feat(ir): more flexible dereferencing support for join right hand side

ibis/backends/bigquery/tests/unit/snapshots/test_compiler/test_projection_fusion_only_peeks_at_immediate_parent/out.sql

@@ -15,5 +15,5 @@ SELECT
   `t3`.`val`,
   `t3`.`XYZ`
 FROM `t1` AS `t3`
-INNER JOIN `t1` AS `t5`
+INNER JOIN `t1` AS `t4`
   ON TRUE

ibis/backends/bigquery/tests/unit/test_compiler.py

@@ -274,7 +274,8 @@ class MockBackend(ibis.backends.bigquery.Backend):
     table = ops.SQLQueryResult("select * from t", schema, ibis_client).to_expr()
     for _ in range(num_joins):  # noqa: F402
         table = table.mutate(dummy=ibis.literal(""))
-        table = table.left_join(table, ["dummy"])[[table]]
+        table_ = table.view()
+        table = table.left_join(table_, ["dummy"])[[table_]]
 
     start = time.time()
     table.compile()

ibis/backends/clickhouse/tests/snapshots/test_select/test_join_self_reference/out.sql

@@ -13,5 +13,5 @@ SELECT
   "t1"."year",
   "t1"."month"
 FROM "functional_alltypes" AS "t1"
-INNER JOIN "functional_alltypes" AS "t3"
-  ON "t1"."id" = "t3"."id"
+INNER JOIN "functional_alltypes" AS "t2"
+  ON "t1"."id" = "t2"."id"

ibis/backends/impala/tests/snapshots/test_sql/test_join_key_name2/out.sql

@@ -1 +1 @@
-WITH `t9` AS (SELECT EXTRACT(year FROM `t8`.`odate`) AS `year`, COUNT(*) AS `CountStar()` FROM (SELECT `t6`.`c_custkey`, `t6`.`c_name`, `t6`.`c_address`, `t6`.`c_nationkey`, `t6`.`c_phone`, `t6`.`c_acctbal`, `t6`.`c_mktsegment`, `t6`.`c_comment`, `t4`.`r_name` AS `region`, `t7`.`o_totalprice`, CAST(`t7`.`o_orderdate` AS TIMESTAMP) AS `odate` FROM `tpch_region` AS `t4` INNER JOIN `tpch_nation` AS `t5` ON `t4`.`r_regionkey` = `t5`.`n_regionkey` INNER JOIN `tpch_customer` AS `t6` ON `t6`.`c_nationkey` = `t5`.`n_nationkey` INNER JOIN `tpch_orders` AS `t7` ON `t7`.`o_custkey` = `t6`.`c_custkey`) AS `t8` GROUP BY 1) SELECT `t11`.`year`, `t11`.`CountStar()` AS `pre_count`, `t13`.`CountStar()` AS `post_count` FROM `t9` AS `t11` INNER JOIN `t9` AS `t13` ON `t11`.`year` = `t13`.`year`
+WITH `t9` AS (SELECT EXTRACT(year FROM `t8`.`odate`) AS `year`, COUNT(*) AS `CountStar()` FROM (SELECT `t6`.`c_custkey`, `t6`.`c_name`, `t6`.`c_address`, `t6`.`c_nationkey`, `t6`.`c_phone`, `t6`.`c_acctbal`, `t6`.`c_mktsegment`, `t6`.`c_comment`, `t4`.`r_name` AS `region`, `t7`.`o_totalprice`, CAST(`t7`.`o_orderdate` AS TIMESTAMP) AS `odate` FROM `tpch_region` AS `t4` INNER JOIN `tpch_nation` AS `t5` ON `t4`.`r_regionkey` = `t5`.`n_regionkey` INNER JOIN `tpch_customer` AS `t6` ON `t6`.`c_nationkey` = `t5`.`n_nationkey` INNER JOIN `tpch_orders` AS `t7` ON `t7`.`o_custkey` = `t6`.`c_custkey`) AS `t8` GROUP BY 1) SELECT `t11`.`year`, `t11`.`CountStar()` AS `pre_count`, `t12`.`CountStar()` AS `post_count` FROM `t9` AS `t11` INNER JOIN `t9` AS `t12` ON `t11`.`year` = `t12`.`year`

ibis/backends/impala/tests/snapshots/test_sql/test_join_with_nested_or_condition/out.sql

