Return-Path: X-Original-To: apmail-tika-commits-archive@www.apache.org Delivered-To: apmail-tika-commits-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id 3F3369175 for ; Tue, 20 Dec 2011 06:15:55 +0000 (UTC) Received: (qmail 98308 invoked by uid 500); 20 Dec 2011 06:15:53 -0000 Delivered-To: apmail-tika-commits-archive@tika.apache.org Received: (qmail 98130 invoked by uid 500); 20 Dec 2011 06:15:52 -0000 Mailing-List: contact commits-help@tika.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: dev@tika.apache.org Delivered-To: mailing list commits@tika.apache.org Received: (qmail 98119 invoked by uid 99); 20 Dec 2011 06:15:51 -0000 Received: from athena.apache.org (HELO athena.apache.org) (140.211.11.136) by apache.org (qpsmtpd/0.29) with ESMTP; Tue, 20 Dec 2011 06:15:51 +0000 X-ASF-Spam-Status: No, hits=-2000.0 required=5.0 tests=ALL_TRUSTED X-Spam-Check-By: apache.org Received: from [140.211.11.4] (HELO eris.apache.org) (140.211.11.4) by apache.org (qpsmtpd/0.29) with ESMTP; Tue, 20 Dec 2011 06:15:50 +0000 Received: from eris.apache.org (localhost [127.0.0.1]) by eris.apache.org (Postfix) with ESMTP id 77D1F23888CD; Tue, 20 Dec 2011 06:15:29 +0000 (UTC) Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: svn commit: r1221112 - /tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/AbstractPOIFSExtractor.java Date: Tue, 20 Dec 2011 06:15:29 -0000 To: commits@tika.apache.org From: nick@apache.org X-Mailer: svnmailer-1.0.8-patched Message-Id: <20111220061529.77D1F23888CD@eris.apache.org> Author: nick Date: Tue Dec 20 06:15:29 2011 New Revision: 1221112 URL: http://svn.apache.org/viewvc?rev=1221112&view=rev Log: TIKA-757 Tidy the OLE10Native extractor code now that POI has been upgraded Modified: tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/AbstractPOIFSExtractor.java Modified: tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/AbstractPOIFSExtractor.java URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/AbstractPOIFSExtractor.java?rev=1221112&r1=1221111&r2=1221112&view=diff ============================================================================== --- tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/AbstractPOIFSExtractor.java (original) +++ tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/AbstractPOIFSExtractor.java Tue Dec 20 06:15:29 2011 @@ -16,16 +16,15 @@ */ package org.apache.tika.parser.microsoft; -import java.io.ByteArrayOutputStream; import java.io.IOException; import org.apache.poi.poifs.filesystem.DirectoryEntry; +import org.apache.poi.poifs.filesystem.DirectoryNode; import org.apache.poi.poifs.filesystem.DocumentEntry; import org.apache.poi.poifs.filesystem.DocumentInputStream; import org.apache.poi.poifs.filesystem.Entry; import org.apache.poi.poifs.filesystem.Ole10Native; import org.apache.poi.poifs.filesystem.Ole10NativeException; -import org.apache.poi.util.IOUtils; import org.apache.tika.exception.TikaException; import org.apache.tika.extractor.EmbeddedDocumentExtractor; import org.apache.tika.extractor.ParsingEmbeddedDocumentExtractor; @@ -107,24 +106,16 @@ abstract class AbstractPOIFSExtractor { try { if (type == POIFSDocumentType.OLE10_NATIVE) { - Entry entry = dir.getEntry(Ole10Native.OLE10_NATIVE); - ByteArrayOutputStream bos = new ByteArrayOutputStream(); - - // TODO: once we upgrade to POI 3.8 beta 5 - // we can avoid this full copy/serialize by - // passing the DirectoryNode instead: - IOUtils.copy(new DocumentInputStream((DocumentEntry) entry), bos); - byte[] data = bos.toByteArray(); - try { - // Maybe unwrap OLE10Native record: - Ole10Native ole = new Ole10Native(data, 0); - data = ole.getDataBuffer(); + // Try to un-wrap the OLE10Native record: + Ole10Native ole = Ole10Native.createFromEmbeddedOleObject((DirectoryNode)dir); metadata.set(Metadata.RESOURCE_NAME_KEY, dir.getName() + '/' + ole.getLabel()); + + byte[] data = ole.getDataBuffer(); + embedded = TikaInputStream.get(data); } catch (Ole10NativeException ex) { - // Not an OLE10Native record + // Not a valid OLE10Native record, skip it } - embedded = TikaInputStream.get(data); } else { metadata.set(Metadata.CONTENT_TYPE, type.getType().toString()); metadata.set(Metadata.RESOURCE_NAME_KEY, dir.getName() + '.' + type.getExtension());