Author: nick
Date: Fri Apr 27 13:59:49 2012
New Revision: 1331434
URL: http://svn.apache.org/viewvc?rev=1331434&view=rev
Log:
TIKA-861 Patch from Ryan Quam to enable extracting PDF Links. (Links are
extracted for now at the end of the page, further work will be needed to match
them to the text they apply to)
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=1331434&r1=1331433&r2=1331434&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
Fri Apr 27 13:59:49 2012
@@ -22,7 +22,10 @@ import java.io.Writer;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.util.PDFTextStripper;
+import org.apache.pdfbox.pdmodel.interactive.action.type.PDAction;
+import org.apache.pdfbox.pdmodel.interactive.action.type.PDActionURI;
import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotation;
+import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotationLink;
import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotationMarkup;
import org.apache.pdfbox.util.TextPosition;
import org.apache.tika.exception.TikaException;
@@ -140,6 +143,23 @@ class PDF2XHTML extends PDFTextStripper
// TODO: remove once PDFBOX-1143 is fixed:
if (extractAnnotationText) {
for(Object o : page.getAnnotations()) {
+ if( o instanceof PDAnnotationLink ) {
+ PDAnnotationLink annotationlink = (PDAnnotationLink) o;
+ if (annotationlink.getAction() != null) {
+ PDAction action = annotationlink.getAction();
+ if( action instanceof PDActionURI ) {
+ PDActionURI uri = (PDActionURI) action;
+ String link = uri.getURI();
+ if (link != null) {
+ handler.startElement("div", "class",
"annotation");
+ handler.startElement("a", "href", link);
+ handler.endElement("a");
+ handler.endElement("div");
+ }
+ }
+ }
+ }
+
if ((o instanceof PDAnnotation) &&
PDAnnotationMarkup.SUB_TYPE_FREETEXT.equals(((PDAnnotation) o).getSubtype())) {
// It's a text annotation:
PDAnnotationMarkup annot = (PDAnnotationMarkup) o;
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=1331434&r1=1331433&r2=1331434&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 Apr 27 13:59:49 2012
@@ -308,6 +308,19 @@ public class PDFParserTest extends TikaT
assertContains("<p>1</p>", content);
}
+ /**
+ * Test to ensure that Links are extracted from the text
+ *
+ * Note - the PDF contains the text "This is a hyperlink" which
+ * a hyperlink annotation, linking to the tika site, on it. This
+ * test will need updating when we're able to apply the annotation
+ * to the text itself, rather than following on afterwards as now
+ */
+ public void testLinks() throws Exception {
+ final XMLResult result = getXML("testPDFVarious.pdf");
+ assertContains("<div class=\"annotation\"><a
href=\"http://tika.apache.org/\"/></div>", result.xml);
+ }
+
public void testDisableAutoSpace() throws Exception {
PDFParser parser = new PDFParser();
parser.setEnableAutoSpace(false);
