a1c965da1e
Sixty-five headers sat side by side in include/, so `#include "irq.h"` said nothing about where irq.h was or what it belonged to, and errno.h, stat.h and fcntl.h at the top shadowed the system's for any host tool built with -I./include. They are in folders now -- arch/ core/ fs/ dev/ gfx/ net/ uapi/ (and ldls/ for the Linux driver layer) -- and every include names the folder, as Linux's do: "core/proc.h". Done mechanically and checked the hard way: the kernel built from this tree disassembles identically to the one built from the tree before it. The full image boots, and userland is the same set of programs. Paths in docs and comments follow; docs/guides/layout.md has a table of what is where, and tools/fix-includes.py rewrites old-style includes from the folders in the tree, for code written before this. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01S1giNvrHTrPMPw7V6x1kQ4
297 lines
11 KiB
C
297 lines
11 KiB
C
// Keyboard layouts. See include/dev/keymap.h for the interface and its limits.
|
||
//
|
||
// Every table is indexed by set-1 scancode, with the E0-prefixed keys folded
|
||
// into 0x80..0xFF by kbd.c before the lookup -- the same numbering the single
|
||
// hardcoded table used, so a layout is a diff against a shape that was already
|
||
// proven to work rather than a new mapping to get wrong.
|
||
//
|
||
// The tables are `uint32` and not `uchar`. That is the whole reason this file
|
||
// exists: `ą` is U+0105 and does not fit in a byte, and a Polish layout that
|
||
// cannot type `ą` is not one.
|
||
|
||
#include "core/types.h"
|
||
#include "core/defs.h"
|
||
#include "dev/kbd.h"
|
||
#include "dev/keymap.h"
|
||
|
||
// Shared by every layout that does not move the navigation block, which is
|
||
// all of them -- the arrow keys are not a national matter. Merged into each
|
||
// level table below rather than consulted separately, because a layout is
|
||
// allowed to disagree and none currently does.
|
||
#define NAV_KEYS \
|
||
[0xC8] = KBD_UP, [0xD0] = KBD_DN, \
|
||
[0xC9] = KBD_PGUP, [0xD1] = KBD_PGDN, \
|
||
[0xCB] = KBD_LF, [0xCD] = KBD_RT, \
|
||
[0x97] = KBD_HOME, [0xCF] = KBD_END, \
|
||
[0xD2] = KBD_INS, [0xD3] = KBD_DEL, \
|
||
[0x9C] = '\n', /* KP_Enter */ \
|
||
[0xB5] = '/' /* KP_Div */
|
||
|
||
// --- US ---------------------------------------------------------------------
|
||
|
||
static const uint32 us_plain[256] = {
|
||
NO, 0x1B, '1', '2', '3', '4', '5', '6', // 0x00
|
||
'7', '8', '9', '0', '-', '=', '\b', '\t',
|
||
'q', 'w', 'e', 'r', 't', 'y', 'u', 'i', // 0x10
|
||
'o', 'p', '[', ']', '\n', NO, 'a', 's',
|
||
'd', 'f', 'g', 'h', 'j', 'k', 'l', ';', // 0x20
|
||
'\'', '`', NO, '\\', 'z', 'x', 'c', 'v',
|
||
'b', 'n', 'm', ',', '.', '/', NO, '*', // 0x30
|
||
NO, ' ', NO, NO, NO, NO, NO, NO,
|
||
NO, NO, NO, NO, NO, NO, NO, '7', // 0x40
|
||
'8', '9', '-', '4', '5', '6', '+', '1',
|
||
'2', '3', '0', '.', NO, NO, NO, NO, // 0x50
|
||
NAV_KEYS
|
||
};
|
||
|
||
static const uint32 us_shift[256] = {
|
||
NO, 0x1B, '!', '@', '#', '$', '%', '^', // 0x00
|
||
'&', '*', '(', ')', '_', '+', '\b', '\t',
|
||
'Q', 'W', 'E', 'R', 'T', 'Y', 'U', 'I', // 0x10
|
||
'O', 'P', '{', '}', '\n', NO, 'A', 'S',
|
||
'D', 'F', 'G', 'H', 'J', 'K', 'L', ':', // 0x20
|
||
'"', '~', NO, '|', 'Z', 'X', 'C', 'V',
|
||
'B', 'N', 'M', '<', '>', '?', NO, '*', // 0x30
|
||
NO, ' ', NO, NO, NO, NO, NO, NO,
|
||
NO, NO, NO, NO, NO, NO, NO, '7', // 0x40
|
||
'8', '9', '-', '4', '5', '6', '+', '1',
|
||
'2', '3', '0', '.', NO, NO, NO, NO, // 0x50
|
||
NAV_KEYS
|
||
};
|
||
|
||
// --- Polish (programmers) ---------------------------------------------------
|
||
//
|
||
// US QWERTY with nine letters on AltGr. This is the layout essentially every
|
||
// Polish developer uses, and the reason is that the alternative -- "Polish
|
||
// (214)", a genuine national arrangement -- moves Y, Z and most of the
|
||
// punctuation, which makes every shell and every editor shortcut land
|
||
// somewhere else. The diacritics go on AltGr and nothing else moves.
