From: Gabriel Krisman Bertazi <krisman@collabora.co.uk>
To: linux-fsdevel@vger.kernel.org
Cc: jra@google.com, tytso@mit.edu, olaf@sgi.com,
darrick.wong@oracle.com, kernel@lists.collabora.co.uk,
Gabriel Krisman Bertazi <krisman@collabora.co.uk>
Subject: [PATCH 04/15] nls: Split default charset from NLS core
Date: Wed, 9 May 2018 03:47:55 -0300 [thread overview]
Message-ID: <20180509064800.28658-5-krisman@collabora.co.uk> (raw)
In-Reply-To: <20180509064800.28658-1-krisman@collabora.co.uk>
Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.co.uk>
---
fs/nls/Makefile | 2 +-
fs/nls/nls_base.c | 458 -----------------------------------------
fs/nls/nls_default.c | 473 +++++++++++++++++++++++++++++++++++++++++++
3 files changed, 474 insertions(+), 459 deletions(-)
create mode 100644 fs/nls/nls_default.c
diff --git a/fs/nls/Makefile b/fs/nls/Makefile
index ac54db297128..d7cdcc797db7 100644
--- a/fs/nls/Makefile
+++ b/fs/nls/Makefile
@@ -3,7 +3,7 @@
# Makefile for native language support
#
-obj-$(CONFIG_NLS) += nls_base.o
+obj-$(CONFIG_NLS) += nls_base.o nls_default.o
obj-$(CONFIG_NLS_CODEPAGE_437) += nls_cp437.o
obj-$(CONFIG_NLS_CODEPAGE_737) += nls_cp737.o
diff --git a/fs/nls/nls_base.c b/fs/nls/nls_base.c
index 0bb0acf6893f..47deb2fcf3aa 100644
--- a/fs/nls/nls_base.c
+++ b/fs/nls/nls_base.c
@@ -15,223 +15,11 @@
#include <linux/errno.h>
#include <linux/kmod.h>
#include <linux/spinlock.h>
-#include <asm/byteorder.h>
static struct nls_table default_table;
static struct nls_table *tables = &default_table;
static DEFINE_SPINLOCK(nls_lock);
-/*
- * Sample implementation from Unicode home page.
- * http://www.stonehand.com/unicode/standard/fss-utf.html
- */
-struct utf8_table {
- int cmask;
- int cval;
- int shift;
- long lmask;
- long lval;
-};
-
-static const struct utf8_table utf8_table[] =
-{
- {0x80, 0x00, 0*6, 0x7F, 0, /* 1 byte sequence */},
- {0xE0, 0xC0, 1*6, 0x7FF, 0x80, /* 2 byte sequence */},
- {0xF0, 0xE0, 2*6, 0xFFFF, 0x800, /* 3 byte sequence */},
- {0xF8, 0xF0, 3*6, 0x1FFFFF, 0x10000, /* 4 byte sequence */},
- {0xFC, 0xF8, 4*6, 0x3FFFFFF, 0x200000, /* 5 byte sequence */},
- {0xFE, 0xFC, 5*6, 0x7FFFFFFF, 0x4000000, /* 6 byte sequence */},
- {0, /* end of table */}
-};
-
-#define UNICODE_MAX 0x0010ffff
-#define PLANE_SIZE 0x00010000
-
-#define SURROGATE_MASK 0xfffff800
-#define SURROGATE_PAIR 0x0000d800
-#define SURROGATE_LOW 0x00000400
-#define SURROGATE_BITS 0x000003ff
-
-int utf8_to_utf32(const u8 *s, int inlen, unicode_t *pu)
-{
- unsigned long l;
- int c0, c, nc;
- const struct utf8_table *t;
-
- nc = 0;
- c0 = *s;
- l = c0;
- for (t = utf8_table; t->cmask; t++) {
- nc++;
- if ((c0 & t->cmask) == t->cval) {
- l &= t->lmask;
- if (l < t->lval || l > UNICODE_MAX ||
- (l & SURROGATE_MASK) == SURROGATE_PAIR)
- return -1;
- *pu = (unicode_t) l;
- return nc;
- }
- if (inlen <= nc)
- return -1;
- s++;
- c = (*s ^ 0x80) & 0xFF;
- if (c & 0xC0)
- return -1;
- l = (l << 6) | c;
- }
- return -1;
-}
-EXPORT_SYMBOL(utf8_to_utf32);
-
-int utf32_to_utf8(unicode_t u, u8 *s, int maxout)
-{
- unsigned long l;
- int c, nc;
- const struct utf8_table *t;
-
- if (!s)
- return 0;
-
- l = u;
- if (l > UNICODE_MAX || (l & SURROGATE_MASK) == SURROGATE_PAIR)
- return -1;
-
- nc = 0;
- for (t = utf8_table; t->cmask && maxout; t++, maxout--) {
- nc++;
- if (l <= t->lmask) {
- c = t->shift;
- *s = (u8) (t->cval | (l >> c));
- while (c > 0) {
- c -= 6;
