mirror of
https://github.com/ThearchyHelios/AgentLab.git
synced 2026-11-15 01:11:59 +00:00
ThearchyHelios
120 lines
6.2 KiB
Python
120 lines
6.2 KiB
Python
"""按行号取多行查询里的一格，重跑、核对时行序不一定一样（next-round 验收遗留）：
|
|
|
|
- 认法（data/sql_semantics.row_stable）：最外层带 ORDER BY 的按位置认；一定只出一行的第 0 行认得住；别的（多行、又没有
|
|
ORDER BY）行序不定——库可以按任何顺序交回这些行；
|
|
- 口径账本的指标标签：答案的一格和口径卡的一格按「同一行」认来自口径，只在行认得住时成立；行序不定的照实标「相关」、
|
|
写明行序不定，不再标成来自口径；
|
|
- 口径召回：两版都按行号取一格、查询又行序不定的指标，照实记「行序不定」（changed 为空），不按位置硬比；
|
|
- 对账：多行结果按维度对齐之后，每一组对账指标先核对那一行的维度是不是它（重跑时缺了一行、多了一行，后面的行会错位），
|
|
对不上的记空值，不拿别的维度的数冒充。
|
|
数据是虚构店铺库。
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
from app.data.sql_semantics import ordered, row_stable
|
|
from app.engine.runner import run_manager
|
|
from app.ledger import match as ledger_match
|
|
from app.ledger import recall as ledger_recall
|
|
from app.ledger import reconcile as ledger_reconcile
|
|
from tests import ledger_samples as S
|
|
|
|
UNORDERED = ("SELECT region AS 区域, SUM(amount) AS gmv FROM orders WHERE status = 'paid' "
|
|
"AND paid_at >= '{{ input.start }}' AND paid_at < '{{ input.end }}' GROUP BY region")
|
|
UNORDERED_ALL = ("SELECT region AS 区域, SUM(amount) AS gmv FROM orders WHERE status = 'paid' "
|
|
"AND paid_at >= '2026-09-01' AND paid_at < '2026-09-08' GROUP BY region")
|
|
|
|
|
|
def test_which_rows_survive_a_rerun():
|
|
assert ordered("SELECT a, b FROM t ORDER BY a") and not ordered("SELECT a, b FROM t")
|
|
assert row_stable("SELECT a, SUM(b) FROM t GROUP BY a ORDER BY a", 3)
|
|
assert row_stable("SELECT SUM(b) FROM t", 0) and not row_stable("SELECT SUM(b) FROM t", 1)
|
|
assert not row_stable("SELECT a, SUM(b) FROM t GROUP BY a", 0)
|
|
assert not row_stable("这不是 SQL", 0)
|
|
|
|
|
|
@pytest.fixture
|
|
async def shop(tmp_path):
|
|
await run_manager.setup()
|
|
await S.fresh_source(tmp_path / "shop.db")
|
|
yield
|
|
await ledger_match.drain()
|
|
await run_manager.shutdown()
|
|
|
|
|
|
async def _label(monkeypatch, caliber_sql: str, answer_sql: str, row: int) -> dict:
|
|
from tests.test_ledger_match import matched, only_label
|
|
|
|
await S.publish(graph=S.caliber_graph(caliber_sql, expression=f"cell(nodes.fetch, {row}, 'gmv')"))
|
|
run = await S.explore(monkeypatch, answer_sql, text="这一区销售额 [[m:gmv]]。",
|
|
card_expression=f"cell(nodes.q, {row}, 'gmv')")
|
|
recorded, _ = await matched(run.id)
|
|
return only_label(recorded.content)
|
|
|
|
|
|
async def test_an_unordered_multi_row_cell_is_not_claimed_to_come_from_the_caliber(shop, monkeypatch):
|
|
label = await _label(monkeypatch, UNORDERED, UNORDERED_ALL, 1)
|
|
assert label["kind"] == "related" and label["reason"] == ledger_match.ROW_ORDER_UNSTABLE, label
|
|
|
|
|
|
async def test_with_order_by_the_same_row_still_comes_from_the_caliber(shop, monkeypatch):
|
|
label = await _label(monkeypatch, UNORDERED + " ORDER BY region", UNORDERED_ALL + " ORDER BY region", 1)
