public void TestProblemMetadata()
{
WordExtractor extractor =
new WordExtractor(POIDataSamples.GetDocumentInstance().OpenResourceAsStream("ProblemExtracting.doc"));
// Check it gives text without error
string text=extractor.Text;
string[] paratext=extractor.ParagraphText;
string textfrompieces=extractor.TextFromPieces;
}
public void SetUp()
{
String filename = "test2.doc";
String filename2 = "test.doc";
filename3 = "excel_with_embeded.xls";
filename4 = "ThreeColHeadFoot.doc";
filename5 = "HeaderFooterUnicode.doc";
filename6 = "footnote.doc";
POIDataSamples docTests = POIDataSamples.GetDocumentInstance();
extractor = new WordExtractor(docTests.OpenResourceAsStream(filename));
extractor2 = new WordExtractor(docTests.OpenResourceAsStream(filename2));
// Build splat'd out text version
for (int i = 0; i < p_text1.Length; i++)
{
p_text1_block += p_text1[i];
}
}
public void TestProblemHeaderStories49936()
{
HWPFDocument doc = HWPFTestDataSamples.OpenSampleFile("HeaderFooterProblematic.doc");
HeaderStories hs = new HeaderStories(doc);
Assert.AreEqual("", hs.FirstHeader);
Assert.AreEqual("\r", hs.EvenHeader);
Assert.AreEqual("", hs.OddHeader);
Assert.AreEqual("", hs.FirstFooter);
Assert.AreEqual("", hs.EvenFooter);
Assert.AreEqual("", hs.OddFooter);
WordExtractor ext = new WordExtractor(doc);
Assert.AreEqual("\n", ext.HeaderText);
Assert.AreEqual("", ext.FooterText);
}
public void TestFirstParagraphFix()
{
extractor = new WordExtractor(
POIDataSamples.GetDocumentInstance().OpenResourceAsStream("Bug48075.doc")
);
String text = extractor.Text;
Assert.IsTrue(text.StartsWith("\u041f\u0440\u0438\u043b\u043e\u0436\u0435\u043d\u0438\u0435"));
}
public void TestFastSaved()
{
extractor = new WordExtractor(
POIDataSamples.GetDocumentInstance().OpenResourceAsStream("rasp.doc")
);
String text = extractor.Text;
Assert.IsTrue(text.Contains("\u0425\u0425\u0425\u0425\u0425"));
Assert.IsTrue(text.Contains("\u0423\u0423\u0423\u0423\u0423"));
}
public void TestWord6()
{
// Too old for the default
try
{
extractor = new WordExtractor(
POIDataSamples.GetDocumentInstance().OpenResourceAsStream("Word6.doc")
);
Assert.Fail();
}
catch (OldWordFileFormatException) { }
Word6Extractor w6e = new Word6Extractor(
POIDataSamples.GetDocumentInstance().OpenResourceAsStream("Word6.doc")
);
String text = w6e.Text;
Assert.IsTrue(text.Contains("The quick brown fox jumps over the lazy dog"));
String[] tp = w6e.ParagraphText;
Assert.AreEqual(1, tp.Length);
Assert.AreEqual("The quick brown fox jumps over the lazy dog\r\n", tp[0]);
}
public void TestWord95()
{
// Too old for the default
try
{
extractor = new WordExtractor(
POIDataSamples.GetDocumentInstance().OpenResourceAsStream("Word95.doc")
);
Assert.Fail();
}
catch (OldWordFileFormatException ) { }
// Can work with the special one
Word6Extractor w6e = new Word6Extractor(
POIDataSamples.GetDocumentInstance().OpenResourceAsStream("Word95.doc")
);
String text = w6e.Text;
Assert.IsTrue(text.Contains("The quick brown fox jumps over the lazy dog"));
Assert.IsTrue(text.Contains("Paragraph 2"));
Assert.IsTrue(text.Contains("Paragraph 3. Has some RED text and some BLUE BOLD text in it"));
Assert.IsTrue(text.Contains("Last (4th) paragraph"));
String[] tp = w6e.ParagraphText;
Assert.AreEqual(7, tp.Length);
