From: Andrew Dunstan Date: Mon, 16 Mar 2026 20:50:24 +0000 (-0400) Subject: json format for COPY TO X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=7dadd38cda95bf5bc0c4715d9ab71766d1693379;p=thirdparty%2Fpostgresql.git json format for COPY TO This introduces the JSON format option for the COPY TO command, allowing users to export query results or table data directly as a stream of JSON objects (one per line, NDJSON style). The JSON format is currently supported only for COPY TO operations; it is not available for COPY FROM. JSON format is incompatible with some standard text/CSV formatting options, including HEADER, DEFAULT, NULL, DELIMITER, FORCE QUOTE, FORCE NOT NULL, and FORCE NULL. Column list support is included: when a column list is specified, only the named columns are emitted in each JSON object. Regression tests covering valid JSON exports and error handling for incompatible options have been added to src/test/regress/sql/copy.sql. Author: Joe Conway Author: jian he Co-Authored-By: Andrew Dunstan Reviewed-by: Andrey M. Borodin Reviewed-by: Dean Rasheed Reviewed-by: Daniel Verite Reviewed-by: Davin Shearer Reviewed-by: Masahiko Sawada Reviewed-by: Alvaro Herrera Reviewed-by: Junwang Zhao 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 --- diff --git a/doc/src/sgml/ref/copy.sgml b/doc/src/sgml/ref/copy.sgml index 0ad890ef95f..f9c2717339b 100644 --- a/doc/src/sgml/ref/copy.sgml +++ b/doc/src/sgml/ref/copy.sgml @@ -228,10 +228,31 @@ COPY { table_name [ ( text, csv (Comma Separated Values), + json (JavaScript Object Notation), or binary. The default is text. See below for details. + + The json option is allowed only in + COPY TO. + + + + In JSON format, SQL NULL values are output as + JSON null. However, a JSON or JSONB column + whose value is the JSON literal null is also + output as null, making the two cases + indistinguishable in the COPY output. + For example: + +COPY (SELECT j FROM (VALUES ('null'::json), (NULL::json)) v(j)) + TO stdout (FORMAT JSON); +{"j":null} +{"j":null} + + + @@ -266,7 +287,7 @@ COPY { table_name [ ( CSV format. This must be a single one-byte character. - This option is not allowed when using binary format. + This option is not allowed when using binary or json format. @@ -280,7 +301,7 @@ COPY { table_name [ ( CSV format. You might prefer an empty string even in text format for cases where you don't want to distinguish nulls from empty strings. - This option is not allowed when using binary format. + This option is not allowed when using binary or json format. @@ -303,7 +324,7 @@ COPY { table_name [ ( COPY FROM, and only when - not using binary format. + not using binary or json format. @@ -330,7 +351,7 @@ COPY { table_name [ ( COPY FROM commands. - This option is not allowed when using binary format. + This option is not allowed when using binary or json format. diff --git a/src/backend/commands/copy.c b/src/backend/commands/copy.c index 2f46be516f2..29e22d91ecd 100644 --- a/src/backend/commands/copy.c +++ b/src/backend/commands/copy.c @@ -597,6 +597,8 @@ ProcessCopyOptions(ParseState *pstate, opts_out->format = COPY_FORMAT_CSV; else if (strcmp(fmt, "binary") == 0) opts_out->format = COPY_FORMAT_BINARY; + else if (strcmp(fmt, "json") == 0) + opts_out->format = COPY_FORMAT_JSON; else ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), @@ -756,21 +758,32 @@ ProcessCopyOptions(ParseState *pstate, * Check for incompatible options (must do these three before inserting * defaults) */ - if (opts_out->format == COPY_FORMAT_BINARY && opts_out->delim) + if (opts_out->delim && + (opts_out->format == COPY_FORMAT_BINARY || + opts_out->format == COPY_FORMAT_JSON)) ereport(ERROR, - (errcode(ERRCODE_SYNTAX_ERROR), - /*- translator: %s is the name of a COPY option, e.g. ON_ERROR */ - errmsg("cannot specify %s in BINARY mode", "DELIMITER"))); - - if (opts_out->format == COPY_FORMAT_BINARY && opts_out->null_print) + errcode(ERRCODE_SYNTAX_ERROR), + opts_out->format == COPY_FORMAT_BINARY + ? errmsg("cannot specify %s in BINARY mode", "DELIMITER") + : errmsg("cannot specify %s in JSON mode", "DELIMITER")); + + if (opts_out->null_print && + (opts_out->format == COPY_FORMAT_BINARY || + opts_out->format == COPY_FORMAT_JSON)) ereport(ERROR, - (errcode(ERRCODE_SYNTAX_ERROR), - errmsg("cannot specify %s in BINARY mode", "NULL"))); - - if (opts_out->format == COPY_FORMAT_BINARY && opts_out->default_print) + errcode(ERRCODE_SYNTAX_ERROR), + opts_out->format == COPY_FORMAT_BINARY + ? errmsg("cannot specify %s in BINARY mode", "NULL") + : errmsg("cannot specify %s in JSON mode", "NULL")); + + if (opts_out->default_print && + (opts_out->format == COPY_FORMAT_BINARY || + opts_out->format == COPY_FORMAT_JSON)) ereport(ERROR, - (errcode(ERRCODE_SYNTAX_ERROR), - errmsg("cannot specify %s in BINARY mode", "DEFAULT"))); + errcode(ERRCODE_SYNTAX_ERROR), + opts_out->format == COPY_FORMAT_BINARY + ? errmsg("cannot specify %s in BINARY mode", "DEFAULT") + : errmsg("cannot specify %s in JSON mode", "DEFAULT")); /* Set defaults for omitted options */ if (!opts_out->delim) @@ -836,11 +849,15 @@ ProcessCopyOptions(ParseState *pstate, errmsg("COPY delimiter cannot be \"%s\"", opts_out->delim))); /* Check header */ - if (opts_out->format == COPY_FORMAT_BINARY && opts_out->header_line != COPY_HEADER_FALSE) + if (opts_out->header_line != COPY_HEADER_FALSE && + (opts_out->format == COPY_FORMAT_BINARY || + opts_out->format == COPY_FORMAT_JSON)) ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errcode(ERRCODE_FEATURE_NOT_SUPPORTED), /*- translator: %s is the name of a COPY option, e.g. ON_ERROR */ - errmsg("cannot specify %s in BINARY mode", "HEADER"))); + opts_out->format == COPY_FORMAT_BINARY + ? errmsg("cannot specify %s in BINARY mode", "HEADER") + : errmsg("cannot specify %s in JSON mode", "HEADER")); /* Check quote */ if (opts_out->format != COPY_FORMAT_CSV && opts_out->quote != NULL) @@ -944,6 +961,12 @@ ProcessCopyOptions(ParseState *pstate, errmsg("COPY %s cannot be used with %s", "FREEZE", "COPY TO"))); + /* Check json format */ + if (opts_out->format == COPY_FORMAT_JSON && is_from) + ereport(ERROR, + errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("COPY %s is not supported for %s", "FORMAT JSON", "COPY FROM")); + if (opts_out->default_print) { if (!is_from) diff --git a/src/backend/commands/copyto.c b/src/backend/commands/copyto.c index 3593cb49bf0..489e73be7b4 100644 --- a/src/backend/commands/copyto.c +++ b/src/backend/commands/copyto.c @@ -27,6 +27,7 @@ #include "executor/execdesc.h" #include "executor/executor.h" #include "executor/tuptable.h" +#include "funcapi.h" #include "libpq/libpq.h" #include "libpq/pqformat.h" #include "mb/pg_wchar.h" @@ -34,6 +35,7 @@ #include "pgstat.h" #include "storage/fd.h" #include "tcop/tcopprot.h" +#include "utils/json.h" #include "utils/lsyscache.