You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@poi.apache.org by ta...@apache.org on 2016/10/28 13:26:49 UTC
svn commit: r1767021 -
/poi/trunk/src/scratchpad/testcases/org/apache/poi/hslf/extractor/TestExtractor.java
Author: tallison
Date: Fri Oct 28 13:26:49 2016
New Revision: 1767021
URL: http://svn.apache.org/viewvc?rev=1767021&view=rev
Log:
whitespace clean up before fix for BUG-60305
Modified:
poi/trunk/src/scratchpad/testcases/org/apache/poi/hslf/extractor/TestExtractor.java
Modified: poi/trunk/src/scratchpad/testcases/org/apache/poi/hslf/extractor/TestExtractor.java
URL: http://svn.apache.org/viewvc/poi/trunk/src/scratchpad/testcases/org/apache/poi/hslf/extractor/TestExtractor.java?rev=1767021&r1=1767020&r2=1767021&view=diff
==============================================================================
--- poi/trunk/src/scratchpad/testcases/org/apache/poi/hslf/extractor/TestExtractor.java (original)
+++ poi/trunk/src/scratchpad/testcases/org/apache/poi/hslf/extractor/TestExtractor.java Fri Oct 28 13:26:49 2016
@@ -46,181 +46,188 @@ import org.junit.Test;
* Tests that the extractor correctly gets the text out of our sample file
*/
public final class TestExtractor {
- /** Extractor primed on the 2 page basic test data */
- private PowerPointExtractor ppe;
- private static final String expectText = "This is a test title\nThis is a test subtitle\nThis is on page 1\nThis is the title on page 2\nThis is page two\nIt has several blocks of text\nNone of them have formatting\n";
-
- /** Extractor primed on the 1 page but text-box'd test data */
- private PowerPointExtractor ppe2;
- private static final String expectText2 = "Hello, World!!!\nI am just a poor boy\nThis is Times New Roman\nPlain Text \n";
-
- /** Where our embeded files live */
- private static POIDataSamples slTests = POIDataSamples.getSlideShowInstance();
-
- @Before
- public void setUp() throws Exception {
- ppe = new PowerPointExtractor(slTests.getFile("basic_test_ppt_file.ppt").getCanonicalPath());
- ppe2 = new PowerPointExtractor(slTests.getFile("with_textbox.ppt").getCanonicalPath());
- }
-
- @After
- public void closeResources() throws Exception {
- ppe2.close();
- ppe.close();
- }
-
+ /**
+ * Extractor primed on the 2 page basic test data
+ */
+ private PowerPointExtractor ppe;
+ private static final String expectText = "This is a test title\nThis is a test subtitle\nThis is on page 1\nThis is the title on page 2\nThis is page two\nIt has several blocks of text\nNone of them have formatting\n";
+
+ /**
+ * Extractor primed on the 1 page but text-box'd test data
+ */
+ private PowerPointExtractor ppe2;
+ private static final String expectText2 = "Hello, World!!!\nI am just a poor boy\nThis is Times New Roman\nPlain Text \n";
+
+ /**
+ * Where our embeded files live
+ */
+ private static POIDataSamples slTests = POIDataSamples.getSlideShowInstance();
+
+ @Before
+ public void setUp() throws Exception {
+ ppe = new PowerPointExtractor(slTests.getFile("basic_test_ppt_file.ppt").getCanonicalPath());
+ ppe2 = new PowerPointExtractor(slTests.getFile("with_textbox.ppt").getCanonicalPath());
+ }
+
+ @After
+ public void closeResources() throws Exception {
+ ppe2.close();
+ ppe.close();
