reftable/reader: make table iterator reseekable

In 67ce50ba26 (Merge branch 'ps/reftable-reusable-iterator', 2024-05-30)
we have refactored the interface of reftable iterators such that they
can be reused in theory. This patch series only landed the required
changes on the interface level, but didn't yet implement the actual
logic to make iterators reusable.

As it turns out almost all of the infrastructure already does support
re-seeking. The only exception is the table iterator, which does not
reset its `is_finished` bit. Do so and add a couple of tests that verify
that we can re-seek iterators.

Signed-off-by: Patrick Steinhardt <ps@pks.im>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/Makefile b/Makefile
index 9460a80d0ddb4f8f3821e9142f0a09cbff34cfa9..4039e355b093efbf09ef8d3646f7bf8befd8aa69 100644 (file)
--- a/Makefile
+++ b/Makefile
@@ -1346,6 +1346,7 @@ UNIT_TEST_PROGRAMS += t-reftable-basics
 UNIT_TEST_PROGRAMS += t-reftable-block
 UNIT_TEST_PROGRAMS += t-reftable-merged
 UNIT_TEST_PROGRAMS += t-reftable-pq
+UNIT_TEST_PROGRAMS += t-reftable-reader
 UNIT_TEST_PROGRAMS += t-reftable-readwrite
 UNIT_TEST_PROGRAMS += t-reftable-record
 UNIT_TEST_PROGRAMS += t-reftable-stack

diff --git a/reftable/reader.c b/reftable/reader.c
index f8770990876b89b83cdd5158d47249e45f4b0523..6494ce2e32705e391ab1a1077dba07112cedf928 100644 (file)
--- a/reftable/reader.c
+++ b/reftable/reader.c
@@ -328,6 +328,7 @@ static int table_iter_seek_to(struct table_iter *ti, uint64_t off, uint8_t typ)
        ti->typ = block_reader_type(&ti->br);
        ti->block_off = off;
        block_iter_seek_start(&ti->bi, &ti->br);
+       ti->is_finished = 0;
        return 0;
 }
 

diff --git a/t/unit-tests/t-reftable-merged.c b/t/unit-tests/t-reftable-merged.c
index b8c92fdb365aba4d0df943f90e3e4e1dd7043543..19e54bdfb8b5ead3929299220e52d59dd13804a1 100644 (file)
--- a/t/unit-tests/t-reftable-merged.c
+++ b/t/unit-tests/t-reftable-merged.c
@@ -194,6 +194,81 @@ static void t_merged_refs(void)
        reftable_free(bs);
 }
 
+static void t_merged_seek_multiple_times(void)
+{
+       struct reftable_ref_record r1[] = {
+               {
+                       .refname = (char *) "a",
+                       .update_index = 1,
+                       .value_type = REFTABLE_REF_VAL1,
+                       .value.val1 = { 1 },
+               },
+               {
+                       .refname = (char *) "c",
+                       .update_index = 1,
+                       .value_type = REFTABLE_REF_VAL1,
+                       .value.val1 = { 2 },
+               }
+       };
+       struct reftable_ref_record r2[] = {
+               {
+                       .refname = (char *) "b",
+                       .update_index = 2,
+                       .value_type = REFTABLE_REF_VAL1,
+                       .value.val1 = { 3 },
+               },
+               {
+                       .refname = (char *) "d",
+                       .update_index = 2,
+                       .value_type = REFTABLE_REF_VAL1,
+                       .value.val1 = { 4 },
+               },
+       };
+       struct reftable_ref_record *refs[] = {
+               r1, r2,
+       };
+       size_t sizes[] = {
+               ARRAY_SIZE(r1), ARRAY_SIZE(r2),
+       };
+       struct strbuf bufs[] = {
+               STRBUF_INIT, STRBUF_INIT,
+       };
+       struct reftable_block_source *sources = NULL;
+       struct reftable_reader **readers = NULL;
+       struct reftable_ref_record rec = { 0 };
+       struct reftable_iterator it = { 0 };
+       struct reftable_merged_table *mt;
+
+       mt = merged_table_from_records(refs, &sources, &readers, sizes, bufs, 2);
+       merged_table_init_iter(mt, &it, BLOCK_TYPE_REF);
+
+       for (size_t i = 0; i < 5; i++) {
+               int err = reftable_iterator_seek_ref(&it, "c");
+               check(!err);
+
+               err = reftable_iterator_next_ref(&it, &rec);
+               check(!err);
+               err = reftable_ref_record_equal(&rec, &r1[1], GIT_SHA1_RAWSZ);
+               check(err == 1);
+
+               err = reftable_iterator_next_ref(&it, &rec);
+               check(!err);
+               err = reftable_ref_record_equal(&rec, &r2[1], GIT_SHA1_RAWSZ);
+               check(err == 1);
+
+               err = reftable_iterator_next_ref(&it, &rec);
+               check(err > 0);
+       }
+
+       for (size_t i = 0; i < ARRAY_SIZE(bufs); i++)
+               strbuf_release(&bufs[i]);
+       readers_destroy(readers, ARRAY_SIZE(refs));
+       reftable_ref_record_release(&rec);
+       reftable_iterator_destroy(&it);
+       reftable_merged_table_free(mt);
+       reftable_free(sources);
+}
+
 static struct reftable_merged_table *
 merged_table_from_log_records(struct reftable_log_record **logs,
                              struct reftable_block_source **source,
@@ -383,6 +458,7 @@ int cmd_main(int argc UNUSED, const char *argv[] UNUSED)
        TEST(t_default_write_opts(), "merged table with default write opts");
        TEST(t_merged_logs(), "merged table with multiple log updates for same ref");
        TEST(t_merged_refs(), "merged table with multiple updates to same ref");
+       TEST(t_merged_seek_multiple_times(), "merged table can seek multiple times");
        TEST(t_merged_single_record(), "ref ocurring in only one record can be fetched");
 
