Migrate sync objects into ProductionDataBaseSync schema + add permanent audit archive

- Add sql/00_schema.sql: create dedicated ProductionDataBaseSync schema (idempotent)
- Move SyncQueue and usp_SyncApply from dbo into ProductionDataBaseSync
- Add sql/03_sync_log_archive.sql: permanent, append-only SyncLogArchive that
  records both OriginalOperateType and ProcessedOperateType plus the Access log
  OriginalTime, so pipeline divergences (e.g. Insert applied as Delete) stay
  reconstructible forever (SyncQueue is transient and only keeps processed type)
- config.py: inject sync_queue_table / archive_table / apply_proc (default to the
  new schema); SqlWriter takes these names instead of hardcoding dbo
- sql_writer.py: add ArchiveRow + insert_archive_row (dedup on source keys),
  parametrize queue/archive/proc names throughout
- capture.py: archive every consumed log row before enqueue (preserves evidence
  before cleanup deletes the Access log)
- service.py: pass the three names into SqlWriter
- tests: read queue/proc names from config instead of hardcoding dbo.SyncQueue
This commit is contained in:
Misaka_Company
2026-07-16 12:32:22 +08:00
parent 4179d3e232
commit d71b7eab62
11 changed files with 242 additions and 61 deletions

12
sql/00_schema.sql Normal file
View File

@@ -0,0 +1,12 @@
-- ProductionDataBaseSync: dedicated schema that groups every object owned by
-- the Access -> SQL Server sync (SyncQueue staging, SyncLogArchive audit store,
-- and the usp_SyncApply procedure). Keeping them out of dbo makes ownership and
-- housekeeping explicit.
-- Idempotent: CREATE SCHEMA must be the only statement in its batch, so it is
-- wrapped in EXEC() behind an existence check.
IF NOT EXISTS (SELECT 1 FROM sys.schemas WHERE name = 'ProductionDataBaseSync')
BEGIN
EXEC('CREATE SCHEMA ProductionDataBaseSync');
END
GO

View File

@@ -1,9 +1,10 @@
-- SyncQueue: staging table for the Access -> SQL Server one-way sync. -- SyncQueue: staging table for the Access -> SQL Server one-way sync.
-- Lives under the ProductionDataBaseSync schema (run 00_schema.sql first).
-- Idempotent: safe to re-run (table created only if absent; indexes only if absent). -- Idempotent: safe to re-run (table created only if absent; indexes only if absent).
IF OBJECT_ID('dbo.SyncQueue', 'U') IS NULL IF OBJECT_ID('ProductionDataBaseSync.SyncQueue', 'U') IS NULL
BEGIN BEGIN
CREATE TABLE dbo.SyncQueue ( CREATE TABLE ProductionDataBaseSync.SyncQueue (
QueueID bigint IDENTITY(1,1) NOT NULL, QueueID bigint IDENTITY(1,1) NOT NULL,
SourceFile nvarchar(255) NOT NULL, SourceFile nvarchar(255) NOT NULL,
SourceTable nvarchar(255) NOT NULL, SourceTable nvarchar(255) NOT NULL,
@@ -18,6 +19,7 @@ BEGIN
ErrorMsg nvarchar(max) NULL, ErrorMsg nvarchar(max) NULL,
CapturedAt datetime2 NOT NULL CONSTRAINT DF_SyncQueue_Captured DEFAULT sysdatetime(), CapturedAt datetime2 NOT NULL CONSTRAINT DF_SyncQueue_Captured DEFAULT sysdatetime(),
AppliedAt datetime2 NULL, AppliedAt datetime2 NULL,
CleanedAt datetime2 NULL,
CONSTRAINT PK_SyncQueue PRIMARY KEY CLUSTERED (QueueID) CONSTRAINT PK_SyncQueue PRIMARY KEY CLUSTERED (QueueID)
); );
END END
@@ -25,38 +27,27 @@ GO
IF NOT EXISTS (SELECT 1 FROM sys.indexes IF NOT EXISTS (SELECT 1 FROM sys.indexes
WHERE name = 'UX_SyncQueue_Dedup' WHERE name = 'UX_SyncQueue_Dedup'
AND object_id = OBJECT_ID('dbo.SyncQueue')) AND object_id = OBJECT_ID('ProductionDataBaseSync.SyncQueue'))
BEGIN BEGIN
CREATE UNIQUE INDEX UX_SyncQueue_Dedup CREATE UNIQUE INDEX UX_SyncQueue_Dedup
ON dbo.SyncQueue(SourceFile, SourceTable, SourceLogID); ON ProductionDataBaseSync.SyncQueue(SourceFile, SourceTable, SourceLogID);
END END
GO GO
IF NOT EXISTS (SELECT 1 FROM sys.indexes IF NOT EXISTS (SELECT 1 FROM sys.indexes
WHERE name = 'IX_SyncQueue_Pending' WHERE name = 'IX_SyncQueue_Pending'
AND object_id = OBJECT_ID('dbo.SyncQueue')) AND object_id = OBJECT_ID('ProductionDataBaseSync.SyncQueue'))
BEGIN BEGIN
CREATE INDEX IX_SyncQueue_Pending CREATE INDEX IX_SyncQueue_Pending
ON dbo.SyncQueue(Status, TargetSchema, TargetTable); ON ProductionDataBaseSync.SyncQueue(Status, TargetSchema, TargetTable);
END
GO
-- Cleanup bookkeeping: track when a queue row's Access log counterpart has
-- been physically deleted, so cleanup never re-deletes the same IDs and the
-- table can be purged to bound its growth.
IF NOT EXISTS (SELECT 1 FROM sys.columns
WHERE object_id = OBJECT_ID('dbo.SyncQueue')
AND name = 'CleanedAt')
BEGIN
ALTER TABLE dbo.SyncQueue ADD CleanedAt datetime2 NULL;
END END
GO GO
IF NOT EXISTS (SELECT 1 FROM sys.indexes IF NOT EXISTS (SELECT 1 FROM sys.indexes
WHERE name = 'IX_SyncQueue_Cleaned' WHERE name = 'IX_SyncQueue_Cleaned'
AND object_id = OBJECT_ID('dbo.SyncQueue')) AND object_id = OBJECT_ID('ProductionDataBaseSync.SyncQueue'))
BEGIN BEGIN
CREATE INDEX IX_SyncQueue_Cleaned CREATE INDEX IX_SyncQueue_Cleaned
ON dbo.SyncQueue(Status, CleanedAt); ON ProductionDataBaseSync.SyncQueue(Status, CleanedAt);
END END
GO GO

