2001-11-29 16:07:20

by Petr Titěra

[permalink] [raw]
Subject: [Patch] Windows CP1250 support

diff -urN linux-2.4.14-v/Documentation/Configure.help linux-2.4.14-p/Documentation/Configure.help
--- linux-2.4.14-v/Documentation/Configure.help Mon Nov 5 22:40:59 2001
+++ linux-2.4.14-p/Documentation/Configure.help Sun Nov 18 19:18:24 2001
@@ -13427,6 +13427,16 @@
say Y here if you want to include the DOS codepage for Traditional
Chinese(Big5).

+nls codepage 1250
+CONFIG_NLS_CODEPAGE_1250
+ If you want to display filenames with native language characters
+ from the Microsoft FAT file system family or from JOLIET CDROMs
+ correctly on the screen, you need to include the appropriate
+ input/output character sets. Say Y here for the Windows CP-1250
+ character set, which works for most Latin-written Slavic and Central
+ European languages: Czech, German, Hungarian, Polish, Rumanian, Croatian,
+ Slovak, Slovene.
+
nls iso8859-1
CONFIG_NLS_ISO8859_1
If you want to display filenames with native language characters
diff -urN linux-2.4.14-v/fs/nls/Config.in linux-2.4.14-p/fs/nls/Config.in
--- linux-2.4.14-v/fs/nls/Config.in Thu Jun 28 02:10:55 2001
+++ linux-2.4.14-p/fs/nls/Config.in Sun Nov 18 19:05:02 2001
@@ -43,6 +43,7 @@
tristate 'Korean charset (CP949, EUC-KR)' CONFIG_NLS_CODEPAGE_949
tristate 'Thai charset (CP874, TIS-620)' CONFIG_NLS_CODEPAGE_874
tristate 'Hebrew charsets (ISO-8859-8, CP1255)' CONFIG_NLS_ISO8859_8
+ tristate 'Windows CP1250 (Slavic/Central European Languages)' CONFIG_NLS_CODEPAGE_1250
tristate 'Windows CP1251 (Bulgarian, Belarusian)' CONFIG_NLS_CODEPAGE_1251
tristate 'NLS ISO 8859-1 (Latin 1; Western European Languages)' CONFIG_NLS_ISO8859_1
tristate 'NLS ISO 8859-2 (Latin 2; Slavic/Central European Languages)' CONFIG_NLS_ISO8859_2
diff -urN linux-2.4.14-v/fs/nls/nls_cp1250.c linux-2.4.14-p/fs/nls/nls_cp1250.c
--- linux-2.4.14-v/fs/nls/nls_cp1250.c Thu Jan 1 01:00:00 1970
+++ linux-2.4.14-p/fs/nls/nls_cp1250.c Sun Nov 18 18:59:15 2001
@@ -0,0 +1,365 @@
+/*
+ * linux/fs/nls_cp1250.c
+ *
+ * Charset cp1250 translation tables.
+ * Generated automatically from the Unicode and charset
+ * tables from the Unicode Organization (http://www.unicode.org).
+ * The Unicode to charset table has only exact mappings.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/nls.h>
+#include <linux/errno.h>
+
+static wchar_t charset2uni[256] = {
+ /* 0x00*/
+ 0x0000, 0x0001, 0x0002, 0x0003,
+ 0x0004, 0x0005, 0x0006, 0x0007,
+ 0x0008, 0x0009, 0x000a, 0x000b,
+ 0x000c, 0x000d, 0x000e, 0x000f,
+ /* 0x10*/
+ 0x0010, 0x0011, 0x0012, 0x0013,
+ 0x0014, 0x0015, 0x0016, 0x0017,
+ 0x0018, 0x0019, 0x001a, 0x001b,
+ 0x001c, 0x001d, 0x001e, 0x001f,
+ /* 0x20*/
+ 0x0020, 0x0021, 0x0022, 0x0023,
+ 0x0024, 0x0025, 0x0026, 0x0027,
+ 0x0028, 0x0029, 0x002a, 0x002b,
+ 0x002c, 0x002d, 0x002e, 0x002f,
+ /* 0x30*/
+ 0x0030, 0x0031, 0x0032, 0x0033,
+ 0x0034, 0x0035, 0x0036, 0x0037,
+ 0x0038, 0x0039, 0x003a, 0x003b,
+ 0x003c, 0x003d, 0x003e, 0x003f,
+ /* 0x40*/
+ 0x0040, 0x0041, 0x0042, 0x0043,
+ 0x0044, 0x0045, 0x0046, 0x0047,
+ 0x0048, 0x0049, 0x004a, 0x004b,
+ 0x004c, 0x004d, 0x004e, 0x004f,
+ /* 0x50*/
+ 0x0050, 0x0051, 0x0052, 0x0053,
+ 0x0054, 0x0055, 0x0056, 0x0057,
+ 0x0058, 0x0059, 0x005a, 0x005b,
+ 0x005c, 0x005d, 0x005e, 0x005f,
+ /* 0x60*/
+ 0x0060, 0x0061, 0x0062, 0x0063,
+ 0x0064, 0x0065, 0x0066, 0x0067,
+ 0x0068, 0x0069, 0x006a, 0x006b,
+ 0x006c, 0x006d, 0x006e, 0x006f,
+ /* 0x70*/
+ 0x0070, 0x0071, 0x0072, 0x0073,
+ 0x0074, 0x0075, 0x0076, 0x0077,
+ 0x0078, 0x0079, 0x007a, 0x007b,
+ 0x007c, 0x007d, 0x007e, 0x007f,
+ /* 0x80*/
+ 0x20ac, 0x0000, 0x201a, 0x0000,
+ 0x201e, 0x2026, 0x2020, 0x2021,
+ 0x0000, 0x2030, 0x0160, 0x2039,
+ 0x015a, 0x0164, 0x017d, 0x0179,
+ /* 0x90*/
+ 0x0000, 0x2018, 0x2019, 0x201c,
+ 0x201d, 0x2022, 0x2013, 0x2014,
+ 0x0000, 0x2122, 0x0161, 0x203a,
+ 0x015b, 0x0165, 0x017e, 0x017a,
+ /* 0xa0*/
+ 0x00a0, 0x02c7, 0x02d8, 0x0141,
+ 0x00a4, 0x0104, 0x00a6, 0x00a7,
+ 0x00a8, 0x00a9, 0x015e, 0x00ab,
+ 0x00ac, 0x00ad, 0x00ae, 0x017b,
+ /* 0xb0*/
+ 0x00b0, 0x00b1, 0x02db, 0x0142,
+ 0x00b4, 0x00b5, 0x00b6, 0x00b7,
+ 0x00b8, 0x0105, 0x015f, 0x00bb,
+ 0x013d, 0x02dd, 0x013e, 0x017c,
+ /* 0xc0*/
+ 0x0154, 0x00c1, 0x00c2, 0x0102,
+ 0x00c4, 0x0139, 0x0106, 0x00c7,
+ 0x010c, 0x00c9, 0x0118, 0x00cb,
+ 0x011a, 0x00cd, 0x00ce, 0x010e,
+ /* 0xd0*/
+ 0x0110, 0x0143, 0x0147, 0x00d3,
+ 0x00d4, 0x0150, 0x00d6, 0x00d7,
+ 0x0158, 0x016e, 0x00da, 0x0170,
+ 0x00dc, 0x00dd, 0x0162, 0x00df,
+ /* 0xe0*/
+ 0x0155, 0x00e1, 0x00e2, 0x0103,
+ 0x00e4, 0x013a, 0x0107, 0x00e7,
+ 0x010d, 0x00e9, 0x0119, 0x00eb,
+ 0x011b, 0x00ed, 0x00ee, 0x010f,
+ /* 0xf0*/
+ 0x0111, 0x0144, 0x0148, 0x00f3,
+ 0x00f4, 0x0151, 0x00f6, 0x00f7,
+ 0x0159, 0x016f, 0x00fa, 0x0171,
+ 0x00fc, 0x00fd, 0x0163, 0x02d9,
+ };
+
+static unsigned char page00[256] = {
