// POST: api/Document
public async Task <HttpResponseMessage> Post()
{
// Check if the request contains multipart/form-data.
if (!Request.Content.IsMimeMultipartContent())
{
throw new HttpResponseException(HttpStatusCode.UnsupportedMediaType);
}
string root = HttpContext.Current.Server.MapPath("~/App_Data");
var provider = new MultipartFormDataStreamProvider(root);
try
{
// Read the form data.
await Request.Content.ReadAsMultipartAsync(provider);
// This illustrates how to get the file names.
foreach (MultipartFileData file in provider.FileData)
{
Document doc = new Document();
string textExtractionResult = new TextExtractor().Extract(file.LocalFileName).Text;
List <string> shingles = _minHashes.GetShingles(textExtractionResult);
doc.ID = documents.Count + 1;
doc.Name = file.Headers.ContentDisposition.FileName.Replace("\"", "");
doc.MinHashes = _minHashes.GetMinHash(shingles);
documents.Add(doc);
}
return(Request.CreateResponse(HttpStatusCode.OK));
}
catch (System.Exception e)
{
return(Request.CreateErrorResponse(HttpStatusCode.InternalServerError, e));
}
}
public void GetShinglesTest()
{
MinHash minHash = new MinHash(10);
string input = "Hello world I am a string";
List <string> result = minHash.GetShingles(input);
List <string> expected = new List <string>()
{
"hello world i", "world i am", "i am a", "am a string", "a string", "string"
};
Assert.AreEqual(string.Join(" ", expected), string.Join(" ", result));
}