mirror of
https://github.com/ThearchyHelios/AgentLab.git
synced 2026-11-18 12:21:59 +00:00
SQL 语义复核修正:同一个口径不再因为子查询里的别名、HAVING 里的别名被报成不同;取哪几行逐段比,连同 OFFSET 和取前几行时的排序
条件里套着的子查询(EXISTS、IN (SELECT …))原来按外层的来源整个照抄进外层那个条件,别名原样留着:带别名和不带别名的同一条 NOT EXISTS 被报成两处筛选不同,双盲复算就会说盲算换了口径。现在每段 SELECT 在语法树上记段号(复制出来的子查询靠它找回原树上那一段算好的来源,相关子查询照样到外层找),改写时每一列按它所在那一段认,子查询里的表去掉别名;比较两边排序时也按那一段的来源排。HAVING 引用 SELECT 别名(HAVING s > 100)换成别名指的表达式,和 GROUP BY 别名一个读法,聚合函数里的同名列不换。 取哪几行原来只看最外层 LIMIT 的行数:CTE 里 LIMIT 10 和 LIMIT 100、OFFSET 0 和 OFFSET 10、取前 10 行时降序和升序都报成没有不同,取到的却是不同的行。Facets 加 limits,逐段收集(最外层、CTE、FROM 里的子查询;条件里的子查询已经整个写在条件里,不单算,免得报两遍)行数、跳过的行数,以及这一段的排序(ORDER BY 1、别名换成 SELECT 里的表达式);OFFSET 0 算没写,排序只在限了行的段里比。原来的 limit(最外层行数)照旧保留。
This commit is contained in:
@@ -3,7 +3,8 @@
|
||||
- normalize_sql:字面量换成占位符后的规范文本 + 字面量。只有字面量不同的两条 SQL 规范文本相同(定时运行每期的日期
|
||||
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、LIMIT。别名换成真实表名、比较的两边排好顺序;解析不了带 parse_error,不抛
|
||||
(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
|
||||
- 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
|
||||
|
||||
@@ -186,6 +187,27 @@ def test_having_and_limit():
|
||||
assert facets("SELECT a FROM orders LIMIT 5, 20", "mysql").limit == "20"
|
||||
|
||||
|
||||
def test_having_reads_select_aliases():
|
||||
"""HAVING 里引用 SELECT 的别名(MySQL、SQLite 的写法)换成别名指的表达式,和 GROUP BY 别名一样。"""
|
||||
by_alias = facets("SELECT region AS r, SUM(amount) AS s FROM orders GROUP BY r HAVING s > 100")
|
||||
explicit = facets("SELECT o.region, SUM(o.amount) FROM orders o GROUP BY o.region HAVING SUM(o.amount) > 100")
|
||||
assert [p.key for p in by_alias.having] == [p.key for p in explicit.having] == ["SUM(orders.amount) > 100"]
|
||||
|
||||
|
||||
def test_limits_are_collected_per_segment_with_offset_and_order():
|
||||
"""LIMIT 逐段收集(CTE、FROM 里的子查询各算一段),连同 OFFSET 和这一段的排序:只取前几行时,按什么排、
|
||||
跳过几行决定了取到的是哪几行。OFFSET 0 等于没写。"""
|
||||
f = facets("WITH top AS (SELECT amount FROM orders ORDER BY amount DESC LIMIT 10) "
|
||||
"SELECT SUM(amount) FROM top LIMIT 1")
|
||||
assert [(x.scope, x.count, x.offset) for x in f.limits] == [(None, "1", None), ("top", "10", None)]
|
||||
[(key, desc)] = f.limits[1].order
|
||||
assert key.text == "amount" and desc is True
|
||||
mysql = facets("SELECT a FROM orders ORDER BY 1 LIMIT 5, 20", "mysql")
|
||||
assert (mysql.limits[0].count, mysql.limits[0].offset) == ("20", "5")
|
||||
assert [(k.text, d) for k, d in mysql.limits[0].order] == [("a", False)], "ORDER BY 1 换成 SELECT 里的第一项"
|
||||
assert facets("SELECT a FROM orders LIMIT 10 OFFSET 0").limits[0].offset is None
|
||||
|
||||
|
||||
@pytest.mark.parametrize("dialect,sql", [
|
||||
("sqlite", 'SELECT SUM("金额") AS "销售额" FROM "订单" WHERE "是否作废" = 0'),
|
||||
("mysql", "SELECT SUM(`金额`) AS `销售额` FROM `订单` WHERE `是否作废` = 0"),
|
||||
@@ -211,8 +233,18 @@ def test_a_correlated_subquery_reads_the_outer_alias():
|
||||
"""子查询里引用外层的别名(o.id)到外层去找:写成真实表名,两张表的列互相比的条件也写出表名。"""
|
||||
f = facets("SELECT o.id FROM orders o WHERE NOT EXISTS (SELECT 1 FROM refunds r WHERE r.order_id = o.id)")
|
||||
assert "orders.id = refunds.order_id" in [p.text for p in f.where]
|
||||
assert facets("SELECT orders.id FROM orders WHERE NOT EXISTS "
|
||||
"(SELECT 1 FROM refunds WHERE orders.id = refunds.order_id)").where[1].key == f.where[1].key
|
||||
plain = facets("SELECT orders.id FROM orders WHERE NOT EXISTS "
|
||||
"(SELECT 1 FROM refunds WHERE orders.id = refunds.order_id)")
|
||||
assert plain.where[1].key == f.where[1].key
|
||||
# 外层那个条件(NOT EXISTS 整句)也一样:子查询按它自己那一段的来源写,别名换成真实表名
|
||||
