Disallow generated columns in COPY WHERE clause

Stored generated columns are not yet computed when the filtering
happens, so we need to prohibit them to avoid incorrect behavior.

Virtual generated columns currently error out ("unexpected virtual
generated column reference").  They could probably work if we expand
them in the right place, but for now let's keep them consistent with
the stored variant.  This doesn't change the behavior, it only gives a
nicer error message.

Co-authored-by: jian he <jian.universality@gmail.com>
Reviewed-by: Kirill Reshke <reshkekirill@gmail.com>
Reviewed-by: Masahiko Sawada <sawada.mshk@gmail.com>
Discussion: https://www.postgresql.org/message-id/flat/CACJufxHb8YPQ095R_pYDr77W9XKNaXg5Rzy-WP525mkq+hRM3g@mail.gmail.com

5 files changed, 59 insertions, 0 deletions

diff --git a/src/backend/commands/copy.c b/src/backend/commands/copy.c
index 44020d0ae80..28e878c3688 100644
--- a/src/backend/commands/copy.c
+++ b/src/backend/commands/copy.c
@@ -133,6 +133,9 @@ DoCopy(ParseState *pstate, const CopyStmt *stmt,
 
 		if (stmt->whereClause)
 		{
+			Bitmapset  *expr_attrs = NULL;
+			int			i;
+
 			/* add nsitem to query namespace */
 			addNSItemToQuery(pstate, nsitem, false, true, true);
 
@@ -145,6 +148,42 @@ DoCopy(ParseState *pstate, const CopyStmt *stmt,
 			/* we have to fix its collations too */
 			assign_expr_collations(pstate, whereClause);
 
+			/*
+			 * Examine all the columns in the WHERE clause expression.  When
+			 * the whole-row reference is present, examine all the columns of
+			 * the table.
+			 */
+			pull_varattnos(whereClause, 1, &expr_attrs);
+			if (bms_is_member(0 - FirstLowInvalidHeapAttributeNumber, expr_attrs))
+			{
+				expr_attrs = bms_add_range(expr_attrs,
+										   1 - FirstLowInvalidHeapAttributeNumber,
+										   RelationGetNumberOfAttributes(rel) - FirstLowInvalidHeapAttributeNumber);
+				expr_attrs = bms_del_member(expr_attrs, 0 - FirstLowInvalidHeapAttributeNumber);
+			}
+
+			i = -1;
+			while ((i = bms_next_member(expr_attrs, i)) >= 0)
+			{
+				AttrNumber	attno = i + FirstLowInvalidHeapAttributeNumber;
+
+				Assert(attno != 0);
+
+				/*
+				 * Prohibit generated columns in the WHERE clause.  Stored
+				 * generated columns are not yet computed when the filtering
+				 * happens.  Virtual generated columns could probably work (we
+				 * would need to expand them somewhere around here), but for
+				 * now we keep them consistent with the stored variant.
+				 */
+				if (TupleDescAttr(RelationGetDescr(rel), attno - 1)->attgenerated)
+					ereport(ERROR,
+							errcode(ERRCODE_INVALID_COLUMN_REFERENCE),
+							errmsg("generated columns are not supported in COPY FROM WHERE conditions"),
+							errdetail("Column \"%s\" is a generated column.",
+									  get_attname(RelationGetRelid(rel), attno, false)));
+			}
+
 			whereClause = eval_const_expressions(NULL, whereClause);
 
 			whereClause = (Node *) canonicalize_qual((Expr *) whereClause, false);
diff --git a/src/test/regress/expected/generated_stored.out b/src/test/regress/expected/generated_stored.out
index b3710a49de6..8b7a71d8f0c 100644
--- a/src/test/regress/expected/generated_stored.out
+++ b/src/test/regress/expected/generated_stored.out
@@ -502,6 +502,12 @@ COPY gtest1 FROM stdin;
 COPY gtest1 (a, b) FROM stdin;
 ERROR:  column "b" is a generated column
 DETAIL:  Generated columns cannot be used in COPY.
+COPY gtest1 FROM stdin WHERE b <> 10;
+ERROR:  generated columns are not supported in COPY FROM WHERE conditions
+DETAIL:  Column "b" is a generated column.
+COPY gtest1 FROM stdin WHERE gtest1 IS NULL;
+ERROR:  generated columns are not supported in COPY FROM WHERE conditions
+DETAIL:  Column "b" is a generated column.
 SELECT * FROM gtest1 ORDER BY a;
  a | b 
 ---+---
diff --git a/src/test/regress/expected/generated_virtual.out b/src/test/regress/expected/generated_virtual.out
index 4ec3d330017..dde325e46c6 100644
--- a/src/test/regress/expected/generated_virtual.out
+++ b/src/test/regress/expected/generated_virtual.out
@@ -496,6 +496,12 @@ COPY gtest1 FROM stdin;
 COPY gtest1 (a, b) FROM stdin;
 ERROR:  column "b" is a generated column
 DETAIL:  Generated columns cannot be used in COPY.
+COPY gtest1 FROM stdin WHERE b <> 10;
+ERROR:  generated columns are not supported in COPY FROM WHERE conditions
+DETAIL:  Column "b" is a generated column.
+COPY gtest1 FROM stdin WHERE gtest1 IS NULL;
+ERROR:  generated columns are not supported in COPY FROM WHERE conditions
+DETAIL:  Column "b" is a generated column.
 SELECT * FROM gtest1 ORDER BY a;
  a | b 
 ---+---
diff --git a/src/test/regress/sql/generated_stored.sql b/src/test/regress/sql/generated_stored.sql
index 99ea0105685..2001a47bcc6 100644
--- a/src/test/regress/sql/generated_stored.sql
+++ b/src/test/regress/sql/generated_stored.sql
@@ -217,6 +217,10 @@ COPY gtest1 FROM stdin;
 
 COPY gtest1 (a, b) FROM stdin;
 
+COPY gtest1 FROM stdin WHERE b <> 10;
+
+COPY gtest1 FROM stdin WHERE gtest1 IS NULL;
+
 SELECT * FROM gtest1 ORDER BY a;
 
 TRUNCATE gtest3;
diff --git a/src/test/regress/sql/generated_virtual.sql b/src/test/regress/sql/generated_virtual.sql
index 992c0cdae65..2911439776c 100644
--- a/src/test/regress/sql/generated_virtual.sql
+++ b/src/test/regress/sql/generated_virtual.sql
@@ -217,6 +217,10 @@ COPY gtest1 FROM stdin;
 
 COPY gtest1 (a, b) FROM stdin;
 
+COPY gtest1 FROM stdin WHERE b <> 10;
+
+COPY gtest1 FROM stdin WHERE gtest1 IS NULL;
+
 SELECT * FROM gtest1 ORDER BY a;
 
 TRUNCATE gtest3;