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -86,6 +88,13 @@ 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? */ + StringInfo json_buf; /* reusable buffer for JSON output, + * initialized in BeginCopyTo */ + TupleDesc tupDesc; /* Descriptor for JSON output; for a column + * list this is a projected descriptor */ + Datum *json_projvalues; /* pre-allocated projection values, or + * NULL */ + bool *json_projnulls; /* pre-allocated projection nulls, or NULL */ copy_data_dest_cb data_dest_cb; /* function for writing data */ CopyFormatOptions opts; @@ -132,6 +141,7 @@ static void CopyToCSVOneRow(CopyToState cstate, TupleTableSlot *slot); static void CopyToTextLikeOneRow(CopyToState cstate, TupleTableSlot *slot, bool is_csv); static void CopyToTextLikeEnd(CopyToState cstate); +static void CopyToJsonOneRow(CopyToState cstate, TupleTableSlot *slot); static void CopyToBinaryStart(CopyToState cstate, TupleDesc tupDesc); static void CopyToBinaryOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo); static void CopyToBinaryOneRow(CopyToState cstate, TupleTableSlot *slot); @@ -150,9 +160,6 @@ static void CopySendInt16(CopyToState cstate, int16 val); /* * COPY TO routines for built-in formats. - * - * CSV and text formats share the same TextLike routines except for the - * one-row callback. */ /* text format */ @@ -171,6 +178,14 @@ static const CopyToRoutine CopyToRoutineCSV = { .CopyToEnd = CopyToTextLikeEnd, }; +/* json format */ +static const CopyToRoutine CopyToRoutineJson = { + .CopyToStart = CopyToTextLikeStart, + .CopyToOutFunc = CopyToTextLikeOutFunc, + .CopyToOneRow = CopyToJsonOneRow, + .CopyToEnd = CopyToTextLikeEnd, +}; + /* binary format */ static const CopyToRoutine CopyToRoutineBinary = { .CopyToStart = CopyToBinaryStart, @@ -187,12 +202,14 @@ CopyToGetRoutine(const CopyFormatOptions *opts) return &CopyToRoutineCSV; else if (opts->format == COPY_FORMAT_BINARY) return &CopyToRoutineBinary; + else if (opts->format == COPY_FORMAT_JSON) + return &CopyToRoutineJson; /* default is text */ return &CopyToRoutineText; } -/* Implementation of the start callback for text and CSV formats */ +/* Implementation of the start callback for text, CSV, and json formats */ static void CopyToTextLikeStart(CopyToState cstate, TupleDesc tupDesc) { @@ -211,6 +228,8 @@ CopyToTextLikeStart(CopyToState cstate, TupleDesc tupDesc) ListCell *cur; bool hdr_delim = false; + Assert(cstate->opts.format != COPY_FORMAT_JSON); + foreach(cur, cstate->attnumlist) { int attnum = lfirst_int(cur); @@ -233,7 +252,7 @@ CopyToTextLikeStart(CopyToState cstate, TupleDesc tupDesc) } /* - * Implementation of the outfunc callback for text and CSV formats. Assign + * Implementation of the outfunc callback for text, CSV, and json formats. Assign * the output function data to the given *finfo. */ static void @@ -306,13 +325,79 @@ CopyToTextLikeOneRow(CopyToState cstate, CopySendTextLikeEndOfRow(cstate); } -/* Implementation of the end callback for text and CSV formats */ +/* Implementation of the end callback for text, CSV, and json formats */ static void CopyToTextLikeEnd(CopyToState cstate) { /* Nothing to do here */ } +/* Implementation of per-row callback for json format */ +static void +CopyToJsonOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + Datum rowdata; + + resetStringInfo(cstate->json_buf); + + if (cstate->json_projvalues != NULL) + { + /* + * Column list case: project selected column values into sequential + * positions matching the custom TupleDesc, then form a new tuple. + */ + HeapTuple tup; + int i = 0; + + foreach_int(attnum, cstate->attnumlist) + { + cstate->json_projvalues[i] = slot->tts_values[attnum - 1]; + cstate->json_projnulls[i] = slot->tts_isnull[attnum - 1]; + i++; + } + + tup = heap_form_tuple(cstate->tupDesc, + cstate->json_projvalues, + cstate->json_projnulls); + + /* + * heap_form_tuple already stamps the datum-length, type-id, and + * type-mod fields on t_data, so we can use it directly as a composite + * Datum without the extra pallocmemcpy that heap_copy_tuple_as_datum + * would do. Any TOAST pointers in the projected values will be + * detoasted by the per-column