public ToxyDocument Parse()
{
if (!File.Exists(Context.Path))
throw new FileNotFoundException("File " + Context.Path + " is not found");
bool extractHeader = false;
if (Context.Properties.ContainsKey("ExtractHeader"))
{
extractHeader = Utility.IsTrue(Context.Properties["ExtractHeader"]);
}
bool extractFooter = false;
if (Context.Properties.ContainsKey("ExtractFooter"))
{
extractFooter = Utility.IsTrue(Context.Properties["ExtractFooter"]);
}
ToxyDocument rdoc = new ToxyDocument();
using (FileStream stream = File.OpenRead(Context.Path))
{
HWPFDocument worddoc = new HWPFDocument(stream);
if (extractHeader && worddoc.GetHeaderStoryRange() != null)
{
StringBuilder sb = new StringBuilder();
rdoc.Header = worddoc.GetHeaderStoryRange().Text;
}
if (extractFooter && worddoc.GetFootnoteRange() != null)
{
StringBuilder sb = new StringBuilder();
rdoc.Footer = worddoc.GetFootnoteRange().Text;
}
for (int i=0;i<worddoc.GetRange().NumParagraphs;i++)
{
Paragraph para = worddoc.GetRange().GetParagraph(i);
string text = para.Text;
ToxyParagraph p = new ToxyParagraph();
p.Text = text;
//var runs = para.Runs;
p.StyleID = para.GetStyleIndex().ToString();
//for (int i = 0; i < runs.Count; i++)
//{
// var run = runs[i];
//}
rdoc.Paragraphs.Add(p);
}
}
return rdoc;
}
public void TestInnerTableCellsDetection()
{
HWPFDocument hwpfDocument = new HWPFDocument(POIDataSamples
.GetDocumentInstance().OpenResourceAsStream("innertable.doc"));
hwpfDocument.GetRange();
Range documentRange = hwpfDocument.GetRange();
Paragraph startOfInnerTable = documentRange.GetParagraph(6);
Table innerTable = documentRange.GetTable(startOfInnerTable);
Assert.AreEqual(2, innerTable.NumRows);
TableRow tableRow = innerTable.GetRow(0);
Assert.AreEqual(2, tableRow.NumCells());
}
public string Parse()
{
if (!File.Exists(Context.Path))
throw new FileNotFoundException("File " + Context.Path + " is not found");
StringBuilder sb = new StringBuilder();
using (FileStream stream = File.OpenRead(Context.Path))
{
HWPFDocument worddoc = new HWPFDocument(stream);
return worddoc.GetRange().Text;
}
}
static void Main(string[] args)
{
// POI apparently can't create a document from scratch,
// so we need an existing empty dummy document
POIFSFileSystem fs = new POIFSFileSystem(File.OpenRead("empty.doc"));
HWPFDocument doc = new HWPFDocument(fs);
// centered paragraph with large font size
Range range = doc.GetRange();
CharacterRun run1 = range.InsertAfter("one");
//par1.SetSpacingAfter(200);
//par1.SetJustification((byte)1);
// justification: 0=left, 1=center, 2=right, 3=left and right
//CharacterRun run1 = par1.InsertAfter("one");
run1.SetFontSize(2 * 18);
// font size: twice the point size
// paragraph with bold typeface
Paragraph par2 = run1.InsertAfter(new ParagraphProperties(), 0);
par2.SetSpacingAfter(200);
CharacterRun run2 = par2.InsertAfter("two two two two two two two two two two two two two");
run2.SetBold(true);
// paragraph with italic typeface and a line indent in the first line
Paragraph par3 = run2.InsertAfter(new ParagraphProperties(), 0);
par3.SetFirstLineIndent(200);
par3.SetSpacingAfter(200);
CharacterRun run3 = par3.InsertAfter("three three three three three three three three three "
+ "three three three three three three three three three three three three three three "
+ "three three three three three three three three three three three three three three");
run3.SetItalic(true);
// add a custom document property (needs POI 3.5; POI 3.2 doesn't save custom properties)
DocumentSummaryInformation dsi = doc.DocumentSummaryInformation;
CustomProperties cp = dsi.CustomProperties;
if (cp == null)
cp = new CustomProperties();
cp.Put("myProperty", "foo bar baz");
doc.Write(File.OpenWrite("new-hwpf-file.doc"));
}