unicode: Support characters beyond the first unicode plane

We used 16-bit variables to store the 'character code' everywhere but
this won't let us represent anything beyond U+FFFF.

This patch changes those variables to a custom type that can be 32 or 16
bits depending on the build, and adjusts numerous internal APIs and
datastructures to match.  This includes:

 * utf8decode() and friends
 * font manipulation, caching, rendering, and generation
 * on-screen keyboard
 * FAT filesystem (parsing and generating utf16 LFNs)
 * WIN32 simulator platform code

Note that this patch doesn't _enable_ >16bit unicode support; a followup
patch will turn that on for appropriate targets.

Appears to work on:

  * hosted linux, native, linux simulator in both 16/32-bit modes.

Needs testing on:

  * windows and macos simulator (16bit+32bit)

Change-Id: Iba111b27d2433019b6bff937cf1ebd2c4353a0e8
This commit is contained in:
Solomon Peachy 2024-12-17 08:55:21 -05:00
parent 2a88253426
commit a2c10f6189
44 changed files with 476 additions and 330 deletions

View file

@ -385,7 +385,7 @@ static void LCDFN(mono_bmp_part_helper)(const unsigned char *src, int src_x,
/* put a string at a given pixel position, skipping first ofs pixel columns */
static void LCDFN(putsxyofs)(int x, int y, int ofs, const unsigned char *str)
{
unsigned short *ucs;
ucschar_t *ucs;
struct viewport *vp = LCDFN(current_viewport);
font_lock(vp->font, true);
struct font* pf = font_get(vp->font);
@ -429,7 +429,7 @@ static void LCDFN(putsxyofs)(int x, int y, int ofs, const unsigned char *str)
bool is_rtl, is_diac;
const unsigned char *bits;
int width, base_width, base_ofs = 0;
const unsigned short next_ch = ucs[1];
const ucschar_t next_ch = ucs[1];
if (x >= vp->width)
break;
@ -447,7 +447,7 @@ static void LCDFN(putsxyofs)(int x, int y, int ofs, const unsigned char *str)
{
if (!rtl_next_non_diac_width)
{
const unsigned short *u;
const ucschar_t *u;
/* Jump to next non-diacritic char, and calc its width */
for (u = &ucs[1]; *u && IS_DIACRITIC(*u); u++);
@ -529,7 +529,7 @@ static void LCDFN(putsxyofs)(int x, int y, int ofs, const unsigned char *str)
/* put a string at a given pixel position, skipping first ofs pixel columns */
static void LCDFN(putsxyofs)(int x, int y, int ofs, const unsigned char *str)
{
unsigned short *ucs;
ucschar_t *ucs;
struct viewport *vp = LCDFN(current_viewport);
struct font* pf = font_get(vp->font);
const unsigned char *bits;
@ -567,7 +567,7 @@ static void LCDFN(putsxyofs)(int x, int y, int ofs, const unsigned char *str)
/* allow utf but no diacritics or rtl lang */
for (ucs = bidi_l2v(str, 1); *ucs; ucs++)
{
const unsigned short next_ch = ucs[1];
const ucschar_t next_ch = ucs[1];
if (x >= vp->width)
break;