Return-Path: 
 <commits-return-35284-apmail-lucene-commits-archive=www.apache.org@lucene.apache.org>
X-Original-To: apmail-lucene-commits-archive@www.apache.org
Delivered-To: apmail-lucene-commits-archive@www.apache.org
Received: from mail.apache.org (hermes.apache.org [140.211.11.3])
	by minotaur.apache.org (Postfix) with SMTP id E574D10ECC
	for <apmail-lucene-commits-archive@www.apache.org>;
 Sun, 20 Oct 2013 08:22:04 +0000 (UTC)
Received: (qmail 60897 invoked by uid 500); 20 Oct 2013 08:22:04 -0000
Mailing-List: contact commits-help@lucene.apache.org; run by ezmlm
Precedence: bulk
List-Help: <mailto:commits-help@lucene.apache.org>
List-Unsubscribe: <mailto:commits-unsubscribe@lucene.apache.org>
List-Post: <mailto:commits@lucene.apache.org>
List-Id: <commits.lucene.apache.org>
Reply-To: dev@lucene.apache.org
Delivered-To: mailing list commits@lucene.apache.org
Received: (qmail 60890 invoked by uid 99); 20 Oct 2013 08:22:03 -0000
Received: from athena.apache.org (HELO athena.apache.org) (140.211.11.136)
    by apache.org (qpsmtpd/0.29) with ESMTP; Sun, 20 Oct 2013 08:22:03 +0000
X-ASF-Spam-Status: No, hits=-2000.0 required=5.0
	tests=ALL_TRUSTED
X-Spam-Check-By: apache.org
Received: from [140.211.11.4] (HELO eris.apache.org) (140.211.11.4)
    by apache.org (qpsmtpd/0.29) with ESMTP; Sun, 20 Oct 2013 08:22:02 +0000
Received: from eris.apache.org (localhost [127.0.0.1])
	by eris.apache.org (Postfix) with ESMTP id 1B0EA2388980;
	Sun, 20 Oct 2013 08:21:42 +0000 (UTC)
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Subject: svn commit: r1533858 - in
 /lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/java/org/apache/lucene/analysis/ko:
 IndexWord.java KoreanFilter.java Token.java
Date: Sun, 20 Oct 2013 08:21:42 -0000
To: commits@lucene.apache.org
From: uschindler@apache.org
X-Mailer: svnmailer-1.0.9
Message-Id: <20131020082142.1B0EA2388980@eris.apache.org>
X-Virus-Checked: Checked by ClamAV on apache.org

Author: uschindler
Date: Sun Oct 20 08:21:41 2013
New Revision: 1533858

URL: http://svn.apache.org/r1533858
Log:
LUCENE-4956: Rename IndexWord to Token like in Kuromoji!

Added:
    lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/java/org/apache/lucene/analysis/ko/Token.java
      - copied, changed from r1533856, lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/java/org/apache/lucene/analysis/ko/IndexWord.java
Removed:
    lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/java/org/apache/lucene/analysis/ko/IndexWord.java
Modified:
    lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/java/org/apache/lucene/analysis/ko/KoreanFilter.java

Modified: lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/java/org/apache/lucene/analysis/ko/KoreanFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/java/org/apache/lucene/analysis/ko/KoreanFilter.java?rev=1533858&r1=1533857&r2=1533858&view=diff
==============================================================================
--- lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/java/org/apache/lucene/analysis/ko/KoreanFilter.java (original)
+++ lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/java/org/apache/lucene/analysis/ko/KoreanFilter.java Sun Oct 20 08:21:41 2013
@@ -44,7 +44,7 @@ import org.apache.lucene.analysis.tokena
 
 public final class KoreanFilter extends TokenFilter {
 
-  private final LinkedList<IndexWord> morphQueue = new LinkedList<IndexWord>();;
+  private final LinkedList<Token> morphQueue = new LinkedList<Token>();;
   private final MorphAnalyzer morph = new MorphAnalyzer();
   private final WordSpaceAnalyzer wsAnal = new WordSpaceAnalyzer();
   private final CompoundNounAnalyzer cnAnalyzer = new CompoundNounAnalyzer();
@@ -125,7 +125,7 @@ public final class KoreanFilter extends 
   
 
   private void setAttributesFromQueue(boolean isFirst) {
-    final IndexWord iw = morphQueue.removeFirst();
+    final Token iw = morphQueue.removeFirst();
     final String word = iw.getWord();
     final int ofs = iw.getOffset();
     
