Revision: 6085
          
http://languagetool.svn.sourceforge.net/languagetool/?rev=6085&view=rev
Author:   taolin2011
Date:     2011-12-22 01:50:13 +0000 (Thu, 22 Dec 2011)
Log Message:
-----------
add some Chinese rules, modify the changes and prepare for the 1.6 release

Modified Paths:
--------------
    trunk/JLanguageTool/CHANGES.txt
    trunk/JLanguageTool/src/java/org/languagetool/language/Chinese.java
    trunk/JLanguageTool/src/rules/zh/grammar.xml

Modified: trunk/JLanguageTool/CHANGES.txt
===================================================================
--- trunk/JLanguageTool/CHANGES.txt     2011-12-21 21:25:25 UTC (rev 6084)
+++ trunk/JLanguageTool/CHANGES.txt     2011-12-22 01:50:13 UTC (rev 6085)
@@ -23,6 +23,8 @@
    -several new rules
  -Italian:
    -several new rules (Paolo Bianchini)
+ -Chinese:
+   -several new rules (Tao Lin)
  -Tagalog:
    -new trigram profile
    -new rules

Modified: trunk/JLanguageTool/src/java/org/languagetool/language/Chinese.java
===================================================================
--- trunk/JLanguageTool/src/java/org/languagetool/language/Chinese.java 
2011-12-21 21:25:25 UTC (rev 6084)
+++ trunk/JLanguageTool/src/java/org/languagetool/language/Chinese.java 
2011-12-22 01:50:13 UTC (rev 6085)
@@ -35,63 +35,68 @@
 
 public class Chinese extends Language {
 
-  private Tagger tagger;
-  private Tokenizer wordTokenizer;
-  private SentenceTokenizer sentenceTokenizer;
+       private Tagger tagger;
+       private Tokenizer wordTokenizer;
+       private SentenceTokenizer sentenceTokenizer;
 
-  @Override
-  public String getShortName() {
-    return "zh";
-  }
+       @Override
+       public String getShortName() {
+               return "zh";
+       }
 
-  @Override
-  public String getName() {
-    return "Chinese";
-  }
+       @Override
+       public String getName() {
+               return "Chinese";
+       }
 
-  @Override
-  public String[] getCountryVariants() {
-    return new String[] { "CN" };
-  }
+       @Override
+       public String[] getCountryVariants() {
+               return new String[] { "CN" };
+       }
 
-  @Override
-  public Locale getLocale() {
-    return new Locale(getShortName());
-  }
+       @Override
+       public Locale getLocale() {
+               return new Locale(getShortName());
+       }
 
-  @Override
-  public Contributor[] getMaintainers() {
-    return new Contributor[] { new Contributor("Tao Lin"), new 
Contributor("Fangjie Wang"),
-        new Contributor("Wenting Cheng") };
-  }
+       @Override
+       public Contributor[] getMaintainers() {
+               return new Contributor[] { new Contributor("Tao Lin"),
+                               new Contributor("Fangjie Wang"),
+                               new Contributor("Wenting Cheng"), new 
Contributor("Xiang Yao"),
+                               new Contributor("Tong Wang"), new 
Contributor("Jiawen Mo"),
+                               new Contributor("Jiarong Li"), new 
Contributor("Weijie Huang"),
+                               new Contributor("Yixin Zhou"), new 
Contributor("Xinmin Chen"),
+                               new Contributor("Xiaofei Liu"), new 
Contributor("Debiao Luo"), };
+       }
 
-  @Override
-  public List<Class<? extends Rule>> getRelevantRules() {
-    return Arrays.asList(DoublePunctuationRule.class, WhitespaceRule.class);
-  }
+       @Override
+       public List<Class<? extends Rule>> getRelevantRules() {
+               return Arrays.asList(DoublePunctuationRule.class, 
WhitespaceRule.class);
+       }
 