+ }
+
@Test
public void testReadSheetText() {
- // Basic 2 page example
- String sheetText = ppe.getText();
+ // Basic 2 page example
+ String sheetText = ppe.getText();
+
+ ensureTwoStringsTheSame(expectText, sheetText);
+
+
+ // 1 page example with text boxes
+ sheetText = ppe2.getText();
+
+ ensureTwoStringsTheSame(expectText2, sheetText);
+ }
+
+ @Test
+ public void testReadNoteText() {
+ // Basic 2 page example
+ String notesText = ppe.getNotes();
+ String expText = "These are the notes for page 1\nThese are the notes on page two, again lacking formatting\n";
+
+ ensureTwoStringsTheSame(expText, notesText);
+
+ // Other one doesn't have notes
+ notesText = ppe2.getNotes();
+ expText = "";
+
+ ensureTwoStringsTheSame(expText, notesText);
+ }
+
+ @Test
+ public void testReadBoth() {
+ String[] slText = new String[]{
+ "This is a test title\nThis is a test subtitle\nThis is on page 1\n",
+ "This is the title on page 2\nThis is page two\nIt has several blocks of text\nNone of them have formatting\n"
+ };
+ String[] ntText = new String[]{
+ "These are the notes for page 1\n",
+ "These are the notes on page two, again lacking formatting\n"
+ };
+
+ ppe.setSlidesByDefault(true);
+ ppe.setNotesByDefault(false);
+ assertEquals(slText[0] + slText[1], ppe.getText());
+
+ ppe.setSlidesByDefault(false);
+ ppe.setNotesByDefault(true);
+ assertEquals(ntText[0] + ntText[1], ppe.getText());
+
+ ppe.setSlidesByDefault(true);
+ ppe.setNotesByDefault(true);
+ assertEquals(slText[0] + slText[1] + "\n" + ntText[0] + ntText[1], ppe.getText());
+ }
+
+ /**
+ * Test that when presented with a PPT file missing the odd
+ * core record, we can still get the rest of the text out
+ *
+ * @throws Exception
+ */
+ @Test
+ public void testMissingCoreRecords() throws Exception {
+ ppe.close();
+ ppe = new PowerPointExtractor(slTests.openResourceAsStream("missing_core_records.ppt"));
+
+ String text = ppe.getText(true, false);
+ String nText = ppe.getNotes();
+
+ assertNotNull(text);
+ assertNotNull(nText);
+
+ // Notes record were corrupt, so don't expect any
+ assertEquals(nText.length(), 0);
+
+ // Slide records were fine
+ assertTrue(text.startsWith("Using Disease Surveillance and Response"));
+ }
- ensureTwoStringsTheSame(expectText, sheetText);
-
-
- // 1 page example with text boxes
- sheetText = ppe2.getText();
-
- ensureTwoStringsTheSame(expectText2, sheetText);
- }
-
- @Test
- public void testReadNoteText() {
- // Basic 2 page example
- String notesText = ppe.getNotes();
- String expText = "These are the notes for page 1\nThese are the notes on page two, again lacking formatting\n";
-
- ensureTwoStringsTheSame(expText, notesText);
-
- // Other one doesn't have notes
- notesText = ppe2.getNotes();
- expText = "";
-
- ensureTwoStringsTheSame(expText, notesText);
- }
-
- @Test
- public void testReadBoth() {
- String[] slText = new String[] {
- "This is a test title\nThis is a test subtitle\nThis is on page 1\n",
- "This is the title on page 2\nThis is page two\nIt has several blocks of text\nNone of them have formatting\n"
- };
- String[] ntText = new String[] {
- "These are the notes for page 1\n",
- "These are the notes on page two, again lacking formatting\n"
- };
-
