public void TestTableFootnotes()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("table_footnotes.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
Assert.IsTrue(extractor.Text.Contains("snoska"));
}
public void TestGetSimpleText()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("sample.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
String text = extractor.Text;
Assert.IsTrue(text.Length > 0);
// Check contents
Assert.IsTrue(text.StartsWith(
"Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Nunc at risus vel erat tempus posuere. Aenean non ante. Suspendisse vehicula dolor sit amet odio."
));
Assert.IsTrue(text.EndsWith(
"Phasellus ultricies mi nec leo. Sed tempus. In sit amet lorem at velit faucibus vestibulum.\n"
));
// Check number of paragraphs
int ps = 0;
char[] t = text.ToCharArray();
for (int i = 0; i < t.Length; i++)
{
if (t[i] == '\n')
{
ps++;
}
}
Assert.AreEqual(3, ps);
}
public void Init(string path)
{
if (path.EndsWith(".doc"))
{
HWPFDocument hwpf;
using (FileStream file = new FileStream(path, FileMode.Open, FileAccess.Read))
{
hwpf = new HWPFDocument(file);
}
this.textBody = hwpf.Text.ToString();
}
else if (path.EndsWith(".docx"))
{
XWPFDocument xwpf;
using (FileStream file = new FileStream(path, FileMode.Open, FileAccess.Read))
{
xwpf = new XWPFDocument(file);
}
XWPFWordExtractor ex = new XWPFWordExtractor(xwpf);
this.textBody = ex.Text;
}
textBody = textBody.Replace("（", "(").Replace("）", ")");
}
public void TestGetWithHyperlinks()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("TestDocument.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
// Now check contents
extractor.SetFetchHyperlinks(false);
Assert.AreEqual(
"This is a test document.\nThis bit is in bold and italic\n" +
"Back to normal\n" +
"This contains BOLD, ITALIC and BOTH, as well as RED and YELLOW text.\n" +
"We have a hyperlink here, and another.\n",
extractor.Text
);
// One hyperlink is a real one, one is just to the top of page
extractor.SetFetchHyperlinks(true);
Assert.AreEqual(
"This is a test document.\nThis bit is in bold and italic\n" +
"Back to normal\n" +
"This contains BOLD, ITALIC and BOTH, as well as RED and YELLOW text.\n" +
"We have a hyperlink <http://poi.apache.org/> here, and another.\n",
extractor.Text
);
}
public void TestDrawings()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("drawing.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
String text = extractor.Text;
Assert.IsTrue(text.Length > 0);
}
public void TestInsertedDeletedText()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("delins.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
Assert.IsTrue(extractor.Text.Contains("pendant worn"));
Assert.IsTrue(extractor.Text.Contains("extremely well"));
}
public void TestFootnotes()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("footnotes.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
String text = extractor.Text;
Assert.IsTrue(extractor.Text.Contains("snoska"));
Assert.IsTrue(text.Contains("Eto ochen prostoy[footnoteRef:1] text so snoskoy"));
}
/// <summary>
/// 读取Word以字符串方式返回
/// </summary>
/// <param name="filepath">文档地址</param>
/// <returns>字符串形式的文档内容</returns>
public string ReaderWord(string filepath)
{
using (FileStream fs = File.OpenRead(filepath))
{
XWPFDocument doc = new XWPFDocument(fs);
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
return(extractor.ToString());
}
}
public void TestFldSimpleContent()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("FldSimple.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
String text = extractor.Text;
Assert.IsTrue(text.Length > 0);
Assert.IsTrue(text.Contains("FldSimple.docx"));
}
public void TestDOCMFiles()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("45690.docm");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
Assert.IsTrue(extractor.Text.Contains("2004"));
Assert.IsTrue(extractor.Text.Contains("2008"));
Assert.IsTrue(extractor.Text.Contains("(120 "));
}
public void TestParagraphHeader()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("Headers.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
Assert.IsTrue(extractor.Text.Contains("Section 1"));
Assert.IsTrue(extractor.Text.Contains("Section 2"));
Assert.IsTrue(extractor.Text.Contains("Section 3"));
}
public void TestEndnotes()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("endnotes.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
string text = extractor.Text;
Assert.IsTrue(text.Contains("XXX"));
Assert.IsTrue(text.Contains("tilaka [endnoteRef:2]or 'tika'"));
}
public void TestNoFieldCodes()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("FieldCodes.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
String text = extractor.Text;
Assert.IsTrue(text.Length > 0);
Assert.IsFalse(text.Contains("AUTHOR"));
Assert.IsFalse(text.Contains("CREATEDATE"));
}
public void TestFormFootnotes()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("form_footnotes.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
String text = extractor.Text;
Assert.IsTrue(text.Contains("testdoc"), "Unable to find expected word in text\n" + text);
Assert.IsTrue(text.Contains("test phrase"), "Unable to find expected word in text\n" + text);
}
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();
}
