public void TestPictureInHeader()
{
XWPFDocument sampleDoc = XWPFTestDataSamples.OpenSampleDocument("headerPic.docx");
XWPFHeaderFooterPolicy policy = sampleDoc.GetHeaderFooterPolicy();
XWPFHeader header = policy.GetDefaultHeader();
int count = 0;
foreach (XWPFParagraph p in header.Paragraphs)
{
foreach (XWPFRun r in p.Runs)
{
List <XWPFPicture> pictures = r.GetEmbeddedPictures();
foreach (XWPFPicture pic in pictures)
{
Assert.IsNotNull(pic.GetPictureData());
Assert.AreEqual("DOZOR", pic.GetDescription());
}
count += pictures.Count;
}
}
Assert.AreEqual(1, count);
}
public void TestSetParagraphStyle()
{
//System.Text.Encoding.RegisterProvider(System.Text.CodePagesEncodingProvider.Instance);
//new clean instance of paragraph
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("heading123.docx");
XWPFParagraph p = doc.CreateParagraph();
XWPFRun run = p.CreateRun();
run.SetText("Heading 1");
CT_SdtBlock block = doc.Document.body.AddNewSdt();
Assert.IsNull(p.Style);
p.Style = HEADING1;
Assert.AreEqual(HEADING1, p.GetCTP().pPr.pStyle.val);
doc.CreateTOC();
/*
* // TODO - finish this test
* if (false) {
* CTStyles styles = doc.Style;
* CTStyle style = styles.AddNewStyle();
* style.Type=(STStyleType.PARAGRAPH);
* style.StyleId=("Heading1");
* }
*
* if (false) {
* File file = TempFile.CreateTempFile("testHeaders", ".docx");
* OutputStream out1 = new FileOutputStream(file);
* doc.Write(out1);
* out1.Close();
* }
*/
}
public void TestRegisterPackagePictureData()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("issue_51265_1.docx");
/* manually assemble a new image package part*/
OPCPackage opcPckg = doc.Package;
XWPFRelation jpgRelation = XWPFRelation.IMAGE_JPEG;
PackagePartName partName = PackagingUriHelper.CreatePartName(jpgRelation.DefaultFileName.Replace('#', '2'));
PackagePart newImagePart = opcPckg.CreatePart(partName, jpgRelation.ContentType);
byte[] nature1 = XWPFTestDataSamples.GetImage("abstract4.jpg");
Stream os = newImagePart.GetOutputStream();
os.Write(nature1, 0, nature1.Length);
os.Close();
XWPFHeader xwpfHeader = doc.HeaderList[(0)];
PackageRelationship relationship = xwpfHeader.GetPackagePart().AddRelationship(partName, TargetMode.Internal, jpgRelation.Relation);
XWPFPictureData newPicData = new XWPFPictureData(newImagePart, relationship);
/* new part is now Ready to rumble */
Assert.IsFalse(xwpfHeader.AllPictures.Contains(newPicData));
Assert.IsFalse(doc.AllPictures.Contains(newPicData));
Assert.IsFalse(doc.AllPackagePictures.Contains(newPicData));
doc.RegisterPackagePictureData(newPicData);
Assert.IsFalse(xwpfHeader.AllPictures.Contains(newPicData));
Assert.IsFalse(doc.AllPictures.Contains(newPicData));
Assert.IsTrue(doc.AllPackagePictures.Contains(newPicData));
doc.Package.Revert();
}
public void TestGetAllPictures()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("issue_51265_3.docx");
IList <XWPFPictureData> allPictures = doc.AllPictures;
IList <XWPFPictureData> allPackagePictures = doc.AllPackagePictures;
Assert.IsNotNull(allPictures);
Assert.AreEqual(3, allPictures.Count);
foreach (XWPFPictureData xwpfPictureData in allPictures)
{
Assert.IsTrue(allPackagePictures.Contains(xwpfPictureData));
}
try
{
allPictures.Add(allPictures[0]);
Assert.Fail("This list must be unmodifiable!");
}
catch (NotSupportedException)
{
// all ok
}
doc.Package.Revert();
}
public void TestSetWatermark()
{
XWPFDocument sampleDoc = XWPFTestDataSamples.OpenSampleDocument("SampleDoc.docx");
// no header is Set (yet)
XWPFHeaderFooterPolicy policy = sampleDoc.GetHeaderFooterPolicy();
Assert.IsNull(policy.GetDefaultHeader());
Assert.IsNull(policy.GetFirstPageHeader());
Assert.IsNull(policy.GetDefaultFooter());
policy.CreateWatermark("DRAFT");
Assert.IsNotNull(policy.GetDefaultHeader());
Assert.IsNotNull(policy.GetFirstPageHeader());
Assert.IsNotNull(policy.GetEvenPageHeader());
// Re-open, and check
XWPFDocument reopened = XWPFTestDataSamples.WriteOutAndReadBack(sampleDoc);
policy = reopened.GetHeaderFooterPolicy();
