feat(sync): add one-shot full sync (TRUNCATE + bulk INSERT)

- New `sync.fullsync` CLI: `python -m sync.fullsync config.yaml [--db F] [--table T] [--clear-change-log]`
- AccessReader: list_user_tables / read_all_rows / read_all_log_ids
- SqlWriter: table_exists / truncate_target (TRUNCATE w/ DELETE fallback) / bulk_insert (SET IDENTITY_INSERT + chunked fast_executemany)
- Reuses FileMapping exclude/include rules (exclude beats include, same as capture)
- Preserves Access IDs via IDENTITY_INSERT; target schemas have no FKs so TRUNCATE is safe
- TableChangeLog NOT cleared by default (opt-in --clear-change-log)
- tests/test_fullsync.py covers resolve_tables exclude/include precedence
This commit is contained in:
Misaka_Company
2026-07-14 18:06:39 +08:00
parent ea48de290f
commit a227aed0cb
4 changed files with 339 additions and 0 deletions

159
src/sync/fullsync.py Normal file
View File

@@ -0,0 +1,159 @@
"""One-shot full sync: TRUNCATE each target table, then bulk-insert every row
from the corresponding Access table.
This is a manual, out-of-band operation — ``python -m sync.fullsync
config.yaml [--db FILE] [--table NAME] [--clear-change-log]``. It deliberately
bypasses the incremental ``SyncQueue`` pipeline and writes straight to the SQL
Server mirror tables. Use it to (re)seed a schema from scratch or to repair
drift between Access and SQL Server.
Contract with the target tables (same as ``usp_SyncApply``): they already
exist and mirror the Access schema column-for-column, with ``ID`` as an
IDENTITY primary key. Because ``ID`` is an identity, ``SET IDENTITY_INSERT`` is
enabled during insert so the original Access primary keys survive — that is
what keeps the incremental sync's RecordID matching correct afterwards.
"""
from __future__ import annotations
import argparse
import logging
from .config import load_config, FileMapping, SyncConfig
from .access_reader import AccessReader
from .sql_writer import SqlWriter
from .logging_setup import setup_logging
log = logging.getLogger("sync.fullsync")
def resolve_tables(reader: AccessReader, fm: FileMapping) -> list[str]:
"""Tables to fully sync for one file, after exclude/include rules.
Mirrors the precedence used by ``capture.capture_file``: a table in
``exclude_tables`` is dropped even if it also appears in ``include_tables``.
System tables (``MSys*`` / ``~*``) are already filtered by
``AccessReader.list_user_tables``.
"""
exclude = set(fm.exclude_tables or [])
include = set(fm.include_tables) if fm.include_tables else None
out = []
for t in reader.list_user_tables():
if t in exclude:
continue
if include is not None and t not in include:
continue
out.append(t)
return out
def full_sync_file(fm: FileMapping, reader: AccessReader, writer: SqlWriter) -> dict:
"""Full-sync every eligible table in one Access file. Returns a summary."""
summary = {"file": fm.file, "tables": 0, "rows": 0, "skipped": []}
for access_table in resolve_tables(reader, fm):
target = fm.target_table(access_table)
if not writer.table_exists(fm.schema, target):
log.warning(
"skip %s -> %s.%s (target table missing)",
access_table, fm.schema, target,
)
summary["skipped"].append(access_table)
continue
try:
cols, rows = reader.read_all_rows(access_table)
writer.truncate_target(fm.schema, target)
n = writer.bulk_insert(fm.schema, target, cols, rows)
summary["tables"] += 1
summary["rows"] += n
log.info(
"full-synced %s -> %s.%s : %d rows",
access_table, fm.schema, target, n,
)
except Exception:
log.exception(
"full sync failed for %s -> %s.%s",
access_table, fm.schema, target,
)
summary["skipped"].append(access_table)
return summary
def full_sync(
cfg: SyncConfig,
db_filter: str | None = None,
table_filter: str | None = None,
clear_change_log: bool = False,
) -> list[dict]:
"""Run a full sync across all (optionally filtered) files.
``db_filter`` limits to a single Access file (matched on ``FileMapping.file``).
``table_filter`` restricts every considered file to that one table by
overriding ``include_tables``. ``clear_change_log`` additionally empties the
``TableChangeLog`` on each synced file after loading (use with care — it
mutates the Access side so the incremental service won't replay old deltas).
"""
files = cfg.files
if db_filter:
files = [f for f in files if f.file == db_filter]
if not files:
log.warning("no file matches --db %r", db_filter)
return []
if table_filter:
files = [f.model_copy(update={"include_tables": [table_filter]}) for f in files]
writer = SqlWriter(cfg.sql_server.conn_str, cfg.sql_server.sync_queue_table)
summaries = []
try:
for fm in files:
reader = AccessReader(fm.source_path(cfg), cfg.access.driver)
try:
summary = full_sync_file(fm, reader, writer)
summaries.append(summary)
if clear_change_log:
try:
ids = reader.read_all_log_ids()
deleted = reader.delete_log_ids(
ids, 500, 3
) if ids else 0
log.info("cleared %d TableChangeLog rows from %s", deleted, fm.file)
except Exception:
log.exception("clear-change-log failed for %s", fm.file)
finally:
reader.close()
finally:
writer.close()
return summaries
def main():
"""CLI entry point: ``python -m sync.fullsync config.yaml [options]``."""
ap = argparse.ArgumentParser(
description="One-shot full sync: Access -> SQL Server (TRUNCATE + bulk INSERT)."
)
ap.add_argument("config", nargs="?", default="config.yaml",
help="path to config.yaml (default: config.yaml)")
ap.add_argument("--db", help="limit to one Access file (by FileMapping.file)")
ap.add_argument("--table", help="limit to one table (applies to all matched files)")
ap.add_argument("--clear-change-log", action="store_true",
help="after loading, clear TableChangeLog on the synced files")
args = ap.parse_args()
cfg = load_config(args.config)
setup_logging(cfg.logging)
summaries = full_sync(
cfg,
db_filter=args.db,
table_filter=args.table,
clear_change_log=args.clear_change_log,
)
total_tables = sum(s["tables"] for s in summaries)
total_rows = sum(s["rows"] for s in summaries)
log.info("FULL SYNC COMPLETE: %d tables, %d rows", total_tables, total_rows)
for s in summaries:
if s["skipped"]:
log.warning(" %s: skipped %s", s["file"], s["skipped"])
if __name__ == "__main__":
main()