ww/lib/strconv/strconv.ww

// strconv — number↔string conversions.
//
// Mirrors Hare's strconv:: surface. The *tos functions return a
// `const str` view into a module-level buffer that is overwritten on
// the next call to the same function; callers must copy the bytes if
// they need to outlive the next invocation. See [[strings.dup]] to
// duplicate. Matches Hare's strconv::*tos semantics.

package strconv;

import os;
import strings;

// invalid — input wasn't a valid number in the requested format.
// Payload is the byte index of the first offending position.
// Mirrors Hare's strconv::invalid = !size.
export type invalid = !i32;

// overflow — input was valid but doesn't fit the target type.
// Mirrors Hare's strconv::overflow = !void.
export type overflow = !void;

// error — any error from a strconv call. Mirrors Hare's strconv::error.
export type error = !(invalid | overflow);

// base — numeric base for parsing/formatting. Mirrors Hare's
// `strconv::base` (Hare uses `enum uint`; we pick `enum i32` since
// the underlying parse/format loops index with i32).
//
// HEX is an alias for HEX_UPPER; HEX_LOWER is a pseudo-base that
// produces lowercase a-f digits.
export type base = enum i32 {
	DEFAULT   = 0,
	BIN       = 2,
	OCT       = 8,
	DEC       = 10,
	HEX_UPPER = 16,
	HEX       = 16,
	HEX_LOWER = 17,
};

fn basenum(b: base) i64 = {
	if (b == base.BIN)       { return 2;  };
	if (b == base.OCT)       { return 8;  };
	if (b == base.HEX)       { return 16; };
	if (b == base.HEX_UPPER) { return 16; };
	if (b == base.HEX_LOWER) { return 16; };
	return 10;	// DEC and DEFAULT
};

fn basedigit(d: i64, b: base) u8 = {
	if (d < 10) { return (d + 48): u8; };
	let off: i64 = d - 10;
	if (b == base.HEX_LOWER) { return (off + 97): u8; };
	return (off + 65): u8;
};

// u64tos — convert v to a base-b numeric string. Returns a view into
// `u64tos_buf` which is overwritten on the next call. Matches Hare's
// strconv::u64tos.
let u64tos_buf: [65]u8;

export fn u64tos(v: u64, b: base) str = {
	let nb: u64 = basenum(b): u64;
	let tmp: [65]u8;
	let i: i32 = 0;
	let n: u64 = v;
	if (n == 0u64) { tmp[0] = 48u8; i = 1; };
	for (n > 0u64) {
		let d: i64 = (n % nb): i64;
		tmp[i] = basedigit(d, b);
		n = n / nb;
		i += 1;
	};
	let out: i32 = 0;
	for (i > 0) {
		i -= 1;
		u64tos_buf[out] = tmp[i];
		out += 1;
	};
	let r: str;
	r.ptr = &u64tos_buf[0];
	r.len = out;
	return r;
};

// i64tos — convert v to a base-b numeric string. Returns a view into
// `i64tos_buf` which is overwritten on the next call. Independent
// buffer from u64tos so i64tos's own call to u64tos doesn't clobber
// the in-flight result. Matches Hare's strconv::i64tos.
let i64tos_buf: [66]u8;

export fn i64tos(v: i64, b: base) str = {
	let neg: bool = false;
	let n: i64 = v;
	if (n < 0) { neg = true; n = -n; };
	let nb: i64 = basenum(b);
	let tmp: [65]u8;
	let i: i32 = 0;
	if (n == 0) { tmp[0] = 48u8; i = 1; };
	for (n > 0) {
		let d: i64 = n % nb;
		tmp[i] = basedigit(d, b);
		n = n / nb;
		i += 1;
	};
	let out: i32 = 0;
	if (neg) { i64tos_buf[out] = 45u8; out += 1; };	// '-'
	for (i > 0) {
		i -= 1;
		i64tos_buf[out] = tmp[i];
		out += 1;
	};
	let r: str;
	r.ptr = &i64tos_buf[0];
	r.len = out;
	return r;
};

export fn i32tos(v: i32, b: base) str = { return i64tos(v: i64, b); };
export fn i16tos(v: i16, b: base) str = { return i64tos(v: i64, b); };
export fn i8tos(v: i8,   b: base) str = { return i64tos(v: i64, b); };

export fn u32tos(v: u32, b: base) str = { return u64tos(v: u64, b); };
export fn u16tos(v: u16, b: base) str = { return u64tos(v: u64, b); };
export fn u8tos(v: u8,   b: base) str = { return u64tos(v: u64, b); };

