diff options
author | Tom Lane <tgl@sss.pgh.pa.us> | 2014-02-23 16:59:05 -0500 |
---|---|---|
committer | Tom Lane <tgl@sss.pgh.pa.us> | 2014-02-23 16:59:05 -0500 |
commit | 769065c1b2471f484bb48bb58a8bdcf1d12a419c (patch) | |
tree | dc0344a494ceabe955b403b992f4092ec4140f8b /src/pl/plperl/plperl_helpers.h | |
parent | 49c817eab78c6f0ce8c3bf46766b73d6cf3190b7 (diff) | |
download | postgresql-769065c1b2471f484bb48bb58a8bdcf1d12a419c.tar.gz postgresql-769065c1b2471f484bb48bb58a8bdcf1d12a419c.zip |
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.
Diffstat (limited to 'src/pl/plperl/plperl_helpers.h')
-rw-r--r-- | src/pl/plperl/plperl_helpers.h | 25 |
1 files changed, 7 insertions, 18 deletions
diff --git a/src/pl/plperl/plperl_helpers.h b/src/pl/plperl/plperl_helpers.h index 3e8aa7c4a26..c1c7c297cc5 100644 --- a/src/pl/plperl/plperl_helpers.h +++ b/src/pl/plperl/plperl_helpers.h @@ -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; } |