Fix todo: ISO-2022-CN is x-cp50227 in .NET (#97)

* Fix todo: ISO-2022-CN is x-cp50227 in .NET * Fix mistake with wrong replace alias * Simplify documentation for iso-2022-cn * Fix typo in `iso-2022-cn` * Fix simplified * Fix simplified (x2)
CharsetDetector · Nov 16, 2019 · 9f6a0d6 · 9f6a0d6
1 parent cb3dca2
commit 9f6a0d6
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 3 deletions.
diff --git a/src/Core/CodepageName.cs b/src/Core/CodepageName.cs
@@ -94,9 +94,9 @@ internal static class CodepageName
         /// ISO 2022 Chinese codepage name.
         /// </summary>
         /// <remarks>
-        /// TODO: Not supported? Maybe fix to x-cp50227?
+        /// Supported by alias is x-cp50227 (Codepage 50227) in. NET. Codepage identifier 50229 is currently unsupported (see for example https://github.com/microsoft/referencesource/blob/17b97365645da62cf8a49444d979f94a59bbb155/mscorlib/system/text/iso2022encoding.cs#L92).
         /// </remarks>
-        internal const string ISO_2022_CN = "iso-2022-ch";
+        internal const string ISO_2022_CN = "iso-2022-cn";
 
         /// <summary>
         /// ISO 2022 Korean codepage name.
@@ -110,6 +110,14 @@ internal static class CodepageName
         /// ISO 2022 Japanese codepage name.
         /// </summary>
         internal const string ISO_2022_JP = "iso-2022-jp";
+
+        /// <summary>
+        /// ISO 2022 Simplified Chinese codepage name.
+        /// </summary>
+        /// <remarks>
+        /// Other alias is cp50227.
+        /// </remarks>
+        internal const string X_CP50227 = "x-cp50227";
 
         /// <summary>
         /// Big5 codepage name.

diff --git a/src/DetectionDetail.cs b/src/DetectionDetail.cs
@@ -19,7 +19,8 @@ public class DetectionDetail
             new Dictionary<string, string>
             {
                 // CP949 is superset of ks_c_5601-1987 (see https://github.com/CharsetDetector/UTF-unknown/pull/74#issuecomment-550362133)
-                {CodepageName.CP949, CodepageName.KS_C_5601_1987}
+                {CodepageName.CP949, CodepageName.KS_C_5601_1987},
+                {CodepageName.ISO_2022_CN, CodepageName.X_CP50227},
             };
 
         /// <summary>