FileDocCategorySizeDatePackage
TextExtractor.javaAPI DocApache Poi 3.0.13800Thu May 31 18:46:28 BST 2007org.apache.poi.hslf.extractor

TextExtractor

public class TextExtractor extends TestCase
Tests that the extractor correctly gets the text out of our sample file
author
Nick Burch (nick at torchbox dot com)

Fields Summary
private PowerPointExtractor
ppe
Extractor primed on the 2 page basic test data
private PowerPointExtractor
ppe2
Extractor primed on the 1 page but text-box'd test data
private String
dirname
Where to go looking for our test files
Constructors Summary
public TextExtractor()

		dirname = System.getProperty("HSLF.testdata.path");
		String filename = dirname + "/basic_test_ppt_file.ppt";
		ppe = new PowerPointExtractor(filename);
		String filename2 = dirname + "/with_textbox.ppt";
		ppe2 = new PowerPointExtractor(filename2);
Methods Summary
private voidensureTwoStringsTheSame(java.lang.String exp, java.lang.String act)

		assertEquals(exp.length(),act.length());
		char[] expC = exp.toCharArray();
		char[] actC = act.toCharArray();
		for(int i=0; i<expC.length; i++) {
			System.out.println(i + "\t" + expC[i] + " " + actC[i]);
			assertEquals(expC[i],actC[i]);
		}
		assertEquals(exp,act);
public voidtestMissingCoreRecords()
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

		String filename = dirname + "/missing_core_records.ppt";
		ppe = new PowerPointExtractor(filename);
		
		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"));
public voidtestReadNoteText()

		// Basic 2 page example
		String notesText = ppe.getNotes();
		String expectText = "These are the notes for page 1\nThese are the notes on page two, again lacking formatting\n";

		ensureTwoStringsTheSame(expectText, notesText);
		
		// Other one doesn't have notes
		notesText = ppe2.getNotes();
		expectText = "";
		
		ensureTwoStringsTheSame(expectText, notesText);
public voidtestReadSheetText()

    	// Basic 2 page example
		String sheetText = ppe.getText();
		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";

		ensureTwoStringsTheSame(expectText, sheetText);
		
		
		// 1 page example with text boxes
		sheetText = ppe2.getText();
		expectText = "Hello, World!!!\nI am just a poor boy\nThis is Times New Roman\nPlain Text \n"; 

		ensureTwoStringsTheSame(expectText, sheetText);