On 1/3/26 4:05 AM, zengman wrote:
I don't have any major objections, but I noticed a few minor details that might
need a bit more tweaking.
`signficant` -> `significant`
`realtively` -> `relatively`
`if (status != U_BUFFER_OVERFLOW_ERROR && U_FAILURE(status))` -> `if (U_FAILURE(status)
&& status != U_BUFFER_OVERFLOW_ERROR)`
Fixed, thanks!
Andreas
From d01e1ae7c3a9353b3c33c184eaedb95d08a59942 Mon Sep 17 00:00:00 2001
From: Andreas Karlsson <[email protected]>
Date: Tue, 17 Dec 2024 22:47:00 +0100
Subject: [PATCH v5] Use optimized versions of ICU case conversion for UTF-8
Instead of converting to and from UChar when doing case conversions we
use the UTF-8 versions of the functions. This can give a significant
speedup, 30-40%, on short to medium length strings.
The only cost we incur is that we have to allocate a casemap object on
locale initialization for UTF-8 databases but the object is realtively
small and the assumption is that most users will at some point want to
run case conversion functions.
While at it we also remove some duplication in the non-UTF-8 code.
---
src/backend/utils/adt/pg_locale_icu.c | 300 ++++++++++++++++++--------
src/include/utils/pg_locale.h | 2 +
2 files changed, 208 insertions(+), 94 deletions(-)
diff --git a/src/backend/utils/adt/pg_locale_icu.c b/src/backend/utils/adt/pg_locale_icu.c
index de80642f9dc..ac01524b51c 100644
--- a/src/backend/utils/adt/pg_locale_icu.c
+++ b/src/backend/utils/adt/pg_locale_icu.c
@@ -52,6 +52,7 @@ extern pg_locale_t create_pg_locale_icu(Oid collid, MemoryContext context);
#ifdef USE_ICU
extern UCollator *pg_ucol_open(const char *loc_str);
+static UCaseMap *pg_ucasemap_open(const char *loc_str);
static size_t strlower_icu(char *dest, size_t destsize, const char *src,
ssize_t srclen, pg_locale_t locale);
@@ -61,6 +62,14 @@ static size_t strupper_icu(char *dest, size_t destsize, const char *src,
ssize_t srclen, pg_locale_t locale);
static size_t strfold_icu(char *dest, size_t destsize, const char *src,
ssize_t srclen, pg_locale_t locale);
+static size_t strlower_icu_utf8(char *dest, size_t destsize, const char *src,
+ ssize_t srclen, pg_locale_t locale);
+static size_t strtitle_icu_utf8(char *dest, size_t destsize, const char *src,
+ ssize_t srclen, pg_locale_t locale);
+static size_t strupper_icu_utf8(char *dest, size_t destsize, const char *src,
+ ssize_t srclen, pg_locale_t locale);
+static size_t strfold_icu_utf8(char *dest, size_t destsize, const char *src,
+ ssize_t srclen, pg_locale_t locale);
static size_t downcase_ident_icu(char *dst, size_t dstsize, const char *src,
ssize_t srclen, pg_locale_t locale);
static int strncoll_icu(const char *arg1, ssize_t len1,
@@ -111,9 +120,12 @@ static size_t icu_from_uchar(char *dest, size_t destsize,
const UChar *buff_uchar, int32_t len_uchar);
static void icu_set_collation_attributes(UCollator *collator, const char *loc,
UErrorCode *status);
-static int32_t icu_convert_case(ICU_Convert_Func func, pg_locale_t mylocale,
- UChar **buff_dest, UChar *buff_source,
- int32_t len_source);
+static int32_t icu_convert_case(ICU_Convert_Func func, char *dest,
+ size_t destsize, const char *src,
+ ssize_t srclen, pg_locale_t locale);
