You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by bo...@apache.org on 2016/01/06 04:50:57 UTC
svn commit: r1723223 [16/32] - in /tika/branches/2.x:
tika-core/src/test/resources/META-INF/
tika-core/src/test/resources/META-INF/services/ tika-parser-modules/
tika-parser-modules/tika-advanced-module/
tika-parser-modules/tika-advanced-module/src/ ti...
Added: tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/OutlookParserTest.java
URL: http://svn.apache.org/viewvc/tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/OutlookParserTest.java?rev=1723223&view=auto
==============================================================================
--- tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/OutlookParserTest.java (added)
+++ tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/OutlookParserTest.java Wed Jan 6 03:50:50 2016
@@ -0,0 +1,239 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.tika.parser.microsoft;
+
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertFalse;
+import static org.junit.Assert.assertTrue;
+
+import javax.xml.transform.OutputKeys;
+import javax.xml.transform.sax.SAXTransformerFactory;
+import javax.xml.transform.sax.TransformerHandler;
+import javax.xml.transform.stream.StreamResult;
+import java.io.InputStream;
+import java.io.StringWriter;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+import org.apache.tika.TikaTest;
+import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.TikaCoreProperties;
+import org.apache.tika.parser.AutoDetectParser;
+import org.apache.tika.parser.ParseContext;
+import org.apache.tika.parser.Parser;
+import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
+import org.xml.sax.ContentHandler;
+
+/**
+ * Test case for parsing Outlook files.
+ */
+public class OutlookParserTest extends TikaTest {
+
+ @Test
+ public void testOutlookParsing() throws Exception {
+ Parser parser = new AutoDetectParser(); // Should auto-detect!
+ ContentHandler handler = new BodyContentHandler();
+ Metadata metadata = new Metadata();
+
+ try (InputStream stream = OutlookParserTest.class.getResourceAsStream(
+ "/test-documents/test-outlook.msg")) {
+ parser.parse(stream, handler, metadata, new ParseContext());
+ }
+
+ assertEquals(
+ "application/vnd.ms-outlook",
+ metadata.get(Metadata.CONTENT_TYPE));
+ assertEquals(
+ "Microsoft Outlook Express 6",
+ metadata.get(TikaCoreProperties.TITLE));
+ assertEquals(
+ "Nouvel utilisateur de Outlook Express",
+ metadata.get(Metadata.MESSAGE_RECIPIENT_ADDRESS));
+ assertEquals(
+ "L'\u00C9quipe Microsoft Outlook Express",
+ metadata.get(TikaCoreProperties.CREATOR));
+ assertEquals(
+ "L'\u00C9quipe Microsoft Outlook Express",
+ metadata.get(Metadata.AUTHOR));
+
+ // Stored as Thu, 5 Apr 2007 09:26:06 -0700
+ assertEquals(
+ "2007-04-05T16:26:06Z",
+ metadata.get(TikaCoreProperties.CREATED));
+
+ String content = handler.toString();
+ assertContains("Microsoft Outlook Express 6", content);
+ assertContains("L'\u00C9quipe Microsoft Outlook Express", content);
+ assertContains("Nouvel utilisateur de Outlook Express", content);
+ assertContains("Messagerie et groupes de discussion", content);
+ }
+
+ /**
+ * Test case for TIKA-197
+ *
+ * @see <a href="https://issues.apache.org/jira/browse/TIKA-197">TIKA-197</a>
+ */
+ @Test
+ public void testMultipleCopies() throws Exception {
+ Parser parser = new AutoDetectParser();
+ ContentHandler handler = new BodyContentHandler();
+ Metadata metadata = new Metadata();
+
+ try (InputStream stream = OutlookParserTest.class.getResourceAsStream(
+ "/test-documents/testMSG.msg")) {
+ parser.parse(stream, handler, metadata, new ParseContext());
+ }
+
+ assertEquals(
+ "application/vnd.ms-outlook",
+ metadata.get(Metadata.CONTENT_TYPE));
+
+ String content = handler.toString();
+ Pattern pattern = Pattern.compile("From");
+ Matcher matcher = pattern.matcher(content);
+ assertTrue(matcher.find());
+ assertFalse(matcher.find());
+ }
+
+ /**
+ * Test case for TIKA-395, to ensure parser works for new Outlook formats.
+ *
+ * @see <a href="https://issues.apache.org/jira/browse/TIKA-395">TIKA-395</a>
+ */
+ @Test
+ public void testOutlookNew() throws Exception {
+ Parser parser = new AutoDetectParser();
+ ContentHandler handler = new BodyContentHandler();
+ Metadata metadata = new Metadata();
+
+ try (InputStream stream = OutlookParserTest.class.getResourceAsStream(
+ "/test-documents/test-outlook2003.msg")) {
+ parser.parse(stream, handler, metadata, new ParseContext());
+ }
+
+ assertEquals(
+ "application/vnd.ms-outlook",
+ metadata.get(Metadata.CONTENT_TYPE));
+ assertEquals(
+ "Welcome to Microsoft Office Outlook 2003",
+ metadata.get(TikaCoreProperties.TITLE));
+
+ String content = handler.toString();
+ assertContains("Outlook 2003", content);
+ assertContains("Streamlined Mail Experience", content);
+ assertContains("Navigation Pane", content);
+ }
+
+ @Test
+ public void testOutlookHTMLVersion() throws Exception {
+ Parser parser = new AutoDetectParser();
+ Metadata metadata = new Metadata();
+
+ // Check the HTML version
+ StringWriter sw = new StringWriter();
+ SAXTransformerFactory factory = (SAXTransformerFactory)
+ SAXTransformerFactory.newInstance();
+ TransformerHandler handler = factory.newTransformerHandler();
+ handler.getTransformer().setOutputProperty(OutputKeys.METHOD, "xml");
+ handler.getTransformer().setOutputProperty(OutputKeys.INDENT, "yes");
+ handler.setResult(new StreamResult(sw));
+
+ try (InputStream stream = OutlookParserTest.class.getResourceAsStream(
+ "/test-documents/testMSG_chinese.msg")) {
+ parser.parse(stream, handler, metadata, new ParseContext());
+ }
+
+ // As the HTML version should have been processed, ensure
+ // we got some of the links
+ String content = sw.toString();
+ assertContains("<dd>tests.chang@fengttt.com</dd>", content);
+ assertContains("<p>Alfresco MSG format testing", content);
+ assertContains("<li>1", content);
+ assertContains("<li>2", content);
+
+ // Make sure we don't have nested html docs
+ assertEquals(2, content.split("<body>").length);
+ assertEquals(2, content.split("<\\/body>").length);
+
+ // Make sure that the Chinese actually came through
+ assertContains("\u5F35\u6BD3\u502B", metadata.get(TikaCoreProperties.CREATOR));
+ assertContains("\u9673\u60E0\u73CD", content);
+ }
+
+ @Test
+ public void testOutlookForwarded() throws Exception {
+ Parser parser = new AutoDetectParser();
+ Metadata metadata = new Metadata();
+
+ // Check the HTML version
+ StringWriter sw = new StringWriter();
+ SAXTransformerFactory factory = (SAXTransformerFactory)
+ SAXTransformerFactory.newInstance();
+ TransformerHandler handler = factory.newTransformerHandler();
+ handler.getTransformer().setOutputProperty(OutputKeys.METHOD, "xml");
+ handler.getTransformer().setOutputProperty(OutputKeys.INDENT, "yes");
+ handler.setResult(new StreamResult(sw));
+
+ try (InputStream stream = OutlookParserTest.class.getResourceAsStream(
+ "/test-documents/testMSG_forwarded.msg")) {
+ parser.parse(stream, handler, metadata, new ParseContext());
+ }
+
+ // Make sure we don't have nested docs
+ String content = sw.toString();
+ assertEquals(2, content.split("<body>").length);
+ assertEquals(2, content.split("<\\/body>").length);
+ }
+
+ @Test
+ public void testOutlookHTMLfromRTF() throws Exception {
+ Parser parser = new AutoDetectParser();
+ Metadata metadata = new Metadata();
+
+ // Check the HTML version
+ StringWriter sw = new StringWriter();
+ SAXTransformerFactory factory = (SAXTransformerFactory)
+ SAXTransformerFactory.newInstance();
+ TransformerHandler handler = factory.newTransformerHandler();
+ handler.getTransformer().setOutputProperty(OutputKeys.METHOD, "xml");
+ handler.getTransformer().setOutputProperty(OutputKeys.INDENT, "yes");
+ handler.setResult(new StreamResult(sw));
+
+ try (InputStream stream = OutlookParserTest.class.getResourceAsStream(
+ "/test-documents/test-outlook2003.msg")) {
+ parser.parse(stream, handler, metadata, new ParseContext());
+ }
+
+ // As the HTML version should have been processed, ensure
+ // we got some of the links
+ String content = sw.toString().replaceAll("<p>\\s+", "<p>");
+ assertContains("<dd>New Outlook User</dd>", content);
+ assertContains("designed <i>to help you", content);
+ assertContains("<p><a href=\"http://r.office.microsoft.com/r/rlidOutlookWelcomeMail10?clid=1033\">Cached Exchange Mode</a>", content);
+
+ // Link - check text around it, and the link itself
+ assertContains("sign up for a free subscription", content);
+ assertContains("Office Newsletter", content);
+ assertContains("newsletter will be sent to you", content);
+ assertContains("http://r.office.microsoft.com/r/rlidNewsletterSignUp?clid=1033", content);
+
+ // Make sure we don't have nested html docs
+ assertEquals(2, content.split("<body>").length);
+ assertEquals(2, content.split("<\\/body>").length);
+ }
+}
Added: tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java
URL: http://svn.apache.org/viewvc/tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java?rev=1723223&view=auto
==============================================================================
--- tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java (added)
+++ tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/POIContainerExtractionTest.java Wed Jan 6 03:50:50 2016
@@ -0,0 +1,345 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.tika.parser.microsoft;
+
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertNull;
+import static org.junit.Assert.assertTrue;
+
+import org.apache.tika.TikaTest.TrackingHandler;
+import org.apache.tika.extractor.ContainerExtractor;
+import org.apache.tika.extractor.ParserContainerExtractor;
+import org.apache.tika.mime.MediaType;
+import org.junit.Test;
+
+/**
+ * Tests that the various POI powered parsers are
+ * able to extract their embedded contents.
