ICU support

Add a column collprovider to pg_collation that determines which library
provides the collation data.  The existing choices are default and libc,
and this adds an icu choice, which uses the ICU4C library.

The pg_locale_t type is changed to a union that contains the
provider-specific locale handles.  Users of locale information are
changed to look into that struct for the appropriate handle to use.

Also add a collversion column that records the version of the collation
when it is created, and check at run time whether it is still the same.
This detects potentially incompatible library upgrades that can corrupt
indexes and other structures.  This is currently only supported by
ICU-provided collations.

initdb initializes the default collation set as before from the `locale
-a` output but also adds all available ICU locales with a "-x-icu"
appended.

Currently, ICU-provided collations can only be explicitly named
collations.  The global database locales are still always libc-provided.

ICU support is enabled by configure --with-icu.

Reviewed-by: Thomas Munro <thomas.munro@enterprisedb.com>
Reviewed-by: Andreas Karlsson <andreas@proxel.se>

1 files changed, 275 insertions, 0 deletions

diff --git a/config/pkg.m4 b/config/pkg.m4
new file mode 100644
index 0000000000..13a8890178
--- /dev/null
+++ b/config/pkg.m4
@@ -0,0 +1,275 @@
+# pkg.m4 - Macros to locate and utilise pkg-config.   -*- Autoconf -*-
+# serial 12 (pkg-config-0.29.2)
+
+dnl Copyright © 2004 Scott James Remnant <scott@netsplit.com>.
+dnl Copyright © 2012-2015 Dan Nicholson <dbn.lists@gmail.com>
+dnl
+dnl This program is free software; you can redistribute it and/or modify
+dnl it under the terms of the GNU General Public License as published by
+dnl the Free Software Foundation; either version 2 of the License, or
+dnl (at your option) any later version.
+dnl
+dnl This program is distributed in the hope that it will be useful, but
+dnl WITHOUT ANY WARRANTY; without even the implied warranty of
+dnl MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+dnl General Public License for more details.
+dnl
+dnl You should have received a copy of the GNU General Public License
+dnl along with this program; if not, write to the Free Software
+dnl Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
+dnl 02111-1307, USA.
+dnl
+dnl As a special exception to the GNU General Public License, if you
+dnl distribute this file as part of a program that contains a
+dnl configuration script generated by Autoconf, you may include it under
+dnl the same distribution terms that you use for the rest of that
+dnl program.
+
+dnl PKG_PREREQ(MIN-VERSION)
+dnl -----------------------
+dnl Since: 0.29
+dnl
+dnl Verify that the version of the pkg-config macros are at least
+dnl MIN-VERSION. Unlike PKG_PROG_PKG_CONFIG, which checks the user's
+dnl installed version of pkg-config, this checks the developer's version
+dnl of pkg.m4 when generating configure.
+dnl
