]> source.dussan.org Git - poi.git/commitdiff
* Verify some more Text-Extraction features as part of integration tests, fix some...
authorDominik Stadler <centic@apache.org>
Fri, 27 Feb 2015 14:58:41 +0000 (14:58 +0000)
committerDominik Stadler <centic@apache.org>
Fri, 27 Feb 2015 14:58:41 +0000 (14:58 +0000)
* Also handle a XLSX which does not have row-numbers in the sheet-xml. Excel can read it so it makes sense to also allow to read it in the XSSFSheetXMLHandler
* Remove some Eclipse warnings in test-code

git-svn-id: https://svn.apache.org/repos/asf/poi/trunk@1662691 13f79535-47bb-0310-9956-ffa450edef68

12 files changed:
src/integrationtest/org/apache/poi/stress/AbstractFileHandler.java
src/integrationtest/org/apache/poi/stress/HPSFFileHandler.java
src/integrationtest/org/apache/poi/stress/XSSFFileHandler.java
src/java/org/apache/poi/hpsf/extractor/HPSFPropertiesExtractor.java
src/java/org/apache/poi/hssf/eventusermodel/HSSFEventFactory.java
src/ooxml/java/org/apache/poi/POIXMLPropertiesTextExtractor.java
src/ooxml/java/org/apache/poi/extractor/ExtractorFactory.java
src/ooxml/java/org/apache/poi/xssf/eventusermodel/XSSFSheetXMLHandler.java
src/ooxml/testcases/org/apache/poi/xssf/extractor/TestXSSFEventBasedExcelExtractor.java
src/testcases/org/apache/poi/hpsf/extractor/TestHPSFPropertiesExtractor.java
src/testcases/org/apache/poi/hssf/eventusermodel/TestHSSFEventFactory.java
src/testcases/org/apache/poi/hssf/extractor/TestExcelExtractor.java

index d7e303e4a8cc92f1cd8b71daaa0c6c8a8616ad79..8a27e6d0e9c2c39da95b992d0c51f4620eb790e8 100644 (file)
 ==================================================================== */\r
 package org.apache.poi.stress;\r
 \r
+import static org.junit.Assert.assertEquals;\r
 import static org.junit.Assert.assertFalse;\r
 import static org.junit.Assert.assertNotNull;\r
 \r
 import java.io.File;\r
+import java.io.FileInputStream;\r
+import java.io.FileNotFoundException;\r
+import java.io.IOException;\r
+import java.io.InputStream;\r
 import java.util.HashSet;\r
 import java.util.Set;\r
 \r
 import org.apache.poi.POITextExtractor;\r
 import org.apache.poi.extractor.ExtractorFactory;\r
+import org.apache.poi.openxml4j.exceptions.InvalidFormatException;\r
+import org.apache.poi.openxml4j.exceptions.OpenXML4JException;\r
+import org.apache.xmlbeans.XmlException;\r
 \r
 public abstract class AbstractFileHandler implements FileHandler {\r
     public static final Set<String> EXPECTED_EXTRACTOR_FAILURES = new HashSet<String>();\r
@@ -48,6 +56,22 @@ public abstract class AbstractFileHandler implements FileHandler {
     }\r
 \r
     public void handleExtracting(File file) throws Exception {\r
+        boolean before = ExtractorFactory.getThreadPrefersEventExtractors();\r
+        try {\r
+            ExtractorFactory.setThreadPrefersEventExtractors(true);\r
+            handleExtractingInternal(file);\r
+\r
+            ExtractorFactory.setThreadPrefersEventExtractors(false);\r
+            handleExtractingInternal(file);\r
+        } finally {\r
+            ExtractorFactory.setThreadPrefersEventExtractors(before);\r
+        }\r
+    }\r
+\r
+    private void handleExtractingInternal(File file) throws Exception {\r
+        long length = file.length();\r
+        long modified = file.lastModified();\r
+        \r
         POITextExtractor extractor = ExtractorFactory.createExtractor(file);\r
         try  {\r
             assertNotNull(extractor);\r
@@ -60,6 +84,11 @@ public abstract class AbstractFileHandler implements FileHandler {
 \r
             assertFalse("Expected Extraction to fail for file " + file + " and handler " + this + ", but did not fail!", \r
                     EXPECTED_EXTRACTOR_FAILURES.contains(file));\r
+            \r
+            assertEquals("File should not be modified by extractor", length, file.length());\r
+            assertEquals("File should not be modified by extractor", modified, file.lastModified());\r
+            \r
+            handleExtractingAsStream(file);\r
         } catch (IllegalArgumentException e) {\r
             if(!EXPECTED_EXTRACTOR_FAILURES.contains(file)) {\r
                 throw new Exception("While handling " + file, e);\r
@@ -68,4 +97,22 @@ public abstract class AbstractFileHandler implements FileHandler {
             extractor.close();\r
         }\r
     }\r
+\r
+    private void handleExtractingAsStream(File file) throws FileNotFoundException,\r
+            IOException, InvalidFormatException, OpenXML4JException,\r
+            XmlException {\r
+        InputStream stream = new FileInputStream(file);\r
+        try {\r
+            POITextExtractor streamExtractor = ExtractorFactory.createExtractor(stream);\r
+            try {\r
+                assertNotNull(streamExtractor);\r
+   \r
+                assertNotNull(streamExtractor.getText());\r
+            } finally {\r
+                streamExtractor.close();\r
+            }\r
+        } finally {\r
+            stream.close();\r
+        }\r
+    }\r
 }\r
index 477ee859cb9ed848cd61d9cd81614a1f8af867b4..6a53b2e00995fea2a9493820e08bbdeeb8be6bf7 100644 (file)
@@ -18,6 +18,7 @@ package org.apache.poi.stress;
 
