[v11,3/5] Abbreviated alternative month names (%Ob) also added (bug 10871).
Commit Message
All the previous changes also repeated to support abbreviated
alternative month names. In most languages which have declension and
need nominative/genitive month names the abbreviated forms for both
cases are the same. An example where they do differ is May in Russian:
this name is too short to be abbreviated so even the abbreviated form
features the declension suffixes.
[BZ #10871]
* locale/C-time.c: Add abbreviated alternative month names, define
them as the same as abbreviated month names explicitly.
* locale/categories.def: ab_alt_mon and wide-ab_alt_mon added.
* locale/langinfo.h: New public symbols _NL_ABALTMON_1,
_NL_ABALTMON_2, _NL_ABALTMON_3, _NL_ABALTMON_4, _NL_ABALTMON_5,
_NL_ABALTMON_6, _NL_ABALTMON_7, _NL_ABALTMON_8, _NL_ABALTMON_9,
_NL_ABALTMON_10, _NL_ABALTMON_11, _NL_ABALTMON_12,
_NL_WABALTMON_1, _NL_WABALTMON_2, _NL_WABALTMON_3, _NL_WABALTMON_4,
_NL_WABALTMON_5, _NL_WABALTMON_6, _NL_WABALTMON_7, _NL_WABALTMON_8,
_NL_WABALTMON_9, _NL_WABALTMON_10, _NL_WABALTMON_11, _NL_WABALTMON_12.
* locale/programs/ld-time.c: Abbreviated alternative month names
support added, they are a copy of abmon if not provided
explicitly.
* locale/programs/locfile-kw.gperf: ab_alt_mon defined.
* locale/programs/locfile-token.h: tok_ab_alt_mon defined.
* time/Makefile (LOCALES): Add ru_RU.UTF-8 for tests.
* time/strftime_l.c: %Ob (%Oh) format for abbreviated
alternative month names added.
* time/strptime_l.c: Abbreviated alternative month names also
recognized.
* time/tst-strptime.c: Add more tests to parse different forms of
month names including the new %Ob format specifier.
---
locale/C-time.c | 28 ++++++++++++++++++++++++++--
locale/categories.def | 6 ++++--
locale/langinfo.h | 36 ++++++++++++++++++++++++++++++++++--
locale/programs/ld-time.c | 19 +++++++++++++++++++
locale/programs/locfile-kw.gperf | 1 +
locale/programs/locfile-token.h | 1 +
time/Makefile | 3 ++-
time/strftime_l.c | 14 ++++++++++++--
time/strptime_l.c | 18 ++++++++++++++++++
time/tst-strptime.c | 13 +++++++++++++
10 files changed, 130 insertions(+), 9 deletions(-)
Comments
On 01/08/2018 04:01 PM, Rafal Luzynski wrote:
> All the previous changes also repeated to support abbreviated
> alternative month names. In most languages which have declension and
> need nominative/genitive month names the abbreviated forms for both
> cases are the same. An example where they do differ is May in Russian:
> this name is too short to be abbreviated so even the abbreviated form
> features the declension suffixes.
>
> [BZ #10871]
> * locale/C-time.c: Add abbreviated alternative month names, define
> them as the same as abbreviated month names explicitly.
> * locale/categories.def: ab_alt_mon and wide-ab_alt_mon added.
> * locale/langinfo.h: New public symbols _NL_ABALTMON_1,
> _NL_ABALTMON_2, _NL_ABALTMON_3, _NL_ABALTMON_4, _NL_ABALTMON_5,
> _NL_ABALTMON_6, _NL_ABALTMON_7, _NL_ABALTMON_8, _NL_ABALTMON_9,
> _NL_ABALTMON_10, _NL_ABALTMON_11, _NL_ABALTMON_12,
> _NL_WABALTMON_1, _NL_WABALTMON_2, _NL_WABALTMON_3, _NL_WABALTMON_4,
> _NL_WABALTMON_5, _NL_WABALTMON_6, _NL_WABALTMON_7, _NL_WABALTMON_8,
> _NL_WABALTMON_9, _NL_WABALTMON_10, _NL_WABALTMON_11, _NL_WABALTMON_12.