View File

@@ -11,7 +11,7 @@
-- and silently drop a row whose true last op was an Insert. Routing off the one -- and silently drop a row whose true last op was an Insert. Routing off the one
-- winning row's OperateType guarantees only the genuine last op wins. -- winning row's OperateType guarantees only the genuine last op wins.
CREATE OR ALTER PROCEDURE dbo.usp_SyncApply CREATE OR ALTER PROCEDURE ProductionDataBaseSync.usp_SyncApply
@MaxRetries INT = 5 @MaxRetries INT = 5
AS AS
BEGIN BEGIN
@@ -21,13 +21,13 @@ BEGIN
DECLARE @sql NVARCHAR(MAX), @cols NVARCHAR(MAX), @upd NVARCHAR(MAX), @ins NVARCHAR(MAX); DECLARE @sql NVARCHAR(MAX), @cols NVARCHAR(MAX), @upd NVARCHAR(MAX), @ins NVARCHAR(MAX);
-- Re-queue rows still under the retry budget. -- Re-queue rows still under the retry budget.
UPDATE dbo.SyncQueue UPDATE ProductionDataBaseSync.SyncQueue
SET Status = 'pending' SET Status = 'pending'
WHERE Status = 'error' AND RetryCount < @MaxRetries; WHERE Status = 'error' AND RetryCount < @MaxRetries;
DECLARE cur CURSOR LOCAL FAST_FORWARD FOR DECLARE cur CURSOR LOCAL FAST_FORWARD FOR
SELECT DISTINCT TargetSchema, TargetTable SELECT DISTINCT TargetSchema, TargetTable
FROM dbo.SyncQueue FROM ProductionDataBaseSync.SyncQueue
WHERE Status = 'pending'; WHERE Status = 'pending';
OPEN cur; OPEN cur;
@@ -70,7 +70,7 @@ BEGIN
+ N';WITH ranked AS (' + N';WITH ranked AS ('
+ N' SELECT RecordID, OperateType, RowData,' + N' SELECT RecordID, OperateType, RowData,'
+ N' ROW_NUMBER() OVER (PARTITION BY RecordID ORDER BY SourceLogID DESC) rn' + N' ROW_NUMBER() OVER (PARTITION BY RecordID ORDER BY SourceLogID DESC) rn'
+ N' FROM dbo.SyncQueue' + N' FROM ProductionDataBaseSync.SyncQueue'
+ N' WHERE TargetSchema=@sch AND TargetTable=@tbl AND Status=''pending''' + N' WHERE TargetSchema=@sch AND TargetTable=@tbl AND Status=''pending'''
+ N')' + N')'
+ N'MERGE ' + @FullName + N' WITH (HOLDLOCK) AS tgt' + N'MERGE ' + @FullName + N' WITH (HOLDLOCK) AS tgt'
@@ -90,7 +90,7 @@ BEGIN
SET @sql = N';WITH ranked AS (' SET @sql = N';WITH ranked AS ('
+ N' SELECT RecordID, OperateType,' + N' SELECT RecordID, OperateType,'
+ N' ROW_NUMBER() OVER (PARTITION BY RecordID ORDER BY SourceLogID DESC) rn' + N' ROW_NUMBER() OVER (PARTITION BY RecordID ORDER BY SourceLogID DESC) rn'
+ N' FROM dbo.SyncQueue' + N' FROM ProductionDataBaseSync.SyncQueue'
+ N' WHERE TargetSchema=@sch AND TargetTable=@tbl AND Status=''pending''' + N' WHERE TargetSchema=@sch AND TargetTable=@tbl AND Status=''pending'''
+ N')' + N')'
+ N'DELETE t FROM ' + @FullName + N' t' + N'DELETE t FROM ' + @FullName + N' t'
@@ -100,7 +100,7 @@ BEGIN
N'@sch NVARCHAR(128),@tbl NVARCHAR(255)', @sch, @tbl; N'@sch NVARCHAR(128),@tbl NVARCHAR(255)', @sch, @tbl;
END END
UPDATE dbo.SyncQueue UPDATE ProductionDataBaseSync.SyncQueue
SET Status = 'applied', AppliedAt = SYSDATETIME() SET Status = 'applied', AppliedAt = SYSDATETIME()
WHERE TargetSchema = @sch AND TargetTable = @tbl AND Status = 'pending'; WHERE TargetSchema = @sch AND TargetTable = @tbl AND Status = 'pending';
@@ -113,7 +113,7 @@ BEGIN
-- issues its own rollback. We roll back here so the partial per-table -- issues its own rollback. We roll back here so the partial per-table
-- work is discarded before marking rows as 'error'/'dead'. -- work is discarded before marking rows as 'error'/'dead'.
IF @@TRANCOUNT > 0 ROLLBACK; IF @@TRANCOUNT > 0 ROLLBACK;
UPDATE dbo.SyncQueue UPDATE ProductionDataBaseSync.SyncQueue
SET Status = CASE WHEN RetryCount + 1 >= @MaxRetries THEN 'dead' ELSE 'error' END, SET Status = CASE WHEN RetryCount + 1 >= @MaxRetries THEN 'dead' ELSE 'error' END,
RetryCount = RetryCount + 1, RetryCount = RetryCount + 1,
ErrorMsg = ERROR_MESSAGE() ErrorMsg = ERROR_MESSAGE()

