From d87d548cd0304477413a73e9c1d148fb2d40b50d Mon Sep 17 00:00:00 2001 From: Jeff Davis Date: Thu, 23 Feb 2023 10:55:20 -0800 Subject: Refactor to add pg_strcoll(), pg_strxfrm(), and variants. Offers a generally better separation of responsibilities for collation code. Also, a step towards multi-lib ICU, which should be based on a clean separation of the routines required for collation providers. Callers with NUL-terminated strings should call pg_strcoll() or pg_strxfrm(); callers with strings and their length should call the variants pg_strncoll() or pg_strnxfrm(). Reviewed-by: Peter Eisentraut, Peter Geoghegan Discussion: https://postgr.es/m/a581136455c940d7bd0ff482d3a2bd51af25a94f.camel%40j-davis.com --- src/backend/utils/adt/varchar.c | 51 ++++++++++++++++++++++------------------- 1 file changed, 27 insertions(+), 24 deletions(-) (limited to 'src/backend/utils/adt/varchar.c') diff --git a/src/backend/utils/adt/varchar.c b/src/backend/utils/adt/varchar.c index 8ddbae8f51d..9ff3bcbdb75 100644 --- a/src/backend/utils/adt/varchar.c +++ b/src/backend/utils/adt/varchar.c @@ -1024,21 +1024,22 @@ hashbpchar(PG_FUNCTION_ARGS) #ifdef USE_ICU if (mylocale->provider == COLLPROVIDER_ICU) { - int32_t ulen = -1; - UChar *uchar = NULL; - Size bsize; - uint8_t *buf; + Size bsize, rsize; + char *buf; - ulen = icu_to_uchar(&uchar, keydata, keylen); + bsize = pg_strnxfrm(NULL, 0, keydata, keylen, mylocale); + buf = palloc(bsize + 1); - bsize = ucol_getSortKey(mylocale->info.icu.ucol, - uchar, ulen, NULL, 0); - buf = palloc(bsize); - ucol_getSortKey(mylocale->info.icu.ucol, - uchar, ulen, buf, bsize); - pfree(uchar); + rsize = pg_strnxfrm(buf, bsize + 1, keydata, keylen, mylocale); + if (rsize != bsize) + elog(ERROR, "pg_strnxfrm() returned unexpected result"); - result = hash_any(buf, bsize); + /* + * In principle, there's no reason to include the terminating NUL + * character in the hash, but it was done before and the behavior + * must be preserved. + */ + result = hash_any((uint8_t *) buf, bsize + 1); pfree(buf); } @@ -1086,21 +1087,23 @@ hashbpcharextended(PG_FUNCTION_ARGS) #ifdef USE_ICU if (mylocale->provider == COLLPROVIDER_ICU) { - int32_t ulen = -1; - UChar *uchar = NULL; - Size bsize; - uint8_t *buf; + Size bsize, rsize; + char *buf; - ulen = icu_to_uchar(&uchar, keydata, keylen); + bsize = pg_strnxfrm(NULL, 0, keydata, keylen, mylocale); + buf = palloc(bsize + 1); - bsize = ucol_getSortKey(mylocale->info.icu.ucol, - uchar, ulen, NULL, 0); - buf = palloc(bsize); - ucol_getSortKey(mylocale->info.icu.ucol, - uchar, ulen, buf, bsize); - pfree(uchar); + rsize = pg_strnxfrm(buf, bsize + 1, keydata, keylen, mylocale); + if (rsize != bsize) + elog(ERROR, "pg_strnxfrm() returned unexpected result"); - result = hash_any_extended(buf, bsize, PG_GETARG_INT64(1)); + /* + * In principle, there's no reason to include the terminating NUL + * character in the hash, but it was done before and the behavior + * must be preserved. + */ + result = hash_any_extended((uint8_t *) buf, bsize + 1, + PG_GETARG_INT64(1)); pfree(buf); } -- cgit v1.2.3