+static int32_t icu_convert_case_uchar(ICU_Convert_Func func, pg_locale_t mylocale,
+ UChar **buff_dest, UChar *buff_source,
+ int32_t len_source);
static int32_t u_strToTitle_default_BI(UChar *dest, int32_t destCapacity,
const UChar *src, int32_t srcLength,
const char *locale,
@@ -140,6 +152,8 @@ tolower_icu(pg_wchar wc, pg_locale_t locale)
return u_tolower(wc);
}
+static int32_t icu_foldcase_options(const char *locale);
+
static const struct collate_methods collate_methods_icu = {
.strncoll = strncoll_icu,
.strnxfrm = strnxfrm_icu,
@@ -245,6 +259,27 @@ static const struct ctype_methods ctype_methods_icu = {
.wc_tolower = tolower_icu,
};
+static const struct ctype_methods ctype_methods_icu_utf8 = {
+ .strlower = strlower_icu_utf8,
+ .strtitle = strtitle_icu_utf8,
+ .strupper = strupper_icu_utf8,
+ .strfold = strfold_icu_utf8,
+ .downcase_ident = downcase_ident_icu,
+ .wc_isdigit = wc_isdigit_icu,
+ .wc_isalpha = wc_isalpha_icu,
+ .wc_isalnum = wc_isalnum_icu,
+ .wc_isupper = wc_isupper_icu,
+ .wc_islower = wc_islower_icu,
+ .wc_isgraph = wc_isgraph_icu,
+ .wc_isprint = wc_isprint_icu,
+ .wc_ispunct = wc_ispunct_icu,
+ .wc_isspace = wc_isspace_icu,
+ .wc_isxdigit = wc_isxdigit_icu,
+ .wc_iscased = wc_iscased_icu,
+ .wc_toupper = toupper_icu,
+ .wc_tolower = tolower_icu,
+};
+
/*
* ICU still depends on libc for compatibility with certain historical
* behavior for single-byte encodings. See downcase_ident_icu().
@@ -347,10 +382,16 @@ create_pg_locale_icu(Oid collid, MemoryContext context)
result->collate_is_c = false;
result->ctype_is_c = false;
if (GetDatabaseEncoding() == PG_UTF8)
+ {
+ result->icu.ucasemap = pg_ucasemap_open(iculocstr);
result->collate = &collate_methods_icu_utf8;
+ result->ctype = &ctype_methods_icu_utf8;
+ }
else
+ {
result->collate = &collate_methods_icu;
- result->ctype = &ctype_methods_icu;
+ result->ctype = &ctype_methods_icu;
+ }
return result;
#else
@@ -366,41 +407,18 @@ create_pg_locale_icu(Oid collid, MemoryContext context)
#ifdef USE_ICU
/*
- * Wrapper around ucol_open() to handle API differences for older ICU
- * versions.
- *
- * Ensure that no path leaks a UCollator.
+ * In ICU versions 54 and earlier, "und" is not a recognized spelling of the
+ * root locale. If the first component of the locale is "und", replace with
+ * "root" before opening.
*/
-UCollator *
-pg_ucol_open(const char *loc_str)
+static char *
+fix_icu_locale_str(const char *loc_str)
{
- UCollator *collator;
- UErrorCode status;
- const char *orig_str = loc_str;
- char *fixed_str = NULL;
-
- /*
- * Must never open default collator, because it depends on the environment
- * and may change at any time. Should not happen, but check here to catch
- * bugs that might be hard to catch otherwise.
- *
- * NB: the default collator is not the same as the collator for the root
- * locale. The root locale may be specified as the empty string, "und", or
- * "root". The default collator is opened by passing NULL to ucol_open().
- */
- if (loc_str == NULL)
- elog(ERROR, "opening default collator is not supported");
-
- /*
- * In ICU versions 54 and earlier, "und" is not a recognized spelling of
- * the root locale. If the first component of the locale is "und", replace
- * with "root" before opening.
