x/text/encoding/charmap: support for code page 1125 aka cp866u

Add Ukrainian government standard (RST 2018-91) for DOS, based on common alternative encoding, but different from cp866 in 0xF2-0xF9 Fixes #69779
golang · Oct 5, 2024 · a58b05d · a58b05d
1 parent 3043346
commit a58b05d
Show file tree

Hide file tree

Showing 4 changed files with 200 additions and 1 deletion.
diff --git a/encoding/charmap/charmap_test.go b/encoding/charmap/charmap_test.go
@@ -79,6 +79,10 @@ func TestBasics(t *testing.T) {
 		e:       CodePage1047,
 		encoded: "\xc8\x54\x93\x93\x9f",
 		utf8:    "Hèll¤",
+	}, {
+		e:       CodePage1125,
+		encoded: "Hello.\x20\x80\x81\x82\x83\xF2\x84\x85\xF4\xF0\x86\x87\x88\xF6\xF8\x89\x8A\x8B\x8C\x8D\x8E\x8F\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9A\x9B\x9C\x9D\x9E\x9F\xA0\xA1\xA2\xA3\xF3\xA4\xA5\xF5\xF1\xA6\xA7\xA8\xF7\xF9\xA9\xAA\xAB\xAC\xAD\xAE\xAF\xE0\xE1\xE2\xE3\xE4\xE5\xE6\xE7\xE8\xE9\xEA\xEB\xEC\xED\xEE\xEF\xB0\xB1\xB2\xB3\xB4\xB5\xB6\xB7\xB8\xB9\xBA\xBB\xBC\xBD\xBE\xBF\xC0\xC1\xC2\xC3\xC4\xC5\xC6\xC7\xC8\xC9\xCA\xCB\xCC\xCD\xCE\xCF\xD0\xD1\xD2\xD3\xD4\xD5\xD6\xD7\xD8\xD9\xDA\xDB\xDC\xDD\xDE\xDF\xFA\xFB\xFC\xFD\xFE",
+		utf8:    "Hello. АБВГҐДЕЄЁЖЗИІЇЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯабвгґдеєёжзиіїйклмнопрстуфхцчшщъыьэюя░▒▓│┤╡╢╖╕╣║╗╝╜╛┐└┴┬├─┼╞╟╚╔╩╦╠═╬╧╨╤╥╙╘╒╓╫╪┘┌█▄▌▐▀·√№¤■",
 	}, {
 		e:       CodePage1140,
 		encoded: "\xc8\x9f\x93\x93\xcf",

diff --git a/encoding/charmap/maketables.go b/encoding/charmap/maketables.go
@@ -129,6 +129,14 @@ var encodings = []struct {
 		0x3f,
 		"https://raw.githubusercontent.com/unicode-org/icu-data/main/charset/data/ucm/glibc-IBM1047-2.1.2.ucm",
 	},
+	{
+		"IBM Code Page 1125 (aka cp866u)",
+		"IBM1125",
+		"Ukrainian government standard (RST 2018-91) for DOS, based on common alternative encoding, but different from cp866 in 0xF2-0xF9",
+		"CodePage1125",
+		encoding.ASCIISub,
+		"https://raw.githubusercontent.com/unicode-org/icu-data/main/charset/data/ucm/glibc-CP1125-2.3.3.ucm",
+	},
 	{
 		"IBM Code Page 1140",
 		"IBM01140",

diff --git a/encoding/charmap/tables.go b/encoding/charmap/tables.go
diff --git a/encoding/internal/identifier/mib.go b/encoding/internal/identifier/mib.go