|
||
//
|
||
// AltGr+x is ź and AltGr+z is ż, which looks arbitrary and is not: the letter
|
||
// x is unused in Polish, so its key is free, and ź and ż both need one.
|
||
|
||
static const uint32 pl_altgr[256] = {
|
||
[0x1E] = 0x0105, // a -> ą
|
||
[0x2E] = 0x0107, // c -> ć
|
||
[0x12] = 0x0119, // e -> ę
|
||
[0x26] = 0x0142, // l -> ł
|
||
[0x31] = 0x0144, // n -> ń
|
||
[0x18] = 0x00F3, // o -> ó
|
||
[0x1F] = 0x015B, // s -> ś
|
||
[0x2D] = 0x017A, // x -> ź
|
||
[0x2C] = 0x017C, // z -> ż
|
||
};
|
||
|
||
static const uint32 pl_shiftaltgr[256] = {
|
||
[0x1E] = 0x0104, // A -> Ą
|
||
[0x2E] = 0x0106, // C -> Ć
|
||
[0x12] = 0x0118, // E -> Ę
|
||
[0x26] = 0x0141, // L -> Ł
|
||
[0x31] = 0x0143, // N -> Ń
|
||
[0x18] = 0x00D3, // O -> Ó
|
||
[0x1F] = 0x015A, // S -> Ś
|
||
[0x2D] = 0x0179, // X -> Ź
|
||
[0x2C] = 0x017B, // Z -> Ż
|
||
};
|
||
|
||
// --- German (QWERTZ) --------------------------------------------------------
|
||
//
|
||
// Y and Z swap, the umlauts and ß take the punctuation keys on the home and
|
||
// top rows, and the key between left Shift and Z -- scancode 0x56, which a US
|
||
// keyboard does not have at all -- carries < > |.
|
||
//
|
||
// The acute (0x0D) and circumflex (0x29) keys are dead on a real German
|
||
// layout. Here they type the accent on its own. See include/dev/keymap.h.
|
||
|
||
static const uint32 de_plain[256] = {
|
||
NO, 0x1B, '1', '2', '3', '4', '5', '6', // 0x00
|
||
'7', '8', '9', '0', 0x00DF, 0x00B4, '\b', '\t', // ß ´
|
||
'q', 'w', 'e', 'r', 't', 'z', 'u', 'i', // 0x10
|
||
'o', 'p', 0x00FC, '+', '\n', NO, 'a', 's', // ü
|
||
'd', 'f', 'g', 'h', 'j', 'k', 'l', 0x00F6, // ö
|
||
0x00E4, '^', NO, '#', 'y', 'x', 'c', 'v', // ä
|
||
'b', 'n', 'm', ',', '.', '-', NO, '*', // 0x30
|
||
NO, ' ', NO, NO, NO, NO, NO, NO,
|
||
NO, NO, NO, NO, NO, NO, NO, '7', // 0x40
|
||
'8', '9', '-', '4', '5', '6', '+', '1',
|
||
'2', '3', '0', ',', NO, NO, '<', NO, // 0x50, 0x56 = <>|
|
||
NAV_KEYS
|
||
};
|
||
|
||
static const uint32 de_shift[256] = {
|
||
NO, 0x1B, '!', '"', 0x00A7, '$', '%', '&', // 0x00 §
|
||
'/', '(', ')', '=', '?', '`', '\b', '\t',
|
||
'Q', 'W', 'E', 'R', 'T', 'Z', 'U', 'I', // 0x10
|
||
'O', 'P', 0x00DC, '*', '\n', NO, 'A', 'S', // Ü
|
||
'D', 'F', 'G', 'H', 'J', 'K', 'L', 0x00D6, // Ö
|
||
0x00C4, 0x00B0, NO, '\'', 'Y', 'X', 'C', 'V', // Ä °
|
||
'B', 'N', 'M', ';', ':', '_', NO, '*', // 0x30
|
||
NO, ' ', NO, NO, NO, NO, NO, NO,
|
||
NO, NO, NO, NO, NO, NO, NO, '7', // 0x40
|
||
'8', '9', '-', '4', '5', '6', '+', '1',
|
||
'2', '3', '0', ',', NO, NO, '>', NO, // 0x50
|
||
NAV_KEYS
|
||
};
|
||
|
||
static const uint32 de_altgr[256] = {
|
||
[0x03] = 0x00B2, // 2 -> ²
|
||
[0x04] = 0x00B3, // 3 -> ³
|
||
[0x08] = '{', // 7
|
||
