From 95cb863a1ef7760a11272bbd7ba5fe62dc41be54 Mon Sep 17 00:00:00 2001 From: Rafal Luzynski Date: Tue, 14 Nov 2017 02:19:35 +0100 Subject: Implement alternative month names (bug 10871). Some languages (Slavic, Baltic, etc.) require a genitive case of the month name when formatting a full date (with the day number) while they require a nominative case when referring to the month standalone. This requirement cannot be fulfilled without providing two forms for each month name. From now it is specified that nl_langinfo(MON_1) series (up to MON_12) and strftime("%B") generate the month names in the grammatical form used when the month is a part of a complete date. If the grammatical form used when the month is named by itself is needed, the new values nl_langinfo(ALTMON_1) (up to ALTMON_12) and strftime("%OB") are supported. This new feature is optional so the languages which do not need it or do not yet provide the updated locales simply do not use it and their behaviour is unchanged. [BZ #10871] * locale/C-time.c (_nl_C_LC_TIME): Add alternative month names, define them as the same as primary full month names explicitly. * locale/categories.def (LC_TIME): Add alt_mon and wide-alt_mon. * locale/langinfo.h (__ALTMON_1, __ALTMON_2, __ALTMON_3, __ALTMON_4, __ALTMON_5, __ALTMON_6, __ALTMON_7, __ALTMON_8, __ALTMON_9, __ALTMON_10, __ALTMON_11, __ALTMON_12, _NL_WALTMON_1, _NL_WALTMON_2, _NL_WALTMON_3, _NL_WALTMON_4, _NL_WALTMON_5, _NL_WALTMON_6, _NL_WALTMON_7, _NL_WALTMON_8, _NL_WALTMON_9, _NL_WALTMON_10, _NL_WALTMON_11, _NL_WALTMON_12): New enum constants. [__USE_GNU] (ALTMON_1, ALTMON_2, ALTMON_3, ALTMON_4, ALTMON_5, ALTMON_6, ALTMON_7, ALTMON_8, ALTMON_9, ALTMON_10, ALTMON_11, ALTMON_12): New macros. * locale/programs/ld-time.c (struct locale_time_t): Add alt_mon, walt_mon, and alt_mon_defined members. (time_output): Output alt_mon and walt_mon members. (time_read): Read them, initialize them as copies of mon and wmon respectively if they are missing, initialize alt_mon_defined. * locale/programs/locfile-kw.gperf (alt_mon): Define. * locale/programs/locfile-kw.h: Regenerate. * locale/programs/locfile-token.h (tok_alt_mon): New enum constant. * localedata/tst-langinfo.c (map): Add tests for the new constants ALTMON_1 .. ALTMON_12. * time/Makefile [$(run-built-tests) = yes] (LOCALES): Add fr_FR.UTF-8 and pl_PL.UTF-8. * time/strftime_l.c (f_altmonth): New macro. (__strftime_internal): Handle %OB format. * time/strptime_l.c [_LIBC] (alt_month_name): New macro. (__strptime_internal): Handle %OB format. * time/tst-strptime.c (day_tests): Add tests to parse different forms of month names including the new %OB format specifier. Reviewed-by: Carlos O'Donell --- time/Makefile | 3 ++- time/strftime_l.c | 11 +++++++++-- time/strptime_l.c | 32 ++++++++++++++++++++++++++++---- time/tst-strptime.c | 12 ++++++++++++ 4 files changed, 51 insertions(+), 7 deletions(-) (limited to 'time') diff --git a/time/Makefile b/time/Makefile index 264eed9..2deb025 100644 --- a/time/Makefile +++ b/time/Makefile @@ -48,7 +48,8 @@ tests := test_time clocktest tst-posixtz tst-strptime tst_wcsftime \ include ../Rules ifeq ($(run-built-tests),yes) -LOCALES := de_DE.ISO-8859-1 en_US.ISO-8859-1 ja_JP.EUC-JP +LOCALES := de_DE.ISO-8859-1 en_US.ISO-8859-1 ja_JP.EUC-JP fr_FR.UTF-8 \ + pl_PL.UTF-8 include ../gen-locales.mk $(objpfx)tst-ftime_l.out: $(gen-locales) diff --git a/time/strftime_l.c b/time/strftime_l.c index 18651ff..ac5d28f 100644 --- a/time/strftime_l.c +++ b/time/strftime_l.c @@ -492,6 +492,9 @@ __strftime_internal (CHAR_T *s, size_t maxsize, const CHAR_T *format, # define f_month \ ((const CHAR_T *) (tp->tm_mon < 0 || tp->tm_mon > 11 \ ? "?" : _NL_CURRENT (LC_TIME, NLW(MON_1) + tp->tm_mon))) +# define f_altmonth \ + ((const CHAR_T *) (tp->tm_mon < 0 || tp->tm_mon > 11 \ + ? "?" : _NL_CURRENT (LC_TIME, NLW(ALTMON_1) + tp->tm_mon))) # define ampm \ ((const CHAR_T *) _NL_CURRENT (LC_TIME, tp->tm_hour > 11 \ ? NLW(PM_STR) : NLW(AM_STR))) @@ -507,6 +510,7 @@ __strftime_internal (CHAR_T *s, size_t maxsize, const CHAR_T *format, ? "?" : month_name[tp->tm_mon]) # define