> * locale/programs/ld-time.c: Abbreviated alternative month names
> support added, they are a copy of abmon if not provided
> explicitly.
> * locale/programs/locfile-kw.gperf: ab_alt_mon defined.
> * locale/programs/locfile-token.h: tok_ab_alt_mon defined.
> * time/Makefile (LOCALES): Add ru_RU.UTF-8 for tests.
> * time/strftime_l.c: %Ob (%Oh) format for abbreviated
> alternative month names added.
> * time/strptime_l.c: Abbreviated alternative month names also
> recognized.
> * time/tst-strptime.c: Add more tests to parse different forms of
> month names including the new %Ob format specifier.
Why is there no ABALTMON_* via #ifdef __USE_GNU like there is for ALTMON_*?
It is OK without them, but seems like a missing useful feature.
OK with the test case changes to write UTF-8 directly in the test case string.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
> ---
> locale/C-time.c | 28 ++++++++++++++++++++++++++--
> locale/categories.def | 6 ++++--
> locale/langinfo.h | 36 ++++++++++++++++++++++++++++++++++--
> locale/programs/ld-time.c | 19 +++++++++++++++++++
> locale/programs/locfile-kw.gperf | 1 +
> locale/programs/locfile-token.h | 1 +
> time/Makefile | 3 ++-
> time/strftime_l.c | 14 ++++++++++++--
> time/strptime_l.c | 18 ++++++++++++++++++
> time/tst-strptime.c | 13 +++++++++++++
> 10 files changed, 130 insertions(+), 9 deletions(-)
>
> diff --git a/locale/C-time.c b/locale/C-time.c
> index 73bc700..e2b3b17 100644
> --- a/locale/C-time.c
> +++ b/locale/C-time.c
> @@ -30,7 +30,7 @@ const struct __locale_data _nl_C_LC_TIME attribute_hidden =
> { NULL, }, /* no cached data */
> UNDELETABLE,
> 0,
> - 135,
> + 159,
OK.
> {
> { .string = "Sun" },
> { .string = "Mon" },
> @@ -166,6 +166,30 @@ const struct __locale_data _nl_C_LC_TIME attribute_hidden =
> { .wstr = (const uint32_t *) L"September" },
> { .wstr = (const uint32_t *) L"October" },
> { .wstr = (const uint32_t *) L"November" },
> - { .wstr = (const uint32_t *) L"December" }
> + { .wstr = (const uint32_t *) L"December" },
> + { .string = "Jan" },
> + { .string = "Feb" },
> + { .string = "Mar" },
> + { .string = "Apr" },
> + { .string = "May" },
> + { .string = "Jun" },
> + { .string = "Jul" },
> + { .string = "Aug" },
> + { .string = "Sep" },
> + { .string = "Oct" },
> + { .string = "Nov" },
> + { .string = "Dec" },
> + { .wstr = (const uint32_t *) L"Jan" },
> + { .wstr = (const uint32_t *) L"Feb" },
> + { .wstr = (const uint32_t *) L"Mar" },
> + { .wstr = (const uint32_t *) L"Apr" },
> + { .wstr = (const uint32_t *) L"May" },
> + { .wstr = (const uint32_t *) L"Jun" },
> + { .wstr = (const uint32_t *) L"Jul" },
> + { .wstr = (const uint32_t *) L"Aug" },
> + { .wstr = (const uint32_t *) L"Sep" },
> + { .wstr = (const uint32_t *) L"Oct" },
> + { .wstr = (const uint32_t *) L"Nov" },
> + { .wstr = (const uint32_t *) L"Dec" }
OK.