 import static org.junit.Assert.assertNotNull;
 
+import java.io.File;
 import java.io.FileInputStream;
 import java.io.InputStream;
 
@@ -43,4 +44,10 @@ public class HPSFFileHandler extends AbstractFileHandler {
                        stream.close();
                }
        }
+
+    // a test-case to test this locally without executing the full TestAllFiles
+    @Test
+    public void testExtractor() throws Exception {
+        handleExtracting(new File("test-data/hpsf/TestBug44375.xls"));
+    }
 }
index 54a386ea00dad6aab6de6121a7f5451844d24ba0..a268ed46582b2e35e79fa78bb5adb5ebb70e2eee 100644 (file)
@@ -17,6 +17,7 @@
 package org.apache.poi.stress;
 
 import java.io.ByteArrayOutputStream;
+import java.io.File;
 import java.io.FileInputStream;
 import java.io.InputStream;
 
@@ -71,4 +72,10 @@ public class XSSFFileHandler extends SpreadsheetHandler {
                        stream.close();
                }
        }
+
+    // a test-case to test this locally without executing the full TestAllFiles
+    @Test
+    public void testExtractor() throws Exception {
+        handleExtracting(new File("test-data/spreadsheet/56278.xlsx"));
+    }
 }
\ No newline at end of file
index ce5301ac608a5ede0cabd7e3dd05f7d3290d888b..1a0db038972d9bb280dbcef7558f6c43b62fb9f2 100644 (file)
@@ -57,6 +57,10 @@ public class HPSFPropertiesExtractor extends POITextExtractor {
     }
 
     public String getDocumentSummaryInformationText() {
+        if(document == null) {  // event based extractor does not have a document
+            return "";
+        }
+
         DocumentSummaryInformation dsi = document.getDocumentSummaryInformation();
         StringBuffer text = new StringBuffer();
 
@@ -78,6 +82,10 @@ public class HPSFPropertiesExtractor extends POITextExtractor {
         return text.toString();
     }
     public String getSummaryInformationText() {
+        if(document == null) {  // event based extractor does not have a document
+            return "";
+        }
+
         SummaryInformation si = document.getSummaryInformation();
 
         // Just normal properties
index 45ab8d81317a9b2a740d97a21936745b686a1ba5..4d0b894e01577e42c43002001b0a3ce33216cefa 100644 (file)
@@ -19,6 +19,7 @@ package org.apache.poi.hssf.eventusermodel;
 
 import java.io.InputStream;
 import java.io.IOException;
+import java.util.Set;
 
 import org.apache.poi.hssf.eventusermodel.HSSFUserException;
 import org.apache.poi.hssf.record.*;
@@ -56,11 +57,24 @@ public class HSSFEventFactory {
     * @param req an Instance of HSSFRequest which has your registered listeners
     * @param dir  a DirectoryNode containing your workbook
     */
-   public void processWorkbookEvents(HSSFRequest req, DirectoryNode dir) throws IOException {
-      InputStream in = dir.createDocumentInputStream("Workbook");
-
-      processEvents(req, in);
-   }
+    public void processWorkbookEvents(HSSFRequest req, DirectoryNode dir) throws IOException {
+        // some old documents have "WORKBOOK" or "BOOK"
+        final String name;
+        Set<String> entryNames = dir.getEntryNames();
+        if (entryNames.contains("Workbook")) {
+            name = "Workbook";
+        } else if (entryNames.contains("WORKBOOK")) {
+            name = "WORKBOOK";
+        } else if (entryNames.contains("BOOK")) {
+            name = "BOOK";
+        } else {
+            name = "Workbook";
+        }
+
+        InputStream in = dir.createDocumentInputStream(name);
+
+        processEvents(req, in);
+    }
 
