lib/regex: fold-2b tranche D — test/find (the exec surface)

Port of test (ref/hare/regex/regex.ha:901-904) and find (ha:907-918)
— the exported exec surface over tranche C's search. fold 2b is
COMPLETE: compile → test/find runs end to end on the 2a literal
programs.

Both are |success|=2 `?` sites in Hare (`search(...)?` over
(void | []capture | nomem)); ww's `?` is gated to single-success
unions (the C6 interim), so each spells the propagation as the
explicit 3-arm match harec lowers `?` into (ref/harec/src/check.c:
2780) — the ratified D13 spelling, on task #14's acceptance list for
reversion when subset-union `?` lands. find's no-match `return [];`
(ha:916) binds a zero header first (#25/#31 ruling) — a valid empty
result the caller still result_frees. io::handle args are the landed
memio→io cast (&strm.vt); import memio added.

PD1 probed first (scratch/pd1.ww): []capture values returning
through (result | nomem) — the nominal-alias member — plus the
(bool | nomem) round-trip; build/run/byte-id green at base, so no
new compiler surface was crossed.

regex_test: +2 @test fns (signalled 23-24). test_matches = 8-row
tcase table (the six search-table inputs → true, thread-drain and
EOF-mid-pattern → false). find_cases = 8-row fcase table: the six
match rows reuse the search table's root-capture expectations (all
four indices + content), the two no-match rows pin the empty result;
result_free on every row, matched or not. Every fcase row also
cross-pins test/find agreement (test(re, s) == find(re, s) matched),
so an arm-swap in either D13 match is caught by the other surface.

Both drivers run the fixture exit 0; w6c vs w6c_ww on the
regenerated combined byte-identical (FC0).

lib/regex/regex.ww

@@ -4,11 +4,12 @@
 // 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.
+// tranche C = search, the first end-to-end match; fold 2b tranche D
+// = the exec surface (test/find — the D13 explicit-match spelling of
+// Hare's multi-success `?`, ww-core #14). Every other metacharacter
+// arm (and replace/findall) is DEFERRED behind compiler fixes —
+// probed pre-port, pA*/pB*/PB*/PC*/PD* 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):
@@ -20,6 +21,7 @@ package regex;
 
 import bufio;
 import io;
+import memio;
 import strings;
 import types;
 import encoding.utf8;
@@ -597,6 +599,49 @@ fn search(
 	};
 };
 
+// Returns whether or not a [[regex]] matches any part of a given
+// string.
+//
+// ref/hare/regex/regex.ha:900-904. Hare's io::handle arg `&strm` is
+// the landed memio→io cast `&strm.vt`. Hare unwraps with
+// `search(...)? is []capture` — a |success|=2 union; ww's `?` is
+// gated to single-success unions (the C6 interim, ww-core #14), so
+// the propagation is spelled as the explicit match harec lowers `?`
+// into (ref/harec/src/check.c:2780) — the ratified D13 spelling,
+// reverts with #14.
+export fn test(re: *regex, string: str) (bool | nomem) = {
+	let strm: memio.stream = memio.fixed(strings.toutf8(string));
+	let r: (void | []capture | nomem) =
+		search(re, string, &strm.vt, false);
+	match (r) {
+	case let m: []capture => return true;
+	case void => return false;
+	case let n: nomem => return n;
+	};
+};
+
+// Attempts to match a [[regex]] against a string and returns the
+// longest leftmost match as a [[result]]. The caller must free the
+// return value with [[result_free]].
+//
+// ref/hare/regex/regex.ha:907-918. Same explicit `?` lowering as
+// test() (D13, ww-core #14); the no-match `return [];` (ha:916)
+// binds a zero header first (#25/#31 ruling) — a valid empty result
+// the caller still result_frees.
+export fn find(re: *regex, string: str) (result | nomem) = {
+	let strm: memio.stream = memio.fixed(strings.toutf8(string));
+	let r: (void | []capture | nomem) =
+		search(re, string, &strm.vt, true);
+	match (r) {
+	case let m: []capture => return m;
+	case void => {
+		let empty: []capture;
+		return empty;
+	};
+	case let n: nomem => return n;
+	};
+};
+
 // Frees a [[result]].
 //
 // ref/hare/regex/regex.ha:1113-1116, verbatim — the free() builtin is

lib/regex/regex_test.ww

@@ -2,8 +2,8 @@
 // model + finish()), the fold-2a compile() literal core, the
 // fold-2b tranche-A/B thread machine (thread/newmatch + result_free
 // + strerror; delete_thread/is_consuming_inst/add_thread/run_thread),
-// and the tranche-C search end-to-end matches (the exec surface
-// test/find is tranche D — see regex.ww). Run with
+// the tranche-C search end-to-end matches, and the tranche-D exec
+// surface (test/find). Run with
 // `out/bin/ww run lib/regex/regex_test.ww`.
 //
 // Private symbols (thread, newmatch) are reached unqualified: this
@@ -789,6 +789,117 @@ type scase = struct {
 	};
 };
 