- ppe.setSlidesByDefault(true);
- ppe.setNotesByDefault(false);
- assertEquals(slText[0]+slText[1], ppe.getText());
-
- ppe.setSlidesByDefault(false);
- ppe.setNotesByDefault(true);
- assertEquals(ntText[0]+ntText[1], ppe.getText());
-
- ppe.setSlidesByDefault(true);
- ppe.setNotesByDefault(true);
- assertEquals(slText[0]+slText[1]+"\n"+ntText[0]+ntText[1], ppe.getText());
- }
-
- /**
- * Test that when presented with a PPT file missing the odd
- * core record, we can still get the rest of the text out
- * @throws Exception
- */
- @Test
- public void testMissingCoreRecords() throws Exception {
- ppe.close();
- ppe = new PowerPointExtractor(slTests.openResourceAsStream("missing_core_records.ppt"));
-
- String text = ppe.getText(true, false);
- String nText = ppe.getNotes();
-
- assertNotNull(text);
- assertNotNull(nText);
-
- // Notes record were corrupt, so don't expect any
- assertEquals(nText.length(), 0);
-
- // Slide records were fine
- assertTrue(text.startsWith("Using Disease Surveillance and Response"));
- }
-
private void ensureTwoStringsTheSame(String exp, String act) {
- assertEquals(exp.length(),act.length());
- char[] expC = exp.toCharArray();
- char[] actC = act.toCharArray();
- for(int i=0; i<expC.length; i++) {
- assertEquals("Char " + i, expC[i], actC[i]);
- }
- assertEquals(exp,act);
+ assertEquals(exp.length(), act.length());
+ char[] expC = exp.toCharArray();
+ char[] actC = act.toCharArray();
+ for (int i = 0; i < expC.length; i++) {
+ assertEquals("Char " + i, expC[i], actC[i]);
+ }
+ assertEquals(exp, act);
}
-
+
@Test
public void testExtractFromEmbeded() throws Exception {
- POIFSFileSystem fs = new POIFSFileSystem(
- POIDataSamples.getSpreadSheetInstance().openResourceAsStream("excel_with_embeded.xls")
- );
- HSLFSlideShowImpl ss;
-
- DirectoryNode dirA = (DirectoryNode)
- fs.getRoot().getEntry("MBD0000A3B6");
- DirectoryNode dirB = (DirectoryNode)
- fs.getRoot().getEntry("MBD0000A3B3");
-
- assertNotNull(dirA.getEntry("PowerPoint Document"));
- assertNotNull(dirB.getEntry("PowerPoint Document"));
-
- // Check the first file
- ss = new HSLFSlideShowImpl(dirA);
- ppe.close();
- ppe = new PowerPointExtractor(ss);
- assertEquals("Sample PowerPoint file\nThis is the 1st file\nNot much too it\n",
- ppe.getText(true, false)
- );
-
- // And the second
- ss = new HSLFSlideShowImpl(dirB);
- ppe.close();
- ppe = new PowerPointExtractor(ss);
- assertEquals("Sample PowerPoint file\nThis is the 2nd file\nNot much too it either\n",
- ppe.getText(true, false)
- );
- fs.close();
- }
-
- /**
- * A powerpoint file with embeded powerpoint files
- */
- @SuppressWarnings("unused")
- @Test
- public void testExtractFromOwnEmbeded() throws Exception {
- String path = "ppt_with_embeded.ppt";
- ppe.close();
- ppe = new PowerPointExtractor(POIDataSamples.getSlideShowInstance().openResourceAsStream(path));
- List<OLEShape> shapes = ppe.getOLEShapes();
- assertEquals("Expected 6 ole shapes in " + path, 6, shapes.size());
- int num_ppt = 0, num_doc = 0, num_xls = 0;
- for(OLEShape ole : shapes) {
- String name = ole.getInstanceName();
- InputStream data = ole.getObjectData().getData();
- if ("Worksheet".equals(name)) {
- HSSFWorkbook wb = new HSSFWorkbook(data);