a_wkday f_wkday # define a_month f_month +# define f_altmonth f_month # define ampm (L_("AMPM") + 2 * (tp->tm_hour > 11)) size_t aw_len = 3; @@ -785,7 +789,7 @@ __strftime_internal (CHAR_T *s, size_t maxsize, const CHAR_T *format, #endif case L_('B'): - if (modifier != 0) + if (modifier == L_('E')) goto bad_format; if (change_case) { @@ -793,7 +797,10 @@ __strftime_internal (CHAR_T *s, size_t maxsize, const CHAR_T *format, to_lowcase = 0; } #if defined _NL_CURRENT || !HAVE_STRFTIME - cpy (STRLEN (f_month), f_month); + if (modifier == L_('O')) + cpy (STRLEN (f_altmonth), f_altmonth); + else + cpy (STRLEN (f_month), f_month); break; #else goto underlying_strftime; diff --git a/time/strptime_l.c b/time/strptime_l.c index 7d4758e..39cf38d 100644 --- a/time/strptime_l.c +++ b/time/strptime_l.c @@ -124,6 +124,8 @@ extern const struct __locale_data _nl_C_LC_TIME attribute_hidden; (&_nl_C_LC_TIME.values[_NL_ITEM_INDEX (ABDAY_1)].string) # define month_name (&_nl_C_LC_TIME.values[_NL_ITEM_INDEX (MON_1)].string) # define ab_month_name (&_nl_C_LC_TIME.values[_NL_ITEM_INDEX (ABMON_1)].string) +# define alt_month_name \ + (&_nl_C_LC_TIME.values[_NL_ITEM_INDEX (ALTMON_1)].string) # define HERE_D_T_FMT (_nl_C_LC_TIME.values[_NL_ITEM_INDEX (D_T_FMT)].string) # define HERE_D_FMT (_nl_C_LC_TIME.values[_NL_ITEM_INDEX (D_FMT)].string) # define HERE_AM_STR (_nl_C_LC_TIME.values[_NL_ITEM_INDEX (AM_STR)].string) @@ -319,10 +321,9 @@ __strptime_internal (const char *rp, const char *fmt, struct tm *tmp, while (*fmt >= '0' && *fmt <= '9') ++fmt; -#ifndef _NL_CURRENT - /* We need this for handling the `E' modifier. */ + /* In some cases, modifiers are handled by adjusting state and + then restarting the switch statement below. */ start_over: -#endif /* Make back up of current processing pointer. */ rp_backup = rp; @@ -423,13 +424,32 @@ __strptime_internal (const char *rp, const char *fmt, struct tm *tmp, ab_month_name[cnt])) decided_longest = loc; } +#ifdef _LIBC + /* Now check the alt month. */ + trp = rp; + if (match_string (_NL_CURRENT (LC_TIME, ALTMON_1 + cnt), trp) + && trp > rp_longest) + { + rp_longest = trp; + cnt_longest = cnt; + if (s.decided == not + && strcmp (_NL_CURRENT (LC_TIME, ALTMON_1 + cnt), + alt_month_name[cnt])) + decided_longest = loc; + } +#endif } #endif if (s.decided != loc && (((trp = rp, match_string (month_name[cnt], trp)) && trp > rp_longest) || ((trp = rp, match_string (ab_month_name[cnt], trp)) - && trp > rp_longest))) + && trp > rp_longest) +#ifdef _LIBC + || ((trp = rp, match_string (alt_month_name[cnt], trp)) + && trp > rp_longest) +#endif + )) { rp_longest = trp; cnt_longest = cnt; @@ -1015,6 +1035,10 @@ __strptime_internal (const char *rp, const char *fmt, struct tm *tmp, case 'O': switch (*fmt++) { + case 'B': + /* Match month name. Reprocess as plain 'B'. */ + fmt--; + goto start_over; case 'd': case 'e': /* Match day of month using alternate numeric symbols. */ diff --git a/time/tst-strptime.c b/time/tst-strptime.c index 34ad797..62ecb7c 100644 --- a/time/tst-strptime.c +++ b/time/tst-strptime.c @@ -51,6 +51,18 @@ static const struct 6, 0, 0, 1 }, { "ja_JP.EUC-JP", "2001 20 \xb7\xee", "%Y %U %a", 1, 140, 4, 21 }, { "ja_JP.EUC-JP", "2001 21 \xb7\xee", "%Y %W %a", 1, 140, 4, 21 }, + /* Most of the languages do not need the declension of the month names + and do not distinguish between %B and %OB. */ + { "en_US.ISO-8859-1", "November 17, 2017", "%B %e, %Y", 5, 320, 10, 17 }, + { "de_DE.ISO-8859-1", "18. Nov 2017", "%d. %b %Y", 6, 321, 10, 18 }, + { "fr_FR.UTF-8", "19 novembre 2017", "%d %OB %Y", 0, 322, 10, 19 }, + /* Some languages do need the declension of the month names. */ + { "pl_PL.UTF-8", "21 lis 2017", "%d %b %Y", 2, 324, 10, 21 }, + { "pl_PL.UTF-8", "22 LIS 2017", "%d %B %Y", 3, 325, 10, 22 }, + /* TODO: Use the genitive case here as soon as it is added to localedata. */ + { "pl_PL.UTF-8", "23 listopad 2017", "%d %B %Y", 4, 326, 10, 23 }, + /* The nominative case is incorrect here but it is parseable. */ + { "pl_PL.UTF-8", "24 listopad 2017", "%d %OB %Y", 5, 327, 10, 24 }, }; -- cgit v1.1