View File

@@ -0,0 +1,71 @@
-- SyncLogArchive: permanent, append-only audit store for every Access change-log
-- row consumed by the incremental sync. This is the durable evidence layer that
-- SyncQueue is NOT: SyncQueue is a transient work queue (purged 24h after a row
-- is cleaned) and it only stores the *processed* OperateType, so a downgrade
-- (e.g. capture turning an Insert into a Delete when the row is momentarily
-- unreadable) erases the original intent. This table preserves both the ORIGINAL
-- operate type recorded by the Access data macro and the PROCESSED type actually
-- sent to SQL Server, plus the original Access log timestamp and the row payload.
--
-- With this in place, cases like the 14287 incident (a real Insert applied to SQL
-- as a Delete) stay fully reconstructible: OriginalOperateType != ProcessedOperateType
-- flags exactly where the pipeline diverged from the source.
--
-- Retention: PERMANENT. No purge job touches this table. SyncQueue keeps its
-- short-lived queue role; this table keeps history. Lives under the
-- ProductionDataBaseSync schema (run 00_schema.sql first).
-- Idempotent: safe to re-run.
IF OBJECT_ID('ProductionDataBaseSync.SyncLogArchive', 'U') IS NULL
BEGIN
CREATE TABLE ProductionDataBaseSync.SyncLogArchive (
ArchiveID bigint IDENTITY(1,1) NOT NULL,
SourceFile nvarchar(255) NOT NULL,
SourceTable nvarchar(255) NOT NULL,
SourceLogID bigint NOT NULL,
RecordID nvarchar(50) NOT NULL,
TargetSchema nvarchar(128) NOT NULL,
TargetTable nvarchar(255) NOT NULL,
OriginalOperateType varchar(10) NOT NULL, -- as recorded by the Access data macro
ProcessedOperateType varchar(10) NOT NULL, -- as actually sent to SyncQueue / SQL
RowData nvarchar(max) NULL, -- captured row payload (NULL for Delete)
OriginalTime datetime2 NULL, -- Access TableChangeLog.Time (previously discarded)
CapturedAt datetime2 NOT NULL
CONSTRAINT DF_SyncLogArchive_Captured DEFAULT sysdatetime(),
CONSTRAINT PK_SyncLogArchive PRIMARY KEY CLUSTERED (ArchiveID)
);
END
GO
-- Dedup: one archive row per source log entry. Capture may re-run the same log
-- row if a prior cycle's apply failed (the Access log is only deleted after a
-- successful apply), so the write path uses IF NOT EXISTS on these keys.
IF NOT EXISTS (SELECT 1 FROM sys.indexes
WHERE name = 'UX_SyncLogArchive_Dedup'
AND object_id = OBJECT_ID('ProductionDataBaseSync.SyncLogArchive'))
BEGIN
CREATE UNIQUE INDEX UX_SyncLogArchive_Dedup
ON ProductionDataBaseSync.SyncLogArchive(SourceFile, SourceTable, SourceLogID);
END
GO
-- Evidence lookup by table + record (e.g. "show every log ever seen for ID 14287").
IF NOT EXISTS (SELECT 1 FROM sys.indexes
WHERE name = 'IX_SyncLogArchive_Record'
AND object_id = OBJECT_ID('ProductionDataBaseSync.SyncLogArchive'))
BEGIN
CREATE INDEX IX_SyncLogArchive_Record
ON ProductionDataBaseSync.SyncLogArchive(SourceTable, RecordID);
END
GO
-- Fast filter for the anomaly the archive exists to catch: original != processed.
IF NOT EXISTS (SELECT 1 FROM sys.indexes
WHERE name = 'IX_SyncLogArchive_Divergence'
AND object_id = OBJECT_ID('ProductionDataBaseSync.SyncLogArchive'))
BEGIN
CREATE INDEX IX_SyncLogArchive_Divergence
ON ProductionDataBaseSync.SyncLogArchive(OriginalOperateType, ProcessedOperateType)
INCLUDE (SourceFile, SourceTable, RecordID, CapturedAt);
END
GO

