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 ascii;
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); };

// rune_to_integer — digit value of r (0-9 → 0-9; a-z/A-Z → 10-35),
// or void if r is not alphanumeric. Verbatim port of
// ref/hare/strconv/stou.ha:8-15 (ww yields the void variant with a
// bare `return;`, per lib/bytes/bytes.ww:65).
fn rune_to_integer(r: rune) (u64 | void) = {
	if (ascii.isdigit(r)) {
		return (r: u32 - '0'): u64;
	} else if (ascii.isalpha(r) && ascii.islower(r)) {
		return (r: u32 - 'a'): u64 + 10;
	} else if (ascii.isalpha(r) && ascii.isupper(r)) {
		return (r: u32 - 'A'): u64 + 10;
	};
	return;
};

// parseint — shared sign+digit+overflow core for stoi64/stou64.
// Verbatim port of ref/hare/strconv/stou.ha:17-65. Divergences:
//   - param `base` → `b` (ww: avoid the type/value name collision; the
//     file already names the enum arg `b`).
//   - Hare's DEFAULT→DEC / HEX_LOWER→HEX base reassignment + the
//     base-validity assert collapse into basenum(b), which already maps
//     every base to its numeric value {2,8,10,16} (default 10). HEX_LOWER
//     thus parses case-insensitively, matching Hare's normalize-then-parse.
//   - str is byte-indexable, so Hare's `buf = strings::toutf8(s)` is
//     elided (existing file convention, cf. the old stoi64/stou64).
//   - n *= base / n += digit spelled as plain assignment (sibling-fn
//     convention).
fn parseint(s: str, b: base) ((bool, u64) | invalid | overflow) = {
	let nb: u64 = basenum(b): u64;

	if (s.len == 0) {
		return 0: invalid;
	};

	let i: i32 = 0;

	let sign: bool = s[i] == '-';
	if (sign || s[i] == '+') {
		i += 1;
	};

	// Require at least one digit.
	if (i == s.len) {
		return i: invalid;
	};

	let n: u64 = 0u64;
	// Hare's `for (i < len(buf); i += 1)` (stou.ha:43) → condition-only
	// for + tail increment (ww has no 2-clause for; sort.ww:25). Early
	// returns exit before the increment, so it's never skipped.
	for (i < s.len) {
		let digit: u64 = match (rune_to_integer(s[i]: rune)) {
		case void => return i: invalid;
		case let d: u64 => yield d;
		};

		if (digit >= nb) {
			return i: invalid;
		};

		let old: u64 = n;

		n = n * nb;
		n = n + digit;

		if (n < old) {
			return overflow{};
		};

		i += 1;
	};
	return (sign, n);
};

// stoi64 — parse signed base-b number. Verbatim port of
// ref/hare/strconv/stoi.ha:9-17. types.I64_MAX is inlined (the const is
// package-private — see the mulshift32 note in ftos.ww).
export fn stoi64(s: str, b: base) (i64 | invalid | overflow) = {
	let (sign, u) = parseint(s, b)?;
	// Two's complement: I64_MIN = -I64_MAX - 1. Hare's two if-expressions
	// (stoi.ha:12,16) are lowered to statement-if — ww has no
	// if-expression (standing divergence, see the note in stof.ww:31).
	let max: u64 = 9223372036854775807u64;
	if (sign) {
		max = max + 1u64;
	};
	if (u > max) {
		return overflow{};
	};
	let r: i64 = u: i64;
	if (sign) {
		r = -r;
	};
	return r;
};

// stou64 — parse unsigned base-b number. Verbatim port of
// ref/hare/strconv/stou.ha:70-76.
export fn stou64(s: str, b: base) (u64 | invalid | overflow) = {
	let (sign, u) = parseint(s, b)?;
	if (sign) {
		return overflow{};
	};
	return u;
};

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 — graduated to the Ryū shortest-round-trippable implementation
// in ftos.ww (strconv #106 fold-5). The old lossy fixed-point version
// (6 fractional digits, "huge" fallback ≥9e18, no NaN/Inf) was deleted
// here per the lib-note graduation rule ("replace in one go, don't keep
// both"); ftos.ww's f64tos is the live one. f32tos follows in fold-5b
// (task #67, gated on the #143 f32-arg-push cgen fix).

// 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("");
};