+ 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */
+ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */
+ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */
+ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */
+ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */
+ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */
+ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */
+ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */
+ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */
+ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */
+ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */
+ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */
+ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */
+ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */
+ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */
+ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */
+
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */
+ 0xa0, 0x00, 0x00, 0x00, 0xa4, 0x00, 0xa6, 0xa7, /* 0xa0-0xa7 */
+ 0xa8, 0xa9, 0x00, 0xab, 0xac, 0xad, 0xae, 0x00, /* 0xa8-0xaf */
+ 0xb0, 0xb1, 0x00, 0x00, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */
+ 0xb8, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */
+ 0x00, 0xc1, 0xc2, 0x00, 0xc4, 0x00, 0x00, 0xc7, /* 0xc0-0xc7 */
+ 0x00, 0xc9, 0x00, 0xcb, 0x00, 0xcd, 0xce, 0x00, /* 0xc8-0xcf */
+ 0x00, 0x00, 0x00, 0xd3, 0xd4, 0x00, 0xd6, 0xd7, /* 0xd0-0xd7 */
+ 0x00, 0x00, 0xda, 0x00, 0xdc, 0xdd, 0x00, 0xdf, /* 0xd8-0xdf */
+ 0x00, 0xe1, 0xe2, 0x00, 0xe4, 0x00, 0x00, 0xe7, /* 0xe0-0xe7 */
+ 0x00, 0xe9, 0x00, 0xeb, 0x00, 0xed, 0xee, 0x00, /* 0xe8-0xef */
+ 0x00, 0x00, 0x00, 0xf3, 0xf4, 0x00, 0xf6, 0xf7, /* 0xf0-0xf7 */
+ 0x00, 0x00, 0xfa, 0x00, 0xfc, 0xfd, 0x00, 0x00, /* 0xf8-0xff */
+ };
+
+static unsigned char page01[256] = {
+ 0x00, 0x00, 0xc3, 0xe3, 0xa5, 0xb9, 0xc6, 0xe6, /* 0x00-0x07 */
+ 0x00, 0x00, 0x00, 0x00, 0xc8, 0xe8, 0xcf, 0xef, /* 0x08-0x0f */
+ 0xd0, 0xf0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */
+ 0xca, 0xea, 0xcc, 0xec, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */
+ 0x00, 0xc5, 0xe5, 0x00, 0x00, 0xbc, 0xbe, 0x00, /* 0x38-0x3f */
+ 0x00, 0xa3, 0xb3, 0xd1, 0xf1, 0x00, 0x00, 0xd2, /* 0x40-0x47 */
+ 0xf2, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */
+ 0xd5, 0xf5, 0x00, 0x00, 0xc0, 0xe0, 0x00, 0x00, /* 0x50-0x57 */
+ 0xd8, 0xf8, 0x8c, 0x9c, 0x00, 0x00, 0xaa, 0xba, /* 0x58-0x5f */
+ 0x8a, 0x9a, 0xde, 0xfe, 0x8d, 0x9d, 0x00, 0x00, /* 0x60-0x67 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xd9, 0xf9, /* 0x68-0x6f */
+ 0xdb, 0xfb, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */
+ 0x00, 0x8f, 0x9f, 0xaf, 0xbf, 0x8e, 0x9e, 0x00, /* 0x78-0x7f */
+
+ };
+
+static unsigned char page02[256] = {
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */
+
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xa1, /* 0xc0-0xc7 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */
+ 0xa2, 0xff, 0x00, 0xb2, 0x00, 0xbd, 0x00, 0x00, /* 0xd8-0xdf */
+ };
+
+static unsigned char page20[256] = {
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */
+ 0x00, 0x00, 0x00, 0x96, 0x97, 0x00, 0x00, 0x00, /* 0x10-0x17 */
+ 0x91, 0x92, 0x82, 0x00, 0x93, 0x94, 0x84, 0x00, /* 0x18-0x1f */
+ 0x86, 0x87, 0x95, 0x00, 0x00, 0x00, 0x85, 0x00, /* 0x20-0x27 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */
+ 0x89, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */
+ 0x00, 0x8b, 0x9b, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */
+
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */
+ 0x00, 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, /* 0xa8-0xaf */
+ };
+
+static unsigned char page21[256] = {
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */
+ 0x00, 0x00, 0x99, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */
+ };
+
+static unsigned char *page_uni2charset[256] = {
+ page00, page01, page02, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+ page20, page21, NULL, NULL, NULL, NULL, NULL, NULL,
+ };
+
+static unsigned char charset2lower[256] = {
+ 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */
+ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */
+ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */
+ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */
+ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */
+ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */
+ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */
+ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */
+ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */
+ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */
+ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */
+ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */
+ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */
+ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */
+ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */
+ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */
+
+ 0x80, 0x00, 0x82, 0x00, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */
+ 0x00, 0x89, 0x9a, 0x8b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x88-0x8f */
+ 0x00, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */
+ 0x00, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */
+ 0xa0, 0xa1, 0xa2, 0xb3, 0xa4, 0xb9, 0xa6, 0xa7, /* 0xa0-0xa7 */
+ 0xa8, 0xa9, 0xba, 0xab, 0xac, 0xad, 0xae, 0xbf, /* 0xa8-0xaf */
+ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */
+ 0xb8, 0xb9, 0xba, 0xbb, 0xbe, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */
+ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xc0-0xc7 */
+ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xc8-0xcf */
+ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xd7, /* 0xd0-0xd7 */
+ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xdf, /* 0xd8-0xdf */
+ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */
+ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */
+ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */
+ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */
+ };
+
+static unsigned char charset2upper[256] = {
+ 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */
+ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */
+ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */
+ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */
+ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */
+ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */
+ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */
+ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */
+ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */
+ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */
+ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */
+ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */
+ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */
+ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */
+ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */
+ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */
+
+ 0x80, 0x00, 0x82, 0x00, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */
+ 0x00, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */
+ 0x00, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */
+ 0x00, 0x99, 0x8a, 0x9b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x98-0x9f */
+ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */
+ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */
+ 0xb0, 0xb1, 0xb2, 0xa3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */
+ 0xb8, 0xa5, 0xaa, 0xbb, 0xbc, 0xbd, 0xbc, 0xaf, /* 0xb8-0xbf */
+ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */
+ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */
+ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */
+ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0x00, /* 0xd8-0xdf */
+ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xe0-0xe7 */
+ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xe8-0xef */
+ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xf7, /* 0xf0-0xf7 */
+ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xff, /* 0xf8-0xff */
+ };
+
+static int uni2char(wchar_t uni, unsigned char *out, int boundlen)
+{
+ unsigned char *uni2charset;
+ unsigned char cl = uni & 0x00ff;
+ unsigned char ch = (uni & 0xff00) >> 8;
+
+ if (boundlen <= 0)
+ return -ENAMETOOLONG;
+
+ uni2charset = page_uni2charset[ch];
+ if (uni2charset && uni2charset[cl])
+ out[0] = uni2charset[cl];
+ else
+ return -EINVAL;
+ return 1;
+}
+
+static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni)
+{
+ *uni = charset2uni[*rawstring];
+ if (*uni == 0x0000)
+ return -EINVAL;
+ return 1;
+}
+
+static struct nls_table table = {
+ "cp1250",
+ uni2char,
+ char2uni,
+ charset2lower,
+ charset2upper,
+ THIS_MODULE,
+};
+
+static int __init init_nls_cp1250(void)
+{
+ return register_nls(&table);
+}
+static void __exit exit_nls_cp1250(void)
+{
+ unregister_nls(&table);
+}
+
+module_init(init_nls_cp1250)
+module_exit(exit_nls_cp1250)
+
+MODULE_LICENSE("BSD without advertising clause");
+
+/*
+ * Overrides for Emacs so that we follow Linus's tabbing style.
+ * Emacs will notice this stuff at the end of the file and automatically
+ * adjust the settings for this buffer only. This must remain at the end
+ * of the file.
+ * ---------------------------------------------------------------------------
+ * Local variables:
+ * c-indent-level: 8
+ * c-brace-imaginary-offset: 0
+ * c-brace-offset: -8
+ * c-argdecl-indent: 8
+ * c-label-offset: -8
+ * c-continued-statement-offset: 8
+ * c-continued-brace-offset: 0
+ * End:
+ */
+


