Index: tika-parsers/src/test/java/org/apache/tika/detect/TestContainerAwareDetector.java =================================================================== --- tika-parsers/src/test/java/org/apache/tika/detect/TestContainerAwareDetector.java (revision 1085429) +++ tika-parsers/src/test/java/org/apache/tika/detect/TestContainerAwareDetector.java (working copy) @@ -21,7 +21,7 @@ import junit.framework.TestCase; -import org.apache.poi.poifs.filesystem.POIFSFileSystem; +import org.apache.poi.poifs.filesystem.NPOIFSFileSystem; import org.apache.tika.io.TikaInputStream; import org.apache.tika.metadata.Metadata; import org.apache.tika.mime.MediaType; @@ -70,7 +70,7 @@ assertEquals( MediaType.parse("application/vnd.ms-powerpoint"), detector.detect(stream, new Metadata())); - assertTrue(stream.getOpenContainer() instanceof POIFSFileSystem); + assertTrue(stream.getOpenContainer() instanceof NPOIFSFileSystem); } finally { stream.close(); } Index: tika-parsers/src/main/java/org/apache/tika/detect/POIFSContainerDetector.java =================================================================== --- tika-parsers/src/main/java/org/apache/tika/detect/POIFSContainerDetector.java (revision 1085429) +++ tika-parsers/src/main/java/org/apache/tika/detect/POIFSContainerDetector.java (working copy) @@ -28,7 +28,7 @@ import java.util.Set; import org.apache.poi.poifs.filesystem.Entry; -import org.apache.poi.poifs.filesystem.POIFSFileSystem; +import org.apache.poi.poifs.filesystem.NPOIFSFileSystem; import org.apache.tika.io.CloseShieldInputStream; import org.apache.tika.io.TaggedInputStream; import org.apache.tika.io.TikaInputStream; @@ -141,9 +141,13 @@ TaggedInputStream tagged = new TaggedInputStream( new BufferedInputStream(new FileInputStream(file))); try { - // POIFSFileSystem might try close the stream - POIFSFileSystem fs = - new POIFSFileSystem(new CloseShieldInputStream(tagged)); + NPOIFSFileSystem fs; + if (stream.hasFile()) { + fs = new NPOIFSFileSystem(stream.getFile()); + } else { + // Load from a stream, but prevent the stream being closed + fs = new NPOIFSFileSystem(new CloseShieldInputStream(tagged)); + } // Optimize a possible later parsing process by keeping // a reference to the already opened POI file system Index: tika-parsers/src/main/java/org/apache/tika/parser/microsoft/WordExtractor.java =================================================================== --- tika-parsers/src/main/java/org/apache/tika/parser/microsoft/WordExtractor.java (revision 1085429) +++ tika-parsers/src/main/java/org/apache/tika/parser/microsoft/WordExtractor.java (working copy) @@ -40,7 +40,7 @@ import org.apache.poi.hwpf.usermodel.TableRow; import org.apache.poi.poifs.filesystem.DirectoryEntry; import org.apache.poi.poifs.filesystem.Entry; -import org.apache.poi.poifs.filesystem.POIFSFileSystem; +import org.apache.poi.poifs.filesystem.NPOIFSFileSystem; import org.apache.tika.exception.TikaException; import org.apache.tika.io.TikaInputStream; import org.apache.tika.parser.ParseContext; @@ -54,11 +54,11 @@ } protected void parse( - POIFSFileSystem filesystem, XHTMLContentHandler xhtml) + NPOIFSFileSystem filesystem, XHTMLContentHandler xhtml) throws IOException, SAXException, TikaException { HWPFDocument document; try { - document = new HWPFDocument(filesystem); + document = new HWPFDocument(filesystem.getRoot()); } catch(OldWordFileFormatException e) { parseWord6(filesystem, xhtml); return; @@ -345,9 +345,9 @@ } protected void parseWord6( - POIFSFileSystem filesystem, XHTMLContentHandler xhtml) + NPOIFSFileSystem filesystem, XHTMLContentHandler xhtml) throws IOException, SAXException, TikaException { - HWPFOldDocument doc = new HWPFOldDocument(filesystem); + HWPFOldDocument doc = new HWPFOldDocument(filesystem.getRoot()); Word6Extractor extractor = new Word6Extractor(doc); for(String p : extractor.getParagraphText()) { Index: tika-parsers/src/main/java/org/apache/tika/parser/microsoft/HSLFExtractor.java =================================================================== --- tika-parsers/src/main/java/org/apache/tika/parser/microsoft/HSLFExtractor.java (revision 1085429) +++ tika-parsers/src/main/java/org/apache/tika/parser/microsoft/HSLFExtractor.java (working copy) @@ -16,28 +16,29 @@ */ package org.apache.tika.parser.microsoft; +import java.io.IOException; +import java.util.List; + import org.apache.poi.hslf.extractor.PowerPointExtractor; import org.apache.poi.hslf.model.OLEShape; -import org.apache.poi.poifs.filesystem.POIFSFileSystem; +import org.apache.poi.poifs.filesystem.NPOIFSFileSystem; import