- s++;
- *s = (u8) (0x80 | ((l >> c) & 0x3F));
- }
- return nc;
- }
- }
- return -1;
-}
-EXPORT_SYMBOL(utf32_to_utf8);
-
-static inline void put_utf16(wchar_t *s, unsigned c, enum utf16_endian endian)
-{
- switch (endian) {
- default:
- *s = (wchar_t) c;
- break;
- case UTF16_LITTLE_ENDIAN:
- *s = __cpu_to_le16(c);
- break;
- case UTF16_BIG_ENDIAN:
- *s = __cpu_to_be16(c);
- break;
- }
-}
-
-int utf8s_to_utf16s(const u8 *s, int inlen, enum utf16_endian endian,
- wchar_t *pwcs, int maxout)
-{
- u16 *op;
- int size;
- unicode_t u;
-
- op = pwcs;
- while (inlen > 0 && maxout > 0 && *s) {
- if (*s & 0x80) {
- size = utf8_to_utf32(s, inlen, &u);
- if (size < 0)
- return -EINVAL;
- s += size;
- inlen -= size;
-
- if (u >= PLANE_SIZE) {
- if (maxout < 2)
- break;
- u -= PLANE_SIZE;
- put_utf16(op++, SURROGATE_PAIR |
- ((u >> 10) & SURROGATE_BITS),
- endian);
- put_utf16(op++, SURROGATE_PAIR |
- SURROGATE_LOW |
- (u & SURROGATE_BITS),
- endian);
- maxout -= 2;
- } else {
- put_utf16(op++, u, endian);
- maxout--;
- }
- } else {
- put_utf16(op++, *s++, endian);
- inlen--;
- maxout--;
- }
- }
- return op - pwcs;
-}
-EXPORT_SYMBOL(utf8s_to_utf16s);
-
-static inline unsigned long get_utf16(unsigned c, enum utf16_endian endian)
-{
- switch (endian) {
- default:
- return c;
- case UTF16_LITTLE_ENDIAN:
- return __le16_to_cpu(c);
- case UTF16_BIG_ENDIAN:
- return __be16_to_cpu(c);
- }
-}
-
-int utf16s_to_utf8s(const wchar_t *pwcs, int inlen, enum utf16_endian endian,
- u8 *s, int maxout)
-{
- u8 *op;
- int size;
- unsigned long u, v;
-
- op = s;
- while (inlen > 0 && maxout > 0) {
- u = get_utf16(*pwcs, endian);
- if (!u)
- break;
- pwcs++;
- inlen--;
- if (u > 0x7f) {
- if ((u & SURROGATE_MASK) == SURROGATE_PAIR) {
- if (u & SURROGATE_LOW) {
- /* Ignore character and move on */
- continue;
- }
- if (inlen <= 0)
- break;
- v = get_utf16(*pwcs, endian);
- if ((v & SURROGATE_MASK) != SURROGATE_PAIR ||
- !(v & SURROGATE_LOW)) {
- /* Ignore character and move on */
- continue;
- }
- u = PLANE_SIZE + ((u & SURROGATE_BITS) << 10)
- + (v & SURROGATE_BITS);
- pwcs++;
- inlen--;
- }
- size = utf32_to_utf8(u, op, maxout);
- if (size == -1) {
- /* Ignore character and move on */
- } else {
- op += size;
- maxout -= size;
- }
- } else {
- *op++ = (u8) u;
- maxout--;
- }
- }
- return op - s;
-}
-EXPORT_SYMBOL(utf16s_to_utf8s);
-
int __register_nls(struct nls_table *nls, struct module *owner)
{
struct nls_table ** tmp = &tables;
@@ -299,254 +87,8 @@ void unload_nls(struct nls_table *nls)
module_put(nls->owner);
}
-static const 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*/
- 0x0080, 0x0081, 0x0082, 0x0083,
- 0x0084, 0x0085, 0x0086, 0x0087,
- 0x0088, 0x0089, 0x008a, 0x008b,
- 0x008c, 0x008d, 0x008e, 0x008f,
- /* 0x90*/
- 0x0090, 0x0091, 0x0092, 0x0093,
- 0x0094, 0x0095, 0x0096, 0x0097,
- 0x0098, 0x0099, 0x009a, 0x009b,
- 0x009c, 0x009d, 0x009e, 0x009f,
- /* 0xa0*/
- 0x00a0, 0x00a1, 0x00a2, 0x00a3,
- 0x00a4, 0x00a5, 0x00a6, 0x00a7,
- 0x00a8, 0x00a9, 0x00aa, 0x00ab,
- 0x00ac, 0x00ad, 0x00ae, 0x00af,
- /* 0xb0*/
- 0x00b0, 0x00b1, 0x00b2, 0x00b3,
- 0x00b4, 0x00b5, 0x00b6, 0x00b7,
- 0x00b8, 0x00b9, 0x00ba, 0x00bb,
- 0x00bc, 0x00bd, 0x00be, 0x00bf,
- /* 0xc0*/
- 0x00c0, 0x00c1, 0x00c2, 0x00c3,
- 0x00c4, 0x00c5, 0x00c6, 0x00c7,
- 0x00c8, 0x00c9, 0x00ca, 0x00cb,
- 0x00cc, 0x00cd, 0x00ce, 0x00cf,
- /* 0xd0*/
- 0x00d0, 0x00d1, 0x00d2, 0x00d3,
- 0x00d4, 0x00d5, 0x00d6, 0x00d7,
