From 477cbb438c44ef241599f07b4d8b427c96b57832 Mon Sep 17 00:00:00 2001 From: Jeff Davis Date: Wed, 25 Sep 2024 14:35:11 -0700 Subject: [PATCH v5 2/8] Move libc-specific code from pg_locale.c into pg_locale_libc.c. --- src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/meson.build | 1 + src/backend/utils/adt/pg_locale.c | 294 +--------------------- src/backend/utils/adt/pg_locale_libc.c | 326 +++++++++++++++++++++++++ 4 files changed, 337 insertions(+), 285 deletions(-) create mode 100644 src/backend/utils/adt/pg_locale_libc.c diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index bb416c86744..85e5eaf32eb 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -80,6 +80,7 @@ OBJS = \ partitionfuncs.o \ pg_locale.o \ pg_locale_icu.o \ + pg_locale_libc.o \ pg_lsn.o \ pg_upgrade_support.o \ pgstatfuncs.o \ diff --git a/src/backend/utils/adt/meson.build b/src/backend/utils/adt/meson.build index 19a27465a29..f73f294b8f5 100644 --- a/src/backend/utils/adt/meson.build +++ b/src/backend/utils/adt/meson.build @@ -67,6 +67,7 @@ backend_sources += files( 'partitionfuncs.c', 'pg_locale.c', 'pg_locale_icu.c', + 'pg_locale_libc.c', 'pg_lsn.c', 'pg_upgrade_support.c', 'pgstatfuncs.c', diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c index 9ca8cacffbd..ce80ead86dd 100644 --- a/src/backend/utils/adt/pg_locale.c +++ b/src/backend/utils/adt/pg_locale.c @@ -103,6 +103,15 @@ extern size_t strnxfrm_prefix_icu(char *dest, size_t destsize, pg_locale_t locale); #endif +extern locale_t make_libc_collator(const char *collate, + const char *ctype); +extern int strncoll_libc(const char *arg1, ssize_t len1, + const char *arg2, ssize_t len2, + pg_locale_t locale); +extern size_t strnxfrm_libc(char *dest, size_t destsize, + const char *src, ssize_t srclen, + pg_locale_t locale); + /* GUC settings */ char *locale_messages; char *locale_monetary; @@ -1256,108 +1265,6 @@ lookup_collation_cache(Oid collation) return cache_entry; } -/* simple subroutine for reporting errors from newlocale() */ -static void -report_newlocale_failure(const char *localename) -{ - int save_errno; - - /* - * Windows doesn't provide any useful error indication from - * _create_locale(), and BSD-derived platforms don't seem to feel they - * need to set errno either (even though POSIX is pretty clear that - * newlocale should do so). So, if errno hasn't been set, assume ENOENT - * is what to report. - */ - if (errno == 0) - errno = ENOENT; - - /* - * ENOENT means "no such locale", not "no such file", so clarify that - * errno with an errdetail message. - */ - save_errno = errno; /* auxiliary funcs might change errno */ - ereport(ERROR, - (errcode(ERRCODE_INVALID_PARAMETER_VALUE), - errmsg("could not create locale \"%s\": %m", - localename), - (save_errno == ENOENT ? - errdetail("The operating system could not find any locale data for the locale name \"%s\".", - localename) : 0))); -} - -/* - * Create a locale_t with the given collation and ctype. - * - * The "C" and "POSIX" locales are not actually handled by libc, so return - * NULL. - * - * Ensure that no path leaks a locale_t. - */ -static locale_t -make_libc_collator(const char *collate, const char *ctype) -{ - locale_t loc = 0; - - if (strcmp(collate, ctype) == 0) - { - if (strcmp(ctype, "C") != 0 && strcmp(ctype, "POSIX") != 