ww/lib/regex/regex.ww

// regex — POSIX extended regular expressions. Port of
// ref/hare/regex/regex.ha. Fold 1 = the data model; fold 2a = the
// compile() literal core (lit/any/match + the leading skip); fold 2b
// tranche A = the thread-machine scaffolding (thread/newmatch types,
// result_free, strerror); fold 2b tranche B = the engine
// (delete_thread/is_consuming_inst/add_thread/run_thread); fold 2b
// tranche C = search, the first end-to-end match. Every other
// metacharacter arm and the exec surface (test/find on the C6
// multi-success `?` gate, tranche D; replace) are DEFERRED behind
// compiler fixes — probed pre-port, pA*/pB*/PB*/PC* probes. They
// land with those fixes.
//
// One fold-1 construct is held back behind a filed compiler/fidelity
// gap (see the charclass_map site below):
//   - charclass_map (regex.ha:74-87) — a module-level const slice of
//     (str, *fn(rune) bool) tuples. Blocked on the array-literal→slice
//     element-coercion checker gap (#25; type.c:402-404 #258 borrow
//     uses exact type_eq, no element decay).
package regex;

import bufio;
import io;
import strings;
import types;
import encoding.utf8;

// ref/hare/regex/regex.ha:14 — an error string describing a compilation
// error.
export type error = !str;

// ref/hare/regex/regex.ha:16-30.
export type inst_lit = rune;
export type inst_charset = struct { idx: size, is_positive: bool };
export type inst_any = void;
export type inst_split = size;
export type inst_jump = size;
export type inst_skip = void;
export type inst_match = bool;
export type inst_groupstart = size;
export type inst_groupend = void;
export type inst_repeat = struct {
	id: size,
	origin: size,
	min: (void | size),
	max: (void | size),
};

// ref/hare/regex/regex.ha:32-35.
export type inst = (inst_lit | inst_any | inst_split | inst_jump |
	inst_skip | inst_match | inst_charset |
	inst_groupstart | inst_groupend |
	inst_repeat);

// The resulting match of a [[regex]] applied to a string.
//
// The first [[capture]] corresponds to the implicit zeroth capture
// group, i.e. the whole expression.
//
// The rest of the [[capture]]s correspond to the rest of the capture
// groups, i.e. the sub-expressions.
// ref/hare/regex/regex.ha:44.
export type result = []capture;

// A (sub)match corresponding to a regular expression's capture group.
// ref/hare/regex/regex.ha:47-53.
export type capture = struct {
	content: str,
	start: size,
	start_bytesize: size,
	end: size,
	end_bytesize: size,
};

// ref/hare/regex/regex.ha:55-64.
type thread = struct {
	pc: size,
	start_idx: size,
	start_bytesize: size,
	root_capture: capture,
	captures: []capture,
	rep_counters: []size,
	matched: bool,
	failed: bool,
};

// Discriminates a fresh match from plain void at run_thread's return
// boundary. ref/hare/regex/regex.ha:66.
type newmatch = void;

// ref/hare/regex/regex.ha:68-72.
export type charset = [](charset_lit_item | charset_range_item |
	charset_class_item);
export type charset_lit_item = rune;
export type charset_range_item = (u32, u32);
export type charset_class_item = (str, *fn(c: rune) bool);

// ref/hare/regex/regex.ha:74-87 — charclass_map: the const
// [](str, *fn(rune) bool) table mapping POSIX class tokens to the
// matching ascii predicate. DEFERRED: the array-literal→slice
// assignability check (type.c:402-404, the #258 borrow) compares
// element types with exact type_eq and applies NO element coercion, so
// the literal `[(":alnum:]", &ascii.isalnum), ...]` (typed
// `[N](untyped_str, *fn(rune) bool)`) is rejected against the declared
// `[](str, *fn(rune) bool)`. Minimal repro: `let xs: [](size, size) =
// [(1, 2)];`. Reshaping to a fixed `[12](...)` array would compile but
// is an unfaithful workaround (CLAUDE.md rule-7), so the table — and
// the `import ascii;` it needs — land with the consuming fold (compile)
// once the checker gap is fixed.