Attachments:
patch-cp1250.diff (17.76 kB)

2001-11-29 16:35:40

by Andreas Dilger

[permalink] [raw]
Subject: Re: [Patch] Windows CP1250 support

On Nov 29, 2001 17:06 +0100, Petr Titera wrote:
> Linux contains two codepages for Central European languages (CP852 and
> iso8859-2) but neither one is correct for character encoding used in
> Central European version of Windows (which uses Microsoft's CP1250).
> This patch adds support for this codepage.
>
> +MODULE_LICENSE("BSD without advertising clause");

Can you please pick a valid license for new files? ("Dual GPL/BSD" is
probably what you want).

Cheers, Andreas
--
Andreas Dilger
http://sourceforge.net/projects/ext2resize/
http://www-mddsp.enel.ucalgary.ca/People/adilger/

2001-11-29 16:53:50

by Petr Vandrovec

[permalink] [raw]
Subject: Re: [Patch] Windows CP1250 support

On 29 Nov 01 at 17:06, Petr Titera wrote:
>
> Linux contains two codepages for Central European languages (CP852 and
> iso8859-2) but neither one is correct for character encoding used in
> Central European version of Windows (which uses Microsoft's CP1250).
> This patch adds support for this codepage.

> + If you want to display filenames with native language characters
> + from the Microsoft FAT file system family or from JOLIET CDROMs
> + correctly on the screen, you need to include the appropriate

Correct me, if I'm wrong, but FAT (MSDOS, VFAT short name) uses
CP852, and VFAT long name uses unicode. JOLIET also uses unicode.
CP1250 is not used anywhere near to filesystems in Microsoft Windows,
even Microsoft was bright enough to use only one (MSDOS compatible)
encoding (+ unicode) on externally visible filenames.

And your system itself (userspace) should use ISO-8859-2, so I see
no need for CP1250 - everything works fine here without it. Maybe you
are creating your CDROMs with 16bit-encoded CP1250 instead of unicode,
but then you should replace your CDROM creating software.
Best regards,
Petr Vandrovec
[email protected]