0) - { - /* Normal case where they're the same */ - errno = 0; -#ifndef WIN32 - loc = newlocale(LC_COLLATE_MASK | LC_CTYPE_MASK, collate, - NULL); -#else - loc = _create_locale(LC_ALL, collate); -#endif - if (!loc) - report_newlocale_failure(collate); - } - } - else - { -#ifndef WIN32 - /* We need two newlocale() steps */ - locale_t loc1 = 0; - - if (strcmp(collate, "C") != 0 && strcmp(collate, "POSIX") != 0) - { - errno = 0; - loc1 = newlocale(LC_COLLATE_MASK, collate, NULL); - if (!loc1) - report_newlocale_failure(collate); - } - - if (strcmp(ctype, "C") != 0 && strcmp(ctype, "POSIX") != 0) - { - errno = 0; - loc = newlocale(LC_CTYPE_MASK, ctype, loc1); - if (!loc) - { - if (loc1) - freelocale(loc1); - report_newlocale_failure(ctype); - } - } - else - loc = loc1; -#else - - /* - * XXX The _create_locale() API doesn't appear to support this. Could - * perhaps be worked around by changing pg_locale_t to contain two - * separate fields. - */ - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("collations with different collate and ctype values are not supported on this platform"))); -#endif - } - - return loc; -} - /* * Initialize default_locale with database locale settings. */ @@ -1722,150 +1629,6 @@ get_collation_actual_version(char collprovider, const char *collcollate) return collversion; } -/* - * strncoll_libc_win32_utf8 - * - * Win32 does not have UTF-8. Convert UTF8 arguments to wide characters and - * invoke wcscoll_l(). - * - * An input string length of -1 means that it's NUL-terminated. - */ -#ifdef WIN32 -static int -strncoll_libc_win32_utf8(const char *arg1, ssize_t len1, const char *arg2, - ssize_t len2, pg_locale_t locale) -{ - char sbuf[TEXTBUFLEN]; - char *buf = sbuf; - char *a1p, - *a2p; - int a1len; - int a2len; - int r; - int result; - - Assert(locale->provider == COLLPROVIDER_LIBC); - Assert(GetDatabaseEncoding() == PG_UTF8); - - if (len1 == -1) - len1 = strlen(arg1); - if (len2 == -1) - len2 = strlen(arg2); - - a1len = len1 * 2 + 2; - a2len = len2 * 2 + 2; - - if (a1len + a2len > TEXTBUFLEN) - buf = palloc(a1len + a2len); - - a1p = buf; - a2p = buf + a1len; - - /* API does not work for zero-length input */ - if (len1 == 0) - r = 0; - else - { - r = MultiByteToWideChar(CP_UTF8, 0, arg1, len1, - (LPWSTR) a1p, a1len / 2); - if (!r) - ereport(ERROR, - (errmsg("could not convert string to UTF-16: error code %lu", - GetLastError()))); - } - ((LPWSTR) a1p)[r] = 0; - - if (len2 == 0) - r = 0; - else - { - r = MultiByteToWideChar(CP_UTF8, 0, arg2, len2, - (LPWSTR) a2p, a2len / 2); - if (!r) - ereport(ERROR, - (errmsg("could not convert string to UTF-16: error code %lu", - GetLastError()))); - } - ((LPWSTR) a2p)[r] = 0; - - errno = 0; - result = wcscoll_l((LPWSTR) a1p, (LPWSTR) a2p, locale->info.lt); - if (result == 2147483647) /* _NLSCMPERROR; missing from mingw headers */ - ereport(ERROR, - (errmsg("could not compare Unicode strings: %m"))); - - if (buf != sbuf) - pfree(buf); - - return result; -} -#endif /* WIN32 */ - -/* - * strncoll_libc - * - * NUL-terminate arguments, if necessary, and pass to strcoll_l(). - * - * An input string length of -1 means that it's already NUL-terminated. - */ -static int -strncoll_libc(const char *arg1, ssize_t len1, const char *arg2, ssize_t len2, - pg_locale_t locale) -{ - char sbuf[TEXTBUFLEN]; - char *buf = sbuf; - size_t bufsize1 = (len1 == -1) ? 