View File

@@ -1,7 +1,7 @@
from __future__ import annotations from __future__ import annotations
import json, logging import json, logging
from .access_reader import AccessReader from .access_reader import AccessReader
from .sql_writer import SqlWriter, QueueRow from .sql_writer import SqlWriter, QueueRow, ArchiveRow
from .config import FileMapping, SyncConfig from .config import FileMapping, SyncConfig
from .targets import is_synced_table from .targets import is_synced_table
@@ -24,12 +24,30 @@ def capture_file(fm: FileMapping, reader: AccessReader, writer: SqlWriter, cfg:
elif op != "Delete": elif op != "Delete":
log.warning("unknown OperateType %r in %s log %s", op, fm.file, lr.id) log.warning("unknown OperateType %r in %s log %s", op, fm.file, lr.id)
continue continue
target_schema = fm.schema
target_table = fm.target_table(lr.table_name)
# Persist the ORIGINAL log entry to the permanent audit store BEFORE the
# queue insert (and long before cleanup deletes the Access log). This
# keeps both the source operate type (lr.operate_type) and the processed
# one (op) so a downgrade like Insert->Delete stays reconstructible.
writer.insert_archive_row(ArchiveRow(
source_file=fm.file,
source_table=lr.table_name,
source_log_id=lr.id,
record_id=lr.record_id,
target_schema=target_schema,
target_table=target_table,
original_operate_type=lr.operate_type,
processed_operate_type=op,
row_data=row_data,
original_time=lr.time,
))
qr = QueueRow( qr = QueueRow(
source_file=fm.file, source_file=fm.file,
source_table=lr.table_name, source_table=lr.table_name,
record_id=lr.record_id, record_id=lr.record_id,
target_schema=fm.schema, target_schema=target_schema,
target_table=fm.target_table(lr.table_name), target_table=target_table,
source_log_id=lr.id, source_log_id=lr.id,
operate_type=op, operate_type=op,
row_data=row_data, row_data=row_data,

View File

@@ -1,6 +1,6 @@
"""Cleanup phase: delete applied Access log rows. """Cleanup phase: delete applied Access log rows.
After ``dbo.usp_SyncApply`` flips queue rows to ``applied``, those rows' After ``usp_SyncApply`` flips queue rows to ``applied``, those rows'
``SourceLogID`` values are no longer needed on the Access side. This module ``SourceLogID`` values are no longer needed on the Access side. This module
asks the writer which log IDs have been applied for a given source file and asks the writer which log IDs have been applied for a given source file and
deletes them from ``TableChangeLog`` via the reader, in batches with lock deletes them from ``TableChangeLog`` via the reader, in batches with lock

View File

@@ -5,7 +5,9 @@ from pydantic import BaseModel, ConfigDict, Field
class SqlServerConfig(BaseModel): class SqlServerConfig(BaseModel):
conn_str: str conn_str: str
sync_queue_table: str = "dbo.SyncQueue" sync_queue_table: str = "ProductionDataBaseSync.SyncQueue"
archive_table: str = "ProductionDataBaseSync.SyncLogArchive"
apply_proc: str = "ProductionDataBaseSync.usp_SyncApply"
class AccessConfig(BaseModel): class AccessConfig(BaseModel):
model_config = ConfigDict(coerce_numbers_to_str=True) model_config = ConfigDict(coerce_numbers_to_str=True)