+ */
+public class POIContainerExtractionTest extends AbstractPOIContainerExtractionTest {
+
+ /**
+ * For office files which don't have anything embedded in them
+ */
+ @Test
+ public void testWithoutEmbedded() throws Exception {
+ ContainerExtractor extractor = new ParserContainerExtractor();
+
+ String[] files = new String[]{
+ "testEXCEL.xls", "testWORD.doc", "testPPT.ppt",
+ "testVISIO.vsd", "test-outlook.msg"
+ };
+ for (String file : files) {
+ // Process it without recursing
+ TrackingHandler handler = process(file, extractor, false);
+
+ // Won't have fired
+ assertEquals(0, handler.filenames.size());
+ assertEquals(0, handler.mediaTypes.size());
+
+ // Ditto with recursing
+ handler = process(file, extractor, true);
+ assertEquals(0, handler.filenames.size());
+ assertEquals(0, handler.mediaTypes.size());
+ }
+ }
+
+ /**
+ * Office files with embedded images, but no other
+ * office files in them
+ */
+ @Test
+ public void testEmbeddedImages() throws Exception {
+ ContainerExtractor extractor = new ParserContainerExtractor();
+ TrackingHandler handler;
+
+ // Excel with 1 image
+ handler = process("testEXCEL_1img.xls", extractor, false);
+ assertEquals(1, handler.filenames.size());
+ assertEquals(1, handler.mediaTypes.size());
+
+ assertEquals(null, handler.filenames.get(0));
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(0));
+
+
+ // PowerPoint with 2 images + sound
+ // TODO
+
+
+ // Word with 1 image
+ handler = process("testWORD_1img.doc", extractor, false);
+ assertEquals(1, handler.filenames.size());
+ assertEquals(1, handler.mediaTypes.size());
+
+ assertEquals("image1.png", handler.filenames.get(0));
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(0));
+
+
+ // Word with 3 images
+ handler = process("testWORD_3imgs.doc", extractor, false);
+ assertEquals(3, handler.filenames.size());
+ assertEquals(3, handler.mediaTypes.size());
+
+ assertEquals("image1.png", handler.filenames.get(0));
+ assertEquals("image2.jpg", handler.filenames.get(1));
+ assertEquals("image3.png", handler.filenames.get(2));
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(0));
+ assertEquals(TYPE_JPG, handler.mediaTypes.get(1));
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(2));
+ }
+
+ /**
+ * Office files which have other office files
+ * embedded into them. The embedded office files
+ * will sometimes have images in them.
+ * <p/>
+ * eg xls
+ * -> word
+ * -> image
+ * -> image
+ * -> powerpoint
+ * -> excel
+ * -> image
+ */
+ @Test
+ public void testEmbeddedOfficeFiles() throws Exception {
+ ContainerExtractor extractor = new ParserContainerExtractor();
+ TrackingHandler handler;
+
+
+ // Excel with a word doc and a powerpoint doc, both of which have images in them
+ // Without recursion, should see both documents + the images
+ handler = process("testEXCEL_embeded.xls", extractor, false);
+ assertEquals(5, handler.filenames.size());
+ assertEquals(5, handler.mediaTypes.size());
+
+ // We don't know their filenames
+ assertEquals(null, handler.filenames.get(0));
+ assertEquals(null, handler.filenames.get(1));
+ assertEquals(null, handler.filenames.get(2));
+ assertEquals("MBD0003271D.ppt", handler.filenames.get(3));
+ assertEquals("MBD00032A24.doc", handler.filenames.get(4));
+ // But we do know their types
+ assertEquals(TYPE_EMF, handler.mediaTypes.get(0)); // Icon of embedded office doc
+ assertEquals(TYPE_EMF, handler.mediaTypes.get(1)); // Icon of embedded office doc
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(2)); // Embedded image
+ assertEquals(TYPE_PPT, handler.mediaTypes.get(3)); // Embedded office doc
+ assertEquals(TYPE_DOC, handler.mediaTypes.get(4)); // Embedded office doc
+
+
+ // With recursion, should get the images embedded in the office files too
+ handler = process("testEXCEL_embeded.xls", extractor, true);
+ assertEquals(17, handler.filenames.size());
+ assertEquals(17, handler.mediaTypes.size());
+
+ assertEquals(null, handler.filenames.get(0));
+ assertEquals(null, handler.filenames.get(1));
+ assertEquals(null, handler.filenames.get(2));
+ assertEquals("MBD0003271D.ppt", handler.filenames.get(3));
+ assertEquals("1", handler.filenames.get(4));
+ assertEquals(null, handler.filenames.get(5));
+ assertEquals("2", handler.filenames.get(6));
+ assertEquals("image1.png", handler.filenames.get(7));
+ assertEquals("image2.jpg", handler.filenames.get(8));
+ assertEquals("image3.png", handler.filenames.get(9));
+ assertEquals("image1.png", handler.filenames.get(16));
+
+ assertEquals(TYPE_EMF, handler.mediaTypes.get(0)); // Icon of embedded office doc
+ assertEquals(TYPE_EMF, handler.mediaTypes.get(1)); // Icon of embedded office doc
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(2)); // Embedded image
+ assertEquals(TYPE_PPT, handler.mediaTypes.get(3)); // Embedded presentation
+ assertEquals(TYPE_XLS, handler.mediaTypes.get(4)); // Embedded XLS
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(5)); // Embedded image
+ assertEquals(TYPE_DOC, handler.mediaTypes.get(6)); // Embedded office doc
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(7)); // Embedded image
+ assertEquals(TYPE_JPG, handler.mediaTypes.get(8)); // Embedded image
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(9)); // Embedded image
+ assertEquals(TYPE_DOC, handler.mediaTypes.get(15)); // Embedded office doc
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(16)); // Embedded image
+
+ // Word with .docx, powerpoint and excel
+ handler = process("testWORD_embeded.doc", extractor, false);
+ assertEquals(9, handler.filenames.size());
+ assertEquals(9, handler.mediaTypes.size());
+
+ // Filenames are a bit iffy...
+ // Should really be 3*embedded pictures then 3*icons then embedded docs
+ assertEquals("image1.emf", handler.filenames.get(0));
+ assertEquals("image4.png", handler.filenames.get(1));
+ assertEquals("image5.jpg", handler.filenames.get(2));
+ assertEquals("image6.png", handler.filenames.get(3));
+ assertEquals("image2.emf", handler.filenames.get(4));
+ assertEquals("image3.emf", handler.filenames.get(5));
+ assertEquals(null, handler.filenames.get(6));
+ assertEquals("_1345471035.ppt", handler.filenames.get(7));
+ assertEquals("_1345470949.xls", handler.filenames.get(8));
+
+ // But we do know their types
+ assertEquals(TYPE_EMF, handler.mediaTypes.get(0)); // Icon of embedded office doc?
