feat(bench): add SQLite and PostgreSQL wrappers for benchmark queries

- implement SQLite and PostgreSQL wrappers to execute benchmark queries
- update README to reflect task 09 as implemented
- enhance storage size updates to handle (format, variant) replacements
- clarify benchmarking methodology for remote PostgreSQL setup
This commit is contained in:
administrator
2026-07-11 22:34:23 -04:00
parent 48c102d2a4
commit eda11aa63e
6 changed files with 686 additions and 6 deletions

View File

@@ -1,8 +1,10 @@
"""Idempotent per-format updates to out/bench/storage_sizes.csv.
"""Idempotent per-(format, variant) updates to out/bench/storage_sizes.csv.
Contract (docs/rules/build-pipeline-tasks.md section 4): columns
format,variant,bytes; a task re-run REPLACES its own format's rows and never
touches other formats' rows.
format,variant,bytes; a task re-run REPLACES its own (format, variant) rows
and never touches other rows. Replacement is per variant, not per format:
converters 04-07 own the working-footprint variants while task 09 appends
archival variants of the same formats.
"""
from __future__ import annotations
@@ -25,12 +27,13 @@ def update_storage_sizes(bench_dir: Path, fmt: str, variants: list[tuple[str, in
lock = bench_dir / "storage_sizes.lock"
fd = _acquire(lock)
try:
replaced = {(fmt, variant) for variant, _ in variants}
kept: list[str] = []
if path.exists():
lines = path.read_text(encoding="ascii").splitlines()
if lines and lines[0] != HEADER:
raise ValueError(f"{path}: unexpected header {lines[0]!r}")
kept = [ln for ln in lines[1:] if ln and ln.split(",", 1)[0] != fmt]
kept = [ln for ln in lines[1:] if ln and tuple(ln.split(",")[:2]) not in replaced]
rows = kept + [f"{fmt},{variant},{nbytes}" for variant, nbytes in variants]
with open(path, "w", encoding="ascii", newline="\n") as fh:
fh.write(HEADER + "\n" + "\n".join(rows) + "\n")