Work on unicode
This commit is contained in:
@@ -33,7 +33,7 @@ arena_init :: (a: *Arena)
|
||||
a.memory = Os.reserve(a.DEFAULT_RESERVE_SIZE)
|
||||
a.alignment = a.DEFAULT_ALIGNMENT
|
||||
a.di = arena_di++
|
||||
a.allocator.proc = arena_allocator_proc
|
||||
// a.allocator.proc = arena_allocator_proc
|
||||
|
||||
arena_push_size :: (a: *Arena, size: SizeU): *void
|
||||
generous_size := size + a.alignment
|
||||
@@ -73,6 +73,80 @@ arena_allocator_proc :: (a: *Allocator, action: ALLOCATOR_ACTION, size: SizeU, o
|
||||
|
||||
allocate :: (a: *Allocator, size: SizeU): *void
|
||||
return a.proc(a, ALLOCATOR_ACTION.ALLOCATE, size, 0)
|
||||
*/
|
||||
|
||||
//
|
||||
// Unicode
|
||||
//
|
||||
question_mark16 :: 0x003f
|
||||
String32 :: struct;; str: *U32; len: S64
|
||||
String16 :: struct;; str: *U16; len: S64
|
||||
|
||||
*/
|
||||
utf8_to_utf32 :: (c: *U8, max_advance: S64): U32, S64
|
||||
out_str: U32
|
||||
advance: S64
|
||||
if (c[0] & 0b10000000) == 0
|
||||
if max_advance >= 1
|
||||
c0 := c[0]->U32
|
||||
out_str = c0
|
||||
advance = 1
|
||||
|
||||
elif (c[0] & 0b11100000) == 0b11000000
|
||||
if (c[1] & 0b11000000) == 0b10000000 // Continuation byte required
|
||||
if max_advance >= 2
|
||||
c0 := c[0]->U32; c1 := c[1]->U32
|
||||
out_str = (c0 & 0b00011111) << 6 | (c1 & 0b00111111)
|
||||
advance = 2
|
||||
|
||||
elif (c[0] & 0b11110000) == 0b11100000
|
||||
if (c[1] & 0b11000000) == 0b10000000 && (c[2] & 0b11000000) == 0b10000000 // Two continuation bytes required
|
||||
if max_advance >= 3
|
||||
c0 := c[0]->U32; c1 := c[1]->U32; c2 := c[2]->U32
|
||||
out_str = (c0 & 0b00001111) << 12 | (c1 & 0b00111111) << 6 | (c2 & 0b00111111)
|
||||
advance = 3
|
||||
|
||||
elif (c[0] & 0b11111000) == 0b11110000
|
||||
if (c[1] & 0b11000000) == 0b10000000 && (c[2] & 0b11000000) == 0b10000000 && (c[3] & 0b11000000) == 0b10000000 // Three continuation bytes required
|
||||
if max_advance >= 4
|
||||
c0 := c[0]->U32; c1 := c[1]->U32; c2 := c[2]->U32; c3 := c[3]->U32
|
||||
out_str = (c0 & 0b00001111) << 18 | (c1 & 0b00111111) << 12 | (c2 & 0b00111111) << 6 | (c3 & 0b00111111)
|
||||
advance = 4
|
||||
|
||||
return out_str, advance
|
||||
|
||||
utf32_to_utf16 :: (codepoint: U32): [2]U16, S64
|
||||
str: [2]U16
|
||||
len := 0
|
||||
if codepoint < 0x10000
|
||||
str[0] = codepoint->U16
|
||||
len = 1
|
||||
elif codepoint <= 0x10FFFF
|
||||
code: U32 = (codepoint - 0x10000)
|
||||
str[0] = (0xD800 | (code >> 10))->U16
|
||||
str[1] = (0xDC00 | (code & 0x3FF))->U16
|
||||
len = 2
|
||||
|
||||
return str, len
|
||||
|
||||
string_to_string16 :: (arena: *Arena, in: String): String16
|
||||
in_str := &in[0]
|
||||
// @Note(Krzosa): Should be more then enough space
|
||||
alloc_size := (length_of(in)*2)+1
|
||||
result := String16{str = arena_push_size(arena, alloc_size->U64)}
|
||||
for i := 0, i < length_of(in)
|
||||
s32, s32_len := utf8_to_utf32(in_str + i, length_of(in) - i)
|
||||
if s32_len != 0
|
||||
i += s32_len
|
||||
s16, s16_len := utf32_to_utf16(s32)
|
||||
if s16_len != 0
|
||||
for j := 0, j < s16_len, j++
|
||||
result.str[result.len++] = s16[j]
|
||||
else
|
||||
result.str[result.len++] = question_mark16
|
||||
break
|
||||
else
|
||||
result.str[result.len++] = question_mark16
|
||||
break
|
||||
|
||||
result.str[result.len] = 0
|
||||
return result
|
||||
|
||||
Reference in New Issue
Block a user