fix: get table size from metadata, not files (#3790)

Some issues:
- file_size_bytes is optional in the manifest, so if it's not there (old
writer I guess) it'll under-report the table size.
- it changes results a little bit from the old way by including per-file
footers and metadata (probably not a big difference at real scale)

---------

Co-authored-by: Will Jones <willjones127@gmail.com>
This commit is contained in:
Dan Tasse
2026-08-07 17:41:41 -04:00
committed by GitHub
parent 7bb501839a
commit 77a93fee76
8 changed files with 253 additions and 11 deletions
+9 -1
View File
@@ -3713,7 +3713,8 @@ def test_stats(mem_db: DBConnection):
stats = table.stats()
print(f"{stats=}")
assert stats == {
"total_bytes": 60,
# Full on-disk size of the data file, footer and metadata included.
"total_bytes": 633,
"num_rows": 2,
"num_indices": 0,
"fragment_stats": {
@@ -3731,6 +3732,13 @@ def test_stats(mem_db: DBConnection):
},
}
# Index files count toward total_bytes too (only deletion files and
# manifests are excluded).
table.create_index("id", config=BTree())
stats_with_index = table.stats()
assert stats_with_index["num_indices"] == 1
assert stats_with_index["total_bytes"] > stats["total_bytes"]
def test_create_table_empty_list_with_schema(mem_db: DBConnection):
"""Test creating table with empty list data and schema