diff options
| author | Peter Eisentraut <peter@eisentraut.org> | 2023-03-08 16:35:42 +0100 |
|---|---|---|
| committer | Peter Eisentraut <peter@eisentraut.org> | 2023-03-08 16:56:37 +0100 |
| commit | 30a53b792959b36f07200dae246067b3adbcc0b9 (patch) | |
| tree | abaa763d759b931b2202bea85ec4800592b31624 /src/backend/utils/adt/pg_locale.c | |
| parent | b1534ed99dc35878e1f9300759e4f10893a32d45 (diff) | |
| download | postgresql-30a53b792959b36f07200dae246067b3adbcc0b9.tar.gz postgresql-30a53b792959b36f07200dae246067b3adbcc0b9.zip | |
Allow tailoring of ICU locales with custom rules
This exposes the ICU facility to add custom collation rules to a
standard collation.
New options are added to CREATE COLLATION, CREATE DATABASE, createdb,
and initdb to set the rules.
Reviewed-by: Laurenz Albe <laurenz.albe@cybertec.at>
Reviewed-by: Daniel Verite <daniel@manitou-mail.org>
Discussion: https://www.postgresql.org/message-id/flat/821c71a4-6ef0-d366-9acf-bb8e367f739f@enterprisedb.com
Diffstat (limited to 'src/backend/utils/adt/pg_locale.c')
| -rw-r--r-- | src/backend/utils/adt/pg_locale.c | 41 |
1 files changed, 40 insertions, 1 deletions
diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c index 4aa5eaa9848..1d3d4d86d39 100644 --- a/src/backend/utils/adt/pg_locale.c +++ b/src/backend/utils/adt/pg_locale.c @@ -69,6 +69,7 @@ #ifdef USE_ICU #include <unicode/ucnv.h> +#include <unicode/ustring.h> #endif #ifdef __GLIBC__ @@ -1421,6 +1422,7 @@ struct pg_locale_struct default_locale; void make_icu_collator(const char *iculocstr, + const char *icurules, struct pg_locale_struct *resultp) { #ifdef USE_ICU @@ -1437,6 +1439,35 @@ make_icu_collator(const char *iculocstr, if (U_ICU_VERSION_MAJOR_NUM < 54) icu_set_collation_attributes(collator, iculocstr); + /* + * If rules are specified, we extract the rules of the standard collation, + * add our own rules, and make a new collator with the combined rules. + */ + if (icurules) + { + const UChar *default_rules; + UChar *agg_rules; + UChar *my_rules; + int32_t length; + + default_rules = ucol_getRules(collator, &length); + icu_to_uchar(&my_rules, icurules, strlen(icurules)); + + agg_rules = palloc_array(UChar, u_strlen(default_rules) + u_strlen(my_rules) + 1); + u_strcpy(agg_rules, default_rules); + u_strcat(agg_rules, my_rules); + + ucol_close(collator); + + status = U_ZERO_ERROR; + collator = ucol_openRules(agg_rules, u_strlen(agg_rules), + UCOL_DEFAULT, UCOL_DEFAULT_STRENGTH, NULL, &status); + if (U_FAILURE(status)) + ereport(ERROR, + (errmsg("could not open collator for locale \"%s\" with rules \"%s\": %s", + iculocstr, icurules, u_errorName(status)))); + } + /* We will leak this string if the caller errors later :-( */ resultp->info.icu.locale = MemoryContextStrdup(TopMemoryContext, iculocstr); resultp->info.icu.ucol = collator; @@ -1608,11 +1639,19 @@ pg_newlocale_from_collation(Oid collid) else if (collform->collprovider == COLLPROVIDER_ICU) { const char *iculocstr; + const char *icurules; datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_colliculocale, &isnull); Assert(!isnull); iculocstr = TextDatumGetCString(datum); - make_icu_collator(iculocstr, &result); + + datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collicurules, &isnull); + if (!isnull) + icurules = TextDatumGetCString(datum); + else + icurules = NULL; + + make_icu_collator(iculocstr, icurules, &result); } datum = SysCacheGetAttr(COLLOID, tp, Anum_pg_collation_collversion, |