- */
if (U_ICU_VERSION_MAJOR_NUM < 55)
{
char lang[ULOC_LANG_CAPACITY];
+ UErrorCode status = U_ZERO_ERROR;
- status = U_ZERO_ERROR;
uloc_getLanguage(loc_str, lang, ULOC_LANG_CAPACITY, &status);
if (U_FAILURE(status) || status == U_STRING_NOT_TERMINATED_WARNING)
{
@@ -413,15 +431,49 @@ pg_ucol_open(const char *loc_str)
if (strcmp(lang, "und") == 0)
{
const char *remainder = loc_str + strlen("und");
+ char *fixed_str;
fixed_str = palloc(strlen("root") + strlen(remainder) + 1);
strcpy(fixed_str, "root");
strcat(fixed_str, remainder);
- loc_str = fixed_str;
+ return fixed_str;
}
}
+ return NULL;
+}
+
+/*
+ * Wrapper around ucol_open() to handle API differences for older ICU
+ * versions.
+ *
+ * Ensure that no path leaks a UCollator.
+ */
+UCollator *
+pg_ucol_open(const char *loc_str)
+{
+ UCollator *collator;
+ UErrorCode status;
+ const char *orig_str = loc_str;
+ char *fixed_str;
+
+ /*
+ * Must never open default collator, because it depends on the environment
+ * and may change at any time. Should not happen, but check here to catch
+ * bugs that might be hard to catch otherwise.
+ *
+ * NB: the default collator is not the same as the collator for the root
+ * locale. The root locale may be specified as the empty string, "und", or
+ * "root". The default collator is opened by passing NULL to ucol_open().
+ */
+ if (loc_str == NULL)
+ elog(ERROR, "opening default collator is not supported");
+
+ fixed_str = fix_icu_locale_str(loc_str);
+ if (fixed_str)
+ loc_str = fixed_str;
+
status = U_ZERO_ERROR;
collator = ucol_open(loc_str, &status);
if (U_FAILURE(status))
@@ -456,6 +508,37 @@ pg_ucol_open(const char *loc_str)
return collator;
}
+/*
+ * Wrapper around ucasemap_open() to handle API differences for older ICU
+ * versions.
+ *
+ * Additionally makes sure we get the right options for case folding.
+ */
+static UCaseMap *
+pg_ucasemap_open(const char *loc_str)
+{
+ UErrorCode status = U_ZERO_ERROR;
+ UCaseMap *casemap;
+ const char *orig_str = loc_str;
+ char *fixed_str;
+
+ fixed_str = fix_icu_locale_str(loc_str);
+ if (fixed_str)
+ loc_str = fixed_str;
+
+ casemap = ucasemap_open(loc_str, icu_foldcase_options(loc_str), &status);
+ if (U_FAILURE(status))
+ ereport(ERROR,
+ errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+ errmsg("could not open casemap for locale \"%s\": %s",
+ orig_str, u_errorName(status)));
+
+ if (fixed_str != NULL)
+ pfree(fixed_str);
+
+ return casemap;
+}
+
/*
* Create a UCollator with the given locale string and rules.
