如何使用动态SQL设置复合变量字段的值

时间：2011-10-10 10:25:40

标签： postgresql stored-procedures types composite plpgsql

鉴于此类型：

-- Just for testing purposes:
CREATE TYPE testType as (name text)

我可以使用此函数动态获取字段的值：

CREATE OR REPLACE FUNCTION get_field(object anyelement, field text) RETURNS text as
$BODY$
DECLARE
    value text;
BEGIN
    EXECUTE 'SELECT $1."' || field || '"'
      USING object
       INTO value;

    return value;
END;
$BODY$
LANGUAGE plpgsql

调用get_field('(david)'::testType, 'name')按预期工作，返回“david”。

但是如何在复合类型中设置字段的值？我试过这些功能：

CREATE OR REPLACE FUNCTION set_field_try1(object anyelement, field text, value text)
RETURNS anyelement
as
$BODY$
DECLARE
    value text;
BEGIN
    EXECUTE '$1."' || field || '" := $2'
      USING object, value;

    return object;
END;
$BODY$
LANGUAGE plpgsql

CREATE OR REPLACE FUNCTION set_field_try2(object anyelement, field text, value text)
RETURNS anyelement
as
$BODY$
DECLARE
    value text;
BEGIN
    EXECUTE 'SELECT $1 INTO $2."' || field || '"'
      USING value, object;

    return object;
END;
$BODY$
LANGUAGE plpgsql

CREATE OR REPLACE FUNCTION set_field_try3(object anyelement, field text, value text)
RETURNS anyelement
as
$BODY$
DECLARE
    value text;
BEGIN
    EXECUTE 'BEGIN $1."' || field || '" := $2; SELECT $1; END;'
       INTO object
      USING value, object;

    return object;
END;
$BODY$
LANGUAGE plpgsql

和一些变化。 调用set_field_tryX不起作用。我总是得到“错误：语法错误在...附近”。 我怎么能做到这一点？

注意：

  • 参数为anyelement，字段可以是复合类型中的任何字段。我不能只使用object.name。
  • 我关注SQL注入。任何建议都会受到赞赏，但这不是我的问题。

6 个答案:

答案 0 :(得分：13)

hstore

更快

由于Postgres 9.0 ，数据库中安装了additional module hstore，因此#= operator有一个非常简单快速的解决方案...

  

将record中的[s]字段替换为hstore的匹配值。

安装模块：

CREATE EXTENSION hstore;

示例：

SELECT my_record #= '"field"=>"value"'::hstore;  -- with string literal
SELECT my_record #= hstore(field, value);        -- with values

显然，必须将值转换为text并返回。

示例plpgsql函数以及更多详细信息：

json

几乎一样快

在Postgres中有类似的，但目前未记录的（如第9.5页）解决方案json（第9.3+页）或jsonb（第9.4+页），所以你没有需要一个额外的模块。

See @Geir's added answer for details.

没有hstore和json

如果您使用的是旧版本或无法安装附加模块hstore或无法假设已安装，则以下是我之前发布的改进版本。但仍然比hstore运算符慢：

CREATE OR REPLACE FUNCTION f_setfield(INOUT _comp_val anyelement
                                          , _field text, _val text)
  RETURNS anyelement AS
$func$
BEGIN

EXECUTE 'SELECT ' || array_to_string(ARRAY(
      SELECT CASE WHEN attname = _field
                THEN '$2'
                ELSE '($1).' || quote_ident(attname)
             END AS fld
      FROM   pg_catalog.pg_attribute
      WHERE  attrelid = pg_typeof(_comp_val)::text::regclass
      AND    attnum > 0
      AND    attisdropped = FALSE
      ORDER  BY attnum
      ), ',')
USING  _comp_val, _val
INTO   _comp_val;

END
$func$ LANGUAGE plpgsql STABLE;

呼叫：

CREATE TEMP TABLE t( a int, b text);  -- Composite type for testing
SELECT f_setfield(NULL::t, 'a', '1');

注释

  • 不需要将值_val显式转换为目标数据类型，动态查询中的字符串文字将自动强制转换，从而避免pg_type上的子查询。但我更进了一步：

  • 通过quote_literal(_val)子句将USING替换为直接值插入。保存一个函数调用和两个强制转换，无论如何都更安全。 text在现代PostgreSQL中自动强制转换为目标类型。 （未使用9.1之前的版本进行测试。）

