Tighten the check in initdb and CREATE DATABASE that the chosen encoding

matches the encoding of the locale. LC_COLLATE is now checked in addition
to LC_CTYPE.

diff --git a/doc/src/sgml/charset.sgml b/doc/src/sgml/charset.sgml
index c012294ef81f1ccdbdd4a99152accd9a80050474..0aeef78966b4e29a4de935756f49af4356dea985 100644 (file)
--- a/doc/src/sgml/charset.sgml
+++ b/doc/src/sgml/charset.sgml
@@ -1,4 +1,4 @@
-<!-- $PostgreSQL: pgsql/doc/src/sgml/charset.sgml,v 2.88 2008/09/23 09:20:34 heikki Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/charset.sgml,v 2.89 2008/09/23 10:58:03 heikki Exp $ -->
 
 <chapter id="charset">
  <title>Localization</>
@@ -320,10 +320,10 @@ initdb --locale=sv_SE
 
   <para>
    An important restriction, however, is that each database's character set
-   must be compatible with the database's <envar>LC_CTYPE</> setting.
-   When <envar>LC_CTYPE</> is <literal>C</> or <literal>POSIX</>, any
-   character set is allowed, but for other settings of <envar>LC_CTYPE</>
-   there is only one character set that will work correctly.
+   must be compatible with the database's <envar>LC_CTYPE</> and
+   <envvar>LC_COLLATE</> locale settings. For <literal>C</> or
+   <literal>POSIX</> locale, any character set is allowed, but for other
+   locales there is only one character set that will work correctly.
   </para>
 
    <sect2 id="multibyte-charset-supported">

diff --git a/src/backend/commands/dbcommands.c b/src/backend/commands/dbcommands.c
index ce3754f5928269e436d754520647c1c5b552e2d1..29dc0733a737779c13112647a2df95238676ca3a 100644 (file)
--- a/src/backend/commands/dbcommands.c
+++ b/src/backend/commands/dbcommands.c
@@ -13,7 +13,7 @@
  *
  *
  * IDENTIFICATION
- *   $PostgreSQL: pgsql/src/backend/commands/dbcommands.c,v 1.211 2008/09/23 09:20:35 heikki Exp $
+ *   $PostgreSQL: pgsql/src/backend/commands/dbcommands.c,v 1.212 2008/09/23 10:58:03 heikki Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -118,6 +118,7 @@ createdb(const CreatedbStmt *stmt)
    int         encoding = -1;
    int         dbconnlimit = -1;
    int         ctype_encoding;
+   int         collate_encoding;
    int         notherbackends;
    int         npreparedxacts;
    createdb_failure_params fparms;
@@ -334,6 +335,7 @@ createdb(const CreatedbStmt *stmt)
     * Note: if you change this policy, fix initdb to match.
     */
    ctype_encoding = pg_get_encoding_from_locale(dbctype);
+   collate_encoding = pg_get_encoding_from_locale(dbcollate);
 
    if (!(ctype_encoding == encoding ||
          ctype_encoding == PG_SQL_ASCII ||
@@ -345,9 +347,22 @@ createdb(const CreatedbStmt *stmt)
                (errmsg("encoding %s does not match locale %s",
                        pg_encoding_to_char(encoding),
                        dbctype),
-            errdetail("The chosen LC_CTYPE setting requires encoding %s.",
+            errdetail("The chosen CTYPE setting requires encoding %s.",
                       pg_encoding_to_char(ctype_encoding))));
 
+   if (!(collate_encoding == encoding ||
+         collate_encoding == PG_SQL_ASCII ||
+#ifdef WIN32
+         encoding == PG_UTF8 ||
+#endif
+         (encoding == PG_SQL_ASCII && superuser())))
+       ereport(ERROR,
+               (errmsg("encoding %s does not match locale %s",
+                       pg_encoding_to_char(encoding),
+                       dbcollate),
+            errdetail("The chosen COLLATE setting requires encoding %s.",
+                      pg_encoding_to_char(collate_encoding))));
+
    /*
     * Check that the new locale is compatible with the source database.
     *

diff --git a/src/bin/initdb/initdb.c b/src/bin/initdb/initdb.c
index a4bd34cb685ce1392569e30eb969e2ecfec518fd..4caee3e21547ea3a6084bee82190fd64b11d2e0c 100644 (file)
--- a/src/bin/initdb/initdb.c
+++ b/src/bin/initdb/initdb.c
@@ -42,7 +42,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  * Portions taken from FreeBSD.
  *
- * $PostgreSQL: pgsql/src/bin/initdb/initdb.c,v 1.160 2008/09/23 09:20:37 heikki Exp $
+ * $PostgreSQL: pgsql/src/bin/initdb/initdb.c,v 1.161 2008/09/23 10:58:03 heikki Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -188,7 +188,8 @@ static void trapsig(int signum);
 static void check_ok(void);
 static char *escape_quotes(const char *src);
 static int locale_date_order(const char *locale);
-static bool chklocale(const char *locale);
+static bool check_locale_name(const char *locale);
+static bool check_locale_encoding(const char *locale, int encoding);
 static void setlocales(void);
 static void usage(const char *progname);
 
@@ -2187,7 +2188,7 @@ locale_date_order(const char *locale)
  * this should match the backend check_locale() function
  */
 static bool
-chklocale(const char *locale)
+check_locale_name(const char *locale)
 {
    bool        ret;
    int         category = LC_CTYPE;
@@ -2211,6 +2212,50 @@ chklocale(const char *locale)
    return ret;
 }
 