- 0x00d8, 0x00d9, 0x00da, 0x00db,
- 0x00dc, 0x00dd, 0x00de, 0x00df,
- /* 0xe0*/
- 0x00e0, 0x00e1, 0x00e2, 0x00e3,
- 0x00e4, 0x00e5, 0x00e6, 0x00e7,
- 0x00e8, 0x00e9, 0x00ea, 0x00eb,
- 0x00ec, 0x00ed, 0x00ee, 0x00ef,
- /* 0xf0*/
- 0x00f0, 0x00f1, 0x00f2, 0x00f3,
- 0x00f4, 0x00f5, 0x00f6, 0x00f7,
- 0x00f8, 0x00f9, 0x00fa, 0x00fb,
- 0x00fc, 0x00fd, 0x00fe, 0x00ff,
-};
-
-static const 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 */
-
- 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */
- 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */
- 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */
- 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 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, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */
- 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 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, 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 const unsigned char *const page_uni2charset[256] = {
- page00
-};
-
-static const 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, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */
- 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */
- 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */
- 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 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, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */
- 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 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, 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 const 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, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */
- 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */
- 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */
- 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 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, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */
- 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 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, 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 int uni2char(wchar_t uni, unsigned char *out, int boundlen)
-{
- const 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 const struct nls_ops charset_ops = {
- .uni2char = uni2char,
- .char2uni = char2uni,
-};
-
-static struct nls_table default_table = {
- .charset = "default",
- .ops = &charset_ops,
- .charset2lower = charset2lower,
- .charset2upper = charset2upper,
-};
-
-/* Returns a simple default translation table */
-struct nls_table *load_nls_default(void)
-{
- struct nls_table *default_nls;
-
- default_nls = load_nls(CONFIG_NLS_DEFAULT);
- if (default_nls != NULL)
- return default_nls;
- else
- return &default_table;
-}
-
EXPORT_SYMBOL(unregister_nls);
EXPORT_SYMBOL(unload_nls);
EXPORT_SYMBOL(load_nls);
-EXPORT_SYMBOL(load_nls_default);
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/fs/nls/nls_default.c b/fs/nls/nls_default.c
new file mode 100644
index 000000000000..2cf2c8b12e78
--- /dev/null
+++ b/fs/nls/nls_default.c
@@ -0,0 +1,473 @@
+/*
+ * linux/fs/nls/nls_default.c
+ *
+ * Native language support--charsets and unicode translations.
+ * By Gordon Chaffee 1996, 1997
+ *
+ * Unicode based case conversion 1999 by Wolfram Pienkoss
+ *
+ */
+
+/*
+ * Sample implementation from Unicode home page.
