diff --git a/doc/src/sgml/charset.sgml b/doc/src/sgml/charset.sgml index cca029ea56..f54201fd26 100644 --- a/doc/src/sgml/charset.sgml +++ b/doc/src/sgml/charset.sgml @@ -1,4 +1,4 @@ - + Localization</> @@ -249,7 +249,7 @@ initdb --locale=sv_SE <title>Problems</> <para> - If locale support doesn't work in spite of the explanation above, + If locale support doesn't work according to the explanation above, check that the locale support in your operating system is correctly configured. To check what locales are installed on your system, you can use the command <literal>locale -a</literal> if @@ -301,7 +301,8 @@ initdb --locale=sv_SE <para> The character set support in <productname>PostgreSQL</productname> - allows you to store text in a variety of character sets, including + allows you to store text in a variety of character sets (also called + encodings), including single-byte character sets such as the ISO 8859 series and multiple-byte character sets such as <acronym>EUC</> (Extended Unix Code), UTF-8, and Mule internal code. All supported character sets @@ -314,6 +315,20 @@ initdb --locale=sv_SE databases each with a different character set. </para> + <para> + An important restriction, however, is that each database character set + must be compatible with the server'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. + Since the <envar>LC_CTYPE</> setting is frozen by <command>initdb</>, the + apparent flexibility to use different encodings in different databases + of a cluster is more theoretical than real, except when you select + <literal>C</> or <literal>POSIX</> locale (thus disabling any real locale + awareness). It is likely that these mechanisms will be revisited in future + versions of <productname>PostgreSQL</productname>. + </para> + <sect2 id="multibyte-charset-supported"> <title>Supported Character Sets @@ -716,7 +731,8 @@ initdb -E EUC_JP - You can create a database with a different character set: + If you have selected C or POSIX locale, + you can create a database with a different character set: createdb -E EUC_KR korean @@ -731,7 +747,7 @@ CREATE DATABASE korean WITH ENCODING 'EUC_KR'; The encoding for a database is stored in the system catalog - pg_database. You can see that by using the + pg_database. You can see it by using the option or the \l command of psql. @@ -756,26 +772,23 @@ $ psql -l - Although you can specify any encoding you want for a database, it is - unwise to choose an encoding that is not what is expected by the locale - you have selected. The LC_COLLATE and - LC_CTYPE settings imply a particular encoding, - and locale-dependent operations (such as sorting) are likely to - misinterpret data that is in an incompatible encoding. + On most modern operating systems, PostgreSQL + can determine which character set is implied by an LC_CTYPE + setting, and it will enforce that only the correct database encoding is + used. On older systems it is your responsibility to ensure that you use + the encoding expected by the locale you have selected. A mistake in + this area is likely to lead to strange misbehavior of locale-dependent + operations such as sorting. - Since these locale settings are frozen by initdb, the - apparent flexibility to use different encodings in different databases - of a cluster is more theoretical than real. It is likely that these - mechanisms will be revisited in future versions of - PostgreSQL. - - - - One