You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@uima.apache.org by pk...@apache.org on 2014/11/14 14:02:14 UTC

svn commit: r1639627 - in /uima/ruta/trunk/ruta-core/src: main/java/org/apache/uima/ruta/engine/PlainTextAnnotator.java test/java/org/apache/uima/ruta/engine/PlainTextAnnotatorTest.java test/resources/org/apache/uima/ruta/engine/PlainTextAnnotatorTest.txt

Author: pkluegl
Date: Fri Nov 14 13:02:13 2014
New Revision: 1639627

URL: http://svn.apache.org/r1639627
Log:
UIMA-4103
- fixed nbsp-white-space-lines in PlainTextAnnotator
- extended test

Modified:
    uima/ruta/trunk/ruta-core/src/main/java/org/apache/uima/ruta/engine/PlainTextAnnotator.java
    uima/ruta/trunk/ruta-core/src/test/java/org/apache/uima/ruta/engine/PlainTextAnnotatorTest.java
    uima/ruta/trunk/ruta-core/src/test/resources/org/apache/uima/ruta/engine/PlainTextAnnotatorTest.txt

Modified: uima/ruta/trunk/ruta-core/src/main/java/org/apache/uima/ruta/engine/PlainTextAnnotator.java
URL: http://svn.apache.org/viewvc/uima/ruta/trunk/ruta-core/src/main/java/org/apache/uima/ruta/engine/PlainTextAnnotator.java?rev=1639627&r1=1639626&r2=1639627&view=diff
==============================================================================
--- uima/ruta/trunk/ruta-core/src/main/java/org/apache/uima/ruta/engine/PlainTextAnnotator.java (original)
+++ uima/ruta/trunk/ruta-core/src/main/java/org/apache/uima/ruta/engine/PlainTextAnnotator.java Fri Nov 14 13:02:13 2014
@@ -60,6 +60,10 @@ public class PlainTextAnnotator extends 
     try {
       while ((eachLine = br.readLine()) != null) {
         boolean wsLine = StringUtils.isBlank(eachLine);
+        if(!wsLine && StringUtils.isBlank(eachLine.trim().replaceAll("\u00A0|\u202F|\uFEFF|\u2007|\u180E", ""))) {
+          // HOTFIX for NBSPs
+          wsLine = true;
+        }
         boolean emptyLine = StringUtils.isEmpty(eachLine);
         int offsetAfterLine = offsetTillNow + eachLine.length();
         int nlLength = 1;

Modified: uima/ruta/trunk/ruta-core/src/test/java/org/apache/uima/ruta/engine/PlainTextAnnotatorTest.java
URL: http://svn.apache.org/viewvc/uima/ruta/trunk/ruta-core/src/test/java/org/apache/uima/ruta/engine/PlainTextAnnotatorTest.java?rev=1639627&r1=1639626&r2=1639627&view=diff
==============================================================================
--- uima/ruta/trunk/ruta-core/src/test/java/org/apache/uima/ruta/engine/PlainTextAnnotatorTest.java (original)
+++ uima/ruta/trunk/ruta-core/src/test/java/org/apache/uima/ruta/engine/PlainTextAnnotatorTest.java Fri Nov 14 13:02:13 2014
@@ -67,7 +67,7 @@ public class PlainTextAnnotatorTest {
     assertEquals(8, ai.size());
 
     ai = cas.getAnnotationIndex(cas.getTypeSystem().getType("org.apache.uima.ruta.type.WSLine"));
-    assertEquals(4, ai.size());
+    assertEquals(5, ai.size());
 
     ai = cas.getAnnotationIndex(cas.getTypeSystem().getType("org.apache.uima.ruta.type.Paragraph"));
     assertEquals(4, ai.size());

Modified: uima/ruta/trunk/ruta-core/src/test/resources/org/apache/uima/ruta/engine/PlainTextAnnotatorTest.txt
URL: http://svn.apache.org/viewvc/uima/ruta/trunk/ruta-core/src/test/resources/org/apache/uima/ruta/engine/PlainTextAnnotatorTest.txt?rev=1639627&r1=1639626&r2=1639627&view=diff
==============================================================================
--- uima/ruta/trunk/ruta-core/src/test/resources/org/apache/uima/ruta/engine/PlainTextAnnotatorTest.txt (original)
+++ uima/ruta/trunk/ruta-core/src/test/resources/org/apache/uima/ruta/engine/PlainTextAnnotatorTest.txt Fri Nov 14 13:02:13 2014
@@ -1,7 +1,7 @@
 1 some text
 2 some text
 3 some text
-
+Â