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(1)); // Embedded image - logo
+ assertEquals(TYPE_JPG, handler.mediaTypes.get(2)); // Embedded image - safe
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(3)); // Embedded image - try
+ assertEquals(TYPE_EMF, handler.mediaTypes.get(4)); // Icon of embedded office doc?
+ assertEquals(TYPE_EMF, handler.mediaTypes.get(5)); // Icon of embedded office doc?
+ assertEquals(TYPE_DOCX, handler.mediaTypes.get(6)); // Embedded office doc
+ assertEquals(TYPE_PPT, handler.mediaTypes.get(7)); // Embedded office doc
+ assertEquals(TYPE_XLS, handler.mediaTypes.get(8)); // Embedded office doc
+
+
+ // With recursion, should get their images too
+ handler = process("testWORD_embeded.doc", extractor, true);
+ assertEquals(16, handler.filenames.size());
+ assertEquals(16, handler.mediaTypes.size());
+
+ // We don't know their filenames, except for doc images + docx
+ assertEquals("image1.emf", handler.filenames.get(0));
+ assertEquals("image4.png", handler.filenames.get(1));
+ assertEquals("image5.jpg", handler.filenames.get(2));
+ assertEquals("image6.png", handler.filenames.get(3));
+ assertEquals("image2.emf", handler.filenames.get(4));
+ assertEquals("image3.emf", handler.filenames.get(5));
+ assertEquals(null, handler.filenames.get(6));
+ assertEquals("image2.png", handler.filenames.get(7));
+ assertEquals("image3.jpeg", handler.filenames.get(8));
+ assertEquals("image4.png", handler.filenames.get(9));
+ for (int i = 11; i < 14; i++) {
+ assertNull(handler.filenames.get(i));
+ }
+ // But we do know their types
+ assertEquals(TYPE_EMF, handler.mediaTypes.get(0)); // Icon of embedded office doc
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(1)); // Embedded image - logo
+ assertEquals(TYPE_JPG, handler.mediaTypes.get(2)); // Embedded image - safe
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(3)); // Embedded image - try
+ assertEquals(TYPE_EMF, handler.mediaTypes.get(4)); // Icon of embedded office doc
+ assertEquals(TYPE_EMF, handler.mediaTypes.get(5)); // Icon of embedded office doc
+ assertEquals(TYPE_DOCX, handler.mediaTypes.get(6)); // Embedded office doc
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(7)); // PNG inside .docx
+ assertEquals(TYPE_JPG, handler.mediaTypes.get(8)); // JPG inside .docx
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(9)); // PNG inside .docx
+ assertEquals(TYPE_PPT, handler.mediaTypes.get(10)); // Embedded office doc
+ assertEquals(TYPE_XLS, handler.mediaTypes.get(14)); // Embedded office doc
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(15)); // PNG inside .xls
+
+
+ // PowerPoint with excel and word
+ handler = process("testPPT_embeded.ppt", extractor, false);
+ assertEquals(7, handler.filenames.size());
+ assertEquals(7, handler.mediaTypes.size());
+
+ // We don't get all that helpful filenames
+ assertEquals("1", handler.filenames.get(0));
+ assertEquals("2", handler.filenames.get(1));
+ assertEquals(null, handler.filenames.get(2));
+ assertEquals(null, handler.filenames.get(3));
+ assertEquals(null, handler.filenames.get(4));
+ assertEquals(null, handler.filenames.get(5));
+ assertEquals(null, handler.filenames.get(6));
+ // But we do know their types
+ assertEquals(TYPE_XLS, handler.mediaTypes.get(0)); // Embedded office doc
+ assertEquals(TYPE_DOC, handler.mediaTypes.get(1)); // Embedded office doc
+ assertEquals(TYPE_EMF, handler.mediaTypes.get(2)); // Icon of embedded office doc
+ assertEquals(TYPE_EMF, handler.mediaTypes.get(3)); // Icon of embedded office doc
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(4)); // Embedded image
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(5)); // Embedded image
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(6)); // Embedded image
+
+ // Run again on PowerPoint but with recursion
+ handler = process("testPPT_embeded.ppt", extractor, true);
+ assertEquals(11, handler.filenames.size());
+ assertEquals(11, handler.mediaTypes.size());
+
+ assertEquals("1", handler.filenames.get(0));
+ assertEquals(null, handler.filenames.get(1));
+ assertEquals("2", handler.filenames.get(2));
+ assertEquals("image1.png", handler.filenames.get(3));
+ assertEquals("image2.jpg", handler.filenames.get(4));
+ assertEquals("image3.png", handler.filenames.get(5));
+ assertEquals(null, handler.filenames.get(6));
+ assertEquals(null, handler.filenames.get(7));
+ assertEquals(null, handler.filenames.get(8));
+ assertEquals(null, handler.filenames.get(9));
+ assertEquals(null, handler.filenames.get(10));
+
+ assertEquals(TYPE_XLS, handler.mediaTypes.get(0)); // Embedded office doc
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(1)); // PNG inside .xls
+ assertEquals(TYPE_DOC, handler.mediaTypes.get(2)); // Embedded office doc
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(3)); // PNG inside .docx
+ assertEquals(TYPE_JPG, handler.mediaTypes.get(4)); // JPG inside .docx
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(5)); // PNG inside .docx
+ assertEquals(TYPE_EMF, handler.mediaTypes.get(6)); // Icon of embedded office doc
+ assertEquals(TYPE_EMF, handler.mediaTypes.get(7)); // Icon of embedded office doc
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(8)); // Embedded image
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(9)); // Embedded image
+ assertEquals(TYPE_PNG, handler.mediaTypes.get(10)); // Embedded image
+
+
+ // Word, with a non-office file (PDF)
+ handler = process("testWORD_embedded_pdf.doc", extractor, true);
+ assertEquals(2, handler.filenames.size());
+ assertEquals(2, handler.mediaTypes.size());
+
+ assertEquals("image1.emf", handler.filenames.get(0));
+ assertEquals("_1402837031.pdf", handler.filenames.get(1));
+
+ assertEquals(TYPE_EMF, handler.mediaTypes.get(0)); // Icon of embedded pdf
+ assertEquals(TYPE_PDF, handler.mediaTypes.get(1)); // The embedded PDF itself
+
+
+ // Outlook with a text file and a word document
+ handler = process("testMSG_att_doc.msg", extractor, true);
+ assertEquals(2, handler.filenames.size());
+ assertEquals(2, handler.mediaTypes.size());
+
+ assertEquals("test-unicode.doc", handler.filenames.get(0));
+ assertEquals(TYPE_DOC, handler.mediaTypes.get(0));
+
+ assertEquals("pj1.txt", handler.filenames.get(1));
+ assertEquals(TYPE_TXT, handler.mediaTypes.get(1));
+
+
+ // Outlook with a pdf and another outlook message
+ handler = process("testMSG_att_msg.msg", extractor, true);
+ assertEquals(2, handler.filenames.size());
+ assertEquals(2, handler.mediaTypes.size());
+
+ assertEquals("__substg1.0_3701000D.msg", handler.filenames.get(0));
+ assertEquals(TYPE_MSG, handler.mediaTypes.get(0));
+
+ assertEquals("smbprn.00009008.KdcPjl.pdf", handler.filenames.get(1));
+ assertEquals(TYPE_PDF, handler.mediaTypes.get(1));
+ }
+
+ @Test
+ public void testEmbeddedOfficeFilesXML() throws Exception {
+ ContainerExtractor extractor = new ParserContainerExtractor();
+ TrackingHandler handler;
+
+ handler = process("EmbeddedDocument.docx", extractor, false);
+ assertTrue(handler.filenames.contains("Microsoft_Office_Excel_97-2003_Worksheet1.bin"));
+ assertEquals(2, handler.filenames.size());
+ }
+
+ @Test
+ public void testPowerpointImages() throws Exception {
+ ContainerExtractor extractor = new ParserContainerExtractor();
+ TrackingHandler handler;
+
+ handler = process("pictures.ppt", extractor, false);
+ assertTrue(handler.mediaTypes.contains(new MediaType("image", "jpeg")));
+ assertTrue(handler.mediaTypes.contains(new MediaType("image", "png")));
+ }
+}
Added: tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java
URL: http://svn.apache.org/viewvc/tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java?rev=1723223&view=auto
==============================================================================
--- tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java (added)
+++ tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/PowerPointParserTest.java Wed Jan 6 03:50:50 2016
@@ -0,0 +1,241 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ * <p/>
+ * http://www.apache.org/licenses/LICENSE-2.0
+ * <p/>
