From d839ebe3f14d8ef27a2679a4ccb31a8b0730162c Mon Sep 17 00:00:00 2001 From: Andrew Dunstan Date: Mon, 5 Oct 2026 16:28:25 -0400 Subject: [PATCH v2] COPY TO FORMAT JSON: use the query's column names as keys CopyToJsonOneRow() stamped the row datum with the query's blessed descriptor only when the output slot's descriptor was of type RECORD. When the top plan node is a scan that does not project, the slot carries the scanned table's row type instead, so composite_to_json() took the keys from the table rather than from the query. For example, with u1 (a int, b int) containing (10, 1) and u2 (b int, a int) containing (20, 2): copy (select * from u1 union all select * from u2) to stdout (format json); {"a":10,"b":1} {"b":20,"a":2} The query's columns are (a, b), so the second row should be {"a":20,"b":2}, which is what row_to_json() over the same query produces. Column aliases were lost in the same way. Fix by always stamping the datum with the query's descriptor. For a virtual slot, form the tuple from the slot's values as before. For any other slot, copy the slot's tuple with heap_copy_tuple_as_datum(), passing the query's descriptor, so this costs no more than the old code did. That is safe because a scan returns its tuple unprojected only when tlist_matches_tupdesc() holds, which rules out dropped columns and columns with missing values, so the tuple's physical layout matches the query's descriptor. Add regression tests for column aliases over an unprojected scan, UNION ALL over tables with different column orders, and a table with a column that has a missing value. Bug introduced in 7dadd38cda9. Discussion: https://postgr.es/m/CAGRkXqQHjxgufHPz86+dxGaQZt37hikduUArYtfbn2_3mryZAw@mail.gmail.com Backpatch-through: 19 --- src/backend/commands/copyto.c | 44 ++++++++++++++++++++---------- src/test/regress/expected/copy.out | 13 +++++++++ src/test/regress/sql/copy.sql | 10 +++++++ 3 files changed, 53 insertions(+), 14 deletions(-) diff --git a/src/backend/commands/copyto.c b/src/backend/commands/copyto.c index 5850608a3fb..a187d8ec284 100644 --- a/src/backend/commands/copyto.c +++ b/src/backend/commands/copyto.c @@ -395,22 +395,38 @@ CopyToJsonOneRow(CopyToState cstate, TupleTableSlot *slot) else { /* - * Full table or query without column list. For queries, the slot's - * TupleDesc may carry RECORDOID, which is not registered in the type - * cache and would cause composite_to_json's lookup_rowtype_tupdesc - * call to fail. Build a HeapTuple stamped with the blessed - * descriptor so the type can be looked up correctly. + * Full table or query without column list. For a query, the slot's + * descriptor is either an unregistered RECORD type, which + * composite_to_json's lookup_rowtype_tupdesc() cannot look up, or, + * when the top plan node does not project, the row type of a scanned + * table, whose column names need not match the query's. Either way, + * the datum must be stamped with the query's blessed descriptor. + * + * A virtual slot has no physical tuple, so form one directly. + * Otherwise copy the slot's tuple and stamp the copy with the query's + * descriptor. That is safe because the tuple's physical layout + * matches the query's result descriptor: a scan returns its scan + * tuple unprojected only if tlist_matches_tupdesc() holds, which + * rules out dropped columns and columns with missing values. */ - if (!cstate->rel && slot->tts_tupleDescriptor->tdtypeid == RECORDOID) - { - HeapTuple tup = heap_form_tuple(cstate->tupDesc, - slot->tts_values, - slot->tts_isnull); - - rowdata = HeapTupleGetDatum(tup); - } - else + if (cstate->rel) rowdata = ExecFetchSlotHeapTupleDatum(slot); + else if (TTS_IS_VIRTUAL(slot)) + rowdata = HeapTupleGetDatum(heap_form_tuple(cstate->tupDesc, + slot->tts_values, + slot->tts_isnull)); + else + { + HeapTuple tup; + bool shouldFree; + + Assert(slot->tts_tupleDescriptor->natts == cstate->tupDesc->natts); + + tup = ExecFetchSlotHeapTuple(slot, false, &shouldFree); + rowdata = heap_copy_tuple_as_datum(tup, cstate->tupDesc); + if (shouldFree) + heap_freetuple(tup); + } } composite_to_json(rowdata, cstate->json_buf, false); diff --git a/src/test/regress/expected/copy.out b/src/test/regress/expected/copy.out index 0af0b646921..979bef5f3f2 100644 --- a/src/test/regress/expected/copy.out +++ b/src/test/regress/expected/copy.out @@ -117,6 +117,19 @@ copy (select * from copytest) to stdout (format json); {"style":"Unix","test":"abc\ndef","filler":2} {"style":"Mac","test":"abc\rdef","filler":3} {"style":"esc\\ape","test":"a\\r\\\r\\\n\\nb","filler":4} +-- keys are the query's column names, also when a scan does not project +copy (select a as x, b as y, c as z from copytest_order) to stdout (format json); +{"x":1,"y":2,"z":3} +create temp table copytest_order2 (c int, b int, a int); +insert into copytest_order2 values (4, 5, 6); +copy (select * from copytest_order union all select * from copytest_order2) + to stdout (format json); +{"a":1,"b":2,"c":3} +{"a":4,"b":5,"c":6} +-- columns with missing values force a projection +alter table copytest_order2 add column d int default 7; +copy (select * from copytest_order2) to stdout (format json); +{"c":4,"b":5,"a":6,"d":7} -- all of the following should yield error copy copytest to stdout (format json, delimiter '|'); ERROR: cannot specify DELIMITER in JSON mode diff --git a/src/test/regress/sql/copy.sql b/src/test/regress/sql/copy.sql index 14da3c5ec37..6d3923fb3f0 100644 --- a/src/test/regress/sql/copy.sql +++ b/src/test/regress/sql/copy.sql @@ -101,6 +101,16 @@ copy copytest to stdout json; copy copytest to stdout (format json); copy (select * from copytest) to stdout (format json); +-- keys are the query's column names, also when a scan does not project +copy (select a as x, b as y, c as z from copytest_order) to stdout (format json); +create temp table copytest_order2 (c int, b int, a int); +insert into copytest_order2 values (4, 5, 6); +copy (select * from copytest_order union all select * from copytest_order2) + to stdout (format json); +-- columns with missing values force a projection +alter table copytest_order2 add column d int default 7; +copy (select * from copytest_order2) to stdout (format json); + -- all of the following should yield error copy copytest to stdout (format json, delimiter '|'); copy copytest to stdout (format json, null '\N'); -- 2.43.0