way to use multiple encodings safely is to set the locale to - C or POSIX during initdb, thus - disabling any real locale awareness. + PostgreSQL will allow superusers to create + databases with SQL_ASCII encoding even when + LC_CTYPE is not C or POSIX. As noted + above, SQL_ASCII does not enforce that the data stored in + the database has any particular encoding, and so this choice poses risks + of locale-dependent misbehavior. Using this combination of settings is + deprecated and may someday be forbidden altogether. diff --git a/doc/src/sgml/ref/create_database.sgml b/doc/src/sgml/ref/create_database.sgml index d4301a73f6..b1b1333245 100644 --- a/doc/src/sgml/ref/create_database.sgml +++ b/doc/src/sgml/ref/create_database.sgml @@ -1,5 +1,5 @@ @@ -107,7 +107,8 @@ CREATE DATABASE name to use the default encoding (namely, the encoding of the template database). The character sets supported by the PostgreSQL server are described in - . + . See below for + additional restrictions. @@ -178,6 +179,21 @@ CREATE DATABASE name See for more information. + + Any character set encoding specified for the new database must be + compatible with the server's LC_CTYPE locale setting. + If LC_CTYPE is C (or equivalently + POSIX), then all encodings are allowed, but for other + locale settings there is only one encoding that will work properly, + and so the apparent freedom to specify an encoding is illusory if + you didn't initialize the database cluster in C locale. + CREATE DATABASE will allow superusers to specify + SQL_ASCII encoding regardless of the locale setting, + but this choice is deprecated and may result in misbehavior of + character-string functions if data that is not encoding-compatible + with the locale is stored in the database. + + The CONNECTION LIMIT option is only enforced approximately; if two new sessions start at about the same time when just one diff --git a/src/Makefile.global.in b/src/Makefile.global.in index 3f81b9e786..cbe2634091 100644 --- a/src/Makefile.global.in +++ b/src/Makefile.global.in @@ -1,5 +1,5 @@ # -*-makefile-*- -# $PostgreSQL: pgsql/src/Makefile.global.in,v 1.238 2007/08/20 08:53:12 petere Exp $ +# $PostgreSQL: pgsql/src/Makefile.global.in,v 1.239 2007/09/28 22:25:49 tgl Exp $ #------------------------------------------------------------------------------ # All PostgreSQL makefiles include this file and use the variables it sets, @@ -423,7 +423,7 @@ endif # # substitute implementations of C library routines (see src/port/) -LIBOBJS = @LIBOBJS@ copydir.o dirmod.o exec.o noblock.o path.o pipe.o pgsleep.o pgstrcasecmp.o qsort.o qsort_arg.o sprompt.o thread.o +LIBOBJS = @LIBOBJS@ LIBS := -lpgport $(LIBS) # add location of libpgport.a to LDFLAGS diff --git a/src/backend/commands/dbcommands.c b/src/backend/commands/dbcommands.c index f627480362..094f51b5cc 100644 --- a/src/backend/commands/dbcommands.c +++ b/src/backend/commands/dbcommands.c @@ -13,13 +13,14 @@ * * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/commands/dbcommands.c,v 1.198 2007/09/03 18:46:29 tgl Exp $ + * $PostgreSQL: pgsql/src/backend/commands/dbcommands.c,v 1.199 2007/09/28 22:25:49 tgl Exp $ * *------------------------------------------------------------------------- */ #include "postgres.h" #include +#include #include #include @@ -96,6 +97,7 @@ createdb(const CreatedbStmt *stmt) const char *dbtemplate = NULL; int encoding = -1; int