assert plain.where[0].key == f.where[0].key
|
||||
assert f.where[0].excludes == "EXISTS(SELECT 1 FROM refunds WHERE orders.id = refunds.order_id)"
|
||||
|
||||
|
||||
def test_a_subquery_in_a_condition_is_written_with_its_own_tables():
|
||||
f = facets("SELECT SUM(o.amount) FROM orders o WHERE o.user_id IN (SELECT u.id FROM users u WHERE u.vip = 1)")
|
||||
assert f.where[0].text == "user_id IN (SELECT id FROM users WHERE vip = 1)"
|
||||
assert f.where[0].key == "orders.user_id IN (SELECT users.id FROM users WHERE users.vip = 1)"
|
||||
|
||||
|
||||
def test_the_schema_tells_which_table_an_unqualified_column_belongs_to():
|
||||
@@ -380,11 +412,47 @@ def test_an_unparsable_side_is_reported_once_without_item_by_item_comparison():
|
||||
("SELECT SUM(o.amount) FROM orders o, stores s WHERE o.store_id = s.id AND s.city = '虚构市'",
|
||||
"SELECT SUM(orders.amount) FROM orders INNER JOIN stores ON stores.id = orders.store_id "
|
||||
"WHERE stores.city = '虚构市'"),
|
||||
# 条件里套着的子查询用了别名:NOT EXISTS、IN (SELECT …)
|
||||
("SELECT o.id FROM orders o WHERE NOT EXISTS (SELECT 1 FROM refunds r WHERE r.order_id = o.id)",
|
||||
"SELECT orders.id FROM orders WHERE NOT EXISTS (SELECT 1 FROM refunds WHERE refunds.order_id = orders.id)"),
|
||||
("SELECT SUM(o.amount) FROM orders o WHERE o.user_id IN (SELECT u.id FROM users u WHERE u.vip = 1)",
|
||||
"SELECT SUM(amount) FROM orders WHERE user_id IN (SELECT id FROM users WHERE vip = 1)"),
|
||||
# HAVING 里用 SELECT 的别名
|
||||
("SELECT o.region, SUM(o.amount) FROM orders o GROUP BY o.region HAVING SUM(o.amount) > 100",
|
||||
"SELECT region AS r, SUM(amount) AS s FROM orders GROUP BY r HAVING s > 100"),
|
||||
# OFFSET 0 等于没写;取前几行时 ORDER BY 1 和写出列名是同一个排序
|
||||
("SELECT amount FROM orders ORDER BY 1 DESC LIMIT 10 OFFSET 0",
|
||||
"SELECT o.amount FROM orders o ORDER BY o.amount DESC LIMIT 10"),
|
||||
])
|
||||
def test_the_same_meaning_written_differently_is_no_difference(a, b):
|
||||
assert texts(a, b) == []
|
||||
|
||||
|
||||
def test_a_real_difference_inside_a_subquery_is_still_reported():
|
||||
a = "SELECT SUM(o.amount) FROM orders o WHERE o.user_id IN (SELECT u.id FROM users u WHERE u.vip = 1)"
|
||||
b = "SELECT SUM(o.amount) FROM orders o WHERE o.user_id IN (SELECT u.referrer_id FROM users u WHERE u.vip = 1)"
|
||||
assert texts(a, b) == ["A 按 user_id IN (SELECT id FROM users WHERE vip = 1) 筛选,"
|
||||
"B 按 user_id IN (SELECT referrer_id FROM users WHERE vip = 1) 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",
|
||||
"A 在 top 里只取前 10 行,B 只取前 100 行"),
|
||||
("SELECT amount FROM orders LIMIT 10 OFFSET 0", "SELECT amount FROM orders LIMIT 10 OFFSET 10",
|
||||
"A 不跳过行,B 跳过前 10 行"),
|
||||
("SELECT amount FROM orders ORDER BY 1 DESC LIMIT 10", "SELECT amount FROM orders ORDER BY 1 ASC LIMIT 10",
|
||||
"A 取行前按 amount 降序排,B 按 amount 升序排"),
|
||||
("SELECT amount FROM orders ORDER BY amount DESC LIMIT 10", "SELECT amount FROM orders LIMIT 10",
|
||||
"A 取行前按 amount 降序排,B 没有排序"),
|
||||
])
|
||||
def test_which_rows_are_taken_is_compared(a, b, text):
|
||||
"""取哪几行:每一段的行数、跳过的行数,以及取前几行时的排序。排序只在有 LIMIT / OFFSET 的段里比:
|
||||
没有取前几行,排序不影响算出来的数。"""
|
||||
assert texts(a, b) == [text]
|
||||
assert texts("SELECT SUM(amount) FROM orders ORDER BY 1 DESC", "SELECT SUM(amount) FROM orders") == []
|
||||
|
||||
|
||||
@pytest.mark.parametrize("dialect", DIALECTS)
|
||||
def test_each_dialect_gives_the_same_three_findings(dialect):
|
||||
q = {"sqlite": '"', "postgres": '"', "mysql": "`"}[dialect]
|
||||
|
||||
Reference in New Issue
Block a user