+ * http://www.stonehand.com/unicode/standard/fss-utf.html
+ */
+
+#include <linux/module.h>
+#include <asm/byteorder.h>
+#include <linux/nls.h>
+
+static struct nls_table default_table;
+
+struct utf8_table {
+ int cmask;
+ int cval;
+ int shift;
+ long lmask;
+ long lval;
+};
+
+static const struct utf8_table utf8_table[] =
+{
+ {0x80, 0x00, 0*6, 0x7F, 0, /* 1 byte sequence */},
+ {0xE0, 0xC0, 1*6, 0x7FF, 0x80, /* 2 byte sequence */},
+ {0xF0, 0xE0, 2*6, 0xFFFF, 0x800, /* 3 byte sequence */},
+ {0xF8, 0xF0, 3*6, 0x1FFFFF, 0x10000, /* 4 byte sequence */},
+ {0xFC, 0xF8, 4*6, 0x3FFFFFF, 0x200000, /* 5 byte sequence */},
+ {0xFE, 0xFC, 5*6, 0x7FFFFFFF, 0x4000000, /* 6 byte sequence */},
+ {0, /* end of table */}
+};
+
+#define UNICODE_MAX 0x0010ffff
+#define PLANE_SIZE 0x00010000
+
+#define SURROGATE_MASK 0xfffff800
+#define SURROGATE_PAIR 0x0000d800
+#define SURROGATE_LOW 0x00000400
+#define SURROGATE_BITS 0x000003ff
+
+int utf8_to_utf32(const u8 *s, int inlen, unicode_t *pu)
+{
+ unsigned long l;
+ int c0, c, nc;
+ const struct utf8_table *t;
+
+ nc = 0;
+ c0 = *s;
+ l = c0;
+ for (t = utf8_table; t->cmask; t++) {
+ nc++;
+ if ((c0 & t->cmask) == t->cval) {
+ l &= t->lmask;
+ if (l < t->lval || l > UNICODE_MAX ||
+ (l & SURROGATE_MASK) == SURROGATE_PAIR)
+ return -1;
+ *pu = (unicode_t) l;
+ return nc;
+ }
+ if (inlen <= nc)
+ return -1;
+ s++;
+ c = (*s ^ 0x80) & 0xFF;
+ if (c & 0xC0)
+ return -1;
+ l = (l << 6) | c;
+ }
+ return -1;
+}
+EXPORT_SYMBOL(utf8_to_utf32);
+
+int utf32_to_utf8(unicode_t u, u8 *s, int maxout)
+{
+ unsigned long l;
+ int c, nc;
+ const struct utf8_table *t;
+
+ if (!s)
+ return 0;
+
+ l = u;
+ if (l > UNICODE_MAX || (l & SURROGATE_MASK) == SURROGATE_PAIR)
+ return -1;
+
+ nc = 0;
+ for (t = utf8_table; t->cmask && maxout; t++, maxout--) {
+ nc++;
+ if (l <= t->lmask) {
+ c = t->shift;
+ *s = (u8) (t->cval | (l >> c));
+ while (c > 0) {
+ c -= 6;
+ s++;
+ *s = (u8) (0x80 | ((l >> c) & 0x3F));
+ }
+ return nc;
+ }
+ }
+ return -1;
+}
+EXPORT_SYMBOL(utf32_to_utf8);
+
+static inline void put_utf16(wchar_t *s, unsigned c, enum utf16_endian endian)
+{
+ switch (endian) {
+ default:
+ *s = (wchar_t) c;
+ break;
+ case UTF16_LITTLE_ENDIAN:
+ *s = __cpu_to_le16(c);
+ break;
+ case UTF16_BIG_ENDIAN:
+ *s = __cpu_to_be16(c);
+ break;
+ }
+}
+
+int utf8s_to_utf16s(const u8 *s, int inlen, enum utf16_endian endian,
+ wchar_t *pwcs, int maxout)
+{
+ u16 *op;
+ int size;
+ unicode_t u;
+
+ op = pwcs;
+ while (inlen > 0 && maxout > 0 && *s) {
+ if (*s & 0x80) {
+ size = utf8_to_utf32(s, inlen, &u);
+ if (size < 0)
+ return -EINVAL;
+ s += size;
+ inlen -= size;
+
+ if (u >= PLANE_SIZE) {
+ if (maxout < 2)
+ break;
+ u -= PLANE_SIZE;
+ put_utf16(op++, SURROGATE_PAIR |
+ ((u >> 10) & SURROGATE_BITS),
+ endian);
+ put_utf16(op++, SURROGATE_PAIR |
+ SURROGATE_LOW |
+ (u & SURROGATE_BITS),
+ endian);
+ maxout -= 2;
+ } else {
+ put_utf16(op++, u, endian);
+ maxout--;
+ }
+ } else {
+ put_utf16(op++, *s++, endian);
+ inlen--;
+ maxout--;
+ }
+ }
+ return op - pwcs;
+}
+EXPORT_SYMBOL(utf8s_to_utf16s);
+
+static inline unsigned long get_utf16(unsigned c, enum utf16_endian endian)
+{
+ switch (endian) {
+ default:
+ return c;
+ case UTF16_LITTLE_ENDIAN:
+ return __le16_to_cpu(c);
+ case UTF16_BIG_ENDIAN:
+ return __be16_to_cpu(c);
+ }
+}
+
+int utf16s_to_utf8s(const wchar_t *pwcs, int inlen, enum utf16_endian endian,
+ u8 *s, int maxout)
+{
+ u8 *op;
+ int size;
