PlotDirector/PlotLine/Services/StoryIntelligenceEntityTextNormaliser.cs

66 lines
2.3 KiB
C#
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

using System.Text.RegularExpressions;
namespace PlotLine.Services;
public static class StoryIntelligenceEntityTextNormaliser
{
private static readonly Regex Whitespace = new(@"\s+", RegexOptions.Compiled);
private static readonly Regex TitleFullStops = new(@"\b(Mr|Mrs|Ms|Miss|Dr|Prof|Rev|Revd)\.", RegexOptions.IgnoreCase | RegexOptions.Compiled);
private static readonly Regex NonKeyCharacters = new(@"[^\p{L}\p{N}']+", RegexOptions.Compiled);
public static string Clean(string? value)
=> Whitespace.Replace((value ?? string.Empty).Replace('’', '\''), " ").Trim();
public static string CleanName(string? value)
=> Clean(value).Trim(' ', '.', ',', ';', ':', '!', '?', '"', '\'');
public static string StripLeadingArticle(string value)
{
var clean = Clean(value);
return clean.StartsWith("the ", StringComparison.OrdinalIgnoreCase)
? clean[4..]
: clean.StartsWith("a ", StringComparison.OrdinalIgnoreCase)
? clean[2..]
: clean.StartsWith("an ", StringComparison.OrdinalIgnoreCase)
? clean[3..]
: clean;
}
public static string SafeKey(string? value)
{
var clean = TitleFullStops.Replace(Clean(value), "$1");
clean = NonKeyCharacters.Replace(clean, " ");
clean = Whitespace.Replace(clean, " ").Trim().ToLowerInvariant();
return clean;
}
public static string SingulariseSafeFinalWord(string value, IReadOnlySet<string> singularisableWords)
{
var words = SafeKey(value).Split(' ', StringSplitOptions.RemoveEmptyEntries).ToList();
if (words.Count == 0)
{
return string.Empty;
}
var last = words[^1];
if (last.EndsWith("ies", StringComparison.OrdinalIgnoreCase))
{
var singular = $"{last[..^3]}y";
if (singularisableWords.Contains(singular))
{
words[^1] = singular;
}
}
else if (last.EndsWith('s') && last.Length > 3)
{
var singular = last[..^1];
if (singularisableWords.Contains(singular))
{
words[^1] = singular;
}
}
return string.Join(' ', words);
}
}