/// <summary>
/// 文档属性
/// </summary>
/// <param name="filepath">文档地址</param>
/// <returns>0.创建者,1分类,2标题</returns>
public Tuple <string, string, string> GetDocProperties(string filepath)
{
using (FileStream fs = File.OpenRead(filepath))
{
XWPFDocument doc = new XWPFDocument(fs);
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
CoreProperties t = extractor.GetCoreProperties();
return(new Tuple <string, string, string>(t.Creator, t.Category, t.Title));
}
}
public void TestDocTabs()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("WithTabs.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
// Check bits
Assert.IsTrue(extractor.Text.Contains("a"));
Assert.IsTrue(extractor.Text.Contains("\t"));
Assert.IsTrue(extractor.Text.Contains("b"));
// Now check the first paragraph in total
Assert.IsTrue(extractor.Text.Contains("a\tb\n"));
}
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 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 TestWriteFromReadOnlyOPC()
{
OPCPackage opc = OPCPackage.Open(
POIDataSamples.GetDocumentInstance().GetFileInfo("SampleDoc.docx"),
PackageAccess.READ
);
XWPFDocument doc = new XWPFDocument(opc);
XWPFWordExtractor ext = new XWPFWordExtractor(doc);
String origText = ext.Text;
doc = XWPFTestDataSamples.WriteOutAndReadBack(doc);
ext = new XWPFWordExtractor(doc);
Assert.AreEqual(origText, ext.Text);
}
public void TestHeadersFooters()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("ThreeColHeadFoot.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
Assert.AreEqual(
"First header column!\tMid header\tRight header!\n" +
"This is a sample word document. It has two pages. It has a three column heading, and a three column footer\n" +
"\n" +
"HEADING TEXT\n" +
"\n" +
"More on page one\n" +
"\n\n" +
"End of page 1\n\n\n" +
"This is page two. It also has a three column heading, and a three column footer.\n" +
"Footer Left\tFooter Middle\tFooter Right\n",
extractor.Text
);
// Now another file, expect multiple headers
// and multiple footers
doc = XWPFTestDataSamples.OpenSampleDocument("DiffFirstPageHeadFoot.docx");
extractor = new XWPFWordExtractor(doc);
extractor =
new XWPFWordExtractor(doc);
//extractor.Text;
Assert.AreEqual(
"I am the header on the first page, and I" + '\u2019' + "m nice and simple\n" +
"First header column!\tMid header\tRight header!\n" +
"This is a sample word document. It has two pages. It has a simple header and footer, which is different to all the other pages.\n" +
"\n" +
"HEADING TEXT\n" +
"\n" +
"More on page one\n" +
"\n\n" +
"End of page 1\n\n\n" +
"This is page two. It also has a three column heading, and a three column footer.\n" +
"The footer of the first page\n" +
"Footer Left\tFooter Middle\tFooter Right\n",
extractor.Text
);
}
public IActionResult PostearDoc(IFormFile file)
{
string texto;
if (file.ContentType == "application/pdf")
{
using (MemoryStream ms = new MemoryStream())
{
file.CopyTo(ms);
byte[] que = ms.ToArray();
PdfReader pdfReader = new PdfReader(que);
byte[] contenidoPageUno = pdfReader.GetPageContent(1);
PrTokeniser tokenizer = new PrTokeniser(new RandomAccessFileOrArray(contenidoPageUno));
List <string> strList = new List <string>();
texto = String.Empty;
while (tokenizer.NextToken())
{
if (tokenizer.TokenType == PrTokeniser.TK_STRING)
{
strList.Add(tokenizer.StringValue);
texto = texto + tokenizer.StringValue;
}
}
pdfReader.Close();
}
}
else
{
XWPFDocument doc = new XWPFDocument(file.OpenReadStream());
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
texto = extractor.Text;
}
return(Json(new { texto }));
}
public void TestGetComplexText()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("IllustrativeCases.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
String text = extractor.Text;
Assert.IsTrue(text.Length > 0);
char euro = '\u20ac';
Debug.WriteLine("'" + text.Substring(text.Length - 40) + "'");
//Check contents
Assert.IsTrue(text.StartsWith(
" \n(V) ILLUSTRATIVE CASES\n\n"
));
Assert.IsTrue(text.Contains(
"As well as gaining " + euro + "90 from child benefit increases, he will also receive the early childhood supplement of " + euro + "250 per quarter for Vincent for the full four quarters of the year.\n\n\n\n"// \n\n\n"
));
Assert.IsTrue(text.EndsWith(
"11.4%\t\t90\t\t\t\t\t250\t\t1,310\t\n\n \n\n\n"
));
// Check number of paragraphs
int ps = 0;
char[] t = text.ToCharArray();
for (int i = 0; i < t.Length; i++)
{
if (t[i] == '\n')
{
ps++;
}
}
Assert.AreEqual(134, ps);
}
public string ReadData()
{
string fileData = string.Empty;
logger.AppendLog("Validating file extension..");
if (ValidateFile() != FileValidationError.NoError)
{
logger.AppendError("Incorrect file extension.");
return(fileData);
}
logger.AppendLog("Valid file extension.");
logger.AppendLog("Reading file...");
try
{
using (FileStream fs = new FileStream(this.FileName,
FileMode.Open, FileAccess.Read))
{
XWPFDocument doc = new XWPFDocument(fs);
XWPFWordExtractor docExtractor = new XWPFWordExtractor(doc);
fileData = docExtractor.Text;
}
logger.AppendLog("File read successfully.");
}
catch (Exception ex)
{
string errorMsg = "Error reading word file. Aborting read operation.";
logger.AppendError(errorMsg);
throw new Exception(errorMsg + ex.Message);
}
return(fileData);
}
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();
}