View File

@@ -2,7 +2,7 @@
``cycle(cfg)`` runs one full pass over every configured file: ``cycle(cfg)`` runs one full pass over every configured file:
1. capture — read each file's change log and stage rows into SyncQueue; 1. capture — read each file's change log and stage rows into SyncQueue;
2. apply — drain the queue via ``dbo.usp_SyncApply``; 2. apply — drain the queue via ``usp_SyncApply``;
3. cleanup — delete applied log rows from each file's Access log. 3. cleanup — delete applied log rows from each file's Access log.
Each file's capture and cleanup is wrapped in its own try/except so one Each file's capture and cleanup is wrapped in its own try/except so one
@@ -45,7 +45,12 @@ def cycle(cfg):
Apply failure does not block cleanup. The writer is always closed in a Apply failure does not block cleanup. The writer is always closed in a
``finally``. Safe to call directly from tests (does not sleep or loop). ``finally``. Safe to call directly from tests (does not sleep or loop).
""" """
writer = SqlWriter(cfg.sql_server.conn_str, cfg.sql_server.sync_queue_table) writer = SqlWriter(
cfg.sql_server.conn_str,
cfg.sql_server.sync_queue_table,
cfg.sql_server.archive_table,
cfg.sql_server.apply_proc,
)
try: try:
total_captured = 0 total_captured = 0
for fm in cfg.files: for fm in cfg.files:

View File

@@ -1,8 +1,12 @@
"""SQL-side writer for the Access -> SQL Server sync. """SQL-side writer for the Access -> SQL Server sync.
SqlWriter owns the pyodbc connection used to (a) dedup-insert rows into SqlWriter owns the pyodbc connection used to (a) dedup-insert rows into the
``dbo.SyncQueue``, (b) invoke ``dbo.usp_SyncApply`` to drain the queue, and staging queue (``ProductionDataBaseSync.SyncQueue`` by default), (b) invoke the
(c) report which SourceLogIDs have been applied. apply proc (``ProductionDataBaseSync.usp_SyncApply``) to drain the queue,
(c) report which SourceLogIDs have been applied, and (d) append every consumed
Access change-log row to the permanent audit store
(``ProductionDataBaseSync.SyncLogArchive``). The queue/archive/proc names are
injected from config so the whole sync can live under a dedicated schema.
The connection is opened with ``autocommit=True`` on purpose. ``usp_SyncApply`` The connection is opened with ``autocommit=True`` on purpose. ``usp_SyncApply``
manages its own transaction internally (BEGIN TRAN ... ROLLBACK on error); if manages its own transaction internally (BEGIN TRAN ... ROLLBACK on error); if
@@ -20,7 +24,7 @@ import pyodbc
@dataclass @dataclass
class QueueRow: class QueueRow:
"""A single staged change to enqueue into ``dbo.SyncQueue``.""" """A single staged change to enqueue into the SyncQueue table."""
source_file: str source_file: str
source_table: str source_table: str
@@ -32,12 +36,43 @@ class QueueRow:
row_data: str | None row_data: str | None
class SqlWriter: @dataclass
"""Writes to SyncQueue and drives the apply proc over a pyodbc connection.""" class ArchiveRow:
"""A single Access change-log row to append to ``SyncLogArchive``.
def __init__(self, conn_str: str, queue_table: str = "dbo.SyncQueue"): Captures both the ORIGINAL operate type recorded by the Access data macro
and the PROCESSED operate type actually sent to the queue, so a downgrade
(e.g. Insert -> Delete when the row is momentarily unreadable) stays visible
forever. ``original_time`` preserves the Access log's own timestamp, which
the queue path discards.
"""
source_file: str
source_table: str
source_log_id: int
record_id: str
target_schema: str
target_table: str
original_operate_type: str
processed_operate_type: str
row_data: str | None
original_time: object
class SqlWriter:
"""Writes to SyncQueue/SyncLogArchive and drives the apply proc."""
def __init__(
self,
conn_str: str,
queue_table: str = "ProductionDataBaseSync.SyncQueue",
archive_table: str = "ProductionDataBaseSync.SyncLogArchive",
apply_proc: str = "ProductionDataBaseSync.usp_SyncApply",
):
self.conn_str = conn_str self.conn_str = conn_str
self.queue_table = queue_table self.queue_table = queue_table
self.archive_table = archive_table
self.apply_proc = apply_proc
# autocommit=True: usp_SyncApply manages its own transaction internally. # autocommit=True: usp_SyncApply manages its own transaction internally.
# An outer pyodbc transaction would conflict on ROLLBACK (SQL error 266). # An outer pyodbc transaction would conflict on ROLLBACK (SQL error 266).
self._conn = pyodbc.connect(conn_str, autocommit=True) self._conn = pyodbc.connect(conn_str, autocommit=True)
@@ -53,9 +88,9 @@ class SqlWriter:
# twice (once for the EXISTS check, once for the INSERT). # twice (once for the EXISTS check, once for the INSERT).
cur = self._conn.cursor() cur = self._conn.cursor()
cur.execute( cur.execute(
"IF NOT EXISTS (SELECT 1 FROM dbo.SyncQueue " f"IF NOT EXISTS (SELECT 1 FROM {self.queue_table} "
"WHERE SourceFile=? AND SourceTable=? AND SourceLogID=?) " "WHERE SourceFile=? AND SourceTable=? AND SourceLogID=?) "
"INSERT dbo.SyncQueue(SourceFile,SourceTable,SourceLogID," f"INSERT {self.queue_table}(SourceFile,SourceTable,SourceLogID,"
"TargetSchema,TargetTable,RecordID,OperateType,RowData,Status) " "TargetSchema,TargetTable,RecordID,OperateType,RowData,Status) "
"VALUES (?,?,?,?,?,?,?,?, 'pending')", "VALUES (?,?,?,?,?,?,?,?, 'pending')",
row.source_file, row.source_file,
@@ -72,19 +107,52 @@ class SqlWriter:
) )
# autocommit: statement already committed. # autocommit: statement already committed.
def insert_archive_row(self, row: ArchiveRow) -> None:
"""Append ``row`` to the permanent audit store (dedup on source keys).
Written during capture, BEFORE cleanup deletes the Access log, so the
original evidence survives even after the queue row is purged. Stores
both the original and processed operate types plus the Access log time.
``IF NOT EXISTS`` keeps the first archive record if capture re-runs the
same log id (a prior cycle's apply failed and the Access log persisted).
"""
cur = self._conn.cursor()
cur.execute(
f"IF NOT EXISTS (SELECT 1 FROM {self.archive_table} "
"WHERE SourceFile=? AND SourceTable=? AND SourceLogID=?) "
f"INSERT {self.archive_table}(SourceFile,SourceTable,SourceLogID,"
"RecordID,TargetSchema,TargetTable,OriginalOperateType,"
"ProcessedOperateType,RowData,OriginalTime) "
"VALUES (?,?,?,?,?,?,?,?,?,?)",
row.source_file,
row.source_table,
row.source_log_id,
row.source_file,
row.source_table,
row.source_log_id,
row.record_id,
row.target_schema,
row.target_table,
row.original_operate_type,
row.processed_operate_type,
row.row_data,
row.original_time,
)
# autocommit: statement already committed.
def call_apply(self, max_retries: int) -> None: def call_apply(self, max_retries: int) -> None:
"""Drain the pending queue via the stored procedure. """Drain the pending queue via the stored procedure.
``usp_SyncApply`` flips rows to ``applied`` (or ``error`` after retries). ``usp_SyncApply`` flips rows to ``applied`` (or ``error`` after retries).
""" """
cur = self._conn.cursor() cur = self._conn.cursor()
cur.execute("EXEC dbo.usp_SyncApply ?", max_retries) cur.execute(f"EXEC {self.apply_proc} ?", max_retries)
def applied_log_ids(self, source_file: str) -> list[int]: def applied_log_ids(self, source_file: str) -> list[int]:
"""Return applied SourceLogIDs for ``source_file`` in ascending order.""" """Return applied SourceLogIDs for ``source_file`` in ascending order."""
cur = self._conn.cursor() cur = self._conn.cursor()
cur.execute( cur.execute(
"SELECT SourceLogID FROM dbo.SyncQueue " f"SELECT SourceLogID FROM {self.queue_table} "
"WHERE SourceFile=? AND Status='applied' ORDER BY SourceLogID", "WHERE SourceFile=? AND Status='applied' ORDER BY SourceLogID",
source_file, source_file,
) )
@@ -107,7 +175,7 @@ class SqlWriter:
chunk = source_log_ids[i:i + 1000] chunk = source_log_ids[i:i + 1000]
placeholders = ",".join("?" * len(chunk)) placeholders = ",".join("?" * len(chunk))
cur.execute( cur.execute(
f"UPDATE dbo.SyncQueue SET Status='cleaned', " f"UPDATE {self.queue_table} SET Status='cleaned', "
f"CleanedAt=sysdatetime() " f"CleanedAt=sysdatetime() "
f"WHERE SourceFile=? AND Status='applied' " f"WHERE SourceFile=? AND Status='applied' "
f"AND SourceLogID IN ({placeholders})", f"AND SourceLogID IN ({placeholders})",
@@ -120,12 +188,12 @@ class SqlWriter:
Keeps the table bounded: cleanup marks rows ``cleaned`` every cycle, Keeps the table bounded: cleanup marks rows ``cleaned`` every cycle,
and this removes the old ones after a short audit/debug window so and this removes the old ones after a short audit/debug window so
``dbo.SyncQueue`` stops growing without bound. Returns the number of the queue table stops growing without bound. Returns the number of
rows removed. rows removed.
""" """
cur = self._conn.cursor() cur = self._conn.cursor()
cur.execute( cur.execute(
"DELETE FROM dbo.SyncQueue " f"DELETE FROM {self.queue_table} "
"WHERE Status='cleaned' " "WHERE Status='cleaned' "
"AND CleanedAt < DATEADD(hour, -?, GETDATE())", "AND CleanedAt < DATEADD(hour, -?, GETDATE())",
retention_hours, retention_hours,

