From 40442f887ba717ae47620b152315f21b252fe049 Mon Sep 17 00:00:00 2001
From: Luke Pulverenti <luke.pulverenti@gmail.com>
Date: Wed, 9 Aug 2017 15:56:38 -0400
Subject: consolidate emby.server.core into emby.server.implementations

---
 .../Localization/TextLocalizer.cs                  | 63 ++++++++++++++++++++++
 1 file changed, 63 insertions(+)
 create mode 100644 Emby.Server.Implementations/Localization/TextLocalizer.cs

(limited to 'Emby.Server.Implementations/Localization/TextLocalizer.cs')

diff --git a/Emby.Server.Implementations/Localization/TextLocalizer.cs b/Emby.Server.Implementations/Localization/TextLocalizer.cs
new file mode 100644
index 000000000..5188a959e
--- /dev/null
+++ b/Emby.Server.Implementations/Localization/TextLocalizer.cs
@@ -0,0 +1,63 @@
+using System;
+using System.Globalization;
+using System.Linq;
+using System.Text;
+using System.Text.RegularExpressions;
+
+namespace Emby.Server.Implementations.Localization
+{
+    public class TextLocalizer : ITextLocalizer
+    {
+        public string RemoveDiacritics(string text)
+        {
+            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);
+                }
+            }
+
+            try
+            {
+                return text.Normalize(form);
+            }
+            catch (ArgumentException)
+            {
+                // if it still fails, return the original text
+                return text;
+            }
+        }
+
+        private static string StripInvalidUnicodeCharacters(string str)
+        {
+            var invalidCharactersRegex = new Regex("([\ud800-\udbff](?![\udc00-\udfff]))|((?<![\ud800-\udbff])[\udc00-\udfff])");
+            return invalidCharactersRegex.Replace(str, "");
+        }
+
+        public string NormalizeFormKD(string text)
+        {
+            return text.Normalize(NormalizationForm.FormKD);
+        }
+    }
+}
-- 
cgit v1.2.3