        return test_done();

diff --git a/t/unit-tests/t-reftable-reader.c b/t/unit-tests/t-reftable-reader.c
new file mode 100644 (file)
index 0000000..eea8696
--- /dev/null
+++ b/t/unit-tests/t-reftable-reader.c
@@ -0,0 +1,96 @@
+#include "test-lib.h"
+#include "lib-reftable.h"
+#include "reftable/blocksource.h"
+#include "reftable/reader.h"
+
+static int t_reader_seek_once(void)
+{
+       struct reftable_ref_record records[] = {
+               {
+                       .refname = (char *) "refs/heads/main",
+                       .value_type = REFTABLE_REF_VAL1,
+                       .value.val1 = { 42 },
+               },
+       };
+       struct reftable_block_source source = { 0 };
+       struct reftable_ref_record ref = { 0 };
+       struct reftable_iterator it = { 0 };
+       struct reftable_reader *reader;
+       struct strbuf buf = STRBUF_INIT;
+       int ret;
+
+       t_reftable_write_to_buf(&buf, records, ARRAY_SIZE(records), NULL, 0, NULL);
+       block_source_from_strbuf(&source, &buf);
+
+       ret = reftable_reader_new(&reader, &source, "name");
+       check(!ret);
+
+       reftable_reader_init_ref_iterator(reader, &it);
+       ret = reftable_iterator_seek_ref(&it, "");
+       check(!ret);
+       ret = reftable_iterator_next_ref(&it, &ref);
+       check(!ret);
+
+       ret = reftable_ref_record_equal(&ref, &records[0], GIT_SHA1_RAWSZ);
+       check_int(ret, ==, 1);
+
+       ret = reftable_iterator_next_ref(&it, &ref);
+       check_int(ret, ==, 1);
+
+       reftable_ref_record_release(&ref);
+       reftable_iterator_destroy(&it);
+       reftable_reader_decref(reader);
+       strbuf_release(&buf);
+       return 0;
+}
+
+static int t_reader_reseek(void)
+{
+       struct reftable_ref_record records[] = {
+               {
+                       .refname = (char *) "refs/heads/main",
+                       .value_type = REFTABLE_REF_VAL1,
+                       .value.val1 = { 42 },
+               },
+       };
+       struct reftable_block_source source = { 0 };
+       struct reftable_ref_record ref = { 0 };
+       struct reftable_iterator it = { 0 };
+       struct reftable_reader *reader;
+       struct strbuf buf = STRBUF_INIT;
+       int ret;
+
+       t_reftable_write_to_buf(&buf, records, ARRAY_SIZE(records), NULL, 0, NULL);
+       block_source_from_strbuf(&source, &buf);
+
+       ret = reftable_reader_new(&reader, &source, "name");
+       check(!ret);
+
+       reftable_reader_init_ref_iterator(reader, &it);
+
+       for (size_t i = 0; i < 5; i++) {
+               ret = reftable_iterator_seek_ref(&it, "");
+               check(!ret);
+               ret = reftable_iterator_next_ref(&it, &ref);
+               check(!ret);
+
+               ret = reftable_ref_record_equal(&ref, &records[0], GIT_SHA1_RAWSZ);
+               check_int(ret, ==, 1);
+
+               ret = reftable_iterator_next_ref(&it, &ref);
+               check_int(ret, ==, 1);
+       }
+
+       reftable_ref_record_release(&ref);
+       reftable_iterator_destroy(&it);
+       reftable_reader_decref(reader);
+       strbuf_release(&buf);
+       return 0;
+}
+
+int cmd_main(int argc UNUSED, const char *argv[] UNUSED)
+{
+       TEST(t_reader_seek_once(), "reader can seek once");
+       TEST(t_reader_reseek(), "reader can reseek multiple times");
+       return test_done();
+}