aboutsummaryrefslogtreecommitdiff
path: root/Emby.Server.Implementations/Localization/TextLocalizer.cs
diff options
context:
space:
mode:
authorLuke Pulverenti <luke.pulverenti@gmail.com>2017-08-09 15:56:38 -0400
committerLuke Pulverenti <luke.pulverenti@gmail.com>2017-08-09 15:56:38 -0400
commit40442f887ba717ae47620b152315f21b252fe049 (patch)
tree340be082fd2296f19aed17b24b22b5095e3815a7 /Emby.Server.Implementations/Localization/TextLocalizer.cs
parent52aeb3c40b3e2f0fdc377ac7c793714add2be0ef (diff)
consolidate emby.server.core into emby.server.implementations
Diffstat (limited to 'Emby.Server.Implementations/Localization/TextLocalizer.cs')
-rw-r--r--Emby.Server.Implementations/Localization/TextLocalizer.cs63
1 files changed, 63 insertions, 0 deletions
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);
+ }
+ }
+}