mirror of
https://github.com/ThearchyHelios/AgentLab.git
synced 2026-11-17 06:52:00 +00:00
SQL 语义复核修正(第 2 轮):CTE、子查询起的名字不再进比较,条件里的子查询选出来的列名也不算;派生来源按位置编号,编号错开时再按不写编号的写法配一遍
上一轮只去掉了条件里子查询的表别名,子查询整段写进外层条件的 key 时还带着各自起的名字:标量子查询、IN 子查询给选出来的列起的名字(AVG(amount) AS avg_amount),子查询里 FROM 的子查询别名(s 换成 agg),以及外层引用 CTE、FROM 里的子查询算出来的列时的来源名(派生来源的 key 就是别名)。CTE 改个名,外层的 total > 100 就被报成两边各有一个、互相矛盾的条件;双盲复算里盲算的名字本来就是自己起的,会被说成换了口径。 现在派生来源(引用 CTE 的表、FROM / JOIN 里的子查询和 LATERAL 子查询)按位置编号作比较用的 key:从外往里一层一层地编,CTE 在第一次用到的地方编号,写成 CTE 还是 FROM 里的子查询、CTE 定义的先后都不影响;给人看的写法照写名字。不拿里面那段查询的写法作 key:里面差一个条件,外层按它的列写的条件就全跟着变,同一处不同会报好几遍。条件里的子查询写进外层 key 时,引用 CTE 的表、子查询(含 LATERAL)、子查询自带的 CTE 定义都换成编号,只看取值的子查询(IN、EXISTS、标量子查询)去掉选出来的列名;FROM 里的子查询、CTE 定义选出来的列名留着,外层按名字引用它们。LATERAL 的别名原来没登记成来源,按「别名写错了」照写,一并改成派生来源。 编号只看位置:一边多出一个排在前面的 CTE(比如盲算先关联一个筛 VIP 的 CTE),后面的编号就错开了,同名的 CTE 反倒比原来按名字比时多报出两条自相矛盾的话。Part 加 anon(派生来源一律写「@」、不写编号),diff_facets 每个方面先按编号比,比不上的再按 anon 一对一地配,配上的不算不同;比较两边的先后先按 anon 排、分不出再按编号;连接先配完全一样的再按关联的表配,免得错开的两个 CTE 被配成一对、说成关联条件不同。编号对得上时照样分得清是哪个 CTE 的同名列(p.total > r.total 写反成 r.total > p.total 照报)。筛选条件配对改按列的比较写法(Part.column_keys,CTE、子查询的列写「@.列」),CTE 名不同、阈值不同时说成「按 total > 100 筛选,盲算按 total > 200 筛选」,不再拆成两条各说各的。 仍按名字比的只有 CTE、子查询选出来、外层按名字引用的列(一边叫 total、一边叫 sum_amt),写进了模块说明。
This commit is contained in:
@@ -4,11 +4,13 @@
|
||||
不同,不能算模板变了);关键字大小写、空白、注释也不算不同;解析不了的退回逐词规范化,照样认得出只改了字面量
|
||||
- facets:表、连接(类型 / 关联进来的表 / ON 条件)、WHERE 合取式、时间条件(列 / 运算符 / 取值)、分组、聚合
|
||||
(函数 / 参数 / 去重)、HAVING、取哪几行(各段的 LIMIT / OFFSET / 排序)。别名换成真实表名(条件里套着的子查询、
|
||||
HAVING 里的别名也是)、比较的两边排好顺序;解析不了带 parse_error,不抛
|
||||
HAVING 里的别名也是),CTE、子查询按位置编号、不按起的名字比,条件里的子查询选出来的列名不算;比较的两边排好
|
||||
顺序;解析不了带 parse_error,不抛
|
||||
- diff_facets:每处不同一句中文:「A 按支付时间 paid_at 筛时间,B 按下单时间 created_at」「A 排除了
|
||||
is_deleted = 1 的行,B 没有」「A 对 order_id 去重计数,B 没去重」……写法不同、口径相同的不报
|
||||
is_deleted = 1 的行,B 没有」「A 对 order_id 去重计数,B 没去重」……写法不同、口径相同的不报,一边多出一个排在
|
||||
前面的 CTE、编号错开了也不报
|
||||
|
||||
夹具全是虚构的表:订单 orders、退款 refunds、门店 stores,以及一张中文表「订单」。
|
||||
夹具全是虚构的表:订单 orders、退款 refunds、门店 stores、用户 users、付款 payments,以及一张中文表「订单」。
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -435,6 +437,229 @@ def test_a_real_difference_inside_a_subquery_is_still_reported():
|
||||
"B 按 user_id IN (SELECT referrer_id FROM users WHERE vip = 1) 筛选"]
|
||||
|
||||
|
||||
@pytest.mark.parametrize("dialect,a,b", [
|
||||
# 条件里的子查询给选出来的列起了名字:IN、标量子查询只看取值,列名不影响口径
|
||||
("sqlite",
|
||||
"SELECT SUM(o.amount) FROM orders o WHERE o.amount > "