@@ -2,12 +2,12 @@ SELECT
   `t1`.`a`,
   `t1`.`b`
 FROM `t` AS `t1`
-INNER JOIN `t` AS `t3`
-  ON `t1`.`a` = `t3`.`a`
+INNER JOIN `t` AS `t2`
+  ON `t1`.`a` = `t2`.`a`
   AND (
     (
-      `t1`.`a` <> `t3`.`b`
+      `t1`.`a` <> `t2`.`b`
     ) OR (
-      `t1`.`b` <> `t3`.`a`
+      `t1`.`b` <> `t2`.`a`
     )
   )

ibis/backends/impala/tests/snapshots/test_sql/test_join_with_nested_xor_condition/out.sql

@@ -2,13 +2,13 @@ SELECT
   `t1`.`a`,
   `t1`.`b`
 FROM `t` AS `t1`
-INNER JOIN `t` AS `t3`
-  ON `t1`.`a` = `t3`.`a`
+INNER JOIN `t` AS `t2`
+  ON `t1`.`a` = `t2`.`a`
   AND (
     (
-      `t1`.`a` <> `t3`.`b` OR `t1`.`b` <> `t3`.`a`
+      `t1`.`a` <> `t2`.`b` OR `t1`.`b` <> `t2`.`a`
     )
     AND NOT (
-      `t1`.`a` <> `t3`.`b` AND `t1`.`b` <> `t3`.`a`
+      `t1`.`a` <> `t2`.`b` AND `t1`.`b` <> `t2`.`a`
     )
   )

ibis/backends/impala/tests/snapshots/test_sql/test_limit_cte_extract/out.sql

@@ -19,5 +19,5 @@ SELECT
   `t3`.`year`,
   `t3`.`month`
 FROM `t1` AS `t3`
-INNER JOIN `t1` AS `t5`
+INNER JOIN `t1` AS `t4`
   ON TRUE

ibis/backends/impala/tests/snapshots/test_sql/test_nested_join_base/out.sql

@@ -7,7 +7,7 @@ WITH `t1` AS (
     1
 )
 SELECT
-  `t5`.`uuid`,
+  `t3`.`uuid`,
   `t3`.`CountStar(t)`
 FROM (
   SELECT

ibis/backends/impala/tests/snapshots/test_sql/test_nested_joins_single_cte/out.sql

@@ -7,7 +7,7 @@ WITH `t1` AS (
     1
 )
 SELECT
-  `t7`.`uuid`,
+  `t4`.`uuid`,
   `t4`.`CountStar(t)`,
   `t5`.`last_visit`
 FROM (
@@ -28,4 +28,4 @@ LEFT OUTER JOIN (
   GROUP BY
     1
 ) AS `t5`
-  ON `t7`.`uuid` = `t5`.`uuid`
+  ON `t4`.`uuid` = `t5`.`uuid`

ibis/backends/pandas/executor.py

@@ -540,7 +540,7 @@ def visit(cls, op: ops.DummyTable, values):
         return df
 
     @classmethod
-    def visit(cls, op: ops.SelfReference | ops.JoinTable, parent, **kwargs):
+    def visit(cls, op: ops.Reference, parent, **kwargs):
         return parent
 
     @classmethod

ibis/backends/polars/compiler.py

@@ -1239,13 +1239,8 @@ def execute_view(op, *, ctx: pl.SQLContext, **kw):
     return child
 
 
-@translate.register(ops.SelfReference)
-def execute_self_reference(op, **kw):
-    return translate(op.parent, **kw)
-
-
-@translate.register(ops.JoinTable)
-def execute_join_table(op, **kw):
+@translate.register(ops.Reference)
+def execute_reference(op, **kw):
     return translate(op.parent, **kw)
 
