reftable/block: expose a generic iterator over reftable records

Expose a generic iterator over reftable records and expose it via the
public interface. Together with an upcoming iterator for reftable blocks
contained in a table this will allow users to trivially iterate through
blocks and their respective records individually.

This functionality will be used to implement consistency checks for the
reftable backend, which requires more fine-grained control over how we
read data.

Signed-off-by: Patrick Steinhardt <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: pks-t

reftable/block.c

@@ -10,6 +10,7 @@
 
 #include "blocksource.h"
 #include "constants.h"
+#include "iter.h"
 #include "record.h"
 #include "reftable-error.h"
 #include "system.h"
@@ -581,6 +582,61 @@ int block_iter_seek_key(struct block_iter *it, struct reftable_buf *want)
 	return err;
 }
 
+static int block_iter_seek_void(void *it, struct reftable_record *want)
+{
+	struct reftable_buf buf = REFTABLE_BUF_INIT;
+	struct block_iter *bi = it;
+	int err;
+
+	if (bi->block->block_type != want->type)
+		return REFTABLE_API_ERROR;
+
+	err = reftable_record_key(want, &buf);
+	if (err < 0)
+		goto out;
+
+	err = block_iter_seek_key(it, &buf);
+	if (err < 0)
+		goto out;
+
+	err = 0;
+
+out:
+	reftable_buf_release(&buf);
+	return err;
+}
+
+static int block_iter_next_void(void *it, struct reftable_record *rec)
+{
+	return block_iter_next(it, rec);
+}
+
+static void block_iter_close_void(void *it)
+{
+	block_iter_close(it);
+}
+
+static struct reftable_iterator_vtable block_iter_vtable = {
+	.seek = &block_iter_seek_void,
+	.next = &block_iter_next_void,
+	.close = &block_iter_close_void,
+};
+
+int reftable_block_init_iterator(const struct reftable_block *b,
+				 struct reftable_iterator *it)
+{
+	struct block_iter *bi;
+
+	REFTABLE_CALLOC_ARRAY(bi, 1);
+	block_iter_init(bi, b);
+
+	assert(!it->ops);
+	it->iter_arg = bi;
+	it->ops = &block_iter_vtable;
+
+	return 0;
+}
+
 void block_writer_release(struct block_writer *bw)
 {
 	deflateEnd(bw->zstream);

reftable/block.h

@@ -63,7 +63,7 @@ int block_writer_finish(struct block_writer *w);
 /* clears out internally allocated block_writer members. */
 void block_writer_release(struct block_writer *bw);
 
-/* Iterate over entries in a block */
+/* Iterator for records contained in a single block. */
 struct block_iter {
 	/* offset within the block of the next entry to read. */
 	uint32_t next_off;

reftable/reftable-block.h

@@ -13,6 +13,7 @@
 
 #include "reftable-basics.h"
 #include "reftable-blocksource.h"
+#include "reftable-iterator.h"
 
 struct z_stream_s;
 
@@ -60,6 +61,10 @@ int reftable_block_init(struct reftable_block *b,
 /* Release resources allocated by the block. */
 void reftable_block_release(struct reftable_block *b);
 
+/* Initialize a generic record iterator from the given block. */
+int reftable_block_init_iterator(const struct reftable_block *b,
+				 struct reftable_iterator *it);
+
 /* Returns the block type (eg. 'r' for refs). */
 uint8_t reftable_block_type(const struct reftable_block *b);
 

t/unit-tests/t-reftable-block.c

@@ -372,12 +372,90 @@ static void t_index_block_read_write(void)
 		reftable_record_release(&recs[i]);
 }
 
+static void t_block_iterator(void)
+{
+	struct reftable_block_source source = { 0 };
+	struct block_writer writer = {
+		.last_key = REFTABLE_BUF_INIT,
+	};
+	struct reftable_record expected_refs[20];
+	struct reftable_ref_record ref = { 0 };
+	struct reftable_iterator it = { 0 };
+	struct reftable_block block = { 0 };
+	struct reftable_buf data;
+	int err;
+
+	data.len = 1024;
+	REFTABLE_CALLOC_ARRAY(data.buf, data.len);
+	check(data.buf != NULL);
+
+	err = block_writer_init(&writer, BLOCK_TYPE_REF, (uint8_t *) data.buf, data.len,
+				0, hash_size(REFTABLE_HASH_SHA1));
+	check(!err);
+
+	for (size_t i = 0; i < ARRAY_SIZE(expected_refs); i++) {
+		expected_refs[i] = (struct reftable_record) {
+			.type = BLOCK_TYPE_REF,
+			.u.ref = {
+				.value_type = REFTABLE_REF_VAL1,
+				.refname = xstrfmt("refs/heads/branch-%02"PRIuMAX, (uintmax_t)i),
+			},
+		};
+		memset(expected_refs[i].u.ref.value.val1, i, REFTABLE_HASH_SIZE_SHA1);
+
+		err = block_writer_add(&writer, &expected_refs[i]);
+		check_int(err, ==, 0);
+	}
+
+	err = block_writer_finish(&writer);
+	check_int(err, >, 0);
+
+	block_source_from_buf(&source, &data);
+	reftable_block_init(&block, &source, 0, 0, data.len, REFTABLE_HASH_SIZE_SHA1);
+
+	err = reftable_block_init_iterator(&block, &it);
+	check_int(err, ==, 0);
+
+	for (size_t i = 0; ; i++) {
+		err = reftable_iterator_next_ref(&it, &ref);
+		if (err > 0) {
+			check_int(i, ==, ARRAY_SIZE(expected_refs));
+			break;
+		}
+		check_int(err, ==, 0);
+
+		check(reftable_ref_record_equal(&ref, &expected_refs[i].u.ref,
+						REFTABLE_HASH_SIZE_SHA1));
+	}
+
+	err = reftable_iterator_seek_ref(&it, "refs/heads/does-not-exist");
+	check_int(err, ==, 0);
+	err = reftable_iterator_next_ref(&it, &ref);
+	check_int(err, ==, 1);
+
+	err = reftable_iterator_seek_ref(&it, "refs/heads/branch-13");
+	check_int(err, ==, 0);
+	err = reftable_iterator_next_ref(&it, &ref);
+	check_int(err, ==, 0);
+	check(reftable_ref_record_equal(&ref, &expected_refs[13].u.ref,
+					REFTABLE_HASH_SIZE_SHA1));
+
+	for (size_t i = 0; i < ARRAY_SIZE(expected_refs); i++)
+		reftable_free(expected_refs[i].u.ref.refname);
+	reftable_ref_record_release(&ref);
+	reftable_iterator_destroy(&it);
+	reftable_block_release(&block);
+	block_writer_release(&writer);
+	reftable_buf_release(&data);
+}
+
 int cmd_main(int argc UNUSED, const char *argv[] UNUSED)
 {
 	TEST(t_index_block_read_write(), "read-write operations on index blocks work");
 	TEST(t_log_block_read_write(), "read-write operations on log blocks work");
 	TEST(t_obj_block_read_write(), "read-write operations on obj blocks work");
 	TEST(t_ref_block_read_write(), "read-write operations on ref blocks work");
+	TEST(t_block_iterator(), "block iterator works");
 
 	return test_done();
 }