+// test() (regex.ha:901-904) — the exported boolean surface over the
+// same inputs the search table pins, plus the two void rows.
+type tcase = struct {
+	expr: str,
+	input: str,
+	want: bool,
+};
+
+@test fn test_matches() void = {
+	let rows: [8]tcase = [
+		tcase { expr = "ab", input = "xab", want = true },
+		tcase { expr = "bcd", input = "abcd", want = true },
+		tcase { expr = "aa", input = "aaa", want = true },
+		tcase { expr = "", input = "", want = true },
+		tcase { expr = "b.d", input = "aßbxd", want = true },
+		tcase { expr = "aa", input = "aaaa", want = true },
+		tcase { expr = "ab", input = "xyz", want = false },
+		tcase { expr = "ab", input = "a", want = false },
+	];
+	let i: i32 = 0;
+	for (i < len(rows)) {
+		let ex: str = rows[i].expr;
+		let inp: str = rows[i].input;
+		let c: (regex.regex | regex.error | nomem) = regex.compile(ex);
+		match (c) {
+		case let re: regex.regex => {
+			let tr: (bool | nomem) = regex.test(&re, inp);
+			if (!(tr is bool)) { fail(); };
+			if ((tr as bool) != rows[i].want) { fail(); };
+			regex.finish(&re);
+		};
+		case => fail();
+		};
+		i += 1;
+	};
+};
+
+// find() (regex.ha:910-918) — the exported result surface: match rows
+// reuse the search table's expectations; no-match rows return the
+// empty result (ha:916) the caller still result_frees. Every row also
+// cross-pins test() == (find() matched).
+type fcase = struct {
+	expr: str,
+	input: str,
+	matches: bool,
+	start: size,
+	sb: size,
+	end: size,
+	eb: size,
+	content: str,
+};
+
+@test fn find_cases() void = {
+	let rows: [8]fcase = [
+		fcase { expr = "ab", input = "xab", matches = true,
+			start = 1, sb = 1, end = 3, eb = 3, content = "ab" },
+		fcase { expr = "bcd", input = "abcd", matches = true,
+			start = 1, sb = 1, end = 4, eb = 4, content = "bcd" },
+		fcase { expr = "aa", input = "aaa", matches = true,
+			start = 0, sb = 0, end = 2, eb = 2, content = "aa" },
+		fcase { expr = "", input = "", matches = true,
+			start = 0, sb = 0, end = 0, eb = 0, content = "" },
+		fcase { expr = "b.d", input = "aßbxd", matches = true,
+			start = 2, sb = 3, end = 5, eb = 6, content = "bxd" },
+		fcase { expr = "aa", input = "aaaa", matches = true,
+			start = 0, sb = 0, end = 2, eb = 2, content = "aa" },
+		fcase { expr = "ab", input = "xyz", matches = false, ... },
+		fcase { expr = "ab", input = "a", matches = false, ... },
+	];
+	let i: i32 = 0;
+	for (i < len(rows)) {
+		let ex: str = rows[i].expr;
+		let inp: str = rows[i].input;
+		let c: (regex.regex | regex.error | nomem) = regex.compile(ex);
+		match (c) {
+		case let re: regex.regex => {
+			let fr: (regex.result | nomem) = regex.find(&re, inp);
+			if (!(fr is regex.result)) { fail(); };
+			let res: regex.result = fr as regex.result;
+			if (rows[i].matches) {
+				if (len(res) != 1) { fail(); };
+				if (res[0].start != rows[i].start) { fail(); };
+				if (res[0].start_bytesize != rows[i].sb) {
+					fail();
+				};
+				if (res[0].end != rows[i].end) { fail(); };
+				if (res[0].end_bytesize != rows[i].eb) {
+					fail();
+				};
+				let wc: str = rows[i].content;
+				if (strings.compare(res[0].content, wc) != 0) {
+					fail();
+				};
+			} else {
+				if (len(res) != 0) { fail(); };
+			};
+			// the two surfaces share search; pin their
+			// agreement so an arm-swap in either D13 match
+			// can't hide behind a one-sided table
+			let tr: (bool | nomem) = regex.test(&re, inp);
+			if (!(tr is bool)) { fail(); };
+			if ((tr as bool) != (len(res) != 0)) { fail(); };
+			regex.result_free(res);
+			regex.finish(&re);
+		};
+		case => fail();
+		};
+		i += 1;
+	};
+};
+
 export fn main() i32 = {
 	signalled = 1; lit_and_match();
 	signalled = 2; size_aliases_distinct();
@@ -812,5 +923,7 @@ export fn main() i32 = {
 	signalled = 20; search_matches();
 	signalled = 21; search_early_exit();
 	signalled = 22; search_no_match();
+	signalled = 23; test_matches();
+	signalled = 24; find_cases();
 	return 0;
 };