fix(hash): honor a custom comparator on legacy unsorted hash pages

src/hash/hash_page.c

@@ -682,11 +682,15 @@ __ham_getindex_unsorted(dbc, p, key, match, indx)
 			break;
 		case H_KEYDATA:
 			if (t->h_compare != NULL) {
-				DB_INIT_DBT(pg_dbt,
-				    HKEYDATA_DATA(hk), key->size);
-				if (t->h_compare(
-				    dbp, key, &pg_dbt) != 0)
-					break;
+				/*
+				 * Compare against the stored key at its own
+				 * length -- as __ham_getindex_sorted does --
+				 * and record the result: a 0 return means the
+				 * keys are equal and the search is done.
+				 */
+				DB_INIT_DBT(pg_dbt, HKEYDATA_DATA(hk),
+				    LEN_HKEY(dbp, p, dbp->pgsize, i));
+				res = t->h_compare(dbp, key, &pg_dbt);
 			} else if (key->size ==
 			    LEN_HKEY(dbp, p, dbp->pgsize, i))
 				res = memcmp(key->data, HKEYDATA_DATA(hk),

test/coverage/README.md

@@ -77,6 +77,27 @@ timeout, so they cannot hang:
     current db, because current off-page dups are already stored as a Recno
     tree (P_LRECNO/P_IRECNO), not a flat page chain. A genuine pre-3.1 fixture
     is required.
+- **Legacy unsorted-hash lookup with a custom comparator** —
+  `test/db/run_hash_unsorted_cmp.sh` builds `test/db/hash_unsorted_cmp.c`, the
+  regression test for issue #139. `__ham_getindex_unsorted`
+  (`src/hash/hash_page.c`) is the linear search over a pre-4.6
+  `P_HASH_UNSORTED` page; its `t->h_compare != NULL` inline-key branch was
+  never reached by any test, because the branch needs a legacy page **and** an
+  explicitly configured `DB->set_h_compare` at the same time (`test093` sets a
+  comparator but only over current-format sorted pages, which take
+  `__ham_getindex_sorted`; `run_upgrade.sh` reads legacy pages but never sets a
+  comparator). The branch called the comparator, dropped its result, and built
+  the stored-key DBT with the *search* key's length -- so an equal key was
+  reported absent (`DB->get` → `DB_NOTFOUND`, `DB_NOOVERWRITE` → success plus a
+  duplicate) and a search key that merely prefixed a stored key compared equal.
+  The driver manufactures its legacy fixture the same way `run_upgrade.sh`
+  does, without an old library or a committed blob: it creates a current-format
+  Hash db (small pages, inline + off-page keys), then rewrites each bucket
+  page's `PAGE.type` byte from `P_HASH` to `P_HASH_UNSORTED` and the metadata
+  version back to the 4.5.20 hash version 8 -- exactly what `__ham_getindex`
+  dispatches to the unsorted path. Every check runs twice, with and without the
+  comparator, so a failure is attributable to the comparator path and not to
+  the fixture.
 - **Async I/O backends (os_aio)** — `test/os/run_os_aio.sh` builds
   `test/os/os_aio_direct.c`, which links the internal libdb symbols and drives
   the async-I/O abstraction (`src/os/os_aio.c`) and its backends

test/coverage/full_run3_combined.sh

@@ -166,6 +166,7 @@ run_driver db_upgrade  "$R/test/db/run_upgrade.sh"
 run_driver os_aio      "$R/test/os/run_os_aio.sh"
 run_driver backup      "$R/test/backup/run_backup_direct.sh"
 run_driver recd_compact "$R/test/db/run_recd_compact.sh"
+run_driver hash_unsorted_cmp "$R/test/db/run_hash_unsorted_cmp.sh"
 log "  .gcda after C drivers: $(find .libs -name '*.gcda' | wc -l)"
 
 # COV_DEAD_REG: deadlock detector + DB_REGISTER (driver-per-test)

test/coverage/run_coverage.sh

@@ -347,6 +347,16 @@ if [ "${COV_BACKUP:-1}" = 1 ]; then
   else
     echo "FAIL recd_handlers (rc=$?)"; tail -5 /tmp/cov-recdhandlers.log
   fi
+  # Legacy P_HASH_UNSORTED lookup with a custom DB->set_h_compare: the
+  # h_compare branch of __ham_getindex_unsorted needs a pre-4.6 page AND an
+  # explicit comparator at the same time, which no Tcl test arranges
+  # (test093 sets a comparator over sorted pages; run_upgrade.sh reads legacy
+  # pages without one).  Regression gate for issue #139.
+  if sh "$root/test/db/run_hash_unsorted_cmp.sh" >/tmp/cov-hashunsorted.log 2>&1; then
+    echo "PASS hash_unsorted_cmp"
+  else
+    echo "FAIL hash_unsorted_cmp (rc=$?)"; tail -5 /tmp/cov-hashunsorted.log
+  fi
   echo "  .gcda files after backup/compact: $(find . -name '*.gcda' | wc -l)"
 fi