Assert.IsNotNull(policy.GetDefaultHeader());
Assert.IsNotNull(policy.GetFirstPageHeader());
Assert.IsNotNull(policy.GetEvenPageHeader());
}
public void TestGetSDTs()
{
String[] contents = 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",
"Watermelon",
"Dirt",
"4/16/2013",
"rich_text_in_paragraph_in_cell",
"Footer_rich_text",
"Footnote_sdt",
"Endnote_sdt"
};
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("Bug54849.docx");
List <XWPFSDT> sdts = extractAllSDTs(doc);
Assert.AreEqual(contents.Length, sdts.Count, "number of sdts");
for (int i = 0; i < sdts.Count; i++)
{//contents.Length; i++){
XWPFSDT sdt = sdts[i];
Assert.AreEqual(contents[i], sdt.Content.ToString(), i + ": " + contents[i]);
}
}
public void TestEndnotes()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("endnotes.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
Assert.IsTrue(extractor.Text.Contains("XXX"));
}
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 TestRead()
{
XWPFDocument sampleDoc = XWPFTestDataSamples.OpenSampleDocument("VariousPictures.docx");
IList <XWPFPictureData> pictures = sampleDoc.AllPictures;
Assert.AreEqual(5, pictures.Count);
String[] ext = { "wmf", "png", "emf", "emf", "jpeg" };
for (int i = 0; i < pictures.Count; i++)
{
Assert.AreEqual(ext[i], pictures[(i)].SuggestFileExtension());
}
int num = pictures.Count;
byte[] pictureData = XWPFTestDataSamples.GetImage("nature1.jpg");
String relationId = sampleDoc.AddPictureData(pictureData, (int)PictureType.JPEG);
// picture list was updated
Assert.AreEqual(num + 1, pictures.Count);
XWPFPictureData pict = (XWPFPictureData)sampleDoc.GetRelationById(relationId);
Assert.AreEqual("jpeg", pict.SuggestFileExtension());
Assert.IsTrue(Arrays.Equals(pictureData, pict.Data));
}
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 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 void TestCreateTable()
{
// open an empty document
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("sample.docx");
// create a table with 5 rows and 7 coloumns
int noRows = 5;
int noCols = 7;
XWPFTable table = doc.CreateTable(noRows, noCols);
// assert the table is empty
List <XWPFTableRow> rows = table.Rows;
Assert.AreEqual(noRows, rows.Count, "Table has less rows than requested.");
foreach (XWPFTableRow xwpfRow in rows)
{
Assert.IsNotNull(xwpfRow);
for (int i = 0; i < 7; i++)
{
XWPFTableCell xwpfCell = xwpfRow.GetCell(i);
Assert.IsNotNull(xwpfCell);
Assert.AreEqual(1, xwpfCell.Paragraphs.Count, "Empty cells should not have one paragraph.");
xwpfCell = xwpfRow.GetCell(i);
Assert.AreEqual(1, xwpfCell.Paragraphs.Count, "Calling 'getCell' must not modify cells content.");
}
}
doc.Package.Revert();
}
public void TestTableFootnotes()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("table_footnotes.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
Assert.IsTrue(extractor.Text.Contains("snoska"));
}
public void Bug57312_NullPointException()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("57312.docx");
Assert.IsNotNull(doc);
foreach (IBodyElement bodyElement in doc.BodyElements)
{
BodyElementType elementType = bodyElement.ElementType;
if (elementType == BodyElementType.PARAGRAPH)
{
XWPFParagraph paragraph = (XWPFParagraph)bodyElement;
foreach (IRunElement iRunElem in paragraph.IRuns)
{
if (iRunElem is XWPFRun)
{
XWPFRun RunElement = (XWPFRun)iRunElem;
UnderlinePatterns underline = RunElement.Underline;
Assert.IsNotNull(underline);
//System.out.Println("Found: " + underline + ": " + RunElement.GetText(0));
}
}
}
}
}
public void TestBug51770()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("Bug51170.docx");
XWPFHeaderFooterPolicy policy = doc.GetHeaderFooterPolicy();
XWPFHeader header = policy.GetDefaultHeader();
foreach (XWPFParagraph paragraph in header.Paragraphs)
{
foreach (XWPFRun run in paragraph.Runs)
{
foreach (XWPFPicture picture in run.GetEmbeddedPictures())
{
if (paragraph.Document != null)
{
System.Console.WriteLine(picture.GetCTPicture());
