You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ju...@apache.org on 2010/11/01 00:09:17 UTC
svn commit: r1029510 - in /tika/trunk/tika-parsers: pom.xml
src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java
src/main/java/org/apache/tika/parser/pdf/PDFParser.java
Author: jukka
Date: Sun Oct 31 23:09:17 2010
New Revision: 1029510
URL: http://svn.apache.org/viewvc?rev=1029510&view=rev
Log:
TIKA-446: Upgrade to PDFBox 1.3.1
Modified:
tika/trunk/tika-parsers/pom.xml
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDFParser.java
Modified: tika/trunk/tika-parsers/pom.xml
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/pom.xml?rev=1029510&r1=1029509&r2=1029510&view=diff
==============================================================================
--- tika/trunk/tika-parsers/pom.xml (original)
+++ tika/trunk/tika-parsers/pom.xml Sun Oct 31 23:09:17 2010
@@ -72,7 +72,7 @@
<dependency>
<groupId>org.apache.pdfbox</groupId>
<artifactId>pdfbox</artifactId>
- <version>1.2.1</version>
+ <version>1.3.1</version>
</dependency>
<!-- TIKA-370: PDFBox declares the Bouncy Castle dependencies
as optional, but we prefer to have them always to avoid
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=1029510&r1=1029509&r2=1029510&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 Sun Oct 31 23:09:17 2010
@@ -65,6 +65,8 @@ class PDF2XHTML extends PDFTextStripper
private PDF2XHTML(ContentHandler handler, Metadata metadata)
throws IOException {
this.handler = new XHTMLContentHandler(handler, metadata);
+ setForceParsing(true);
+ setSortByPosition(true);
}
@Override
@@ -125,47 +127,4 @@ class PDF2XHTML extends PDFTextStripper
}
}
- // Two methods added to work around lack of support for processWordSeparator
- // and processLineSeparator in PDFBox-0.7.3. This is fixed in CVS Head (PDFBox-0.7.4)
- @Override
- public String getWordSeparator()
- {
- try
- {
- handler.characters(" ");
- } catch(SAXException e) {
-
- }
- return super.getWordSeparator(); //To change body of overridden methods use File | Settings | File Templates.
- }
-
- @Override
- public String getLineSeparator()
- {
- try
- {
- handler.characters("\n");
- } catch(SAXException e) {
-
- }
- return super.getLineSeparator();
- }
-
-// protected void processLineSeparator(TextPosition p) throws IOException {
-// try {
-// handler.characters("\n");
-// } catch (SAXException e) {
-// throw new IOExceptionWithCause("Unable to write a newline", e);
-// }
-// }
-//
-// protected void processWordSeparator(TextPosition a, TextPosition b)
-// throws IOException {
-// try {
-// handler.characters(" ");
-// } catch (SAXException e) {
-// throw new IOExceptionWithCause("Unable to write a space", 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=1029510&r1=1029509&r2=1029510&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 Sun Oct 31 23:09:17 2010
@@ -50,6 +50,9 @@ import org.xml.sax.SAXException;
*/
public class PDFParser implements Parser {
+ /** Serial version UID */
+ private static final long serialVersionUID = -752276948656079347L;
+
/**
* Metadata key for giving the document password to the parser.
*
@@ -68,7 +71,7 @@ public class PDFParser implements Parser
InputStream stream, ContentHandler handler,
Metadata metadata, ParseContext context)
throws IOException, SAXException, TikaException {
- PDDocument pdfDocument = PDDocument.load(stream);
+ PDDocument pdfDocument = PDDocument.load(stream, true);
try {
if (pdfDocument.isEncrypted()
&& !pdfDocument.getCurrentAccessPermission().canExtractContent()) {