  • array_to_string(ARRAY())比string_agg()快。

  • 无需变量，无DECLARE。分配较少。

  • 动态SQL中没有子查询。 ($1).field更快。

  • pg_typeof(_comp_val)::text::regclass
    和
    一样 (SELECT typrelid FROM pg_catalog.pg_type WHERE oid = pg_typeof($1)::oid)
    对于有效的复合类型，只需更快 最后一个修改是基于pg_type.typname始终与注册的复合类型的关联pg_class.relname相同的假设，并且双重转换可以替换子查询。我在一个大型数据库中运行此测试以进行验证，并且它按预期显示为空：

    SELECT *
FROM   pg_catalog.pg_type t
JOIN   pg_namespace  n ON n.oid = t.typnamespace
WHERE  t.typrelid > 0  -- exclude non-composite types
AND    t.typrelid IS DISTINCT FROM
      (quote_ident(n.nspname ) || '.' || quote_ident(typname))::regclass

  • 使用INOUT参数无需显式RETURN。这只是一个符号捷径。帕维尔不喜欢它，他更喜欢明确的RETURN声明......

将所有内容放在一起几乎是之前版本的两倍。

原创（过时）答案：

结果是版本〜2.25倍。但是如果没有Pavel的第二个版本，我可能无法做到。

此外，此版本通过在单个查询中执行所有内容来避免大部分投射文本和后退，因此它应该更不容易出错。
使用 PostgreSQL 9.0和9.1 进行测试。

CREATE FUNCTION f_setfield(_comp_val anyelement, _field text, _val text)
  RETURNS anyelement AS
$func$
DECLARE
   _list text;
BEGIN
_list := (
   SELECT string_agg(x.fld, ',')
   FROM  (
      SELECT CASE WHEN a.attname = $2
              THEN quote_literal($3) || '::'|| (SELECT quote_ident(typname)
                                                FROM   pg_catalog.pg_type
                                                WHERE  oid = a.atttypid)
              ELSE quote_ident(a.attname)
             END AS fld
      FROM   pg_catalog.pg_attribute a 
      WHERE  a.attrelid = (SELECT typrelid
                           FROM   pg_catalog.pg_type
                           WHERE  oid = pg_typeof($1)::oid)
      AND    a.attnum > 0
      AND    a.attisdropped = false
      ORDER  BY a.attnum
      ) x
   );

EXECUTE 'SELECT ' || _list || ' FROM  (SELECT $1.*) x'
USING  $1
INTO   $1;

RETURN $1;
END
$func$ LANGUAGE plpgsql STABLE;

答案 1 :(得分：7)

我写了第二版的setfield函数。它适用于 postgres 9.1 我没有在旧版本上测试它。这不是一个奇迹（从性能角度来看），但它更强大，比以前快8倍。

CREATE OR REPLACE FUNCTION public.setfield2(anyelement, text, text)
 RETURNS anyelement
 LANGUAGE plpgsql
AS $function$
DECLARE 
  _name text;
  _values text[];
  _value text;
  _attnum int;
BEGIN
  FOR _name, _attnum
     IN SELECT a.attname, a.attnum
          FROM pg_catalog.pg_attribute a 
         WHERE a.attrelid = (SELECT typrelid
                               FROM pg_type
                              WHERE oid = pg_typeof($1)::oid)
           AND a.attnum > 0 
  LOOP
    IF _name = $2 THEN
      _value := $3;
    ELSE
      EXECUTE 'SELECT (($1).' || quote_ident(_name) || ')::text' INTO _value USING $1;
    END IF;
    _values[_attnum] :=  COALESCE('"' || replace(replace(_value, '"', '""'), '''', '''''') || '"', ''); 
  END LOOP;
  EXECUTE 'SELECT (' || quote_ident(pg_typeof($1)::text) || ' ''(' || array_to_string(_values,',') || ')'').*' INTO $1; 
  RETURN $1;
END;
$function$;

答案 2 :(得分：4)