|
||||
"(SELECT AVG(o2.amount) AS avg_amount FROM orders o2 WHERE o2.is_deleted = 0)",
|
||||
"SELECT SUM(amount) FROM orders WHERE amount > (SELECT AVG(amount) FROM orders WHERE is_deleted = 0)"),
|
||||
("sqlite",
|
||||
"SELECT SUM(o.amount) FROM orders o WHERE o.user_id IN (SELECT u.id AS uid FROM users u WHERE u.vip = 1)",
|
||||
"SELECT SUM(amount) FROM orders WHERE user_id IN (SELECT id FROM users WHERE vip = 1)"),
|
||||
# 条件里的子查询从 FROM 里的子查询取数,两边给它起的别名不同
|
||||
("sqlite",
|
||||
"SELECT SUM(o.amount) FROM orders o WHERE o.user_id IN (SELECT s.user_id FROM "
|
||||
"(SELECT user_id, SUM(amount) AS total FROM payments GROUP BY user_id) s WHERE s.total > 100)",
|
||||
"SELECT SUM(o.amount) FROM orders o WHERE o.user_id IN (SELECT agg.user_id FROM "
|
||||
"(SELECT user_id, SUM(amount) AS total FROM payments GROUP BY user_id) agg WHERE agg.total > 100)"),
|
||||
# CTE 起的名字不同,外层按 CTE 算出来的列筛选
|
||||
("sqlite",
|
||||
"WITH user_totals AS (SELECT user_id, SUM(amount) AS total FROM orders WHERE is_deleted = 0 GROUP BY user_id) "
|
||||
"SELECT COUNT(*) FROM user_totals WHERE total > 100",
|
||||
"WITH t AS (SELECT user_id, SUM(amount) AS total FROM orders WHERE is_deleted = 0 GROUP BY user_id) "
|
||||
"SELECT COUNT(*) FROM t WHERE t.total > 100"),
|
||||
# 写成 CTE 还是写成 FROM 里的子查询
|
||||
("postgres",
|
||||
"WITH user_totals AS (SELECT user_id, SUM(amount) AS total FROM orders GROUP BY user_id) "
|
||||
"SELECT COUNT(*) FROM user_totals WHERE total > 100",
|
||||
"SELECT COUNT(*) FROM (SELECT user_id, SUM(amount) AS total FROM orders GROUP BY user_id) AS agg "
|
||||
"WHERE agg.total > 100"),
|
||||
# LATERAL 子查询的别名不同:别名挂在 LATERAL 上,不在子查询上
|
||||
("postgres",
|
||||
"SELECT SUM(o.amount) FROM orders o, LATERAL (SELECT COUNT(*) AS n FROM refunds r WHERE r.order_id = o.id) l "
|
||||
"WHERE l.n > 0",
|
||||
"SELECT SUM(o.amount) FROM orders o CROSS JOIN LATERAL (SELECT COUNT(*) AS n FROM refunds r "
|
||||
"WHERE r.order_id = o.id) AS x WHERE x.n > 0"),
|
||||
# 关联进来的是子查询,两边的别名不同(一边是带反引号的中文别名)
|
||||
("mysql",
|
||||
"SELECT SUM(o.amount) FROM orders o JOIN (SELECT order_id, COUNT(*) AS n FROM refunds GROUP BY order_id) r "
|
||||
"ON r.order_id = o.id WHERE r.n > 1",
|
||||
"SELECT SUM(o.amount) FROM orders o JOIN (SELECT order_id, COUNT(*) AS n FROM refunds GROUP BY order_id) "
|
||||
"`退款` ON o.id = `退款`.order_id WHERE `退款`.n > 1"),
|
||||
# 条件里的子查询用到 CTE,两边给 CTE 起的名字不同
|
||||
("sqlite",
|
||||