+dnl To ensure that this macro is defined, also add:
+dnl m4_ifndef([PKG_PREREQ],
+dnl     [m4_fatal([must install pkg-config 0.29 or later before running autoconf/autogen])])
+dnl
+dnl See the "Since" comment for each macro you use to see what version
+dnl of the macros you require.
+m4_defun([PKG_PREREQ],
+[m4_define([PKG_MACROS_VERSION], [0.29.2])
+m4_if(m4_version_compare(PKG_MACROS_VERSION, [$1]), -1,
+    [m4_fatal([pkg.m4 version $1 or higher is required but ]PKG_MACROS_VERSION[ found])])
+])dnl PKG_PREREQ
+
+dnl PKG_PROG_PKG_CONFIG([MIN-VERSION])
+dnl ----------------------------------
+dnl Since: 0.16
+dnl
+dnl Search for the pkg-config tool and set the PKG_CONFIG variable to
+dnl first found in the path. Checks that the version of pkg-config found
+dnl is at least MIN-VERSION. If MIN-VERSION is not specified, 0.9.0 is
+dnl used since that's the first version where most current features of
+dnl pkg-config existed.
+AC_DEFUN([PKG_PROG_PKG_CONFIG],
+[m4_pattern_forbid([^_?PKG_[A-Z_]+$])
+m4_pattern_allow([^PKG_CONFIG(_(PATH|LIBDIR|SYSROOT_DIR|ALLOW_SYSTEM_(CFLAGS|LIBS)))?$])
+m4_pattern_allow([^PKG_CONFIG_(DISABLE_UNINSTALLED|TOP_BUILD_DIR|DEBUG_SPEW)$])
+AC_ARG_VAR([PKG_CONFIG], [path to pkg-config utility])
+AC_ARG_VAR([PKG_CONFIG_PATH], [directories to add to pkg-config's search path])
+AC_ARG_VAR([PKG_CONFIG_LIBDIR], [path overriding pkg-config's built-in search path])
+
+if test "x$ac_cv_env_PKG_CONFIG_set" != "xset"; then
+	AC_PATH_TOOL([PKG_CONFIG], [pkg-config])
+fi
+if test -n "$PKG_CONFIG"; then
+	_pkg_min_version=m4_default([$1], [0.9.0])
+	AC_MSG_CHECKING([pkg-config is at least version $_pkg_min_version])
+	if $PKG_CONFIG --atleast-pkgconfig-version $_pkg_min_version; then
+		AC_MSG_RESULT([yes])
+	else
+		AC_MSG_RESULT([no])
+		PKG_CONFIG=""
+	fi
+fi[]dnl
+])dnl PKG_PROG_PKG_CONFIG
+
+dnl PKG_CHECK_EXISTS(MODULES, [ACTION-IF-FOUND], [ACTION-IF-NOT-FOUND])
+dnl -------------------------------------------------------------------
+dnl Since: 0.18
+dnl
+dnl Check to see whether a particular set of modules exists. Similar to
+dnl PKG_CHECK_MODULES(), but does not set variables or print errors.
+dnl
+dnl Please remember that m4 expands AC_REQUIRE([PKG_PROG_PKG_CONFIG])
+dnl only at the first occurence in configure.ac, so if the first place
+dnl it's called might be skipped (such as if it is within an "if", you
+dnl have to call PKG_CHECK_EXISTS manually
+AC_DEFUN([PKG_CHECK_EXISTS],
+[AC_REQUIRE([PKG_PROG_PKG_CONFIG])dnl
+if test -n "$PKG_CONFIG" && \
+    AC_RUN_LOG([$PKG_CONFIG --exists --print-errors "$1"]); then
+  m4_default([$2], [:])
+m4_ifvaln([$3], [else
+  $3])dnl
+fi])
+
+dnl _PKG_CONFIG([VARIABLE], [COMMAND], [MODULES])
+dnl ---------------------------------------------
+dnl Internal wrapper calling pkg-config via PKG_CONFIG and setting
+dnl pkg_failed based on the result.
+m4_define([_PKG_CONFIG],
+[if test -n "$$1"; then
+    pkg_cv_[]$1="$$1"
+ elif test -n "$PKG_CONFIG"; then