    /**
     * Processes a file into essentially record events.
index ce576439f27c1fe5bb36091acbd543028adaeaf6..8a35a34e4c2cc5ec909313ee614db4b2bcd2c396 100644 (file)
@@ -67,9 +67,14 @@ public class POIXMLPropertiesTextExtractor extends POIXMLTextExtractor {
         * Returns the core document properties, eg author
         */
        public String getCorePropertiesText() {
+           POIXMLDocument document = getDocument();
+        if(document == null) {  // event based extractor does not have a document
+            return "";
+        }
+
                StringBuffer text = new StringBuffer();
-               PackagePropertiesPart props =
-                       getDocument().getProperties().getCoreProperties().getUnderlyingProperties();
+        PackagePropertiesPart props =
+                       document.getProperties().getCoreProperties().getUnderlyingProperties();
 
                appendIfPresent(text, "Category", props.getCategoryProperty().getValue());
                appendIfPresent(text, "Category", props.getCategoryProperty().getValue());
@@ -99,9 +104,14 @@ public class POIXMLPropertiesTextExtractor extends POIXMLTextExtractor {
         *  application
         */
        public String getExtendedPropertiesText() {
+        POIXMLDocument document = getDocument();
+        if(document == null) {  // event based extractor does not have a document
+            return "";
+        }
+
                StringBuffer text = new StringBuffer();
                org.openxmlformats.schemas.officeDocument.x2006.extendedProperties.CTProperties
-                       props = getDocument().getProperties().getExtendedProperties().getUnderlyingProperties();
+                       props = document.getProperties().getExtendedProperties().getUnderlyingProperties();
 
                appendIfPresent(text, "Application", props.getApplication());
                appendIfPresent(text, "AppVersion", props.getAppVersion());
@@ -127,9 +137,14 @@ public class POIXMLPropertiesTextExtractor extends POIXMLTextExtractor {
     */
    @SuppressWarnings("deprecation")
    public String getCustomPropertiesText() {
+       POIXMLDocument document = getDocument();
+       if(document == null) {  // event based extractor does not have a document
+           return "";
+       }
+
       StringBuilder text = new StringBuilder();
       org.openxmlformats.schemas.officeDocument.x2006.customProperties.CTProperties
-      props = getDocument().getProperties().getCustomProperties().getUnderlyingProperties();
+      props = document.getProperties().getCustomProperties().getUnderlyingProperties();
 
        for(CTProperty property : props.getPropertyArray()) {
          String val = "(not implemented!)";
index a0b6b5db17480330fd264d5fccf135e5ecec76e6..60a0f518109a7e52a8410f1d026e7e8d963287d4 100644 (file)
@@ -265,10 +265,10 @@ public class ExtractorFactory {
 
        /**
         * Returns an array of text extractors, one for each of
-        *  the embeded documents in the file (if there are any).
-        * If there are no embeded documents, you'll get back an
+        *  the embedded documents in the file (if there are any).
+        * If there are no embedded documents, you'll get back an
         *  empty array. Otherwise, you'll get one open
-        *  {@link POITextExtractor} for each embeded file.
+        *  {@link POITextExtractor} for each embedded file.
         */
        public static POITextExtractor[] getEmbededDocsTextExtractors(POIOLE2TextExtractor ext) throws IOException, InvalidFormatException, OpenXML4JException, XmlException {
           // All the embded directories we spotted
index 767742687613de6812f84757a2b99a7f6af9b29c..227441859eb577762e3c5b4c4bc97566d34d12f6 100644 (file)
@@ -96,6 +96,7 @@ public class XSSFSheetXMLHandler extends DefaultHandler {
    private String formatString;
    private final DataFormatter formatter;
    private int rowNum;
+   private int nextRowNum;      // some sheets do not have rowNums, Excel can read them so we should try to handle them correctly as well
    private String cellRef;
    private boolean formulasNotResults;
 