XWPFPictureData data = picture.GetPictureData();
if (data != null)
{
System.Console.WriteLine(data.FileName);
}
}
}
}
}
}
public void TestEasyAccessToStyles()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("SampleDoc.docx");
XWPFStyles styles = doc.GetStyles();
Assert.IsNotNull(styles);
// Has 3 paragraphs on page one, a break, and 3 on page 2
Assert.AreEqual(7, doc.Paragraphs.Count);
// Check the first three have no run styles, just default paragraph style
for (int i = 0; i < 3; i++)
{
XWPFParagraph p = doc.Paragraphs[(i)];
Assert.AreEqual(null, p.Style);
Assert.AreEqual(null, p.StyleID);
Assert.AreEqual(1, p.Runs.Count);
XWPFRun r = p.Runs[(0)];
Assert.AreEqual(null, r.GetColor());
Assert.AreEqual(null, r.FontFamily);
Assert.AreEqual(null, r.FontName);
Assert.AreEqual(-1, r.FontSize);
}
// On page two, has explicit styles, but on Runs not on
// the paragraph itself
for (int i = 4; i < 7; i++)
{
XWPFParagraph p = doc.Paragraphs[(i)];
Assert.AreEqual(null, p.Style);
Assert.AreEqual(null, p.StyleID);
Assert.AreEqual(1, p.Runs.Count);
XWPFRun r = p.Runs[(0)];
Assert.AreEqual("Arial Black", r.FontFamily);
Assert.AreEqual("Arial Black", r.FontName);
Assert.AreEqual(16, r.FontSize);
Assert.AreEqual("548DD4", r.GetColor());
}
// Check the document styles
// Should have a style defined for each type
Assert.AreEqual(4, styles.NumberOfStyles);
Assert.IsNotNull(styles.GetStyle("Normal"));
Assert.IsNotNull(styles.GetStyle("DefaultParagraphFont"));
Assert.IsNotNull(styles.GetStyle("TableNormal"));
Assert.IsNotNull(styles.GetStyle("NoList"));
// We can't do much yet with latent styles
Assert.AreEqual(137, styles.LatentStyles.NumberOfStyles);
// Check the default styles
Assert.IsNotNull(styles.DefaultRunStyle);
Assert.IsNotNull(styles.DefaultParagraphStyle);
Assert.AreEqual(11, styles.DefaultRunStyle.FontSize);
Assert.AreEqual(200, styles.DefaultParagraphStyle.SpacingAfter);
}
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 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 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"));
}
public void SetUp()
{
XWPFDocument sampleDoc = XWPFTestDataSamples.OpenSampleDocument("documentProperties.docx");
_props = sampleDoc.GetProperties();
_coreProperties = _props.CoreProperties;
Assert.IsNotNull(_props);
}
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 TestTika792()
{
//This test forces the loading of CTMoveBookmark and
//CTMoveBookmarkImpl into ooxml-lite.
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("Tika-792.docx");
XWPFParagraph paragraph = doc.Paragraphs[(0)];
Assert.AreEqual("s", paragraph.Text);
}
public void TestGetNumIlvl()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("Numbering.docx");
string numIlvl = "0";
Assert.AreEqual(numIlvl, doc.Paragraphs[0].GetNumIlvl());
numIlvl = "1";
Assert.AreEqual(numIlvl, doc.Paragraphs[5].GetNumIlvl());
}
public void TestPictureHandlingHeaderDocumentImages()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("issue_51265_2.docx");
Assert.AreEqual(1, doc.AllPictures.Count);
Assert.AreEqual(1, doc.AllPackagePictures.Count);
Assert.AreEqual(1, doc.HeaderList[(0)].AllPictures.Count);
doc.Package.Revert();
}
public void SetUp()
{
noHeader = XWPFTestDataSamples.OpenSampleDocument("NoHeadFoot.docx");
header = XWPFTestDataSamples.OpenSampleDocument("ThreeColHead.docx");
headerFooter = XWPFTestDataSamples.OpenSampleDocument("SimpleHeadThreeColFoot.docx");
footer = XWPFTestDataSamples.OpenSampleDocument("FancyFoot.docx");
oddEven = XWPFTestDataSamples.OpenSampleDocument("PageSpecificHeadFoot.docx");
diffFirst = XWPFTestDataSamples.OpenSampleDocument("DiffFirstPageHeadFoot.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 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 TestBug55733()
{
XWPFDocument doc = XWPFTestDataSamples.OpenSampleDocument("55733.docx");
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
// Check it gives text without error
string text = extractor.Text;
extractor.Close();
}