svn commit: r1036562 - in /tika/trunk/tika-parsers/src: main/java/org/apache/tika/parser/pdf/PDF2XHTML.java test/java/org/apache/tika/parser/pdf/PDFParserTest.java

[ju...@apache.org]

Author: jukka
Date: Thu Nov 18 18:10:29 2010
New Revision: 1036562

URL: http://svn.apache.org/viewvc?rev=1036562&view=rev
Log:
TIKA-548: PDF content extracted as single line

With test assertions by Staffan Olsson

Modified:
    tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java
    tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java

Modified: tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java?rev=1036562&r1=1036561&r2=1036562&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java (original)
+++ tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java Thu Nov 18 18:10:29 2010
@@ -17,6 +17,7 @@
 package org.apache.tika.parser.pdf;
 
 import java.io.IOException;
+import java.io.Writer;
 
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.pdmodel.PDPage;
@@ -50,7 +51,19 @@ class PDF2XHTML extends PDFTextStripper 
             PDDocument document, ContentHandler handler, Metadata metadata)
             throws SAXException, TikaException {
         try {
-            new PDF2XHTML(handler, metadata).getText(document);
+            // Extract text using a dummy Writer as we override the
+            // key methods to output to the given content handler.
+            new PDF2XHTML(handler, metadata).writeText(document, new Writer() {
+                @Override
+                public void write(char[] cbuf, int off, int len) {
+                }
+                @Override
+                public void flush() {
+                }
+                @Override
+                public void close() {
+                }
+            });
         } catch (IOException e) {
             if (e.getCause() instanceof SAXException) {
                 throw (SAXException) e.getCause();
@@ -127,4 +140,14 @@ class PDF2XHTML extends PDFTextStripper 
         }
     }
 
+    @Override
+    protected void writeLineSeparator() throws IOException {
+        try {
+            handler.characters("\n");
+        } catch (SAXException e) {
+            throw new IOExceptionWithCause(
+                    "Unable to write a newline character", e);
+        }
+    }
+
 }

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=1036562&r1=1036561&r2=1036562&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 Thu Nov 18 18:10:29 2010
@@ -47,7 +47,7 @@ public class PDFParserTest extends TestC
         }
 
         assertEquals("application/pdf", metadata.get(Metadata.CONTENT_TYPE));
-        assertEquals("Bertrand Delacrétaz", metadata.get(Metadata.AUTHOR));
+        assertEquals("Bertrand Delacr\u00e9taz", metadata.get(Metadata.AUTHOR));
         assertEquals("Apache Tika - Apache Tika", metadata.get(Metadata.TITLE));
         
         // Can't reliably test dates yet - see TIKA-451 
@@ -59,6 +59,11 @@ public class PDFParserTest extends TestC
         assertTrue(content.contains("Tika - Content Analysis Toolkit"));
         assertTrue(content.contains("incubator"));
         assertTrue(content.contains("Apache Software Foundation"));
+        // testing how the end of one paragraph is separated from start of the next one
+        assertTrue("should have word boundary after headline", 
+                !content.contains("ToolkitApache"));
+        assertTrue("should have word boundary between paragraphs", 
+                !content.contains("libraries.Apache"));
     }
 
     public void testCustomMetadata() throws Exception {