View File

@@ -1,15 +1,23 @@
"""Integration test for dbo.usp_SyncApply. """Integration test for usp_SyncApply.
Validates: IDENTITY-preserving INSERT, last-write-wins UPDATE, BIT conversion Validates: IDENTITY-preserving INSERT, last-write-wins UPDATE, BIT conversion
from JSON ``true``/``false``, and DELETE of the last op. Creates a throwaway from JSON ``true``/``false``, and DELETE of the last op. Creates a throwaway
schema ``sync_test`` and table ``ApplyDemo_YEAR2026`` and cleans them up at the schema ``sync_test`` and table ``ApplyDemo_YEAR2026`` and cleans them up at the
end so no residue is left on CompanyDB. end so no residue is left on CompanyDB.
Queue table and apply proc names are read from ``config.yaml`` so the test
follows whichever schema the deployment targets (currently ProductionDataBaseSync).
""" """
import pytest import pytest
from sync.config import load_config
@pytest.mark.integration @pytest.mark.integration
def test_upsert_insert_update_delete_last_write_wins(sql_conn): def test_upsert_insert_update_delete_last_write_wins(sql_conn):
cfg = load_config("config.yaml")
qt = cfg.sql_server.sync_queue_table
proc = cfg.sql_server.apply_proc
cur = sql_conn.cursor() cur = sql_conn.cursor()
sch, tbl = "sync_test", "ApplyDemo_YEAR2026" sch, tbl = "sync_test", "ApplyDemo_YEAR2026"
@@ -27,17 +35,17 @@ def test_upsert_insert_update_delete_last_write_wins(sql_conn):
"时间 DATETIME2 NULL, " "时间 DATETIME2 NULL, "
"标记 BIT NULL)" "标记 BIT NULL)"
) )
cur.execute("DELETE dbo.SyncQueue WHERE TargetSchema='sync_test'") cur.execute("DELETE " + qt + " WHERE TargetSchema='sync_test'")
# Insert then a later Update for the same RecordID=1 -> last write wins. # Insert then a later Update for the same RecordID=1 -> last write wins.
cur.execute( cur.execute(
"INSERT dbo.SyncQueue(SourceFile,SourceTable,SourceLogID,TargetSchema," "INSERT " + qt + "(SourceFile,SourceTable,SourceLogID,TargetSchema,"
"TargetTable,RecordID,OperateType,RowData,Status) " "TargetTable,RecordID,OperateType,RowData,Status) "
"VALUES('t.accdb','ApplyDemo',1,'sync_test','ApplyDemo_YEAR2026','1'," "VALUES('t.accdb','ApplyDemo',1,'sync_test','ApplyDemo_YEAR2026','1',"
"'Insert','{\"ID\":1,\"名字\":\"A\",\"数量\":3,\"时间\":\"2026-01-01T00:00:00\",\"标记\":true}','pending')" "'Insert','{\"ID\":1,\"名字\":\"A\",\"数量\":3,\"时间\":\"2026-01-01T00:00:00\",\"标记\":true}','pending')"
) )
cur.execute( cur.execute(
"INSERT dbo.SyncQueue(SourceFile,SourceTable,SourceLogID,TargetSchema," "INSERT " + qt + "(SourceFile,SourceTable,SourceLogID,TargetSchema,"
"TargetTable,RecordID,OperateType,RowData,Status) " "TargetTable,RecordID,OperateType,RowData,Status) "
"VALUES('t.accdb','ApplyDemo',2,'sync_test','ApplyDemo_YEAR2026','1'," "VALUES('t.accdb','ApplyDemo',2,'sync_test','ApplyDemo_YEAR2026','1',"
"'Update','{\"ID\":1,\"名字\":\"A2\",\"数量\":5,\"时间\":\"2026-01-02T00:00:00\",\"标记\":false}','pending')" "'Update','{\"ID\":1,\"名字\":\"A2\",\"数量\":5,\"时间\":\"2026-01-02T00:00:00\",\"标记\":false}','pending')"
@@ -45,7 +53,7 @@ def test_upsert_insert_update_delete_last_write_wins(sql_conn):
sql_conn.commit() sql_conn.commit()
# --- Act 1: apply upsert ---------------------------------------------- # --- Act 1: apply upsert ----------------------------------------------
cur.execute("EXEC dbo.usp_SyncApply @MaxRetries=5") cur.execute("EXEC " + proc + " @MaxRetries=5")
sql_conn.commit() sql_conn.commit()
# --- Assert 1: the later Update wins; BIT false -> 0 ------------------ # --- Assert 1: the later Update wins; BIT false -> 0 ------------------
@@ -57,15 +65,15 @@ def test_upsert_insert_update_delete_last_write_wins(sql_conn):
assert row.标记 == 0 # BIT false assert row.标记 == 0 # BIT false
# --- Act 2: a later Delete wins --------------------------------------- # --- Act 2: a later Delete wins ---------------------------------------
cur.execute("DELETE dbo.SyncQueue WHERE TargetSchema='sync_test'") cur.execute("DELETE " + qt + " WHERE TargetSchema='sync_test'")
cur.execute( cur.execute(
"INSERT dbo.SyncQueue(SourceFile,SourceTable,SourceLogID,TargetSchema," "INSERT " + qt + "(SourceFile,SourceTable,SourceLogID,TargetSchema,"
"TargetTable,RecordID,OperateType,RowData,Status) " "TargetTable,RecordID,OperateType,RowData,Status) "
"VALUES('t.accdb','ApplyDemo',3,'sync_test','ApplyDemo_YEAR2026','1'," "VALUES('t.accdb','ApplyDemo',3,'sync_test','ApplyDemo_YEAR2026','1',"
"'Delete',NULL,'pending')" "'Delete',NULL,'pending')"
) )
sql_conn.commit() sql_conn.commit()
cur.execute("EXEC dbo.usp_SyncApply @MaxRetries=5") cur.execute("EXEC " + proc + " @MaxRetries=5")
sql_conn.commit() sql_conn.commit()
# --- Assert 2: row removed -------------------------------------------- # --- Assert 2: row removed --------------------------------------------
@@ -77,5 +85,5 @@ def test_upsert_insert_update_delete_last_write_wins(sql_conn):
"IF OBJECT_ID('sync_test.ApplyDemo_YEAR2026') IS NOT NULL " "IF OBJECT_ID('sync_test.ApplyDemo_YEAR2026') IS NOT NULL "
"DROP TABLE sync_test.ApplyDemo_YEAR2026" "DROP TABLE sync_test.ApplyDemo_YEAR2026"
) )
cur.execute("DELETE dbo.SyncQueue WHERE TargetSchema='sync_test'") cur.execute("DELETE " + qt + " WHERE TargetSchema='sync_test'")
sql_conn.commit() sql_conn.commit()