> }
> };
> diff --git a/locale/categories.def b/locale/categories.def
> index 3cbb4e6..56c5f88 100644
> --- a/locale/categories.def
> +++ b/locale/categories.def
> @@ -249,8 +249,10 @@ DEFINE_CATEGORY
> DEFINE_ELEMENT (_DATE_FMT, "date_fmt", opt, string)
> DEFINE_ELEMENT (_NL_W_DATE_FMT, "wide-date_fmt", opt,
> wstring)
> DEFINE_ELEMENT (_NL_TIME_CODESET, "time-codeset", std, string)
> - DEFINE_ELEMENT (ALTMON_1, "alt_mon", opt, stringarray, 12, 12)
> - DEFINE_ELEMENT (_NL_WALTMON_1, "wide-alt_mon", opt, wstringarray, 12, 12)
> + DEFINE_ELEMENT (ALTMON_1, "alt_mon", opt, stringarray, 12,
> 12)
> + DEFINE_ELEMENT (_NL_WALTMON_1, "wide-alt_mon", opt, wstringarray, 12,
> 12)
> + DEFINE_ELEMENT (_NL_ABALTMON_1, "ab_alt_mon", opt, stringarray, 12,
> 12)
> + DEFINE_ELEMENT (_NL_WABALTMON_1, "wide-ab_alt_mon", opt, wstringarray, 12,
OK.
> 12)
> ), NO_POSTLOAD)
>
>
> diff --git a/locale/langinfo.h b/locale/langinfo.h
> index 0fbd838..4749e9d 100644
> --- a/locale/langinfo.h
> +++ b/locale/langinfo.h
> @@ -74,7 +74,8 @@ enum
> DAY_7, /* Saturday */
> #define DAY_7 DAY_7
>
> - /* Abbreviated month names. */
> + /* Abbreviated month names, in the grammatical form used when the month
> + forms part of a complete date. */
OK.
> ABMON_1, /* Jan */
> #define ABMON_1 ABMON_1
> ABMON_2,
> @@ -176,7 +177,8 @@ enum
> _NL_WDAY_6, /* Friday */
> _NL_WDAY_7, /* Saturday */
>
> - /* Abbreviated month names. */
> + /* Abbreviated month names, in the grammatical form used when the month
> + forms part of a complete date. */
OK.
> _NL_WABMON_1, /* Jan */
> _NL_WABMON_2,
> _NL_WABMON_3,
> @@ -277,6 +279,36 @@ enum
> _NL_WALTMON_11,
> _NL_WALTMON_12,
>
> + /* Abbreviated month names, in the grammatical form used when the month
> + is named by itself. */
> + _NL_ABALTMON_1, /* Jan */
> + _NL_ABALTMON_2,
> + _NL_ABALTMON_3,
> + _NL_ABALTMON_4,
> + _NL_ABALTMON_5,
> + _NL_ABALTMON_6,
> + _NL_ABALTMON_7,
> + _NL_ABALTMON_8,
> + _NL_ABALTMON_9,
> + _NL_ABALTMON_10,
> + _NL_ABALTMON_11,
> + _NL_ABALTMON_12,
> +
> + /* Abbreviated month names, in the grammatical form used when the month
> + is named by itself. */
> + _NL_WABALTMON_1, /* Jan */
> + _NL_WABALTMON_2,
> + _NL_WABALTMON_3,
> + _NL_WABALTMON_4,
> + _NL_WABALTMON_5,
> + _NL_WABALTMON_6,
> + _NL_WABALTMON_7,
> + _NL_WABALTMON_8,
> + _NL_WABALTMON_9,
> + _NL_WABALTMON_10,
> + _NL_WABALTMON_11,
> + _NL_WABALTMON_12,
OK.
> +
> _NL_NUM_LC_TIME, /* Number of indices in LC_TIME category. */
>
> /* LC_COLLATE category: text sorting.