@@ -240,7 +241,12 @@ public class XSSFSheetXMLHandler extends DefaultHandler {
           headerFooter.setLength(0);
        }
        else if("row".equals(name)) {
-           rowNum = Integer.parseInt(attributes.getValue("r")) - 1;
+           String rowNumStr = attributes.getValue("r");
+           if(rowNumStr != null) {
+               rowNum = Integer.parseInt(rowNumStr) - 1;
+           } else {
+               rowNum = nextRowNum;
+           }
            output.startRow(rowNum);
        }
        // c => cell
@@ -343,7 +349,7 @@ public class XSSFSheetXMLHandler extends DefaultHandler {
 
                case NUMBER:
                    String n = value.toString();
-                   if (this.formatString != null)
+                   if (this.formatString != null && n.length() > 0)
                        thisStr = formatter.formatRawCellContents(Double.parseDouble(n), this.formatIndex, this.formatString);
                    else
                        thisStr = n;
@@ -370,6 +376,9 @@ public class XSSFSheetXMLHandler extends DefaultHandler {
           
           // Finish up the row
           output.endRow(rowNum);
+          
+          // some sheets do not have rowNum set in the XML, Excel can read them so we should try to read them as well
+          nextRowNum = rowNum + 1;
        } else if ("sheetData".equals(name)) {
            // Handle any "missing" cells which had comments attached
            checkForEmptyCellComments(EmptyCellCommentsCheckType.END_OF_SHEET_DATA);
index e48787be0c8a78329c17ecff4b09e6d1f9449930..b56b3791f010a0d3d49d4e82b3ed41459ff2c4d2 100644 (file)
@@ -23,6 +23,7 @@ import java.util.regex.Pattern;
 import junit.framework.TestCase;
 
 import org.apache.poi.POITextExtractor;
+import org.apache.poi.POIXMLTextExtractor;
 import org.apache.poi.hssf.HSSFTestDataSamples;
 import org.apache.poi.hssf.extractor.ExcelExtractor;
 import org.apache.poi.xssf.XSSFTestDataSamples;
@@ -155,7 +156,6 @@ public class TestXSSFEventBasedExcelExtractor extends TestCase {
                POITextExtractor[] extractors =
                        new POITextExtractor[] { ooxmlExtractor, ole2Extractor };
                for (int i = 0; i < extractors.length; i++) {
-                       @SuppressWarnings("resource")
             POITextExtractor extractor = extractors[i];
                        
                        String text = extractor.getText().replaceAll("[\r\t]", "");
@@ -316,4 +316,25 @@ public class TestXSSFEventBasedExcelExtractor extends TestCase {
             fixture.close();
         }
     }
+    
+    public void testFile56278_normal() throws Exception {
+        // first with normal Text Extractor
+        POIXMLTextExtractor extractor = new XSSFExcelExtractor(
+                XSSFTestDataSamples.openSampleWorkbook("56278.xlsx"));
+        try {
+            assertNotNull(extractor.getText());
+        } finally {
+            extractor.close();
+        }
+    }
+    
+    public void testFile56278_event() throws Exception {
+        // then with event based one
+        POIXMLTextExtractor extractor = getExtractor("56278.xlsx");        
+        try {
+            assertNotNull(extractor.getText());
+        } finally {
+            extractor.close();
+        }
+    }
 }
index 22238d75f1a1b663911708875d9f56992821d613..c6ad03db2d9daa0800d39f6ee8b4738183e582c4 100644 (file)
@@ -22,10 +22,12 @@ import java.io.IOException;
 import junit.framework.TestCase;
 
 import org.apache.poi.POIDataSamples;
+import org.apache.poi.POITextExtractor;
 import org.apache.poi.hpsf.Thumbnail;
 import org.apache.poi.hssf.HSSFTestDataSamples;
 import org.apache.poi.hssf.extractor.ExcelExtractor;
 import org.apache.poi.hssf.usermodel.HSSFWorkbook;
+import org.apache.poi.hwpf.extractor.Word6Extractor;
 import org.apache.poi.poifs.filesystem.POIFSFileSystem;
 