output functions called from + * composite_to_json. + */ + rowdata = HeapTupleGetDatum(tup); + } + 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. + */ + 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 + rowdata = ExecFetchSlotHeapTupleDatum(slot); + } + + composite_to_json(rowdata, cstate->json_buf, false); + + CopySendData(cstate, cstate->json_buf->data, cstate->json_buf->len); + + CopySendTextLikeEndOfRow(cstate); +} + /* * Implementation of the start callback for binary format. Send a header * for a binary copy. @@ -404,9 +489,23 @@ SendCopyBegin(CopyToState cstate) pq_beginmessage(&buf, PqMsg_CopyOutResponse); pq_sendbyte(&buf, format); /* overall format */ - pq_sendint16(&buf, natts); - for (i = 0; i < natts; i++) - pq_sendint16(&buf, format); /* per-column formats */ + if (cstate->opts.format != COPY_FORMAT_JSON) + { + pq_sendint16(&buf, natts); + for (i = 0; i < natts; i++) + pq_sendint16(&buf, format); /* per-column formats */ + } + else + { + /* + * For JSON format, report one text-format column. Each CopyData + * message contains one complete JSON object, not individual column + * values, so the per-column count is always 1. + */ + pq_sendint16(&buf, 1); + pq_sendint16(&buf, 0); + } + pq_endmessage(&buf); cstate->copy_dest = COPY_FRONTEND; } @@ -508,7 +607,7 @@ CopySendEndOfRow(CopyToState cstate) } /* - * Wrapper function of CopySendEndOfRow for text and CSV formats. Sends the + * Wrapper function of CopySendEndOfRow for text, CSV, and json formats. Sends the * line termination and do common appropriate things for the end of row. */ static inline void @@ -751,6 +850,7 @@ BeginCopyTo(ParseState *pstate, tupDesc = RelationGetDescr(cstate->rel); cstate->partitions = children; + cstate->tupDesc = tupDesc; } else { @@ -887,11 +987,53 @@ BeginCopyTo(ParseState *pstate, ExecutorStart(cstate->queryDesc, 0); tupDesc = cstate->queryDesc->tupDesc; + tupDesc = BlessTupleDesc(tupDesc); + cstate->tupDesc = tupDesc; } /* Generate or convert list of attributes to process */ cstate->attnumlist = CopyGetAttnums(tupDesc, cstate->rel, attnamelist); + /* Set up JSON-specific state */ + if (cstate->opts.format == COPY_FORMAT_JSON) + { + cstate->json_buf = makeStringInfo(); + + if (attnamelist != NIL && rel) + { + int natts = list_length(cstate->attnumlist); + TupleDesc resultDesc; + + /* + * Build a TupleDesc describing only the selected columns so that + * composite_to_json() emits the right column names and types. + */ + resultDesc = CreateTemplateTupleDesc(natts); + + foreach_int(attnum, cstate->attnumlist) + { + Form_pg_attribute attr = TupleDescAttr(tupDesc, attnum - 1); + + TupleDescInitEntry(resultDesc, + foreach_current_index(attnum) + 1, + NameStr(attr->attname), + attr->atttypid, + attr->atttypmod, + attr->attndims); + } + + TupleDescFinalize(resultDesc); + cstate->tupDesc = BlessTupleDesc(resultDesc); + + /* + * Pre-allocate arrays for projecting selected column values into + * sequential positions matching the custom TupleDesc. + */ + cstate->json_projvalues = palloc_array(Datum, natts); + cstate->json_projnulls = palloc_array(bool, natts); + } + } + num_phys_attrs = tupDesc->natts; /* Convert FORCE_QUOTE name list to per-column flags, check validity */ diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y index 92ded5307b3..0fea726cdd5 100644 --- a/src/backend/parser/gram.y +++ b/src/backend/parser/gram.y @@ -3650,6 +3650,10 @@ copy_opt_item: { $$ = makeDefElem("format", (Node *) makeString("csv"), @1); } + | JSON + { + $$ = makeDefElem("format", (Node *) makeString("json"), @1); + } | HEADER_P { $$ = makeDefElem("header", (Node *) makeBoolean(true), @1); @@ -3732,6 +3736,10 @@ copy_generic_opt_elem: { $$ = makeDefElem($1, $2, @1); } + | FORMAT_LA copy_generic_opt_arg + { + $$ = makeDefElem("format", $2, @1); + } ; copy_generic_opt_arg: diff --git a/src/backend/utils/adt/json.c b/src/backend/utils/adt/json.c index ae73c64fbb5..0fee1b40d63 100644 --- a/src/backend/utils/adt/json.c +++ b/src/backend/utils/adt/json.c @@ -86,8 +86,6 @@ typedef struct JsonAggState JsonUniqueBuilderState unique_check; } JsonAggState; -static void composite_to_json(Datum composite, StringInfo result, - bool use_line_feeds); static void array_dim_to_json(StringInfo result, int dim, int ndims, int *dims, const Datum *vals, const bool *nulls, int *valcount, JsonTypeCategory tcategory, Oid outfuncoid, @@ -517,8 +515,9 @@ array_to_json_internal(Datum array, StringInfo result, bool use_line_feeds) /* * Turn a composite / record into JSON. + * Exported so COPY TO can use it. */ -static void +void composite_to_json(Datum composite, StringInfo result, bool use_line_feeds) { HeapTupleHeader td; diff --git a/src/bin/psql/tab-complete.in.c b/src/bin/psql/tab-complete.in.c index 2f674764cad..b6cbb077326 100644 --- a/src/bin/psql/tab-complete.in.c +++ b/src/bin/psql/tab-complete.in.c @@ -3461,7 +3461,7 @@ match_previous_words(int pattern_id, /* Complete COPY FROM|TO filename WITH (FORMAT */ else if (TailMatches("FORMAT")) - COMPLETE_WITH("binary", "csv", "text"); + COMPLETE_WITH("binary", "csv", "text", "json"); /* Complete COPY FROM|TO filename WITH (FREEZE */ else if (TailMatches("FREEZE")) diff --git a/src/include/commands/copy.h b/src/include/commands/copy.h index 2430fb0b2e5..2b5bef6738e 100644 --- a/src/include/commands/copy.h +++ b/src/include/commands/copy.h @@ -57,6 +57,7 @@ typedef enum CopyFormat COPY_FORMAT_TEXT = 0, COPY_FORMAT_BINARY, COPY_FORMAT_CSV, + COPY_FORMAT_JSON, } CopyFormat; /* diff --git a/src/include/utils/json.h b/src/include/utils/json.h index f8cc52b1e78..2f4be40518d 100644 --- a/src/include/utils/json.h +++ b/src/include/utils/json.h @@ -17,6 +17,8 @@ #include "lib/stringinfo.h" /* functions in json.c */ +extern void composite_to_json(Datum composite, StringInfo result, + bool use_line_feeds); extern void escape_json(StringInfo buf, const char *str); extern void escape_json_with_len(StringInfo buf, const char *str, int len); extern void escape_json_text(StringInfo buf, const text *txt); diff --git a/src/test/regress/expected/copy.out b/src/test/regress/expected/copy.out index d0d563e0fa8..7f2d2e065f6 100644 --- a/src/test/regress/expected/copy.out +++ b/src/test/regress/expected/copy.out @@ -73,6 +73,152 @@ copy copytest3 to stdout csv header; c1,"col with , comma","col with "" quote" 1,a,1 2,b,2 +--- test copying in JSON mode with various styles +copy (select 1 union all select 2) to stdout with (format json); +{"?column?":1} +{"?column?":2} +copy (select 1 as foo union all select 2) to stdout with (format json); +{"foo":1} +{"foo":2} +copy (values (1), (2)) TO stdout with (format json); +{"column1":1} +{"column1":2} +copy copytest to stdout json; +{"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); +{"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 (select * from copytest) to stdout (format json); +{"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} +-- all of the following should yield error +copy copytest to stdout (format json, delimiter '|'); +ERROR: cannot specify DELIMITER in JSON mode +copy copytest to stdout (format json, null '\N'); +ERROR: cannot specify NULL in JSON mode +copy copytest to stdout (format json, default '|'); +ERROR: cannot specify DEFAULT in JSON mode +copy copytest to stdout (format json, header); +ERROR: cannot specify