*
@@ -528,80 +611,84 @@ static size_t
strlower_icu(char *dest, size_t destsize, const char *src, ssize_t srclen,
pg_locale_t locale)
{
- int32_t len_uchar;
- int32_t len_conv;
- UChar *buff_uchar;
- UChar *buff_conv;
- size_t result_len;
-
- len_uchar = icu_to_uchar(&buff_uchar, src, srclen);
- len_conv = icu_convert_case(u_strToLower, locale,
- &buff_conv, buff_uchar, len_uchar);
- result_len = icu_from_uchar(dest, destsize, buff_conv, len_conv);
- pfree(buff_uchar);
- pfree(buff_conv);
-
- return result_len;
+ return icu_convert_case(u_strToLower, dest, destsize, src, srclen, locale);
}
static size_t
strtitle_icu(char *dest, size_t destsize, const char *src, ssize_t srclen,
pg_locale_t locale)
{
- int32_t len_uchar;
- int32_t len_conv;
- UChar *buff_uchar;
- UChar *buff_conv;
- size_t result_len;
-
- len_uchar = icu_to_uchar(&buff_uchar, src, srclen);
- len_conv = icu_convert_case(u_strToTitle_default_BI, locale,
- &buff_conv, buff_uchar, len_uchar);
- result_len = icu_from_uchar(dest, destsize, buff_conv, len_conv);
- pfree(buff_uchar);
- pfree(buff_conv);
-
- return result_len;
+ return icu_convert_case(u_strToTitle_default_BI, dest, destsize, src, srclen, locale);
}
static size_t
strupper_icu(char *dest, size_t destsize, const char *src, ssize_t srclen,
pg_locale_t locale)
{
- int32_t len_uchar;
- int32_t len_conv;
- UChar *buff_uchar;
- UChar *buff_conv;
- size_t result_len;
-
- len_uchar = icu_to_uchar(&buff_uchar, src, srclen);
- len_conv = icu_convert_case(u_strToUpper, locale,
- &buff_conv, buff_uchar, len_uchar);
- result_len = icu_from_uchar(dest, destsize, buff_conv, len_conv);
- pfree(buff_uchar);
- pfree(buff_conv);
-
- return result_len;
+ return icu_convert_case(u_strToUpper, dest, destsize, src, srclen, locale);
}
static size_t
strfold_icu(char *dest, size_t destsize, const char *src, ssize_t srclen,
pg_locale_t locale)
{
- int32_t len_uchar;
- int32_t len_conv;
- UChar *buff_uchar;
- UChar *buff_conv;
- size_t result_len;
+ return icu_convert_case(u_strFoldCase_default, dest, destsize, src, srclen, locale);
+}
- len_uchar = icu_to_uchar(&buff_uchar, src, srclen);
- len_conv = icu_convert_case(u_strFoldCase_default, locale,
- &buff_conv, buff_uchar, len_uchar);
- result_len = icu_from_uchar(dest, destsize, buff_conv, len_conv);
- pfree(buff_uchar);
- pfree(buff_conv);
+static size_t
+strlower_icu_utf8(char *dest, size_t destsize, const char *src, ssize_t srclen,
+ pg_locale_t locale)
+{
+ UErrorCode status = U_ZERO_ERROR;
+ int32_t needed;
- return result_len;
+ needed = ucasemap_utf8ToLower(locale->icu.ucasemap, dest, destsize, src, srclen, &status);
+ if (U_FAILURE(status) && status != U_BUFFER_OVERFLOW_ERROR)
+ ereport(ERROR,
+ errmsg("case conversion failed: %s", u_errorName(status)));
+ return needed;
+}
+
+static size_t
+strtitle_icu_utf8(char *dest, size_t destsize, const char *src, ssize_t srclen,
+ pg_locale_t locale)
+{
+ UErrorCode status = U_ZERO_ERROR;
+ int32_t needed;
+
+ needed = ucasemap_utf8ToTitle(locale->icu.ucasemap, dest, destsize, src, srclen, &status);
+ if (U_FAILURE(status) && status != U_BUFFER_OVERFLOW_ERROR)
+ ereport(ERROR,
+ errmsg("case conversion failed: %s", u_errorName(status)));
+ return needed;
+}
+
+static size_t
+strupper_icu_utf8(char *dest, size_t destsize, const char *src, ssize_t srclen,