// ref/hare/regex/regex.ha:89-93.
export type regex = struct {
	insts: []inst,
	charsets: []charset,
	n_reps: size,
};

// Frees resources associated with a [[regex]].
//
// ref/hare/regex/regex.ha:96-102, verbatim. The free() builtin is a
// documented no-op (#27 landed): ww is a no-free runtime (rt/alloc.s:30
// — the bump allocator can't reclaim, process-exit does), so each free
// below evaluates its operand and reclaims nothing. Kept verbatim for
// API + source parity with the Hare surface.
export fn finish(re: *regex) void = {
	free(re.insts);
	for (let charset .. re.charsets) {
		free(charset);
	};
	free(re.charsets);
};

// Compiles a regular expression string into a [[regex]].
//
// ref/hare/regex/regex.ha:227-263. Fold 2a ports the literal core:
// inst_lit / inst_any / inst_match plus the leading inst_skip
// (regex.ha:261-263 — unanchored exec depends on it). Every other
// metacharacter arm is one loud not-yet-ported error — the explicit
// fold boundary; falling to literal would be a silent semantic lie.
// State serving only the deferred arms is dropped with them:
// jump_idxs (ha:241-248), the bracket quad (ha:249-252),
// was_prev_rune_pipe / group_level / capture_idx (ha:253-256).
//
// Hare's `defer if (!ok) free(...)` cleanup (ha:231-237) is omitted:
// ww has no `defer if` (cf lib/strings/strings.ww:85), and the free()
// builtin is a no-op anyway (#27 — ww is a no-free runtime), so the
// cleanup would reclaim nothing.
export fn compile(expr: str) (regex | error | nomem) = {
	// Hare `let insts: []inst = [];` — a bare ww slice declaration
	// zeroes the header (cgen.c:9836 no-rhs multi-word composite
	// zero-fill, symmetric in cgenstmt.ww).
	let insts: []inst;
	let charsets: []charset;	// stays empty until the '[' fold
	let iter: strings.iterator = strings.iter(expr);
	let r_idx: size = 0;
	let n_reps: size = 0;

	for (true) {
		let next: (rune | utf8.done) = strings.next(&iter);

		if (r_idx == 0 && next is rune && (next as rune) != '^') {
			// Bare append: ww append returns void; Hare's
			// `append(...)?` nomem propagation is filed #36.
			// Hare appends the bare type name (`inst_skip`) as
			// the void-variant value; in ww that resolves as a
			// symbol ref (cf the alloc(T) rule), so void
			// variants go through a typed let.
			let sk: inst_skip;
			let v: inst = sk;
			append(insts, v);
		};

		// regex.ha:277-284 minus the group_level check (it rides
		// the deferred '(' arm's state).
		let r: rune = match (next) {
		case utf8.done => break;
		case let x: rune => yield x;
		};

		switch (r) {
		case '.': {		// regex.ha:460-461
			let av: inst_any;
			let v: inst = av;
			append(insts, v);
		};
		case ']':		// regex.ha:315-316 — literal outside a bracket
			append(insts, (r: inst_lit));
		case '\\', '^', '$', '[', '(', ')', '|', '{', '?', '*', '+':
			// fold-2a boundary: regex.ha:286-459 arms deferred.
			return "regex: metacharacter not yet ported": error;
		case:			// regex.ha:462-463
			append(insts, (r: inst_lit));
		};
		r_idx += 1;
	};

	// regex.ha:475-477. `$` appends true: inst_match — deferred, so
	// the guard can only see no-match today; kept verbatim.
	if (insts.len == 0 || !(insts[insts.len - 1] is inst_match)) {
		append(insts, (false: inst_match));
	};
	// regex.ha:479-484. The alternation fixup (ha:470-473) drops with
	// jump_idxs.
	return regex {
		insts = insts,
		charsets = charsets,
		n_reps = n_reps,
	};
};

// ref/hare/regex/regex.ha:547-551, verbatim — both free()s are the
// documented no-op (#27; see finish()), kept for source parity. ww
// has no pointer auto-deref, so Hare's `threads[i]` spells
// `(*threads)[i]` (the test-804-pinned delete shape).
fn delete_thread(i: size, threads: *[]thread) void = {
	free((*threads)[i].captures);
	free((*threads)[i].rep_counters);
	delete((*threads)[i]);
};

// ref/hare/regex/regex.ha:553-555. Hare's multi-type membership test
// `a is (inst_lit | inst_any | inst_charset)` is loud-rejected by
// design (filed as a Hare-parity task, ww-core #13); the ruled
// spelling is the chained ||.
fn is_consuming_inst(a: inst) bool = {
	return a is inst_lit || a is inst_any || a is inst_charset;
};

// ref/hare/regex/regex.ha:557-587. The dedup scan (ha:560-566) is an
// index loop: ww has no by-ref `&..` range and a by-value range over
// `*threads` miscompiles (F1, ww-core #11). Hare's `append(...)?`
// nomem propagation and the ok/defer-if unwind (ha:568/573/586) drop
// together: ww append returns void (#36 filed) and free() reclaims
// nothing (#27), so there is nothing to propagate or unwind.
fn add_thread(threads: *[]thread, parent_idx: size, new_pc: size) (void | nomem) = {
	// Do not add this thread if there is already another thread with
	// the same PC
	for (let k: size = 0; k < (len(*threads): size); k += 1) {
		if ((*threads)[k].pc == new_pc
				&& !(*threads)[k].matched
				&& (*threads)[k].start_idx
				< (*threads)[parent_idx].start_idx) {
			return;
		};
	};