Assert.AreEqual("The quick brown fox jumps over the lazy dog\r\n", tp[0]);
Assert.AreEqual("\r\n", tp[1]);
Assert.AreEqual("Paragraph 2\r\n", tp[2]);
Assert.AreEqual("\r\n", tp[3]);
Assert.AreEqual("Paragraph 3. Has some RED text and some BLUE BOLD text in it.\r\n", tp[4]);
Assert.AreEqual("\r\n", tp[5]);
Assert.AreEqual("Last (4th) paragraph.\r\n", tp[6]);
}
public void TestComments()
{
HWPFDocument doc = HWPFTestDataSamples.OpenSampleFile(filename6);
extractor = new WordExtractor(doc);
String[] text = extractor.CommentsText;
StringBuilder b = new StringBuilder();
for (int i = 0; i < text.Length; i++)
{
b.Append(text[i]);
}
Assert.IsTrue(b.ToString().Contains("TestComment"));
}
public void TestWithFooter()
{
// Non-unicode
HWPFDocument doc = HWPFTestDataSamples.OpenSampleFile(filename4);
extractor = new WordExtractor(doc);
Assert.AreEqual("Footer Left\tFooter Middle Footer Right\n", extractor.FooterText);
String text = extractor.Text;
Assert.IsTrue(text.IndexOf("Footer Left") > -1);
// Unicode
doc = HWPFTestDataSamples.OpenSampleFile(filename5);
extractor = new WordExtractor(doc);
Assert.AreEqual("The footer, with Moli\u00e8re, has Unicode in it.\n", extractor
.FooterText);
text = extractor.Text;
Assert.IsTrue(text.IndexOf("The footer, with") > -1);
}
public void TestWithHeader()
{
// Non-unicode
HWPFDocument doc = HWPFTestDataSamples.OpenSampleFile(filename4);
extractor = new WordExtractor(doc);
Assert.AreEqual("First header column!\tMid header Right header!\n", extractor.HeaderText);
String text = extractor.Text;
Assert.IsTrue(text.IndexOf("First header column!") > -1);
// Unicode
doc = HWPFTestDataSamples.OpenSampleFile(filename5);
extractor = new WordExtractor(doc);
Assert.AreEqual("This is a simple header, with a \u20ac euro symbol in it.\n\n", extractor
.HeaderText);
text = extractor.Text;
Assert.IsTrue(text.IndexOf("This is a simple header") > -1);
}
public void TestExtractFromEmbeded()
{
POIFSFileSystem fs = new POIFSFileSystem(POIDataSamples.GetSpreadSheetInstance().OpenResourceAsStream(filename3));
HWPFDocument doc;
WordExtractor extractor3;
DirectoryNode dirA = (DirectoryNode)fs.Root.GetEntry("MBD0000A3B7");
DirectoryNode dirB = (DirectoryNode)fs.Root.GetEntry("MBD0000A3B2");
// Should have WordDocument and 1Table
Assert.IsNotNull(dirA.GetEntry("1Table"));
Assert.IsNotNull(dirA.GetEntry("WordDocument"));
Assert.IsNotNull(dirB.GetEntry("1Table"));
Assert.IsNotNull(dirB.GetEntry("WordDocument"));
// Check each in turn
doc = new HWPFDocument(dirA, fs);
extractor3 = new WordExtractor(doc);
Assert.IsNotNull(extractor3.Text);
Assert.IsTrue(extractor3.Text.Length > 20);
Assert.AreEqual("I am a sample document\r\nNot much on me\r\nI am document 1\r\n", extractor3
.Text);
Assert.AreEqual("Sample Doc 1", extractor3.SummaryInformation.Title);
Assert.AreEqual("Sample Test", extractor3.SummaryInformation.Subject);
doc = new HWPFDocument(dirB, fs);
extractor3 = new WordExtractor(doc);
Assert.IsNotNull(extractor3.Text);
Assert.IsTrue(extractor3.Text.Length > 20);
Assert.AreEqual("I am another sample document\r\nNot much on me\r\nI am document 2\r\n",
extractor3.Text);
Assert.AreEqual("Sample Doc 2", extractor3.SummaryInformation.Title);
Assert.AreEqual("Another Sample Test", extractor3.SummaryInformation.Subject);
}
