mirror of
https://github.com/postgres/postgres.git
synced 2025-07-15 19:21:59 +03:00
Further hacking on ICU collation creation and usage.
pg_import_system_collations() refused to create any ICU collations if the current database's encoding didn't support ICU. This is wrongheaded: initdb must initialize pg_collation in an encoding-independent way since it might be used in other databases with different encodings. The reason for the restriction seems to be that get_icu_locale_comment() used icu_from_uchar() to convert the UChar-format display name, and that unsurprisingly doesn't know what to do in unsupported encodings. But by the same token that the initial catalog contents must be encoding-independent, we can't allow non-ASCII characters in the comment strings. So we don't really need icu_from_uchar() here: just check for Unicode codes outside the ASCII range, and if there are none, the format conversion is trivial. If there are some, we can simply not install the comment. (In my testing, this affects only Norwegian Bokmål, which has given us trouble before.) For paranoia's sake, also check for non-ASCII characters in ICU locale names, and skip such locales, as we do for libc locales. I don't currently have a reason to believe that this will ever reject anything, but then again the libc maintainers should have known better too. With just the import changes, ICU collations can be found in pg_collation in databases with unsupported encodings. This resulted in more or less clean failures at runtime, but that's not how things act for unsupported encodings with libc collations. Make it work the same as our traditional behavior for libc collations by having collation lookup take into account whether is_encoding_supported_by_icu(). Adjust documentation to match. Also, expand Table 23.1 to show which encodings are supported by ICU. catversion bump because of likely change in pg_collation/pg_description initial contents in ICU-enabled builds. Discussion: https://postgr.es/m/20c74bc3-d6ca-243d-1bbc-12f17fa4fe9a@gmail.com
This commit is contained in:
@ -353,6 +353,21 @@ pg_collation_actual_version(PG_FUNCTION_ARGS)
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
* Check a string to see if it is pure ASCII
|
||||
*/
|
||||
static bool
|
||||
is_all_ascii(const char *str)
|
||||
{
|
||||
while (*str)
|
||||
{
|
||||
if (IS_HIGHBIT_SET(*str))
|
||||
return false;
|
||||
str++;
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
/* will we use "locale -a" in pg_import_system_collations? */
|
||||
#if defined(HAVE_LOCALE_T) && !defined(WIN32)
|
||||
#define READ_LOCALE_A_OUTPUT
|
||||
@ -431,7 +446,9 @@ get_icu_language_tag(const char *localename)
|
||||
|
||||
/*
|
||||
* Get a comment (specifically, the display name) for an ICU locale.
|
||||
* The result is a palloc'd string.
|
||||
* The result is a palloc'd string, or NULL if we can't get a comment
|
||||
* or find that it's not all ASCII. (We can *not* accept non-ASCII
|
||||
* comments, because the contents of template0 must be encoding-agnostic.)
|
||||
*/
|
||||
static char *
|
||||
get_icu_locale_comment(const char *localename)
|
||||
@ -439,6 +456,7 @@ get_icu_locale_comment(const char *localename)
|
||||
UErrorCode status;
|
||||
UChar displayname[128];
|
||||
int32 len_uchar;
|
||||
int32 i;
|
||||
char *result;
|
||||
|
||||
status = U_ZERO_ERROR;
|
||||
@ -446,11 +464,20 @@ get_icu_locale_comment(const char *localename)
|
||||
displayname, lengthof(displayname),
|
||||
&status);
|
||||
if (U_FAILURE(status))
|
||||
ereport(ERROR,
|
||||
(errmsg("could not get display name for locale \"%s\": %s",
|
||||
localename, u_errorName(status))));
|
||||
return NULL; /* no good reason to raise an error */
|
||||
|
||||
icu_from_uchar(&result, displayname, len_uchar);
|
||||
/* Check for non-ASCII comment (can't use is_all_ascii for this) */
|
||||
for (i = 0; i < len_uchar; i++)
|
||||
{
|
||||
if (displayname[i] > 127)
|
||||
return NULL;
|
||||
}
|
||||
|
||||
/* OK, transcribe */
|
||||
result = palloc(len_uchar + 1);
|
||||
for (i = 0; i < len_uchar; i++)
|
||||
result[i] = displayname[i];
|
||||
result[len_uchar] = '\0';
|
||||
|
||||
return result;
|
||||
}
|
||||
@ -502,7 +529,6 @@ pg_import_system_collations(PG_FUNCTION_ARGS)
|
||||
{
|
||||
size_t len;
|
||||
int enc;
|
||||
bool skip;
|
||||
char alias[NAMEDATALEN];
|
||||
|
||||
len = strlen(localebuf);
|
||||
@ -521,16 +547,7 @@ pg_import_system_collations(PG_FUNCTION_ARGS)
|
||||
* interpret the non-ASCII characters. We can't do much with
|
||||
* those, so we filter them out.
