From 61ea6a492ef900bf8745455847e2d9cffb396152 Mon Sep 17 00:00:00 2001 From: jian he Date: Fri, 6 Mar 2026 14:47:58 +0800 Subject: [PATCH v26 3/4] Add option force_array for COPY JSON FORMAT This adds the force_array option, which is available exclusively when using COPY TO with the JSON format. When enabled, this option wraps the output in a top-level JSON array (enclosed in square brackets with comma-separated elements), making the entire result a valid single JSON value. Without this option, the default behavior is to output a stream of independent JSON objects. Attempting to use this option with COPY FROM or with formats other than JSON will raise an error. Author: Joe Conway Author: jian he Reviewed-by: Junwang Zhao Reviewed-by: Masahiko Sawada , Reviewed-by: Florents Tselai Reviewed-by: Andrew Dunstan discussion: https://postgr.es/m/CALvfUkBxTYy5uWPFVwpk_7ii2zgT07t3d-yR_cy4sfrrLU%3Dkcg%40mail.gmail.com discussion: https://postgr.es/m/6a04628d-0d53-41d9-9e35-5a8dc302c34c@joeconway.com --- doc/src/sgml/ref/copy.sgml | 30 ++++++++++++++++++++++ src/backend/commands/copy.c | 13 ++++++++++ src/backend/commands/copyto.c | 41 ++++++++++++++++++++++++++++-- src/bin/psql/tab-complete.in.c | 2 +- src/include/commands/copy.h | 1 + src/test/regress/expected/copy.out | 33 ++++++++++++++++++++++++ src/test/regress/sql/copy.sql | 10 ++++++++ 7 files changed, 127 insertions(+), 3 deletions(-) diff --git a/doc/src/sgml/ref/copy.sgml b/doc/src/sgml/ref/copy.sgml index 75f55bbf6f8..a79587f7613 100644 --- a/doc/src/sgml/ref/copy.sgml +++ b/doc/src/sgml/ref/copy.sgml @@ -40,6 +40,7 @@ COPY { table_name [ ( boolean | integer | MATCH ] QUOTE 'quote_character' ESCAPE 'escape_character' + FORCE_ARRAY [ boolean ] FORCE_QUOTE { ( column_name [, ...] ) | * } FORCE_NOT_NULL { ( column_name [, ...] ) | * } FORCE_NULL { ( column_name [, ...] ) | * } @@ -366,6 +367,19 @@ COPY { table_name [ ( + + FORCE_ARRAY + + + Force output of square brackets as array decorations at the beginning + and end of output, and commas between the rows. It is allowed only in + COPY TO, and only when using + json format. The default is + false. + + + + FORCE_QUOTE @@ -1103,6 +1117,22 @@ COPY country TO STDOUT (DELIMITER '|'); + + When the FORCE_ARRAY option is enabled, + the entire output is wrapped in a single JSON array with rows separated by commas: + +COPY (SELECT * FROM (VALUES(1),(2)) val(id)) TO STDOUT (FORMAT JSON, FORCE_ARRAY); + +The output is as follows: + +[ + {"id":1} +,{"id":2} +] + + + + To copy data from a file into the country table: diff --git a/src/backend/commands/copy.c b/src/backend/commands/copy.c index 29c121c7f08..84254d46a67 100644 --- a/src/backend/commands/copy.c +++ b/src/backend/commands/copy.c @@ -569,6 +569,7 @@ ProcessCopyOptions(ParseState *pstate, bool on_error_specified = false; bool log_verbosity_specified = false; bool reject_limit_specified = false; + bool force_array_specified = false; ListCell *option; /* Support external use for option sanity checking */ @@ -725,6 +726,13 @@ ProcessCopyOptions(ParseState *pstate, defel->defname), parser_errposition(pstate, defel->location))); } + else if (strcmp(defel->defname, "force_array") == 0) + { + if (force_array_specified) + errorConflictingDefElem(defel, pstate); + force_array_specified = true; + opts_out->force_array = defGetBoolean(defel); + } else if (strcmp(defel->defname, "on_error") == 0) { if (on_error_specified) @@ -967,6 +975,11 @@ ProcessCopyOptions(ParseState *pstate, errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("COPY %s mode cannot be used with %s", "JSON", "COPY FROM")); + if (opts_out->format != COPY_FORMAT_JSON && opts_out->force_array) + ereport(ERROR, + errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("COPY %s can only be used with JSON mode", "FORCE_ARRAY")); + if (opts_out->default_print) { if (!is_from) diff --git a/src/backend/commands/copyto.c b/src/backend/commands/copyto.c index e87310ec5a0..4ea44daee0a 100644 --- a/src/backend/commands/copyto.c +++ b/src/backend/commands/copyto.c @@ -86,6 +86,7 @@ typedef struct CopyToStateData List *attnumlist; /* integer list of attnums to copy */ char *filename; /* filename, or NULL for STDOUT */ bool is_program; /* is 'filename' a program to popen? */ + bool json_row_delim_needed; /* need delimiter before next row */ StringInfo json_buf; /* reusable buffer for JSON output, it is * initliazed in BeginCopyTo */ copy_data_dest_cb data_dest_cb; /* function for writing data */ @@ -135,6 +136,7 @@ static void CopyToTextLikeOneRow(CopyToState cstate, TupleTableSlot *slot, bool is_csv); static void CopyToTextLikeEnd(CopyToState cstate); static void CopyToJsonOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToJsonEnd(CopyToState cstate); static void CopyToBinaryStart(CopyToState cstate, TupleDesc tupDesc); static void CopyToBinaryOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo); static void CopyToBinaryOneRow(CopyToState cstate, TupleTableSlot *slot); @@ -176,7 +178,7 @@ static const CopyToRoutine CopyToRoutineJson = { .CopyToStart = CopyToTextLikeStart, .CopyToOutFunc = CopyToTextLikeOutFunc, .CopyToOneRow = CopyToJsonOneRow, - .CopyToEnd = CopyToTextLikeEnd, + .CopyToEnd = CopyToJsonEnd, }; /* binary format */ @@ -242,6 +244,18 @@ CopyToTextLikeStart(CopyToState cstate, TupleDesc tupDesc) CopySendTextLikeEndOfRow(cstate); } + + if (cstate->opts.format == COPY_FORMAT_JSON) + { + /* + * If FORCE_ARRAY has been specified, send the opening bracket. + */ + if (cstate->opts.force_array) + { + CopySendChar(cstate, '['); + CopySendTextLikeEndOfRow(cstate); + } + } } /* @@ -318,13 +332,24 @@ CopyToTextLikeOneRow(CopyToState cstate, CopySendTextLikeEndOfRow(cstate); } -/* Implementation of the end callback for text, CSV, and json formats */ +/* Implementation of the end callback for text and CSV formats */ static void CopyToTextLikeEnd(CopyToState cstate) { /* Nothing to do here */ } +/* Implementation of the end callback for json format */ +static void +CopyToJsonEnd(CopyToState cstate) +{ + if (cstate->opts.force_array) + { + CopySendChar(cstate, ']'); + CopySendTextLikeEndOfRow(cstate); + } +} + /* Implementation of per-row callback for json format */ static void CopyToJsonOneRow(CopyToState cstate, TupleTableSlot *slot) @@ -345,6 +370,18 @@ CopyToJsonOneRow(CopyToState cstate, TupleTableSlot *slot) rowdata = ExecFetchSlotHeapTupleDatum(slot); composite_to_json(rowdata, cstate->json_buf, false); + if (cstate->opts.force_array) + { + if (cstate->json_row_delim_needed) + CopySendChar(cstate, ','); + else + { + /* first row needs no delimiter */ + CopySendChar(cstate, ' '); + cstate->json_row_delim_needed = true; + } + } + CopySendData(cstate, cstate->json_buf->data, cstate->json_buf->len); CopySendTextLikeEndOfRow(cstate); diff --git a/src/bin/psql/tab-complete.in.c b/src/bin/psql/tab-complete.in.c index 0d9649c1f0a..4b18cc6e2cd 100644 --- a/src/bin/psql/tab-complete.in.c +++ b/src/bin/psql/tab-complete.in.c @@ -1232,7 +1232,7 @@ Copy_common_options, "DEFAULT", "FORCE_NOT_NULL", "FORCE_NULL", "FREEZE", \ /* COPY TO options */ #define Copy_to_options \ -Copy_common_options, "FORCE_QUOTE" +Copy_common_options, "FORCE_QUOTE", "FORCE_ARRAY" /* * These object types were introduced later than our support cutoff of diff --git a/src/include/commands/copy.h b/src/include/commands/copy.h index 2b5bef6738e..abecfe51098 100644 --- a/src/include/commands/copy.h +++ b/src/include/commands/copy.h @@ -88,6 +88,7 @@ typedef struct CopyFormatOptions List *force_notnull; /* list of column names */ bool force_notnull_all; /* FORCE_NOT_NULL *? */ bool *force_notnull_flags; /* per-column CSV FNN flags */ + bool force_array; /* add JSON array decorations */ List *force_null; /* list of column names */ bool force_null_all; /* FORCE_NULL *? */ bool *force_null_flags; /* per-column CSV FN flags */ diff --git a/src/test/regress/expected/copy.out b/src/test/regress/expected/copy.out index 4324e3e4961..309a33ca2e7 100644 --- a/src/test/regress/expected/copy.out +++ b/src/test/regress/expected/copy.out @@ -80,6 +80,16 @@ copy (select 1 union all select 2) to stdout with (format json); copy (values (1), (2)) TO stdout with (format json); {"column1":1} {"column1":2} +copy (select 1 union all select 2) to stdout with (format json, force_array true); +[ + {"?column?":1} +,{"?column?":2} +] +copy (values (1), (2)) TO stdout with (format json, force_array true); +[ + {"column1":1} +,{"column1":2} +] copy copytest to stdout json; {"style":"DOS","test":"abc\r\ndef","filler":1} {"style":"Unix","test":"abc\ndef","filler":2} @@ -122,6 +132,29 @@ ERROR: COPY JSON mode cannot be used with COPY FROM copy copytest (style) to stdout (format json); ERROR: column selection is not supported in JSON mode -- all of the above should yield error +-- should fail: force_array requires json format +copy copytest to stdout (format csv, force_array true); +ERROR: COPY FORCE_ARRAY can only be used with JSON mode +-- force_array variants +copy copytest to stdout (format json, force_array); +[ + {"style":"DOS","test":"abc\r\ndef","filler":1} +,{"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} +] +copy copytest to stdout (format json, force_array true); +[ + {"style":"DOS","test":"abc\r\ndef","filler":1} +,{"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} +] +copy copytest to stdout (format json, force_array false); +{"style":"DOS","test":"abc\r\ndef","filler":1} +{"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} -- embedded escaped characters create temp table copyjsontest ( id bigserial, diff --git a/src/test/regress/sql/copy.sql b/src/test/regress/sql/copy.sql index 4e9f74537f8..8a20907dd4c 100644 --- a/src/test/regress/sql/copy.sql +++ b/src/test/regress/sql/copy.sql @@ -85,6 +85,8 @@ copy copytest3 to stdout csv header; --- test copying in JSON mode with various styles copy (select 1 union all select 2) to stdout with (format json); copy (values (1), (2)) TO stdout with (format json); +copy (select 1 union all select 2) to stdout with (format json, force_array true); +copy (values (1), (2)) TO stdout with (format json, force_array true); copy copytest to stdout json; copy copytest to stdout (format json); @@ -105,6 +107,14 @@ copy copytest from stdin(format json); copy copytest (style) to stdout (format json); -- all of the above should yield error +-- should fail: force_array requires json format +copy copytest to stdout (format csv, force_array true); + +-- force_array variants +copy copytest to stdout (format json, force_array); +copy copytest to stdout (format json, force_array true); +copy copytest to stdout (format json, force_array false); + -- embedded escaped characters create temp table copyjsontest ( id bigserial, -- 2.34.1