dbconnlimit = -1; + int ctype_encoding; /* Extract options from the statement node tree */ foreach(option, stmt->options) @@ -254,6 +256,32 @@ createdb(const CreatedbStmt *stmt) (errcode(ERRCODE_WRONG_OBJECT_TYPE), errmsg("invalid server encoding %d", encoding))); + /* + * Check whether encoding matches server locale settings. We allow + * mismatch in two cases: + * + * 1. ctype_encoding = SQL_ASCII, which means either that the locale + * is C/POSIX which works with any encoding, or that we couldn't determine + * the locale's encoding and have to trust the user to get it right. + * + * 2. selected encoding is SQL_ASCII, but only if you're a superuser. + * This is risky but we have historically allowed it --- notably, the + * regression tests require it. + * + * Note: if you change this policy, fix initdb to match. + */ + ctype_encoding = pg_get_encoding_from_locale(NULL); + + if (!(ctype_encoding == encoding || + ctype_encoding == PG_SQL_ASCII || + (encoding == PG_SQL_ASCII && superuser()))) + ereport(ERROR, + (errmsg("encoding %s does not match server's locale %s", + pg_encoding_to_char(encoding), + setlocale(LC_CTYPE, NULL)), + errdetail("The server's LC_CTYPE setting requires encoding %s.", + pg_encoding_to_char(ctype_encoding)))); + /* Resolve default tablespace for new database */ if (dtablespacename && dtablespacename->arg) { diff --git a/src/bin/initdb/initdb.c b/src/bin/initdb/initdb.c index 52f50f195b..1216bbd67c 100644 --- 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 1.142 2007/09/28 15:25:44 tgl Exp $ + * $PostgreSQL: pgsql/src/bin/initdb/initdb.c,v 1.143 2007/09/28 22:25:49 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -54,9 +54,6 @@ #include #include #include -#ifdef HAVE_LANGINFO_H -#include -#endif #include #include "libpq/pqsignal.h" @@ -720,197 +717,6 @@ get_encoding_id(char *encoding_name) exit(1); } -#if defined(HAVE_LANGINFO_H) && defined(CODESET) -/* - * Checks whether the encoding selected for PostgreSQL and the - * encoding used by the system locale match. - */ - -struct encoding_match -{ - enum pg_enc pg_enc_code; - const char *system_enc_name; -}; - -static const struct encoding_match encoding_match_list[] = { - {PG_EUC_JP, "EUC-JP"}, - {PG_EUC_JP, "eucJP"}, - {PG_EUC_JP, "IBM-eucJP"}, - {PG_EUC_JP, "sdeckanji"}, - - {PG_EUC_CN, "EUC-CN"}, - {PG_EUC_CN, "eucCN"}, - {PG_EUC_CN, "IBM-eucCN"}, - {PG_EUC_CN, "GB2312"}, - {PG_EUC_CN, "dechanzi"}, - - {PG_EUC_KR, "EUC-KR"}, - {PG_EUC_KR, "eucKR"}, - {PG_EUC_KR, "IBM-eucKR"}, - {PG_EUC_KR, "deckorean"}, - {PG_EUC_KR, "5601"}, - - {PG_EUC_TW, "EUC-TW"}, - {PG_EUC_TW, "eucTW"}, - {PG_EUC_TW, "IBM-eucTW"}, - {PG_EUC_TW, "cns11643"}, - -#ifdef NOT_VERIFIED - {PG_JOHAB, "???"}, -#endif - - {PG_UTF8, "UTF-8"}, - {PG_UTF8, "utf8"}, - - {PG_LATIN1, "ISO-8859-1"}, - {PG_LATIN1, "ISO8859-1"}, - {PG_LATIN1, "iso88591"}, - - {PG_LATIN2, "ISO-8859-2"}, - {PG_LATIN2, "ISO8859-2"}, - {PG_LATIN2, "iso88592"}, - - {PG_LATIN3, "ISO-8859-3"}, - {PG_LATIN3, "ISO8859-3"}, - {PG_LATIN3, "iso88593"}, - - {PG_LATIN4, "ISO-8859-4"}, - {PG_LATIN4, "ISO8859-4"}, - {PG_LATIN4, "iso88594"}, - - {PG_LATIN5, "ISO-8859-9"}, - {PG_LATIN5, "ISO8859-9"}, - {PG_LATIN5, "iso88599"}, - - {PG_LATIN6, "ISO-8859-10"}, - {PG_LATIN6, "ISO8859-10"}, - {PG_LATIN6, "iso885910"}, - - {PG_LATIN7, "ISO-8859-13"}, - {PG_LATIN7, "ISO8859-13"}, - {PG_LATIN7, "iso885913"}, - - {PG_LATIN8, "ISO-8859-14"}, - {PG_LATIN8, "ISO8859-14"}, - {PG_LATIN8, "iso885914"}, - - {PG_LATIN9, "ISO-8859-15"}, - {PG_LATIN9, "ISO8859-15"}, - {PG_LATIN9, "iso885915"}, - - {PG_LATIN10, "ISO-8859-16"}, - {PG_LATIN10, "ISO8859-16"}, - {PG_LATIN10, "iso885916"}, - - {PG_WIN1252, "CP1252"}, - {PG_WIN1253, "CP1253"}, - {PG_WIN1254, "CP1254"}, - {PG_WIN1255, "CP1255"}, - {PG_WIN1256, "CP1256"}, - {PG_WIN1257, "CP1257"}, - {PG_WIN1258, "CP1258"}, -#ifdef NOT_VERIFIED - {PG_WIN874, "???"