更新/警告： Erwin指出这是currently undocumented，manual表示不应该以这种方式更改记录。

请改用hstore或Pavel's solution。

这个简单的基于json的解决方案几乎和hstore一样快，只需要Postgres 9.3 或更新。如果您不能使用hstore扩展，这应该是一个不错的选择，并且性能差异应该可以忽略不计。基准：https://stackoverflow.com/a/28673542/1914376

a）我们可以通过cast / concat进行内联。 Json函数需要Postgres 9.3：

SELECT json_populate_record( 
     record
    , ('{"'||'key'||'":"'||'new-value'||'"}')::json
);

b）或使用Postgres 9.4 中的函数进行内联。 

SELECT json_populate_record (
      record
     ,json_object(ARRAY['key', 'new-value'])
);

注意：我选择了json_object（ARRAY [key，value]），因为它比json_build_object（key，value）快一点：

要隐藏投射细节，您可以在函数中使用a），而且开销很小。

CREATE FUNCTION x.setfield_json(in_element anyelement, key text, value text)
    RETURNS anyelement AS
$BODY$
    SELECT json_populate_record( in_element, ('{"'||key||'":"'||value||'"}')::json);
$BODY$ LANGUAGE sql;

答案 3 :(得分：3)

“SELECT INTO”在plpgsql之外（在动态SQL上下文中）有不同的意义 - 它将查询结果存储到表中。

可以修改任何字段，但不是简单

CREATE OR REPLACE FUNCTION public.setfield(a anyelement, text, text)
RETURNS anyelement
LANGUAGE plpgsql
AS $function$
begin
  create temp table aux as select $1.*;
  execute 'update aux set ' || quote_ident($2) || ' = ' || quote_literal($3);
  select into $1 * from aux;
  drop table aux;
  return $1;
end;
$function$

但是这段代码不是很有效 - 不可能在plpgsql中写得好。你可以找到一些应该做的C库。

答案 4 :(得分：1)

2015年3月更新：
现在已经过时了。考虑具有更快变体的new benchmark by @Geir。

测试设置和基准

我采用了三种解决方案（截至2011年10月16日）并在PostgreSQL 9.0上进行了测试。 您可以在下面找到完整的设置。由于我使用的是真实数据库（非合成数据），因此不包括测试数据。它全部封装在自己的模式中，用于非侵入式使用。

我想鼓励任何想要重现测试的人。也许与postgres 9.1？并在此处添加结果？ ：）

-- DROP SCHEMA x CASCADE;
CREATE SCHEMA x;

-- Pavel 1
CREATE OR REPLACE FUNCTION x.setfield(anyelement, text, text)
RETURNS anyelement
LANGUAGE plpgsql
AS $function$
begin
  create temp table aux as select $1.*;
  execute 'update aux set ' || quote_ident($2) || ' = ' || quote_literal($3);
  select into $1 * from aux;
  drop table aux;
  return $1;
end;
$function$;

-- Pavel 2 (with patches)
CREATE OR REPLACE FUNCTION x.setfield2(anyelement, text, text)
 RETURNS anyelement
 LANGUAGE plpgsql
AS $function$
DECLARE 
  _name text;
  _values text[];
  _value text;
  _attnum int;
BEGIN
  FOR _name, _attnum
     IN SELECT a.attname, a.attnum
           FROM pg_catalog.pg_attribute a 
          WHERE a.attrelid = (SELECT typrelid
                                 FROM pg_type
                                WHERE oid = pg_typeof($1)::oid) 
  LOOP
    IF _name = $2 THEN
      _value := $3;
    ELSE
      EXECUTE 'SELECT (($1).' || quote_ident(_name) || ')::text' INTO _value USING $1;
    END IF;
    _values[_attnum] :=  COALESCE('"' || replace(replace(_value, '"', '""'), '''', '''''') || '"', '');
  END LOOP;
  EXECUTE 'SELECT (' || pg_typeof($1)::text || '''(' || array_to_string(_values,',') || ')'').*' INTO $1; 
  RETURN $1;
END;
$function$;

-- Erwin 1
CREATE OR REPLACE FUNCTION x.setfield3(anyelement, text, text)
RETURNS anyelement
AS $body$
DECLARE
 _list text;

