ww/lib/strings/strings.ww

// strings — operations over the immutable str type ({ *u8, len }).
// Mirrors Hare's strings::; `len` and `is-empty` aren't functions
// (callers use `s.len` and `s.len == 0` directly).

use os;

// compare — bytewise three-way comparison: negative if a<b, 0 if equal,
// positive if a>b. Matches Hare's strings::compare. ASCII-order, not
// locale-aware. Callers that just need equality use `compare(a, b) == 0`.
export fn compare(a: str, b: str) i32 = {
	let n: i32 = a.len;
	if (b.len < n) { n = b.len; };
	let i: i32 = 0;
	for (i < n) {
		if (a[i] != b[i]) { return (a[i]: i32) - (b[i]: i32); };
		i += 1;
	};
	return a.len - b.len;
};

export fn hasprefix(s: str, p: str) bool = {
	if (p.len > s.len) { return false; };
	let i: i32 = 0;
	for (i < p.len) {
		if (s[i] != p[i]) { return false; };
		i += 1;
	};
	return true;
};

export fn hassuffix(s: str, suf: str) bool = {
	if (suf.len > s.len) { return false; };
	let off: i32 = s.len - suf.len;
	let i: i32 = 0;
	for (i < suf.len) {
		if (s[off + i] != suf[i]) { return false; };
		i += 1;
	};
	return true;
};

// byteindex — first byte position of `needle` in `s`. Mirrors Hare's
// strings::byteindex: a single-codepoint rune scans for the byte that
// encodes it (ASCII only here — multi-byte UTF-8 awaits utf8 encode),
// a str needle scans for the substring. Returns void if absent.
export fn byteindex(s: str, needle: (str | rune)) (i32 | void) = {
	match (needle) {
	case let r: rune => {
		let c: u8 = r: u8;
		let i: i32 = 0;
		for (i < s.len) {
			if (s[i] == c) { return i; };
			i += 1;
		};
		return;
	};
	case let sub: str => {
		if (sub.len == 0) { return 0; };
		if (sub.len > s.len) { return; };
		let last: i32 = s.len - sub.len;
		let i: i32 = 0;
		for (i <= last) {
			let j: i32 = 0;
			let ok: bool = true;
			for (j < sub.len) {
				if (s[i + j] != sub[j]) { ok = false; j = sub.len; }
				else { j += 1; };
			};
			if (ok) { return i; };
			i += 1;
		};
		return;
	};
	};
	return;
};

// contains — true iff `sub` appears in `s`. Mirrors Hare's
// strings::contains shape (byte-wise on the str-needle case).
export fn contains(s: str, sub: str) bool = {
	let r: (i32 | void) = byteindex(s, sub);
	match (r) {
	case let i: i32 => return true;
	case void => return false;
	};
	return false;
};

// concat — joins two strings into a fresh str. Caller owns the
// returned str's storage; release via `os.free(r.ptr, r.len)`. Mirrors
// Hare's strings::concat shape.
export fn concat(a: str, b: str) str = {
	let total: i32 = a.len + b.len;
	let buf: *u8 = os.alloc(total: u64): *u8;
	let i: i32 = 0;
	for (i < a.len) { buf[i] = a[i]; i += 1; };
	let j: i32 = 0;
	for (j < b.len) { buf[a.len + j] = b[j]; j += 1; };
	let r: str;
	r.ptr = buf;
	r.len = total;
	return r;
};

// dup — duplicate a string into a fresh allocation. Caller owns the
// returned str's storage; release via `os.free(r.ptr, r.len)`. Mirrors
// Hare's strings::dup shape — Hare returns `(str | nomem)`, ww doesn't
// have nomem (os.alloc aborts on OOM), so we return plain `str`.
//
// Empty input yields a `{nil, 0}` str — Hare returns the static empty
// string; same observable result.
export fn dup(s: str) str = {
	let r: str;
	r.ptr = nil;
	r.len = 0;
	if (s.len == 0) { return r; };
	let buf: *u8 = os.alloc(s.len: u64): *u8;
	let i: i32 = 0;
	for (i < s.len) { buf[i] = s[i]; i += 1; };
	r.ptr = buf;
	r.len = s.len;
	return r;
};

// rbyteindex — last byte position of `needle` in `s`. Mirrors Hare's
// strings::rbyteindex. Rune needle scans for the byte that encodes it
// (ASCII only); str needle scans for the substring. Empty str needle
// matches at s.len.
export fn rbyteindex(s: str, needle: (str | rune)) (i32 | void) = {
	match (needle) {
	case let r: rune => {
		let c: u8 = r: u8;
		let i: i32 = s.len - 1;
		for (i >= 0) {
			if (s[i] == c) { return i; };
			i -= 1;
		};
		return;
	};
	case let sub: str => {
		if (sub.len == 0) { return s.len; };
		if (sub.len > s.len) { return; };
		let i: i32 = s.len - sub.len;
		for (i >= 0) {
			let j: i32 = 0;
			let ok: bool = true;
			for (j < sub.len) {
				if (s[i + j] != sub[j]) { ok = false; j = sub.len; }
				else { j += 1; };
			};
			if (ok) { return i; };
			i -= 1;
		};
		return;
	};
	};
	return;
};

// sub — borrowed substring `s[start..end]`. Mirrors Hare's
// strings::sub. Caller must ensure 0 <= start <= end <= s.len; out-of-
// range indices are clamped silently here, where Hare aborts.
export fn sub(s: str, start: i32, end: i32) str = {
	let lo: i32 = start;
	let hi: i32 = end;
	if (lo < 0)     { lo = 0; };
	if (hi > s.len) { hi = s.len; };
	if (hi < lo)    { hi = lo; };
	let r: str;
	r.ptr = s.ptr + (lo: u64);
	r.len = hi - lo;
	return r;
};

// trimprefix — `s` with `pre` stripped from the front, or `s`
// unchanged if it doesn't start with `pre`. Returns a borrowed view.
// Mirrors Hare's strings::trimprefix.
export fn trimprefix(s: str, pre: str) str = {
	if (!hasprefix(s, pre)) { return s; };
	let r: str;
	r.ptr = s.ptr + (pre.len: u64);
	r.len = s.len - pre.len;
	return r;
};

// trimsuffix — `s` with `suf` stripped from the end, or `s` unchanged
// if it doesn't end with `suf`. Returns a borrowed view. Mirrors
// Hare's strings::trimsuffix.
export fn trimsuffix(s: str, suf: str) str = {
	if (!hassuffix(s, suf)) { return s; };
	let r: str;
	r.ptr = s.ptr;
	r.len = s.len - suf.len;
	return r;
};

// ltrimbyte / rtrimbyte / trimbyte — strip occurrences of a single
// byte from the left, right, or both ends. Returns a borrowed view.
// Hare's strings::ltrim / rtrim / trim take a rune varargs set; ww's
// subset takes a single byte (the common ASCII case).
export fn ltrimbyte(s: str, c: u8) str = {
	let i: i32 = 0;
	for (i < s.len) {
		if (s[i] != c) { break; };
		i += 1;
	};
	let r: str;
	r.ptr = s.ptr + (i: u64);
	r.len = s.len - i;
	return r;
};

export fn rtrimbyte(s: str, c: u8) str = {
	let n: i32 = s.len;
	for (n > 0) {
		if (s[n - 1] != c) { break; };
		n -= 1;
	};
	let r: str;
	r.ptr = s.ptr;
	r.len = n;
	return r;
};

export fn trimbyte(s: str, c: u8) str = {
	return rtrimbyte(ltrimbyte(s, c), c);
};