"WITH vip AS (SELECT id FROM users WHERE grade >= 3) "
|
||||
"SELECT SUM(amount) FROM orders WHERE user_id IN (SELECT id FROM vip)",
|
||||
"WITH good_users AS (SELECT id FROM users WHERE grade >= 3) "
|
||||
"SELECT SUM(amount) FROM orders WHERE user_id IN (SELECT g.id FROM good_users g)"),
|
||||
# CTE 定义在条件里的子查询里:定义连同子查询整个写进外层的条件,定义上的名字也不算
|
||||
("postgres",
|
||||
"SELECT SUM(amount) FROM orders WHERE user_id IN "
|
||||
"(WITH t AS (SELECT id FROM users WHERE grade >= 3) SELECT id FROM t)",
|
||||
"SELECT SUM(amount) FROM orders WHERE user_id IN "
|
||||
"(WITH g AS (SELECT id FROM users WHERE grade >= 3) SELECT g.id FROM g)"),
|
||||
# 两个 CTE 定义的先后、起的名字都不同,按用到的先后它们是同一对
|
||||
("sqlite",
|
||||
"WITH paid AS (SELECT user_id, SUM(amount) AS total FROM orders WHERE status = 'paid' GROUP BY user_id), "
|
||||
"refunded AS (SELECT user_id, SUM(amount) AS total FROM refunds GROUP BY user_id) "
|
||||
"SELECT COUNT(*) FROM paid p JOIN refunded r ON r.user_id = p.user_id WHERE p.total > r.total",
|
||||
"WITH r AS (SELECT user_id, SUM(amount) AS total FROM refunds GROUP BY user_id), "
|
||||
"p AS (SELECT user_id, SUM(amount) AS total FROM orders WHERE status = 'paid' GROUP BY user_id) "
|
||||
"SELECT COUNT(*) FROM p JOIN r ON p.user_id = r.user_id WHERE p.total > r.total"),
|
||||
# CTE 定义的先后和用到的先后不一致,另一边又把它们写成了 FROM 里的子查询:按用到的先后编号才对得上
|
||||
("sqlite",
|
||||
"WITH c AS (SELECT user_id, SUM(amount) AS total FROM orders GROUP BY user_id), "
|
||||
"d AS (SELECT user_id, COUNT(*) AS n FROM refunds GROUP BY user_id), "
|
||||
"a AS (SELECT * FROM c WHERE total > 100), b AS (SELECT * FROM d WHERE n > 1) "
|
||||
"SELECT COUNT(*) FROM b JOIN a ON a.user_id = b.user_id",
|
||||
"SELECT COUNT(*) FROM (SELECT * FROM (SELECT user_id, COUNT(*) AS n FROM refunds GROUP BY user_id) x "
|
||||
"WHERE n > 1) b JOIN (SELECT * FROM (SELECT user_id, SUM(amount) AS total FROM orders GROUP BY user_id) y "
|
||||
"WHERE total > 100) a ON a.user_id = b.user_id"),
|
||||
# 同上,两个 CTE 还算出了同名的列、外层拿它们互相比:不写编号的写法分不出是哪个的 total,编号得对得上
|
||||
("sqlite",
|
||||
"WITH c AS (SELECT user_id, SUM(amount) AS total FROM orders GROUP BY user_id), "
|
||||
"d AS (SELECT user_id, SUM(amount) AS total FROM refunds GROUP BY user_id), "
|
||||
"a AS (SELECT * FROM c), b AS (SELECT * FROM d) "
|
||||
"SELECT COUNT(*) FROM b JOIN a ON a.user_id = b.user_id WHERE a.total > b.total",
|
||||
"SELECT COUNT(*) FROM (SELECT * FROM (SELECT user_id, SUM(amount) AS total FROM refunds GROUP BY user_id) x) b "
