Index: CHANGES.txt =================================================================== --- CHANGES.txt (revision 1188802) +++ CHANGES.txt (working copy) @@ -22,6 +22,9 @@ * TIKA-724: Added option to PDFParser to enable (the default) or disable auto-space insertion. + * TIKA-736: OpenOffice Presentation: text from the master slide is + now extracted. + Release 0.10 - 09/25/2011 The most notable changes in Tika 0.10 over previous releases are: Index: tika-parsers/src/test/java/org/apache/tika/parser/odf/ODFParserTest.java =================================================================== --- tika-parsers/src/test/java/org/apache/tika/parser/odf/ODFParserTest.java (revision 1188802) +++ tika-parsers/src/test/java/org/apache/tika/parser/odf/ODFParserTest.java (working copy) @@ -18,16 +18,16 @@ import java.io.InputStream; -import junit.framework.TestCase; - +import org.apache.tika.TikaTest; import org.apache.tika.metadata.Metadata; +import org.apache.tika.parser.AutoDetectParser; import org.apache.tika.parser.ParseContext; import org.apache.tika.parser.Parser; import org.apache.tika.parser.opendocument.OpenOfficeParser; import org.apache.tika.sax.BodyContentHandler; import org.xml.sax.ContentHandler; -public class ODFParserTest extends TestCase { +public class ODFParserTest extends TikaTest { /** * For now, allow us to run some tests against both * the old and the new parser @@ -207,4 +207,19 @@ input.close(); } } -} \ No newline at end of file + + public void testODPMasterFooter() throws Exception { + InputStream input = ODFParserTest.class.getResourceAsStream( + "/test-documents/testMasterFooter.odp"); + try { + Metadata metadata = new Metadata(); + ContentHandler handler = new BodyContentHandler(); + new AutoDetectParser().parse(input, handler, metadata); + + String content = handler.toString(); + assertContains("Master footer is here", content); + } finally { + input.close(); + } + } +} Index: tika-parsers/src/test/resources/test-documents/testMasterFooter.odp =================================================================== Cannot display: file marked as a binary type. svn:mime-type = application/octet-stream Property changes on: tika-parsers/src/test/resources/test-documents/testMasterFooter.odp ___________________________________________________________________ Added: svn:executable + * Added: svn:mime-type + application/octet-stream Index: tika-parsers/src/main/java/org/apache/tika/parser/pkg/ZipContainerDetector.java =================================================================== --- tika-parsers/src/main/java/org/apache/tika/parser/pkg/ZipContainerDetector.java (revision 1188802) +++ tika-parsers/src/main/java/org/apache/tika/parser/pkg/ZipContainerDetector.java (working copy) @@ -82,6 +82,10 @@ return MediaType.application("java-archive"); } } finally { + // TODO: shouldn't we record the open + // container so it can be later + // reused...? + // tis.setOpenContainer(zip); zip.close(); } } catch (IOException ignore) { Index: tika-parsers/src/main/java/org/apache/tika/parser/odf/OpenDocumentContentParser.java =================================================================== --- tika-parsers/src/main/java/org/apache/tika/parser/odf/OpenDocumentContentParser.java (revision 1188802) +++ tika-parsers/src/main/java/org/apache/tika/parser/odf/OpenDocumentContentParser.java (working copy) @@ -174,10 +174,18 @@ InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context) throws IOException, SAXException, TikaException { - final XHTMLContentHandler xhtml = - new XHTMLContentHandler(handler,metadata); - DefaultHandler dh = new ElementMappingContentHandler(xhtml, MAPPINGS) { + parseInternal(stream, + new XHTMLContentHandler(handler,metadata), + metadata, context); + } + void parseInternal( + InputStream stream, final ContentHandler handler, + Metadata metadata, ParseContext context) + throws IOException, SAXException, TikaException { + + DefaultHandler dh = new ElementMappingContentHandler(handler, MAPPINGS) { + private final BitSet textNodeStack = new BitSet(); private int nodeDepth = 0; @@ -231,7 +239,7 @@ * Check if a node is a text node */ private boolean isTextNode(String namespaceURI, String localName) { - if (TEXT_NS.equals(namespaceURI)) { + if (TEXT_NS.equals(namespaceURI) && !localName.equals("page-number")) { return true; } if (SVG_NS.equals(namespaceURI)) { @@ -263,10 +271,10 @@ // call next handler if no filtering if (completelyFiltered == 0) { // special handling of text:h, that are directly passed - // to xhtml handler + // to incoming handler if (TEXT_NS.equals(namespaceURI) && "h".equals(localName)) { - xhtml.startElement(headingStack.push( - getXHTMLHeaderTagName(atts))); + final String el = headingStack.push(getXHTMLHeaderTagName(atts)); + handler.startElement(namespaceURI, el, el, atts); } else { super.startElement( namespaceURI, localName, qName, atts); @@ -281,9 +289,10 @@ // call next handler if no filtering if (completelyFiltered == 0) { // special handling of text:h, that are directly passed - // to xhtml handler + // to incoming handler if (TEXT_NS.equals(namespaceURI) && "h".equals(localName)) { - xhtml.endElement(headingStack.pop()); + final String el = headingStack.pop(); + handler.endElement(namespaceURI, el, el); } else { super.endElement(namespaceURI,localName,qName); } Index: tika-parsers/src/main/java/org/apache/tika/parser/odf/OpenDocumentParser.java =================================================================== --- tika-parsers/src/main/java/org/apache/tika/parser/odf/OpenDocumentParser.java (revision 1188802) +++ tika-parsers/src/main/java/org/apache/tika/parser/odf/OpenDocumentParser.java (working copy) @@ -25,6 +25,8 @@ import java.util.zip.ZipEntry; import java.util.zip.ZipInputStream; +//import org.apache.commons.compress.archivers.zip.ZipArchiveEntry; +//import org.apache.commons.compress.archivers.zip.ZipFile; import org.apache.tika.exception.TikaException; import org.apache.tika.io.IOUtils; import org.apache.tika.metadata.Metadata; @@ -33,6 +35,7 @@ import org.apache.tika.parser.ParseContext; import org.apache.tika.parser.Parser; import org.apache.tika.sax.EndDocumentShieldingContentHandler; +import org.apache.tika.sax.XHTMLContentHandler; import org.xml.sax.ContentHandler; import org.xml.sax.SAXException; import org.xml.sax.helpers.DefaultHandler; @@ -106,12 +109,37 @@ InputStream stream, ContentHandler baseHandler, Metadata metadata, ParseContext context) throws IOException, SAXException, TikaException { - + + // TODO: reuse the already opened ZIPFile, if + // present + + /* + ZipFile zipFile; + if (stream instanceof TikaInputStream) { + TikaInputStream tis = (TikaInputStream) stream; + Object container = ((TikaInputStream) stream).getOpenContainer(); + if (container instanceof ZipFile) { + zipFile = (ZipFile) container; + } else if (tis.hasFile()) { + zipFile = new ZipFile(tis.getFile()); + } + } + */ + + // TODO: if incoming IS is a TIS with a file + // associated, we should open ZipFile so we can + // visit metadata, mimetype first; today we lose + // all the metadata if meta.xml is hit after + // content.xml in the stream. Then we can still + // read-once for the content.xml. + + XHTMLContentHandler xhtml = new XHTMLContentHandler(baseHandler, metadata); + // As we don't know which of the metadata or the content // we'll hit first, catch the endDocument call initially EndDocumentShieldingContentHandler handler = - new EndDocumentShieldingContentHandler(baseHandler); - + new EndDocumentShieldingContentHandler(xhtml); + // Process the file in turn ZipInputStream zip = new ZipInputStream(stream); ZipEntry entry = zip.getNextEntry(); @@ -122,7 +150,19 @@ } else if (entry.getName().equals("meta.xml")) { meta.parse(zip, new DefaultHandler(), metadata, context); } else if (entry.getName().endsWith("content.xml")) { - content.parse(zip, handler, metadata, context); + if (content instanceof OpenDocumentContentParser) { + ((OpenDocumentContentParser) content).parseInternal(zip, handler, metadata, context); + } else { + // Foreign content parser was set: + content.parse(zip, handler, metadata, context); + } + } else if (entry.getName().endsWith("styles.xml")) { + if (content instanceof OpenDocumentContentParser) { + ((OpenDocumentContentParser) content).parseInternal(zip, handler, metadata, context); + } else { + // Foreign content parser was set: + content.parse(zip, handler, metadata, context); + } } entry = zip.getNextEntry(); }