}, -#endif - {PG_KOI8R, "KOI8-R"}, - {PG_WIN1251, "CP1251"}, - {PG_WIN866, "CP866"}, - - {PG_ISO_8859_5, "ISO-8859-5"}, - {PG_ISO_8859_5, "ISO8859-5"}, - {PG_ISO_8859_5, "iso88595"}, - - {PG_ISO_8859_6, "ISO-8859-6"}, - {PG_ISO_8859_6, "ISO8859-6"}, - {PG_ISO_8859_6, "iso88596"}, - - {PG_ISO_8859_7, "ISO-8859-7"}, - {PG_ISO_8859_7, "ISO8859-7"}, - {PG_ISO_8859_7, "iso88597"}, - - {PG_ISO_8859_8, "ISO-8859-8"}, - {PG_ISO_8859_8, "ISO8859-8"}, - {PG_ISO_8859_8, "iso88598"}, - - {PG_SQL_ASCII, NULL} /* end marker */ -}; - -static char * -get_encoding_from_locale(const char *ctype) -{ - char *save; - char *sys; - - save = setlocale(LC_CTYPE, NULL); - if (!save) - return NULL; - save = xstrdup(save); - - setlocale(LC_CTYPE, ctype); - sys = nl_langinfo(CODESET); - sys = xstrdup(sys); - - setlocale(LC_CTYPE, save); - free(save); - - return sys; -} - -static void -check_encodings_match(int pg_enc, const char *ctype) -{ - char *sys; - int i; - - sys = get_encoding_from_locale(ctype); - - for (i = 0; encoding_match_list[i].system_enc_name; i++) - { - if (pg_enc == encoding_match_list[i].pg_enc_code - && pg_strcasecmp(sys, encoding_match_list[i].system_enc_name) == 0) - { - free(sys); - return; - } - } - - fprintf(stderr, - _("%s: warning: encoding mismatch\n"), progname); - fprintf(stderr, - _("The encoding you selected (%s) and the encoding that the selected\n" - "locale uses (%s) are not known to match. This might lead to\n" - "misbehavior in various character string processing functions. To fix\n" - "this situation, rerun %s and either do not specify an encoding\n" - "explicitly, or choose a matching combination.\n"), - pg_encoding_to_char(pg_enc), sys, progname); - - free(sys); - return; -} - -static int -find_matching_encoding(const char *ctype) -{ - char *sys; - int i; - - sys = get_encoding_from_locale(ctype); - - for (i = 0; encoding_match_list[i].system_enc_name; i++) - { - if (pg_strcasecmp(sys, encoding_match_list[i].system_enc_name) == 0) - { - free(sys); - return encoding_match_list[i].pg_enc_code; - } - } - - free(sys); - return -1; -} -#endif /* HAVE_LANGINFO_H && CODESET */ - - /* * Support for determining the best default text search configuration. * We key this off LC_CTYPE, after stripping its encoding indicator if any. @@ -2909,10 +2715,6 @@ main(int argc, char *argv[]) if (strlen(username) == 0) username = effective_user; - - if (strlen(encoding)) - encodingid = get_encoding_id(encoding); - set_input(&bki_file, "postgres.bki"); set_input(&desc_file, "postgres.description"); set_input(&shdesc_file, "postgres.shdescription"); @@ -2988,32 +2790,58 @@ main(int argc, char *argv[]) lc_time); } -#if defined(HAVE_LANGINFO_H) && defined(CODESET) - if (strcmp(lc_ctype, "C") != 0 && strcmp(lc_ctype, "POSIX") != 0) + if (strlen(encoding) == 0) { - if (strlen(encoding) == 0) - { - int tmp; + int ctype_enc; - tmp = find_matching_encoding(lc_ctype); - if (tmp == -1) - { - fprintf(stderr, _("%s: could not find suitable encoding for locale \"%s\"\n"), progname, lc_ctype); - fprintf(stderr, _("Rerun %s with the -E option.