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

This commit is contained in:
Misaka_Company
2026-07-15 14:03:21 +08:00
parent 5ca0715801
commit e9f012eab5
6 changed files with 319 additions and 0 deletions

105
tests/test_compare.py Normal file
View File

@@ -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