私はこのスレッドに遅れていることを知っていますが、ダウンロードした映画のファイル名をサニタイズするための簡単なアルゴリズムを作成しました。
これにより、次の手順が実行されます。
- 括弧内のすべてを削除します（年が見つかった場合は情報を保持しようとします）
- 一般的に使用される単語のリストを削除します（720p、bdrip、h264など...）
- それがタイトルの言語情報である可能性があると想定し、残りの文字列の最後（特別な単語の前）でそれらを削除します
- 括弧内に年が見つからなかった場合は、残りの文字列の終わりを確認します（言語の場合）
これを行うと、ドットとスペースが置き換えられるため、たとえば、タイトルを検索APIのクエリとして使用できるようになります。
これがXUnitでのテストです（私はほとんどのイタリア語のタイトルを使用してテストしました）
using Grappachu.Movideo.Core.Helpers.TitleCleaner;
using SharpTestsEx;
using Xunit;
namespace Grappachu.MoVideo.Test
{
public class TitleCleanerTest
{
[Theory]
[InlineData("Avengers.Confidential.La.Vedova.Nera.E.Punisher.2014.iTALiAN.Bluray.720p.x264 - BG.mkv",
"Avengers Confidential La Vedova Nera E Punisher", 2014)]
[InlineData("Fuck You, Prof! (2013) BDRip 720p HEVC ITA GER AC3 Multi Sub PirateMKV.mkv",
"Fuck You, Prof!", 2013)]
[InlineData("Il Libro della Giungla(2016)(BDrip1080p_H264_AC3 5.1 Ita Eng_Sub Ita Eng)by siste82.avi",
"Il Libro della Giungla", 2016)]
[InlineData("Il primo dei bugiardi (2009) [Mux by Little-Boy]", "Il primo dei bugiardi", 2009)]
[InlineData("Il.Viaggio.Di.Arlo-The.Good.Dinosaur.2015.DTS.ITA.ENG.1080p.BluRay.x264-BLUWORLD",
"il viaggio di arlo", 2015)]
[InlineData("La Mafia Uccide Solo D'estate 2013 .avi",
"La Mafia Uccide Solo D'estate", 2013)]
[InlineData("Ip.Man.3.2015.iTA.AC3.5.1.448.Chi.Aac.BluRay.m1080p.x264.Sub.[scambiofile.info].mkv",
"Ip Man 3", 2015)]
[InlineData("Inferno.2016.BluRay.1080p.AC3.ITA.AC3.ENG.Subs.x264-WGZ.mkv",
"Inferno", 2016)]
[InlineData("Ghostbusters.2016.iTALiAN.BDRiP.EXTENDED.XviD-HDi.mp4",
"Ghostbusters", 2016)]
[InlineData("Transcendence.mkv", "Transcendence", null)]
[InlineData("Being Human (Forsyth, 1994).mkv", "Being Human", 1994)]
public void Clean_should_return_title_and_year_when_possible(string filename, string title, int? year)
{
var res = MovieTitleCleaner.Clean(filename);
res.Title.ToLowerInvariant().Should().Be.EqualTo(title.ToLowerInvariant());
res.Year.Should().Be.EqualTo(year);
}
}
}
および最初のバージョンのコード
using System;
using System.Globalization;
using System.IO;
using System.Linq;
using System.Text.RegularExpressions;
namespace Grappachu.Movideo.Core.Helpers.TitleCleaner
{
public class MovieTitleCleanerResult
{
public string Title { get; set; }
public int? Year { get; set; }
public string SubTitle { get; set; }
}
public class MovieTitleCleaner
{
private const string SpecialMarker = "§=§";
private static readonly string[] ReservedWords;
private static readonly string[] SpaceChars;
private static readonly string[] Languages;
static MovieTitleCleaner()
{
ReservedWords = new[]
{
SpecialMarker, "hevc", "bdrip", "Bluray", "x264", "h264", "AC3", "DTS", "480p", "720p", "1080p"
};
var cultures = CultureInfo.GetCultures(CultureTypes.AllCultures);
var l = cultures.Select(x => x.EnglishName).ToList();
l.AddRange(cultures.Select(x => x.ThreeLetterISOLanguageName));
Languages = l.Distinct().ToArray();
SpaceChars = new[] {".", "_", " "};
}
public static MovieTitleCleanerResult Clean(string filename)
{
var temp = Path.GetFileNameWithoutExtension(filename);
int? maybeYear = null;
// Remove what's inside brackets trying to keep year info.
