public void PdfToTextConverterConstructorTest()
{
var infile = Input;
var target = new PdfToTextConverter(infile);
Check.That(infile).IsEqualTo(target.Original);
}
/// <summary>
/// Returns a Task<string> which when awaited yields all of the text in the PdfFile.
/// </summary>
/// <returns>A Task<string> which when awaited yields all of the text in the PdfFile.</returns>
public override async Task <string> LoadTextAsync()
{
var converter = new PdfToTextConverter(this);
var converted = await converter.ConvertFileAsync().ConfigureAwait(false);
return(await converted.LoadTextAsync().ConfigureAwait(false));
}
public void LoadTextTest()
{
var target = new PdfFile(TestPdfFilePath);
var expected = new PdfToTextConverter(target).ConvertFile().LoadText();
var actual = target.LoadText();
Check.That(actual).IsEqualTo(expected);
}
public void ConvertFileAsyncTest()
{
var infile = Input;
var target = new PdfToTextConverter(infile);
var expected = infile.LoadText();
string actual;
actual = target.ConvertFileAsync().Result.LoadText();
Check.That(actual).IsEqualTo(expected);
}
public void Execute(IndexFieldEvent e)
{
var umbracoFileName = e.UmbracoProperty.Value != null?e.UmbracoProperty.Value.ToString() : string.Empty;
var docPath = ConfigurationManager.AppSettings["Dexter:DocumentPath"];
var filePath = string.IsNullOrWhiteSpace(docPath)
? umbracoFileName
: umbracoFileName.Replace("~/media", ConfigurationManager.AppSettings["Dexter:DocumentPath"])
.Replace("/media", ConfigurationManager.AppSettings["Dexter:DocumentPath"]);
var text = string.Empty;
switch (System.IO.Path.GetExtension(filePath))
{
case ".pdf":
text = new PdfToTextConverter().Convert(filePath);
break;
case ".doc":
text = new DocToTextConverter().Convert(filePath);
break;
case ".xls":
text = new XlsToTextConverter().Convert(filePath);
break;
case ".docx":
text = new DocxToTextConverter().Convert(filePath);
break;
case ".xlsx":
text = new XlsxToTextConverter().Convert(filePath);
break;
case ".pptx":
text = new PptxToTextConverter().Convert(filePath);
break;
case ".ppt":
text = System.IO.Path.GetFileName(filePath);
break;
case ".zip":
text = new ZipToTextConverter().Convert(filePath);
break;
}
e.Value = string.Join(" ", text.Split(new[] { ' ' }).Except(IGNORE));
}
/// <summary>
/// Parses the contents of a raw, untagged PdfFile into a new Document instance.
/// </summary>
/// <param name="pdf">The raw, untagged PdfFile to parse.</param>
/// <returns>
/// The contents of the PdfFile composed into a fully reified
/// <see cref="Document"/> instance.
/// </returns>
public Document DocumentFromPdf(PdfFile pdf)
{
var txt = new PdfToTextConverter(pdf).ConvertFile();
return(new TaggedSourceParser(new TaggedFile(new SharpNLPTagger(this.TaggerMode, txt.FullPath).ProcessFile())).LoadDocument(txt.NameSansExt));
}