0 : len1 + 1; - size_t bufsize2 = (len2 == -1) ? 0 : len2 + 1; - const char *arg1n; - const char *arg2n; - int result; - - Assert(locale->provider == COLLPROVIDER_LIBC); - -#ifdef WIN32 - /* check for this case before doing the work for nul-termination */ - if (GetDatabaseEncoding() == PG_UTF8) - return strncoll_libc_win32_utf8(arg1, len1, arg2, len2, locale); -#endif /* WIN32 */ - - if (bufsize1 + bufsize2 > TEXTBUFLEN) - buf = palloc(bufsize1 + bufsize2); - - /* nul-terminate arguments if necessary */ - if (len1 == -1) - { - arg1n = arg1; - } - else - { - char *buf1 = buf; - - memcpy(buf1, arg1, len1); - buf1[len1] = '\0'; - arg1n = buf1; - } - - if (len2 == -1) - { - arg2n = arg2; - } - else - { - char *buf2 = buf + bufsize1; - - memcpy(buf2, arg2, len2); - buf2[len2] = '\0'; - arg2n = buf2; - } - - result = strcoll_l(arg1n, arg2n, locale->info.lt); - - if (buf != sbuf) - pfree(buf); - - return result; -} - /* * pg_strcoll * @@ -1922,45 +1685,6 @@ pg_strncoll(const char *arg1, ssize_t len1, const char *arg2, ssize_t len2, return result; } -/* - * strnxfrm_libc - * - * NUL-terminate src, if necessary, and pass to strxfrm_l(). - * - * A source length of -1 means that it's already NUL-terminated. - */ -static size_t -strnxfrm_libc(char *dest, size_t destsize, const char *src, ssize_t srclen, - pg_locale_t locale) -{ - char sbuf[TEXTBUFLEN]; - char *buf = sbuf; - size_t bufsize = srclen + 1; - size_t result; - - Assert(locale->provider == COLLPROVIDER_LIBC); - - if (srclen == -1) - return strxfrm_l(dest, src, destsize, locale->info.lt); - - if (bufsize > TEXTBUFLEN) - buf = palloc(bufsize); - - /* nul-terminate argument */ - memcpy(buf, src, srclen); - buf[srclen] = '\0'; - - result = strxfrm_l(dest, buf, destsize, locale->info.lt); - - if (buf != sbuf) - pfree(buf); - - /* if dest is defined, it should be nul-terminated */ - Assert(result >= destsize || dest[result] == '\0'); - - return result; -} - /* * Return true if the collation provider supports pg_strxfrm() and * pg_strnxfrm(); otherwise false. diff --git a/src/backend/utils/adt/pg_locale_libc.c b/src/backend/utils/adt/pg_locale_libc.c new file mode 100644 index 00000000000..ab53995b786 --- /dev/null +++ b/src/backend/utils/adt/pg_locale_libc.c @@ -0,0 +1,326 @@ +/*----------------------------------------------------------------------- + * + * PostgreSQL locale utilities for libc + * + * Portions Copyright (c) 2002-2024, PostgreSQL Global Development Group + * + * src/backend/utils/adt/pg_locale_libc.c + * + *----------------------------------------------------------------------- + */ + +#include "postgres.h" + +#include "catalog/pg_collation.h" +#include "mb/pg_wchar.h" +#include "utils/formatting.h" +#include "utils/pg_locale.h" + +/* + * This should be large enough that most strings will fit, but small enough + * that we feel comfortable putting it on the stack + */ +#define TEXTBUFLEN 1024 + +extern locale_t make_libc_collator(const char *collate, + const char *ctype); +extern int strncoll_libc(const char *arg1, ssize_t len1, + const char *arg2, ssize_t len2, + pg_locale_t locale); +extern size_t strnxfrm_libc(char *dest, size_t destsize, + const char *src, ssize_t