reftable: add a heap-based priority queue for reftable records

This is needed to create a merged view multiple reftables

Signed-off-by: Han-Wen Nienhuys <hanwen@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

4 files changed, 221 insertions, 0 deletions

diff --git a/reftable/pq.c b/reftable/pq.c
new file mode 100644
index 0000000000..efc474017a
--- /dev/null
+++ b/reftable/pq.c
@@ -0,0 +1,105 @@
+/*
+Copyright 2020 Google LLC
+
+Use of this source code is governed by a BSD-style
+license that can be found in the LICENSE file or at
+https://developers.google.com/open-source/licenses/bsd
+*/
+
+#include "pq.h"
+
+#include "reftable-record.h"
+#include "system.h"
+#include "basics.h"
+
+int pq_less(struct pq_entry *a, struct pq_entry *b)
+{
+	struct strbuf ak = STRBUF_INIT;
+	struct strbuf bk = STRBUF_INIT;
+	int cmp = 0;
+	reftable_record_key(&a->rec, &ak);
+	reftable_record_key(&b->rec, &bk);
+
+	cmp = strbuf_cmp(&ak, &bk);
+
+	strbuf_release(&ak);
+	strbuf_release(&bk);
+
+	if (cmp == 0)
+		return a->index > b->index;
+
+	return cmp < 0;
+}
+
+struct pq_entry merged_iter_pqueue_top(struct merged_iter_pqueue pq)
+{
+	return pq.heap[0];
+}
+
+int merged_iter_pqueue_is_empty(struct merged_iter_pqueue pq)
+{
+	return pq.len == 0;
+}
+
+struct pq_entry merged_iter_pqueue_remove(struct merged_iter_pqueue *pq)
+{
+	int i = 0;
+	struct pq_entry e = pq->heap[0];
+	pq->heap[0] = pq->heap[pq->len - 1];
+	pq->len--;
+
+	i = 0;
+	while (i < pq->len) {
+		int min = i;
+		int j = 2 * i + 1;
+		int k = 2 * i + 2;
+		if (j < pq->len && pq_less(&pq->heap[j], &pq->heap[i])) {
+			min = j;
+		}
+		if (k < pq->len && pq_less(&pq->heap[k], &pq->heap[min])) {
+			min = k;
+		}
+
+		if (min == i) {
+			break;
+		}
+
+		SWAP(pq->heap[i], pq->heap[min]);
+		i = min;
+	}
+
+	return e;
+}
+
+void merged_iter_pqueue_add(struct merged_iter_pqueue *pq, struct pq_entry e)
+{
+	int i = 0;
+	if (pq->len == pq->cap) {
+		pq->cap = 2 * pq->cap + 1;
+		pq->heap = reftable_realloc(pq->heap,
+					    pq->cap * sizeof(struct pq_entry));
+	}
+
+	pq->heap[pq->len++] = e;
+	i = pq->len - 1;
+	while (i > 0) {
+		int j = (i - 1) / 2;
+		if (pq_less(&pq->heap[j], &pq->heap[i])) {
+			break;
+		}
+
+		SWAP(pq->heap[j], pq->heap[i]);
+
+		i = j;
+	}
+}
+
+void merged_iter_pqueue_release(struct merged_iter_pqueue *pq)
+{
+	int i = 0;
+	for (i = 0; i < pq->len; i++) {
+		reftable_record_destroy(&pq->heap[i].rec);
+	}
+	FREE_AND_NULL(pq->heap);
+	pq->len = pq->cap = 0;
+}
diff --git a/reftable/pq.h b/reftable/pq.h
new file mode 100644
index 0000000000..56fc1b6d87
--- /dev/null
+++ b/reftable/pq.h
@@ -0,0 +1,33 @@
+/*
+Copyright 2020 Google LLC
+
+Use of this source code is governed by a BSD-style
+license that can be found in the LICENSE file or at
+https://developers.google.com/open-source/licenses/bsd
+*/
+
+#ifndef PQ_H
+#define PQ_H
+
+#include "record.h"
+
+struct pq_entry {
+	int index;
+	struct reftable_record rec;
+};
+
+struct merged_iter_pqueue {
+	struct pq_entry *heap;