+ pg_locale_t locale)
+{
+ UErrorCode status = U_ZERO_ERROR;
+ int32_t needed;
+
+ needed = ucasemap_utf8ToUpper(locale->icu.ucasemap, dest, destsize, src, srclen, &status);
+ if (U_FAILURE(status) && status != U_BUFFER_OVERFLOW_ERROR)
+ ereport(ERROR,
+ errmsg("case conversion failed: %s", u_errorName(status)));
+ return needed;
+}
+
+static size_t
+strfold_icu_utf8(char *dest, size_t destsize, const char *src, ssize_t srclen,
+ pg_locale_t locale)
+{
+ UErrorCode status = U_ZERO_ERROR;
+ int32_t needed;
+
+ needed = ucasemap_utf8FoldCase(locale->icu.ucasemap, dest, destsize, src, srclen, &status);
+ if (U_FAILURE(status) && status != U_BUFFER_OVERFLOW_ERROR)
+ ereport(ERROR,
+ errmsg("case conversion failed: %s", u_errorName(status)));
+ return needed;
}
/*
@@ -829,8 +916,28 @@ icu_from_uchar(char *dest, size_t destsize, const UChar *buff_uchar, int32_t len
}
static int32_t
-icu_convert_case(ICU_Convert_Func func, pg_locale_t mylocale,
- UChar **buff_dest, UChar *buff_source, int32_t len_source)
+icu_convert_case(ICU_Convert_Func func, char *dest, size_t destsize,
+ const char *src, ssize_t srclen, pg_locale_t locale)
+{
+ int32_t len_uchar;
+ int32_t len_conv;
+ UChar *buff_uchar;
+ UChar *buff_conv;
+ size_t result_len;
+
+ len_uchar = icu_to_uchar(&buff_uchar, src, srclen);
+ len_conv = icu_convert_case_uchar(func, locale, &buff_conv,
+ buff_uchar, len_uchar);
+ result_len = icu_from_uchar(dest, destsize, buff_conv, len_conv);
+ pfree(buff_uchar);
+ pfree(buff_conv);
+
+ return result_len;
+}
+
+static int32_t
+icu_convert_case_uchar(ICU_Convert_Func func, pg_locale_t mylocale,
+ UChar **buff_dest, UChar *buff_source, int32_t len_source)
{
UErrorCode status;
int32_t len_dest;
@@ -870,10 +977,17 @@ u_strFoldCase_default(UChar *dest, int32_t destCapacity,
const UChar *src, int32_t srcLength,
const char *locale,
UErrorCode *pErrorCode)
+{
+ return u_strFoldCase(dest, destCapacity, src, srcLength,
+ icu_foldcase_options(locale), pErrorCode);
+}
+
+static int32_t
+icu_foldcase_options(const char *locale)
{
uint32 options = U_FOLD_CASE_DEFAULT;
char lang[3];
- UErrorCode status;
+ UErrorCode status = U_ZERO_ERROR;
/*
* Unlike the ICU APIs for lowercasing, titlecasing, and uppercasing, case
@@ -881,7 +995,6 @@ u_strFoldCase_default(UChar *dest, int32_t destCapacity,
* option relevant to Turkic languages 'az' and 'tr'; check for those
* languages to enable the option.
*/
- status = U_ZERO_ERROR;
uloc_getLanguage(locale, lang, 3, &status);
if (U_SUCCESS(status))
{
@@ -893,8 +1006,7 @@ u_strFoldCase_default(UChar *dest, int32_t destCapacity,
options = U_FOLD_CASE_EXCLUDE_SPECIAL_I;
}
- return u_strFoldCase(dest, destCapacity, src, srcLength,
- options, pErrorCode);
+ return options;
}
/*
diff --git a/src/include/utils/pg_locale.h b/src/include/utils/pg_locale.h
index b1ee5fb0ef5..465f170ba79 100644
--- a/src/include/utils/pg_locale.h
+++ b/src/include/utils/pg_locale.h
@@ -21,6 +21,7 @@
#undef U_SHOW_CPLUSPLUS_HEADER_API
#define U_SHOW_CPLUSPLUS_HEADER_API 0
#include <unicode/ucol.h>
+#include <unicode/ucasemap.h>
#endif
/* use for libc locale names */
@@ -168,6 +169,7 @@ struct pg_locale_struct
const char *locale;
UCollator *ucol;
locale_t lt;
+ UCaseMap *ucasemap;
} icu;
#endif
};
--
2.47.3
