Revision: 19912
          http://sourceforge.net/p/gate/code/19912
Author:   markagreenwood
Date:     2017-01-04 13:17:07 +0000 (Wed, 04 Jan 2017)
Log Message:
-----------
merged in the fix for the nasty URL hackery

Modified Paths:
--------------
    
gate/branches/sawdust2/plugins/Stanford_CoreNLP/src/main/java/gate/stanford/NER.java

Property Changed:
----------------
    
gate/branches/sawdust2/plugins/Stanford_CoreNLP/src/main/java/gate/stanford/NER.java

Modified: 
gate/branches/sawdust2/plugins/Stanford_CoreNLP/src/main/java/gate/stanford/NER.java
===================================================================
--- 
gate/branches/sawdust2/plugins/Stanford_CoreNLP/src/main/java/gate/stanford/NER.java
        2017-01-04 13:06:20 UTC (rev 19911)
+++ 
gate/branches/sawdust2/plugins/Stanford_CoreNLP/src/main/java/gate/stanford/NER.java
        2017-01-04 13:17:07 UTC (rev 19912)
@@ -21,6 +21,19 @@
  */
 package gate.stanford;
 
+import java.io.InputStream;
+import java.net.URL;
+import java.text.NumberFormat;
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.Iterator;
+import java.util.List;
+import java.util.ListIterator;
+import java.util.zip.GZIPInputStream;
+
+import org.apache.log4j.Level;
+import org.apache.log4j.Logger;
+
 import edu.stanford.nlp.ie.AbstractSequenceClassifier;
 import edu.stanford.nlp.ie.crf.CRFClassifier;
 import edu.stanford.nlp.ling.CoreAnnotations;
@@ -41,17 +54,6 @@
 import gate.util.OffsetComparator;
 import gate.util.SimpleFeatureMapImpl;
 
-import java.net.URL;
-import java.text.NumberFormat;
-import java.util.ArrayList;
-import java.util.Collections;
-import java.util.Iterator;
-import java.util.List;
-import java.util.ListIterator;
-
-import org.apache.log4j.Level;
-import org.apache.log4j.Logger;
-
 /**
  * This class is a wrapper for the Stanford NER tool v3.2.0.
  */
@@ -94,10 +96,9 @@
   public Resource init() throws ResourceInstantiationException {
     if(tagger == null) {
       fireStatusChanged("Loading Stanford NER model");
-      try {
-        // nasty workaround for stanford NER's path format inconsistency -
-        // tagger is content with uris beginning file:, ner labeller is not
-        tagger = 
CRFClassifier.getClassifier(modelFile.toString().substring(5));
+      try (InputStream in = modelFile.openStream();
+          GZIPInputStream gzipIn = new GZIPInputStream(in)){
+        tagger = CRFClassifier.getClassifier(gzipIn);
       } catch(Exception e) {
         throw new ResourceInstantiationException(e);
       }
@@ -188,10 +189,12 @@
         Iterator<CoreLabel> resIter = taggerResults.iterator();
         Iterator<Annotation> tokIter = tokensInCurrentSentence.iterator();
         String previousLabel = outsideLabel;
-        Long previousEnd = -1L;
-        Long entityStart = -1L;
-        // No idea why this was there so lets comment it out
-        // Long entityEnd = new Long(-1);
+        Long previousEnd = new Long(-1);
+        Long entityStart = new Long(-1);
+        
+        //No idea why this was there so lets comment it out
+        //Long entityEnd = new Long(-1);
+
         Annotation annot;
         String nerLabel = "";
         while(resIter.hasNext()) {


Property changes on: 
gate/branches/sawdust2/plugins/Stanford_CoreNLP/src/main/java/gate/stanford/NER.java
___________________________________________________________________
Added: svn:mergeinfo
## -0,0 +1,7 ##
+/gate/branches/new-ontology-api/plugins/Stanford_CoreNLP/src/main/java/gate/stanford/NER.java:10584-11598
+/gate/branches/release-7.0/plugins/Stanford_CoreNLP/src/main/java/gate/stanford/NER.java:15335-15398
+/gate/branches/release-8.1/plugins/Stanford_CoreNLP/src/main/java/gate/stanford/NER.java:18736-18747
+/gate/branches/sawdust/plugins/Stanford_CoreNLP/src/main/java/gate/stanford/NER.java:17055-17079
+/gate/tags/release-7.0/plugins/Stanford_CoreNLP/src/main/java/gate/stanford/NER.java:15399-15407
+/gate/trunk/plugins/Stanford_CoreNLP/src/gate/stanford/NER.java:19180-19911
+/gate/trunk/plugins/Stanford_CoreNLP/src/main/java/gate/stanford/NER.java:3-390,19180-19522
\ No newline at end of property
This was sent by the SourceForge.net collaborative development platform, the 
world's largest Open Source development site.


------------------------------------------------------------------------------
Check out the vibrant tech community on one of the world's most 
engaging tech sites, SlashDot.org! http://sdm.link/slashdot
_______________________________________________
GATE-cvs mailing list
GATE-cvs@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/gate-cvs

Reply via email to