|
|
assert label["kind"] == "caliber", label
|
|
|
|
|
|
def _pinned(sql: str, expression: str, version: int):
|
|
from app.ledger.derive import Pinned
|
|
|
|
graph = S.caliber_graph(sql, expression=expression)
|
|
card = next(n for n in graph["nodes"] if n["id"] == "card")
|
|
fetch = next(n for n in graph["nodes"] if n["id"] == "fetch")
|
|
return Pinned(workflow_id="wf", workflow_name="周销售", version=version, node_id="card", level="governed",
|
|
published=True, retired=False, card=card, fetches=(fetch,), reads=(("fetch", S.tool(), ("gmv",)),),
|
|
entry_fields=(), defaults={})
|
|
|
|
|
|
def test_recall_marks_unordered_row_comparisons_instead_of_comparing_by_position():
|
|
pair = ledger_recall.Pair(old=_pinned(UNORDERED, "cell(nodes.fetch, 1, 'gmv')", 1),
|
|
new=_pinned(UNORDERED + " AND 1 = 1", "cell(nodes.fetch, 1, 'gmv')", 2))
|
|
_, meta = ledger_recall.recall_card([pair])
|
|
assert meta[0]["row_order"] == "unstable"
|
|
values = {"old_0": {"value": 1.0, "rendered": "1"}, "new_0": {"value": 2.0, "rendered": "2"},
|
|
"diff_0": {"value": 1.0, "rendered": "1"}}
|
|
[item] = ledger_recall.compare(meta, values)
|
|
assert item["changed"] is None and item["row_order"] == "unstable"
|
|
# 带 ORDER BY 的照常比
|
|
pair = ledger_recall.Pair(old=_pinned(UNORDERED + " ORDER BY region", "cell(nodes.fetch, 1, 'gmv')", 1),
|
|
new=_pinned(UNORDERED + " ORDER BY region", "cell(nodes.fetch, 1, 'gmv')", 2))
|
|
_, meta = ledger_recall.recall_card([pair])
|
|
assert "row_order" not in meta[0]
|
|
[item] = ledger_recall.compare(meta, values)
|
|
assert item["changed"] is True
|
|
|
|
|
|
def test_reconcile_checks_each_aligned_row_is_the_one_it_stands_for():
|
|
plan = ledger_reconcile.Plan(pairs=[ledger_reconcile.Pair(ours="gmv", column="gmv")], rows=[0, 1],
|
|
keys=[("区域", "区域")], key_values=[("east",), ("west",)])
|
|
nodes = ledger_reconcile.tail_nodes(plan, card_id="card", fetch_id="fetch")
|
|
card = next(n for n in nodes if n["id"] == "reconcile")
|
|
metrics = {m["id"]: m["expression"] for m in card["data"]["config"]["metrics"]}
|
|
from app.engine.expressions import eval_expression
|
|
|
|
def run(rows):
|
|
table = {"columns": ["区域", "ours_0", "cal_0"], "rows": rows}
|
|
return {mid: _eval(eval_expression, expr, table) for mid, expr in metrics.items() if mid.startswith("ours_")}
|
|
|
|
# 重跑时东区那一行没了：西区挪到了第 0 行。以前东区那一组拿的是西区的数
|
|
got = run([["west", 58.0, 20.0]])
|
|
assert got["ours_0_0"] is None, "东区对不上：记空值，不拿西区的数冒充"
|
|
assert run([["east", 163.0, 150.5], ["west", 58.0, 20.0]]) == {"ours_0_0": 163.0, "ours_1_0": 58.0}
|
|
|
|
|
|
def _eval(fn, expression, table):
|
|
from app.engine.expressions import CellError, ExpressionError
|
|
|
|
try:
|
|
return fn(expression, {"nodes": {"align": table}})
|
|
except (CellError, ExpressionError, IndexError, KeyError, TypeError):
|
|
return None
|