[0x09] = '[', // 8
|
||
[0x0A] = ']', // 9
|
||
[0x0B] = '}', // 0
|
||
[0x0C] = '\\', // ß
|
||
[0x10] = '@', // q
|
||
[0x12] = 0x20AC, // e -> €
|
||
[0x1B] = '~', // +
|
||
[0x32] = 0x00B5, // m -> µ
|
||
[0x56] = '|',
|
||
};
|
||
|
||
// --- the catalogue ----------------------------------------------------------
|
||
//
|
||
// Order matters only in that the first entry is the default. US, because a
|
||
// machine whose keyboard layout has never been set should behave the way the
|
||
// scancodes are printed on the majority of keyboards, and because every
|
||
// installation instruction anyone follows is written in ASCII.
|
||
|
||
static const struct keylayout layouts[] = {
|
||
{ "us", "English (US), QWERTY",
|
||
{ us_plain, us_shift, 0, 0 } },
|
||
{ "pl", "Polish (programmers) -- US QWERTY, diacritics on AltGr",
|
||
{ us_plain, us_shift, pl_altgr, pl_shiftaltgr } },
|
||
{ "de", "German, QWERTZ -- no dead keys, so the accent keys type the accent",
|
||
{ de_plain, de_shift, de_altgr, 0 } },
|
||
};
|
||
|
||
#define NLAYOUTS ((int)(sizeof(layouts) / sizeof(layouts[0])))
|
||
|
||
static const struct keylayout *active = &layouts[0];
|
||
|
||
const struct keylayout *
|
||
keymap_active(void)
|
||
{
|
||
return active;
|
||
}
|
||
|
||
const struct keylayout *
|
||
keymap_by_index(int i)
|
||
{
|
||
if (i < 0 || i >= NLAYOUTS)
|
||
return 0;
|
||
return &layouts[i];
|
||
}
|
||
|
||
int
|
||
keymap_set(const char *name)
|
||
{
|
||
for (int i = 0; i < NLAYOUTS; i++) {
|
||
const char *a = layouts[i].name, *b = name;
|
||
while (*a && *a == *b) { a++; b++; }
|
||
if (*a == 0 && *b == 0) {
|
||
active = &layouts[i];
|
||
return 0;
|
||
}
|
||
}
|
||
return -1;
|
||
}
|
||
|
||
// A control character from the plain codepoint rather than from a table of
|
||
// its own.
|
||
//
|
||
// The table this replaces was indexed by scancode, which quietly assumed a US
|
||
// keyboard: on QWERTZ, Ctrl+Z and Ctrl+Y would have swapped with the letters,
|
||
// so suspending a job would have depended on the layout. Deriving from what
|
||
// the key actually types is both shorter and correct everywhere.
|
||
static uint32
|
||
control_of(uint32 cp)
|
||
{
|
||
if (cp >= 'a' && cp <= 'z') return cp - 'a' + 1;
|
||
if (cp >= 'A' && cp <= 'Z') return cp - 'A' + 1;
|
||
switch (cp) {
|
||
case '@': case ' ': case '2': return 0; // NUL
|
||
case '[': return 0x1B; // ESC
|
||
case '\\': return 0x1C;
|
||
case ']': return 0x1D;
|
||
case '^': case '6': return 0x1E;
|
||
case '_': case '-': case '/': return 0x1F;
|
||
case '?': return 0x7F;
|
||
case '\n': case '\r': return '\r';
|
||
}
|
||
return 0; // no control character on this key
|
||
}
|
||
|
||
// Upper <-> lower for the letters these layouts can produce.