> diff --git a/locale/programs/ld-time.c b/locale/programs/ld-time.c
> index 4186448..a755792 100644
> --- a/locale/programs/ld-time.c
> +++ b/locale/programs/ld-time.c
> @@ -94,6 +94,9 @@ struct locale_time_t
> const char *alt_mon[12];
> const uint32_t *walt_mon[12];
> int alt_mon_defined;
> + const char *ab_alt_mon[12];
> + const uint32_t *wab_alt_mon[12];
> + int ab_alt_mon_defined;
OK.
> unsigned char week_ndays;
> uint32_t week_1stday;
> unsigned char week_1stweek;
> @@ -651,6 +654,14 @@ time_output (struct localedef_t *locale, const struct
> charmap_t *charmap,
> for (n = 0; n < 12; ++n)
> add_locale_wstring (&file, time->walt_mon[n] ?: empty_wstr);
>
> + /* The ab'alt'mons. */
> + for (n = 0; n < 12; ++n)
> + add_locale_string (&file, time->ab_alt_mon[n] ?: "");
> +
> + /* The wide character ab'alt'mons. */
> + for (n = 0; n < 12; ++n)
> + add_locale_wstring (&file, time->wab_alt_mon[n] ?: empty_wstr);
OK.
> +
> write_locale_data (output_path, LC_TIME, "LC_TIME", &file);
> }
>
> @@ -795,6 +806,7 @@ time_read (struct linereader *ldfile, struct localedef_t
> *result,
> STRARR_ELEM (am_pm, 2, 2);
> STRARR_ELEM (alt_digits, 0, 100);
> STRARR_ELEM (alt_mon, 12, 12);
> + STRARR_ELEM (ab_alt_mon, 12, 12);
OK.
>
> case tok_era:
> /* Ignore the rest of the line if we don't need the input of
> @@ -955,6 +967,13 @@ time_read (struct linereader *ldfile, struct localedef_t
> *result,
> memcpy (time->walt_mon, time->wmon, sizeof (time->wmon));
> time->alt_mon_defined = 1;
> }
> + /* The same for abbreviated versions. */
> + if (!ignore_content && !time->ab_alt_mon_defined)
> + {
> + memcpy (time->ab_alt_mon, time->abmon, sizeof (time->abmon));
> + memcpy (time->wab_alt_mon, time->wabmon, sizeof (time->wabmon));
> + time->ab_alt_mon_defined = 1;
OK. Good, copy the abmon/wabmon versions.
> + }
> return;
>
> default:
> diff --git a/locale/programs/locfile-kw.gperf b/locale/programs/locfile-kw.gperf
> index dad7f21..6bf2f60 100644
> --- a/locale/programs/locfile-kw.gperf
> +++ b/locale/programs/locfile-kw.gperf
> @@ -149,6 +149,7 @@ cal_direction, tok_cal_direction, 0
> timezone, tok_timezone, 0
> date_fmt, tok_date_fmt, 0
> alt_mon, tok_alt_mon, 0
> +ab_alt_mon, tok_ab_alt_mon, 0
> LC_MESSAGES, tok_lc_messages, 0
> yesexpr, tok_yesexpr, 0
> noexpr, tok_noexpr, 0
> diff --git a/locale/programs/locfile-token.h b/locale/programs/locfile-token.h
> index d49da5e..e3cd18e 100644
> --- a/locale/programs/locfile-token.h
> +++ b/locale/programs/locfile-token.h
> @@ -187,6 +187,7 @@ enum token_t
> tok_timezone,
> tok_date_fmt,
> tok_alt_mon,
> + tok_ab_alt_mon,
OK. New token.
> tok_lc_messages,
> tok_yesexpr,
> tok_noexpr,
> diff --git a/time/Makefile b/time/Makefile
> index 91adcd0..4e631a1 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 pl_PL.UTF-8
> +LOCALES := de_DE.ISO-8859-1 en_US.ISO-8859-1 ja_JP.EUC-JP pl_PL.UTF-8 \
> + ru_RU.UTF-8
OK.
