From cd9ee1b0468bdcfd14b357905ad4467b51c25367 Mon Sep 17 00:00:00 2001
From: Gil Forsyth <gforsyth@users.noreply.github.com>
Date: Mon, 23 Sep 2024 11:54:46 -0400
Subject: [PATCH] refactor(joins): require explicit abstract table as RHS of
 joins (#9661)

## Description of changes

We have (had) limited support for passing in in-memory objects as the
RHS of a join, where we would create a memtable for the user and then
use that.  For backends where memtable creation is expensive, or for
queries where there may be multiple calls to the same in-memory data, it
is better to be explicit and first register the in-memory data with the
backend using either `memtable` or `create_table`.

BREAKING CHANGE: Passing a `pyarrow.Table` or a `pandas.DataFrame` as
the right-hand-side of a join is no longer supported.

To join against in-memory data, you can pass the in-memory object to
`ibis.memtable` or `con.create_table` and use the resulting table object
instead.


## Issues closed

* Resolves #9571
---
 ibis/backends/tests/test_join.py |  7 +++++--
 ibis/expr/types/joins.py         | 29 +++++------------------------
 ibis/tests/expr/test_table.py    |  2 +-
 3 files changed, 11 insertions(+), 27 deletions(-)

diff --git a/ibis/backends/tests/test_join.py b/ibis/backends/tests/test_join.py
index 88fdd5489384..b81b1878a882 100644
--- a/ibis/backends/tests/test_join.py
+++ b/ibis/backends/tests/test_join.py
@@ -188,7 +188,8 @@ def test_join_with_pandas(batting, awards_players):
     batting_filt = batting.filter(lambda t: t.yearID < 1900)
     awards_players_filt = awards_players.filter(lambda t: t.yearID < 1900).execute()
     assert isinstance(awards_players_filt, pd.DataFrame)
-    expr = batting_filt.join(awards_players_filt, "yearID")
+    t = ibis.memtable(awards_players_filt)
+    expr = batting_filt.join(t, "yearID")
     df = expr.execute()
     assert df.yearID.nunique() == 7
 
@@ -206,7 +207,9 @@ def test_join_with_pandas_non_null_typed_columns(batting, awards_players):
 
     assert sch.infer(awards_players_filt) == sch.Schema(dict(yearID="int"))
     assert isinstance(awards_players_filt, pd.DataFrame)
-    expr = batting_filt.join(awards_players_filt, "yearID")
+
+    t = ibis.memtable(awards_players_filt)
+    expr = batting_filt.join(t, "yearID")
     df = expr.execute()
     assert df.yearID.nunique() == 7
 
diff --git a/ibis/expr/types/joins.py b/ibis/expr/types/joins.py
index 2987848802af..c0b9a7a8b817 100644
--- a/ibis/expr/types/joins.py
+++ b/ibis/expr/types/joins.py
@@ -5,7 +5,6 @@
 
 from public import public
 
-import ibis
 import ibis.expr.operations as ops
 from ibis import util
 from ibis.common.deferred import Deferred
@@ -13,6 +12,7 @@
 from ibis.common.exceptions import (
     ExpressionError,
     IbisInputError,
+    IbisTypeError,
     InputTypeError,
     IntegrityError,
 )
@@ -31,28 +31,6 @@
     from ibis.expr.operations.relations import JoinKind
 
 
-def coerce_to_table(data):
-    try:
-        import pandas as pd
-    except ImportError:
-        pass
-    else:
-        if isinstance(data, pd.DataFrame):
-            return ibis.memtable(data)
-
-    try:
-        import pyarrow as pa
-    except ImportError:
-        pass
-    else:
-        if isinstance(data, pa.Table):
-            return ibis.memtable(data)
-
-    if not isinstance(data, Table):
-        raise TypeError(f"right operand must be a Table, got {type(data).__name__}")
-    return data
-
-
 def disambiguate_fields(
     how,
     predicates,
@@ -254,7 +232,10 @@ def join(
         lname: str = "",
         rname: str = "{name}_right",
     ):
-        right = coerce_to_table(right)
+        if not isinstance(right, Table):
+            raise IbisTypeError(
+                f"Right side of join must be an Ibis table, got {type(right)}."
+            )
 
         if how == "left_semi":
             how = "semi"
diff --git a/ibis/tests/expr/test_table.py b/ibis/tests/expr/test_table.py
index 2b117cbb93ab..b0ebe5b76355 100644
--- a/ibis/tests/expr/test_table.py
+++ b/ibis/tests/expr/test_table.py
@@ -1315,7 +1315,7 @@ def test_join_invalid_expr_type(con):
     invalid_right = left.foo_id
     join_key = ["bar_id"]
 
-    with pytest.raises(TypeError):
+    with pytest.raises(com.IbisTypeError):
         left.inner_join(invalid_right, join_key)