/// <summary>
/// Semantic Size of the Paragraph
/// </summary>
public async Task <decimal> SSOTP(StructuredParagraph paragraph)
{
var terms = paragraph.Terms.Distinct(new TermComparer()).ToList();
var otherTerms = terms.ToList();
var Re = 0m;
foreach (var from in terms)
{
otherTerms.Remove(from);
foreach (var to in otherTerms)
{
Re += await SDIP(from.Id, to.Id, paragraph);
}
}
if (Re == 0)
{
return(0);
}
//var R = 1m / Re;
return(Re);
}
/// <summary>
/// Semantic Distance In Paragraph
/// </summary>
public async Task <decimal> SDIP(long from, long to, StructuredParagraph paragraph)
{
var L = await SDIO(from, to);
var Ns = new Dictionary <long, long>()
{
{ 0, 0 }, // речення
{ 2, 0 }, // параграф
};
var paragraphSentances = new List <StructuredSentence>();
paragraphSentances.AddRange(paragraph.Sentences);
foreach (var sentence in paragraph.Sentences)
{
if (sentence.Terms.Any(v => v.Id == from) && sentence.Terms.Any(v => v.Id == to))
{
Ns[0] += sentence.Terms.Count(v => v.Id == from) * sentence.Terms.Count(v => v.Id == to);
}
paragraphSentances.Remove(sentence);
var sentencesTerms = paragraphSentances.SelectMany(v => v.Terms);
Ns[2] += sentence.Terms.Count(v => v.Id == from) * sentencesTerms.Count(v => v.Id == to)
+ sentence.Terms.Count(v => v.Id == to) * sentencesTerms.Count(v => v.Id == from);
}
var Re = ((Ns[0] * 1m) / (L + 0m)) + ((Ns[2] * 1m) / (L + 2m));
//var R = 1m / Re;
return(Re);
}
/// <summary>
/// Return text splited to paragraphs, sentences and with terms
/// </summary>
public async Task <StructuredText> GetStructuredText(string text)
{
var response = new StructuredText
{
OriginalText = text,
Paragraphs = new List <StructuredParagraph>(),
Terms = new List <Term>()
};
var paragraphsSeperators = new Regex(@"[\n]");
var sentenceSeperators = new Regex(@"[.!?]");
var paragraphsTexts = paragraphsSeperators.Split(text).ToList();
// Поділ на речення, абзаци і тд
foreach (var paragraphText in paragraphsTexts)
{
var paragraph = new StructuredParagraph
{
OriginalText = paragraphText,
Sentences = new List <StructuredSentence>(),
Terms = new List <Term>()
};
var sentenceTexts = sentenceSeperators.Split(paragraphText);
foreach (var sentenceText in sentenceTexts)
{
var sentence = new StructuredSentence
{
OriginalText = sentenceText,
Terms = new List <Term>()
};
paragraph.Sentences.Add(sentence);
}
response.Paragraphs.Add(paragraph);
}
//Отримання всіх термінів
using (var session = _db.GetSession())
{
var result = await session.RunAsync(_transactions.GetTerms());
var sentences = response.Paragraphs.SelectMany(v => v.Sentences).ToList();
while (await result.FetchAsync())
{
var item = new Term(result.Current[0] as INode);
foreach (var sentance in sentences)
{
if (IsUsing(item, sentance.OriginalText))
{
sentance.Terms.Add(item);
}
}
}
}
foreach (var item in response.Paragraphs)
{
item.Terms = item.Sentences.SelectMany(v => v.Terms).ToList();
}
response.Terms = response.Paragraphs.SelectMany(v => v.Terms).ToList();
return(response);
}
