On Thu, 29 Feb 2024 at 01:57, Michael Paquier <mich...@paquier.xyz> wrote:
> I have doubts about the changes in raw_pg_bind_textdomain_codeset(),
> as the encoding could come from the value in the pg_database tuples
> themselves. The current coding is slightly safer from the perspective
> of bogus input values as we would loop over pg_enc2gettext_tbl looking
> for a match. 0003 changes that so as we could point to incorrect
> memory areas rather than fail safely for the NULL check.
That's fair. Attached is a patch that adds a PG_VALID_ENCODING check
to raw_pg_bind_textdomain_codeset to solve this regression.
From a51592bda622746b9f015d7993ca19254bedbc0e Mon Sep 17 00:00:00 2001
From: Jelte Fennema-Nio <jelte.fenn...@microsoft.com>
Date: Tue, 27 Feb 2024 12:26:10 +0100
Subject: [PATCH v7] Simplify pg_enc2gettext_tbl
Use designated initialization of pg_enc2gettext_tbl to simplify the
implementation of raw_pg_bind_textdomain_codeset. Now iteration over the
array is not needed anymore. Instead the desired element can simply be
fetched by its index.
---
src/backend/utils/mb/mbutils.c | 24 ++++------
src/common/encnames.c | 85 +++++++++++++++++-----------------
src/include/mb/pg_wchar.h | 11 ++---
3 files changed, 55 insertions(+), 65 deletions(-)
diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c
index c13f947a827..5818e752280 100644
--- a/src/backend/utils/mb/mbutils.c
+++ b/src/backend/utils/mb/mbutils.c
@@ -1188,24 +1188,20 @@ static bool
raw_pg_bind_textdomain_codeset(const char *domainname, int encoding)
{
bool elog_ok = (CurrentMemoryContext != NULL);
- int i;
- for (i = 0; pg_enc2gettext_tbl[i].name != NULL; i++)
+ if (!PG_VALID_ENCODING(encoding) || pg_enc2gettext_tbl[encoding] == NULL)
{
- if (pg_enc2gettext_tbl[i].encoding == encoding)
- {
- if (bind_textdomain_codeset(domainname,
- pg_enc2gettext_tbl[i].name) != NULL)
- return true;
+ return false;
+ }
- if (elog_ok)
- elog(LOG, "bind_textdomain_codeset failed");
- else
- write_stderr("bind_textdomain_codeset failed");
+ if (bind_textdomain_codeset(domainname,
+ pg_enc2gettext_tbl[encoding]) != NULL)
+ return true;
- break;
- }
- }
+ if (elog_ok)
+ elog(LOG, "bind_textdomain_codeset failed");
+ else
+ write_stderr("bind_textdomain_codeset failed");
return false;
}
diff --git a/src/common/encnames.c b/src/common/encnames.c
index dba6bd2c9ee..d94c740a28b 100644
--- a/src/common/encnames.c
+++ b/src/common/encnames.c
@@ -357,50 +357,49 @@ const pg_enc2name pg_enc2name_tbl[] =
* This covers all encodings except MULE_INTERNAL, which is alien to gettext.
* ----------
*/
-const pg_enc2gettext pg_enc2gettext_tbl[] =
+const char *pg_enc2gettext_tbl[] =
{
- {PG_SQL_ASCII, "US-ASCII"},
- {PG_UTF8, "UTF-8"},
- {PG_LATIN1, "LATIN1"},
- {PG_LATIN2, "LATIN2"},
- {PG_LATIN3, "LATIN3"},
- {PG_LATIN4, "LATIN4"},
- {PG_ISO_8859_5, "ISO-8859-5"},
- {PG_ISO_8859_6, "ISO_8859-6"},
- {PG_ISO_8859_7, "ISO-8859-7"},
- {PG_ISO_8859_8, "ISO-8859-8"},
