svn commit: r1609677 - in /tika/trunk: tika-core/src/main/java/org/apache/tika/parser/ tika-parsers/src/main/java/org/apache/tika/parser/pdf/ tika-parsers/src/test/java/org/apache/tika/parser/pdf/

[sergeyb]

Author: sergeyb
Date: Fri Jul 11 10:27:15 2014
New Revision: 1609677

URL: http://svn.apache.org/r1609677
Log:
[TIKA-1351] Updating AutoDetect, Composite and PDF parsers to guard against 
null content handlers

Modified:
    
tika/trunk/tika-core/src/main/java/org/apache/tika/parser/AutoDetectParser.java
    
tika/trunk/tika-core/src/main/java/org/apache/tika/parser/CompositeParser.java
    
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
    
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java

Modified: 
tika/trunk/tika-core/src/main/java/org/apache/tika/parser/AutoDetectParser.java
URL: 
http://svn.apache.org/viewvc/tika/trunk/tika-core/src/main/java/org/apache/tika/parser/AutoDetectParser.java?rev=1609677&r1=1609676&r2=1609677&view=diff
==============================================================================
--- 
tika/trunk/tika-core/src/main/java/org/apache/tika/parser/AutoDetectParser.java 
(original)
+++ 
tika/trunk/tika-core/src/main/java/org/apache/tika/parser/AutoDetectParser.java 
Fri Jul 11 10:27:15 2014
@@ -114,7 +114,8 @@ public class AutoDetectParser extends Co
             metadata.set(Metadata.CONTENT_TYPE, type.toString());
 
             // TIKA-216: Zip bomb prevention
-            SecureContentHandler sch = new SecureContentHandler(handler, tis);
+            SecureContentHandler sch = 
+                handler != null ? new SecureContentHandler(handler, tis) : 
null;
             try {
                 // Parse the document
                 super.parse(tis, sch, metadata, context);

Modified: 
tika/trunk/tika-core/src/main/java/org/apache/tika/parser/CompositeParser.java
URL: 
http://svn.apache.org/viewvc/tika/trunk/tika-core/src/main/java/org/apache/tika/parser/CompositeParser.java?rev=1609677&r1=1609676&r2=1609677&view=diff
==============================================================================
--- 
tika/trunk/tika-core/src/main/java/org/apache/tika/parser/CompositeParser.java 
(original)
+++ 
tika/trunk/tika-core/src/main/java/org/apache/tika/parser/CompositeParser.java 
Fri Jul 11 10:27:15 2014
@@ -237,7 +237,8 @@ public class CompositeParser extends Abs
         TemporaryResources tmp = new TemporaryResources();
         try {
             TikaInputStream taggedStream = TikaInputStream.get(stream, tmp);
-            TaggedContentHandler taggedHandler = new 
TaggedContentHandler(handler);
+            TaggedContentHandler taggedHandler = 
+                handler != null ? new TaggedContentHandler(handler) : null;
             try {
                 parser.parse(taggedStream, taggedHandler, metadata, context);
             } catch (RuntimeException e) {

Modified: 
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
URL: 
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java?rev=1609677&r1=1609676&r2=1609677&view=diff
==============================================================================
--- 
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java 
(original)
+++ 
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java 
Fri Jul 11 10:27:15 2014
@@ -154,7 +154,9 @@ public class PDFParser extends AbstractP
             }
             metadata.set(Metadata.CONTENT_TYPE, "application/pdf");
             extractMetadata(pdfDocument, metadata);
-            PDF2XHTML.process(pdfDocument, handler, context, metadata, 
localConfig);
+            if (handler != null) {
+                PDF2XHTML.process(pdfDocument, handler, context, metadata, 
localConfig);
+            }
             
         } finally {
             if (pdfDocument != null) {

Modified: 
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
URL: 
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java?rev=1609677&r1=1609676&r2=1609677&view=diff
==============================================================================
--- 
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
 (original)
+++ 
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
 Fri Jul 11 10:27:15 2014
@@ -16,7 +16,6 @@
  */
 package org.apache.tika.parser.pdf;
 
-import org.junit.Ignore;
 import static org.junit.Assert.assertEquals;
 import static org.junit.Assert.assertFalse;
 import static org.junit.Assert.assertNull;
@@ -25,7 +24,6 @@ import static org.junit.Assert.assertTru
 import java.io.File;
 import java.io.FileInputStream;
 import java.io.InputStream;
-import java.util.Arrays;
 import java.util.HashMap;
 import java.util.HashSet;
 import java.util.List;
@@ -90,6 +88,26 @@ public class PDFParserTest extends TikaT
         assertTrue("should have word boundary between paragraphs", 
                 !content.contains("libraries.Apache"));
     }
+    
+    @Test
+    public void testPdfParsingMetadataOnly() throws Exception {
+        Parser parser = new AutoDetectParser(); // Should auto-detect!
+        Metadata metadata = new Metadata();
+
+        InputStream stream = PDFParserTest.class.getResourceAsStream(
+                "/test-documents/testPDF.pdf");
+
+        try {
+            parser.parse(stream, null, metadata, new ParseContext());
+        } finally {
+            stream.close();
+        }
+
+        assertEquals("application/pdf", metadata.get(Metadata.CONTENT_TYPE));
+        assertEquals("Bertrand Delacr\u00e9taz", 
metadata.get(TikaCoreProperties.CREATOR));
+        assertEquals("Firefox", metadata.get(TikaCoreProperties.CREATOR_TOOL));
+        assertEquals("Apache Tika - Apache Tika", 
metadata.get(TikaCoreProperties.TITLE));
+    }
 
     @Test
     public void testCustomMetadata() throws Exception {