+    PKG_CHECK_EXISTS([$3],
+                     [pkg_cv_[]$1=`$PKG_CONFIG --[]$2 "$3" 2>/dev/null`
+		      test "x$?" != "x0" && pkg_failed=yes ],
+		     [pkg_failed=yes])
+ else
+    pkg_failed=untried
+fi[]dnl
+])dnl _PKG_CONFIG
+
+dnl _PKG_SHORT_ERRORS_SUPPORTED
+dnl ---------------------------
+dnl Internal check to see if pkg-config supports short errors.
+AC_DEFUN([_PKG_SHORT_ERRORS_SUPPORTED],
+[AC_REQUIRE([PKG_PROG_PKG_CONFIG])
+if $PKG_CONFIG --atleast-pkgconfig-version 0.20; then
+        _pkg_short_errors_supported=yes
+else
+        _pkg_short_errors_supported=no
+fi[]dnl
+])dnl _PKG_SHORT_ERRORS_SUPPORTED
+
+
+dnl PKG_CHECK_MODULES(VARIABLE-PREFIX, MODULES, [ACTION-IF-FOUND],
+dnl   [ACTION-IF-NOT-FOUND])
+dnl --------------------------------------------------------------
+dnl Since: 0.4.0
+dnl
+dnl Note that if there is a possibility the first call to
+dnl PKG_CHECK_MODULES might not happen, you should be sure to include an
+dnl explicit call to PKG_PROG_PKG_CONFIG in your configure.ac
+AC_DEFUN([PKG_CHECK_MODULES],
+[AC_REQUIRE([PKG_PROG_PKG_CONFIG])dnl
+AC_ARG_VAR([$1][_CFLAGS], [C compiler flags for $1, overriding pkg-config])dnl
+AC_ARG_VAR([$1][_LIBS], [linker flags for $1, overriding pkg-config])dnl
+
+pkg_failed=no
+AC_MSG_CHECKING([for $2])
+
+_PKG_CONFIG([$1][_CFLAGS], [cflags], [$2])
+_PKG_CONFIG([$1][_LIBS], [libs], [$2])
+
+m4_define([_PKG_TEXT], [Alternatively, you may set the environment variables $1[]_CFLAGS
+and $1[]_LIBS to avoid the need to call pkg-config.
+See the pkg-config man page for more details.])
+
+if test $pkg_failed = yes; then
+        AC_MSG_RESULT([no])
+        _PKG_SHORT_ERRORS_SUPPORTED
+        if test $_pkg_short_errors_supported = yes; then
+	        $1[]_PKG_ERRORS=`$PKG_CONFIG --short-errors --print-errors --cflags --libs "$2" 2>&1`
+        else
+	        $1[]_PKG_ERRORS=`$PKG_CONFIG --print-errors --cflags --libs "$2" 2>&1`
+        fi
+	# Put the nasty error message in config.log where it belongs
+	echo "$$1[]_PKG_ERRORS" >&AS_MESSAGE_LOG_FD
+
+	m4_default([$4], [AC_MSG_ERROR(
+[Package requirements ($2) were not met:
+
+$$1_PKG_ERRORS
+
+Consider adjusting the PKG_CONFIG_PATH environment variable if you
+installed software in a non-standard prefix.
+
+_PKG_TEXT])[]dnl
+        ])
+elif test $pkg_failed = untried; then
+        AC_MSG_RESULT([no])
+	m4_default([$4], [AC_MSG_FAILURE(
+[The pkg-config script could not be found or is too old.  Make sure it
+is in your PATH or set the PKG_CONFIG environment variable to the full
+path to pkg-config.
+
+_PKG_TEXT
+
+To get pkg-config, see <http://pkg-config.freedesktop.org/>.])[]dnl
+        ])
+else
+	$1[]_CFLAGS=$pkg_cv_[]$1[]_CFLAGS
+	$1[]_LIBS=$pkg_cv_[]$1[]_LIBS
+        AC_MSG_RESULT([yes])
+	$3
+fi[]dnl
+])dnl PKG_CHECK_MODULES
+
+
+dnl PKG_CHECK_MODULES_STATIC(VARIABLE-PREFIX, MODULES, [ACTION-IF-FOUND],
+dnl   [ACTION-IF-NOT-FOUND])
+dnl ---------------------------------------------------------------------