+/*
+ * check if the chosen encoding matches the encoding required by the locale
+ *
+ * this should match the similar check in the backend createdb() function
+ */
+static bool
+check_locale_encoding(const char *locale, int user_enc)
+{
+   int         locale_enc;
+
+   locale_enc = pg_get_encoding_from_locale(locale);
+
+   /* We allow selection of SQL_ASCII --- see notes in createdb() */
+   if (!(locale_enc == user_enc ||
+         locale_enc == PG_SQL_ASCII ||
+         user_enc == PG_SQL_ASCII
+#ifdef WIN32
+
+   /*
+    * On win32, if the encoding chosen is UTF8, all locales are OK
+    * (assuming the actual locale name passed the checks above). This is
+    * because UTF8 is a pseudo-codepage, that we convert to UTF16 before
+    * doing any operations on, and UTF16 supports all locales.
+    */
+         || user_enc == PG_UTF8
+#endif
+         ))
+   {
+       fprintf(stderr, _("%s: encoding mismatch\n"), progname);
+       fprintf(stderr,
+              _("The encoding you selected (%s) and the encoding that the\n"
+             "selected locale uses (%s) do not match.  This would lead to\n"
+           "misbehavior in various character string processing functions.\n"
+              "Rerun %s and either do not specify an encoding explicitly,\n"
+                "or choose a matching combination.\n"),
+               pg_encoding_to_char(user_enc),
+               pg_encoding_to_char(locale_enc),
+               progname);
+       return false;
+   }
+   return true;
+}
+
+
 /*
  * set up the locale variables
  *
@@ -2241,17 +2286,17 @@ setlocales(void)
     * override absent/invalid config settings from initdb's locale settings
     */
 
-   if (strlen(lc_ctype) == 0 || !chklocale(lc_ctype))
+   if (strlen(lc_ctype) == 0 || !check_locale_name(lc_ctype))
        lc_ctype = xstrdup(setlocale(LC_CTYPE, NULL));
-   if (strlen(lc_collate) == 0 || !chklocale(lc_collate))
+   if (strlen(lc_collate) == 0 || !check_locale_name(lc_collate))
        lc_collate = xstrdup(setlocale(LC_COLLATE, NULL));
-   if (strlen(lc_numeric) == 0 || !chklocale(lc_numeric))
+   if (strlen(lc_numeric) == 0 || !check_locale_name(lc_numeric))
        lc_numeric = xstrdup(setlocale(LC_NUMERIC, NULL));
-   if (strlen(lc_time) == 0 || !chklocale(lc_time))
+   if (strlen(lc_time) == 0 || !check_locale_name(lc_time))
        lc_time = xstrdup(setlocale(LC_TIME, NULL));
-   if (strlen(lc_monetary) == 0 || !chklocale(lc_monetary))
+   if (strlen(lc_monetary) == 0 || !check_locale_name(lc_monetary))
        lc_monetary = xstrdup(setlocale(LC_MONETARY, NULL));
-   if (strlen(lc_messages) == 0 || !chklocale(lc_messages))
+   if (strlen(lc_messages) == 0 || !check_locale_name(lc_messages))
 #if defined(LC_MESSAGES) && !defined(WIN32)
    {
        /* when available get the current locale setting */
@@ -2452,6 +2497,7 @@ main(int argc, char *argv[])
                                 * environment */
    char        bin_dir[MAXPGPATH];
    char       *pg_data_native;
+   int         user_enc;
 
 #ifdef WIN32
    char       *restrict_env;
@@ -2868,44 +2914,12 @@ main(int argc, char *argv[])
        }
    }
    else
-   {
-       int         user_enc;
-       int         ctype_enc;
-
        encodingid = get_encoding_id(encoding);
-       user_enc = atoi(encodingid);
-
-       ctype_enc = pg_get_encoding_from_locale(lc_ctype);
 
-       /* We allow selection of SQL_ASCII --- see notes in createdb() */
-       if (!(ctype_enc == user_enc ||
-             ctype_enc == PG_SQL_ASCII ||
-             user_enc == PG_SQL_ASCII
-#ifdef WIN32
-
-       /*
-        * On win32, if the encoding chosen is UTF8, all locales are OK
-        * (assuming the actual locale name passed the checks above). This is
-        * because UTF8 is a pseudo-codepage, that we convert to UTF16 before
-        * doing any operations on, and UTF16 supports all locales.
-        */
-             || user_enc == PG_UTF8
-#endif
-             ))
-       {
-           fprintf(stderr, _("%s: encoding mismatch\n"), progname);
-           fprintf(stderr,
-              _("The encoding you selected (%s) and the encoding that the\n"
-             "selected locale uses (%s) do not match.  This would lead to\n"
-           "misbehavior in various character string processing functions.\n"
-              "Rerun %s and either do not specify an encoding explicitly,\n"
-                "or choose a matching combination.\n"),
-                   pg_encoding_to_char(user_enc),
-                   pg_encoding_to_char(ctype_enc),
-                   progname);
-           exit(1);
-       }
-   }
+   user_enc = atoi(encodingid);
+   if (!check_locale_encoding(lc_ctype, user_enc) ||
+       !check_locale_encoding(lc_collate, user_enc))
+       exit(1); /* check_locale_encoding printed the error */
 
    if (strlen(default_text_search_config) == 0)
    {