|
||||
"JOIN (SELECT * FROM (SELECT user_id, SUM(amount) AS total FROM orders GROUP BY user_id) y) a "
|
||||
"ON a.user_id = b.user_id WHERE a.total > b.total"),
|
||||
# 先用一个 CTE 筛一遍再汇总,还是直接在汇总的 CTE 里筛:里层多一段,不挪动外层那一段的编号
|
||||
("sqlite",
|
||||
"WITH base AS (SELECT * FROM orders WHERE is_deleted = 0), "
|
||||
"per_user AS (SELECT user_id, SUM(amount) AS total FROM base GROUP BY user_id) "
|
||||
"SELECT COUNT(*) FROM per_user WHERE total > 100",
|
||||
"WITH totals AS (SELECT user_id, SUM(amount) AS total FROM orders WHERE is_deleted = 0 GROUP BY user_id) "
|
||||
"SELECT COUNT(*) FROM totals WHERE total > 100"),
|
||||
])
|
||||
def test_names_given_to_derived_tables_are_no_difference(dialect, a, b):
|
||||
"""CTE 名、子查询的别名、条件里的子查询选出来的列名都是各自起的(双盲复算的盲算更是):只因起的名字不同,
|
||||
不算换了口径。"""
|
||||
assert texts(a, b, dialect) == []
|
||||
|
||||
|
||||
def test_derived_tables_are_compared_by_position_and_shown_by_name():
|
||||
"""派生来源(CTE、FROM 里的子查询)比较用的写法按它在语句里的位置编号,不写名字;给人看的写法照原样写名字。"""
|
||||
a = facets("WITH user_totals AS (SELECT user_id, SUM(amount) AS total FROM orders GROUP BY user_id) "
|
||||
"SELECT COUNT(*) FROM user_totals WHERE total > 100")
|
||||
b = facets("SELECT COUNT(*) FROM (SELECT user_id, SUM(amount) AS total FROM orders GROUP BY user_id) agg "
|
||||
"WHERE agg.total > 100")
|
||||
assert a.where[0].key == b.where[0].key
|
||||
assert "user_totals" not in a.where[0].key and "agg" not in b.where[0].key
|
||||
assert (a.where[0].text, a.where[0].full) == ("total > 100", "user_totals.total > 100")
|
||||
assert (b.where[0].text, b.where[0].full) == ("total > 100", "agg.total > 100")
|
||||
joined = facets("SELECT SUM(o.amount) FROM orders o JOIN (SELECT order_id, COUNT(*) AS n FROM refunds "
|
||||
"GROUP BY order_id) r ON r.order_id = o.id")
|
||||
[join] = joined.joins
|
||||
assert join.table.text == "r" and join.on.text == "orders.id = refunds.order_id"
|
||||
|
||||
|
||||
SHIFTED_A = ("WITH t AS (SELECT user_id, SUM(amount) AS total FROM orders GROUP BY user_id) "
|
||||
"SELECT COUNT(*) FROM t WHERE total > 100 AND user_id IN (SELECT id FROM users WHERE vip = 1)")
|
||||
SHIFTED_B = ("WITH vip AS (SELECT id FROM users WHERE vip = 1), "
|
||||
"t AS (SELECT user_id, SUM(amount) AS total FROM orders GROUP BY user_id) "
|
||||
"SELECT COUNT(*) FROM vip JOIN t ON t.user_id = vip.id WHERE t.total > 100")
|
||||
|
||||
|
||||
