更改 PostgreSQL C 语言函数中的字符编码
Change the character encode in PostgreSQL C language function
我在 windows 服务器上使用 PostgreSQL 9.5 64 位版本。
数据库的字符编码设置为UTF8.
我想创建一个处理多字节字符串的函数。
(例如清洁、更换等)
我从其他系统复制了C语言操作字符的逻辑,
逻辑假设字符编码为sjis。
我不想改变C语言逻辑,所以想在Postgresql的C语言函数中把UTF8转成sjis。
就像 convert_to 函数一样。 (不过,由于convert_to函数returnsbytea类型,所以想用TEXT类型获取。)
请告诉我如何用 C 语言将 UTF 8 转换为 sjis。
创建函数脚本:
CREATE FUNCTION CLEANSING_STRING(character varying)
RETURNS character varying AS
'$libdir/MyFunc/CLEANSING_STRING.dll', 'CLEANSING_STRING'
LANGUAGE c VOLATILE STRICT;
C 来源:
#include <stdio.h>
#include <string.h>
#include <postgres.h>
#include <port.h>
#include <fmgr.h>
#include <stdlib.h>
#include <builtins.h>
#ifdef PG_MODULE_MAGIC
PG_MODULE_MAGIC;
#endif
extern PGDLLEXPORT Datum CLEANSING_STRING(PG_FUNCTION_ARGS);
PG_FUNCTION_INFO_V1(CLEANSING_STRING);
Datum CLEANSING_STRING(PG_FUNCTION_ARGS)
{
// Get Arg
text *arg1 = (text *)PG_GETARG_TEXT_P(0);
// Text to Char[]
char *arg;
arg = text_to_cstring(arg1);
// UTF8 to Sjis
//Char *sjisChar[] = foo(arg); // something like that..
// Copied from other system.(Assumes that the character code is sjis.)
cleansingString(sjisChar);
replaceStrimg(sjisChar);
// Sjis to UTF8
//arg = bar(sjisChar); // something like that..
//Char[] to Text and Return
PG_RETURN_TEXT_P(cstring_to_text(arg));
}
按照问题评论教我的方式成功了。
#include <mb/pg_wchar.h> //Add to include.
...
Datum CLEANSING_STRING(PG_FUNCTION_ARGS)
{
// Get Arg
text *arg1 = (text *)PG_GETARG_TEXT_P(0);
// Text to Char[]
char *arg;
arg = text_to_cstring(arg1);
// UTF8 to Sjis
Char *sjisChar[] = pg_server_to_any(arg, strlen(arg), PG_SJIS);
// Copied from other system.(Assumes that the character code is sjis.)
cleansingString(sjisChar);
replaceStrimg(sjisChar);
// Sjis to UTF8
arg = pg_any_to_server(sjisChar, strlen(sjisChar), PG_SJIS); //It converts from SJIS to server (UTF 8), the third argument sets the encoding of the conversion source.
//Char[] to Text and Return
PG_RETURN_TEXT_P(cstring_to_text(arg));
}
我在 windows 服务器上使用 PostgreSQL 9.5 64 位版本。 数据库的字符编码设置为UTF8.
我想创建一个处理多字节字符串的函数。 (例如清洁、更换等)
我从其他系统复制了C语言操作字符的逻辑, 逻辑假设字符编码为sjis。
我不想改变C语言逻辑,所以想在Postgresql的C语言函数中把UTF8转成sjis。 就像 convert_to 函数一样。 (不过,由于convert_to函数returnsbytea类型,所以想用TEXT类型获取。)
请告诉我如何用 C 语言将 UTF 8 转换为 sjis。
创建函数脚本:
CREATE FUNCTION CLEANSING_STRING(character varying)
RETURNS character varying AS
'$libdir/MyFunc/CLEANSING_STRING.dll', 'CLEANSING_STRING'
LANGUAGE c VOLATILE STRICT;
C 来源:
#include <stdio.h>
#include <string.h>
#include <postgres.h>
#include <port.h>
#include <fmgr.h>
#include <stdlib.h>
#include <builtins.h>
#ifdef PG_MODULE_MAGIC
PG_MODULE_MAGIC;
#endif
extern PGDLLEXPORT Datum CLEANSING_STRING(PG_FUNCTION_ARGS);
PG_FUNCTION_INFO_V1(CLEANSING_STRING);
Datum CLEANSING_STRING(PG_FUNCTION_ARGS)
{
// Get Arg
text *arg1 = (text *)PG_GETARG_TEXT_P(0);
// Text to Char[]
char *arg;
arg = text_to_cstring(arg1);
// UTF8 to Sjis
//Char *sjisChar[] = foo(arg); // something like that..
// Copied from other system.(Assumes that the character code is sjis.)
cleansingString(sjisChar);
replaceStrimg(sjisChar);
// Sjis to UTF8
//arg = bar(sjisChar); // something like that..
//Char[] to Text and Return
PG_RETURN_TEXT_P(cstring_to_text(arg));
}
按照问题评论教我的方式成功了。
#include <mb/pg_wchar.h> //Add to include.
...
Datum CLEANSING_STRING(PG_FUNCTION_ARGS)
{
// Get Arg
text *arg1 = (text *)PG_GETARG_TEXT_P(0);
// Text to Char[]
char *arg;
arg = text_to_cstring(arg1);
// UTF8 to Sjis
Char *sjisChar[] = pg_server_to_any(arg, strlen(arg), PG_SJIS);
// Copied from other system.(Assumes that the character code is sjis.)
cleansingString(sjisChar);
replaceStrimg(sjisChar);
// Sjis to UTF8
arg = pg_any_to_server(sjisChar, strlen(sjisChar), PG_SJIS); //It converts from SJIS to server (UTF 8), the third argument sets the encoding of the conversion source.
//Char[] to Text and Return
PG_RETURN_TEXT_P(cstring_to_text(arg));
}