database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-11-21 00:42:43 +03:00
Code Activity

Add ENCODING option to COPY TO/FROM and file_fdw.

Browse Source 
File encodings can be specified separately from client encoding.
If not specified, client encoding is used for backward compatibility.

Cases when the encoding doesn't match client encoding are slower
than matched cases because we don't have conversion procs for other
encodings. Performance improvement would be be a future work.

Original patch by Hitoshi Harada, and modified by me.
This commit is contained in:
Itagaki Takahiro
2011-02-21 14:08:04 +09:00
parent 48d25bac9f
commit 3cba8240a1
9 changed files with 119 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
src/backend/utils/mb/mbutils.c
View File

@@ -496,6 +496,17 @@ pg_encoding_max_length_sql(PG_FUNCTION_ARGS)
*/
char *
pg_client_to_server(const char *s, int len)
{
Assert(ClientEncoding);
return pg_any_to_server(s, len, ClientEncoding->encoding);
}
/*
* convert any encoding to server encoding.
*/
char *
pg_any_to_server(const char *s, int len, int encoding)
{
Assert(DatabaseEncoding);
Assert(ClientEncoding);
@@ -503,8 +514,8 @@ pg_client_to_server(const char *s, int len)
if (len <= 0)
return (char *) s;
if (ClientEncoding->encoding == DatabaseEncoding->encoding ||
ClientEncoding->encoding == PG_SQL_ASCII)
if (encoding == DatabaseEncoding->encoding ||
encoding == PG_SQL_ASCII)
{
/*
* No conversion is needed, but we must still validate the data.
@@ -524,8 +535,8 @@ pg_client_to_server(const char *s, int len)
* to the parser but we have no way to convert it. We compromise by
* rejecting the data if it contains any non-ASCII characters.
*/
if (PG_VALID_BE_ENCODING(ClientEncoding->encoding))
(void) pg_verify_mbstr(ClientEncoding->encoding, s, len, false);
if (PG_VALID_BE_ENCODING(encoding))
(void) pg_verify_mbstr(encoding, s, len, false);
else
{
int i;
@@ -543,7 +554,11 @@ pg_client_to_server(const char *s, int len)
return (char *) s;
}
return perform_default_encoding_conversion(s, len, true);
if (ClientEncoding->encoding == encoding)
return perform_default_encoding_conversion(s, len, true);
else
return (char *) pg_do_encoding_conversion(
(unsigned char *) s, len, encoding, DatabaseEncoding->encoding);
}
/*
@@ -551,6 +566,17 @@ pg_client_to_server(const char *s, int len)
*/
char *
pg_server_to_client(const char *s, int len)
{
Assert(ClientEncoding);
return pg_any_to_server(s, len, ClientEncoding->encoding);
}
/*
* convert server encoding to any encoding.
*/
char *
pg_server_to_any(const char *s, int len, int encoding)
{
Assert(DatabaseEncoding);
Assert(ClientEncoding);
@@ -558,12 +584,16 @@ pg_server_to_client(const char *s, int len)
if (len <= 0)
return (char *) s;
if (ClientEncoding->encoding == DatabaseEncoding->encoding ||
ClientEncoding->encoding == PG_SQL_ASCII ||
if (encoding == DatabaseEncoding->encoding ||
encoding == PG_SQL_ASCII ||
DatabaseEncoding->encoding == PG_SQL_ASCII)
return (char *) s; /* assume data is valid */
return perform_default_encoding_conversion(s, len, false);
if (ClientEncoding->encoding == encoding)
return perform_default_encoding_conversion(s, len, false);
else
return (char *) pg_do_encoding_conversion(
(unsigned char *) s, len, DatabaseEncoding->encoding, encoding);
}
/*