✨ feat(sync): add data consistency compare (count + ID-set)

tests/test_access_reader.py

@@ -6,6 +6,7 @@ No real log rows are deleted.
 """
 import os
 import pytest
+from unittest.mock import MagicMock
 
 from sync.access_reader import AccessReader
 from sync.config import load_config
@@ -35,3 +36,23 @@ def test_read_log_and_row_and_delete():
         r.delete_log_ids([], 100, 3)  # empty list -> no-op, must not raise
     finally:
         r.close()
+
+
+def test_count_rows_executes_count_sql_and_returns_value():
+    r = AccessReader("dummy.accdb", "{Microsoft Access Driver (*.accdb, *.mdb)}")
+    cur = MagicMock()
+    cur.fetchone.return_value = (42,)
+    r._conn = MagicMock()  # bypass lazy connect
+    r._conn.cursor.return_value = cur
+    assert r.count_rows("表壳焊接记录") == 42
+    cur.execute.assert_called_once_with('SELECT COUNT(*) FROM "表壳焊接记录"')
+
+
+def test_read_ids_returns_ordered_id_list():
+    r = AccessReader("dummy.accdb", "{Microsoft Access Driver (*.accdb, *.mdb)}")
+    cur = MagicMock()
+    cur.fetchall.return_value = [(1,), (3,), (5,)]
+    r._conn = MagicMock()
+    r._conn.cursor.return_value = cur
+    assert r.read_ids("T") == [1, 3, 5]
+    cur.execute.assert_called_once_with('SELECT ID FROM "T" ORDER BY ID')

tests/test_compare.py

@@ -0,0 +1,105 @@
+from unittest.mock import MagicMock
+
+from sync.config import FileMapping
+from sync.compare import compare_file, any_mismatch, format_report, TableResult
+
+
+def _fm(**kw):
+    base = dict(file="x.accdb", root="2026", schema="s", year_suffix="_YEAR2026")
+    base.update(kw)
+    return FileMapping(**base)
+
+
+def _reader_with_tables(tables):
+    r = MagicMock()
+    r.list_user_tables.return_value = tables
+    return r
+
+
+def test_count_match():
+    fm = _fm(exclude_tables=["TableChangeLog"])
+    reader = _reader_with_tables(["T1", "TableChangeLog"])
+    reader.count_rows.return_value = 5
+    writer = MagicMock()
+    writer.table_exists.return_value = True
+    writer.count_target.return_value = 5
+    res = compare_file(fm, reader, writer, "count")
+    assert len(res) == 1
+    assert res[0].access_table == "T1"
+    assert res[0].status == "match"
+    assert res[0].access_count == 5 and res[0].sql_count == 5
+
+
+def test_count_mismatch():
+    fm = _fm()
+    reader = _reader_with_tables(["T1"])
+    reader.count_rows.return_value = 5
+    writer = MagicMock()
+    writer.table_exists.return_value = True
+    writer.count_target.return_value = 7
+    res = compare_file(fm, reader, writer, "count")
+    assert res[0].status == "mismatch"
+
+
+def test_skip_when_mirror_missing():
+    fm = _fm()
+    reader = _reader_with_tables(["T1"])
+    writer = MagicMock()
+    writer.table_exists.return_value = False
+    res = compare_file(fm, reader, writer, "count")
+    assert res[0].status == "skipped"
+    writer.count_target.assert_not_called()
+    writer.read_target_ids.assert_not_called()
+
+
+def test_ids_match():
+    fm = _fm()
+    reader = _reader_with_tables(["T1"])
+    reader.read_ids.return_value = [1, 2, 3]
+    writer = MagicMock()
+    writer.table_exists.return_value = True
+    writer.read_target_ids.return_value = [1, 2, 3]
+    res = compare_file(fm, reader, writer, "ids")
+    assert res[0].status == "match"
+    assert res[0].missing_in_sql == []
+    assert res[0].extra_in_sql == []
+
+
+def test_ids_reports_missing_and_extra():
+    fm = _fm()
+    reader = _reader_with_tables(["T1"])
+    reader.read_ids.return_value = [1, 2, 3]
+    writer = MagicMock()
+    writer.table_exists.return_value = True
+    writer.read_target_ids.return_value = [2, 3, 4]
+    res = compare_file(fm, reader, writer, "ids")
+    assert res[0].status == "mismatch"
+    assert res[0].missing_in_sql == [1]   # in Access, not in SQL
+    assert res[0].extra_in_sql == [4]     # in SQL, not in Access
+
+
+def test_excluded_tables_not_compared():
+    fm = _fm(exclude_tables=["TableChangeLog"])
+    reader = _reader_with_tables(["T1", "TableChangeLog"])
+    reader.count_rows.return_value = 1
+    writer = MagicMock()
+    writer.table_exists.return_value = True
+    writer.count_target.return_value = 1
+    res = compare_file(fm, reader, writer, "count")
+    assert [r.access_table for r in res] == ["T1"]
+
+
+def test_any_mismatch_detects_mismatch_only():
+    r_match = TableResult("f", "T", "s", "T_YEAR2026", "match", 1, 1)
+    r_skip = TableResult("f", "T2", "s", "T2_YEAR2026", "skipped")
+    r_mis = TableResult("f", "T3", "s", "T3_YEAR2026", "mismatch", 1, 2)
+    assert any_mismatch([r_match, r_skip]) is False
+    assert any_mismatch([r_match, r_mis]) is True
+
+
+def test_format_report_count():
+    r = TableResult("x.accdb", "T1", "s", "T1_YEAR2026", "mismatch", 5, 7)
+    rep = format_report([r], "count")
+    assert "x.accdb: T1 -> s.T1_YEAR2026" in rep
+    assert "access=5 sql=7" in rep
+    assert "[MISMATCH]" in rep

tests/test_sql_writer.py

@@ -10,6 +10,7 @@ credentials are hardcoded here. The test self-cleans using a throwaway
 """
 import os
 import pytest
+from unittest.mock import MagicMock
 
 from sync.sql_writer import SqlWriter, QueueRow
 from sync.config import load_config
@@ -53,3 +54,30 @@ def test_insert_dedup_and_applied_ids():
     finally:
         cur.execute("DELETE dbo.SyncQueue WHERE SourceFile='sqlw_test.accdb'")
         w.close()
+
+
+def _writer_with_cursor(fetchone=None, fetchall=None):
+    """A SqlWriter whose pyodbc connection is a mock (no real connect)."""
+    w = SqlWriter.__new__(SqlWriter)
+    w.conn_str = "dummy"
+    w.queue_table = "dbo.SyncQueue"
+    cur = MagicMock()
+    if fetchone is not None:
+        cur.fetchone.return_value = fetchone
+    if fetchall is not None:
+        cur.fetchall.return_value = fetchall
+    w._conn = MagicMock()
+    w._conn.cursor.return_value = cur
+    return w, cur
+
+
+def test_count_target_executes_count_sql_and_returns_value():
+    w, cur = _writer_with_cursor(fetchone=(7,))
+    assert w.count_target("s", "T_YEAR2026") == 7
+    cur.execute.assert_called_once_with("SELECT COUNT(*) FROM [s].[T_YEAR2026]")
+
+
+def test_read_target_ids_returns_ordered_id_list():
+    w, cur = _writer_with_cursor(fetchall=[(2,), (4,), (6,)])
+    assert w.read_target_ids("s", "T_YEAR2026") == [2, 4, 6]
+    cur.execute.assert_called_once_with("SELECT ID FROM [s].[T_YEAR2026] ORDER BY ID")