+	size_t len;
+	size_t cap;
+};
+
+struct pq_entry merged_iter_pqueue_top(struct merged_iter_pqueue pq);
+int merged_iter_pqueue_is_empty(struct merged_iter_pqueue pq);
+void merged_iter_pqueue_check(struct merged_iter_pqueue pq);
+struct pq_entry merged_iter_pqueue_remove(struct merged_iter_pqueue *pq);
+void merged_iter_pqueue_add(struct merged_iter_pqueue *pq, struct pq_entry e);
+void merged_iter_pqueue_release(struct merged_iter_pqueue *pq);
+int pq_less(struct pq_entry *a, struct pq_entry *b);
+
+#endif
diff --git a/reftable/pq_test.c b/reftable/pq_test.c
new file mode 100644
index 0000000000..c9bb05e37b
--- /dev/null
+++ b/reftable/pq_test.c
@@ -0,0 +1,82 @@
+/*
+Copyright 2020 Google LLC
+
+Use of this source code is governed by a BSD-style
+license that can be found in the LICENSE file or at
+https://developers.google.com/open-source/licenses/bsd
+*/
+
+#include "system.h"
+
+#include "basics.h"
+#include "constants.h"
+#include "pq.h"
+#include "record.h"
+#include "reftable-tests.h"
+#include "test_framework.h"
+
+void merged_iter_pqueue_check(struct merged_iter_pqueue pq)
+{
+	int i;
+	for (i = 1; i < pq.len; i++) {
+		int parent = (i - 1) / 2;
+
+		EXPECT(pq_less(&pq.heap[parent], &pq.heap[i]));
+	}
+}
+
+static void test_pq(void)
+{
+	char *names[54] = { NULL };
+	int N = ARRAY_SIZE(names) - 1;
+
+	struct merged_iter_pqueue pq = { NULL };
+	const char *last = NULL;
+
+	int i = 0;
+	for (i = 0; i < N; i++) {
+		char name[100];
+		snprintf(name, sizeof(name), "%02d", i);
+		names[i] = xstrdup(name);
+	}
+
+	i = 1;
+	do {
+		struct reftable_record rec =
+			reftable_new_record(BLOCK_TYPE_REF);
+		struct pq_entry e = { 0 };
+
+		reftable_record_as_ref(&rec)->refname = names[i];
+		e.rec = rec;
+		merged_iter_pqueue_add(&pq, e);
+		merged_iter_pqueue_check(pq);
+		i = (i * 7) % N;
+	} while (i != 1);
+
+	while (!merged_iter_pqueue_is_empty(pq)) {
+		struct pq_entry e = merged_iter_pqueue_remove(&pq);
+		struct reftable_ref_record *ref =
+			reftable_record_as_ref(&e.rec);
+
+		merged_iter_pqueue_check(pq);
+
+		if (last) {
+			EXPECT(strcmp(last, ref->refname) < 0);
+		}
+		last = ref->refname;
+		ref->refname = NULL;
+		reftable_free(ref);
+	}
+
+	for (i = 0; i < N; i++) {
+		reftable_free(names[i]);
+	}
+
+	merged_iter_pqueue_release(&pq);
+}
+
+int pq_test_main(int argc, const char *argv[])
+{
+	RUN_TEST(test_pq);
+	return 0;
+}
diff --git a/reftable/reftable-tests.h b/reftable/reftable-tests.h
index 3d541fa5c0..0019cbcfa4 100644
--- a/reftable/reftable-tests.h
+++ b/reftable/reftable-tests.h
@@ -12,6 +12,7 @@ https://developers.google.com/open-source/licenses/bsd
 int basics_test_main(int argc, const char **argv);
 int block_test_main(int argc, const char **argv);
 int merged_test_main(int argc, const char **argv);
+int pq_test_main(int argc, const char **argv);
 int record_test_main(int argc, const char **argv);
 int refname_test_main(int argc, const char **argv);
 int readwrite_test_main(int argc, const char **argv);