\n"), progname); - fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); - exit(1); - } - else - { - encodingid = encodingid_to_string(tmp); - printf(_("The default database encoding has accordingly been set to %s.\n"), - pg_encoding_to_char(tmp)); - } + ctype_enc = pg_get_encoding_from_locale(lc_ctype); + + if (ctype_enc == PG_SQL_ASCII && + !(pg_strcasecmp(lc_ctype, "C") == 0 || + pg_strcasecmp(lc_ctype, "POSIX") == 0)) + { + fprintf(stderr, _("%s: could not find suitable encoding for locale \"%s\"\n"), + progname, lc_ctype); + fprintf(stderr, _("Rerun %s with the -E option.\n"), progname); + fprintf(stderr, _("Try \"%s --help\" for more information.\n"), + progname); + exit(1); } else - check_encodings_match(atoi(encodingid), lc_ctype); + { + encodingid = encodingid_to_string(ctype_enc); + printf(_("The default database encoding has accordingly been set to %s.\n"), + pg_encoding_to_char(ctype_enc)); + } + } + 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)) + { + 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); + } } -#endif /* HAVE_LANGINFO_H && CODESET */ if (strlen(default_text_search_config) == 0) { diff --git a/src/include/port.h b/src/include/port.h index 77709d45b7..2e46f7cdbc 100644 --- a/src/include/port.h +++ b/src/include/port.h @@ -6,7 +6,7 @@ * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California * - * $PostgreSQL: pgsql/src/include/port.h,v 1.112 2007/07/12 23:28:49 tgl Exp $ + * $PostgreSQL: pgsql/src/include/port.h,v 1.113 2007/09/28 22:25:49 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -391,4 +391,7 @@ typedef int (*qsort_arg_comparator) (const void *a, const void *b, void *arg); extern void qsort_arg(void *base, size_t nel, size_t elsize, qsort_arg_comparator cmp, void *arg); +/* port/chklocale.c */ +extern int pg_get_encoding_from_locale(const char *ctype); + #endif /* PG_PORT_H */ diff --git a/src/port/Makefile b/src/port/Makefile index 5ab4dd0a78..b1131599e3 100644 --- a/src/port/Makefile +++ b/src/port/Makefile @@ -14,8 +14,12 @@ # libpgport_srv.a - contains object files without FRONTEND defined, # for use only by the backend binaries # +# LIBOBJS is set by configure (via Makefile.global) to be the list of +# object files that are conditionally needed depending on platform. +# OBJS adds additional object files that are always compiled. +# # IDENTIFICATION -# $PostgreSQL: pgsql/src/port/Makefile,v 1.34 2007/02/09 15:56:00 petere Exp $ +# $PostgreSQL: pgsql/src/port/Makefile,v 1.35 2007/09/28 22:25:49 tgl Exp $ # #------------------------------------------------------------------------- @@ -26,8 +30,10 @@ include $(top_builddir)/src/Makefile.global override CPPFLAGS := -I$(top_builddir)/src/port -DFRONTEND $(CPPFLAGS) LIBS += $(PTHREAD_LIBS) -# Replace all object files so they use FRONTEND define -LIBOBJS_SRV = $(LIBOBJS:%.o=%_srv.o) +OBJS = $(LIBOBJS) chklocale.o copydir.o dirmod.o exec.o noblock.o path.o pipe.o pgsleep.o pgstrcasecmp.o qsort.o qsort_arg.o sprompt.o thread.o + +# foo_srv.o and foo.o are both built from foo.c, but only foo.o has -DFRONTEND +OBJS_SRV = $(OBJS:%.o=%_srv.o) all: libpgport.a libpgport_srv.a @@ -41,32 +47,29 @@ installdirs: uninstall: rm -f '$(DESTDIR)$(libdir)/libpgport.a' -libpgport.a: $(LIBOBJS) +libpgport.a: $(OBJS) $(AR) $(AROPT) $@ $^ +# thread.o needs