TextUtility.cs

using System.Globalization;
using System.Text.RegularExpressions;

namespace OMinimoScrapper;

public static class TextUtility
{
    // https://www.dotnetperls.com/levenshtein
    public static int GetEditDistance(string s, string t)
    {
        int n = s.Length;
        int m = t.Length;
        int[,] d = new int[n + 1, m + 1];

        // Verify arguments.
        if (n == 0)
        {
            return m;
        }

        if (m == 0)
        {
            return n;
        }

        // Initialize arrays.
        for (int i = 0; i <= n; d[i, 0] = i++)
        {
        }

        for (int j = 0; j <= m; d[0, j] = j++)
        {
        }

        // Begin looping.
        for (int i = 1; i <= n; i++)
        {
            for (int j = 1; j <= m; j++)
            {
                // Compute cost.
                int cost = (t[j - 1] == s[i - 1]) ? 0 : 1;
                d[i, j] = Math.Min(Math.Min(d[i - 1, j] + 1, d[i, j - 1] + 1),
                d[i - 1, j - 1] + cost);
            }
        }
        // Return cost.
        return d[n, m];
    }

    public static DateTime DateFromString(string str)
    {
        var regexp = new Regex(@"Em (\d+) de (\w+) de (\d{4})");
        var result = regexp.Replace(str, "$1/$2/$3");

        var dtfi = CultureInfo.GetCultureInfo("pt-BR").DateTimeFormat;
        return DateTime.Parse(result, dtfi);
    }

    public static string CapitalizeFirst(string str)
    {
        if (string.IsNullOrEmpty(str))
        {
            return str;
        }
        var chars = str.ToCharArray();
        chars[0] = char.ToUpper(chars[0]);
        return new string(chars);
    }
}