1
0
mirror of https://github.com/postgres/postgres.git synced 2025-09-03 15:22:11 +03:00

Prefer pg_any_to_server/pg_server_to_any over pg_do_encoding_conversion.

A large majority of the callers of pg_do_encoding_conversion were
specifying the database encoding as either source or target of the
conversion, meaning that we can use the less general functions
pg_any_to_server/pg_server_to_any instead.

The main advantage of using the latter functions is that they can make use
of a cached conversion-function lookup in the common case that the other
encoding is the current client_encoding.  It's notationally cleaner too in
most cases, not least because of the historical artifact that the latter
functions use "char *" rather than "unsigned char *" in their APIs.

Note that pg_any_to_server will apply an encoding verification step in
some cases where pg_do_encoding_conversion would have just done nothing.
This seems to me to be a good idea at most of these call sites, though
it partially negates the performance benefit.

Per discussion of bug #9210.
This commit is contained in:
Tom Lane
2014-02-23 16:59:05 -05:00
parent 49c817eab7
commit 769065c1b2
12 changed files with 50 additions and 99 deletions

View File

@@ -3811,9 +3811,7 @@ hv_store_string(HV *hv, const char *key, SV *val)
char *hkey;
SV **ret;
hkey = (char *)
pg_do_encoding_conversion((unsigned char *) key, strlen(key),
GetDatabaseEncoding(), PG_UTF8);
hkey = pg_server_to_any(key, strlen(key), PG_UTF8);
/*
* This seems nowhere documented, but under Perl 5.8.0 and up, hv_store()
@@ -3841,9 +3839,7 @@ hv_fetch_string(HV *hv, const char *key)
char *hkey;
SV **ret;
hkey = (char *)
pg_do_encoding_conversion((unsigned char *) key, strlen(key),
GetDatabaseEncoding(), PG_UTF8);
hkey = pg_server_to_any(key, strlen(key), PG_UTF8);
/* See notes in hv_store_string */
hlen = -(int) strlen(hkey);

View File

@@ -9,24 +9,11 @@
static inline char *
utf_u2e(char *utf8_str, size_t len)
{
int enc = GetDatabaseEncoding();
char *ret;
/*
* When we are in a PG_UTF8 or SQL_ASCII database
* pg_do_encoding_conversion() will not do any conversion (which is good)
* or verification (not so much), so we need to run the verification step
* separately.
*/
if (enc == PG_UTF8 || enc == PG_SQL_ASCII)
{
pg_verify_mbstr_len(enc, utf8_str, len, false);
ret = utf8_str;
}
else
ret = (char *) pg_do_encoding_conversion((unsigned char *) utf8_str,
len, PG_UTF8, enc);
ret = pg_any_to_server(utf8_str, len, PG_UTF8);
/* ensure we have a copy even if no conversion happened */
if (ret == utf8_str)
ret = pstrdup(ret);
@@ -41,12 +28,14 @@ utf_u2e(char *utf8_str, size_t len)
static inline char *
utf_e2u(const char *str)
{
char *ret =
(char *) pg_do_encoding_conversion((unsigned char *) str, strlen(str),
GetDatabaseEncoding(), PG_UTF8);
char *ret;
ret = pg_server_to_any(str, strlen(str), PG_UTF8);
/* ensure we have a copy even if no conversion happened */
if (ret == str)
ret = pstrdup(ret);
return ret;
}

View File

@@ -90,11 +90,9 @@ PLyUnicode_Bytes(PyObject *unicode)
{
PG_TRY();
{
encoded = (char *) pg_do_encoding_conversion(
(unsigned char *) utf8string,
strlen(utf8string),
PG_UTF8,
GetDatabaseEncoding());
encoded = pg_any_to_server(utf8string,
strlen(utf8string),
PG_UTF8);
}
PG_CATCH();
{
@@ -109,7 +107,7 @@ PLyUnicode_Bytes(PyObject *unicode)
/* finally, build a bytes object in the server encoding */
rv = PyBytes_FromStringAndSize(encoded, strlen(encoded));
/* if pg_do_encoding_conversion allocated memory, free it now */
/* if pg_any_to_server allocated memory, free it now */
if (utf8string != encoded)
pfree(encoded);
@@ -149,10 +147,7 @@ PLyUnicode_FromString(const char *s)
char *utf8string;
PyObject *o;
utf8string = (char *) pg_do_encoding_conversion((unsigned char *) s,
strlen(s),
GetDatabaseEncoding(),
PG_UTF8);
utf8string = pg_server_to_any(s, strlen(s), PG_UTF8);
o = PyUnicode_FromString(utf8string);

View File

@@ -63,13 +63,17 @@
static unsigned char *
utf_u2e(unsigned char *src)
{
return pg_do_encoding_conversion(src, strlen(src), PG_UTF8, GetDatabaseEncoding());
return (unsigned char *) pg_any_to_server((char *) src,
strlen(src),
PG_UTF8);
}
static unsigned char *
utf_e2u(unsigned char *src)
{
return pg_do_encoding_conversion(src, strlen(src), GetDatabaseEncoding(), PG_UTF8);
return (unsigned char *) pg_server_to_any((char *) src,
strlen(src),
PG_UTF8);
}
#define PLTCL_UTF