 public final class TestHPSFPropertiesExtractor extends TestCase {
@@ -34,45 +36,53 @@ public final class TestHPSFPropertiesExtractor extends TestCase {
        public void testNormalProperties() throws Exception {
                POIFSFileSystem fs = new POIFSFileSystem(_samples.openResourceAsStream("TestMickey.doc"));
                HPSFPropertiesExtractor ext = new HPSFPropertiesExtractor(fs);
-               ext.getText();
-
-               // Check each bit in turn
-               String sinfText = ext.getSummaryInformationText();
-               String dinfText = ext.getDocumentSummaryInformationText();
-
-               assertTrue(sinfText.indexOf("TEMPLATE = Normal") > -1);
-               assertTrue(sinfText.indexOf("SUBJECT = sample subject") > -1);
-               assertTrue(dinfText.indexOf("MANAGER = sample manager") > -1);
-               assertTrue(dinfText.indexOf("COMPANY = sample company") > -1);
-
-               // Now overall
-               String text = ext.getText();
-               assertTrue(text.indexOf("TEMPLATE = Normal") > -1);
-               assertTrue(text.indexOf("SUBJECT = sample subject") > -1);
-               assertTrue(text.indexOf("MANAGER = sample manager") > -1);
-               assertTrue(text.indexOf("COMPANY = sample company") > -1);
+               try {
+               ext.getText();
+    
+               // Check each bit in turn
+               String sinfText = ext.getSummaryInformationText();
+               String dinfText = ext.getDocumentSummaryInformationText();
+    
+               assertTrue(sinfText.indexOf("TEMPLATE = Normal") > -1);
+               assertTrue(sinfText.indexOf("SUBJECT = sample subject") > -1);
+               assertTrue(dinfText.indexOf("MANAGER = sample manager") > -1);
+               assertTrue(dinfText.indexOf("COMPANY = sample company") > -1);
+    
+               // Now overall
+               String text = ext.getText();
+               assertTrue(text.indexOf("TEMPLATE = Normal") > -1);
+               assertTrue(text.indexOf("SUBJECT = sample subject") > -1);
+               assertTrue(text.indexOf("MANAGER = sample manager") > -1);
+               assertTrue(text.indexOf("COMPANY = sample company") > -1);
+               } finally {
+                   ext.close();
+               }
        }
 
        public void testNormalUnicodeProperties() throws Exception {
                POIFSFileSystem fs = new POIFSFileSystem(_samples.openResourceAsStream("TestUnicode.xls"));
                HPSFPropertiesExtractor ext = new HPSFPropertiesExtractor(fs);
-               ext.getText();
-
-               // Check each bit in turn
-               String sinfText = ext.getSummaryInformationText();
-               String dinfText = ext.getDocumentSummaryInformationText();
-
-               assertTrue(sinfText.indexOf("AUTHOR = marshall") > -1);
-               assertTrue(sinfText.indexOf("TITLE = Titel: \u00c4h") > -1);
-               assertTrue(dinfText.indexOf("COMPANY = Schreiner") > -1);
-               assertTrue(dinfText.indexOf("SCALE = false") > -1);
-
-               // Now overall
-               String text = ext.getText();
-               assertTrue(text.indexOf("AUTHOR = marshall") > -1);
-               assertTrue(text.indexOf("TITLE = Titel: \u00c4h") > -1);
-               assertTrue(text.indexOf("COMPANY = Schreiner") > -1);
-               assertTrue(text.indexOf("SCALE = false") > -1);
+               try {
+               ext.getText();
+    
+               // Check each bit in turn
+               String sinfText = ext.getSummaryInformationText();
+               String dinfText = ext.getDocumentSummaryInformationText();
+    
+               assertTrue(sinfText.indexOf("AUTHOR = marshall") > -1);
+               assertTrue(sinfText.indexOf("TITLE = Titel: \u00c4h") > -1);
+               assertTrue(dinfText.indexOf("COMPANY = Schreiner") > -1);
+               assertTrue(dinfText.indexOf("SCALE = false") > -1);
+    
+               // Now overall
+               String text = ext.getText();
+               assertTrue(text.indexOf("AUTHOR = marshall") > -1);
+               assertTrue(text.indexOf("TITLE = Titel: \u00c4h") > -1);
+               assertTrue(text.indexOf("COMPANY = Schreiner") > -1);
+               assertTrue(text.indexOf("SCALE = false") > -1);
+               } finally {
+                   ext.close();
+               }
        }
 
        public void testCustomProperties() throws Exception {
@@ -80,18 +90,21 @@ public final class TestHPSFPropertiesExtractor extends TestCase {
                                _samples.openResourceAsStream("TestMickey.doc")
                );
                HPSFPropertiesExtractor ext = new HPSFPropertiesExtractor(fs);
-
-               // Custom properties are part of the document info stream
-               String dinfText = ext.getDocumentSummaryInformationText();
-               assertTrue(dinfText.indexOf("Client = sample client") > -1);
-               assertTrue(dinfText.indexOf("Division = sample division") > -1);
-
-               String text = ext.getText();
-               assertTrue(text.indexOf("Client = sample client") > -1);
-               assertTrue(text.indexOf("Division = sample division") > -1);
+               try {
+               // Custom properties are part of the document info stream
+               String dinfText = ext.getDocumentSummaryInformationText();
+               assertTrue(dinfText.indexOf("Client = sample client") > -1);
+               assertTrue(dinfText.indexOf("Division = sample division") > -1);
+    
+               String text = ext.getText();
+               assertTrue(text.indexOf("Client = sample client") > -1);
+               assertTrue(text.indexOf("Division = sample division") > -1);
+        } finally {
+            ext.close();
+        }
        }
 