HEADER in JSON mode +copy copytest to stdout (format json, header 1); +ERROR: cannot specify HEADER in JSON mode +copy copytest to stdout (format json, quote '"'); +ERROR: COPY QUOTE requires CSV mode +copy copytest to stdout (format json, escape '"'); +ERROR: COPY ESCAPE requires CSV mode +copy copytest to stdout (format json, force_quote *); +ERROR: COPY FORCE_QUOTE requires CSV mode +copy copytest to stdout (format json, force_not_null *); +ERROR: COPY FORCE_NOT_NULL requires CSV mode +copy copytest to stdout (format json, force_null *); +ERROR: COPY FORCE_NULL requires CSV mode +copy copytest to stdout (format json, on_error ignore); +ERROR: COPY ON_ERROR cannot be used with COPY TO +LINE 1: copy copytest to stdout (format json, on_error ignore); + ^ +copy copytest to stdout (format json, reject_limit 1); +ERROR: COPY REJECT_LIMIT requires ON_ERROR to be set to IGNORE +copy copytest from stdin(format json); +ERROR: COPY FORMAT JSON is not supported for COPY FROM +-- all of the above should yield error +-- column list with json format +copy copytest (style, test, filler) to stdout (format json); +{"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} +-- column list with diverse data types +create temp table copyjsontest_types ( + id int, + js json, + jsb jsonb, + arr int[], + n numeric(10,2), + b boolean, + ts timestamp, + t text); +insert into copyjsontest_types values +(1, '{"a":1}', '{"b":2}', '{1,2,3}', 3.14, true, + '2024-01-15 10:30:00', 'hello'), +(2, '[1,null,"x"]', '{"nested":{"k":"v"}}', '{4,5}', -99.99, false, + '2024-06-30 23:59:59', 'world'), +(3, 'null', 'null', '{}', null, null, null, null); +-- full table +copy copyjsontest_types to stdout (format json); +{"id":1,"js":{"a":1},"jsb":{"b": 2},"arr":[1,2,3],"n":3.14,"b":true,"ts":"2024-01-15T10:30:00","t":"hello"} +{"id":2,"js":[1,null,"x"],"jsb":{"nested": {"k": "v"}},"arr":[4,5],"n":-99.99,"b":false,"ts":"2024-06-30T23:59:59","t":"world"} +{"id":3,"js":null,"jsb":null,"arr":[],"n":null,"b":null,"ts":null,"t":null} +-- column subsets exercising each type +copy copyjsontest_types (id, js, jsb) to stdout (format json); +{"id":1,"js":{"a":1},"jsb":{"b": 2}} +{"id":2,"js":[1,null,"x"],"jsb":{"nested": {"k": "v"}}} +{"id":3,"js":null,"jsb":null} +copy copyjsontest_types (id, arr, n, b) to stdout (format json); +{"id":1,"arr":[1,2,3],"n":3.14,"b":true} +{"id":2,"arr":[4,5],"n":-99.99,"b":false} +{"id":3,"arr":[],"n":null,"b":null} +copy copyjsontest_types (jsb, t) to stdout (format json); +{"jsb":{"b": 2},"t":"hello"} +{"jsb":{"nested": {"k": "v"}},"t":"world"} +{"jsb":null,"t":null} +copy copyjsontest_types (id, ts) to stdout (format json); +{"id":1,"ts":"2024-01-15T10:30:00"} +{"id":2,"ts":"2024-06-30T23:59:59"} +{"id":3,"ts":null} +-- single column: json and jsonb +copy copyjsontest_types (js) to stdout (format json); +{"js":{"a":1}} +{"js":[1,null,"x"]} +{"js":null} +copy copyjsontest_types (jsb) to stdout (format json); +{"jsb":{"b": 2}} +{"jsb":{"nested": {"k": "v"}}} +{"jsb":null} +drop table copyjsontest_types; +-- embedded escaped characters +create temp table copyjsontest ( + id bigserial, + f1 text, + f2 timestamptz); +insert into copyjsontest + select g.i, + CASE WHEN g.i % 2 = 0 THEN + 'line with '' in it: ' || g.i::text + ELSE + 'line with " in it: ' || g.i::text + END, + 'Mon Feb 10 17:32:01 1997 PST' + from generate_series(1,5) as g(i); +insert into copyjsontest (f1) values +(E'aaa\"bbb'::text), +(E'aaa\\bbb'::text), +(E'aaa\/bbb'::text), +(E'aaa\bbbb'::text), +(E'aaa\fbbb'::text), +(E'aaa\nbbb'::text), +(E'aaa\rbbb'::text), +(E'aaa\tbbb'::text); +copy copyjsontest to stdout json; +{"id":1,"f1":"line with \" in it: 