 

ibis/backends/sql/compiler.py

@@ -1158,6 +1158,8 @@ def visit_DatabaseTable(
     def visit_SelfReference(self, op, *, parent, identifier):
         return parent
 
+    visit_JoinReference = visit_SelfReference
+
     def visit_JoinChain(self, op, *, first, rest, values):
         result = sg.select(*self._cleanup_names(values), copy=False).from_(
             first, copy=False
@@ -1388,9 +1390,6 @@ def visit_SQLStringView(self, op, *, query: str, child, schema):
     def visit_SQLQueryResult(self, op, *, query, schema, source):
         return sg.parse_one(query, dialect=self.dialect).subquery(copy=False)
 
-    def visit_JoinTable(self, op, *, parent, index):
-        return parent
-
     def visit_RegexExtract(self, op, *, arg, pattern, index):
         return self.f.regexp_extract(arg, pattern, index, dialect=self.dialect)
 

ibis/backends/tests/sql/snapshots/test_select_sql/test_limit_cte_extract/out.sql

@@ -19,5 +19,5 @@ SELECT
   "t3"."year",
   "t3"."month"
 FROM "t1" AS "t3"
-INNER JOIN "t1" AS "t5"
+INNER JOIN "t1" AS "t4"
   ON TRUE

ibis/backends/tests/sql/snapshots/test_select_sql/test_limit_with_self_join/out.sql

@@ -15,20 +15,20 @@ FROM (
     "t1"."timestamp_col",
     "t1"."year",
     "t1"."month",
-    "t3"."id" AS "id_right",
-    "t3"."bool_col" AS "bool_col_right",
-    "t3"."tinyint_col" AS "tinyint_col_right",
-    "t3"."smallint_col" AS "smallint_col_right",
-    "t3"."int_col" AS "int_col_right",
-    "t3"."bigint_col" AS "bigint_col_right",
-    "t3"."float_col" AS "float_col_right",
-    "t3"."double_col" AS "double_col_right",
-    "t3"."date_string_col" AS "date_string_col_right",
-    "t3"."string_col" AS "string_col_right",
-    "t3"."timestamp_col" AS "timestamp_col_right",
-    "t3"."year" AS "year_right",
-    "t3"."month" AS "month_right"
+    "t2"."id" AS "id_right",
+    "t2"."bool_col" AS "bool_col_right",
+    "t2"."tinyint_col" AS "tinyint_col_right",
+    "t2"."smallint_col" AS "smallint_col_right",
+    "t2"."int_col" AS "int_col_right",
+    "t2"."bigint_col" AS "bigint_col_right",
+    "t2"."float_col" AS "float_col_right",
+    "t2"."double_col" AS "double_col_right",
+    "t2"."date_string_col" AS "date_string_col_right",
+    "t2"."string_col" AS "string_col_right",
+    "t2"."timestamp_col" AS "timestamp_col_right",
+    "t2"."year" AS "year_right",
+    "t2"."month" AS "month_right"
   FROM "functional_alltypes" AS "t1"
-  INNER JOIN "functional_alltypes" AS "t3"
-    ON "t1"."tinyint_col" < EXTRACT(minute FROM "t3"."timestamp_col")
-) AS "t4"
+  INNER JOIN "functional_alltypes" AS "t2"
+    ON "t1"."tinyint_col" < EXTRACT(minute FROM "t2"."timestamp_col")
+) AS "t3"

ibis/backends/tests/sql/snapshots/test_select_sql/test_self_join_subquery_distinct_equal/out.sql