- num_xls++;
- wb.close();
- } else if ("Document".equals(name)) {
- HWPFDocument doc = new HWPFDocument(data);
- num_doc++;
- } else if ("Presentation".equals(name)) {
- num_ppt++;
- HSLFSlideShow ppt = new HSLFSlideShow(data);
- ppt.close();
- }
- data.close();
- }
- assertEquals("Expected 2 embedded Word Documents", 2, num_doc);
- assertEquals("Expected 2 embedded Excel Spreadsheets", 2, num_xls);
- assertEquals("Expected 2 embedded PowerPoint Presentations", 2, num_ppt);
- }
+ POIFSFileSystem fs = new POIFSFileSystem(
+ POIDataSamples.getSpreadSheetInstance().openResourceAsStream("excel_with_embeded.xls")
+ );
+ HSLFSlideShowImpl ss;
+
+ DirectoryNode dirA = (DirectoryNode)
+ fs.getRoot().getEntry("MBD0000A3B6");
+ DirectoryNode dirB = (DirectoryNode)
+ fs.getRoot().getEntry("MBD0000A3B3");
+
+ assertNotNull(dirA.getEntry("PowerPoint Document"));
+ assertNotNull(dirB.getEntry("PowerPoint Document"));
+
+ // Check the first file
+ ss = new HSLFSlideShowImpl(dirA);
+ ppe.close();
+ ppe = new PowerPointExtractor(ss);
+ assertEquals("Sample PowerPoint file\nThis is the 1st file\nNot much too it\n",
+ ppe.getText(true, false)
+ );
+
+ // And the second
+ ss = new HSLFSlideShowImpl(dirB);
+ ppe.close();
+ ppe = new PowerPointExtractor(ss);
+ assertEquals("Sample PowerPoint file\nThis is the 2nd file\nNot much too it either\n",
+ ppe.getText(true, false)
+ );
+ fs.close();
+ }
+
+ /**
+ * A powerpoint file with embeded powerpoint files
+ */
+ @SuppressWarnings("unused")
+ @Test
+ public void testExtractFromOwnEmbeded() throws Exception {
+ String path = "ppt_with_embeded.ppt";
+ ppe.close();
+ ppe = new PowerPointExtractor(POIDataSamples.getSlideShowInstance().openResourceAsStream(path));
+ List<OLEShape> shapes = ppe.getOLEShapes();
+ assertEquals("Expected 6 ole shapes in " + path, 6, shapes.size());
+ int num_ppt = 0, num_doc = 0, num_xls = 0;
+ for (OLEShape ole : shapes) {
+ String name = ole.getInstanceName();
+ InputStream data = ole.getObjectData().getData();
+ if ("Worksheet".equals(name)) {
+ HSSFWorkbook wb = new HSSFWorkbook(data);
+ num_xls++;
+ wb.close();
+ } else if ("Document".equals(name)) {
+ HWPFDocument doc = new HWPFDocument(data);
+ num_doc++;
+ } else if ("Presentation".equals(name)) {
+ num_ppt++;
+ HSLFSlideShow ppt = new HSLFSlideShow(data);
+ ppt.close();
+ }
+ data.close();
+ }
+ assertEquals("Expected 2 embedded Word Documents", 2, num_doc);
+ assertEquals("Expected 2 embedded Excel Spreadsheets", 2, num_xls);
+ assertEquals("Expected 2 embedded PowerPoint Presentations", 2, num_ppt);
+ }
/**
* A powerpoint file with embeded powerpoint files
@@ -231,7 +238,7 @@ public final class TestExtractor {
ppe.close();
ppe = new PowerPointExtractor(POIDataSamples.getSlideShowInstance().openResourceAsStream(path));
List<OLEShape> shapes = ppe.getOLEShapes();
-
+
for (OLEShape shape : shapes) {
IOUtils.copy(shape.getObjectData().getData(), new ByteArrayOutputStream());
}
@@ -243,120 +250,120 @@ public final class TestExtractor {
@Test
public void testWithComments() throws Exception {
ppe.close();
- ppe = new PowerPointExtractor(slTests.openResourceAsStream("WithComments.ppt"));
+ ppe = new PowerPointExtractor(slTests.openResourceAsStream("WithComments.ppt"));
