/*
* This test must be run in a database with UTF-8 encoding
* and a Unicode-aware locale.
+ *
+ * Also disable this file for ICU, because the test for the the
+ * Turkish dotted I is not correct for many ICU locales. citext always
+ * uses the default collation, so it's not easy to restrict the test
+ * to the "tr-TR-x-icu" collation where it will succeed.
*/
SELECT getdatabaseencoding() <> 'UTF8' OR
- current_setting('lc_ctype') = 'C'
+ current_setting('lc_ctype') = 'C' OR
+ (SELECT datlocprovider='i' FROM pg_database
+ WHERE datname=current_database())
AS skip_test \gset
\if :skip_test
\quit
/*
* This test must be run in a database with UTF-8 encoding
* and a Unicode-aware locale.
+ *
+ * Also disable this file for ICU, because the test for the the
+ * Turkish dotted I is not correct for many ICU locales. citext always
+ * uses the default collation, so it's not easy to restrict the test
+ * to the "tr-TR-x-icu" collation where it will succeed.
*/
SELECT getdatabaseencoding() <> 'UTF8' OR
- current_setting('lc_ctype') = 'C'
+ current_setting('lc_ctype') = 'C' OR
+ (SELECT datlocprovider='i' FROM pg_database
+ WHERE datname=current_database())
AS skip_test \gset
\if :skip_test
\quit
/*
* This test must be run in a database with UTF-8 encoding
* and a Unicode-aware locale.
+ *
+ * Also disable this file for ICU, because the test for the the
+ * Turkish dotted I is not correct for many ICU locales. citext always
+ * uses the default collation, so it's not easy to restrict the test
+ * to the "tr-TR-x-icu" collation where it will succeed.
*/
SELECT getdatabaseencoding() <> 'UTF8' OR
- current_setting('lc_ctype') = 'C'
+ current_setting('lc_ctype') = 'C' OR
+ (SELECT datlocprovider='i' FROM pg_database
+ WHERE datname=current_database())
AS skip_test \gset
\if :skip_test
\quit
+-- unaccent is broken if the default collation is provided by ICU and
+-- LC_CTYPE=C
+SELECT current_setting('lc_ctype') = 'C' AND
+ (SELECT datlocprovider='i' FROM pg_database
+ WHERE datname=current_database())
+ AS skip_test \gset
+\if :skip_test
+\quit
+\endif
CREATE EXTENSION unaccent;
-- must have a UTF8 database
SELECT getdatabaseencoding();
--- /dev/null
+-- unaccent is broken if the default collation is provided by ICU and
+-- LC_CTYPE=C
+SELECT current_setting('lc_ctype') = 'C' AND
+ (SELECT datlocprovider='i' FROM pg_database
+ WHERE datname=current_database())
+ AS skip_test \gset
+\if :skip_test
+\quit
+
+-- unaccent is broken if the default collation is provided by ICU and
+-- LC_CTYPE=C
+SELECT current_setting('lc_ctype') = 'C' AND
+ (SELECT datlocprovider='i' FROM pg_database
+ WHERE datname=current_database())
+ AS skip_test \gset
+\if :skip_test
+\quit
+\endif
+
CREATE EXTENSION unaccent;
-- must have a UTF8 database
and character set encoding. These can also be set separately for each
database when it is created. <command>initdb</command> determines those
settings for the template databases, which will serve as the default for
- all other databases. By default, <command>initdb</command> uses the
- locale provider <literal>libc</literal>, takes the locale settings from
- the environment, and determines the encoding from the locale settings.
- This is almost always sufficient, unless there are special requirements.
+ all other databases.
+ </para>
+
+ <para>
+ By default, <command>initdb</command> uses the ICU library to provide
+ locale services if the server was built with ICU support; otherwise it uses
+ the <literal>libc</literal> locale provider (see <xref
+ linkend="locale-providers"/>). To choose the specific ICU locale ID to
+ apply, use the option <option>--icu-locale</option>. Note that for
+ implementation reasons and to support legacy code,
+ <command>initdb</command> will still select and initialize libc locale
+ settings when the ICU locale provider is used.
+ </para>
+
+ <para>
+ Alternatively, <command>initdb</command> can use the locale provider
+ <literal>libc</literal>. To select this option, specify
+ <literal>--locale-provider=libc</literal>, or build the server without ICU
+ support. The <literal>libc</literal> locale provider takes the locale
+ settings from the environment, and determines the encoding from the locale
+ settings. This is almost always sufficient, unless there are special
+ requirements.