@@ -1,6 +1,6 @@
 SELECT
   "t2"."r_name",
-  "t6"."n_name"
+  "t5"."n_name"
 FROM "tpch_region" AS "t2"
 INNER JOIN "tpch_nation" AS "t3"
   ON "t2"."r_regionkey" = "t3"."n_regionkey"
@@ -16,5 +16,5 @@ INNER JOIN (
   FROM "tpch_region" AS "t2"
   INNER JOIN "tpch_nation" AS "t3"
     ON "t2"."r_regionkey" = "t3"."n_regionkey"
-) AS "t6"
-  ON "t2"."r_regionkey" = "t6"."r_regionkey"
+) AS "t5"
+  ON "t2"."r_regionkey" = "t5"."r_regionkey"

ibis/backends/tests/sql/snapshots/test_select_sql/test_subquery_in_union/out.sql

@@ -7,25 +7,25 @@ WITH "t1" AS (
   GROUP BY
     1,
     2
-), "t6" AS (
+), "t5" AS (
   SELECT
     "t3"."a",
     "t3"."g",
     "t3"."metric"
   FROM "t1" AS "t3"
-  INNER JOIN "t1" AS "t5"
-    ON "t3"."g" = "t5"."g"
+  INNER JOIN "t1" AS "t4"
+    ON "t3"."g" = "t4"."g"
 )
 SELECT
-  "t9"."a",
-  "t9"."g",
-  "t9"."metric"
+  "t8"."a",
+  "t8"."g",
+  "t8"."metric"
 FROM (
   SELECT
     *
-  FROM "t6" AS "t7"
+  FROM "t5" AS "t6"
   UNION ALL
   SELECT
     *
-  FROM "t6" AS "t8"
-) AS "t9"
+  FROM "t5" AS "t7"
+) AS "t8"

ibis/backends/tests/sql/snapshots/test_select_sql/test_subquery_used_for_self_join/out.sql

@@ -11,21 +11,21 @@ WITH "t1" AS (
     3
 )
 SELECT
-  "t6"."g",
-  MAX("t6"."total" - "t6"."total_right") AS "metric"
+  "t5"."g",
+  MAX("t5"."total" - "t5"."total_right") AS "metric"
 FROM (
   SELECT
     "t3"."g",
     "t3"."a",
     "t3"."b",
     "t3"."total",
-    "t5"."g" AS "g_right",
-    "t5"."a" AS "a_right",
-    "t5"."b" AS "b_right",
-    "t5"."total" AS "total_right"
+    "t4"."g" AS "g_right",
+    "t4"."a" AS "a_right",
+    "t4"."b" AS "b_right",
+    "t4"."total" AS "total_right"
   FROM "t1" AS "t3"
-  INNER JOIN "t1" AS "t5"
-    ON "t3"."a" = "t5"."b"
-) AS "t6"
+  INNER JOIN "t1" AS "t4"
+    ON "t3"."a" = "t4"."b"
+) AS "t5"
 GROUP BY
   1

ibis/backends/tests/sql/snapshots/test_select_sql/test_tpch_self_join_failure/out.sql

@@ -24,9 +24,9 @@ WITH "t9" AS (
 SELECT
   "t11"."region",
   "t11"."year",
-  "t11"."total" - "t13"."total" AS "yoy_change"
+  "t11"."total" - "t12"."total" AS "yoy_change"
 FROM "t9" AS "t11"
-INNER JOIN "t9" AS "t13"
+INNER JOIN "t9" AS "t12"
   ON "t11"."year" = (
-    "t13"."year" - CAST(1 AS TINYINT)
+    "t12"."year" - CAST(1 AS TINYINT)
   )

ibis/backends/tests/sql/snapshots/test_sql/test_cte_factor_distinct_but_equal/out.sql

@@ -16,5 +16,5 @@ INNER JOIN (
   FROM "alltypes" AS "t1"
   GROUP BY
     1
-) AS "t6"
-  ON "t3"."g" = "t6"."g"
+) AS "t5"
+  ON "t3"."g" = "t5"."g"

ibis/backends/tests/sql/snapshots/test_sql/test_self_reference_join/out.sql

@@ -4,5 +4,5 @@ SELECT
   "t1"."foo_id",
   "t1"."bar_id"
 FROM "star1" AS "t1"
-INNER JOIN "star1" AS "t3"
-  ON "t1"."foo_id" = "t3"."bar_id"
+INNER JOIN "star1" AS "t2"
+  ON "t1"."foo_id" = "t2"."bar_id"