-       public void testConstructors() {
+       public void testConstructors() throws IOException {
                POIFSFileSystem fs;
                HSSFWorkbook wb;
                try {
@@ -102,9 +115,29 @@ public final class TestHPSFPropertiesExtractor extends TestCase {
                }
                ExcelExtractor excelExt = new ExcelExtractor(wb);
 
-               String fsText = (new HPSFPropertiesExtractor(fs)).getText();
-               String hwText = (new HPSFPropertiesExtractor(wb)).getText();
-               String eeText = (new HPSFPropertiesExtractor(excelExt)).getText();
+               final String fsText;
+               HPSFPropertiesExtractor fsExt = new HPSFPropertiesExtractor(fs);
+               try {
+                   fsText = fsExt.getText();
+               } finally {
+                   fsExt.close();
+               }
+        
+        final String hwText; 
+               HPSFPropertiesExtractor hwExt = new HPSFPropertiesExtractor(wb);
+               try {
+                   hwText = hwExt.getText();
+               } finally {
+                   hwExt.close();
+               }
+               
+        final String eeText;
+        HPSFPropertiesExtractor eeExt = new HPSFPropertiesExtractor(excelExt);
+        try {
+            eeText = eeExt.getText();
+        } finally {
+            eeExt.close();
+        }
 
                assertEquals(fsText, hwText);
                assertEquals(fsText, eeText);
@@ -113,13 +146,17 @@ public final class TestHPSFPropertiesExtractor extends TestCase {
                assertTrue(fsText.indexOf("TITLE = Titel: \u00c4h") > -1);
        }
 
-       public void test42726() {
-               HPSFPropertiesExtractor ex = new HPSFPropertiesExtractor(HSSFTestDataSamples.openSampleWorkbook("42726.xls"));
-               String txt = ex.getText();
-               assertTrue(txt.indexOf("PID_AUTHOR") != -1);
-               assertTrue(txt.indexOf("PID_EDITTIME") != -1);
-               assertTrue(txt.indexOf("PID_REVNUMBER") != -1);
-               assertTrue(txt.indexOf("PID_THUMBNAIL") != -1);
+       public void test42726() throws IOException {
+               HPSFPropertiesExtractor ext = new HPSFPropertiesExtractor(HSSFTestDataSamples.openSampleWorkbook("42726.xls"));
+               try {
+               String txt = ext.getText();
+               assertTrue(txt.indexOf("PID_AUTHOR") != -1);
+               assertTrue(txt.indexOf("PID_EDITTIME") != -1);
+               assertTrue(txt.indexOf("PID_REVNUMBER") != -1);
+               assertTrue(txt.indexOf("PID_THUMBNAIL") != -1);
+        } finally {
+            ext.close();
+        }
        }
        
     public void testThumbnail() throws Exception {
@@ -131,4 +168,24 @@ public final class TestHPSFPropertiesExtractor extends TestCase {
         assertNotNull(thumbnail.getThumbnailAsWMF());
         wb.close();
     }
+
+    public void testExtractorFromWord6Extractor() throws Exception {
+        POIFSFileSystem fs = new POIFSFileSystem(_samples.openResourceAsStream("TestMickey.doc"));
+        Word6Extractor wExt = new Word6Extractor(fs);
+        try {
+            POITextExtractor ext = wExt.getMetadataTextExtractor();
+            try {
+                // Now overall
+                String text = ext.getText();
+                assertTrue(text.indexOf("TEMPLATE = Normal") > -1);
+                assertTrue(text.indexOf("SUBJECT = sample subject") > -1);
+                assertTrue(text.indexOf("MANAGER = sample manager") > -1);
+                assertTrue(text.indexOf("COMPANY = sample company") > -1);
+            } finally {
+                ext.close();
+            }
+        } finally {
+            wExt.close();
+        }
+    }
 }
index 97663310850e25d562aebd5cb3ca08bd49a1ed11..ff76cfa19cb3c083564c8b317e4c03f560d7d359 100644 (file)
@@ -107,8 +107,6 @@ public final class TestHSSFEventFactory extends TestCase {
                POIFSFileSystem fs = new POIFSFileSystem(openSample("42844.xls"));
                HSSFEventFactory factory = new HSSFEventFactory();
                factory.processWorkbookEvents(req, fs);
-
-               assertTrue("no errors while processing the file", true);
        }
 
