Reject use of ucol_strcollUTF8() before ICU 53

Various bugs can cause crashes, so don't use that function before ICU
53.  It will fall back to the code path used for other encodings.

Since we now tie the function availability to an ICU version, we don't
need the configure test anymore.  That also resolves the issue that the
test result was previously hardcoded for Windows.

researched by Daniel Verite <[email protected]>, Peter Geoghegan
<[email protected]>, Tom Lane <[email protected]>

Discussion: https://www.postgresql.org/message-id/flat/f1438ec6-22aa-4029-9a3b-26f79d330e72%40manitou-mail.org

5 files changed, 13 insertions, 60 deletions

diff --git a/configure b/configure
index 7218a31407..cc6471bba6 100755
--- a/configure
+++ b/configure
@@ -13923,44 +13923,6 @@ fi
 
 
 
-  # ucol_strcollUTF8() appeared in ICU 50, so check if we have it.
-  # ICU functions are macros, so we need to do this the long way.
-  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for ucol_strcollUTF8" >&5
-$as_echo_n "checking for ucol_strcollUTF8... " >&6; }
-if ${pgac_cv_func_ucol_strcollUTF8+:} false; then :
-  $as_echo_n "(cached) " >&6
-else
-  ac_save_LIBS=$LIBS
-LIBS="$ICU_LIBS $LIBS"
-cat confdefs.h - <<_ACEOF >conftest.$ac_ext
-/* end confdefs.h.  */
-#include <unicode/ucol.h>
-
-int
-main ()
-{
-ucol_strcollUTF8(NULL, NULL, 0, NULL, 0, NULL);
-  ;
-  return 0;
-}
-_ACEOF
-if ac_fn_c_try_link "$LINENO"; then :
-  pgac_cv_func_ucol_strcollUTF8=yes
-else
-  pgac_cv_func_ucol_strcollUTF8=no
-fi
-rm -f core conftest.err conftest.$ac_objext \
-    conftest$ac_exeext conftest.$ac_ext
-LIBS=$ac_save_LIBS
-fi
-{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_func_ucol_strcollUTF8" >&5
-$as_echo "$pgac_cv_func_ucol_strcollUTF8" >&6; }
-  if test "$pgac_cv_func_ucol_strcollUTF8" = yes ; then
-
-$as_echo "#define HAVE_UCOL_STRCOLLUTF8 1" >>confdefs.h
-
-  fi
-
   CPPFLAGS=$ac_save_CPPFLAGS
 fi
 
diff --git a/configure.in b/configure.in
index 44987cdc1e..5c036e7f42 100644
--- a/configure.in
+++ b/configure.in
@@ -1662,22 +1662,6 @@ if test "$with_icu" = yes; then
   AC_CHECK_HEADER(unicode/ucol.h, [],
         [AC_MSG_ERROR([header file <unicode/ucol.h> is required for ICU])])
 
-  # ucol_strcollUTF8() appeared in ICU 50, so check if we have it.
-  # ICU functions are macros, so we need to do this the long way.
-  AC_CACHE_CHECK([for ucol_strcollUTF8], [pgac_cv_func_ucol_strcollUTF8],
-[ac_save_LIBS=$LIBS
-LIBS="$ICU_LIBS $LIBS"
-AC_LINK_IFELSE([AC_LANG_PROGRAM(
-[#include <unicode/ucol.h>
-],
-[ucol_strcollUTF8(NULL, NULL, 0, NULL, 0, NULL);])],
-[pgac_cv_func_ucol_strcollUTF8=yes],
-[pgac_cv_func_ucol_strcollUTF8=no])
-LIBS=$ac_save_LIBS])
-  if test "$pgac_cv_func_ucol_strcollUTF8" = yes ; then
-    AC_DEFINE([HAVE_UCOL_STRCOLLUTF8], 1, [Define to 1 if you have the `ucol_strcollUTF8' function.])
-  fi
-
   CPPFLAGS=$ac_save_CPPFLAGS
 fi
 
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 7a05c7e5b8..dcb7a1a320 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -606,9 +606,6 @@
 /* Define to 1 if you have the external array `tzname'. */
 #undef HAVE_TZNAME
 
-/* Define to 1 if you have the `ucol_strcollUTF8' function. */
-#undef HAVE_UCOL_STRCOLLUTF8
-
 /* Define to 1 if you have the <ucred.h> header file. */
 #undef HAVE_UCRED_H
 
diff --git a/src/include/pg_config.h.win32 b/src/include/pg_config.h.win32
index 9d3021ced8..7f60670fa6 100644
--- a/src/include/pg_config.h.win32
+++ b/src/include/pg_config.h.win32
@@ -457,9 +457,6 @@
 /* Define to 1 if you have the external array `tzname'. */
 /* #undef HAVE_TZNAME */
 
-/* Define to 1 if you have the `ucol_strcollUTF8' function. */
-#define HAVE_UCOL_STRCOLLUTF8 1
-
 /* Define to 1 if the system has the type `uint64'. */
 /* #undef HAVE_UINT64 */
 
diff --git a/src/include/utils/pg_locale.h b/src/include/utils/pg_locale.h
index a02d27ba26..f3e04d4d8c 100644
--- a/src/include/utils/pg_locale.h
+++ b/src/include/utils/pg_locale.h
@@ -21,6 +21,19 @@
 
 #include "utils/guc.h"
 
+#ifdef USE_ICU
+/*
+ * ucol_strcollUTF8() was introduced in ICU 50, but it is buggy before ICU 53.
+ * (see
+ * <https://www.postgresql.org/message-id/flat/f1438ec6-22aa-4029-9a3b-26f79d330e72%40manitou-mail.org>)
+ */
+#if U_ICU_VERSION_MAJOR_NUM >= 53
+#define HAVE_UCOL_STRCOLLUTF8 1
+#else
+#undef HAVE_UCOL_STRCOLLUTF8
+#endif
+#endif
+
 
 /* GUC settings */
 extern char *locale_messages;