View File

@@ -21,10 +21,16 @@ def test_insert_dedup_and_applied_ids():
if not os.environ.get("RUN_INTEGRATION"): if not os.environ.get("RUN_INTEGRATION"):
pytest.skip("integration") pytest.skip("integration")
cfg = load_config("config.yaml") cfg = load_config("config.yaml")
w = SqlWriter(cfg.sql_server.conn_str, "dbo.SyncQueue") qt = cfg.sql_server.sync_queue_table
w = SqlWriter(
cfg.sql_server.conn_str,
qt,
cfg.sql_server.archive_table,
cfg.sql_server.apply_proc,
)
try: try:
cur = w._conn.cursor() cur = w._conn.cursor()
cur.execute("DELETE dbo.SyncQueue WHERE SourceFile='sqlw_test.accdb'") cur.execute(f"DELETE {qt} WHERE SourceFile='sqlw_test.accdb'")
qr = QueueRow( qr = QueueRow(
source_file="sqlw_test.accdb", source_file="sqlw_test.accdb",
source_table="T", source_table="T",
@@ -38,7 +44,7 @@ def test_insert_dedup_and_applied_ids():
w.insert_queue_row(qr) w.insert_queue_row(qr)
w.insert_queue_row(qr) # duplicate must be deduped (ignored) w.insert_queue_row(qr) # duplicate must be deduped (ignored)
cur.execute( cur.execute(
"SELECT COUNT(*) FROM dbo.SyncQueue " f"SELECT COUNT(*) FROM {qt} "
"WHERE SourceFile='sqlw_test.accdb' AND SourceLogID=100" "WHERE SourceFile='sqlw_test.accdb' AND SourceLogID=100"
) )
assert cur.fetchone()[0] == 1 assert cur.fetchone()[0] == 1
@@ -47,12 +53,12 @@ def test_insert_dedup_and_applied_ids():
w.call_apply(max_retries=5) w.call_apply(max_retries=5)
cur.execute( cur.execute(
"UPDATE dbo.SyncQueue SET Status='applied' " f"UPDATE {qt} SET Status='applied' "
"WHERE SourceFile='sqlw_test.accdb'" "WHERE SourceFile='sqlw_test.accdb'"
) )
assert w.applied_log_ids("sqlw_test.accdb") == [100] assert w.applied_log_ids("sqlw_test.accdb") == [100]
finally: finally:
cur.execute("DELETE dbo.SyncQueue WHERE SourceFile='sqlw_test.accdb'") cur.execute(f"DELETE {qt} WHERE SourceFile='sqlw_test.accdb'")
w.close() w.close()