org.apache.tika.exception.TikaException; import org.apache.tika.io.TikaInputStream; import org.apache.tika.parser.ParseContext; import org.apache.tika.sax.XHTMLContentHandler; import org.xml.sax.SAXException; -import java.io.IOException; -import java.util.List; - public class HSLFExtractor extends AbstractPOIFSExtractor { public HSLFExtractor(ParseContext context) { super(context); } protected void parse( - POIFSFileSystem filesystem, XHTMLContentHandler xhtml) + NPOIFSFileSystem filesystem, XHTMLContentHandler xhtml) throws IOException, SAXException, TikaException { + // TODO Tidy up with POI 3.8 beta 2 PowerPointExtractor powerPointExtractor = - new PowerPointExtractor(filesystem); + new PowerPointExtractor(filesystem.getRoot(), null); xhtml.element("p", powerPointExtractor.getText(true, true)); List shapeList = powerPointExtractor.getOLEShapes(); Index: tika-parsers/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java =================================================================== --- tika-parsers/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java (revision 1085429) +++ tika-parsers/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java (working copy) @@ -19,14 +19,21 @@ import java.io.IOException; import java.io.InputStream; import java.security.GeneralSecurityException; -import java.util.*; +import java.util.Arrays; +import java.util.Collections; +import java.util.HashSet; +import java.util.Locale; +import java.util.Set; +import org.apache.poi.hdgf.HDGFDiagram; import org.apache.poi.hdgf.extractor.VisioTextExtractor; +import org.apache.poi.hpbf.HPBFDocument; import org.apache.poi.hpbf.extractor.PublisherTextExtractor; import org.apache.poi.poifs.crypt.Decryptor; import org.apache.poi.poifs.crypt.EncryptionInfo; import org.apache.poi.poifs.filesystem.DirectoryEntry; import org.apache.poi.poifs.filesystem.Entry; +import org.apache.poi.poifs.filesystem.NPOIFSFileSystem; import org.apache.poi.poifs.filesystem.POIFSFileSystem; import org.apache.tika.exception.TikaException; import org.apache.tika.io.TikaInputStream; @@ -93,6 +100,10 @@ return detectType(fs.getRoot()); } + public static POIFSDocumentType detectType(NPOIFSFileSystem fs) { + return detectType(fs.getRoot()); + } + public static POIFSDocumentType detectType(DirectoryEntry node) { for (Entry entry : node) { POIFSDocumentType type = detectType(entry); @@ -152,12 +163,18 @@ XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata); xhtml.startDocument(); - POIFSFileSystem filesystem; - if(stream instanceof TikaInputStream && - ((TikaInputStream)stream).getOpenContainer() != null) { - filesystem = (POIFSFileSystem)((TikaInputStream)stream).getOpenContainer(); + NPOIFSFileSystem filesystem; + if(stream instanceof TikaInputStream) { + TikaInputStream tstream = (TikaInputStream)stream; + if(tstream.getOpenContainer() != null) { + filesystem = (NPOIFSFileSystem)tstream.getOpenContainer(); + } else if(tstream.hasFile()) { + filesystem = new NPOIFSFileSystem(tstream.getFile()); + } else { + filesystem = new NPOIFSFileSystem(tstream); + } } else { - filesystem = new POIFSFileSystem(stream); + filesystem = new NPOIFSFileSystem(stream); } // Parse summary entries first, to make metadata available early @@ -174,8 +191,11 @@ switch (type) { case PUBLISHER: + // TODO Tidy up when POI 3.8 beta 2 is out + HPBFDocument pubDoc = new HPBFDocument(filesystem.getRoot(), null); PublisherTextExtractor publisherTextExtractor = - new PublisherTextExtractor(filesystem); + new PublisherTextExtractor(pubDoc); +// new PublisherTextExtractor(filesystem); xhtml.element("p", publisherTextExtractor.getText()); break; case WORDDOCUMENT: @@ -189,8 +209,11 @@ new ExcelExtractor(context).parse(filesystem, xhtml, locale); break; case VISIO: + // TODO Tidy up when POI 3.8 beta 2 is out + HDGFDiagram visioDoc = new HDGFDiagram(filesystem.getRoot(), null); VisioTextExtractor visioTextExtractor = - new VisioTextExtractor(filesystem); + new VisioTextExtractor(visioDoc); +// new VisioTextExtractor(filesystem); for (String text : visioTextExtractor.getAllText()) { xhtml.element("p", text); } @@ -206,7 +229,12 @@ } break; case ENCRYPTED: - EncryptionInfo info = new EncryptionInfo(filesystem); + // TODO Tidy up when POI 3.8 beta 2 is out + POIFSFileSystem tmp = new POIFSFileSystem(); + tmp.createDocument(filesystem.createDocumentInputStream("EncryptionInfo"), "EncryptionInfo"); + tmp.createDocument(filesystem.createDocumentInputStream("EncryptedPackage"), "EncryptedPackage"); + + EncryptionInfo info = new EncryptionInfo(tmp); Decryptor