> include ../gen-locales.mk
>
> $(objpfx)tst-ftime_l.out: $(gen-locales)
> diff --git a/time/strftime_l.c b/time/strftime_l.c
> index ac5d28f..c71f9f4 100644
> --- a/time/strftime_l.c
> +++ b/time/strftime_l.c
> @@ -106,6 +106,7 @@ extern char *tzname[];
> # define UCHAR_T unsigned char
> # define L_(Str) Str
> # define NLW(Sym) Sym
> +# define ABALTMON_1 _NL_ABALTMON_1
OK.
>
> # if !defined STDC_HEADERS && !defined HAVE_MEMCPY
> # define MEMCPY(d, s, n) bcopy ((s), (d), (n))
> @@ -492,6 +493,9 @@ __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 a_altmonth \
> + ((const CHAR_T *) (tp->tm_mon < 0 || tp->tm_mon > 11 \
> + ? "?" : _NL_CURRENT (LC_TIME, NLW(ABALTMON_1) + tp->tm_mon)))
OK.
> # define f_altmonth \
> ((const CHAR_T *) (tp->tm_mon < 0 || tp->tm_mon > 11 \
> ? "?" : _NL_CURRENT (LC_TIME, NLW(ALTMON_1) + tp->tm_mon)))
> @@ -501,6 +505,7 @@ __strftime_internal (CHAR_T *s, size_t maxsize, const CHAR_T
> *format,
>
> # define aw_len STRLEN (a_wkday)
> # define am_len STRLEN (a_month)
> +# define aam_len STRLEN (a_altmonth)
> # define ap_len STRLEN (ampm)
> #else
> # if !HAVE_STRFTIME
> @@ -510,11 +515,13 @@ __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 a_altmonth a_month
> # define f_altmonth f_month
> # define ampm (L_("AMPM") + 2 * (tp->tm_hour > 11))
>
> size_t aw_len = 3;
> size_t am_len = 3;
> + size_t aam_len = 3;
> size_t ap_len = 2;
> # endif
> #endif
> @@ -779,10 +786,13 @@ __strftime_internal (CHAR_T *s, size_t maxsize, const
> CHAR_T *format,
> to_uppcase = 1;
> to_lowcase = 0;
> }
> - if (modifier != 0)
> + if (modifier == L_('E'))
OK.
> goto bad_format;
> #if defined _NL_CURRENT || !HAVE_STRFTIME
> - cpy (am_len, a_month);
> + if (modifier == L_('O'))
> + cpy (aam_len, a_altmonth);
> + else
> + cpy (am_len, a_month);
OK.
> break;
> #else
> goto underlying_strftime;
> diff --git a/time/strptime_l.c b/time/strptime_l.c
> index 39cf38d..cd901c2 100644
> --- a/time/strptime_l.c
> +++ b/time/strptime_l.c
> @@ -126,6 +126,8 @@ extern const struct __locale_data _nl_C_LC_TIME
> attribute_hidden;
> # 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 ab_alt_month_name \
> + (&_nl_C_LC_TIME.values[_NL_ITEM_INDEX (_NL_ABALTMON_1)].string)
OK.
> # 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)
> @@ -437,6 +439,18 @@ __strptime_internal (const char *rp, const char *fmt,
> struct tm *tmp,
> alt_month_name[cnt]))
> decided_longest = loc;
> }
> + trp = rp;
> + if (match_string (_NL_CURRENT (LC_TIME, _NL_ABALTMON_1 + cnt),
> + trp)
> + && trp > rp_longest)
> + {
> + rp_longest = trp;
> + cnt_longest = cnt;
> + if (s.decided == not
> + && strcmp (_NL_CURRENT (LC_TIME, _NL_ABALTMON_1 + cnt),
> + alt_month_name[cnt]))
> + decided_longest = loc;
OK.
