Merge pull request #1 from yahoojapan/mnagaya/refactor

Trivial changes

README.md

@@ -54,11 +54,11 @@ You can configure package by <config name="language.lib.kuromoji.kuromoji"&gt
 |parameter|type|default|description|
 |:--------|:---|:------|:----------|
 |mode|string|search|mode of Kuromoji (normal OR search OR extended)|
-|kanji.length_threshold|int|2|TODO|
-|kanji.penalty|int|3000|TODO|
-|other.length_threshold|int|7|TODO|
-|other.penalty|int|1700|TODO|
-|nakaguro_split|bool|false|TODO|
+|kanji.length_threshold|int|2|threshold of the length of kanji tokens which is penalized while running the Viterbi search (expert feature).|
+|kanji.penalty|int|3000|additional cost for kanji tokens which is longer than the pre-defined length threshold (expert feature).|
+|other.length_threshold|int|7|threshold of the length of non-kanji tokens which is penalized while running the Viterbi search (expert feature).|
+|other.penalty|int|1700|additional cost for non-kanji tokens which is longer than the pre-defined length threshold (expert feature).|
+|nakaguro_split|bool|false|whether splits unknown words on the middle dot character (U+30FB KATAKANA MIDDLE DOT)|
 |user_dict|string|-|path of user dictionary|
 |tokenlist_name|string|default|target specialtokens name|
 |all_language|bool|false|apply kuromoji tokenizer to all language or only Japanese|

pom.xml

@@ -14,7 +14,14 @@
   <packaging>container-plugin</packaging>
 
   <name>kuromoji-linguistics</name>
-  <url>http://maven.apache.org</url>
+  <url>https://github.com/yahoojapan/vespa-kuromoji-linguistics</url>
+
+  <licenses>
+    <license>
+      <name>The Apache License, Version 2.0</name>
+      <url>http://www.apache.org/licenses/LICENSE-2.0.txt</url>
+    </license>
+  </licenses>
 
   <properties>
     <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
@@ -55,12 +62,6 @@
       <version>${vespa.version}</version>
       <scope>provided</scope>
     </dependency>
-    <dependency>
-      <groupId>com.yahoo.vespa</groupId>
-      <artifactId>container-di</artifactId>
-      <version>${vespa.version}</version>
-      <scope>provided</scope>
-    </dependency>
     <dependency>
       <groupId>com.yahoo.vespa</groupId>
       <artifactId>linguistics</artifactId>

src/main/java/jp/co/yahoo/vespa/language/lib/kuromoji/KuromojiLinguistics.java

@@ -37,11 +37,11 @@
  * <table>
  * <tr><th>parameter</th><th>default</th><th>description</th></tr>
  * <tr><td>mode</td><td>search</td><td>mode of Kuromoji (normal|search|extended)</td></tr>
- * <tr><td>kanji.length_threshold</td><td>2</td><td>TODO</td></tr>
- * <tr><td>kanji.penalty</td><td>3000</td><td>TODO</td></tr>
- * <tr><td>other.length_threshold</td><td>7</td><td>TODO</td></tr>
- * <tr><td>other.penalty</td><td>1700</td><td>TODO</td></tr>
- * <tr><td>nakaguro_split</td><td>false</td><td>TODO</td></tr>
+ * <tr><td>kanji.length_threshold</td><td>2</td><td>threshold of the length of kanji tokens which is penalized while running the Viterbi search (expert feature).</td></tr>
+ * <tr><td>kanji.penalty</td><td>3000</td><td>additional cost for kanji tokens which is longer than the pre-defined length threshold (expert feature).</td></tr>
+ * <tr><td>other.length_threshold</td><td>7</td><td>threshold of the length of non-kanji tokens which is penalized while running the Viterbi search (expert feature).</td></tr>
+ * <tr><td>other.penalty</td><td>1700</td><td>additional cost for non-kanji tokens which is longer than the pre-defined length threshold (expert feature).</td></tr>
+ * <tr><td>nakaguro_split</td><td>false</td><td>whether splits unknown words on the middle dot character (U+30FB KATAKANA MIDDLE DOT)</td></tr>
  * <tr><td>user_dict</td><td>-</td><td>path of user dictionary</td></tr>
  * <tr><td>tokenlist_name</td><td>default</td><td>target specialtokens name</td></tr>
  * <tr><td>all_language</td><td>false</td><td>apply kuromoji tokenizer to all language</td></tr>