+
+ String text = ppe.getText();
+ assertFalse("Comments not in by default", text.contains("This is a test comment"));
+
+ ppe.setCommentsByDefault(true);
+
+ text = ppe.getText();
+ assertContains(text, "This is a test comment");
+
+
+ // And another file
+ ppe.close();
+ ppe = new PowerPointExtractor(slTests.openResourceAsStream("45543.ppt"));
+
+ text = ppe.getText();
+ assertFalse("Comments not in by default", text.contains("testdoc"));
- String text = ppe.getText();
- assertFalse("Comments not in by default", text.contains("This is a test comment"));
-
- ppe.setCommentsByDefault(true);
-
- text = ppe.getText();
- assertContains(text, "This is a test comment");
-
-
- // And another file
- ppe.close();
- ppe = new PowerPointExtractor(slTests.openResourceAsStream("45543.ppt"));
-
- text = ppe.getText();
- assertFalse("Comments not in by default", text.contains("testdoc"));
-
- ppe.setCommentsByDefault(true);
-
- text = ppe.getText();
- assertContains(text, "testdoc");
+ ppe.setCommentsByDefault(true);
+
+ text = ppe.getText();
+ assertContains(text, "testdoc");
}
-
+
/**
* From bug #45537
*/
@Test
public void testHeaderFooter() throws Exception {
- String text;
+ String text;
+
+ // With a header on the notes
+ HSLFSlideShowImpl hslf = new HSLFSlideShowImpl(slTests.openResourceAsStream("45537_Header.ppt"));
+ HSLFSlideShow ss = new HSLFSlideShow(hslf);
+ assertNotNull(ss.getNotesHeadersFooters());
+ assertEquals("testdoc test phrase", ss.getNotesHeadersFooters().getHeaderText());
+ ppe.close();
+
+ ppe = new PowerPointExtractor(hslf);
+
+ text = ppe.getText();
+ assertFalse("Header shouldn't be there by default\n" + text, text.contains("testdoc"));
+ assertFalse("Header shouldn't be there by default\n" + text, text.contains("test phrase"));
+
+ ppe.setNotesByDefault(true);
+ text = ppe.getText();
+ assertContains(text, "testdoc");
+ assertContains(text, "test phrase");
+ ss.close();
+
+ // And with a footer, also on notes
+ hslf = new HSLFSlideShowImpl(slTests.openResourceAsStream("45537_Footer.ppt"));
+ ss = new HSLFSlideShow(hslf);
+ assertNotNull(ss.getNotesHeadersFooters());
+ assertEquals("testdoc test phrase", ss.getNotesHeadersFooters().getFooterText());
+ ppe.close();
+
+ ppe = new PowerPointExtractor(slTests.openResourceAsStream("45537_Footer.ppt"));
+
+ text = ppe.getText();
+ assertFalse("Header shouldn't be there by default\n" + text, text.contains("testdoc"));
+ assertFalse("Header shouldn't be there by default\n" + text, text.contains("test phrase"));
+
+ ppe.setNotesByDefault(true);
+ text = ppe.getText();
+ assertContains(text, "testdoc");
+ assertContains(text, "test phrase");
+ }
+
+ @SuppressWarnings("unused")
+ @Test
+ public void testSlideMasterText() throws Exception {
+ String masterTitleText = "This is the Master Title";
+ String masterRandomText = "This text comes from the Master Slide";
+ String masterFooterText = "Footer from the master slide";
+ HSLFSlideShowImpl hslf = new HSLFSlideShowImpl(slTests.openResourceAsStream("WithMaster.ppt"));
+ ppe.close();
+
+ ppe = new PowerPointExtractor(hslf);
+
+ String text = ppe.getText();
+ //assertContains(text, masterTitleText); // TODO Is this available in PPT?