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.tika.parser.microsoft;
+
+import static org.junit.Assert.assertEquals;
+
+import java.io.InputStream;
+import java.util.Locale;
+
+import org.apache.tika.TikaTest;
+import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.Office;
+import org.apache.tika.metadata.OfficeOpenXMLCore;
+import org.apache.tika.metadata.TikaCoreProperties;
+import org.apache.tika.parser.ParseContext;
+import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
+import org.xml.sax.ContentHandler;
+
+public class PowerPointParserTest extends TikaTest {
+
+ @Test
+ public void testPowerPointParser() throws Exception {
+ try (InputStream input = PowerPointParserTest.class.getResourceAsStream(
+ "/test-documents/testPPT.ppt")) {
+ Metadata metadata = new Metadata();
+ ContentHandler handler = new BodyContentHandler();
+ new OfficeParser().parse(input, handler, metadata, new ParseContext());
+
+ assertEquals(
+ "application/vnd.ms-powerpoint",
+ metadata.get(Metadata.CONTENT_TYPE));
+ assertEquals("Sample Powerpoint Slide", metadata.get(TikaCoreProperties.TITLE));
+ assertEquals("Keith Bennett", metadata.get(TikaCoreProperties.CREATOR));
+ assertEquals("Keith Bennett", metadata.get(Metadata.AUTHOR));
+ String content = handler.toString();
+ assertContains("Sample Powerpoint Slide", content);
+ assertContains("Powerpoint X for Mac", content);
+ }
+ }
+
+ @Test
+ public void testVarious() throws Exception {
+ Metadata metadata = new Metadata();
+ String xml = getXML("testPPT_various.ppt", metadata).xml;
+ assertContains("<p>Footnote appears here", xml);
+ assertContains("<p>[1] This is a footnote.", xml);
+ assertContains("<p>This is the header text.</p>", xml);
+ assertContains("<p>This is the footer text.</p>", xml);
+ assertContains("<p>Here is a text box</p>", xml);
+ assertContains("<p>Bold ", xml);
+ assertContains("italic underline superscript subscript", xml);
+ assertContains("underline", xml);
+ assertContains("superscript", xml);
+ assertContains("subscript", xml);
+ assertContains("<p>Here is a citation:", xml);
+ assertContains("Figure 1 This is a caption for Figure 1", xml);
+ assertContains("(Kramer)", xml);
+ assertContains("<table><tr>\t<td>Row 1 Col 1</td>", xml);
+ assertContains("<td>Row 2 Col 2</td>\t<td>Row 2 Col 3</td></tr>", xml);
+ assertContains("<p>Row 1 column 1</p>", xml);
+ assertContains("<p>Row 2 column 2</p>", xml);
+ assertContains("<p>This is a hyperlink", xml);
+ assertContains("<p>Here is a list:", xml);
+ for(int row=1;row<=3;row++) {
+ //assertContains("·\tBullet " + row, content);
+ //assertContains("\u00b7\tBullet " + row, content);
+ assertContains("<p>Bullet " + row, xml);
+ }
+ assertContains("Here is a numbered list:", xml);
+ for(int row=1;row<=3;row++) {
+ //assertContains(row + ")\tNumber bullet " + row, content);
+ //assertContains(row + ") Number bullet " + row, content);
+ // TODO: OOXMLExtractor fails to number the bullets:
+ assertContains("<p>Number bullet " + row, xml);
+ }
+
+ for(int row=1;row<=2;row++) {
+ for(int col=1;col<=3;col++) {
+ assertContains("Row " + row + " Col " + col, xml);
+ }
+ }
+ assertContains("Keyword1 Keyword2", xml);
+ assertEquals("Keyword1 Keyword2",
+ metadata.get(TikaCoreProperties.KEYWORDS));
+
+ assertContains("Subject is here", xml);
+ assertEquals("Subject is here",
+ metadata.get(OfficeOpenXMLCore.SUBJECT));
+ // TODO: Remove subject in Tika 2.0
+ assertEquals("Subject is here",
+ metadata.get(Metadata.SUBJECT));
+
+ assertContains("Suddenly some Japanese text:", xml);
+ // Special version of (GHQ)
+ assertContains("\uff08\uff27\uff28\uff31\uff09", xml);
+ // 6 other characters
+ assertContains("\u30be\u30eb\u30b2\u3068\u5c3e\u5d0e\u3001\u6de1\u3005\u3068\u6700\u671f",
+ xml);
+
+ assertContains("And then some Gothic text:", xml);
+ assertContains("\uD800\uDF32\uD800\uDF3f\uD800\uDF44\uD800\uDF39\uD800\uDF43\uD800\uDF3A",
+ xml);
+ }
+
+ @Test
+ public void testMasterFooter() throws Exception {
+ ContentHandler handler = new BodyContentHandler();
+ Metadata metadata = new Metadata();
+
+ try (InputStream stream = PowerPointParserTest.class.getResourceAsStream(
+ "/test-documents/testPPT_masterFooter.ppt")) {
+ new OfficeParser().parse(stream, handler, metadata, new ParseContext());
+ }
+
+ String content = handler.toString();
+ assertContains("Master footer is here", content);
+
+ // Make sure boilerplate text didn't come through:
+ assertEquals(-1, content.indexOf("Click to edit Master"));
+
+ //TIKA-1171
+ assertEquals(-1, content.indexOf("*"));
+ }
+
+ /**
+ * TIKA-712 Master Slide Text from PPT and PPTX files
+ * should be extracted too
+ */
+ @Test
+ public void testMasterText() throws Exception {
+ ContentHandler handler = new BodyContentHandler();
+ Metadata metadata = new Metadata();
+
+ try (InputStream stream = PowerPointParserTest.class.getResourceAsStream(
+ "/test-documents/testPPT_masterText.ppt")) {
+ new OfficeParser().parse(stream, handler, metadata, new ParseContext());
+ }
+
+ String content = handler.toString();
+ assertContains("Text that I added to the master slide", content);
+
+ // Make sure boilerplate text didn't come through:
+ assertEquals(-1, content.indexOf("Click to edit Master"));
+
+ //TIKA-1171
+ assertEquals(-1, content.indexOf("*"));
+ }
+
+ @Test
+ public void testMasterText2() throws Exception {
+ ContentHandler handler = new BodyContentHandler();
+ Metadata metadata = new Metadata();
+
+ try (InputStream stream = PowerPointParserTest.class.getResourceAsStream(
+ "/test-documents/testPPT_masterText2.ppt")) {
+ new OfficeParser().parse(stream, handler, metadata, new ParseContext());
+ }
+
+ String content = handler.toString();
+ assertContains("Text that I added to the master slide", content);
+
+ // Make sure boilerplate text didn't come through:
+ assertEquals(-1, content.indexOf("Click to edit Master"));
+ //TIKA-1171
+ assertEquals(-1, content.indexOf("*"));
+ }
+
+ /**
+ * Ensures that custom OLE2 (HPSF) properties are extracted
+ */
+ @Test
+ public void testCustomProperties() throws Exception {
+ Metadata metadata = new Metadata();
+
+ try (InputStream input = PowerPointParserTest.class.getResourceAsStream(
+ "/test-documents/testPPT_custom_props.ppt")) {
+ ContentHandler handler = new BodyContentHandler(-1);
+ ParseContext context = new ParseContext();
+ context.set(Locale.class, Locale.US);
+ new OfficeParser().parse(input, handler, metadata, context);
+ }
+
+ assertEquals("application/vnd.ms-powerpoint", metadata.get(Metadata.CONTENT_TYPE));
+ assertEquals("JOUVIN ETIENNE", metadata.get(TikaCoreProperties.CREATOR));
+ assertEquals("EJ04325S", metadata.get(TikaCoreProperties.MODIFIER));
+ assertEquals("EJ04325S", metadata.get(Metadata.LAST_AUTHOR));
+ assertEquals("2011-08-22T13:32:58Z", metadata.get(TikaCoreProperties.MODIFIED));
+ assertEquals("2011-08-22T13:32:58Z", metadata.get(Metadata.DATE));
+ assertEquals("2011-08-22T13:30:53Z", metadata.get(TikaCoreProperties.CREATED));
+ assertEquals("2011-08-22T13:30:53Z", metadata.get(Metadata.CREATION_DATE));
+ assertEquals("1", metadata.get(Office.SLIDE_COUNT));
+ assertEquals("3", metadata.get(Office.WORD_COUNT));
+ assertEquals("Test extraction properties pptx", metadata.get(TikaCoreProperties.TITLE));
+ assertEquals("true", metadata.get("custom:myCustomBoolean"));
+ assertEquals("3", metadata.get("custom:myCustomNumber"));
+ assertEquals("MyStringValue", metadata.get("custom:MyCustomString"));
+ assertEquals("2010-12-30T22:00:00Z", metadata.get("custom:MyCustomDate"));
+ assertEquals("2010-12-29T22:00:00Z", metadata.get("custom:myCustomSecondDate"));
+ }
+
+ // TIKA-1025
+ @Test
+ public void testEmbeddedPlacedholder() throws Exception {
+ XMLResult result = getXML("testPPT_embedded2.ppt");
+ assertContains("<div class=\"embedded\" id=\"1\" />", result.xml);
+ assertContains("<div class=\"embedded\" id=\"14\" />", result.xml);
+ }
+
+ // TIKA-817
+ @Test
+ public void testAutoDatePPT() throws Exception {
+ //decision was made in POI-52367 not to generate
+ //autodate automatically. For pptx, where value is stored,
+ //value is extracted. For ppt, however, no date is extracted.
