Files
ww/lib/ascii/ascii.ww
Hojun-Cho 1657bdeda3 ww: import toolchain — C bootstrap + ww-side self-host (phases 0-10)
C bootstrap (phases 0-9):
  cmd/wwc, cmd/6c, cmd/6a, cmd/6l, cmd/ww, rt, lib/*.

ww-side self-host (phase 10):
  selfhost/cmd/wwc — ww-cgen frontend; bootstrap fixed point.
  selfhost/cmd/6a  — assembler; byte-identical to C 6a (test 991).
  selfhost/cmd/6l  — linker w/ archive (.a) support; byte-identical
                     to C 6l (test 992).
  selfhost/cmd/ww  — driver (build/run/version); byte-identical to
                     C ww (test 993).

make test: 15/15. make bootstrap: ww2.s == ww3.s, ww2.o == ww3.o,
ww2 == ww3 byte-identical, with the full ww-tooled chain.
2026-05-11 02:17:47 +09:00

93 lines
2.3 KiB
Plaintext

// ascii — byte-class predicates and case folding for the ASCII range.
// Matches Hare's ascii::isdigit family. Bytes outside 0..127 always
// answer `false`. The lexer hot path uses these inline; they are
// expected to inline to a couple of compares.
export fn isdigit(c: u8) bool = {
if (c < 48u8) { return false; };
if (c > 57u8) { return false; };
return true;
};
export fn isupper(c: u8) bool = {
if (c < 65u8) { return false; };
if (c > 90u8) { return false; };
return true;
};
export fn islower(c: u8) bool = {
if (c < 97u8) { return false; };
if (c > 122u8) { return false; };
return true;
};
export fn isalpha(c: u8) bool = {
if (isupper(c)) { return true; };
return islower(c);
};
export fn isalnum(c: u8) bool = {
if (isalpha(c)) { return true; };
return isdigit(c);
};
// isspace — the C/Hare set: space, tab, NL, VT, FF, CR.
export fn isspace(c: u8) bool = {
if (c == 32u8) { return true; }; // ' '
if (c == 9u8) { return true; }; // '\t'
if (c == 10u8) { return true; }; // '\n'
if (c == 11u8) { return true; }; // '\v'
if (c == 12u8) { return true; }; // '\f'
if (c == 13u8) { return true; }; // '\r'
return false;
};
export fn ishex(c: u8) bool = {
if (isdigit(c)) { return true; };
if (c >= 65u8) {
if (c <= 70u8) { return true; }; // 'A'..'F'
};
if (c >= 97u8) {
if (c <= 102u8) { return true; }; // 'a'..'f'
};
return false;
};
// digitval — value of `c` as a hex/decimal digit, or -1 if not one.
// Useful when scanning numeric literals.
export fn digitval(c: u8) i32 = {
if (isdigit(c)) { return (c - 48u8): i32; };
if (c >= 65u8) {
if (c <= 70u8) { return ((c - 65u8) + 10u8): i32; };
};
if (c >= 97u8) {
if (c <= 102u8) { return ((c - 97u8) + 10u8): i32; };
};
return -1;
};
// isidstart / isidpart — identifier classes used by the lexer.
// Alpha or '_' starts; alnum or '_' continues.
export fn isidstart(c: u8) bool = {
if (isalpha(c)) { return true; };
if (c == 95u8) { return true; }; // '_'
return false;
};
export fn isidpart(c: u8) bool = {
if (isalnum(c)) { return true; };
if (c == 95u8) { return true; };
return false;
};
// tolower / toupper — fold ASCII case. Non-letters pass through.
export fn tolower(c: u8) u8 = {
if (isupper(c)) { return c + 32u8; };
return c;
};
export fn toupper(c: u8) u8 = {
if (islower(c)) { return c - 32u8; };
return c;
};