public ExtractionResult ExtractText(IndexingRequestDetails details, Stream stream)
{
using (var reader = new StreamReader(stream, details.Encoding, false, 16, true)) {
var doc = XDocument.Load(reader);
var returnResult = new ExtractionResult(details);
if (Extensions.Count == 0)
{
returnResult.GenerateSegments(doc, SimpleDegrapher.XElementDegrapher);
}
else
{
foreach (var ext in Extensions)
{
if (ext.TryProcess(returnResult, doc))
{
break;
}
}
}
returnResult.AnnotateSegments();
return(returnResult);
}
}
public ExtractionResult ExtractText(IndexingRequestDetails details, Stream stream)
{
using (var reader = new StreamReader(stream, details.Encoding, false, 16, true)) {
var document = reader.ReadToEnd();
var lines = document.Split('\r', '\n').Where(s => !string.IsNullOrEmpty(s)).ToArray();
var returnResult = new ExtractionResult(details);
returnResult.GenerateSegments(lines, null);
returnResult.AnnotateSegments();
return(returnResult);
}
}
public ExtractionResult ExtractText(IndexingRequestDetails details, Stream stream)
{
using (var reader = new StreamReader(stream, details.Encoding, false, 16, true)) {
var obj = JsonConvert.DeserializeObject(reader.ReadToEnd());
var returnResult = new ExtractionResult(details);
returnResult.GenerateSegments(obj, JsonDegrapher);
returnResult.AnnotateSegments();
return(returnResult);
}
}
public ExtractionResult ExtractText(IndexingRequestDetails details, Stream stream)
{
using (var reader = new StreamReader(stream, details.Encoding, false, 16, true)) {
var rows = new List <string>();
var row = string.Empty;
while ((row = reader.ReadLine()) != null)
{
var entry = string.Join("\r\n", row.Split('\t').AsEnumerable().Reverse());
rows.Add(entry);
}
var returnResult = new ExtractionResult(details);
returnResult.GenerateSegments(rows, null);
returnResult.AnnotateSegments();
return(returnResult);
}
}
public ExtractionResult ExtractText(IndexingRequestDetails details, Stream stream)
{
using (var reader = new StreamReader(stream, details.Encoding, false, 16, true)) {
var config = Configuration.Default.WithDefaultLoader();
var document = new HtmlParser(config).Parse(reader.ReadToEnd());
// using degrapher because AngleSharp uses recursion
var returnResult = new ExtractionResult(details);
if (FullDocumentCapture)
{
returnResult.GenerateSegments(document.TextContent, HtmlDegrapher);
}
else
{
returnResult.GenerateSegments(document, HtmlDegrapher);
}
returnResult.AnnotateSegments();
return(returnResult);
}
}