d = new Decryptor(info); try { @@ -216,7 +244,7 @@ OOXMLParser parser = new OOXMLParser(); - parser.parse(d.getDataStream(filesystem), new EmbeddedContentHandler( + parser.parse(d.getDataStream(tmp), new EmbeddedContentHandler( new BodyContentHandler(xhtml)), metadata, context); } catch (GeneralSecurityException ex) { Index: tika-parsers/src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java =================================================================== --- tika-parsers/src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java (revision 1085429) +++ tika-parsers/src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java (working copy) @@ -21,7 +21,7 @@ import org.apache.poi.hsmf.MAPIMessage; import org.apache.poi.hsmf.datatypes.AttachmentChunks; import org.apache.poi.hsmf.exceptions.ChunkNotFoundException; -import org.apache.poi.poifs.filesystem.POIFSFileSystem; +import org.apache.poi.poifs.filesystem.NPOIFSFileSystem; import org.apache.tika.exception.TikaException; import org.apache.tika.io.TikaInputStream; import org.apache.tika.metadata.Metadata; @@ -35,11 +35,12 @@ public class OutlookExtractor extends AbstractPOIFSExtractor { private final MAPIMessage msg; - public OutlookExtractor(POIFSFileSystem filesystem, ParseContext context) throws TikaException { + public OutlookExtractor(NPOIFSFileSystem filesystem, ParseContext context) throws TikaException { super(context); try { - this.msg = new MAPIMessage(filesystem); + // TODO Tidy up when POI 3.8 beta 2 is out + this.msg = new MAPIMessage(filesystem.getRoot(), null); } catch (IOException e) { throw new TikaException("Failed to parse Outlook message", e); } Index: tika-parsers/src/main/java/org/apache/tika/parser/microsoft/SummaryExtractor.java =================================================================== --- tika-parsers/src/main/java/org/apache/tika/parser/microsoft/SummaryExtractor.java (revision 1085429) +++ tika-parsers/src/main/java/org/apache/tika/parser/microsoft/SummaryExtractor.java (working copy) @@ -29,7 +29,7 @@ import org.apache.poi.hpsf.UnexpectedPropertySetTypeException; import org.apache.poi.poifs.filesystem.DocumentEntry; import org.apache.poi.poifs.filesystem.DocumentInputStream; -import org.apache.poi.poifs.filesystem.POIFSFileSystem; +import org.apache.poi.poifs.filesystem.NPOIFSFileSystem; import org.apache.tika.exception.TikaException; import org.apache.tika.metadata.Metadata; import org.apache.tika.metadata.PagedText; @@ -52,14 +52,14 @@ this.metadata = metadata; } - public void parseSummaries(POIFSFileSystem filesystem) + public void parseSummaries(NPOIFSFileSystem filesystem) throws IOException, TikaException { parseSummaryEntryIfExists(filesystem, SUMMARY_INFORMATION); parseSummaryEntryIfExists(filesystem, DOCUMENT_SUMMARY_INFORMATION); } private void parseSummaryEntryIfExists( - POIFSFileSystem filesystem, String entryName) + NPOIFSFileSystem filesystem, String entryName) throws IOException, TikaException { try { DocumentEntry entry = Index: tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ExcelExtractor.java =================================================================== --- tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ExcelExtractor.java (revision 1085429) +++ tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ExcelExtractor.java (working copy) @@ -59,7 +59,7 @@ import org.apache.poi.poifs.filesystem.DirectoryEntry; import org.apache.poi.poifs.filesystem.DocumentInputStream; import org.apache.poi.poifs.filesystem.Entry; -import org.apache.poi.poifs.filesystem.POIFSFileSystem; +import org.apache.poi.poifs.filesystem.NPOIFSFileSystem; import org.apache.tika.exception.TikaException; import org.apache.tika.io.TikaInputStream; import org.apache.tika.parser.ParseContext; @@ -130,7 +130,7 @@ * or writing the extracted content */ protected void parse( - POIFSFileSystem filesystem, XHTMLContentHandler xhtml, + NPOIFSFileSystem filesystem, XHTMLContentHandler xhtml, Locale locale) throws IOException, SAXException, TikaException { TikaHSSFListener listener = new TikaHSSFListener(xhtml, locale, this); listener.processFile(filesystem, isListenForAllRecords()); @@ -243,7 +243,7 @@ * @throws IOException on any IO errors. * @throws SAXException on any SAX parsing errors. */ - public void processFile(POIFSFileSystem filesystem, boolean listenForAllRecords) + public void processFile(NPOIFSFileSystem filesystem, boolean listenForAllRecords) throws IOException, SAXException, TikaException { // Set up listener and register the records we want to process