BEGIN
_list := (
   SELECT string_agg(x.fld, ',')
   FROM   (
      SELECT CASE WHEN a.attname = $2
              THEN quote_literal($3)
              ELSE quote_ident(a.attname)
             END AS fld
      FROM   pg_catalog.pg_attribute a 
      WHERE  a.attrelid = (SELECT typrelid
                           FROM   pg_type
                           WHERE  oid = pg_typeof($1)::oid) 
      ORDER BY a.attnum
   ) x
);

EXECUTE '
SELECT ' || _list || '
FROM   (SELECT $1.*) x'
USING  $1
INTO   $1;

RETURN $1;
END;
$body$ LANGUAGE plpgsql;

-- composite type for tests.
CREATE TYPE x.t_f as (
 id       int
,company  text
,sort     text
,log_up   timestamp 
,log_upby smallint
);

-- temp table with real life test data
DROP   TABLE IF EXISTS tmp_f;
CREATE TEMP table tmp_f AS 
   SELECT ROW(firma_id,firma,sort,log_up,log_upby)::x.t_f AS f
   FROM   ef.firma
   WHERE  firma !~~ '"%';

-- SELECT count(*) FROM tmp_f;  -- 5183

-- Quick test: results are identical?
SELECT *,
       x.setfield (f, 'company','test')
      ,x.setfield2(f, 'company','test')
      ,x.setfield3(f, 'company','test')
 FROM tmp_f
LIMIT 10;

基准

我运行了几次查询来填充缓存。所呈现的结果是具有EXPLAIN ANALYZE的五个总运行时中的最佳结果。

第一轮，1000行

Pavel的第一个原型使用更多行来共享内存。

Pavel 1：2445.112 ms 

SELECT x.setfield (f, 'company','test') FROM tmp_f limit 1000;

Pavel 2：263.753 ms 

SELECT x.setfield2(f, 'company','test') FROM tmp_f limit 1000;

Erwin 1：120.671 ms 

SELECT x.setfield3(f, 'company','test') FROM tmp_f limit 1000;

另有5183行的测试。

Pavel 2：1327.429 ms 

SELECT x.setfield2(f, 'company','test') FROM tmp_f;

Erwin1：588.691 ms 

SELECT x.setfield3(f, 'company','test') FROM tmp_f;

答案 5 :(得分：1)

测试设置和基准测试v2

Erwin鼓励在这个帖子（https://stackoverflow.com/a/7782839/1914376）中重现他的基准，所以我用合成测试数据修改了他的代码，并从我的答案添加了hstore解决方案和json-solution（以及Pavel的json解决方案）在另一个线程中找到）基准测试现在作为一个查询运行，从而更容易捕获结果。

DROP SCHEMA IF EXISTS x CASCADE;
CREATE SCHEMA x;


-- Pavel 1:
--------------------------------------------------------------------------------------------------
CREATE OR REPLACE FUNCTION x.setfield(anyelement, text, text)
RETURNS anyelement
LANGUAGE plpgsql
AS $function$
begin
  create temp table aux as select $1.*;
  execute 'update aux set ' || quote_ident($2) || ' = ' || quote_literal($3);
  select into $1 * from aux;
  drop table aux;
  return $1;
end;
$function$;


-- Pavel 2 (with patches)
--------------------------------------------------------------------------------------------------
CREATE OR REPLACE FUNCTION x.setfield2(anyelement, text, text)
 RETURNS anyelement
 LANGUAGE plpgsql
AS $function$
DECLARE
  _name text;
  _values text[];
  _value text;
  _attnum int;
BEGIN
  FOR _name, _attnum
     IN SELECT a.attname, a.attnum
           FROM pg_catalog.pg_attribute a
          WHERE a.attrelid = (SELECT typrelid
                                 FROM pg_type
                                WHERE oid = pg_typeof($1)::oid)
  LOOP
    IF _name = $2 THEN
      _value := $3;
    ELSE
      EXECUTE 'SELECT (($1).' || quote_ident(_name) || ')::text' INTO _value USING $1;
    END IF;
    _values[_attnum] :=  COALESCE('"' || replace(replace(_value, '"', '""'), '''', '''''') || '"', '');
  END LOOP;
  EXECUTE 'SELECT (' || pg_typeof($1)::text || '''(' || array_to_string(_values,',') || ')'').*' INTO $1;
  RETURN $1;
END;
$function$;