|
||||
*/
|
||||
skip = false;
|
||||
for (i = 0; i < len; i++)
|
||||
{
|
||||
if (IS_HIGHBIT_SET(localebuf[i]))
|
||||
{
|
||||
skip = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
if (skip)
|
||||
if (!is_all_ascii(localebuf))
|
||||
{
|
||||
elog(DEBUG1, "locale name has non-ASCII characters, skipped: \"%s\"", localebuf);
|
||||
continue;
|
||||
@ -642,14 +659,6 @@ pg_import_system_collations(PG_FUNCTION_ARGS)
|
||||
|
||||
/* Load collations known to ICU */
|
||||
#ifdef USE_ICU
|
||||
if (!is_encoding_supported_by_icu(GetDatabaseEncoding()))
|
||||
{
|
||||
ereport(NOTICE,
|
||||
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
|
||||
errmsg("encoding \"%s\" not supported by ICU",
|
||||
pg_encoding_to_char(GetDatabaseEncoding()))));
|
||||
}
|
||||
else
|
||||
{
|
||||
int i;
|
||||
|
||||
@ -661,6 +670,7 @@ pg_import_system_collations(PG_FUNCTION_ARGS)
|
||||
{
|
||||
const char *name;
|
||||
char *langtag;
|
||||
char *icucomment;
|
||||
const char *collcollate;
|
||||
UEnumeration *en;
|
||||
UErrorCode status;
|
||||
@ -674,6 +684,14 @@ pg_import_system_collations(PG_FUNCTION_ARGS)
|
||||
|
||||
langtag = get_icu_language_tag(name);
|
||||
collcollate = U_ICU_VERSION_MAJOR_NUM >= 54 ? langtag : name;
|
||||
|
||||
/*
|
||||
* Be paranoid about not allowing any non-ASCII strings into
|
||||
* pg_collation
|
||||
*/
|
||||
if (!is_all_ascii(langtag) || !is_all_ascii(collcollate))
|
||||
continue;
|
||||
|
||||
collid = CollationCreate(psprintf("%s-x-icu", langtag),
|
||||
nspid, GetUserId(),
|
||||
COLLPROVIDER_ICU, -1,
|
||||
@ -686,8 +704,10 @@ pg_import_system_collations(PG_FUNCTION_ARGS)
|
||||
|
||||
CommandCounterIncrement();
|
||||
|
||||
CreateComments(collid, CollationRelationId, 0,
|
||||
get_icu_locale_comment(name));
|
||||
icucomment = get_icu_locale_comment(name);
|
||||
if (icucomment)
|
||||
CreateComments(collid, CollationRelationId, 0,
|
||||
icucomment);
|
||||
}
|
||||
|
||||
/*
|
||||
@ -708,6 +728,14 @@ pg_import_system_collations(PG_FUNCTION_ARGS)
|
||||
|
||||
langtag = get_icu_language_tag(localeid);
|
||||
collcollate = U_ICU_VERSION_MAJOR_NUM >= 54 ? langtag : localeid;
|
||||
|
||||
/*
|
||||
* Be paranoid about not allowing any non-ASCII strings into
|
||||
* pg_collation
|
||||
*/
|
||||
if (!is_all_ascii(langtag) || !is_all_ascii(collcollate))
|
||||
continue;
|
||||
|
||||
collid = CollationCreate(psprintf("%s-x-icu", langtag),
|
||||
nspid, GetUserId(),
|
||||
COLLPROVIDER_ICU, -1,
|
||||
@ -720,8 +748,10 @@ pg_import_system_collations(PG_FUNCTION_ARGS)
|
||||
|
||||
CommandCounterIncrement();
|
||||
|
||||
CreateComments(collid, CollationRelationId, 0,
|
||||
get_icu_locale_comment(localeid));
|
||||
icucomment = get_icu_locale_comment(name);
|
||||
if (icucomment)
|
||||
CreateComments(collid, CollationRelationId, 0,
|
||||
icucomment);
|
||||
}
|
||||
}
|
||||
if (U_FAILURE(status))
|
||||
|
Reference in New Issue
Block a user