From c80ac9b823d4f128c232d4a69e051af1fd4ea3f4 Mon Sep 17 00:00:00 2001 From: Luke Pulverenti Date: Tue, 29 Nov 2016 14:13:01 -0500 Subject: [PATCH] update artist lists --- .../Localization/TextLocalizer.cs | 41 ++++++++++++++++--- 1 file changed, 36 insertions(+), 5 deletions(-) diff --git a/Emby.Server.Core/Localization/TextLocalizer.cs b/Emby.Server.Core/Localization/TextLocalizer.cs index 016d596590..6690c62638 100644 --- a/Emby.Server.Core/Localization/TextLocalizer.cs +++ b/Emby.Server.Core/Localization/TextLocalizer.cs @@ -2,6 +2,7 @@ using System.Globalization; using System.Linq; using System.Text; +using System.Text.RegularExpressions; using Emby.Server.Implementations.Localization; namespace Emby.Server.Core.Localization @@ -10,11 +11,41 @@ namespace Emby.Server.Core.Localization { public string RemoveDiacritics(string text) { - return String.Concat( - text.Normalize(NormalizationForm.FormD) - .Where(ch => CharUnicodeInfo.GetUnicodeCategory(ch) != - UnicodeCategory.NonSpacingMark) - ).Normalize(NormalizationForm.FormC); + if (text == null) + { + throw new ArgumentNullException("text"); + } + + var chars = Normalize(text, NormalizationForm.FormD) + .Where(ch => CharUnicodeInfo.GetUnicodeCategory(ch) != UnicodeCategory.NonSpacingMark); + + return Normalize(String.Concat(chars), NormalizationForm.FormC); + } + + private static string Normalize(string text, NormalizationForm form, bool stripStringOnFailure = true) + { + if (stripStringOnFailure) + { + try + { + return text.Normalize(form); + } + catch (ArgumentException) + { + // will throw if input contains invalid unicode chars + // https://mnaoumov.wordpress.com/2014/06/14/stripping-invalid-characters-from-utf-16-strings/ + text = StripInvalidUnicodeCharacters(text); + return Normalize(text, form, false); + } + } + + return text.Normalize(form); + } + + private static string StripInvalidUnicodeCharacters(string str) + { + var invalidCharactersRegex = new Regex("([\ud800-\udbff](?![\udc00-\udfff]))|((?