public void TestBug55733()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("55733.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
// Check it gives text without error
string text = extractor.Text;
extractor.Close();
}
public void TestCheckboxes()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("checkboxes.docx");
Console.WriteLine(doc);
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
Assert.AreEqual("This is a small test for checkboxes \nunchecked: |_| \n" +
"Or checked: |X|\n\n\n\n\n" +
"Test a checkbox within a textbox: |_| -> |X|\n\n\n" +
"In Table:\n|_|\t|X|\n\n\n" +
"In Sequence:\n|X||_||X|\n", extractor.Text);
extractor.Close();
}
public void TestFile()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("ExternalEntityInText.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
String text = extractor.Text;
Assert.IsTrue(text.Length > 0);
// Check contents, they should not contain the text from POI web site After colon!
Assert.AreEqual("Here should not be the POI web site: \"\"", text.Trim());
extractor.Close();
}
public void TestFile()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("ExternalEntityInText.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
String text = extractor.Text;
Assert.IsTrue(text.Length > 0);
// Check contents, they should not contain the text from POI web site After colon!
Assert.AreEqual("Here should not be the POI web site: \"\"", text.Trim());
extractor.Close();
}
public void TestSimpleControlContent()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("Bug54849.docx");
String[] targs = new String[] {
"header_rich_text",
"rich_text",
"rich_text_pre_table\nrich_text_cell1\t\t\t\n\nrich_text_post_table",
"plain_text_no_newlines",
"plain_text_with_newlines1\nplain_text_with_newlines2\n",
"watermelon\n",
"dirt\n",
"4/16/2013\n",
"rich_text_in_paragraph_in_cell",
"footer_rich_text",
"footnote_sdt",
"endnote_sdt"
};
XWPFWordExtractor ex = new XWPFWordExtractor(doc);
String s = ex.Text.ToLower();
int hits = 0;
foreach (String targ in targs)
{
bool hit = false;
if (s.IndexOf(targ) > -1)
{
hit = true;
hits++;
}
Assert.AreEqual(true, hit, "controlled content loading-" + targ);
}
Assert.AreEqual(targs.Length, hits, "controlled content loading hit count");
ex.Close();
}
public void TestSimpleControlContent()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("Bug54849.docx");
String[] targs = new String[] {
"header_rich_text",
"rich_text",
"rich_text_pre_table\nrich_text_cell1\t\t\t\n\t\t\t\n\t\t\t\n\nrich_text_post_table",
"plain_text_no_newlines",
"plain_text_with_newlines1\nplain_text_with_newlines2\n",
"watermelon\n",
"dirt\n",
"4/16/2013\n",
"rich_text_in_cell",
"abc",
"rich_text_in_paragraph_in_cell",
"footer_rich_text",
"footnote_sdt",
"endnote_sdt"
};
XWPFWordExtractor ex = new XWPFWordExtractor(doc);
String s = ex.Text.ToLower();
int hits = 0;
foreach (String targ in targs)
{
bool hitted = false;
if (s.Contains(targ))
{
hitted = true;
hits++;
}
Assert.AreEqual(true, hitted, "controlled content loading-" + targ);
}
Assert.AreEqual(targs.Length, hits, "controlled content loading hit count");
ex.Close();
doc = XWPFTestDataSamples.OpenSampleDocument("Bug54771a.docx");
targs = new String[] {
"bb",
"test subtitle\n",
"test user\n",
};
ex = new XWPFWordExtractor(doc);
s = ex.Text.ToLower();
//At one point in development there were three copies of the text.
//This ensures that there is only one copy.
MatchCollection mc;
int hit;
foreach (String targ in targs)
{
mc = Regex.Matches(s, targ);
hit = 0;
foreach (Match m in mc)
{
if (m.Success)
{
hit++;
}
}
Assert.AreEqual(1, hit, "controlled content loading-" + targ);
}
//"test\n" appears twice: once as the "title" and once in the text.
//This also happens when you save this document as text from MSWord.
mc = Regex.Matches(s, "test\n");
hit = 0;
foreach (Match m in mc)
{
if (m.Success)
{
hit++;
}
}
Assert.AreEqual(2, hit, "test<N>");
ex.Close();
}
public void TestBug55733()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("55733.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
// Check it gives text without error
string text = extractor.Text;
extractor.Close();
}
public void TestSimpleControlContent()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("Bug54849.docx");
String[] targs = new String[]{
"header_rich_text",
"rich_text",
"rich_text_pre_table\nrich_text_cell1\t\t\t\n\nrich_text_post_table",
"plain_text_no_newlines",
"plain_text_with_newlines1\nplain_text_with_newlines2\n",
"watermelon\n",
"dirt\n",
"4/16/2013\n",
"rich_text_in_paragraph_in_cell",
"footer_rich_text",
"footnote_sdt",
"endnote_sdt"
};
XWPFWordExtractor ex = new XWPFWordExtractor(doc);
String s = ex.Text.ToLower();
int hits = 0;
foreach (String targ in targs)
{
bool hit = false;
if (s.IndexOf(targ) > -1)
{
hit = true;
hits++;
}
Assert.AreEqual(true, hit, "controlled content loading-" + targ);
}
Assert.AreEqual(targs.Length, hits, "controlled content loading hit count");
ex.Close();
}
public void TestSimpleControlContent()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("Bug54849.docx");
String[] targs = new String[]{
"header_rich_text",
"rich_text",
"rich_text_pre_table\nrich_text_cell1\t\t\t\n\t\t\t\n\t\t\t\n\nrich_text_post_table",
"plain_text_no_newlines",
"plain_text_with_newlines1\nplain_text_with_newlines2\n",
"watermelon\n",
"dirt\n",
"4/16/2013\n",
"rich_text_in_cell",
"abc",
"rich_text_in_paragraph_in_cell",
"footer_rich_text",
"footnote_sdt",
"endnote_sdt"
};
XWPFWordExtractor ex = new XWPFWordExtractor(doc);
String s = ex.Text.ToLower();
int hits = 0;
foreach (String targ in targs)
{
bool hitted = false;
if (s.IndexOf(targ) > -1)
{
hitted = true;
hits++;
}
Assert.AreEqual(true, hitted, "controlled content loading-" + targ);
}
Assert.AreEqual(targs.Length, hits, "controlled content loading hit count");
ex.Close();
doc = XWPFTestDataSamples.OpenSampleDocument("Bug54771a.docx");
targs = new String[]{
"bb",
"test subtitle\n",
"test user\n",
};
ex = new XWPFWordExtractor(doc);
s = ex.Text.ToLower();
//At one point in development there were three copies of the text.
//This ensures that there is only one copy.
MatchCollection mc;
int hit;
foreach (String targ in targs)
{
mc = Regex.Matches(s, targ);
hit = 0;
foreach (Match m in mc)
{
if (m.Success)
hit++;
}
Assert.AreEqual(1, hit, "controlled content loading-" + targ);
}
//"test\n" appears twice: once as the "title" and once in the text.
//This also happens when you save this document as text from MSWord.
mc = Regex.Matches(s, "test\n");
hit = 0;
foreach (Match m in mc)
{
if (m.Success)
hit++;
}
Assert.AreEqual(2, hit, "test<N>");
ex.Close();
}