PTHREAD_CFLAGS (but thread_srv.o does not) thread.o: thread.c $(CC) $(CFLAGS) $(CPPFLAGS) $(PTHREAD_CFLAGS) -c $< -path.o: path.c pg_config_paths.h - -path_srv.o: path.c pg_config_paths.h - # # Server versions of object files # -libpgport_srv.a: $(LIBOBJS_SRV) +libpgport_srv.a: $(OBJS_SRV) $(AR) $(AROPT) $@ $^ %_srv.o: %.c $(CC) $(CFLAGS) $(subst -DFRONTEND,, $(CPPFLAGS)) -c $< -o $@ -# No thread flags for server version -thread_srv.o: thread.c - $(CC) $(CFLAGS) $(subst -DFRONTEND,, $(CPPFLAGS)) -c $< -o $@ - # Dependency is to ensure that path changes propagate -# + +path.o: path.c pg_config_paths.h + +path_srv.o: path.c pg_config_paths.h + # We create a separate file rather than put these in pg_config.h # because many of these values come from makefiles and are not # available to configure. @@ -84,4 +87,4 @@ pg_config_paths.h: $(top_builddir)/src/Makefile.global echo "#define MANDIR \"$(mandir)\"" >>$@ clean distclean maintainer-clean: - rm -f libpgport.a libpgport_srv.a $(LIBOBJS) $(LIBOBJS_SRV) pg_config_paths.h + rm -f libpgport.a libpgport_srv.a $(OBJS) $(OBJS_SRV) pg_config_paths.h diff --git a/src/port/chklocale.c b/src/port/chklocale.c new file mode 100644 index 0000000000..399438fe77 --- /dev/null +++ b/src/port/chklocale.c @@ -0,0 +1,246 @@ +/*------------------------------------------------------------------------- + * + * chklocale.c + * Functions for handling locale-related info + * + * + * Copyright (c) 1996-2007, PostgreSQL Global Development Group + * + * + * IDENTIFICATION + * $PostgreSQL: pgsql/src/port/chklocale.c,v 1.1 2007/09/28 22:25:49 tgl Exp $ + * + *------------------------------------------------------------------------- + */ + +#ifndef FRONTEND +#include "postgres.h" +#else +#include "postgres_fe.h" +#endif + +#include +#ifdef HAVE_LANGINFO_H +#include +#endif + +#include "mb/pg_wchar.h" + + +#if defined(HAVE_LANGINFO_H) && defined(CODESET) + +/* + * This table needs to recognize all the CODESET spellings for supported + * backend encodings. We don't need to handle frontend-only encodings. + * Note that we search the table with pg_strcasecmp(), so variant + * capitalizations don't need their own entries. + */ +struct encoding_match +{ + enum pg_enc pg_enc_code; + const char *system_enc_name; +}; + +static const struct encoding_match encoding_match_list[] = { + {PG_EUC_JP, "EUC-JP"}, + {PG_EUC_JP, "eucJP"}, + {PG_EUC_JP, "IBM-eucJP"}, + {PG_EUC_JP, "sdeckanji"}, + + {PG_EUC_CN, "EUC-CN"}, + {PG_EUC_CN, "eucCN"}, + {PG_EUC_CN, "IBM-eucCN"}, + {PG_EUC_CN, "GB2312"}, + {PG_EUC_CN, "dechanzi"}, + + {PG_EUC_KR, "EUC-KR"}, + {PG_EUC_KR, "eucKR"}, + {PG_EUC_KR, "IBM-eucKR"}, + {PG_EUC_KR, "deckorean"}, + {PG_EUC_KR, "5601"}, + + {PG_EUC_TW, "EUC-TW"}, + {PG_EUC_TW, "eucTW"}, + {PG_EUC_TW, "IBM-eucTW"}, + {PG_EUC_TW, "cns11643"}, + + {PG_UTF8, "UTF-8"}, + {PG_UTF8, "utf8"}, + + {PG_LATIN1, "ISO-8859-1"}, + {PG_LATIN1, "ISO8859-1"}, + {PG_LATIN1, "iso88591"}, + + {PG_LATIN2, "ISO-8859-2"}, + {PG_LATIN2, "ISO8859-2"}, + {PG_LATIN2, "iso88592"}, + + {PG_LATIN3, "ISO-8859-3"}, + {PG_LATIN3, "ISO8859-3"}, + {PG_LATIN3, "iso88593"}, + + {PG_LATIN4, "ISO-8859-4"}, + {PG_LATIN4, "ISO8859-4"}, + {PG_LATIN4, "iso88594"}, + + {PG_LATIN5, "ISO-8859-9"}, + {PG_LATIN5, "ISO8859-9"}, + {PG_LATIN5, "iso88599"}, + + {PG_LATIN6, "ISO-8859-10"}, + {PG_LATIN6, "ISO8859-10"}, + {PG_LATIN6, "iso885910"}, + + {PG_LATIN7, "ISO-8859-13"}, + {PG_LATIN7, "ISO8859-13"}, + {PG_LATIN7, "iso885913"}, + + {PG_LATIN8, "ISO-8859-14"}, + {PG_LATIN8, "ISO8859-14"}, + {PG_LATIN8, "iso885914"}, + + {PG_LATIN9, "ISO-8859-15"}, + {PG_LATIN9, "ISO8859-15"}, + {PG_LATIN9, "iso885915"}, + + {PG_LATIN10, "ISO-8859-16"}, + {PG_LATIN10, "ISO8859-16"}, + {PG_LATIN10, "iso885916"}, + + {PG_KOI8R, "KOI8-R"}, + + {PG_WIN1252, "CP1252"}, + {PG_WIN1253, "CP1253"}, + {PG_WIN1254, "CP1254"}, + {PG_WIN1255, "CP1255"}, + {PG_WIN1256, "CP1256"}, + {PG_WIN1257, "CP1257"}, + {PG_WIN1258, "CP1258"}, +#ifdef NOT_VERIFIED + {PG_WIN874, "???"}, +#endif + {PG_WIN1251, "CP1251"}, + {PG_WIN866, "CP866"}, + + {PG_ISO_8859_5, "ISO-8859-5"}, + {PG_ISO_8859_5, "ISO8859-5"}, + {PG_ISO_8859_5, "iso88595"}, + + {PG_ISO_8859_6, "ISO-8859-6"}, + {PG_ISO_8859_6, "ISO8859-6"}, + {PG_ISO_8859_6, "iso88596"}, + + {PG_ISO_8859_7, "ISO-8859-7"}, + {PG_ISO_8859_7, "ISO8859-7"}, + {PG_ISO_8859_7, "iso88597"}, + + {PG_ISO_8859_8, "ISO-8859-8"}, + {PG_ISO_8859_8, "ISO8859-8"}, + {PG_ISO_8859_8, "iso88598"}, + + {PG_SQL_ASCII, NULL} /* end marker */ +}; + + +/* + * Given a setting for LC_CTYPE, return the Postgres ID of the associated + * encoding, if we can determine it. + * + * Pass in NULL to get the encoding for the current locale setting. + * + * If the result is PG_SQL_ASCII, callers should treat it as being compatible + * with any desired encoding. We return this if the locale is C/POSIX or we + * can't determine the encoding. + */ +int +pg_get_encoding_from_locale(const char *ctype) +{ + char *sys; + int i; + + if (ctype) + { + char *save; + + save = setlocale(LC_CTYPE, NULL); + if (!save) + return PG_SQL_ASCII; /* setlocale() broken? */ + /* must copy result, or it might change after setlocale */ + save = strdup(save); + if (!save) + return PG_SQL_ASCII; /* out of memory; unlikely */ + + if (!setlocale(LC_CTYPE, ctype)) + { + free(save); + return PG_SQL_ASCII; /* bogus ctype passed in? */ + } + + sys = nl_langinfo(CODESET); + if (sys) + sys = strdup(sys); + + setlocale(LC_CTYPE, save); + free(save); + } + else + { + /* much easier... */ + ctype = setlocale(LC_CTYPE, NULL); + if (!ctype) + return PG_SQL_ASCII; /* setlocale() broken? */ + sys = nl_langinfo(CODESET); + if (sys) + sys = strdup(sys); + } + + if (!sys) + return PG_SQL_ASCII; /* out of memory; unlikely */ + + if (pg_strcasecmp(ctype, "C") == 0 || pg_strcasecmp(ctype, "POSIX") == 0) + { + free(sys); + return PG_SQL_ASCII; + } + + for (i = 0; encoding_match_list[i].system_enc_name; i++) + { + if (pg_strcasecmp(sys, encoding_match_list[i].system_enc_name) == 0) + { + free(sys); + return encoding_match_list[i].pg_enc_code; + } + } + + /* + * We print a warning if we got a CODESET string but couldn't recognize + * it. This means we need another entry in the table. + */ +#ifdef FRONTEND + fprintf(stderr, _("could not determine encoding for locale \"%s\": codeset is \"%s\""), + ctype, sys); + /* keep newline separate so there's only one translatable string */ + fputc('\n', stderr); +#else + ereport(WARNING, + (errmsg("could not determine encoding for locale \"%s\": codeset is \"%s\"", + ctype, sys), + errdetail("Please report this to ."))); +#endif + + free(sys); + return PG_SQL_ASCII; +} + +#else /* !(HAVE_LANGINFO_H && CODESET) */ + +/* + * stub if no platform support + */ +int +pg_get_encoding_from_locale(const char *ctype) +{ + return PG_SQL_ASCII; +} + +#endif /* HAVE_LANGINFO_H && CODESET */