feat: capture orchestration with include/exclude and delete-downgrade

Co-Authored-By: Claude <noreply@anthropic.com>

src/sync/capture.py

@@ -0,0 +1,42 @@
+from __future__ import annotations
+import json, logging
+from .access_reader import AccessReader
+from .sql_writer import SqlWriter, QueueRow
+from .config import FileMapping, SyncConfig
+
+log = logging.getLogger(__name__)
+
+def capture_file(fm: FileMapping, reader: AccessReader, writer: SqlWriter, cfg: SyncConfig) -> int:
+    exclude = set(fm.exclude_tables or [])
+    include = set(fm.include_tables) if fm.include_tables else None
+    rows = reader.read_log(cfg.runtime.capture_batch_size)
+    n = 0
+    for lr in rows:
+        if lr.table_name in exclude:
+            continue
+        if include is not None and lr.table_name not in include:
+            continue
+        op = lr.operate_type
+        row_data = None
+        if op in ("Insert", "Update"):
+            d = reader.read_row(lr.table_name, lr.record_id)
+            if d is None:
+                op = "Delete"  # 行已删，降级
+            else:
+                row_data = json.dumps(d, ensure_ascii=False)
+        elif op != "Delete":
+            log.warning("unknown OperateType %r in %s log %s", op, fm.file, lr.id)
+            continue
+        qr = QueueRow(
+            source_file=fm.file,
+            source_table=lr.table_name,
+            record_id=lr.record_id,
+            target_schema=fm.schema,
+            target_table=fm.target_table(lr.table_name),
+            source_log_id=lr.id,
+            operate_type=op,
+            row_data=row_data,
+        )
+        writer.insert_queue_row(qr)
+        n += 1
+    return n