@@ -155,8 +155,8 @@ public final class KoreanFilter extends 
     List<AnalysisOutput> outputs = morph.analyze(input);
     if(outputs.size()==0) return;
     
-    Map<String,IndexWord> map = new LinkedHashMap<String,IndexWord>();
-    if(hasOrigin) map.put("0:"+input, new IndexWord(input,0));
+    Map<String,Token> map = new LinkedHashMap<String,Token>();
+    if(hasOrigin) map.put("0:"+input, new Token(input,0));
 
     if(outputs.get(0).getScore()>=AnalysisOutput.SCORE_COMPOUNDS) {
       extractKeyword(outputs,offsetAtt.startOffset(), map, 0);      
@@ -170,7 +170,7 @@ public final class KoreanFilter extends 
         if(list.size()>1 && wsAnal.getOutputScore(list)>AnalysisOutput.SCORE_ANALYSIS) {
           int offset = 0;
           for(AnalysisOutput o : list) {
-            if(hasOrigin) map.put(o.getSource(), new IndexWord(o.getSource(),offsetAtt.startOffset()+offset,1));        
+            if(hasOrigin) map.put(o.getSource(), new Token(o.getSource(),offsetAtt.startOffset()+offset,1));        
             results.addAll(morph.analyze(o.getSource()));
             offset += o.getSource().length();
           }       
@@ -194,7 +194,7 @@ public final class KoreanFilter extends 
   
   }
   
-  private void extractKeyword(List<AnalysisOutput> outputs, int startoffset, Map<String,IndexWord> map, int position) {
+  private void extractKeyword(List<AnalysisOutput> outputs, int startoffset, Map<String,Token> map, int position) {
 
     int maxDecompounds = 0;
     int maxStem = 0;
@@ -204,7 +204,7 @@ public final class KoreanFilter extends 
       if(output.getPos()==PatternConstants.POS_VERB) continue; // extract keywords from only noun
       if(!originCNoun&&output.getCNounList().size()>0) continue; // except compound nound
       int inc = map.size()>0 ? 0 : 1;
-      map.put(position+":"+output.getStem(), new IndexWord(output.getStem(),startoffset,inc));
+      map.put(position+":"+output.getStem(), new Token(output.getStem(),startoffset,inc));
         
       if(output.getStem().length()>maxStem) maxStem = output.getStem().length();
       if(output.getCNounList().size()>maxDecompounds) maxDecompounds = output.getCNounList().size();
@@ -226,7 +226,7 @@ public final class KoreanFilter extends 
           int cStartoffset = getStartOffset(output, i) + startoffset;
           int inc = i==0 ? 0 : 1;
           map.put((cPosition)+":"+cEntry.getWord(), 
-              new IndexWord(cEntry.getWord(),cStartoffset,inc));
+              new Token(cEntry.getWord(),cStartoffset,inc));
           
           if(bigrammable&&!cEntry.isExist()) 
             cPosition = addBiagramToMap(cEntry.getWord(), cStartoffset, map, cPosition);
@@ -245,7 +245,7 @@ public final class KoreanFilter extends 
     }    
   }
   
-  private int addBiagramToMap(String input, int startoffset, Map<String, IndexWord> map, int position) {
+  private int addBiagramToMap(String input, int startoffset, Map<String, Token> map, int position) {
     int offset = 0;
     int strlen = input.length();
     if(strlen<2) return position;
@@ -256,12 +256,12 @@ public final class KoreanFilter extends 
       
       if(isAlphaNumChar(input.charAt(offset))) {
         String text = findAlphaNumeric(input.substring(offset));
-        map.put(position+":"+text,  new IndexWord(text,startoffset+offset,inc));
+        map.put(position+":"+text,  new Token(text,startoffset+offset,inc));
         offset += text.length();
       } else {
         String text = input.substring(offset,
             offset+2>strlen?strlen:offset+2);
-        map.put(position+":"+text,  new IndexWord(text,startoffset+offset,inc));
+        map.put(position+":"+text,  new Token(text,startoffset+offset,inc));
         offset++;
       }
       
@@ -303,7 +303,7 @@ public final class KoreanFilter extends 
    */
   private void analysisChinese(String term) {  
     
-    morphQueue.add(new IndexWord(term,0));
+    morphQueue.add(new Token(term,0));
     if(term.length()<2) return; // 1글자 한자는 색인어로 한글을 추출하지 않는다.
     