        private static class MockHSSFListener implements HSSFListener {
@@ -125,4 +123,18 @@ public final class TestHSSFEventFactory extends TestCase {
                        records.add(record);
                }
        }
+
+       public void testWithDifferentWorkbookName() throws Exception {
+        HSSFRequest req = new HSSFRequest();
+        MockHSSFListener mockListen = new MockHSSFListener();
+        req.addListenerForAllRecords(mockListen);
+
+        POIFSFileSystem fs = new POIFSFileSystem(openSample("BOOK_in_capitals.xls"));
+        HSSFEventFactory factory = new HSSFEventFactory();
+        factory.processWorkbookEvents(req, fs);
+
+        fs = new POIFSFileSystem(openSample("WORKBOOK_in_capitals.xls"));
+        factory = new HSSFEventFactory();
+        factory.processWorkbookEvents(req, fs);
+       }
 }      
index de82210291505bfaea49688a1a66d272ed283089..f7584ff11be2b4fbceb61c610d068ac78cb89d8a 100644 (file)
@@ -46,15 +46,18 @@ public final class TestExcelExtractor extends TestCase {
        }
 
 
-       public void testSimple() {
-
+       public void testSimple() throws IOException {
                ExcelExtractor extractor = createExtractor("Simple.xls");
 
-               assertEquals("Sheet1\nreplaceMe\nSheet2\nSheet3\n", extractor.getText());
-
-               // Now turn off sheet names
-               extractor.setIncludeSheetNames(false);
-               assertEquals("replaceMe\n", extractor.getText());
+               try {
+               assertEquals("Sheet1\nreplaceMe\nSheet2\nSheet3\n", extractor.getText());
+    
+               // Now turn off sheet names
+               extractor.setIncludeSheetNames(false);
+               assertEquals("replaceMe\n", extractor.getText());
+               } finally {
+                   extractor.close();
+               }
        }
 
        public void testNumericFormula() {
@@ -126,45 +129,47 @@ public final class TestExcelExtractor extends TestCase {
 
 
        public void testEventExtractor() throws Exception {
-               EventBasedExcelExtractor extractor;
-
                // First up, a simple file with string
                //  based formulas in it
-               extractor = new EventBasedExcelExtractor(
+               EventBasedExcelExtractor extractor = new EventBasedExcelExtractor(
                                new POIFSFileSystem(
                                                HSSFTestDataSamples.openSampleFileStream("SimpleWithFormula.xls")
                                )
                );
-               extractor.setIncludeSheetNames(true);
-
-               String text = extractor.getText();
-               assertEquals("Sheet1\nreplaceme\nreplaceme\nreplacemereplaceme\nSheet2\nSheet3\n", text);
-
-               extractor.setIncludeSheetNames(false);
-               extractor.setFormulasNotResults(true);
-
-               text = extractor.getText();
-               assertEquals("replaceme\nreplaceme\nCONCATENATE(A1,A2)\n", text);
-
-
-               // Now, a slightly longer file with numeric formulas
-               extractor = new EventBasedExcelExtractor(
-                               new POIFSFileSystem(
-                                               HSSFTestDataSamples.openSampleFileStream("sumifformula.xls")
-                               )
-               );
-               extractor.setIncludeSheetNames(false);
-               extractor.setFormulasNotResults(true);
-
-               text = extractor.getText();
-               assertEquals(
-                               "1000\t1\tSUMIF(A1:A5,\">4000\",B1:B5)\n" +
-                               "2000\t2\n" +
-                               "3000\t3\n" +
-                               "4000\t4\n" +
-                               "5000\t5\n",
-                               text
-               );
+               try {
+               extractor.setIncludeSheetNames(true);
+    
+               String text = extractor.getText();
+               assertEquals("Sheet1\nreplaceme\nreplaceme\nreplacemereplaceme\nSheet2\nSheet3\n", text);
+    
+               extractor.setIncludeSheetNames(false);
+               extractor.setFormulasNotResults(true);
+    
+               text = extractor.getText();
+               assertEquals("replaceme\nreplaceme\nCONCATENATE(A1,A2)\n", text);
+    
+    
+               // Now, a slightly longer file with numeric formulas
+               extractor = new EventBasedExcelExtractor(
+                               new POIFSFileSystem(
+                                               HSSFTestDataSamples.openSampleFileStream("sumifformula.xls")
+                               )
+               );
+               extractor.setIncludeSheetNames(false);
+               extractor.setFormulasNotResults(true);
+    
+               text = extractor.getText();
+               assertEquals(
+                               "1000\t1\tSUMIF(A1:A5,\">4000\",B1:B5)\n" +
+                               "2000\t2\n" +
+                               "3000\t3\n" +
+                               "4000\t4\n" +
+                               "5000\t5\n",
+                               text
+               );
+               } finally {
+                   extractor.close();
+               }
        }
 