srclen, + pg_locale_t locale); + +static void report_newlocale_failure(const char *localename); + +#ifdef WIN32 +static int strncoll_libc_win32_utf8(const char *arg1, ssize_t len1, + const char *arg2, ssize_t len2, + pg_locale_t locale); +#endif + +/* + * Create a locale_t with the given collation and ctype. + * + * The "C" and "POSIX" locales are not actually handled by libc, so return + * NULL. + * + * Ensure that no path leaks a locale_t. + */ +locale_t +make_libc_collator(const char *collate, const char *ctype) +{ + locale_t loc = 0; + + if (strcmp(collate, ctype) == 0) + { + if (strcmp(ctype, "C") != 0 && strcmp(ctype, "POSIX") != 0) + { + /* Normal case where they're the same */ + errno = 0; +#ifndef WIN32 + loc = newlocale(LC_COLLATE_MASK | LC_CTYPE_MASK, collate, + NULL); +#else + loc = _create_locale(LC_ALL, collate); +#endif + if (!loc) + report_newlocale_failure(collate); + } + } + else + { +#ifndef WIN32 + /* We need two newlocale() steps */ + locale_t loc1 = 0; + + if (strcmp(collate, "C") != 0 && strcmp(collate, "POSIX") != 0) + { + errno = 0; + loc1 = newlocale(LC_COLLATE_MASK, collate, NULL); + if (!loc1) + report_newlocale_failure(collate); + } + + if (strcmp(ctype, "C") != 0 && strcmp(ctype, "POSIX") != 0) + { + errno = 0; + loc = newlocale(LC_CTYPE_MASK, ctype, loc1); + if (!loc) + { + if (loc1) + freelocale(loc1); + report_newlocale_failure(ctype); + } + } + else + loc = loc1; +#else + + /* + * XXX The _create_locale() API doesn't appear to support this. Could + * perhaps be worked around by changing pg_locale_t to contain two + * separate fields. + */ + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("collations with different collate and ctype values are not supported on this platform"))); +#endif + } + + return loc; +} + +/* + * strncoll_libc + * + * NUL-terminate arguments, if necessary, and pass to strcoll_l(). + * + * An input string length of -1 means that it's already NUL-terminated. + */ +int +strncoll_libc(const char *arg1, ssize_t len1, const char *arg2, ssize_t len2, + pg_locale_t locale) +{ + char sbuf[TEXTBUFLEN]; + char *buf = sbuf; + size_t bufsize1 = (len1 == -1) ? 0 : len1 + 1; + size_t bufsize2 = (len2 == -1) ? 0 : len2 + 1; + const char *arg1n; + const char *arg2n; + int result; + + Assert(locale->provider == COLLPROVIDER_LIBC); + +#ifdef WIN32 + /* check for this case before doing the work for nul-termination */ + if (GetDatabaseEncoding() == PG_UTF8) + return strncoll_libc_win32_utf8(arg1, len1, arg2, len2, locale); +#endif /* WIN32 */ + + if (bufsize1 + bufsize2 > TEXTBUFLEN) + buf = palloc(bufsize1 + bufsize2); + + /* nul-terminate arguments if necessary */ + if (len1 == -1) + { + arg1n = arg1; + } + else + { + char *buf1 = buf; + + memcpy(buf1, arg1, len1); + buf1[len1] = '\0'; + arg1n = buf1; + } + + if (len2 == -1) + { + arg2n = arg2; + } + else + { + char *buf2 = buf + bufsize1; + + memcpy(buf2, arg2, len2); + buf2[len2] = '\0'; + arg2n = buf2; + } + + result = strcoll_l(arg1n, arg2n, locale->info.lt); + + if (buf != sbuf) + pfree(buf); + + return result; +} + +/* + * strnxfrm_libc + * + * NUL-terminate src, if necessary, and pass to strxfrm_l(). + * + * A source length of -1 means that it's already NUL-terminated. + */ +size_t +strnxfrm_libc(char *dest, size_t destsize, const