	// Hare dups the parent's captures/rep_counters here
	// (`alloc(threads[parent_idx].captures...)?`, ha:569/572). Every
	// ww route into that dup is blocked today (re-probed post-C3,
	// PB7): the deref-spine spread SOURCE is loud-rejected (#35),
	// the per-element append is loud-rejected (#34 struct element
	// source), and the whole-element let-copy drops bytes (#7/F5).
	// The abort is sound, not a semantic hole: fold-2a's compile()
	// cannot emit inst_groupstart/inst_repeat, so both slices are
	// provably empty in every program this fold can run; the empty
	// case appends honest zeroed headers below. The verbatim dup
	// lands with the group/repeat fold (ww-core #3).
	if ((*threads)[parent_idx].captures.len != 0
			|| (*threads)[parent_idx].rep_counters.len != 0) {
		abort("regex: capture dup not yet portable (#35/#34/#7)");
	};
	let captures: []capture;
	let rep_counters: []size;

	append(*threads, thread {
		pc = new_pc,
		start_idx = (*threads)[parent_idx].start_idx,
		start_bytesize = (*threads)[parent_idx].start_bytesize,
		matched = (*threads)[parent_idx].matched,
		failed = (*threads)[parent_idx].failed,
		captures = captures,
		rep_counters = rep_counters,
		...
	});
	return;
};

// ref/hare/regex/regex.ha:589-742. Only the arms fold-2a's compile()
// can emit execute (skip + match non-consuming; lit + any consuming);
// every other inst arm is one loud not-yet-ported abort — the fold
// boundary, the compile() metachar discipline. The "unreachable"
// aborts on lit/any inside the non-consuming loop (ha:604-605) and
// the trailing default (ha:738) are Hare's own unreachable arms;
// Hare spells them bare `abort()`, ww carries a message — the
// zero-arg builtin form is shadowed in any combined unit that
// declares its own abort fn (os.ww:16 is private yet shadows
// cross-module; filed, ww-core #45). Hare's loop match omits inst_charset
// (consuming — the loop condition excludes it); ww has no
// match-exhaustiveness analysis, so the omission becomes the loud
// default arm.
fn run_thread(
	i: size,
	re: *regex,
	string: str,
	threads: *[]thread,
	r_or_end: (rune | io.eof),
	str_idx: size,
	str_bytesize: size,
) (void | newmatch | nomem) = {
	let str_bytes: []u8 = strings.toutf8(string);
	if ((*threads)[i].matched) {
		return;
	};
	for (!is_consuming_inst(re.insts[(*threads)[i].pc])) {
		match (re.insts[(*threads)[i].pc]) {
		case inst_lit => abort("regex: unreachable");
		case inst_any => abort("regex: unreachable");
		case inst_split =>
			abort("regex: inst_split not yet ported");
		case inst_jump =>
			abort("regex: inst_jump not yet ported");
		case inst_skip => {
			let new_pc: size = (*threads)[i].pc + 1;
			(*threads)[i].start_idx = str_idx;
			(*threads)[i].start_bytesize = str_bytesize;
			add_thread(threads, i, new_pc)?;
			break;
		};
		case let anchored: inst_match => {
			// Do not match if we need an end-anchored match, but we
			// have not exhausted our string
			//
			// Hare spells `anchored` bare (ha:621) — alias
			// transparency; ww named aliases are nominal in bool /
			// comparison position, so this cast and the consuming
			// arm's (lit: rune) are checker-required.
			if ((anchored: bool) && !(r_or_end is io.eof)) {
				(*threads)[i].failed = true;
				return;
			};
			let content: str = strings.frombytes(str_bytes[
				(*threads)[i].start_bytesize:str_bytesize]);
			(*threads)[i].root_capture = capture {
				start = (*threads)[i].start_idx,
				start_bytesize = (*threads)[i].start_bytesize,
				end = str_idx,
				end_bytesize = str_bytesize,
				content = content,
			};
			(*threads)[i].matched = true;
			let nm: newmatch;
			return nm;
		};
		case inst_groupstart =>
			abort("regex: inst_groupstart not yet ported");
		case inst_groupend =>
			abort("regex: inst_groupend not yet ported");
		case inst_repeat =>
			abort("regex: inst_repeat not yet ported");
		case => abort("regex: unreachable");
		};
	};