        public void testWithComments() {
@@ -272,15 +277,22 @@ public final class TestExcelExtractor extends TestCase {
                HSSFWorkbook wbB = new HSSFWorkbook(dirB, fs, true);
 
                ExcelExtractor exA = new ExcelExtractor(wbA);
-               ExcelExtractor exB = new ExcelExtractor(wbB);
-
-               assertEquals("Sheet1\nTest excel file\nThis is the first file\nSheet2\nSheet3\n",
-                               exA.getText());
-               assertEquals("Sample Excel", exA.getSummaryInformation().getTitle());
-
-               assertEquals("Sheet1\nAnother excel file\nThis is the second file\nSheet2\nSheet3\n",
-                               exB.getText());
-               assertEquals("Sample Excel 2", exB.getSummaryInformation().getTitle());
+               try {
+               ExcelExtractor exB = new ExcelExtractor(wbB);
+               try {
+                       assertEquals("Sheet1\nTest excel file\nThis is the first file\nSheet2\nSheet3\n",
+                                       exA.getText());
+                       assertEquals("Sample Excel", exA.getSummaryInformation().getTitle());
+        
+                       assertEquals("Sheet1\nAnother excel file\nThis is the second file\nSheet2\nSheet3\n",
+                                       exB.getText());
+                       assertEquals("Sample Excel 2", exB.getSummaryInformation().getTitle());
+               } finally {
+                   exB.close();
+               }
+               } finally {
+                   exA.close();
+               }
        }
 
        /**
@@ -299,21 +311,32 @@ public final class TestExcelExtractor extends TestCase {
                HSSFWorkbook wbB = new HSSFWorkbook(dirB, fs, true);
 
                ExcelExtractor exA = new ExcelExtractor(wbA);
-               ExcelExtractor exB = new ExcelExtractor(wbB);
-
-               assertEquals("Sheet1\nTest excel file\nThis is the first file\nSheet2\nSheet3\n",
-                               exA.getText());
-               assertEquals("Sample Excel", exA.getSummaryInformation().getTitle());
-
-               assertEquals("Sheet1\nAnother excel file\nThis is the second file\nSheet2\nSheet3\n",
-                               exB.getText());
-               assertEquals("Sample Excel 2", exB.getSummaryInformation().getTitle());
-
-               // And the base file too
-               ExcelExtractor ex = new ExcelExtractor(fs);
-               assertEquals("Sheet1\nI have lots of embeded files in me\nSheet2\nSheet3\n",
-                               ex.getText());
-               assertEquals("Excel With Embeded", ex.getSummaryInformation().getTitle());
+               try {
+               ExcelExtractor exB = new ExcelExtractor(wbB);
+               try {
+                       assertEquals("Sheet1\nTest excel file\nThis is the first file\nSheet2\nSheet3\n",
+                                       exA.getText());
+                       assertEquals("Sample Excel", exA.getSummaryInformation().getTitle());
+        
+                       assertEquals("Sheet1\nAnother excel file\nThis is the second file\nSheet2\nSheet3\n",
+                                       exB.getText());
+                       assertEquals("Sample Excel 2", exB.getSummaryInformation().getTitle());
+        
+                       // And the base file too
+                       ExcelExtractor ex = new ExcelExtractor(fs);
+                       try {
+                       assertEquals("Sheet1\nI have lots of embeded files in me\nSheet2\nSheet3\n",
+                                       ex.getText());
+                       assertEquals("Excel With Embeded", ex.getSummaryInformation().getTitle());
+                       } finally {
+                           ex.close();
+                       }
+            } finally {
+                exB.close();
+            }
+        } finally {
+            exA.close();
+        }
        }
 
        /**