merged

README.md

@@ -3,10 +3,10 @@ Vietnamese Analysis Plugin for Elasticsearch
 
 Vietnamese Analysis plugin integrates Vietnamese language analysis into Elasticsearch.
 
-In order to install the plugin, simply run:
+In order to install the plugin, choose a version in [releases](https://github.com/duydo/elasticsearch-analysis-vietnamese/releases) page then run:
 
 ```sh
-bin/plugin --url https://dl.dropboxusercontent.com/u/1598491/elasticsearch-analysis-vietnamese-0.2.2.zip --install analysis-vietnamese
+bin/plugin install link-to-binary-version
 ```
 
 Or to build from source, you need to build it with Maven:
@@ -20,7 +20,13 @@ bin/plugin install file:target/releases/elasticsearch-analysis-vietnamese-0.2.2.
 
 |Vietnamese Analysis Plugin|Elasticsearch|
 |---|---|
-| master|2.2.0|
+| master|2.3.5|
+| 2.3.5|2.3.5|
+| 2.3.4|2.3.4|
+| 2.3.3|2.3.3|
+| 2.3.2|2.3.2|
+| 2.3.1|2.3.1|
+| 2.3.0|2.3.0|
 | 0.2.2|2.2.0|
 | 0.2.1.1|2.1.1|
 | 0.2.1|2.1.0|

pom.xml

@@ -3,7 +3,7 @@
     <modelVersion>4.0.0</modelVersion>
     <groupId>org.elasticsearch</groupId>
     <artifactId>elasticsearch-analysis-vietnamese</artifactId>
-    <version>0.2.3.5</version>
+    <version>2.3.5</version>
     <packaging>jar</packaging>
     <name>elasticsearch-analysis-vietnamese</name>
     <url>https://github.com/duydo/elasticsearch-analysis-vietnamese/</url>

src/main/java/org/apache/lucene/analysis/vi/VietnameseTokenizer.java

@@ -101,15 +101,15 @@ public final boolean incrementToken() throws IOException {
         while (taggedWords.hasNext()) {
             final TaggedWord word = taggedWords.next();
             if (accept(word)) {
-                final char[] chars = word.getText().trim().toCharArray();
-                termAtt.copyBuffer(chars, 0, chars.length);
-                typeAtt.setType(word.getRule().getName());
                 posIncrAtt.setPositionIncrement(skippedPositions + 1);
-                offsetAtt.setOffset(correctOffset(offset), offset = correctOffset(offset + termAtt.length()));
+                typeAtt.setType(word.getRule().getName());
+                final int length = word.getText().length();
+                termAtt.copyBuffer(word.getText().toCharArray(), 0, length);
+                offsetAtt.setOffset(correctOffset(offset), offset = correctOffset(offset + length));
                 offset++;
                 return true;
             }
-            ++skippedPositions;
+            skippedPositions++;
         }
         return false;
     }
@@ -128,7 +128,8 @@ private final boolean accept(TaggedWord word) {
     @Override
     public final void end() throws IOException {
         super.end();
-        offsetAtt.setOffset(offset, offset);
+        final int finalOffset = correctOffset(offset);
+        offsetAtt.setOffset(finalOffset, finalOffset);
         posIncrAtt.setPositionIncrement(posIncrAtt.getPositionIncrement() + skippedPositions);
     }