// digval — value of digit byte `c` under base `b`, or -1 if not a
// valid digit. Letters are accepted case-insensitively under HEX /
// HEX_UPPER; only lowercase under HEX_LOWER.
fn digval(c: u8, b: base) i32 = {
	if (c >= 48u8) { if (c <= 57u8) { return (c - 48u8): i32; }; };
	if (b == base.HEX_LOWER) {
		if (c >= 97u8) { if (c <= 102u8) { return ((c - 97u8) + 10u8): i32; }; };
		return -1;
	};
	if (c >= 65u8) { if (c <= 70u8)  { return ((c - 65u8) + 10u8): i32; }; };
	if (c >= 97u8) { if (c <= 102u8) { return ((c - 97u8) + 10u8): i32; }; };
	return -1;
};

// stoi64 — parse signed base-b number. Mirrors Hare's strconv::stoi64.
// No locale, no whitespace, no underscores: optional leading '-' then
// digits. Returns invalid with the offending index or overflow on
// out-of-range.
export fn stoi64(s: str, b: base) (i64 | invalid | overflow) = {
	if (s.len == 0) { return 0: invalid; };
	let i: i32 = 0;
	let neg: bool = false;
	if (s[0] == 45u8) { neg = true; i = 1; };
	if (i >= s.len) { return i: invalid; };
	let nb: i32 = basenum(b): i32;
	let v: i64 = 0;
	for (i < s.len) {
		let c: u8 = s[i];
		let d: i32 = digval(c, b);
		if (d < 0)   { return i: invalid; };
		if (d >= nb) { return i: invalid; };
		v = v * (nb: i64) + (d: i64);
		i += 1;
	};
	if (neg) { v = -v; };
	return v;
};

// stou64 — parse unsigned base-b number. Mirrors Hare's strconv::stou64.
export fn stou64(s: str, b: base) (u64 | invalid | overflow) = {
	if (s.len == 0) { return 0: invalid; };
	let nb: u64 = basenum(b): u64;
	let v: u64 = 0u64;
	let i: i32 = 0;
	for (i < s.len) {
		let c: u8 = s[i];
		let d: i32 = digval(c, b);
		if (d < 0)         { return i: invalid; };
		if ((d: u64) >= nb) { return i: invalid; };
		v = v * nb + (d: u64);
		i += 1;
	};
	return v;
};

export fn stoi32(s: str, b: base) (i32 | invalid | overflow) = {
	let r = stoi64(s, b);
	match (r) {
	case let v: i64 => {
		if (v > 2147483647i64)  { return overflow{}; };
		if (v < -2147483648i64) { return overflow{}; };
		return v: i32;
	};
	case let e: invalid  => return e;
	case let e: overflow => return e;
	};
	return 0: invalid;	// unreachable; appeases the path-cov checker
};

export fn stoi16(s: str, b: base) (i16 | invalid | overflow) = {
	let r = stoi64(s, b);
	match (r) {
	case let v: i64 => {
		if (v > 32767i64)  { return overflow{}; };
		if (v < -32768i64) { return overflow{}; };
		return v: i16;
	};
	case let e: invalid  => return e;
	case let e: overflow => return e;
	};
	return 0: invalid;
};

export fn stoi8(s: str, b: base) (i8 | invalid | overflow) = {
	let r = stoi64(s, b);
	match (r) {
	case let v: i64 => {
		if (v > 127i64)  { return overflow{}; };
		if (v < -128i64) { return overflow{}; };
		return v: i8;
	};
	case let e: invalid  => return e;
	case let e: overflow => return e;
	};
	return 0: invalid;
};

export fn stou32(s: str, b: base) (u32 | invalid | overflow) = {
	let r = stou64(s, b);
	match (r) {
	case let v: u64 => {
		if (v > 4294967295u64) { return overflow{}; };
		return v: u32;
	};
	case let e: invalid  => return e;
	case let e: overflow => return e;
	};
	return 0: invalid;
};

export fn stou16(s: str, b: base) (u16 | invalid | overflow) = {
	let r = stou64(s, b);
	match (r) {
	case let v: u64 => {
		if (v > 65535u64) { return overflow{}; };
		return v: u16;
	};
	case let e: invalid  => return e;
	case let e: overflow => return e;
	};
	return 0: invalid;
};

export fn stou8(s: str, b: base) (u8 | invalid | overflow) = {
	let r = stou64(s, b);
	match (r) {
	case let v: u64 => {
		if (v > 255u64) { return overflow{}; };
		return v: u8;
	};
	case let e: invalid  => return e;
	case let e: overflow => return e;
	};
	return 0: invalid;
};