+ unsigned long u, v;
+
+ op = s;
+ while (inlen > 0 && maxout > 0) {
+ u = get_utf16(*pwcs, endian);
+ if (!u)
+ break;
+ pwcs++;
+ inlen--;
+ if (u > 0x7f) {
+ if ((u & SURROGATE_MASK) == SURROGATE_PAIR) {
+ if (u & SURROGATE_LOW) {
+ /* Ignore character and move on */
+ continue;
+ }
+ if (inlen <= 0)
+ break;
+ v = get_utf16(*pwcs, endian);
+ if ((v & SURROGATE_MASK) != SURROGATE_PAIR ||
+ !(v & SURROGATE_LOW)) {
+ /* Ignore character and move on */
+ continue;
+ }
+ u = PLANE_SIZE + ((u & SURROGATE_BITS) << 10)
+ + (v & SURROGATE_BITS);
+ pwcs++;
+ inlen--;
+ }
+ size = utf32_to_utf8(u, op, maxout);
+ if (size == -1) {
+ /* Ignore character and move on */
+ } else {
+ op += size;
+ maxout -= size;
+ }
+ } else {
+ *op++ = (u8) u;
+ maxout--;
+ }
+ }
+ return op - s;
+}
+EXPORT_SYMBOL(utf16s_to_utf8s);
+
+static const 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*/
+ 0x0080, 0x0081, 0x0082, 0x0083,
+ 0x0084, 0x0085, 0x0086, 0x0087,
+ 0x0088, 0x0089, 0x008a, 0x008b,
+ 0x008c, 0x008d, 0x008e, 0x008f,
+ /* 0x90*/
+ 0x0090, 0x0091, 0x0092, 0x0093,
+ 0x0094, 0x0095, 0x0096, 0x0097,
+ 0x0098, 0x0099, 0x009a, 0x009b,
+ 0x009c, 0x009d, 0x009e, 0x009f,
+ /* 0xa0*/
+ 0x00a0, 0x00a1, 0x00a2, 0x00a3,
+ 0x00a4, 0x00a5, 0x00a6, 0x00a7,
+ 0x00a8, 0x00a9, 0x00aa, 0x00ab,
+ 0x00ac, 0x00ad, 0x00ae, 0x00af,
+ /* 0xb0*/
+ 0x00b0, 0x00b1, 0x00b2, 0x00b3,
+ 0x00b4, 0x00b5, 0x00b6, 0x00b7,
+ 0x00b8, 0x00b9, 0x00ba, 0x00bb,
+ 0x00bc, 0x00bd, 0x00be, 0x00bf,
+ /* 0xc0*/
+ 0x00c0, 0x00c1, 0x00c2, 0x00c3,
+ 0x00c4, 0x00c5, 0x00c6, 0x00c7,
+ 0x00c8, 0x00c9, 0x00ca, 0x00cb,
+ 0x00cc, 0x00cd, 0x00ce, 0x00cf,
+ /* 0xd0*/
+ 0x00d0, 0x00d1, 0x00d2, 0x00d3,
+ 0x00d4, 0x00d5, 0x00d6, 0x00d7,
+ 0x00d8, 0x00d9, 0x00da, 0x00db,
+ 0x00dc, 0x00dd, 0x00de, 0x00df,
+ /* 0xe0*/
+ 0x00e0, 0x00e1, 0x00e2, 0x00e3,
+ 0x00e4, 0x00e5, 0x00e6, 0x00e7,
+ 0x00e8, 0x00e9, 0x00ea, 0x00eb,
+ 0x00ec, 0x00ed, 0x00ee, 0x00ef,
+ /* 0xf0*/
+ 0x00f0, 0x00f1, 0x00f2, 0x00f3,
+ 0x00f4, 0x00f5, 0x00f6, 0x00f7,
+ 0x00f8, 0x00f9, 0x00fa, 0x00fb,
+ 0x00fc, 0x00fd, 0x00fe, 0x00ff,
+};
+
+static const 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 */
+
+ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */
+ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */
+ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */
+ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 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, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */
+ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 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, 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 const unsigned char *const page_uni2charset[256] = {
+ page00
+};
+
+static const 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, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */
+ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */
+ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */
+ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 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, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */
+ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 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, 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 const 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, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */
+ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */
+ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */
+ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 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, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */
+ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 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, 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 int uni2char(wchar_t uni, unsigned char *out, int boundlen)
+{
+ const 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 const struct nls_ops charset_ops = {
+ .uni2char = uni2char,
+ .char2uni = char2uni,
+};
+
+static struct nls_table default_table = {
+ .charset = "default",
+ .ops = &charset_ops,
+ .charset2lower = charset2lower,
+ .charset2upper = charset2upper,
+};
+
+/* Returns a simple default translation table */
+struct nls_table *load_nls_default(void)
+{
+ struct nls_table *default_nls;
+
+ default_nls = load_nls(CONFIG_NLS_DEFAULT);
+ if (default_nls != NULL)
+ return default_nls;
+ else
+ return &default_table;
+}
+EXPORT_SYMBOL(load_nls_default);
--
2.17.0
next prev parent reply other threads:[~2018-05-09 6:49 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-05-09 6:47 [PATCH 00/15] NLS refactor and UTF-8 normalization Gabriel Krisman Bertazi
2018-05-09 6:47 ` [PATCH 01/15] nls: Wrap uni2char/char2uni callers Gabriel Krisman Bertazi
2018-05-09 6:47 ` [PATCH 02/15] nls: Wrap charset field access Gabriel Krisman Bertazi
2018-05-09 6:47 ` [PATCH 03/15] nls: Wrap charset hooks in ops structure Gabriel Krisman Bertazi
2018-05-09 6:47 ` Gabriel Krisman Bertazi [this message]
2018-05-09 14:52 ` [PATCH 04/15] nls: Split default charset from NLS core kbuild test robot
2018-05-15 2:45 ` Gabriel Krisman Bertazi
2018-05-09 6:47 ` [PATCH 05/15] nls: Split struct nls_charset from struct nls_table Gabriel Krisman Bertazi
2018-05-09 14:30 ` kbuild test robot
2018-05-15 2:41 ` Gabriel Krisman Bertazi
2018-05-09 6:47 ` [PATCH 06/15] nls: Add support for multiple versions of an encoding Gabriel Krisman Bertazi
2018-05-09 6:47 ` [PATCH 07/15] nls: Add new interface for string comparisons Gabriel Krisman Bertazi
2018-05-09 6:47 ` [PATCH 08/15] nls: Let charsets define the behavior of tolower/toupper Gabriel Krisman Bertazi
2018-05-09 6:48 ` [PATCH 09/15] nls: Add optional normalization and casefold hooks Gabriel Krisman Bertazi
2018-05-09 6:55 ` [PATCH 10/15] nls: utf8norm: Add unicode character database files Gabriel Krisman Bertazi
2018-05-09 6:55 ` [PATCH 11/15] scripts: add trie generator for UTF-8 Gabriel Krisman Bertazi
2018-05-09 6:55 ` [PATCH 12/15] nls: utf8norm: Introduce code for UTF-8 normalization Gabriel Krisman Bertazi
2018-05-09 17:02 ` kbuild test robot
2018-05-09 18:46 ` Gabriel Krisman Bertazi
2018-05-09 6:55 ` [PATCH 13/15] nls: utf8norm: reduce the size of utf8data[] Gabriel Krisman Bertazi
2018-05-09 6:55 ` [PATCH 14/15] nls: utf8norm: Integrate utf8norm code with NLS subsystem Gabriel Krisman Bertazi
2018-05-09 6:55 ` [PATCH 15/15] nls: utf8norm: Introduce test module for utf8norm implementation Gabriel Krisman Bertazi
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180509064800.28658-5-krisman@collabora.co.uk \
--to=krisman@collabora.co.uk \
--cc=darrick.wong@oracle.com \
--cc=jra@google.com \
--cc=kernel@lists.collabora.co.uk \
--cc=linux-fsdevel@vger.kernel.org \
--cc=olaf@sgi.com \
--cc=tytso@mit.edu \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.