def test_a_shifted_derived_number_does_not_split_one_condition_in_two():
|
||||
"""编号只看位置:一边多出一个排在前面的 CTE(筛 VIP 用户),后面那个 CTE 的编号就错开了。按编号比不上的再按
|
||||
不写编号的写法一对一地配,同一个条件不会被说成两边各有一个;真正的不同(VIP 用 IN 筛还是关联进来)照报。"""
|
||||
found = diff_facets(facets(SHIFTED_A), facets(SHIFTED_B), labels=("原流程", "盲算"))
|
||||
filters = [d.text for d in found if d.aspect == "filter"]
|
||||
assert filters == ["原流程只保留 user_id IN (SELECT id FROM users WHERE vip = 1) 的行,盲算没有这个条件"]
|
||||
# 错开之后的条件真不同,也照样配成一对说
|
||||
other = SHIFTED_B.replace("t.total > 100", "t.total > 200")
|
||||
filters = [d.text for d in diff_facets(facets(SHIFTED_A), facets(other), labels=("原流程", "盲算"))
|
||||
if d.aspect == "filter"]
|
||||
assert filters[0] == "原流程按 total > 100 筛选,盲算按 total > 200 筛选" and len(filters) == 2
|
||||
|
||||
|
||||
@pytest.mark.parametrize("aspect,a,b", [
|
||||
# 时间条件、分组键、聚合、HAVING、取前几行时的排序都是按 CTE 算出来的列
|
||||
("time",
|
||||
"WITH t AS (SELECT user_id, DATE(paid_at) AS day, amount FROM orders) "
|
||||
"SELECT SUM(amount) FROM t WHERE day >= '2026-09-01' AND user_id IN (SELECT id FROM users WHERE vip = 1)",
|
||||
"WITH vip AS (SELECT id FROM users WHERE vip = 1), "
|
||||
"t AS (SELECT user_id, DATE(paid_at) AS day, amount FROM orders) "
|
||||
"SELECT SUM(t.amount) FROM vip JOIN t ON t.user_id = vip.id WHERE t.day >= '2026-09-01'"),
|
||||
("group_by",
|
||||
"WITH t AS (SELECT user_id, SUM(amount) AS total, COUNT(*) AS n FROM orders GROUP BY user_id) "
|
||||
"SELECT n, COUNT(*) FROM t WHERE user_id IN (SELECT id FROM users WHERE vip = 1) GROUP BY n",
|
||||
"WITH vip AS (SELECT id FROM users WHERE vip = 1), "
|
||||
"t AS (SELECT user_id, SUM(amount) AS total, COUNT(*) AS n FROM orders GROUP BY user_id) "
|
||||
"SELECT t.n, COUNT(*) FROM vip JOIN t ON t.user_id = vip.id GROUP BY t.n"),
|
||||
("aggregate",
|
||||
"WITH t AS (SELECT user_id, SUM(amount) AS total FROM orders GROUP BY user_id) "
|
||||
"SELECT AVG(total) FROM t WHERE user_id IN (SELECT id FROM users WHERE vip = 1)",
|
||||
"WITH vip AS (SELECT id FROM users WHERE vip = 1), "
|
||||
"t AS (SELECT user_id, SUM(amount) AS total FROM orders GROUP BY user_id) "
|
||||
"SELECT AVG(t.total) FROM vip JOIN t ON t.user_id = vip.id"),
|
||||
("having",
|
||||
"WITH t AS (SELECT store_id, user_id, SUM(amount) AS total FROM orders GROUP BY store_id, user_id) "
|
||||
"SELECT store_id FROM t WHERE user_id IN (SELECT id FROM users WHERE vip = 1) GROUP BY store_id "
|
||||
"HAVING MAX(total) > 100",
|
||||