|
||
//
|
||
// Caps Lock needs this and Shift does not: Shift has its own table, so the
|
||
// layout has already said what the shifted key gives. Caps Lock has no table
|
||
// -- it applies to whatever came out, including `ą` from the AltGr level --
|
||
// so the case pair has to be derived from the codepoint.
|
||
//
|
||
// Latin Extended-A is laid out in alternating pairs, but not all the same way
|
||
// round: U+0100..U+0137 and U+014A..U+0177 have the capital on the even
|
||
// codepoint, while U+0139..U+0148 and U+0179..U+017E have it on the odd one.
|
||
// L-stroke is U+0141/U+0142 and Z-dot is U+017B/U+017C, so Polish lands in
|
||
// both halves and getting the parity wrong would shift one of them to a
|
||
// neighbouring letter rather than to its own capital.
|
||
static uint32
|
||
case_toggle(uint32 cp)
|
||
{
|
||
if (cp >= 'a' && cp <= 'z') return cp - 'a' + 'A';
|
||
if (cp >= 'A' && cp <= 'Z') return cp - 'A' + 'a';
|
||
|
||
// Latin-1: the accented letters run C0..DE and E0..FE, with multiplication
|
||
// and division signs punched out of the middle of each. Eszett (DF) has no
|
||
// single-codepoint capital and stays as it is.
|
||
if (cp >= 0xC0 && cp <= 0xDE && cp != 0xD7) return cp + 0x20;
|
||
if (cp >= 0xE0 && cp <= 0xFE && cp != 0xF7) return cp - 0x20;
|
||
|
||
if ((cp >= 0x0100 && cp <= 0x0137) || (cp >= 0x014A && cp <= 0x0177))
|
||
return (cp & 1) ? cp - 1 : cp + 1; // even is the capital
|
||
if ((cp >= 0x0139 && cp <= 0x0148) || (cp >= 0x0179 && cp <= 0x017E))
|
||
return (cp & 1) ? cp + 1 : cp - 1; // odd is the capital
|
||
|
||
return cp;
|
||
}
|
||
|
||
uint32
|
||
keymap_lookup(uint scancode, uint mods)
|
||
{
|
||
const struct keylayout *l = active;
|
||
uint32 cp;
|
||
|
||
if (scancode > 0xFF)
|
||
return 0;
|
||
|
||
// AltGr first. It is the only modifier that selects a whole different table,
|
||
// and on a layout that has no AltGr level the lookup falls back rather than
|
||
// producing nothing -- otherwise holding AltGr on a US keyboard would make
|
||
// every key dead.
|
||
int level = KM_PLAIN;
|
||
if (mods & RALT) level = (mods & SHIFT) ? KM_SHIFTALTGR : KM_ALTGR;
|
||
else if (mods & SHIFT) level = KM_SHIFT;
|
||
|
||
cp = l->level[level] ? l->level[level][scancode] : 0;
|
||
if (cp == 0 && level >= KM_ALTGR) {
|
||
level = (mods & SHIFT) ? KM_SHIFT : KM_PLAIN;
|
||
cp = l->level[level] ? l->level[level][scancode] : 0;
|
||
}
|
||
if (cp == 0)
|
||
return 0;
|
||
|
||
// Caps Lock is a letter-case toggle, not a Shift: it applies to whatever
|
||
// the table produced, including a letter that only exists on AltGr. `ą`
|
||
// with Caps Lock on is `Ą`, and only the layout knows that -- so the case
|
||
// pair has to come from the codepoint, not from a second table lookup.
|
||
if ((mods & CAPSLOCK) && cp < KBD_SPECIAL)
|
||
cp = case_toggle(cp);
|
||
|
||
// Ctrl is last and overrides: Ctrl+Shift+C is still Ctrl+C.
|
||
if (mods & CTL) {
|
||
if (cp >= KBD_SPECIAL)
|
||
return cp; // Ctrl+arrow stays an arrow
|
||
return control_of(cp);
|
||
}
|
||
|
||
return cp;
|
||
}
|