+ //assertContains(text, masterRandomText); // TODO Extract
+ assertContains(text, masterFooterText);
+ }
+
+ @Test
+ public void testMasterText() throws Exception {
+ ppe.close();
+ ppe = new PowerPointExtractor(slTests.openResourceAsStream("master_text.ppt"));
+
+ // Initially not there
+ String text = ppe.getText();
+ assertFalse(text.contains("Text that I added to the master slide"));
+
+ // Enable, shows up
+ ppe.setMasterByDefault(true);
+ text = ppe.getText();
+ assertTrue(text.contains("Text that I added to the master slide"));
+
+ // Make sure placeholder text does not come out
+ assertFalse(text.contains("Click to edit Master"));
+
+ // Now with another file only containing master text
+ // Will always show up
+ String masterText = "Footer from the master slide";
+ HSLFSlideShowImpl hslf = new HSLFSlideShowImpl(slTests.openResourceAsStream("WithMaster.ppt"));
+ ppe.close();
- // With a header on the notes
- HSLFSlideShowImpl hslf = new HSLFSlideShowImpl(slTests.openResourceAsStream("45537_Header.ppt"));
- HSLFSlideShow ss = new HSLFSlideShow(hslf);
- assertNotNull(ss.getNotesHeadersFooters());
- assertEquals("testdoc test phrase", ss.getNotesHeadersFooters().getHeaderText());
- ppe.close();
-
- ppe = new PowerPointExtractor(hslf);
-
- text = ppe.getText();
- assertFalse("Header shouldn't be there by default\n" + text, text.contains("testdoc"));
- assertFalse("Header shouldn't be there by default\n" + text, text.contains("test phrase"));
-
- ppe.setNotesByDefault(true);
- text = ppe.getText();
- assertContains(text, "testdoc");
- assertContains(text, "test phrase");
- ss.close();
-
- // And with a footer, also on notes
- hslf = new HSLFSlideShowImpl(slTests.openResourceAsStream("45537_Footer.ppt"));
- ss = new HSLFSlideShow(hslf);
- assertNotNull(ss.getNotesHeadersFooters());
- assertEquals("testdoc test phrase", ss.getNotesHeadersFooters().getFooterText());
- ppe.close();
-
- ppe = new PowerPointExtractor(slTests.openResourceAsStream("45537_Footer.ppt"));
-
- text = ppe.getText();
- assertFalse("Header shouldn't be there by default\n" + text, text.contains("testdoc"));
- assertFalse("Header shouldn't be there by default\n" + text, text.contains("test phrase"));
-
- ppe.setNotesByDefault(true);
- text = ppe.getText();
- assertContains(text, "testdoc");
- assertContains(text, "test phrase");
- }
-
- @SuppressWarnings("unused")
- @Test
- public void testSlideMasterText() throws Exception {
- String masterTitleText = "This is the Master Title";
- String masterRandomText = "This text comes from the Master Slide";
- String masterFooterText = "Footer from the master slide";
- HSLFSlideShowImpl hslf = new HSLFSlideShowImpl(slTests.openResourceAsStream("WithMaster.ppt"));
- ppe.close();
-
- ppe = new PowerPointExtractor(hslf);
-
- String text = ppe.getText();
- //assertContains(text, masterTitleText); // TODO Is this available in PPT?
- //assertContains(text, masterRandomText); // TODO Extract
- assertContains(text, masterFooterText);
- }
-
- @Test
- public void testMasterText() throws Exception {
- ppe.close();
- ppe = new PowerPointExtractor(slTests.openResourceAsStream("master_text.ppt"));
-
- // Initially not there
- String text = ppe.getText();
- assertFalse(text.contains("Text that I added to the master slide"));
-
- // Enable, shows up
- ppe.setMasterByDefault(true);
- text = ppe.getText();
- assertTrue(text.contains("Text that I added to the master slide"));
-
- // Make sure placeholder text does not come out
- assertFalse(text.contains("Click to edit Master"));
-
- // Now with another file only containing master text
- // Will always show up
- String masterText = "Footer from the master slide";
- HSLFSlideShowImpl hslf = new HSLFSlideShowImpl(slTests.openResourceAsStream("WithMaster.ppt"));
- ppe.close();
-
- ppe = new PowerPointExtractor(hslf);
-
- text = ppe.getText();
- assertContainsIgnoreCase(text, "master");
- assertContains(text, masterText);
+ ppe = new PowerPointExtractor(hslf);
+
