You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by dm...@apache.org on 2014/11/19 11:45:12 UTC

svn commit: r1640518 - in /tika/trunk/tika-parsers/src: main/java/org/apache/tika/parser/html/HtmlHandler.java test/java/org/apache/tika/parser/chm/TestChmExtraction.java

Author: dmeikle
Date: Wed Nov 19 10:45:12 2014
New Revision: 1640518

URL: http://svn.apache.org/r1640518
Log:
TIKA-1446: Updated test so it loads the test documents from the classpath

Modified:
    tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlHandler.java
    tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/chm/TestChmExtraction.java

Modified: tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlHandler.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlHandler.java?rev=1640518&r1=1640517&r2=1640518&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlHandler.java (original)
+++ tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlHandler.java Wed Nov 19 10:45:12 2014
@@ -16,15 +16,6 @@
  */
 package org.apache.tika.parser.html;
 
-import java.net.MalformedURLException;
-import java.net.URL;
-import java.util.Arrays;
-import java.util.HashSet;
-import java.util.Locale;
-import java.util.Set;
-import java.util.regex.Matcher;
-import java.util.regex.Pattern;
-
 import org.apache.tika.metadata.Metadata;
 import org.apache.tika.metadata.TikaCoreProperties;
 import org.apache.tika.mime.MediaType;
@@ -35,6 +26,15 @@ import org.xml.sax.ContentHandler;
 import org.xml.sax.SAXException;
 import org.xml.sax.helpers.AttributesImpl;
 
+import java.net.MalformedURLException;
+import java.net.URL;
+import java.util.Arrays;
+import java.util.HashSet;
+import java.util.Locale;
+import java.util.Set;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
 class HtmlHandler extends TextContentHandler {
 
     // List of attributes that need to be resolved.
@@ -167,7 +167,7 @@ class HtmlHandler extends TextContentHan
                 metadata.set(Metadata.CONTENT_TYPE, value);
             }
         } else {
-            metadata.set(name, value);
+            metadata.add(name, value);
         }
     }
 

Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/chm/TestChmExtraction.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/chm/TestChmExtraction.java?rev=1640518&r1=1640517&r2=1640518&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/chm/TestChmExtraction.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/chm/TestChmExtraction.java Wed Nov 19 10:45:12 2014
@@ -16,13 +16,23 @@
  */
 package org.apache.tika.parser.chm;
 
-import static org.junit.Assert.assertTrue;
+import org.apache.tika.exception.TikaException;
+import org.apache.tika.metadata.Metadata;
+import org.apache.tika.parser.ParseContext;
+import org.apache.tika.parser.Parser;
+import org.apache.tika.parser.chm.accessor.ChmDirectoryListingSet;
+import org.apache.tika.parser.chm.accessor.DirectoryListingEntry;
+import org.apache.tika.parser.chm.core.ChmExtractor;
+import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
+import org.xml.sax.SAXException;
 
 import java.io.ByteArrayInputStream;
 import java.io.File;
 import java.io.FileInputStream;
 import java.io.IOException;
 import java.io.InputStream;
+import java.net.URL;
 import java.util.Arrays;
 import java.util.HashSet;
 import java.util.List;
@@ -31,16 +41,7 @@ import java.util.concurrent.ExecutorServ
 import java.util.concurrent.Executors;
 import java.util.regex.Pattern;
 
-import org.apache.tika.exception.TikaException;
-import org.apache.tika.metadata.Metadata;
-import org.apache.tika.parser.ParseContext;
-import org.apache.tika.parser.Parser;
-import org.apache.tika.parser.chm.accessor.ChmDirectoryListingSet;
-import org.apache.tika.parser.chm.accessor.DirectoryListingEntry;
-import org.apache.tika.parser.chm.core.ChmExtractor;
-import org.apache.tika.sax.BodyContentHandler;
-import org.junit.Test;
-import org.xml.sax.SAXException;
+import static org.junit.Assert.assertTrue;
 
 public class TestChmExtraction {
 
@@ -197,11 +198,12 @@ public class TestChmExtraction {
     
     @Test
     public void test_TIKA_1446() throws Exception {
-      File chmFolder = new File("./target/test-classes/test-documents/chm/");
-      for (String fileName : chmFolder.list()) {
-        File file = new File(chmFolder, fileName);
-        InputStream stream = new FileInputStream(file);
-        testingChm(stream);
-      }
+        URL chmDir = TestChmExtraction.class.getResource("/test-documents/chm/");
+        File chmFolder = new File(chmDir.toURI());
+        for (String fileName : chmFolder.list()) {
+            File file = new File(chmFolder, fileName);
+            InputStream stream = new FileInputStream(file);
+            testingChm(stream);
+        }
     }
 }