25 lines
751 B
C#
25 lines
751 B
C#
using Api.Services.Contracts;
|
|
|
|
namespace Api.Services;
|
|
|
|
public sealed class TextChunker : ITextChunker
|
|
{
|
|
public IReadOnlyList<string> Chunk(string text, int chunkSize, int overlap)
|
|
{
|
|
if (string.IsNullOrWhiteSpace(text)) return [];
|
|
chunkSize = Math.Clamp(chunkSize, 300, 3000);
|
|
overlap = Math.Clamp(overlap, 0, chunkSize / 2);
|
|
|
|
var chunks = new List<string>();
|
|
var start = 0;
|
|
while (start < text.Length)
|
|
{
|
|
var length = Math.Min(chunkSize, text.Length - start);
|
|
var chunk = text.Substring(start, length).Trim();
|
|
if (!string.IsNullOrWhiteSpace(chunk)) chunks.Add(chunk);
|
|
start += chunkSize - overlap;
|
|
}
|
|
return chunks;
|
|
}
|
|
}
|