char *src, ssize_t srclen, + pg_locale_t locale) +{ + char sbuf[TEXTBUFLEN]; + char *buf = sbuf; + size_t bufsize = srclen + 1; + size_t result; + + Assert(locale->provider == COLLPROVIDER_LIBC); + + if (srclen == -1) + return strxfrm_l(dest, src, destsize, locale->info.lt); + + if (bufsize > TEXTBUFLEN) + buf = palloc(bufsize); + + /* nul-terminate argument */ + memcpy(buf, src, srclen); + buf[srclen] = '\0'; + + result = strxfrm_l(dest, buf, destsize, locale->info.lt); + + if (buf != sbuf) + pfree(buf); + + /* if dest is defined, it should be nul-terminated */ + Assert(result >= destsize || dest[result] == '\0'); + + return result; +} + +/* + * strncoll_libc_win32_utf8 + * + * Win32 does not have UTF-8. Convert UTF8 arguments to wide characters and + * invoke wcscoll_l(). + * + * An input string length of -1 means that it's NUL-terminated. + */ +#ifdef WIN32 +static int +strncoll_libc_win32_utf8(const char *arg1, ssize_t len1, const char *arg2, + ssize_t len2, pg_locale_t locale) +{ + char sbuf[TEXTBUFLEN]; + char *buf = sbuf; + char *a1p, + *a2p; + int a1len; + int a2len; + int r; + int result; + + Assert(locale->provider == COLLPROVIDER_LIBC); + Assert(GetDatabaseEncoding() == PG_UTF8); + + if (len1 == -1) + len1 = strlen(arg1); + if (len2 == -1) + len2 = strlen(arg2); + + a1len = len1 * 2 + 2; + a2len = len2 * 2 + 2; + + if (a1len + a2len > TEXTBUFLEN) + buf = palloc(a1len + a2len); + + a1p = buf; + a2p = buf + a1len; + + /* API does not work for zero-length input */ + if (len1 == 0) + r = 0; + else + { + r = MultiByteToWideChar(CP_UTF8, 0, arg1, len1, + (LPWSTR) a1p, a1len / 2); + if (!r) + ereport(ERROR, + (errmsg("could not convert string to UTF-16: error code %lu", + GetLastError()))); + } + ((LPWSTR) a1p)[r] = 0; + + if (len2 == 0) + r = 0; + else + { + r = MultiByteToWideChar(CP_UTF8, 0, arg2, len2, + (LPWSTR) a2p, a2len / 2); + if (!r) + ereport(ERROR, + (errmsg("could not convert string to UTF-16: error code %lu", + GetLastError()))); + } + ((LPWSTR) a2p)[r] = 0; + + errno = 0; + result = wcscoll_l((LPWSTR) a1p, (LPWSTR) a2p, locale->info.lt); + if (result == 2147483647) /* _NLSCMPERROR; missing from mingw headers */ + ereport(ERROR, + (errmsg("could not compare Unicode strings: %m"))); + + if (buf != sbuf) + pfree(buf); + + return result; +} +#endif /* WIN32 */ + +/* simple subroutine for reporting errors from newlocale() */ +static void +report_newlocale_failure(const char *localename) +{ + int save_errno; + + /* + * Windows doesn't provide any useful error indication from + * _create_locale(), and BSD-derived platforms don't seem to feel they + * need to set errno either (even though POSIX is pretty clear that + * newlocale should do so). So, if errno hasn't been set, assume ENOENT + * is what to report. + */ + if (errno == 0) + errno = ENOENT; + + /* + * ENOENT means "no such locale", not "no such file", so clarify that + * errno with an errdetail message. + */ + save_errno = errno; /* auxiliary funcs might change errno */ + ereport(ERROR, + (errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("could not create locale \"%s\": %m", + localename), + (save_errno == ENOENT ? + errdetail("The operating system could not find any locale data for the locale name \"%s\".", + localename) : 0))); +} + -- 2.34.1