"WITH vip AS (SELECT id FROM users WHERE vip = 1), "
|
||||
"t AS (SELECT store_id, user_id, SUM(amount) AS total FROM orders GROUP BY store_id, user_id) "
|
||||
"SELECT t.store_id FROM vip JOIN t ON t.user_id = vip.id GROUP BY t.store_id HAVING MAX(t.total) > 100"),
|
||||
("limit",
|
||||
"WITH t AS (SELECT user_id, SUM(amount) AS total FROM orders GROUP BY user_id) "
|
||||
"SELECT user_id FROM t WHERE user_id IN (SELECT id FROM users WHERE vip = 1) ORDER BY total DESC LIMIT 10",
|
||||
"WITH vip AS (SELECT id FROM users WHERE vip = 1), "
|
||||
"t AS (SELECT user_id, SUM(amount) AS total FROM orders GROUP BY user_id) "
|
||||
"SELECT t.user_id FROM vip JOIN t ON t.user_id = vip.id ORDER BY t.total DESC LIMIT 10"),
|
||||
])
|
||||
def test_a_shifted_derived_number_is_no_difference_in_any_aspect(aspect, a, b):
|
||||
"""编号错开之后,按 CTE 算出来的列写的时间条件、分组键、聚合、HAVING、排序也不算不同:只剩 VIP 那处真正的
|
||||
不同。"""
|
||||
assert not [x for x in aspects(a, b) if x.startswith(aspect)]
|
||||
|
||||
|
||||
def test_a_shifted_number_inside_a_condition_subquery_is_no_difference():
|
||||
"""条件里的子查询用到的 CTE 编号错开了:子查询整个写进外层条件的那一份,按不写编号的写法也写「@」,照样配得上。"""
|
||||
a = ("WITH t AS (SELECT user_id, SUM(amount) AS total FROM orders GROUP BY user_id) "
|
||||
"SELECT COUNT(*) FROM users u WHERE u.vip = 1 AND u.id IN (SELECT user_id FROM t WHERE total > 100)")
|
||||
b = ("WITH vip AS (SELECT id FROM users WHERE vip = 1), "
|
||||
"t AS (SELECT user_id, SUM(amount) AS total FROM orders GROUP BY user_id) "
|
||||
"SELECT COUNT(*) FROM vip WHERE vip.id IN (SELECT user_id FROM t WHERE total > 100)")
|
||||
assert texts(a, b) == []
|
||||
|
||||
|
||||
def test_a_shifted_derived_join_is_paired_with_its_counterpart():
|
||||
"""关联进来的 CTE 编号错开了(盲算多关联了一个排在前面的 CTE):先把完全一样的关联配掉,再按关联的是哪张表配,
|
||||
不会把原流程的 t 和盲算的 vip 当成同一处关联、说成「关联条件不同」。"""
|
||||
a = ("WITH t AS (SELECT user_id, SUM(amount) AS total FROM orders GROUP BY user_id) "
|
||||
"SELECT COUNT(*) FROM users u JOIN t ON t.user_id = u.id WHERE t.total > 100")
|
||||
b = ("WITH vip AS (SELECT id FROM users WHERE vip = 1), "
|
||||
"t AS (SELECT user_id, SUM(amount) AS total FROM orders GROUP BY user_id) "
|
||||
"SELECT COUNT(*) FROM users u JOIN vip ON vip.id = u.id JOIN t ON t.user_id = u.id WHERE t.total > 100")
|
||||
assert texts(a, b, labels=("原流程", "盲算")) == ["盲算只保留 vip = 1 的行,原流程没有这个条件",
|
||||
"盲算关联了 vip 表,原流程没有"]
|
||||
|
||||
|
||||
def test_swapped_join_order_of_two_derived_tables_is_no_difference():