</para>
<para>
categories can give nonsensical results, so this should be used with care.
</para>
- <para>
- Alternatively, the ICU library can be used to provide locale services.
- (Again, this only sets the default for subsequently created databases.) To
- select this option, specify <literal>--locale-provider=icu</literal>.
- To choose the specific ICU locale ID to apply, use the option
- <option>--icu-locale</option>. Note that
- for implementation reasons and to support legacy code,
- <command>initdb</command> will still select and initialize libc locale
- settings when the ICU locale provider is used.
- </para>
-
<para>
When <command>initdb</command> runs, it will print out the locale settings
it has chosen. If you have complex requirements or specified multiple
<term><option>--icu-locale=<replaceable>locale</replaceable></option></term>
<listitem>
<para>
- Specifies the ICU locale ID, if the ICU locale provider is used.
+ Specifies the ICU locale when the ICU provider is used. Locale support
+ is described in <xref linkend="locale"/>.
+ </para>
+ <para>
+ If this option is not specified, the locale is inherited from the
+ environment in which <command>initdb</command> runs. The environment's
+ locale is matched to a similar ICU locale name, if possible.
</para>
</listitem>
</varlistentry>
<term><option>--locale-provider={<literal>libc</literal>|<literal>icu</literal>}</option></term>
<listitem>
<para>
- This option sets the locale provider for databases created in the
- new cluster. It can be overridden in the <command>CREATE
+ This option sets the locale provider for databases created in the new
+ cluster. It can be overridden in the <command>CREATE
DATABASE</command> command when new databases are subsequently
- created. The default is <literal>libc</literal>.
+ created. The default is <literal>icu</literal> if the server was
+ built with ICU support; otherwise the default is
+ <literal>libc</literal> (see <xref linkend="locale-providers"/>).
</para>
</listitem>
</varlistentry>
top_builddir = ../../..
include $(top_builddir)/src/Makefile.global
-override CPPFLAGS := -I$(libpq_srcdir) -I$(top_srcdir)/src/timezone $(CPPFLAGS)
+override CPPFLAGS := -I$(libpq_srcdir) -I$(top_srcdir)/src/timezone $(ICU_CFLAGS) $(CPPFLAGS)
# Note: it's important that we link to encnames.o from libpgcommon, not
# from libpq, else we have risks of version skew if we run with a libpq
# should ensure that that happens.
#
# We need libpq only because fe_utils does.
-LDFLAGS_INTERNAL += -L$(top_builddir)/src/fe_utils -lpgfeutils $(libpq_pgport)
+LDFLAGS_INTERNAL += -L$(top_builddir)/src/fe_utils -lpgfeutils $(libpq_pgport) $(ICU_LIBS)
# use system timezone data?
ifneq (,$(with_system_tzdata))
#include <netdb.h>
#include <sys/socket.h>
#include <sys/stat.h>
+#ifdef USE_ICU
+#include <unicode/ucol.h>
+#endif
#include <unistd.h>
#include <signal.h>
#include <time.h>
static char *lc_numeric = NULL;
static char *lc_time = NULL;
static char *lc_messages = NULL;
+#ifdef USE_ICU
+static char locale_provider = COLLPROVIDER_ICU;
+#else
static char locale_provider = COLLPROVIDER_LIBC;
+#endif
static char *icu_locale = NULL;
static char *icu_rules = NULL;
static const char *default_text_search_config = NULL;
return true;
}
+/*
+ * Check that ICU accepts the locale name; or if not specified, retrieve the
+ * default ICU locale.