-- Erwin 1
--------------------------------------------------------------------------------------------------
CREATE OR REPLACE FUNCTION x.setfield3(anyelement, text, text)
RETURNS anyelement
AS $body$
DECLARE
 _list text;

BEGIN
_list := (
   SELECT string_agg(x.fld, ',')
   FROM   (
      SELECT CASE WHEN a.attname = $2
              THEN quote_literal($3)
              ELSE quote_ident(a.attname)
             END AS fld
      FROM   pg_catalog.pg_attribute a
      WHERE  a.attrelid = (SELECT typrelid
                           FROM   pg_type
                           WHERE  oid = pg_typeof($1)::oid)
      ORDER BY a.attnum
   ) x
);

EXECUTE '
SELECT ' || _list || '
FROM   (SELECT $1.*) x'
USING  $1
INTO   $1;

RETURN $1;
END;
$body$ LANGUAGE plpgsql;


-- Erwin 2
--------------------------------------------------------------------------------------------------
CREATE OR REPLACE FUNCTION x.setfield4(INOUT _comp_val anyelement
                                       , _field text, _val text)
  RETURNS anyelement AS
$func$
BEGIN

EXECUTE 'SELECT ' || array_to_string(ARRAY(
      SELECT CASE WHEN attname = _field
                THEN '$2'
                ELSE '($1).' || quote_ident(attname)
             END AS fld
      FROM   pg_catalog.pg_attribute
      WHERE  attrelid = pg_typeof(_comp_val)::text::regclass
      AND    attnum > 0
      AND    attisdropped = FALSE
      ORDER  BY attnum
      ), ',')
USING  _comp_val, _val
INTO   _comp_val;

END
$func$ LANGUAGE plpgsql;


-- Pavel 3: json. (Postgres 9.4)
-- Found here: https://stackoverflow.com/a/28284491/1914376
--------------------------------------------------------------------------------------------------
CREATE OR REPLACE FUNCTION x.setfield5(r anyelement, fn text, val text,OUT result anyelement)
 RETURNS anyelement
 LANGUAGE plpgsql
AS $function$
declare jo json;
begin
  jo := (select json_object(array_agg(key), 
                            array_agg(case key when fn then val
                                               else value end)) 
            from json_each_text(row_to_json(r)));
  result := json_populate_record(r, jo);
end;
$function$;


-- Json. Use built-in json functions (Postgres 9.3)
-- This is available from 9.3 since we create json by casting 
-- instead of using json_object/json_build_object only available from 9.4
--------------------------------------------------------------------------------------------------
CREATE FUNCTION x.setfield_json(in_element anyelement, key text, value text)
    RETURNS anyelement AS
$BODY$
    SELECT json_populate_record( in_element, ('{"'||key||'":"'||value||'"}')::json);
$BODY$ LANGUAGE sql;



--------------------------------------------------------------------------------------------------
-- Test setup
--------------------------------------------------------------------------------------------------

-- composite type for tests.
CREATE TYPE x.t_f as (
 id       int
,company  text
,sort     text
,log_up   timestamp
,log_upby smallint
);

-- Create temp table with synthetic test data
DROP TABLE IF EXISTS tmp_f;
CREATE TEMP table tmp_f AS
   SELECT ROW(i, 'company'||i, NULL, NULL, NULL)::x.t_f AS f
   FROM generate_series(1, 5000) S(i);



-- Run the benchmark
DO $$  DECLARE  start_time timestamptz; test_count integer; test_description TEXT; BEGIN

    test_count := 200;
    test_description := 'setfield, Pavel 1: temptable';
    start_time := clock_timestamp();    
    PERFORM x.setfield (f, 'company','new-value-'||md5(random()::text)) FROM tmp_f LIMIT test_count;
    RAISE NOTICE 'Test took: % ms (for % rows) Name: %', extract(MILLISECONDS FROM (clock_timestamp() - start_time))::INTEGER, test_count, test_description;