|
||||
"""两个 CTE 关联的先后对调,编号也跟着对调:拿它们的列互相比的条件,两边先按不写编号的写法排好两边的先后,
|
||||
才配得上(只按编号排,同一个比较会排成两个方向)。"""
|
||||
ctes = ("WITH t AS (SELECT user_id, SUM(amount) AS total FROM orders GROUP BY user_id), "
|
||||
"u AS (SELECT user_id, COUNT(*) AS cnt FROM refunds GROUP BY user_id) ")
|
||||
assert texts(ctes + "SELECT COUNT(*) FROM t JOIN u ON u.user_id = t.user_id WHERE t.total > u.cnt",
|
||||
ctes + "SELECT COUNT(*) FROM u JOIN t ON t.user_id = u.user_id WHERE t.total > u.cnt") == []
|
||||
|
||||
|
||||
def test_a_reversed_comparison_between_two_derived_tables_is_still_reported():
|
||||
"""两个 CTE 算出了同名的列:编号对得上时照样分得清是哪个 CTE 的,比较的方向反了要报出来(不写编号的写法只在
|
||||
按编号比不上时才拿来配,不会把它吞掉)。"""
|
||||
a = ("WITH paid AS (SELECT user_id, SUM(amount) AS total FROM orders GROUP BY user_id), "
|
||||
"refunded AS (SELECT user_id, SUM(amount) AS total FROM refunds GROUP BY user_id) "
|
||||
"SELECT COUNT(*) FROM paid p JOIN refunded r ON r.user_id = p.user_id WHERE p.total > r.total")
|
||||
b = a.replace("WHERE p.total > r.total", "WHERE r.total > p.total")
|
||||
assert texts(a, b) == ["A 只保留 paid.total > refunded.total 的行,B 没有这个条件",
|
||||
"B 只保留 paid.total < refunded.total 的行,A 没有这个条件"]
|
||||
|
||||
|
||||
def test_a_real_difference_next_to_renamed_derived_tables_is_reported_once():
|
||||
"""派生来源起的名字不同、里面又真有不同时,只报真正不同的那一处:CTE 里少一个条件,外层按 CTE 算出来的列
|
||||
筛选的条件不跟着报(不然两边各报一句「只保留 total > 100 的行」,自相矛盾);外层的条件本身不同,两边配成
|
||||
一对说。"""
|
||||
a = ("WITH user_totals AS (SELECT user_id, SUM(amount) AS total FROM orders WHERE is_deleted = 0 "
|
||||
"GROUP BY user_id) SELECT COUNT(*) FROM user_totals WHERE total > 100")
|
||||
inner = ("WITH t AS (SELECT user_id, SUM(amount) AS total FROM orders GROUP BY user_id) "
|
||||
"SELECT COUNT(*) FROM t WHERE total > 100")
|
||||
assert texts(a, inner, labels=("原流程", "盲算")) == ["原流程只保留 is_deleted = 0 的行,盲算没有这个条件"]
|
||||
outer = ("WITH t AS (SELECT user_id, SUM(amount) AS total FROM orders WHERE is_deleted = 0 GROUP BY user_id) "
|
||||
"SELECT COUNT(*) FROM t WHERE total > 200")
|
||||
assert texts(a, outer, labels=("原流程", "盲算")) == ["原流程按 total > 100 筛选,盲算按 total > 200 筛选"]
|
||||
|
||||
|
||||
@pytest.mark.parametrize("a,b,text", [
|
||||
("WITH top AS (SELECT amount FROM orders ORDER BY amount DESC LIMIT 10) SELECT SUM(amount) FROM top",
|
||||
"WITH top AS (SELECT amount FROM orders ORDER BY amount DESC LIMIT 100) SELECT SUM(amount) FROM top",
|
||||
|
||||
Reference in New Issue
Block a user