     List<StringBuilder> candiList = new ArrayList<StringBuilder>();
@@ -350,7 +350,7 @@ public final class KoreanFilter extends 
     if(candiList.size()<maxCandidate) maxCandidate=candiList.size();
     
     for(int i=0;i<maxCandidate;i++) {
-      morphQueue.add(new IndexWord(candiList.get(i).toString(),0));
+      morphQueue.add(new Token(candiList.get(i).toString(),0));
     }
     
     Map<String, String> cnounMap = new HashMap<String, String>();
@@ -368,13 +368,13 @@ public final class KoreanFilter extends 
         // 한글과 매치되는 한자를 짤라서 큐에 저장한다.           
         // nocommit: this is avoiding AIOOBE, original code:
         // morphQueue.add(new IndexWord(term.substring(offset,pos),offset));
-        morphQueue.add(new IndexWord(term.substring(offset,Math.min(pos, term.length())),offset));
+        morphQueue.add(new Token(term.substring(offset,Math.min(pos, term.length())),offset));
         cnounMap.put(entry.getWord(), entry.getWord());
          
         if(entry.getWord().length()<2) continue; //  한글은 2글자 이상만 저장한다.
          
         // 분리된 한글을 큐에 저장한다.  
-        morphQueue.add(new IndexWord(entry.getWord(),offset));
+        morphQueue.add(new Token(entry.getWord(),offset));
          
         offset = pos;
       }       
@@ -402,7 +402,7 @@ public final class KoreanFilter extends 
         buffer[bufferLength-2] == '\'' &&
         (buffer[bufferLength-1] == 's' || buffer[bufferLength-1] == 'S')) {
       // Strip last 2 characters off
-      morphQueue.add(new IndexWord(term.substring(0,bufferLength - 2),0));
+      morphQueue.add(new Token(term.substring(0,bufferLength - 2),0));
     } else if (type == ACRONYM_TYPE) {      // remove dots
       int upto = 0;
       for(int i=0;i<bufferLength;i++) {
@@ -410,9 +410,9 @@ public final class KoreanFilter extends 
         if (c != '.')
           buffer[upto++] = c;
       }
-      morphQueue.add(new IndexWord(term.substring(0,upto),0));
+      morphQueue.add(new Token(term.substring(0,upto),0));
     } else {
-      morphQueue.add(new IndexWord(term,0));
+      morphQueue.add(new Token(term,0));
     }
   }
   

Copied: lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/java/org/apache/lucene/analysis/ko/Token.java (from r1533856, lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/java/org/apache/lucene/analysis/ko/IndexWord.java)
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/java/org/apache/lucene/analysis/ko/Token.java?p2=lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/java/org/apache/lucene/analysis/ko/Token.java&p1=lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/java/org/apache/lucene/analysis/ko/IndexWord.java&r1=1533856&r2=1533858&rev=1533858&view=diff
==============================================================================
--- lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/java/org/apache/lucene/analysis/ko/IndexWord.java (original)
+++ lucene/dev/branches/lucene4956/lucene/analysis/arirang/src/java/org/apache/lucene/analysis/ko/Token.java Sun Oct 20 08:21:41 2013
@@ -20,7 +20,7 @@ package org.apache.lucene.analysis.ko;
 /**
  * Index word extracted from a phrase.
  */
-public class IndexWord {
+public class Token {
 
   // the word to be indexed
   private String word;
@@ -34,21 +34,21 @@ public class IndexWord {
   // the derived korean sound text has the <KOREAN> type
   private String type;
 
-  public IndexWord() {
+  public Token() {
     
   }
   
-  public IndexWord(String word, int pos) {
+  public Token(String word, int pos) {
     this.word = word;
     this.offset = pos;
   }
   
-  public IndexWord(String word, int pos, int inc) {
+  public Token(String word, int pos, int inc) {
     this(word, pos);
     this.increment = inc;
   }
   
-  public IndexWord(String word, int pos, int inc, String t) {
+  public Token(String word, int pos, int inc, String t) {
     this(word, pos, inc);
     this.type = t;
   }