diff options
author | Jeff Davis <jdavis@postgresql.org> | 2023-04-04 10:28:08 -0700 |
---|---|---|
committer | Jeff Davis <jdavis@postgresql.org> | 2023-04-04 10:38:58 -0700 |
commit | ea1db8ae70e5f4ceaae34dc9c06a07d59aaa022e (patch) | |
tree | 2900cfeae37b4c63d24221185bb05708885ef1c7 /src/backend/utils/adt/pg_locale.c | |
parent | d3d53f955cf6ad755ba3682577e0f6fa10106438 (diff) | |
download | postgresql-ea1db8ae70e5f4ceaae34dc9c06a07d59aaa022e.tar.gz postgresql-ea1db8ae70e5f4ceaae34dc9c06a07d59aaa022e.zip |
Canonicalize ICU locale names to language tags.
Convert to BCP47 language tags before storing in the catalog, except
during binary upgrade or when the locale comes from an existing
collation or template database.
The resulting language tags can vary slightly between ICU
versions. For instance, "@colBackwards=yes" is converted to
"und-u-kb-true" in older versions of ICU, and to the simpler (but
equivalent) "und-u-kb" in newer versions.
The process of canonicalizing to a language tag also understands more
input locale string formats than ucol_open(). For instance,
"fr_CA.UTF-8" is misinterpreted by ucol_open() and the region is
ignored; effectively treating it the same as the locale "fr" and
opening the wrong collator. Canonicalization properly interprets the
language and region, resulting in the language tag "fr-CA", which can
then be understood by ucol_open().
This commit fixes a problem in prior versions due to ucol_open()
misinterpreting locale strings as described above. For instance,
creating an ICU collation with locale "fr_CA.UTF-8" would store that
string directly in the catalog, which would later be passed to (and
misinterpreted by) ucol_open(). After this commit, the locale string
will be canonicalized to language tag "fr-CA" in the catalog, which
will be properly understood by ucol_open(). Because this fix affects
the resulting collator, we cannot change the locale string stored in
the catalog for existing databases or collations; otherwise we'd risk
corrupting indexes. Therefore, only canonicalize locales for
newly-created (not upgraded) collations/databases. For similar
reasons, do not backport.
Discussion: https://postgr.es/m/8c7af6820aed94dc7bc259d2aa7f9663518e6137.camel@j-davis.com
Reviewed-by: Peter Eisentraut
Diffstat (limited to 'src/backend/utils/adt/pg_locale.c')
-rw-r--r-- | src/backend/utils/adt/pg_locale.c | 85 |
1 files changed, 85 insertions, 0 deletions
diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c index 9497c20d123..06e73aa012f 100644 --- a/src/backend/utils/adt/pg_locale.c +++ b/src/backend/utils/adt/pg_locale.c @@ -2827,6 +2827,91 @@ icu_set_collation_attributes(UCollator *collator, const char *loc, #endif /* + * Return the BCP47 language tag representation of the requested locale. + * + * This function should be called before passing the string to ucol_open(), + * because conversion to a language tag also performs "level 2 + * canonicalization". In addition to producing a consistent format, level 2 + * canonicalization is able to more accurately interpret different input + * locale string formats, such as POSIX and .NET IDs. + */ +char * +icu_language_tag(const char *loc_str, int elevel) +{ +#ifdef USE_ICU + UErrorCode status; + char lang[ULOC_LANG_CAPACITY]; + char *langtag; + size_t buflen = 32; /* arbitrary starting buffer size */ + const bool strict = true; + + status = U_ZERO_ERROR; + uloc_getLanguage(loc_str, lang, ULOC_LANG_CAPACITY, &status); + if (U_FAILURE(status)) + { + if (elevel > 0) + ereport(elevel, + (errmsg("could not get language from locale \"%s\": %s", + loc_str, u_errorName(status)))); + return NULL; + } + + /* C/POSIX locales aren't handled by uloc_getLanguageTag() */ + if (strcmp(lang, "c") == 0 || strcmp(lang, "posix") == 0) + return pstrdup("en-US-u-va-posix"); + + /* + * A BCP47 language tag doesn't have a clearly-defined upper limit + * (cf. RFC5646 section 4.4). Additionally, in older ICU versions, + * uloc_toLanguageTag() doesn't always return the ultimate length on the + * first call, necessitating a loop. + */ + langtag = palloc(buflen); + while (true) + { + int32_t len; + + status = U_ZERO_ERROR; + len = uloc_toLanguageTag(loc_str, langtag, buflen, strict, &status); + + /* + * If the result fits in the buffer exactly (len == buflen), + * uloc_toLanguageTag() will return success without nul-terminating + * the result. Check for either U_BUFFER_OVERFLOW_ERROR or len >= + * buflen and try again. + */ + if ((status == U_BUFFER_OVERFLOW_ERROR || + (U_SUCCESS(status) && len >= buflen)) && + buflen < MaxAllocSize) + { + buflen = Min(buflen * 2, MaxAllocSize); + langtag = repalloc(langtag, buflen); + continue; + } + + break; + } + + if (U_FAILURE(status)) + { + pfree(langtag); + + if (elevel > 0) + ereport(elevel, + (errmsg("could not convert locale name \"%s\" to language tag: %s", + loc_str, u_errorName(status)))); + return NULL; + } + + return langtag; +#else /* not USE_ICU */ + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("ICU is not supported in this build"))); +#endif /* not USE_ICU */ +} + +/* * Perform best-effort check that the locale is a valid one. */ void |