devs/foxbox
1
0
Fork 0
forked from len0rd/rockbox
Code Pull requests Activity

some unicode fixes by Frank Dischner

Browse source 
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@8988 a1c6a512-1295-4272-9138-f99709370657
This commit is contained in:
Marcoen Hirschberg 2006-03-10 11:13:21 +00:00
parent 16a292d65c
commit ea4dea67ae
2 changed files with 12 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

23
firmware/common/unicode.c
View file

@ -41,7 +41,7 @@ static const char *filename[NUM_TABLES] =
static const char cp_2_table[NUM_CODEPAGES] = static const char cp_2_table[NUM_CODEPAGES] =
{ {
0, 1, 1, 1, 1, 1, 1, 1, 2, 3, 4, 5 0, 1, 1, 1, 1, 1, 1, 1, 2, 3, 4, 5, 0
}; };
/* Load codepage file into memory */ /* Load codepage file into memory */
@ -52,7 +52,7 @@ int load_cp_table(int cp)
int file, tablesize; int file, tablesize;
unsigned char tmp[2]; unsigned char tmp[2];
if (cp == 0 || table == loaded_cp_table) if (table == 0 || table == loaded_cp_table)
return 1; return 1;
file = open(filename[table-1], O_RDONLY|O_BINARY); file = open(filename[table-1], O_RDONLY|O_BINARY);
@ -114,7 +114,7 @@ unsigned char* iso_decode(const unsigned char *iso, unsigned char *utf8,
if (!load_cp_table(cp)) cp = 0; if (!load_cp_table(cp)) cp = 0;
while (count--) { while (count--) {
if (*iso < 128) if (*iso < 128 || cp == 0x0C) /* Already UTF-8 */
*utf8++ = *iso++; *utf8++ = *iso++;
else { else {
@ -125,7 +125,7 @@ unsigned char* iso_decode(const unsigned char *iso, unsigned char *utf8,
case 0x02: /* Hebrew (ISO-8859-8) */ case 0x02: /* Hebrew (ISO-8859-8) */
case 0x03: /* Russian (CP1251) */ case 0x03: /* Russian (CP1251) */
case 0x04: /* Thai (ISO-8859-11) */ case 0x04: /* Thai (ISO-8859-11) */
case 0x05: /* Arabic (ISO-8859-6) */ case 0x05: /* Arabic (CP1256) */
case 0x06: /* Turkish (ISO-8859-9) */ case 0x06: /* Turkish (ISO-8859-9) */
case 0x07: /* Latin Extended (ISO-8859-2) */ case 0x07: /* Latin Extended (ISO-8859-2) */
tmp = ((cp-1)*128) + (*iso++ - 128); tmp = ((cp-1)*128) + (*iso++ - 128);
@ -134,7 +134,7 @@ unsigned char* iso_decode(const unsigned char *iso, unsigned char *utf8,
case 0x08: /* Japanese (SJIS) */ case 0x08: /* Japanese (SJIS) */
if (*iso > 0xA0 && *iso < 0xE0) { if (*iso > 0xA0 && *iso < 0xE0) {
tmp = *iso | 0xA100; tmp = *iso++ | (0xA100 - 0x8000);
ucs = codepage_table[tmp]; ucs = codepage_table[tmp];
break; break;
} }
@ -156,14 +156,13 @@ unsigned char* iso_decode(const unsigned char *iso, unsigned char *utf8,
count--; count--;
break; break;
case 0x0C: /* UTF-8, do nothing */
default: default:
ucs = *iso++; ucs = *iso++;
break; break;
} }
if (ucs == 0) /* unknown char, assume invalid encoding */ if (ucs == 0) /* unknown char, use replacement char */
ucs = 0xffff; ucs = 0xfffd;
utf8 = utf8encode(ucs, utf8); utf8 = utf8encode(ucs, utf8);
} }
} }
@ -268,7 +267,7 @@ const unsigned char* utf8decode(const unsigned char *utf8, unsigned short *ucs)
code = c & 0x07; code = c & 0x07;
} else { } else {
/* Invalid size. */ /* Invalid size. */
code = 0xffff; code = 0xfffd;
} }
while (tail-- && ((c = *utf8++) != 0)) { while (tail-- && ((c = *utf8++) != 0)) {
@ -278,17 +277,17 @@ const unsigned char* utf8decode(const unsigned char *utf8, unsigned short *ucs)
} else { } else {
/* Invalid continuation char */ /* Invalid continuation char */
code = 0xffff; code = 0xfffd;
utf8--; utf8--;
break; break;
} }
} }
} else { } else {
/* Invalid UTF-8 char */ /* Invalid UTF-8 char */
code = 0xffff; code = 0xfffd;
} }
/* currently we don't support chars above U-FFFF */ /* currently we don't support chars above U-FFFF */
*ucs = (code < 0x10000) ? code : 0xffff; *ucs = (code < 0x10000) ? code : 0xfffd;
return utf8; return utf8;
} }

1
firmware/include/rbunicode.h
View file

@ -15,7 +15,6 @@
#define MASK 0xC0 /* 11000000 */ #define MASK 0xC0 /* 11000000 */
#define COMP 0x80 /* 10x */ #define COMP 0x80 /* 10x */
extern int codepage;
/* Encode a UCS value as UTF-8 and return a pointer after this UTF-8 char. */ /* Encode a UCS value as UTF-8 and return a pointer after this UTF-8 char. */
unsigned char* utf8encode(unsigned long ucs, unsigned char *utf8); unsigned char* utf8encode(unsigned long ucs, unsigned char *utf8);