Make the NonDict2 threadsafe

Author: AngledLuffa

src/edu/stanford/nlp/wordseg/Gale2007ChineseSegmenterFeatureFactory.java

@@ -52,6 +52,7 @@ public class Gale2007ChineseSegmenterFeatureFactory<IN extends CoreLabel> extend
 
   private transient TagAffixDetector taDetector; // = null;
   private transient CorpusDictionary outDict; // = null;
+  private transient NonDict2 nonDict; // = null;
 
   @Override
   public void init(SeqClassifierFlags flags) {
@@ -71,6 +72,11 @@ private synchronized void createOutDict() {
     }
   }
 
+  private synchronized void createNonDict() {
+    if (nonDict == null) {
+      nonDict = new NonDict2(flags);
+    }
+  }
 
   /**
    * Extracts all the features from the input data at a certain index.
@@ -479,8 +485,10 @@ protected Collection<String> featuresCpC(PaddedList<? extends CoreLabel> cInfo,
      * This is frickin' useful.  I hadn't realized.  CDM Oct 2007.
      */
     if (flags.useDict2) {
-      NonDict2 nd = new NonDict2(flags);
-      features.add(nd.checkDic(charp+charc, flags)+"nondict");
+      if (nonDict == null) {
+        createNonDict();
+      }
+      features.add(nonDict.checkDic(charp+charc, flags)+"nondict");
     }
 
     if (flags.useOutDict2) {

src/edu/stanford/nlp/wordseg/NonDict2.java

@@ -8,36 +8,32 @@
 public class NonDict2  {
 
   //public String sighanCorporaDict = "/u/nlp/data/chinese-segmenter/";
-  public String corporaDict = "/u/nlp/data/gale/segtool/stanford-seg/data/";
-  private static CorpusDictionary cd = null;
+  public static final String DEFAULT_HOME = "/u/nlp/data/gale/segtool/stanford-seg/data/";
+  public final String corporaDict;
+  private final CorpusDictionary cd;
 
   private static Redwood.RedwoodChannels logger = Redwood.channels(NonDict2.class);
 
   public NonDict2(SeqClassifierFlags flags) {
-    if (cd == null) {
-
-      if (flags.sighanCorporaDict != null) {
-        corporaDict = flags.sighanCorporaDict; // use the same flag for Sighan 2005,
-        // but our list is extracted from ctb
-      }
-      String path;
-      if (flags.useAs || flags.useHk || flags.useMsr) {
-        throw new RuntimeException("only support settings for CTB and PKU now.");
-      } else if ( flags.usePk ) {
-        path = corporaDict+"/dict/pku.non";
-      } else { // CTB
-        path = corporaDict+"/dict/ctb.non";
-      }
-
-      cd = new CorpusDictionary(path);
-      // just output the msg...
-      if (flags.useAs || flags.useHk || flags.useMsr) {
-      } else if ( flags.usePk ) {
-        logger.info("INFO: flags.usePk=true | building NonDict2 from "+path);
-      } else { // CTB
-        logger.info("INFO: flags.usePk=false | building NonDict2 from "+path);
-      }
+    if (flags.sighanCorporaDict != null) {
+      corporaDict = flags.sighanCorporaDict; // use the same flag for Sighan 2005,
+      // but our list is extracted from ctb
+    } else {
+      corporaDict = DEFAULT_HOME;
     }
+
+    String path;
+    if (flags.useAs || flags.useHk || flags.useMsr) {
+      throw new RuntimeException("only support settings for CTB and PKU now.");
+    } else if ( flags.usePk ) {
+      path = corporaDict+"/dict/pku.non";
+      logger.info("INFO: flags.usePk=true | building NonDict2 from "+path);
+    } else { // CTB
+      path = corporaDict+"/dict/ctb.non";
+      logger.info("INFO: flags.usePk=false | building NonDict2 from "+path);
+    }
+
+    cd = new CorpusDictionary(path);
   }
 
   public String checkDic(String c2, SeqClassifierFlags flags) {