+ XMLResult result = getXML("testPPT_autodate.ppt");
+ assertContains(
+ "<div class=\"slide-content\"><p>Now</p>",
+ result.xml);
+ }
+
+ @Test
+ public void testCommentAuthorship() throws Exception {
+ XMLResult r = getXML("testPPT_comment.ppt");
+ assertContains("<p class=\"slide-comment\"><b>Allison, Timothy B. (ATB)", r.xml);
+ }
+}
Added: tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/ProjectParserTest.java
URL: http://svn.apache.org/viewvc/tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/ProjectParserTest.java?rev=1723223&view=auto
==============================================================================
--- tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/ProjectParserTest.java (added)
+++ tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/ProjectParserTest.java Wed Jan 6 03:50:50 2016
@@ -0,0 +1,93 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ * <p/>
+ * http://www.apache.org/licenses/LICENSE-2.0
+ * <p/>
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.tika.parser.microsoft;
+
+import static org.junit.Assert.assertEquals;
+
+import java.io.InputStream;
+
+import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.OfficeOpenXMLCore;
+import org.apache.tika.metadata.OfficeOpenXMLExtended;
+import org.apache.tika.metadata.TikaCoreProperties;
+import org.apache.tika.parser.ParseContext;
+import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
+import org.xml.sax.ContentHandler;
+
+/**
+ * Tests for Microsoft Project (MPP) Files.
+ *
+ * Note - we don't currently have a dedicated Project
+ * Parser, all we have is the common office metadata
+ */
+public class ProjectParserTest {
+
+ @Test
+ public void testProject2003() throws Exception {
+ try (InputStream input = ProjectParserTest.class.getResourceAsStream(
+ "/test-documents/testPROJECT2003.mpp")) {
+ doTestProject(input);
+ }
+ }
+
+ @Test
+ public void testProject2007() throws Exception {
+ try (InputStream input = ProjectParserTest.class.getResourceAsStream(
+ "/test-documents/testPROJECT2007.mpp")) {
+ doTestProject(input);
+ }
+ }
+
+ private void doTestProject(InputStream input) throws Exception {
+ Metadata metadata = new Metadata();
+ ContentHandler handler = new BodyContentHandler();
+ new OfficeParser().parse(input, handler, metadata, new ParseContext());
+
+ assertEquals(
+ "application/vnd.ms-project",
+ metadata.get(Metadata.CONTENT_TYPE));
+
+ assertEquals("The quick brown fox jumps over the lazy dog", metadata.get(TikaCoreProperties.TITLE));
+ assertEquals("Gym class featuring a brown fox and lazy dog", metadata.get(OfficeOpenXMLCore.SUBJECT));
+ assertEquals("Gym class featuring a brown fox and lazy dog", metadata.get(Metadata.SUBJECT));
+ assertEquals("Nevin Nollop", metadata.get(TikaCoreProperties.CREATOR));
+ assertEquals("", metadata.get(TikaCoreProperties.MODIFIER));
+ assertEquals("Pangram, fox, dog", metadata.get(TikaCoreProperties.KEYWORDS));
+ assertEquals("Comment Vulpes vulpes comment", metadata.get(TikaCoreProperties.COMMENTS));
+
+ assertEquals("Category1", metadata.get(OfficeOpenXMLCore.CATEGORY));
+ assertEquals("Mr Burns", metadata.get(OfficeOpenXMLExtended.MANAGER));
+ assertEquals("CompanyA", metadata.get(OfficeOpenXMLExtended.COMPANY));
+
+ assertEquals("2011-11-24T10:58:00Z", metadata.get(TikaCoreProperties.CREATED));
+ assertEquals("2011-11-24T10:58:00Z", metadata.get(Metadata.CREATION_DATE));
+ assertEquals("2011-11-24T11:31:00Z", metadata.get(TikaCoreProperties.MODIFIED));
+ assertEquals("2011-11-24T11:31:00Z", metadata.get(Metadata.DATE));
+
+ // Custom Project metadata is present with prefix
+ assertEquals("0%", metadata.get("custom:% Complete"));
+ assertEquals("0%", metadata.get("custom:% Work Complete"));
+ assertEquals("\u00a3" + "0.00", metadata.get("custom:Cost"));
+ assertEquals("2d?", metadata.get("custom:Duration"));
+ assertEquals("16h", metadata.get("custom:Work"));
+
+ // Currently, we don't do textual contents of the file
+ String content = handler.toString();
+ assertEquals("", content);
+ }
+}
Added: tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/PublisherParserTest.java
URL: http://svn.apache.org/viewvc/tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/PublisherParserTest.java?rev=1723223&view=auto
==============================================================================
--- tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/PublisherParserTest.java (added)
+++ tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/PublisherParserTest.java Wed Jan 6 03:50:50 2016
@@ -0,0 +1,53 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ * <p/>
+ * http://www.apache.org/licenses/LICENSE-2.0
+ * <p/>
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.tika.parser.microsoft;
+
+import static org.apache.tika.TikaTest.assertContains;
+import static org.junit.Assert.assertEquals;
+
+import java.io.InputStream;
+
+import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.TikaCoreProperties;
+import org.apache.tika.parser.ParseContext;
+import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
+import org.xml.sax.ContentHandler;
+
+public class PublisherParserTest {
+
+ @Test
+ public void testPublisherParser() throws Exception {
+ try (InputStream input = PublisherParserTest.class.getResourceAsStream(
+ "/test-documents/testPUBLISHER.pub")) {
+ Metadata metadata = new Metadata();
+ ContentHandler handler = new BodyContentHandler();
+ new OfficeParser().parse(input, handler, metadata, new ParseContext());
+
+ assertEquals(
+ "application/x-mspublisher",
+ metadata.get(Metadata.CONTENT_TYPE));
+ assertEquals(null, metadata.get(TikaCoreProperties.TITLE));
+ assertEquals("Nick Burch", metadata.get(TikaCoreProperties.CREATOR));
+ assertEquals("Nick Burch", metadata.get(Metadata.AUTHOR));
+ String content = handler.toString();
+ assertContains("0123456789", content);
+ assertContains("abcdef", content);
+ }
+ }
+
+}
Added: tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/TNEFParserTest.java
URL: http://svn.apache.org/viewvc/tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/TNEFParserTest.java?rev=1723223&view=auto
==============================================================================
--- tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/TNEFParserTest.java (added)
+++ tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/TNEFParserTest.java Wed Jan 6 03:50:50 2016
@@ -0,0 +1,98 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.tika.parser.microsoft;
+
+import static org.junit.Assert.assertEquals;
+
+import org.apache.tika.TikaTest.TrackingHandler;
+import org.apache.tika.detect.DefaultDetector;
+import org.apache.tika.detect.Detector;
+import org.apache.tika.extractor.ContainerExtractor;
+import org.apache.tika.extractor.ParserContainerExtractor;
+import org.apache.tika.io.TikaInputStream;
+import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.TikaCoreProperties;
+import org.apache.tika.mime.MediaType;
+import org.apache.tika.parser.ParseContext;
+import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
+import org.xml.sax.ContentHandler;
+
+/**
+ * Tests for the TNEF (winmail.dat) parser
+ */
+public class TNEFParserTest extends AbstractPOIContainerExtractionTest {
+ private static final String file = "testWINMAIL.dat";
+
+ @Test
+ public void testBasics() throws Exception {
+ Detector detector = new DefaultDetector();
+ try (TikaInputStream stream = getTestFile(file)) {
+ assertEquals(
+ MediaType.application("vnd.ms-tnef"),
+ detector.detect(stream, new Metadata()));
+ }
+ }
+
+ @Test
+ public void testMetadata() throws Exception {
+ TikaInputStream stream = getTestFile(file);
+
+ Metadata metadata = new Metadata();