temp = RemoveBrackets(temp, '{', '}', ref maybeYear);
temp = RemoveBrackets(temp, '[', ']', ref maybeYear);
temp = RemoveBrackets(temp, '(', ')', ref maybeYear);
// Removes special markers (codec, formats, ecc...)
var tokens = temp.Split(SpaceChars, StringSplitOptions.RemoveEmptyEntries);
var title = string.Empty;
for (var i = 0; i < tokens.Length; i++)
{
var tok = tokens[i];
if (ReservedWords.Any(x => string.Equals(x, tok, StringComparison.OrdinalIgnoreCase)))
{
if (title.Length > 0)
break;
}
else
{
title = string.Join(" ", title, tok).Trim();
}
}
temp = title;
// Remove languages infos when are found before special markers (should not remove "English" if it's inside the title)
tokens = temp.Split(SpaceChars, StringSplitOptions.RemoveEmptyEntries);
for (var i = tokens.Length - 1; i >= 0; i--)
{
var tok = tokens[i];
if (Languages.Any(x => string.Equals(x, tok, StringComparison.OrdinalIgnoreCase)))
tokens[i] = string.Empty;
else
break;
}
title = string.Join(" ", tokens).Trim();
// If year is not found inside parenthesis try to catch at the end, just after the title
if (!maybeYear.HasValue)
{
var resplit = title.Split(SpaceChars, StringSplitOptions.RemoveEmptyEntries);
var last = resplit.Last();
if (LooksLikeYear(last))
{
maybeYear = int.Parse(last);
title = title.Replace(last, string.Empty).Trim();
}
}
// TODO: review this. when there's one dash separates main title from subtitle
var res = new MovieTitleCleanerResult();
res.Year = maybeYear;
if (title.Count(x => x == '-') == 1)
{
var sp = title.Split('-');
res.Title = sp[0];
res.SubTitle = sp[1];
}
else
{
res.Title = title;
}
return res;
}
private static string RemoveBrackets(string inputString, char openChar, char closeChar, ref int? maybeYear)
{
var str = inputString;
while (str.IndexOf(openChar) > 0 && str.IndexOf(closeChar) > 0)
{
var dataGraph = str.GetBetween(openChar.ToString(), closeChar.ToString());
if (LooksLikeYear(dataGraph))
{
maybeYear = int.Parse(dataGraph);
}
else
{
var parts = dataGraph.Split(SpaceChars, StringSplitOptions.RemoveEmptyEntries);
foreach (var part in parts)
if (LooksLikeYear(part))
{
maybeYear = int.Parse(part);
break;
}
}
str = str.ReplaceBetween(openChar, closeChar, string.Format(" {0} ", SpecialMarker));
}
return str;
}
private static bool LooksLikeYear(string dataRound)
{
return Regex.IsMatch(dataRound, "^(19|20)[0-9][0-9]");
}
}
public static class StringUtils
{
public static string GetBetween(this string src, string a, string b,
StringComparison comparison = StringComparison.Ordinal)
{
var idxStr = src.IndexOf(a, comparison);
var idxEnd = src.IndexOf(b, comparison);
if (idxStr >= 0 && idxEnd > 0)
{
if (idxStr > idxEnd)
Swap(ref idxStr, ref idxEnd);
return src.Substring(idxStr + a.Length, idxEnd - idxStr - a.Length);
}
return src;
}
private static void Swap<T>(ref T idxStr, ref T idxEnd)
{
var temp = idxEnd;
idxEnd = idxStr;
idxStr = temp;
}
public static string ReplaceBetween(this string s, char begin, char end, string replacement = null)
{
var regex = new Regex(string.Format("\\{0}.*?\\{1}", begin, end));
return regex.Replace(s, replacement ?? string.Empty);
}
}
}