	// From now on, we're only matching consuming instructions, and these
	// can't do anything without another rune.
	if (r_or_end is io.eof) {
		(*threads)[i].failed = true;
		return;
	};

	let r: rune = r_or_end as rune;

	match (re.insts[(*threads)[i].pc]) {
	case inst_skip => return;
	case let lit: inst_lit => {
		if (r != (lit: rune)) {
			(*threads)[i].failed = true;
		};
	};
	case inst_any => void;
	case inst_charset =>
		abort("regex: inst_charset not yet ported");
	case => abort("regex: unreachable"); // unreachable (ha:738)
	};

	(*threads)[i].pc += 1;
	return;
};

// Attempts to match a regular expression against a string and returns
// either the longest leftmost match or all matches.
//
// ref/hare/regex/regex.ha:746-898. Hare's io::handle param is ww's
// io.stream (callers pass &strm.vt over a memio.fixed). The
// (void | []capture | nomem) signature keeps nomem for Hare API
// parity even though nothing in this fold can produce it: ww append
// returns void (#36 filed) and scanrune has no nomem member.
fn search(
	re: *regex,
	string: str,
	h: io.stream,
	need_captures: bool,
) (void | []capture | nomem) = {
	// Hare builds the initial thread list with `alloc([thread {
	// captures = [], ... }])?` (ha:752-754); ww has per-value alloc
	// only, so the list is a bare decl plus one appended
	// fully-defaulted thread (the `...` fill zeroes captures too).
	let threads: []thread;
	append(threads, thread { ... });
	// Hare's defer-block cleanup (ha:755-761) is omitted: ww defer
	// takes a single expression (cf compile()'s omitted `defer if`)
	// and every free in the block is the documented no-op (#27).

	// ha:763-765 prefills threads[0].rep_counters via
	// `alloc([0...], re.n_reps)?`. No program this fold can compile
	// has n_reps > 0 (the inst_repeat arm is loud), and the sized
	// fill form has no ww spelling yet — loud, like the inst_repeat
	// arm; the real prefill lands with the repeat fold.
	if (re.n_reps > 0) {
		abort("regex: repetitions not yet ported");
	};

	let str_idx: size = 0;
	// Hare writes `= void` (ha:768); a ww bare tagged decl zeroes
	// the tag, which IS the void member here (PC4-pinned).
	let first_match_idx: (void | size);
	let str_bytesize: size = 0;
	let last_bytesize: size = 0;

	// ww has no default arguments: Hare's newscanner(handle) maxread
	// default spells types.I32_MAX explicitly (lib/bufio/bufio.ww).
	let scan: bufio.scanner = bufio.newscanner(h, types.I32_MAX);
	defer bufio.finish(&scan);
	for (true) {
		str_bytesize += last_bytesize;

		if (len(threads) == 0) {
			return;
		};

		let all_matched: bool = true;
		for (let i: size = 0; i < (len(threads): size); i += 1) {
			if (!threads[i].matched) {
				all_matched = false;
				break;
			};
		};

		if (all_matched) {
			let best_len: size = 0;
			let best_n_captures: size = 0;
			let best_idx: size = 0;
			for (let i: size = 0; i < (len(threads): size); i += 1) {
				let match_len: size =
					threads[i].root_capture.end
					- threads[i].root_capture.start;
				let is_better: bool = match_len > best_len
					|| match_len == best_len
					&& (len(threads[i].captures): size)
					> best_n_captures;
				if (is_better) {
					best_len = match_len;
					best_idx = i;
					best_n_captures =
						(len(threads[i].captures): size);
				};
			};

			// length = number of captures (index of final group +
			// 1) + root capture
			let length: size = 1;
			for (let i: size = (len(re.insts): size); i > 0; i -= 1) {
				// match-on-indexed scrutinee binds through a
				// typed let (the run_thread spelling).
				let cur: inst = re.insts[i - 1];
				match (cur) {
				case let z: inst_groupstart => {
					length = (z: size) + 2;
					break;
				};
				case => void;
				};
			};
			// Hare types this `result` with a capacity hint
			// (ha:818). A named-alias local trips the #20/#38
			// alias-value family, so the internal spelling is the
			// structural twin []capture (reverts with ww-core
			// #47); the capacity hint drops with per-value alloc.
			let res: []capture;
			append(res, threads[best_idx].root_capture);
			// ha:820 spreads threads[best_idx].captures into res.
			// The indexed spread source is #35-blocked, but
			// captures only populate via the loud-aborted
			// groupstart arm or add_thread's loud-bounded dup —
			// provably empty in every program this fold can run.
			// Loud-bound like add_thread's dup; the verbatim
			// spread lands with the group fold.
			if (threads[best_idx].captures.len != 0) {
				abort("regex: capture copy not yet ported (#35)");
			};
			// ha:821-824's sized fill-append `[capture { ... }...]`
			// has no ww spelling; the count loop is shape-correct
			// and self-activates with the group fold (length stays
			// 1 until then).
			for (length != (len(res): size)) {
				append(res, capture { ... });
			};
			return res;
		};

