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).
This commit is contained in:
2026-06-04 15:14:54 +09:00
parent 6160277098
commit bc048ebe65
2 changed files with 165 additions and 7 deletions

View File

@@ -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