Re: [uclibc-ng-devel] [PATCH] towlower and locales

Hi, The function towlower doesn't work with locales diffrent from C. Issue was introduced in this commit: https://cgit.openadk.org/cgi/cgit/uclibc-ng.git/commit/?id= 8cde3a9bf2856dcb9a759dec7ecb04a68e712254 Call to setlocale is needed for correct generation of the table uplow_diff. I received the compile time error "range assumption error" after uncommenting the call. Similar problem described here: http://lists.uclibc.org/pipermail/uclibc/2015-March/048852.html The attached patch fix the problem by using int32_t values. Test program: $ cat test.c #include <locale.h> #include <stdio.h> #include <wchar.h> #include <wctype.h> int main(int argc, char *argv[]) { int i = 0; wchar_t str[] = L"ТЕСТОВАЯ СТРОКА"; wchar_t c; setlocale(LC_ALL, "ru_RU.utf-8"); wprintf(L"Input:\t\"%ls\"\n", str); wprintf(L"Output:\t\""); while (str[i]) { c = str[i]; putwchar(towlower(c)); i++; } wprintf(L"\"\n"); return 0; } Output (without patch): $ ./test Input: "ТЕСТОВАЯ СТРОКА" Output: "ТЕСТОВАЯ СТРОКА" Output (with patch): $ ./test Input: "ТЕСТОВАЯ СТРОКА" Output: "тестовая строка" -- Best regards, Eugene

diff --git a/extra/locale/gen_ldc.c b/extra/locale/gen_ldc.c index 2cedbdd..5f45402 100644 --- a/extra/locale/gen_ldc.c +++ b/extra/locale/gen_ldc.c @@ -129,6 +129,20 @@ void out_i16(FILE *f, const int16_t *p, size_t n, char *comment) fprintf(f, "\n},\n"); } +void out_i32(FILE *f, const int32_t *p, size_t n, char *comment) +{ + size_t i; + + fprintf(f, "{\t/* %s */", comment); + for (i = 0 ; i < n ; i++) { + if (!(i & 7)) { + fprintf(f, "\n\t"); + } + fprintf(f, "%11d, ", p[i]); + } + fprintf(f, "\n},\n"); +} + void out_size_t(FILE *f, const size_t *p, size_t n, char *comment) { size_t i; @@ -194,7 +208,7 @@ int main(int argc, char **argv) #ifdef __WCHAR_ENABLED out_uc(lso, __LOCALE_DATA_WCctype_data, __LOCALE_DATA_WCctype_TBL_LEN, "tblwctype"); out_uc(lso, __LOCALE_DATA_WCuplow_data, __LOCALE_DATA_WCuplow_TBL_LEN, "tblwuplow"); - out_i16(lso, __LOCALE_DATA_WCuplow_diff_data, __LOCALE_DATA_WCuplow_diff_TBL_LEN, "tblwuplow_diff"); + out_i32(lso, __LOCALE_DATA_WCuplow_diff_data, __LOCALE_DATA_WCuplow_diff_TBL_LEN, "tblwuplow_diff"); /* const unsigned char tblwcomb[WCcomb_TBL_LEN]; */ /* width?? */ #endif /* __WCHAR_ENABLED */ diff --git a/extra/locale/gen_wctype.c b/extra/locale/gen_wctype.c index 7034509..99c505d 100644 --- a/extra/locale/gen_wctype.c +++ b/extra/locale/gen_wctype.c @@ -83,8 +83,8 @@ #define mywxdigit(D,C) (mywdigit(D,C) || (unsigned)(((C) | 0x20) - 'a') <= 5) typedef struct { - short l; - short u; + int32_t l; + int32_t u; } uldiff_entry; typedef struct { @@ -227,12 +227,11 @@ int main(int argc, char **argv) ++verbose; continue; } - /* setlocale might be just a stub */ - /* if (!setlocale(LC_CTYPE, *argv)) { + /* setlocale might be just a stub */ + if (!setlocale(LC_CTYPE, *argv)) { verbose_msg("setlocale(LC_CTYPE,%s) failed! Skipping this locale...\n", *argv); continue; } - */ if (!(totitle = wctrans("totitle"))) { verbose_msg("no totitle transformation.\n"); } @@ -402,7 +401,7 @@ int main(int argc, char **argv) u = (long)(int) towupper(c) - c; ult[c] = 0; if (l || u) { - if ((l != (short)l) || (u != (short)u)) { + if ((l != (int32_t)l) || (u != (int32_t)u)) { verbose_msg("range assumption error! %x %ld %ld\n", c, l, u); return EXIT_FAILURE; } @@ -684,7 +683,7 @@ int main(int argc, char **argv) printf("#define __LOCALE_DATA_WCuplow_diffs %7u\n", ul_count); printf("\n#ifdef WANT_WCuplow_diff_data\n\n"); - printf("\nstatic const short __LOCALE_DATA_WCuplow_diff_data[%zu] = {", + printf("\nstatic const int32_t __LOCALE_DATA_WCuplow_diff_data[%zu] = {", 2 * (size_t) ul_count); for (i = 0; i < ul_count; i++) { if (i % 4 == 0) { diff --git a/extra/locale/locale_mmap.h b/extra/locale/locale_mmap.h index 5b0df90..d0ae9af 100644 --- a/extra/locale/locale_mmap.h +++ b/extra/locale/locale_mmap.h @@ -45,7 +45,7 @@ typedef struct { #ifdef __WCHAR_ENABLED const unsigned char tblwctype[__LOCALE_DATA_WCctype_TBL_LEN]; const unsigned char tblwuplow[__LOCALE_DATA_WCuplow_TBL_LEN]; - const int16_t tblwuplow_diff[__LOCALE_DATA_WCuplow_diff_TBL_LEN]; + const int32_t tblwuplow_diff[__LOCALE_DATA_WCuplow_diff_TBL_LEN]; /* const unsigned char tblwcomb[WCcomb_TBL_LEN]; */ /* width?? */ #endif diff --git a/libc/misc/locale/locale.c b/libc/misc/locale/locale.c index e38792b..d555f5d 100644 --- a/libc/misc/locale/locale.c +++ b/libc/misc/locale/locale.c @@ -820,7 +820,7 @@ void attribute_hidden _locale_init_l(__locale_t base) base->tblwuplow = (const unsigned char *) &__locale_mmap->tblwuplow; base->tblwuplow_diff - = (const int16_t *) &__locale_mmap->tblwuplow_diff; + = (const int32_t *) &__locale_mmap->tblwuplow_diff; /* base->tblwcomb */ /* = (const unsigned char *) &__locale_mmap->tblwcomb; */ /* width?? */ diff --git a/libc/sysdeps/linux/common/bits/uClibc_locale.h b/libc/sysdeps/linux/common/bits/uClibc_locale.h index 6598eaf..43c1e51 100644 --- a/libc/sysdeps/linux/common/bits/uClibc_locale.h +++ b/libc/sysdeps/linux/common/bits/uClibc_locale.h @@ -192,7 +192,7 @@ struct __uclibc_locale_struct { const unsigned char *tblwctype; const unsigned char *tblwuplow; /* const unsigned char *tblwcomb; */ - const int16_t *tblwuplow_diff; /* yes... signed */ + const int32_t *tblwuplow_diff; /* yes... signed */ /* width?? */ wchar_t decimal_point_wc;

_______________________________________________ devel mailing list devel(a)uclibc-ng.org https://mailman.uclibc-ng.org/cgi-bin/mailman/listinfo/devel