		// ww scanrune has no nomem member, so Hare's `case nomem =>
		// return nomem;` (ha:831-832) drops; the multi-type arms
		// (ha:829/833) split per member (the #13 membership-test
		// gap); the aborts carry messages (the #45 builtin-shadow
		// dodge, cf run_thread). Statement match assigning into the
		// declared local, not Hare's expression match: the cstage
		// checker types a match-expr by its first arm's yield and
		// rejects the io.eof arm against rune — wwstage accepts the
		// expression form, a cs≠ww divergence (filed, ww-core #51;
		// repro scratch/r51.ww).
		let r_or_end: (rune | io.eof);
		match (bufio.scanrune(&scan)) {
		case let r: rune => { r_or_end = r; };
		case io.eof => {
			let e: io.eof;
			r_or_end = e;
		};
		case let e: io.error => abort("regex: scanrune io error");
		case utf8.invalid => abort("regex: scanrune invalid utf8");
		};
		if (r_or_end is rune) {
			last_bytesize = (utf8.runesz(r_or_end as rune): size);
		};

		for (let i: size = 0; i < (len(threads): size); i += 1) {
			// Hare itself binds run_thread without `?` (ha:841) —
			// its nomem drops on the floor here too.
			let res: (void | newmatch | nomem) = run_thread(i, re,
				string, &threads, r_or_end, str_idx,
				str_bytesize);
			let matchlen: size = threads[i].root_capture.end
				- threads[i].root_capture.start;
			if (res is newmatch && matchlen > 0 && !need_captures) {
				// `return [];` (ha:845) — the empty-slice
				// literal in return position has no ww spelling
				// (#25/#31 ruling); a zero header is a valid
				// empty result.
				let none: []capture;
				return none;
			};
			let is_better: bool = res is newmatch && matchlen > 0
				&& (first_match_idx is void
					|| threads[i].start_idx
						< first_match_idx as size);
			if (is_better) {
				first_match_idx = threads[i].start_idx;
			};
		};
		str_idx += 1;

		// When we only want the leftmost match, delete all threads
		// that start after the earliest non-zero-length matched
		// thread. (ww has no by-ref `&..` range — index loop, the
		// add_thread divergence.)
		if (first_match_idx is size) {
			for (let k: size = 0; k < (len(threads): size); k += 1) {
				if (threads[k].start_idx
						> first_match_idx as size) {
					threads[k].failed = true;
				};
			};
		};

		// Delete threads that have a PC that has already been
		// encountered in previous threads. Prioritise threads that
		// have an earlier start_idx, and threads that were added
		// earlier. Hare names these counters i/j (ha:872); they are
		// di/dj here because the wwstage checker resolves the inner
		// init's `i + 1` against a dead same-name `let i: size`
		// sibling scope and rejects size → i64 (cs≠ww, filed
		// ww-core #52).
		for (let di: i64 = 0; di < (len(threads): i64) - 1; di += 1) {
			for (let dj: i64 = di + 1; dj < (len(threads): i64); dj += 1) {
				let same_pc: bool =
					threads[di].pc == threads[dj].pc;
				let none_matched: bool = !threads[dj].matched
					&& !threads[di].matched;
				if (same_pc && none_matched) {
					if (threads[di].start_idx
							<= threads[dj].start_idx) {
						delete_thread((dj: size), &threads);
						dj -= 1;
					} else {
						delete_thread((di: size), &threads);
						di -= 1;
						break;
					};
				};
			};
		};

		for (let i: size = 0; i < (len(threads): size); i += 1) {
			if (threads[i].failed) {
				delete_thread(i, &threads);
				i -= 1;
			};
		};
	};
};

// Frees a [[result]].
//
// ref/hare/regex/regex.ha:1113-1116, verbatim — the free() builtin is
// the documented no-op (#27; see finish()).
export fn result_free(s: result) void = {
	free(s);
};

// Converts an [[error]] into a user-friendly string.
//
// ref/hare/regex/regex.ha:1126-1127 (expression-bodied in Hare; ww
// fns take block bodies).
export fn strerror(err: error) str = {
	return err;
};