From 1c9034579c026562ae6db5a3f2d3a7678653b9ff Mon Sep 17 00:00:00 2001 From: Tom Lane Date: Tue, 11 Jun 2019 13:33:08 -0400 Subject: [PATCH] Fix conversion of JSON strings to JSON output columns in json_to_record(). json_to_record(), when an output column is declared as type json or jsonb, should emit the corresponding field of the input JSON object. But it got this slightly wrong when the field is just a string literal: it failed to escape the contents of the string. That typically resulted in syntax errors if the string contained any double quotes or backslashes. jsonb_to_record() handles such cases correctly, but I added corresponding test cases for it too, to prevent future backsliding. Improve the documentation, as it provided only a very hand-wavy description of the conversion rules used by these functions. Per bug report from Robert Vollmert. Back-patch to v10 where the error was introduced (by commit cf35346e8). Note that PG 9.4 - 9.6 also get this case wrong, but differently so: they feed the de-escaped contents of the string literal to json[b]_in. That behavior is less obviously wrong, so possibly it's being depended on in the field, so I won't risk trying to make the older branches behave like the newer ones. Discussion: https://postgr.es/m/D6921B37-BD8E-4664-8D5F-DB3525765DCD@vllmrt.net --- doc/src/sgml/func.sgml | 87 +++++++++++++++++++++-------- src/backend/utils/adt/jsonfuncs.c | 37 ++++++------ src/test/regress/expected/json.out | 36 ++++++++++++ src/test/regress/expected/jsonb.out | 36 ++++++++++++ src/test/regress/sql/json.sql | 7 +++ src/test/regress/sql/jsonb.sql | 7 +++ 6 files changed, 167 insertions(+), 43 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index 21164038a5..cfa1e781ac 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -12006,29 +12006,72 @@ table2-mapping - - While the examples for the functions - json_populate_record, - json_populate_recordset, - json_to_record and - json_to_recordset use constants, the typical use - would be to reference a table in the FROM clause - and use one of its json or jsonb columns - as an argument to the function. Extracted key values can then be - referenced in other parts of the query, like WHERE - clauses and target lists. Extracting multiple values in this - way can improve performance over extracting them separately with - per-key operators. - + + The functions + json[b]_populate_record, + json[b]_populate_recordset, + json[b]_to_record and + json[b]_to_recordset + operate on a JSON object, or array of objects, and extract the values + associated with keys whose names match column names of the output row + type. + Object fields that do not correspond to any output column name are + ignored, and output columns that do not match any object field will be + filled with nulls. + To convert a JSON value to the SQL type of an output column, the + following rules are applied in sequence: + + + + A JSON null value is converted to a SQL null in all cases. + + + + + If the output column is of type json + or jsonb, the JSON value is just reproduced exactly. + + + + + If the output column is a composite (row) type, and the JSON value is + a JSON object, the fields of the object are converted to columns of + the output row type by recursive application of these rules. + + + + + Likewise, if the output column is an array type and the JSON value is + a JSON array, the elements of the JSON array are converted to elements + of the output array by recursive application of these rules. + + + + + Otherwise, if the JSON value is a string literal, the contents of the + string are fed to the input conversion function for the column's data + type. + + + + + Otherwise, the ordinary text representation of the JSON value is fed + to the input conversion function for the column's data type. + + + + - - JSON keys are matched to identical column names in the target - row type. JSON type coercion for these functions is best - effort and may not result in desired values for some types. - JSON fields that do not appear in the target row type will be - omitted from the output, and target columns that do not match any - JSON field will simply be NULL. - + + While the examples for these functions use constants, the typical use + would be to reference a table in the FROM clause + and use one of its json or jsonb columns + as an argument to the function. Extracted key values can then be + referenced in other parts of the query, like WHERE + clauses and target lists. Extracting multiple values in this + way can improve performance over extracting them separately with + per-key operators. + diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5c3f2fb9f6..17de89d69c 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -2803,26 +2803,7 @@ populate_scalar(ScalarIOData *io, Oid typid, int32 typmod, JsValue *jsv) json = jsv->val.json.str; Assert(json); - - /* already done the hard work in the json case */ - if ((typid == JSONOID || typid == JSONBOID) && - jsv->val.json.type == JSON_TOKEN_STRING) - { - /* - * Add quotes around string value (should be already escaped) if - * converting to json/jsonb. - */ - - if (len < 0) - len = strlen(json); - - str = palloc(len + sizeof(char) * 3); - str[0] = '"'; - memcpy(&str[1], json, len); - str[len + 1] = '"'; - str[len + 2] = '\0'; - } - else if (len >= 0) + if (len >= 0) { /* Need to copy non-null-terminated string */ str = palloc(len + 1 * sizeof(char)); @@ -2830,7 +2811,21 @@ populate_scalar(ScalarIOData *io, Oid typid, int32 typmod, JsValue *jsv) str[len] = '\0'; } else - str = json; /* null-terminated string */ + str = json; /* string is already null-terminated */ + + /* If converting to json/jsonb, make string into valid JSON literal */ + if ((typid == JSONOID || typid == JSONBOID) && + jsv->val.json.type == JSON_TOKEN_STRING) + { + StringInfoData buf; + + initStringInfo(&buf); + escape_json(&buf, str); + /* free temporary buffer */ + if (str != json) + pfree(str); + str = buf.data; + } } else { diff --git a/src/test/regress/expected/json.out b/src/test/regress/expected/json.out index ea1be61eff..a68bf72b31 100644 --- a/src/test/regress/expected/json.out +++ b/src/test/regress/expected/json.out @@ -2276,6 +2276,42 @@ select * from json_to_record('{"ia2": [[[1], [2], [3]]]}') as x(ia2 int4[][]); {{{1},{2},{3}}} (1 row) +select * from json_to_record('{"out": {"key": 1}}') as x(out json); + out +------------ + {"key": 1} +(1 row) + +select * from json_to_record('{"out": [{"key": 1}]}') as x(out json); + out +-------------- + [{"key": 1}] +(1 row) + +select * from json_to_record('{"out": "{\"key\": 1}"}') as x(out json); + out +---------------- + "{\"key\": 1}" +(1 row) + +select * from json_to_record('{"out": {"key": 1}}') as x(out jsonb); + out +------------ + {"key": 1} +(1 row) + +select * from json_to_record('{"out": [{"key": 1}]}') as x(out jsonb); + out +-------------- + [{"key": 1}] +(1 row) + +select * from json_to_record('{"out": "{\"key\": 1}"}') as x(out jsonb); + out +---------------- + "{\"key\": 1}" +(1 row) + -- json_strip_nulls select json_strip_nulls(null); json_strip_nulls diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 4fddd2de14..3dfd626c41 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -2652,6 +2652,42 @@ select * from jsonb_to_record('{"ia2": [[[1], [2], [3]]]}') as x(ia2 int4[][]); {{{1},{2},{3}}} (1 row) +select * from jsonb_to_record('{"out": {"key": 1}}') as x(out json); + out +------------ + {"key": 1} +(1 row) + +select * from jsonb_to_record('{"out": [{"key": 1}]}') as x(out json); + out +-------------- + [{"key": 1}] +(1 row) + +select * from jsonb_to_record('{"out": "{\"key\": 1}"}') as x(out json); + out +---------------- + "{\"key\": 1}" +(1 row) + +select * from jsonb_to_record('{"out": {"key": 1}}') as x(out jsonb); + out +------------ + {"key": 1} +(1 row) + +select * from jsonb_to_record('{"out": [{"key": 1}]}') as x(out jsonb); + out +-------------- + [{"key": 1}] +(1 row) + +select * from jsonb_to_record('{"out": "{\"key\": 1}"}') as x(out jsonb); + out +---------------- + "{\"key\": 1}" +(1 row) + -- test type info caching in jsonb_populate_record() CREATE TEMP TABLE jsbpoptest (js jsonb); INSERT INTO jsbpoptest diff --git a/src/test/regress/sql/json.sql b/src/test/regress/sql/json.sql index d1e4008427..184c5029e9 100644 --- a/src/test/regress/sql/json.sql +++ b/src/test/regress/sql/json.sql @@ -742,6 +742,13 @@ select * from json_to_record('{"ia2": [1, 2, 3]}') as x(ia2 int[][]); select * from json_to_record('{"ia2": [[1, 2], [3, 4]]}') as x(ia2 int4[][]); select * from json_to_record('{"ia2": [[[1], [2], [3]]]}') as x(ia2 int4[][]); +select * from json_to_record('{"out": {"key": 1}}') as x(out json); +select * from json_to_record('{"out": [{"key": 1}]}') as x(out json); +select * from json_to_record('{"out": "{\"key\": 1}"}') as x(out json); +select * from json_to_record('{"out": {"key": 1}}') as x(out jsonb); +select * from json_to_record('{"out": [{"key": 1}]}') as x(out jsonb); +select * from json_to_record('{"out": "{\"key\": 1}"}') as x(out jsonb); + -- json_strip_nulls select json_strip_nulls(null); diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 6cbdfe4395..227f1fcd27 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -709,6 +709,13 @@ select * from jsonb_to_record('{"ia2": [1, 2, 3]}') as x(ia2 int[][]); select * from jsonb_to_record('{"ia2": [[1, 2], [3, 4]]}') as x(ia2 int4[][]); select * from jsonb_to_record('{"ia2": [[[1], [2], [3]]]}') as x(ia2 int4[][]); +select * from jsonb_to_record('{"out": {"key": 1}}') as x(out json); +select * from jsonb_to_record('{"out": [{"key": 1}]}') as x(out json); +select * from jsonb_to_record('{"out": "{\"key\": 1}"}') as x(out json); +select * from jsonb_to_record('{"out": {"key": 1}}') as x(out jsonb); +select * from jsonb_to_record('{"out": [{"key": 1}]}') as x(out jsonb); +select * from jsonb_to_record('{"out": "{\"key\": 1}"}') as x(out jsonb); + -- test type info caching in jsonb_populate_record() CREATE TEMP TABLE jsbpoptest (js jsonb);