From 7dca88aa9f51e7674151bb90506b5305f9107bac Mon Sep 17 00:00:00 2001 From: Jeff Davis Date: Mon, 5 Dec 2022 16:14:18 -0800 Subject: [PATCH v2 5/6] Add get_icu_library_hook. Controls how ICU library symbols are loaded. --- src/backend/commands/collationcmds.c | 6 +-- src/backend/utils/adt/pg_locale.c | 56 ++++++++++++++++++++++---- src/include/utils/pg_locale_internal.h | 10 ++++- 3 files changed, 61 insertions(+), 11 deletions(-) diff --git a/src/backend/commands/collationcmds.c b/src/backend/commands/collationcmds.c index 16b1bcbdc0..f439e832da 100644 --- a/src/backend/commands/collationcmds.c +++ b/src/backend/commands/collationcmds.c @@ -560,7 +560,7 @@ get_icu_language_tag(const char *localename) { char buf[ULOC_FULLNAME_CAPACITY]; UErrorCode status; - pg_icu_library *iculib = get_builtin_icu_library(); + pg_icu_library *iculib = get_icu_library(NULL, NULL, NULL); status = U_ZERO_ERROR; iculib->toLanguageTag(localename, buf, sizeof(buf), true, &status); @@ -586,7 +586,7 @@ get_icu_locale_comment(const char *localename) int32 len_uchar; int32 i; char *result; - pg_icu_library *iculib = get_builtin_icu_library(); + pg_icu_library *iculib = get_icu_library(NULL, NULL, NULL); status = U_ZERO_ERROR; len_uchar = iculib->getDisplayName(localename, "en", @@ -811,7 +811,7 @@ pg_import_system_collations(PG_FUNCTION_ARGS) #ifdef USE_ICU { int i; - pg_icu_library *iculib = get_builtin_icu_library(); + pg_icu_library *iculib = get_icu_library(NULL, NULL, NULL); /* * Start the loop at -1 to sneak in the root locale without too much diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c index 4daff8b7b5..b75a825df6 100644 --- a/src/backend/utils/adt/pg_locale.c +++ b/src/backend/utils/adt/pg_locale.c @@ -109,6 +109,34 @@ char *localized_full_days[7 + 1]; char *localized_abbrev_months[12 + 1]; char *localized_full_months[12 + 1]; +/* + * get_icu_library_hook can be set to control how the pg_icu_library is + * constructed inside a pg_locale_t structure, and therefore which specific + * ICU symbols are called. + * + * Without the hook, Postgres constructs the pg_icu_library from the version + * of ICU that Postgres is linked against at build time. + * + * The hook can instead load the ICU symbols from a different version of the + * ICU library on the system, which can avoid problems when the collation + * subtly changes across different versions of ICU. + * + * If the hook returns true, it indicates that it has successfully filled in + * the pg_icu_library structure that was passed in. If it returns false, + * Postgres will fill in the structure itself. The version of the collation + * returned does not need to match exactly the version that was passed in; + * though if not, Postgres will issue a WARNING. + * + * XXX: For now, the only information the hook has access to is the ICU + * collation name, ICU ctype, and the ICU version string that was obtained at + * the time the collation was created (or when it was last refreshed). We + * should consider what other information can be provided to allow for greater + * control which library is loaded. + */ +#ifdef USE_ICU +get_icu_library_hook_type get_icu_library_hook = NULL; +#endif + /* indicates whether locale information cache is valid */ static bool CurrentLocaleConvValid = false; static bool CurrentLCTimeValid = false; @@ -1463,18 +1491,15 @@ report_newlocale_failure(const char *localename) #endif /* HAVE_LOCALE_T */ #ifdef USE_ICU -pg_icu_library * -get_builtin_icu_library() +static bool +get_builtin_icu_library(pg_icu_library *lib) { - pg_icu_library *lib; - /* * These assignments will fail to compile if an incompatible API change is * made to some future version of ICU, at which point we might need to * consider special treatment for different major version ranges, with * intermediate trampoline functions. */ - lib = palloc0(sizeof(*lib)); lib->getICUVersion = u_getVersion; lib->getUnicodeVersion = u_getUnicodeVersion; lib->getCLDRVersion = ulocdata_getCLDRVersion; @@ -1512,8 +1537,25 @@ get_builtin_icu_library() StaticAssertStmt(U_MAX_VERSION_LENGTH == 4, "ucol_getVersion output buffer size changed incompatibly"); + return true; +} + +pg_icu_library * +get_icu_library(const char *collate, const char *ctype, const char *version) +{ + pg_icu_library *lib = palloc0(sizeof(*lib)); + bool filled = false; + + if (get_icu_library_hook != NULL) + filled = get_icu_library_hook(lib, collate, ctype, version); + + if(!filled) + filled = get_builtin_icu_library(lib); + + Assert(filled); return lib; } + #endif /* @@ -1607,7 +1649,7 @@ pg_newlocale(char provider, bool isdefault, bool deterministic, { UCollator *collator; UErrorCode status; - pg_icu_library *iculib = get_builtin_icu_library(); + pg_icu_library *iculib = get_icu_library(collate, ctype, version); /* collator may be leaked if we encounter an error */ @@ -1926,7 +1968,7 @@ get_collation_actual_version(char collprovider, const char *collcollate) UErrorCode status; UVersionInfo versioninfo; char buf[U_MAX_VERSION_STRING_LENGTH]; - pg_icu_library *iculib = get_builtin_icu_library(); + pg_icu_library *iculib = get_icu_library(NULL, NULL, NULL); status = U_ZERO_ERROR; collator = iculib->openCollator(collcollate, &status); diff --git a/src/include/utils/pg_locale_internal.h b/src/include/utils/pg_locale_internal.h index 54445d8b87..1be0205391 100644 --- a/src/include/utils/pg_locale_internal.h +++ b/src/include/utils/pg_locale_internal.h @@ -162,10 +162,18 @@ struct pg_locale_struct }; #ifdef USE_ICU + +typedef bool (*get_icu_library_hook_type)( + pg_icu_library *lib, const char *collate, const char *ctype, + const char *version); + +extern PGDLLIMPORT get_icu_library_hook_type get_icu_library_hook; + #define PG_ICU_LIB(x) ((x)->info.icu.lib) #define PG_ICU_COL(x) ((x)->info.icu.ucol) -extern pg_icu_library *get_builtin_icu_library(void); +extern pg_icu_library *get_icu_library(const char *collate, const char *ctype, + const char *version); extern int32_t icu_to_uchar(pg_icu_library *lib, UChar **buff_uchar, const char *buff, size_t nbytes); extern int32_t icu_from_uchar(pg_icu_library *lib, char **result, -- 2.34.1