    test_count := 5000;
    test_description := 'setfield2, Pavel 2: reflection';
    start_time := clock_timestamp();
    PERFORM x.setfield2 (f, 'company','new-value-'||md5(random()::text)) FROM tmp_f LIMIT test_count;
    RAISE NOTICE 'Test took: % ms (for % rows) Name: %', extract(MILLISECONDS FROM (clock_timestamp() - start_time))::INTEGER, test_count, test_description;

    test_count := 5000;
    test_description := 'setfield3, Erwin 1: reflection';
    start_time := clock_timestamp();
    PERFORM x.setfield3 (f, 'company','new-value-'||md5(random()::text)) FROM tmp_f LIMIT test_count;
    RAISE NOTICE 'Test took: % ms (for % rows) Name: %', extract(MILLISECONDS FROM (clock_timestamp() - start_time))::INTEGER, test_count, test_description;

    test_count := 5000;
    test_description := 'setfield4, Erwin 2: reflection';
    start_time := clock_timestamp();
    PERFORM x.setfield4 (f, 'company','new-value-'||md5(random()::text)) FROM tmp_f LIMIT test_count;
    RAISE NOTICE 'Test took: % ms (for % rows) Name: %', extract(MILLISECONDS FROM (clock_timestamp() - start_time))::INTEGER, test_count, test_description;

    test_count := 5000;
    test_description := 'setfield5, Pavel 3: json (PG 9.4)';
    start_time := clock_timestamp();
    PERFORM x.setfield5 (f, 'company','new-value-'||md5(random()::text)) FROM tmp_f LIMIT test_count;
    RAISE NOTICE 'Test took: % ms (for % rows) Name: %', extract(MILLISECONDS FROM (clock_timestamp() - start_time))::INTEGER, test_count, test_description;

    test_count := 5000;
    test_description := 'setfield_json, Geir 1: casting (PG 9.3)';
    start_time := clock_timestamp();
    PERFORM x.setfield_json (f, 'company','new-value-'||md5(random()::text)) FROM tmp_f LIMIT test_count;
    RAISE NOTICE 'Test took: % ms (for % rows) Name: %', extract(MILLISECONDS FROM (clock_timestamp() - start_time))::INTEGER, test_count, test_description;

    --json_object(ARRAY(key,value]) is actually faster than json_build_object(key, value)
    test_count := 5000;
    test_description := 'no function/inlined: json_object (PG 9.4)';
    start_time := clock_timestamp();
    PERFORM json_populate_record( f, json_object(ARRAY['company', 'new-value'||md5(random()::text)]  )) FROM tmp_f LIMIT test_count;
    RAISE NOTICE 'Test took: % ms (for % rows) Name: %', extract(MILLISECONDS FROM (clock_timestamp() - start_time))::INTEGER, test_count, test_description;

    test_count := 5000;
    test_description := 'no function/inlined: hstore (PG 9.0)';
    start_time := clock_timestamp();
    PERFORM f #= hstore('company', 'new-value'||md5(random()::text))  FROM tmp_f LIMIT test_count;
    RAISE NOTICE 'Test took: % ms (for % rows) Name: %', extract(MILLISECONDS FROM (clock_timestamp() - start_time))::INTEGER, test_count, test_description;

END; $$;

测试结果见9.4.1，win32，i5-4300U 

NOTICE:  Test took: 1138 ms (for 200 rows) Name: setfield, Pavel 1: temptable
NOTICE:  Test took: 652 ms (for 5000 rows) Name: setfield2, Pavel 2: reflection
NOTICE:  Test took: 364 ms (for 5000 rows) Name: setfield3, Erwin 1: reflection
NOTICE:  Test took: 275 ms (for 5000 rows) Name: setfield4, Erwin 2: reflection
NOTICE:  Test took: 192 ms (for 5000 rows) Name: setfield5, Pavel 3: json (PG 9.4)
NOTICE:  Test took: 23 ms (for 5000 rows) Name: setfield_json, Geir 1: casting (PG 9.3)
NOTICE:  Test took: 25 ms (for 5000 rows) Name: no function/inlined: json_object (PG 9.4)
NOTICE:  Test took: 14 ms (for 5000 rows) Name: no function/inlined: hstore (PG 9.0)
相关问题
最新问题