+dnl Since: 0.29
+dnl
+dnl Checks for existence of MODULES and gathers its build flags with
+dnl static libraries enabled. Sets VARIABLE-PREFIX_CFLAGS from --cflags
+dnl and VARIABLE-PREFIX_LIBS from --libs.
+dnl
+dnl Note that if there is a possibility the first call to
+dnl PKG_CHECK_MODULES_STATIC might not happen, you should be sure to
+dnl include an explicit call to PKG_PROG_PKG_CONFIG in your
+dnl configure.ac.
+AC_DEFUN([PKG_CHECK_MODULES_STATIC],
+[AC_REQUIRE([PKG_PROG_PKG_CONFIG])dnl
+_save_PKG_CONFIG=$PKG_CONFIG
+PKG_CONFIG="$PKG_CONFIG --static"
+PKG_CHECK_MODULES($@)
+PKG_CONFIG=$_save_PKG_CONFIG[]dnl
+])dnl PKG_CHECK_MODULES_STATIC
+
+
+dnl PKG_INSTALLDIR([DIRECTORY])
+dnl -------------------------
+dnl Since: 0.27
+dnl
+dnl Substitutes the variable pkgconfigdir as the location where a module
+dnl should install pkg-config .pc files. By default the directory is
+dnl $libdir/pkgconfig, but the default can be changed by passing
+dnl DIRECTORY. The user can override through the --with-pkgconfigdir
+dnl parameter.
+AC_DEFUN([PKG_INSTALLDIR],
+[m4_pushdef([pkg_default], [m4_default([$1], ['${libdir}/pkgconfig'])])
+m4_pushdef([pkg_description],
+    [pkg-config installation directory @<:@]pkg_default[@:>@])
+AC_ARG_WITH([pkgconfigdir],
+    [AS_HELP_STRING([--with-pkgconfigdir], pkg_description)],,
+    [with_pkgconfigdir=]pkg_default)
+AC_SUBST([pkgconfigdir], [$with_pkgconfigdir])
+m4_popdef([pkg_default])
+m4_popdef([pkg_description])
+])dnl PKG_INSTALLDIR
+
+
+dnl PKG_NOARCH_INSTALLDIR([DIRECTORY])
+dnl --------------------------------
+dnl Since: 0.27
+dnl
+dnl Substitutes the variable noarch_pkgconfigdir as the location where a
+dnl module should install arch-independent pkg-config .pc files. By
+dnl default the directory is $datadir/pkgconfig, but the default can be
+dnl changed by passing DIRECTORY. The user can override through the
+dnl --with-noarch-pkgconfigdir parameter.
+AC_DEFUN([PKG_NOARCH_INSTALLDIR],
+[m4_pushdef([pkg_default], [m4_default([$1], ['${datadir}/pkgconfig'])])
+m4_pushdef([pkg_description],
+    [pkg-config arch-independent installation directory @<:@]pkg_default[@:>@])
+AC_ARG_WITH([noarch-pkgconfigdir],
+    [AS_HELP_STRING([--with-noarch-pkgconfigdir], pkg_description)],,
+    [with_noarch_pkgconfigdir=]pkg_default)
+AC_SUBST([noarch_pkgconfigdir], [$with_noarch_pkgconfigdir])
+m4_popdef([pkg_default])
+m4_popdef([pkg_description])
+])dnl PKG_NOARCH_INSTALLDIR
+
+
+dnl PKG_CHECK_VAR(VARIABLE, MODULE, CONFIG-VARIABLE,
+dnl [ACTION-IF-FOUND], [ACTION-IF-NOT-FOUND])
+dnl -------------------------------------------
+dnl Since: 0.28
+dnl
+dnl Retrieves the value of the pkg-config variable for the given module.
+AC_DEFUN([PKG_CHECK_VAR],
+[AC_REQUIRE([PKG_PROG_PKG_CONFIG])dnl
+AC_ARG_VAR([$1], [value of $3 for $2, overriding pkg-config])dnl
+
+_PKG_CONFIG([$1], [variable="][$3]["], [$2])
+AS_VAR_COPY([$1], [pkg_cv_][$1])
+
+AS_VAR_IF([$1], [""], [$5], [$4])dnl
+])dnl PKG_CHECK_VAR