+ ContentHandler handler = new BodyContentHandler();
+
+ TNEFParser tnef = new TNEFParser();
+ tnef.parse(stream, handler, metadata, new ParseContext());
+
+ assertEquals("This is a test message", metadata.get(TikaCoreProperties.TITLE));
+ assertEquals("This is a test message", metadata.get(Metadata.SUBJECT));
+ }
+
+ /**
+ * Check the Rtf and Attachments are returned
+ * as expected
+ */
+ @Test
+ public void testBodyAndAttachments() throws Exception {
+ ContainerExtractor extractor = new ParserContainerExtractor();
+
+ // Process it with recursing
+ // Will have the message body RTF and the attachments
+ TrackingHandler handler = process(file, extractor, true);
+ assertEquals(6, handler.filenames.size());
+ assertEquals(6, handler.mediaTypes.size());
+
+ // We know the filenames for all of them
+ assertEquals("message.rtf", handler.filenames.get(0));
+ assertEquals(MediaType.application("rtf"), handler.mediaTypes.get(0));
+
+ assertEquals("quick.doc", handler.filenames.get(1));
+ assertEquals(MediaType.application("msword"), handler.mediaTypes.get(1));
+
+ assertEquals("quick.html", handler.filenames.get(2));
+ assertEquals(MediaType.text("html"), handler.mediaTypes.get(2));
+
+ assertEquals("quick.pdf", handler.filenames.get(3));
+ assertEquals(MediaType.application("pdf"), handler.mediaTypes.get(3));
+
+ assertEquals("quick.txt", handler.filenames.get(4));
+ assertEquals(MediaType.text("plain"), handler.mediaTypes.get(4));
+
+ assertEquals("quick.xml", handler.filenames.get(5));
+ assertEquals(MediaType.application("xml"), handler.mediaTypes.get(5));
+ }
+}
Added: tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/VisioParserTest.java
URL: http://svn.apache.org/viewvc/tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/VisioParserTest.java?rev=1723223&view=auto
==============================================================================
--- tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/VisioParserTest.java (added)
+++ tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/VisioParserTest.java Wed Jan 6 03:50:50 2016
@@ -0,0 +1,51 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ * <p/>
+ * http://www.apache.org/licenses/LICENSE-2.0
+ * <p/>
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.tika.parser.microsoft;
+
+import static org.apache.tika.TikaTest.assertContains;
+import static org.junit.Assert.assertEquals;
+
+import java.io.InputStream;
+
+import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.TikaCoreProperties;
+import org.apache.tika.parser.ParseContext;
+import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
+import org.xml.sax.ContentHandler;
+
+public class VisioParserTest {
+
+ @Test
+ public void testVisioParser() throws Exception {
+ try (InputStream input = VisioParserTest.class.getResourceAsStream(
+ "/test-documents/testVISIO.vsd")) {
+ Metadata metadata = new Metadata();
+ ContentHandler handler = new BodyContentHandler();
+ new OfficeParser().parse(input, handler, metadata, new ParseContext());
+
+ assertEquals(
+ "application/vnd.visio",
+ metadata.get(Metadata.CONTENT_TYPE));
+ assertEquals("", metadata.get(TikaCoreProperties.TITLE));
+ assertEquals("Hogwarts", metadata.get(TikaCoreProperties.CREATOR));
+ String content = handler.toString();
+ assertContains("Some random text, on a page", content);
+ }
+ }
+
+}
Added: tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java
URL: http://svn.apache.org/viewvc/tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java?rev=1723223&view=auto
==============================================================================
--- tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java (added)
+++ tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java Wed Jan 6 03:50:50 2016
@@ -0,0 +1,496 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ * <p/>
+ * http://www.apache.org/licenses/LICENSE-2.0
+ * <p/>
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.tika.parser.microsoft;
+
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertFalse;
+import static org.junit.Assert.assertTrue;
+
+import java.io.InputStream;
+import java.util.Locale;
+
+import org.apache.log4j.Level;
+import org.apache.log4j.Logger;
+import org.apache.tika.TikaTest;
+import org.apache.tika.metadata.Metadata;
+import org.apache.tika.metadata.Office;
+import org.apache.tika.metadata.OfficeOpenXMLCore;
+import org.apache.tika.metadata.OfficeOpenXMLExtended;
+import org.apache.tika.metadata.TikaCoreProperties;
+import org.apache.tika.parser.ParseContext;
+import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Ignore;
+import org.junit.Test;
+import org.xml.sax.ContentHandler;
+
+public class WordParserTest extends TikaTest {
+
+ @Test
+ public void testWordParser() throws Exception {
+ try (InputStream input = WordParserTest.class.getResourceAsStream(
+ "/test-documents/testWORD.doc")) {
+ ContentHandler handler = new BodyContentHandler();
+ Metadata metadata = new Metadata();
+ new OfficeParser().parse(input, handler, metadata, new ParseContext());
+
+ assertEquals(
+ "application/msword",
+ metadata.get(Metadata.CONTENT_TYPE));
+ assertEquals("Sample Word Document", metadata.get(TikaCoreProperties.TITLE));
+ assertEquals("Keith Bennett", metadata.get(TikaCoreProperties.CREATOR));
+ assertEquals("Keith Bennett", metadata.get(Metadata.AUTHOR));
+ assertContains("Sample Word Document", handler.toString());
+ }
+ }
+
+ @Test
+ public void testWordWithWAV() throws Exception {
+ try (InputStream input = WordParserTest.class.getResourceAsStream(
+ "/test-documents/Doc1_ole.doc")) {
+ ContentHandler handler = new BodyContentHandler();
+ Metadata metadata = new Metadata();
+ new OfficeParser().parse(input, handler, metadata, new ParseContext());
+
+ assertContains("MSj00974840000[1].wav", handler.toString());
+ }
+ }
+
+ /**
+ * Test that the word converter is able to generate the
+ * correct HTML for the document
+ */
+ @Test
+ public void testWordHTML() throws Exception {
+
+ // Try with a document containing various tables and
+ // formattings
+ XMLResult result = getXML("testWORD.doc");
+ String xml = result.xml;
+ Metadata metadata = result.metadata;
+
+ assertEquals(
+ "application/msword",
+ metadata.get(Metadata.CONTENT_TYPE));
+ assertEquals("Sample Word Document", metadata.get(TikaCoreProperties.TITLE));
+ assertEquals("Keith Bennett", metadata.get(TikaCoreProperties.CREATOR));
+ assertEquals("Keith Bennett", metadata.get(Metadata.AUTHOR));
+ assertTrue(xml.contains("Sample Word Document"));
+
+ // Check that custom headings came through
+ assertTrue(xml.contains("<h1 class=\"title\">"));
+ // Regular headings
+ assertTrue(xml.contains("<h1>Heading Level 1</h1>"));
+ assertTrue(xml.contains("<h3>Heading Level 3</h3>"));
+ // Bold and italic
+ assertTrue(xml.contains("<b>BOLD</b>"));
+ assertTrue(xml.contains("<i>ITALIC</i>"));
+ // Table
+ assertTrue(xml.contains("<table>"));
+ assertTrue(xml.contains("<td>"));
+ // TODO - Check for the nested table
+ // Links
+ assertTrue(xml.contains("<a href=\"http://tika.apache.org/\">Tika</a>"));
+ // Paragraphs with other styles
+ assertTrue(xml.contains("<p class=\"signature\">This one"));
+
+ // Try with a document that contains images
+ xml = getXML("testWORD_3imgs.doc").xml;
+
+ // Images 1-3
+ assertTrue("Image not found in:\n" + xml, xml.contains("src=\"embedded:image1.png\""));
+ assertTrue("Image not found in:\n" + xml, xml.contains("src=\"embedded:image2.jpg\""));
+ assertTrue("Image not found in:\n" + xml, xml.contains("src=\"embedded:image3.png\""));
+
+ // Text too
+ assertTrue(xml.contains("<p>The end!"));
+
+ // TIKA-692: test document containing multiple
+ // character runs within a bold tag:
+ xml = getXML("testWORD_bold_character_runs.doc").xml;
+
+ // Make sure bold text arrived as single
+ // contiguous string even though Word parser
+ // handled this as 3 character runs
+ assertTrue("Bold text wasn't contiguous: " + xml, xml.contains("F<b>oob</b>a<b>r</b>"));
+
+ // TIKA-692: test document containing multiple
+ // character runs within a bold tag:
+ xml = getXML("testWORD_bold_character_runs2.doc").xml;
+
+ // Make sure bold text arrived as single
+ // contiguous string even though Word parser
+ // handled this as 3 character runs
+ assertTrue("Bold text wasn't contiguous: " + xml, xml.contains("F<b>oob</b>a<b>r</b>"));
+ }
+
+ @Test
+ public void testEmbeddedNames() throws Exception {
+ String result = getXML("testWORD_embedded_pdf.doc").xml;
+
+ // Make sure the embedded div comes out after "Here
+ // is the pdf file" and before "Bye Bye":
+ int i = result.indexOf("Here is the pdf file:");
+ assertTrue(i != -1);
+ int j = result.indexOf("<div class=\"embedded\" id=\"_1402837031\" />");
+ assertTrue(j != -1);
+ int k = result.indexOf("Bye Bye");
+ assertTrue(k != -1);
+
+ assertTrue(i < j);
+ assertTrue(j < k);
+ }
+
+ // TIKA-982
+ @Test
+ public void testEmbeddedRTF() throws Exception {
+ String result = getXML("testWORD_embedded_rtf.doc").xml;
+ assertTrue(result.contains("<div class=\"embedded\" id=\"_1404039792\" />"));
+ assertTrue(result.contains("_1404039792.rtf"));
+ }
+
+ // TIKA-1019
+ @Test
+ public void testDocumentLink() throws Exception {
+ String result = getXML("testDocumentLink.doc").xml;
+ assertTrue(result.contains("<div class=\"embedded\" id=\"_1327495610\" />"));
+ assertTrue(result.contains("_1327495610.unknown"));
+ }
+
+ @Test
+ public void testWord6Parser() throws Exception {
+ try (InputStream input = WordParserTest.class.getResourceAsStream(
+ "/test-documents/testWORD6.doc")) {
+ ContentHandler handler = new BodyContentHandler();
+ Metadata metadata = new Metadata();
+ new OfficeParser().parse(input, handler, metadata, new ParseContext());
+
+ assertEquals(
+ "application/msword",
+ metadata.get(Metadata.CONTENT_TYPE));
+ assertEquals("The quick brown fox jumps over the lazy dog", metadata.get(TikaCoreProperties.TITLE));
+ assertEquals("Gym class featuring a brown fox and lazy dog", metadata.get(OfficeOpenXMLCore.SUBJECT));
+ assertEquals("Gym class featuring a brown fox and lazy dog", metadata.get(Metadata.SUBJECT));
+ assertEquals("Nevin Nollop", metadata.get(TikaCoreProperties.CREATOR));
+ assertEquals("Nevin Nollop", metadata.get(Metadata.AUTHOR));
+ assertContains("The quick brown fox jumps over the lazy dog", handler.toString());
+ }
+ }
+
+ @Test
+ public void testVarious() throws Exception {
+ ContentHandler handler = new BodyContentHandler();
+ Metadata metadata = new Metadata();
+
+ try (InputStream stream = WordParserTest.class.getResourceAsStream(
+ "/test-documents/testWORD_various.doc")) {
+ new OfficeParser().parse(stream, handler, metadata, new ParseContext());
+ }
+
+ String content = handler.toString();
+ //content = content.replaceAll("\\s+"," ");
+ assertContains("Footnote appears here", content);
+ assertContains("This is a footnote.", content);
+ assertContains("This is the header text.", content);
+ assertContains("This is the footer text.", content);
+ assertContains("Here is a text box", content);
+ assertContains("Bold", content);
+ assertContains("italic", content);
+ assertContains("underline", content);
+ assertContains("superscript", content);
+ assertContains("subscript", content);
+ assertContains("Here is a citation:", content);
+ assertContains("Figure 1 This is a caption for Figure 1", content);
+ assertContains("(Kramer)", content);
+ assertContains("Row 1 Col 1 Row 1 Col 2 Row 1 Col 3 Row 2 Col 1 Row 2 Col 2 Row 2 Col 3", content.replaceAll("\\s+"," "));
+ assertContains("Row 1 column 1 Row 2 column 1 Row 1 column 2 Row 2 column 2", content.replaceAll("\\s+"," "));
+ assertContains("This is a hyperlink", content);
+ assertContains("Here is a list:", content);
+ for(int row=1;row<=3;row++) {
+ //assertContains("·\tBullet " + row, content);
+ //assertContains("\u00b7\tBullet " + row, content);
+ assertContains("Bullet " + row, content);
+ }
+ assertContains("Here is a numbered list:", content);
+ for(int row=1;row<=3;row++) {
+ //assertContains(row + ")\tNumber bullet " + row, content);
+ //assertContains(row + ") Number bullet " + row, content);
+ // TODO: WordExtractor fails to number the bullets:
+ assertContains("Number bullet " + row, content);
+ }
+
+ for(int row=1;row<=2;row++) {
+ for(int col=1;col<=3;col++) {
+ assertContains("Row " + row + " Col " + col, content);
+ }
+ }
+
+ assertContains("Keyword1 Keyword2", content);
+ assertEquals("Keyword1 Keyword2",
+ metadata.get(TikaCoreProperties.KEYWORDS));
+
+ assertContains("Subject is here", content);
+ // TODO: Move to OO subject in Tika 2.0
+ assertEquals("Subject is here",
+ metadata.get(Metadata.SUBJECT));
+ assertEquals("Subject is here",
+ metadata.get(OfficeOpenXMLCore.SUBJECT));
+
+ assertContains("Suddenly some Japanese text:", content);
+ // Special version of (GHQ)
+ assertContains("\uff08\uff27\uff28\uff31\uff09", content);
+ // 6 other characters
+ assertContains("\u30be\u30eb\u30b2\u3068\u5c3e\u5d0e\u3001\u6de1\u3005\u3068\u6700\u671f", content);
+
+ assertContains("And then some Gothic text:", content);
+ assertContains("\uD800\uDF32\uD800\uDF3f\uD800\uDF44\uD800\uDF39\uD800\uDF43\uD800\uDF3A", content);
+ }
+
+ /**
+ * TIKA-1044 - Handle documents where parts of the
+ * text have no formatting or styles applied to them
+ */
+ @Test
+ public void testNoFormat() throws Exception {
+ ContentHandler handler = new BodyContentHandler();
+ Metadata metadata = new Metadata();
+
+ try (InputStream stream = WordParserTest.class.getResourceAsStream(
+ "/test-documents/testWORD_no_format.doc")) {
+ new OfficeParser().parse(stream, handler, metadata, new ParseContext());
+ }
+
+ String content = handler.toString();
+ assertContains("Will generate an exception", content);
+ }
+
+ /**
+ * Ensures that custom OLE2 (HPSF) properties are extracted
+ */
+ @Test
+ public void testCustomProperties() throws Exception {
+ Metadata metadata = new Metadata();
+
+ try (InputStream input = WordParserTest.class.getResourceAsStream(
+ "/test-documents/testWORD_custom_props.doc")) {
+ ContentHandler handler = new BodyContentHandler(-1);
+ ParseContext context = new ParseContext();
+ context.set(Locale.class, Locale.US);
+ new OfficeParser().parse(input, handler, metadata, context);
+ }
+
+ assertEquals("application/msword", metadata.get(Metadata.CONTENT_TYPE));
+ assertEquals("EJ04325S", metadata.get(TikaCoreProperties.CREATOR));
+ assertEquals("Etienne Jouvin", metadata.get(TikaCoreProperties.MODIFIER));
+ assertEquals("Etienne Jouvin", metadata.get(Metadata.LAST_AUTHOR));
+ assertEquals("2012-01-03T22:14:00Z", metadata.get(TikaCoreProperties.MODIFIED));
+ assertEquals("2012-01-03T22:14:00Z", metadata.get(Metadata.DATE));
+ assertEquals("2010-10-05T09:03:00Z", metadata.get(TikaCoreProperties.CREATED));
+ assertEquals("2010-10-05T09:03:00Z", metadata.get(Metadata.CREATION_DATE));
+ assertEquals("Microsoft Office Word", metadata.get(OfficeOpenXMLExtended.APPLICATION));
+ assertEquals("1", metadata.get(Office.PAGE_COUNT));
+ assertEquals("2", metadata.get(Office.WORD_COUNT));
+ assertEquals("My Title", metadata.get(TikaCoreProperties.TITLE));
+ assertEquals("My Keyword", metadata.get(TikaCoreProperties.KEYWORDS));
+ assertEquals("Normal.dotm", metadata.get(OfficeOpenXMLExtended.TEMPLATE));
+ assertEquals("My Comments", metadata.get(TikaCoreProperties.COMMENTS));
+ // TODO: Move to OO subject in Tika 2.0