-  @Override
-  public final Tagger getTagger() {
-    if (tagger == null) {
-      tagger = new ChineseTagger();
-    }
-    return tagger;
-  }
+       @Override
+       public final Tagger getTagger() {
+               if (tagger == null) {
+                       tagger = new ChineseTagger();
+               }
+               return tagger;
+       }
 
-  @Override
-  public final Tokenizer getWordTokenizer() {
-    if (wordTokenizer == null) {
-      wordTokenizer = new ChineseWordTokenizer();
-    }
-    return wordTokenizer;
-  }
+       @Override
+       public final Tokenizer getWordTokenizer() {
+               if (wordTokenizer == null) {
+                       wordTokenizer = new ChineseWordTokenizer();
+               }
+               return wordTokenizer;
+       }
 
-  @Override
-  public final SentenceTokenizer getSentenceTokenizer() {
-    if (sentenceTokenizer == null) {
-      sentenceTokenizer = new ChineseSentenceTokenizer();
-    }
-    return sentenceTokenizer;
-  }
+       @Override
+       public final SentenceTokenizer getSentenceTokenizer() {
+               if (sentenceTokenizer == null) {
+                       sentenceTokenizer = new ChineseSentenceTokenizer();
+               }
+               return sentenceTokenizer;
+       }
 
 }

Modified: trunk/JLanguageTool/src/rules/zh/grammar.xml
===================================================================
--- trunk/JLanguageTool/src/rules/zh/grammar.xml        2011-12-21 21:25:25 UTC 
(rev 6084)
+++ trunk/JLanguageTool/src/rules/zh/grammar.xml        2011-12-22 01:50:13 UTC 
(rev 6085)
@@ -14,6 +14,41 @@
   <!-- 拼写: 词语错误-->
   <!-- ====================================================================== 
-->
   <category name="词语错误">
+    <rulegroup id="HUN1_HUN2" name="混/浑">
+      <rule>
+        <pattern mark_to="-1">
+          <token>混</token>
+          <token regexp="yes" postag="a|b" postag_regexp="yes">厚|沦</token>
+        </pattern>
+        <message> 您的意思是"<suggestion>浑</suggestion>\2"吗? </message>
+        <short>词语错误</short>
+        <example type="incorrect" correction="浑"> 他的声音很<marker>混</marker>厚。 
</example>
+        <example type="correct">他的声音很浑厚。</example>
+      </rule>
+      <rule>
+        <pattern mark_to="-1">
+          <token>浑</token>
+          <token regexp="yes" postag="a|v|u|vg|ng" 
postag_regexp="yes">杂|淆|乱|合|战|帐</token>
+        </pattern>
+        <message> 您的意思是"<suggestion>混</suggestion>\2"吗? </message>
+        <short>词语错误</short>
+        <example type="incorrect" correction="混">
+          <marker>浑</marker>杂的军队必败。 </example>
+        <example type="correct">混杂的军队必败。</example>
+      </rule>
+      <rule>
+        <pattern>
+          <token>浑</token>
+          <token>为</token>
+          <token>一</token>
+          <token postag="v">谈</token>
+        </pattern>
+        <message> 您的意思是"<suggestion>混\2\3\4</suggestion>"吗? </message>
+        <short>词语错误</short>
+        <example type="incorrect" correction="混为一谈"> 
别将这件事<marker>浑为一谈</marker>。 </example>
+        <example type="correct">别将这件事混为一谈。</example>
+      </rule>
+    </rulegroup>
     <rulegroup id="ZHE_CHAI" name="折/拆">
       <rule>
         <pattern mark_to="-1">

This was sent by the SourceForge.net collaborative development platform, the 
world's largest Open Source development site.


------------------------------------------------------------------------------
Write once. Port to many.
Get the SDK and tools to simplify cross-platform app development. Create 
new or port existing apps to sell to consumers worldwide. Explore the 
Intel AppUpSM program developer opportunity. appdeveloper.intel.com/join
http://p.sf.net/sfu/intel-appdev
_______________________________________________
Languagetool-cvs mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/languagetool-cvs

Reply via email to