// f64tos — convert v to a decimal string. Returns owned str; release
// via os.free. Mirrors Hare's strconv::f64tos (current ww impl is
// fixed-point only, max 6 fractional digits, no NaN/Inf support —
// see graduate-to-Ryū note below).
//
// Surface:
//
//   - finite values only. NaN/±Inf detection needs an f64→u64 bit
//     reinterpret cast that the cgen doesn't expose yet.
//   - fixed-point only, up to 6 fractional digits. Trailing zeros
//     after the decimal point are trimmed. Trailing '.' is dropped.
//   - magnitudes ≥ 9e18 (overflows i64 in the integer-part cast)
//     fall back to the literal token "huge". Hare would print these
//     in scientific notation via Ryū; we will graduate when the
//     compiler grows the bit-reinterpret cast.
//
// Round-trip is therefore lossy past 6 fractional digits.
//
// No float literals in the body — 990's wwdump diff requires this
// file's TK_FLOAT count to match between C and ww front-ends, and
// the ww-side wwdump currently skips TK_FLOAT.fval while the C side
// %g-formats it. Same trick lib/ww/lex/lex.ww's parsef64 uses:
// build f64 constants via int-to-f64 casts.
let f64tos_buf: [64]u8;

export fn f64tos(v: f64) str = {
	let out: i32 = 0;
	let f: f64 = v;
	let zero: f64 = 0: f64;
	if (f < zero) {
		f64tos_buf[out] = 45u8;	// '-'
		out += 1;
		f = -f;
	};
	// 9e18 is comfortably under I64_MAX (9.22e18). Past this the
	// `f: i64` cast wraps and the integer part comes back as garbage.
	let cap: f64 = 9000000000000000000i64: f64;
	if (f >= cap) {
		let s: str = "huge";
		let k: i32 = 0;
		for (k < s.len) { f64tos_buf[out] = s[k]; out += 1; k += 1; };
		let r: str;
		r.ptr = &f64tos_buf[0];
		r.len = out;
		return r;
	};
	let ip: i64 = f: i64;
	// Fractional part scaled to 6 decimal digits, with round-to-
	// nearest via +0.5. (f64 compound assigns mis-lower in cgen —
	// use the explicit form, as the rest of lib does.)
	let frac: f64 = f - (ip: f64);
	let scale: f64 = 1000000: f64;
	frac = frac * scale;
	let half: f64 = (1: f64) / (2: f64);
	let fp: i64 = (frac + half): i64;
	// Carry: e.g. 0.9999996 rounds fp up to 1000000 and the integer
	// part needs to advance.
	if (fp >= 1000000) {
		ip += 1;
		fp = 0;
	};
	let intstr: str = i64tos(ip, base.DEC);
	let k: i32 = 0;
	for (k < intstr.len) { f64tos_buf[out] = intstr.ptr[k]; out += 1; k += 1; };
	if (fp != 0) {
		f64tos_buf[out] = 46u8;	// '.'
		out += 1;
		let fracstr: str = u64tos(fp: u64, base.DEC);
		// Pad fractional to 6 digits with leading zeros (e.g. 0.05 →
		// fp=50000, fracstr="50000", pad one '0' before).
		let z: i32 = 6 - fracstr.len;
		for (z > 0) { f64tos_buf[out] = 48u8; out += 1; z -= 1; };
		k = 0;
		for (k < fracstr.len) { f64tos_buf[out] = fracstr.ptr[k]; out += 1; k += 1; };
		// Trim trailing zeros in the fractional part.
		for (out > 0) {
			if (f64tos_buf[out - 1] != 48u8) { break; };
			out -= 1;
		};
	};
	let r: str;
	r.ptr = &f64tos_buf[0];
	r.len = out;
	return r;
};

// strerror — convert an strconv error to a user-readable string.
// Returns owned str; release via os.free. Mirrors Hare's
// strconv::strerror.
export fn strerror(e: error) str = {
	match (e) {
	case let v: invalid  => return strings.dup("input is not a valid number");
	case let v: overflow => return strings.dup("input number doesn't fit target type");
	};
	return strings.dup("");
};