- {PG_LATIN5, "LATIN5"},
- {PG_LATIN6, "LATIN6"},
- {PG_LATIN7, "LATIN7"},
- {PG_LATIN8, "LATIN8"},
- {PG_LATIN9, "LATIN-9"},
- {PG_LATIN10, "LATIN10"},
- {PG_KOI8R, "KOI8-R"},
- {PG_KOI8U, "KOI8-U"},
- {PG_WIN1250, "CP1250"},
- {PG_WIN1251, "CP1251"},
- {PG_WIN1252, "CP1252"},
- {PG_WIN1253, "CP1253"},
- {PG_WIN1254, "CP1254"},
- {PG_WIN1255, "CP1255"},
- {PG_WIN1256, "CP1256"},
- {PG_WIN1257, "CP1257"},
- {PG_WIN1258, "CP1258"},
- {PG_WIN866, "CP866"},
- {PG_WIN874, "CP874"},
- {PG_EUC_CN, "EUC-CN"},
- {PG_EUC_JP, "EUC-JP"},
- {PG_EUC_KR, "EUC-KR"},
- {PG_EUC_TW, "EUC-TW"},
- {PG_EUC_JIS_2004, "EUC-JP"},
- {PG_SJIS, "SHIFT-JIS"},
- {PG_BIG5, "BIG5"},
- {PG_GBK, "GBK"},
- {PG_UHC, "UHC"},
- {PG_GB18030, "GB18030"},
- {PG_JOHAB, "JOHAB"},
- {PG_SHIFT_JIS_2004, "SHIFT_JISX0213"},
- {0, NULL}
+ [PG_SQL_ASCII] = "US-ASCII",
+ [PG_UTF8] = "UTF-8",
+ [PG_LATIN1] = "LATIN1",
+ [PG_LATIN2] = "LATIN2",
+ [PG_LATIN3] = "LATIN3",
+ [PG_LATIN4] = "LATIN4",
+ [PG_ISO_8859_5] = "ISO-8859-5",
+ [PG_ISO_8859_6] = "ISO_8859-6",
+ [PG_ISO_8859_7] = "ISO-8859-7",
+ [PG_ISO_8859_8] = "ISO-8859-8",
+ [PG_LATIN5] = "LATIN5",
+ [PG_LATIN6] = "LATIN6",
+ [PG_LATIN7] = "LATIN7",
+ [PG_LATIN8] = "LATIN8",
+ [PG_LATIN9] = "LATIN-9",
+ [PG_LATIN10] = "LATIN10",
+ [PG_KOI8R] = "KOI8-R",
+ [PG_KOI8U] = "KOI8-U",
+ [PG_WIN1250] = "CP1250",
+ [PG_WIN1251] = "CP1251",
+ [PG_WIN1252] = "CP1252",
+ [PG_WIN1253] = "CP1253",
+ [PG_WIN1254] = "CP1254",
+ [PG_WIN1255] = "CP1255",
+ [PG_WIN1256] = "CP1256",
+ [PG_WIN1257] = "CP1257",
+ [PG_WIN1258] = "CP1258",
+ [PG_WIN866] = "CP866",
+ [PG_WIN874] = "CP874",
+ [PG_EUC_CN] = "EUC-CN",
+ [PG_EUC_JP] = "EUC-JP",
+ [PG_EUC_KR] = "EUC-KR",
+ [PG_EUC_TW] = "EUC-TW",
+ [PG_EUC_JIS_2004] = "EUC-JP",
+ [PG_SJIS] = "SHIFT-JIS",
+ [PG_BIG5] = "BIG5",
+ [PG_GBK] = "GBK",
+ [PG_UHC] = "UHC",
+ [PG_GB18030] = "GB18030",
+ [PG_JOHAB] = "JOHAB",
+ [PG_SHIFT_JIS_2004] = "SHIFT_JISX0213",
};
diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h
index fd91aefbcb7..32e25a1a6ea 100644
--- a/src/include/mb/pg_wchar.h
+++ b/src/include/mb/pg_wchar.h
@@ -225,7 +225,8 @@ typedef unsigned int pg_wchar;
* PostgreSQL encoding identifiers
*
* WARNING: If you add some encoding don't forget to update
- * the pg_enc2name_tbl[] array (in src/common/encnames.c) and
+ * the pg_enc2name_tbl[] array (in src/common/encnames.c),
+ * the pg_enc2gettext_tbl[] array (in src/common/encnames.c) and
* the pg_wchar_table[] array (in src/common/wchar.c) and to check
* PG_ENCODING_BE_LAST macro.
*
@@ -365,13 +366,7 @@ extern PGDLLIMPORT const pg_enc2name pg_enc2name_tbl[];
/*
* Encoding names for gettext
*/
-typedef struct pg_enc2gettext
-{
- pg_enc encoding;
- const char *name;
-} pg_enc2gettext;
-
-extern PGDLLIMPORT const pg_enc2gettext pg_enc2gettext_tbl[];
+extern PGDLLIMPORT const char *pg_enc2gettext_tbl[];
/*
* pg_wchar stuff
base-commit: ada87a4d95fc39dfb1214edf6653390314b6f0df
--
2.34.1