1","f2":"1997-02-10T17:32:01-08:00"} +{"id":2,"f1":"line with ' in it: 2","f2":"1997-02-10T17:32:01-08:00"} +{"id":3,"f1":"line with \" in it: 3","f2":"1997-02-10T17:32:01-08:00"} +{"id":4,"f1":"line with ' in it: 4","f2":"1997-02-10T17:32:01-08:00"} +{"id":5,"f1":"line with \" in it: 5","f2":"1997-02-10T17:32:01-08:00"} +{"id":1,"f1":"aaa\"bbb","f2":null} +{"id":2,"f1":"aaa\\bbb","f2":null} +{"id":3,"f1":"aaa/bbb","f2":null} +{"id":4,"f1":"aaa\bbbb","f2":null} +{"id":5,"f1":"aaa\fbbb","f2":null} +{"id":6,"f1":"aaa\nbbb","f2":null} +{"id":7,"f1":"aaa\rbbb","f2":null} +{"id":8,"f1":"aaa\tbbb","f2":null} create temp table copytest4 ( c1 int, "colname with tab: " text); diff --git a/src/test/regress/sql/copy.sql b/src/test/regress/sql/copy.sql index 65cbdaf7f3e..404f4321085 100644 --- a/src/test/regress/sql/copy.sql +++ b/src/test/regress/sql/copy.sql @@ -82,6 +82,94 @@ this is just a line full of junk that would error out if parsed 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 (select 1 as foo union all select 2) to stdout with (format json); +copy (values (1), (2)) TO stdout with (format json); +copy copytest to stdout json; +copy copytest to stdout (format json); +copy (select * from copytest) 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'); +copy copytest to stdout (format json, default '|'); +copy copytest to stdout (format json, header); +copy copytest to stdout (format json, header 1); +copy copytest to stdout (format json, quote '"'); +copy copytest to stdout (format json, escape '"'); +copy copytest to stdout (format json, force_quote *); +copy copytest to stdout (format json, force_not_null *); +copy copytest to stdout (format json, force_null *); +copy copytest to stdout (format json, on_error ignore); +copy copytest to stdout (format json, reject_limit 1); +copy copytest from stdin(format json); +-- all of the above should yield error + +-- column list with json format +copy copytest (style, test, filler) to stdout (format json); + +-- column list with diverse data types +create temp table copyjsontest_types ( + id int, + js json, + jsb jsonb, + arr int[], + n numeric(10,2), + b boolean, + ts timestamp, + t text); + +insert into copyjsontest_types values +(1, '{"a":1}', '{"b":2}', '{1,2,3}', 3.14, true, + '2024-01-15 10:30:00', 'hello'), +(2, '[1,null,"x"]', '{"nested":{"k":"v"}}', '{4,5}', -99.99, false, + '2024-06-30 23:59:59', 'world'), +(3, 'null', 'null', '{}', null, null, null, null); + +-- full table +copy copyjsontest_types to stdout (format json); + +-- column subsets exercising each type +copy copyjsontest_types (id, js, jsb) to stdout (format json); +copy copyjsontest_types (id, arr, n, b) to stdout (format json); +copy copyjsontest_types (jsb, t) to stdout (format json); +copy copyjsontest_types (id, ts) to stdout (format json); + +-- single column: json and jsonb +copy copyjsontest_types (js) to stdout (format json); +copy copyjsontest_types (jsb) to stdout (format json); + +drop table copyjsontest_types; + +-- embedded escaped characters +create temp table copyjsontest ( + id bigserial, + f1 text, + f2 timestamptz); + +insert into copyjsontest + select g.i, + CASE WHEN g.i % 2 = 0 THEN + 'line with '' in it: ' || g.i::text + ELSE + 'line with " in it: ' || g.i::text + END, + 'Mon Feb 10 17:32:01 1997 PST' + from generate_series(1,5) as g(i); + +insert into copyjsontest (f1) values +(E'aaa\"bbb'::text), +(E'aaa\\bbb'::text), +(E'aaa\/bbb'::text), +(E'aaa\bbbb'::text), +(E'aaa\fbbb'::text), +(E'aaa\nbbb'::text), +(E'aaa\rbbb'::text), +(E'aaa\tbbb'::text); + +copy copyjsontest to stdout json; + create temp table copytest4 ( c1 int, "colname with tab: " text);