+ */
+static void
+check_icu_locale(void)
+{
+#ifdef USE_ICU
+ UCollator *collator;
+ UErrorCode status;
+
+ status = U_ZERO_ERROR;
+ collator = ucol_open(icu_locale, &status);
+ if (U_FAILURE(status))
+ {
+ if (icu_locale)
+ pg_fatal("could not open collator for locale \"%s\": %s",
+ icu_locale, u_errorName(status));
+ else
+ pg_fatal("could not open collator for default locale: %s",
+ u_errorName(status));
+ }
+
+ /* if not specified, get locale from default collator */
+ if (icu_locale == NULL)
+ {
+ const char *default_locale;
+
+ status = U_ZERO_ERROR;
+ default_locale = ucol_getLocaleByType(collator, ULOC_VALID_LOCALE,
+ &status);
+ if (U_FAILURE(status))
+ {
+ ucol_close(collator);
+ pg_fatal("could not determine default ICU locale");
+ }
+
+ icu_locale = pg_strdup(default_locale);
+ }
+
+ ucol_close(collator);
+#endif
+}
+
/*
* set up the locale variables
*
if (locale_provider == COLLPROVIDER_ICU)
{
- if (!icu_locale)
- pg_fatal("ICU locale must be specified");
+ check_icu_locale();
/*
* In supported builds, the ICU locale ID will be checked by the
if ($ENV{with_icu} eq 'yes')
{
- command_fails_like(
- [ 'initdb', '--no-sync', '--locale-provider=icu', "$tempdir/data2" ],
- qr/initdb: error: ICU locale must be specified/,
- 'locale provider ICU requires --icu-locale');
-
command_ok(
[
'initdb', '--no-sync',
'--locale-provider=icu', '--icu-locale=@colNumeric=lower',
"$tempdir/dataX"
],
- qr/FATAL: could not open collator for locale/,
+ qr/error: could not open collator for locale/,
'fails for invalid ICU locale');
command_fails_like(
create_sql =>
"CREATE DATABASE dump_test2 LOCALE = 'C' TEMPLATE = template0;",
regexp => qr/^
- \QCREATE DATABASE dump_test2 \E.*\QLOCALE = 'C';\E
+ \QCREATE DATABASE dump_test2 \E.*\QLOCALE = 'C'\E
/xm,
like => { pg_dumpall_dbprivs => 1, },
},
program_options_handling_ok('createdb');
my $node = PostgreSQL::Test::Cluster->new('main');
-$node->init;
+$node->init(extra => ['--locale-provider=libc']);
$node->start;
$node->issues_sql_like(
'-DSHELLPROG="$(SHELL)"' \
$(CPPFLAGS)
-# default encoding for regression tests
-ENCODING = SQL_ASCII
-
ifneq ($(build_os),mingw32)
abs_builddir := $(shell pwd)
else
exec sql connect to 'unix:postgresql://localhost/ecpg2_regression' as main user :user USING "connectpw";
exec sql disconnect main;
- exec sql connect to unix:postgresql://localhost/ecpg2_regression?connect_timeout=180&client_encoding=latin1 as main user regress_ecpg_user1/connectpw;
+ exec sql connect to unix:postgresql://localhost/ecpg2_regression?connect_timeout=180&client_encoding=sql_ascii as main user regress_ecpg_user1/connectpw;
exec sql disconnect main;
exec sql connect to "unix:postgresql://200.46.204.71/ecpg2_regression" as main user regress_ecpg_user1/connectpw;
#line 56 "test5.pgc"
- { ECPGconnect(__LINE__, 0, "unix:postgresql://localhost/ecpg2_regression?connect_timeout=180 & client_encoding=latin1" , "regress_ecpg_user1" , "connectpw" , "main", 0); }
+ { ECPGconnect(__LINE__, 0, "unix:postgresql://localhost/ecpg2_regression?connect_timeout=180 & client_encoding=sql_ascii" , "regress_ecpg_user1" , "connectpw" , "main", 0); }
#line 58 "test5.pgc"
{ ECPGdisconnect(__LINE__, "main");}
[NO_PID]: sqlca: code: 0, state: 00000
[NO_PID]: ecpg_finish: connection main closed
[NO_PID]: sqlca: code: 0, state: 00000
-[NO_PID]: ECPGconnect: opening database ecpg2_regression on <DEFAULT> port <DEFAULT> with options connect_timeout=180 & client_encoding=latin1 for user regress_ecpg_user1
+[NO_PID]: ECPGconnect: opening database ecpg2_regression on <DEFAULT> port <DEFAULT> with options connect_timeout=180 & client_encoding=sql_ascii for user regress_ecpg_user1
[NO_PID]: sqlca: code: 0, state: 00000
[NO_PID]: ecpg_finish: connection main closed
[NO_PID]: sqlca: code: 0, state: 00000
ecpg_regress_args = [
'--dbname=ecpg1_regression,ecpg2_regression',
'--create-role=regress_ecpg_user1,regress_ecpg_user2',
- '--encoding=SQL_ASCII',
]
tests += {
}
my $node1 = PostgreSQL::Test::Cluster->new('node1');
-$node1->init;
+$node1->init(extra => ['--locale-provider=libc']);
$node1->start;
$node1->safe_psql('postgres',
projects / postgresql-pgindent.git / commitdiff