12:20:50 GMT

On Jun 13, 2005, at 7:08 AM, Markus Wiederkehr wrote:
> I work on an application that has to index OCR texts of scanned books.
> Naturally there occur many words that are hyphenated across lines.
> I wonder if there is already an Analyzer or maybe a TokenFilter that
> can merge those syllables back into whole words? It looks like Erik
> Hatcher uses something like that at

Markus - you're right, I did develop something to handle hyphenated  
words for  It was sort of a hack in that I had to  
build in a static list of exceptions in how I handled this, so you'll  
likely have to use caution as well.  The LiaAnalyzer is this:

   public TokenStream tokenStream(String fieldName, Reader reader) {
     TokenFilter filter = new DashSplitterFilter(
               new HyphenatedFilter(
                 new DashDashFilter(
                   new LiaTokenizer(reader))));

     filter = new LengthFilter(3, filter);
     filter = new StopFilter(filter, stopSet);

     if (stem) {
       filter = new SnowballFilter(filter, "English");

     return filter;

And my HyphenatedFilter is this:

public class HyphenatedFilter extends TokenFilter {
   private HashMap exceptions = new HashMap();

   private static final String[] EXCEPTION_LIST = {
      "full-text", "information-retrieval", "license-code", "old- 
      "well-designed", "free-form", "file-based", "ramdirectory- 
based", "ram-based",
      "index-modifying", "read-only",
      "top-scoring", "most-recently-used", "queryparser-parsed",
      "in-order", "per-document", "lower-caser", "domain-specific",  
      "utf-encoding", "non-english", "phraseprefix-it", "all-inclusive",
      "date-range", "computation-intensive", "hits-returning", "lower- 
      "number-padding", "utf-address-book", "third-party", "plain- 
text", "google-like",
      "re-add", "english-specific", "file-handling", "already- 
created", "d-add", "d-add",
      "hits-length", "hits-doc", "hits-score", "d-get", "writer-new",  
      "writer-set", "document-new", "doc-add", "field-keyword",  
"field-unstored", "writer-add",
      "writer-optimize", "queryparser-new", "porteranalyzer-new",  
"parser-parse", "indexsearcher-new",
      "hitcollector-new", "searcher-doc", "searcher-search", "jakarta- 
lucene", "www-ibm", "java-specific",
      "non-java", "vis--vis", "medium-sized", "browser-based", "utf- 
before", "concept-based",
      "natural-language", "queue-based", "high-likelihood", "slp-or",  
"noisy-channel", "al-rasheed",
      "hands-free", "top-notch", "google-esque", "search-config",  
      "lucene-so", "lucene-tar", "lucene-jar", "lucene-demos-jar",  
"lucene-web", "lucene-webindex",
      "command-line", "lucene-version", "issue-tracking"

   protected HyphenatedFilter(TokenStream tokenStream) {

     for (int i = 0; i < EXCEPTION_LIST.length; i++) {
       exceptions.put(EXCEPTION_LIST[i], "");

   private Token savedToken;

   public Token next() throws IOException {

     if (savedToken != null) {
       Token token = savedToken;
       savedToken = null;
       return token;

     Token firstToken =;

     if (firstToken == null)
       return firstToken;

     if (firstToken.termText().endsWith("-")) {
       String firstPart;
       firstPart = firstToken.termText();

       // consume next token
       Token secondToken =;
       if (secondToken == null)
         return firstToken;

       String termText = firstPart.substring(0, firstPart.length() -  
1) + secondToken.termText();

       if (exceptions.containsKey(firstPart + secondToken.termText())) {
         savedToken = secondToken;
         return firstToken;

       return new Token(termText, firstToken.startOffset(),  
firstToken.endOffset() + secondToken.termText().length() + 1);

     return firstToken;

Not all that pretty, I'm afraid, but by all means use it if its useful.


To unsubscribe, e-mail:
For additional commands, e-mail:

View raw message