+ text = ppe.getText();
+ assertContainsIgnoreCase(text, "master");
+ assertContains(text, masterText);
}
/**
@@ -364,56 +371,56 @@ public final class TestExtractor {
*/
@Test
public void testChineseText() throws Exception {
- HSLFSlideShowImpl hslf = new HSLFSlideShowImpl(slTests.openResourceAsStream("54880_chinese.ppt"));
- ppe.close();
- ppe = new PowerPointExtractor(hslf);
-
- String text = ppe.getText();
-
- // Check for the english text line
- assertContains(text, "Single byte");
-
- // Check for the english text in the mixed line
- assertContains(text, "Mix");
-
- // Check for the chinese text in the mixed line
- assertContains(text, "\u8868");
-
- // Check for the chinese only text line
- assertContains(text, "\uff8a\uff9d\uff76\uff78");
+ HSLFSlideShowImpl hslf = new HSLFSlideShowImpl(slTests.openResourceAsStream("54880_chinese.ppt"));
+ ppe.close();
+ ppe = new PowerPointExtractor(hslf);
+
+ String text = ppe.getText();
+
+ // Check for the english text line
+ assertContains(text, "Single byte");
+
+ // Check for the english text in the mixed line
+ assertContains(text, "Mix");
+
+ // Check for the chinese text in the mixed line
+ assertContains(text, "\u8868");
+
+ // Check for the chinese only text line
+ assertContains(text, "\uff8a\uff9d\uff76\uff78");
}
-
+
/**
* Tests that we can work with both {@link POIFSFileSystem}
- * and {@link NPOIFSFileSystem}
+ * and {@link NPOIFSFileSystem}
*/
@SuppressWarnings("resource")
@Test
public void testDifferentPOIFS() throws Exception {
- // Open the two filesystems
- DirectoryNode[] files = new DirectoryNode[2];
- files[0] = (new POIFSFileSystem(slTests.openResourceAsStream("basic_test_ppt_file.ppt"))).getRoot();
- NPOIFSFileSystem npoifsFileSystem = new NPOIFSFileSystem(slTests.getFile("basic_test_ppt_file.ppt"));
- files[1] = npoifsFileSystem.getRoot();
-
- // Open directly
- for(DirectoryNode dir : files) {
- PowerPointExtractor extractor = new PowerPointExtractor(dir);
- assertEquals(expectText, extractor.getText());
- }
-
- // Open via a HWPFDocument
- for(DirectoryNode dir : files) {
- HSLFSlideShowImpl slideshow = new HSLFSlideShowImpl(dir);
- PowerPointExtractor extractor = new PowerPointExtractor(slideshow);
- assertEquals(expectText, extractor.getText());
- }
-
- npoifsFileSystem.close();
+ // Open the two filesystems
+ DirectoryNode[] files = new DirectoryNode[2];
+ files[0] = (new POIFSFileSystem(slTests.openResourceAsStream("basic_test_ppt_file.ppt"))).getRoot();
+ NPOIFSFileSystem npoifsFileSystem = new NPOIFSFileSystem(slTests.getFile("basic_test_ppt_file.ppt"));
+ files[1] = npoifsFileSystem.getRoot();
+
+ // Open directly
+ for (DirectoryNode dir : files) {
+ PowerPointExtractor extractor = new PowerPointExtractor(dir);
+ assertEquals(expectText, extractor.getText());
+ }
+
+ // Open via a HWPFDocument
+ for (DirectoryNode dir : files) {
+ HSLFSlideShowImpl slideshow = new HSLFSlideShowImpl(dir);
+ PowerPointExtractor extractor = new PowerPointExtractor(slideshow);
+ assertEquals(expectText, extractor.getText());
+ }
+
+ npoifsFileSystem.close();
}
@Test
- public void testTable() throws Exception{
+ public void testTable() throws Exception {
// ppe = new PowerPointExtractor(slTests.openResourceAsStream("54111.ppt"));
// String text = ppe.getText();
// String target = "TH Cell 1\tTH Cell 2\tTH Cell 3\tTH Cell 4\n"+
@@ -428,7 +435,7 @@ public final class TestExtractor {
ppe = new PowerPointExtractor(slTests.openResourceAsStream("54722.ppt"));
String text = ppe.getText();
- String target = "this\tText\tis\twithin\ta\n"+
+ String target = "this\tText\tis\twithin\ta\n" +
"table\t1\t2\t3\t4";
assertTrue(text.contains(target));
}
@@ -441,7 +448,7 @@ public final class TestExtractor {
ppe = new PowerPointExtractor(hslf);
ppe.setMasterByDefault(true);
-
+
String text = ppe.getText();
assertContains(text, "Prague");
hslf.close();
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@poi.apache.org
For additional commands, e-mail: commits-help@poi.apache.org