+ assertEquals("My subject", metadata.get(Metadata.SUBJECT));
+ assertEquals("My subject", metadata.get(OfficeOpenXMLCore.SUBJECT));
+ assertEquals("EDF-DIT", metadata.get(OfficeOpenXMLExtended.COMPANY));
+ assertEquals("MyStringValue", metadata.get("custom:MyCustomString"));
+ assertEquals("2010-12-30T23:00:00Z", metadata.get("custom:MyCustomDate"));
+ }
+
+ @Test
+ public void testExceptions1() throws Exception {
+ XMLResult xml;
+ Level logLevelStart = Logger.getRootLogger().getLevel();
+ Logger.getRootLogger().setLevel(Level.ERROR);
+ try {
+ xml = getXML("testException1.doc");
+ assertContains("total population", xml.xml);
+ xml = getXML("testException2.doc");
+ assertContains("electric charge", xml.xml);
+ } finally {
+ Logger.getRootLogger().setLevel(logLevelStart);
+ }
+ }
+
+ @Test
+ public void testTabularSymbol() throws Exception {
+ assertContains("one two", getXML("testWORD_tabular_symbol.doc").xml.replaceAll("\\s+", " "));
+ }
+
+ /**
+ * TIKA-1229 Hyperlinks in Headers should be output as such,
+ * not plain text with control characters
+ */
+ @Test
+ public void testHeaderHyperlinks() throws Exception {
+ XMLResult result = getXML("testWORD_header_hyperlink.doc");
+ String xml = result.xml;
+ Metadata metadata = result.metadata;
+
+ assertEquals(
+ "application/msword",
+ metadata.get(Metadata.CONTENT_TYPE));
+ assertEquals("Lutz Theurer", metadata.get(TikaCoreProperties.CREATOR));
+ assertContains("example.com", xml);
+
+ // Check we don't have the special text HYPERLINK
+ assertFalse(xml.contains("HYPERLINK"));
+
+ // Check we do have the link
+ assertContains("<a href=\"http://tw-systemhaus.de\">http:", xml);
+
+ // Check we do have the email
+ assertContains("<a href=\"mailto:ab@example.com\">ab@", xml);
+ }
+
+ @Test
+ public void testControlCharacter() throws Exception {
+ assertContains("1. Introduzione<b> </a></b> </p>", getXML("testControlCharacters.doc").xml.replaceAll("\\s+", " "));
+ }
+
+ @Test
+ public void testParagraphsAfterTables() throws Exception {
+ XMLResult result = getXML("test_TIKA-1251.doc");
+
+ String xml = result.xml;
+ Metadata metadata = result.metadata;
+
+ assertEquals(
+ "application/msword",
+ metadata.get(Metadata.CONTENT_TYPE));
+
+ assertContains("<p>1. Organisering av vakten:</p>", xml);
+
+ }
+
+ @Test
+ public void testHyperlinkStringIOOBESmartQuote() throws Exception {
+ //TIKA-1512, one cause: closing double quote is a smart quote
+ //test file contributed by user
+ XMLResult result = getXML("testWORD_closingSmartQInHyperLink.doc");
+ assertContains("href=\"https://issues.apache.org/jira/browse/TIKA-1512", result.xml);
+ }
+
+ @Test
+ @Ignore //until we determine whether we can include test docs or not
+ public void testHyperlinkStringLongNoCloseQuote() throws Exception {
+ //TIKA-1512, one cause: no closing quote on really long string
+ //test file derived from govdocs1 012152.doc
+ XMLResult result = getXML("testWORD_longHyperLinkNoCloseQuote.doc");
+ assertContains("href=\"http://www.lexis.com", result.xml);
+ }
+
+ @Test
+ @Ignore //until we determine whether we can include test docs or not
+ public void testHyperlinkStringLongCarriageReturn() throws Exception {
+ //TIKA-1512, one cause: no closing quote, but carriage return
+ //test file derived from govdocs1 040044.doc
+ XMLResult result = getXML("testWORD_hyperLinkCarriageReturn.doc");
+ assertContains("href=\"http://www.nib.org", result.xml);
+ }
+
+ @Test
+ public void testDOCParagraphNumbering() throws Exception {
+ String xml = getXML("testWORD_numbered_list.doc").xml;
+ assertContains("1) This", xml);
+ assertContains("a) Is", xml);
+ assertContains("i) A multi", xml);
+ assertContains("ii) Level", xml);
+ assertContains("1. Within cell 1", xml);
+ assertContains("b. Cell b", xml);
+ assertContains("iii) List", xml);
+ assertContains("2) foo", xml);
+ assertContains("ii) baz", xml);
+ assertContains("ii) foo", xml);
+ assertContains("II. bar", xml);
+ assertContains("6. six", xml);
+ assertContains("7. seven", xml);
+ assertContains("a. seven a", xml);
+ assertContains("e. seven e", xml);
+ assertContains("2. A ii 2", xml);
+ assertContains("3. page break list 3", xml);
+ assertContains("Some-1-CrazyFormat Greek numbering with crazy format - alpha", xml);
+ assertContains("1.1.1. 1.1.1", xml);
+ assertContains("1.1. 1.2->1.1 //set the value", xml);
+
+ assertContains("add a list here", xml);
+ //TODO: not currently pulling numbers out of comments
+ assertContains(">comment list 1", xml);
+
+ }
+
+ @Test
+ public void testDOCOverrideParagraphNumbering() throws Exception {
+ String xml = getXML("testWORD_override_list_numbering.doc").xml;
+
+ //Test 1
+ assertContains("1.1.1.1...1 1.1.1.1...1", xml);
+ assertContains("1st.2.3someText 1st.2.3someText", xml);
+ assertContains("1st.2.2someOtherText.1 1st.2.2someOtherText.1", xml);
+ assertContains("5th 5th", xml);
+
+
+ //Test 2
+ assertContains("1.a.I 1.a.I", xml);
+ //test no reset because level 2 is not sufficient to reset
+ assertContains("1.b.III 1.b.III", xml);
+ //test restarted because of level 0's increment to 2
+ assertContains("2.a.I 2.a.I", xml);
+ //test handling of skipped level
+ assertContains("2.b 2.b", xml);
+
+ //Test 3
+ assertContains("(1)) (1))", xml);
+ //tests start level 1 at 17 and
+ assertContains("2.17 2.17", xml);
+ //tests that isLegal turns everything into decimal
+ assertContains("2.18.2.1 2.18.2.1", xml);
+ assertContains(">2 2", xml);
+
+ //Test4
+ assertContains(">1 1", xml);
+ assertContains(">A A", xml);
+ assertContains(">B B", xml);
+ assertContains(">C C", xml);
+ assertContains(">4 4", xml);
+
+ //Test5
+ assertContains(">00 00", xml);
+ assertContains(">01 01", xml);
+ assertContains(">01. 01.", xml);
+ assertContains(">01..1 01..1", xml);
+ assertContains(">02 02", xml);
+ }
+
+ @Test
+ public void testMultiAuthorsManagers() throws Exception {
+ XMLResult r = getXML("testWORD_multi_authors.doc");
+ String[] authors = r.metadata.getValues(TikaCoreProperties.CREATOR);
+ assertEquals(3, authors.length);
+ assertEquals("author2", authors[1]);
+
+ String[] managers = r.metadata.getValues(OfficeOpenXMLExtended.MANAGER);
+ assertEquals(2, managers.length);
+ assertEquals("manager1", managers[0]);
+ assertEquals("manager2", managers[1]);
+ }
+}
+
Added: tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/WriteProtectedParserTest.java
URL: http://svn.apache.org/viewvc/tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/WriteProtectedParserTest.java?rev=1723223&view=auto
==============================================================================
--- tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/WriteProtectedParserTest.java (added)
+++ tika/branches/2.x/tika-parser-modules/tika-office-module/src/test/java/org/apache/tika/parser/microsoft/WriteProtectedParserTest.java Wed Jan 6 03:50:50 2016
@@ -0,0 +1,42 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.tika.parser.microsoft;
+
+import static org.apache.tika.TikaTest.assertContains;
+
+import java.io.InputStream;
+
+import org.apache.tika.metadata.Metadata;
+import org.apache.tika.parser.ParseContext;
+import org.apache.tika.sax.BodyContentHandler;
+import org.junit.Test;
+import org.xml.sax.ContentHandler;
+
+public class WriteProtectedParserTest {
+
+ @Test
+ public void testWriteProtected() throws Exception {
+ InputStream input = ExcelParserTest.class.getResourceAsStream(
+ "/test-documents/protect.xlsx");
+
+ Metadata metadata = new Metadata();
+ ContentHandler handler = new BodyContentHandler();
+ new OfficeParser().parse(input, handler, metadata, new ParseContext());
+ String content = handler.toString();
+ assertContains("Office", content);
+ }
+}