More charset fixes

Properly use the G0/G1 charsets only to map characters being drawn to
the screen. And only decode bytes using either Latin-1 or UTF-8,
defaulting to UTF-8 at startup/reset.
This commit is contained in:
Kovid Goyal
2016-11-30 23:36:10 +05:30
parent 83787fbc40
commit 489504cda5
5 changed files with 44 additions and 32 deletions

View File

@@ -51,8 +51,8 @@ static uint32_t charset_translations[5][256] = {
0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017,
0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f,
0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027,
0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f,
0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037,
0x0028, 0x0029, 0x002a, 0x2192, 0x2190, 0x2191, 0x2193, 0x002f,
0x2588, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037,
0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f,
0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047,
0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f,
@@ -81,10 +81,10 @@ static uint32_t charset_translations[5][256] = {
},
/* IBM Codepage 437 mapped to Unicode */
{
0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007,
0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f,
0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017,
0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f,
0x0000, 0x263a, 0x263b, 0x2665, 0x2666, 0x2663, 0x2660, 0x2022,
0x25d8, 0x25cb, 0x25d9, 0x2642, 0x2640, 0x266a, 0x266b, 0x263c,
0x25b6, 0x25c0, 0x2195, 0x203c, 0x00b6, 0x00a7, 0x25ac, 0x21a8,
0x2191, 0x2193, 0x2192, 0x2190, 0x221f, 0x2194, 0x25b2, 0x25bc,
0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027,
0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f,
0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037,
@@ -116,11 +116,11 @@ static uint32_t charset_translations[5][256] = {
},
// VAX 42 map
{
0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007,
0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f,
0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017,
0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f,
0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027,
0x0000, 0x263a, 0x263b, 0x2665, 0x2666, 0x2663, 0x2660, 0x2022,
0x25d8, 0x25cb, 0x25d9, 0x2642, 0x2640, 0x266a, 0x266b, 0x263c,
0x25b6, 0x25c0, 0x2195, 0x203c, 0x00b6, 0x00a7, 0x25ac, 0x21a8,
0x2191, 0x2193, 0x2192, 0x2190, 0x221f, 0x2194, 0x25b2, 0x25bc,
0x0020, 0x043b, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027,
0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f,
0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037,
0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x0435,
@@ -204,6 +204,9 @@ translation_table(uint32_t which) {
return charset_translations[0];
}
}
uint32_t *latin1_charset = charset_translations[0];
// UTF-8 decode taken from: http://bjoern.hoehrmann.de/utf-8/decoder/dfa/
static const uint8_t utf8_data[] = {