> + }
> #endif
> }
> #endif
> @@ -448,6 +462,8 @@ __strptime_internal (const char *rp, const char *fmt, struct
> tm *tmp,
> #ifdef _LIBC
> || ((trp = rp, match_string (alt_month_name[cnt], trp))
> && trp > rp_longest)
> + || ((trp = rp, match_string (ab_alt_month_name[cnt], trp))
> + && trp > rp_longest)
OK.
> #endif
> ))
> {
> @@ -1035,7 +1051,9 @@ __strptime_internal (const char *rp, const char *fmt,
> struct tm *tmp,
> case 'O':
> switch (*fmt++)
> {
> + case 'b':
> case 'B':
> + case 'h':
OK.
> /* Match month name. Reprocess as plain 'B'. */
> fmt--;
> goto start_over;
> diff --git a/time/tst-strptime.c b/time/tst-strptime.c
> index bbc1390..ab09f0f 100644
> --- a/time/tst-strptime.c
> +++ b/time/tst-strptime.c
> @@ -24,6 +24,11 @@
> #include <time.h>
>
>
> +/* Some Cyrillic letters in UTF-8. */
> +#define CYR_n "\xd0\xbd"
> +#define CYR_o "\xd0\xbe"
> +#define CYR_ya "\xd1\x8f"
Please encode the UTF-8 directly into the test case.
Developers have to use UTF-8 capable editors, and fonts.
> +
> static const struct
> {
> const char *locale;
> @@ -57,6 +62,14 @@ static const struct
> { "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 },
> + { "pl_PL.UTF-8", "25 lis 2017", "%d %Ob %Y", 6, 328, 10, 25 },
> + { "ru_RU.UTF-8", "26 " CYR_n CYR_o CYR_ya " 2017", "%d %b %Y",
> + 0, 329, 10, 26 },
OK.
> + /* TODO: Add an example of "may"/"maya" (5th month, May) using %Ob in
> + Russian when the localedata is updated. Without the genitive forms
> + in localedata the word "maya" is ambiguous and may be mistaken for
> + "mart" (March).
> + */
> };
>
>
>
11.01.2018 06:01 Carlos O'Donell <carlos@redhat.com> wrote:
>
>
> On 01/08/2018 04:01 PM, Rafal Luzynski wrote:
> > [...]
> > * locale/langinfo.h: New public symbols _NL_ABALTMON_1,
> > _NL_ABALTMON_2, _NL_ABALTMON_3, _NL_ABALTMON_4, _NL_ABALTMON_5,
> > _NL_ABALTMON_6, _NL_ABALTMON_7, _NL_ABALTMON_8, _NL_ABALTMON_9,
> > _NL_ABALTMON_10, _NL_ABALTMON_11, _NL_ABALTMON_12,
> > _NL_WABALTMON_1, _NL_WABALTMON_2, _NL_WABALTMON_3, _NL_WABALTMON_4,
> > _NL_WABALTMON_5, _NL_WABALTMON_6, _NL_WABALTMON_7, _NL_WABALTMON_8,
> > _NL_WABALTMON_9, _NL_WABALTMON_10, _NL_WABALTMON_11, _NL_WABALTMON_12.
> > [...]
>
> Why is there no ABALTMON_* via #ifdef __USE_GNU like there is for ALTMON_*?
> It is OK without them, but seems like a missing useful feature.
Short answer: the idea to define ABALTMON_* did not yet exist when
I was implementing this. And even now I'm not sure this is the right
moment to add this already.
Long answer: the reason behind defining ALTMON_ via #ifdef __USE_GNU is
that this standard already exists somewhere (in BSD and as accepted but
not yet published future change in POSIX) but while it is not yet officially
specified by POSIX we treat it as a GNU extension (hence #ifdef __USE_GNU)
while __ALTMON_* symbols are defined unconditionally. But the idea of
introducing abbreviated alternative month names to glibc is originally
mine (although it already exists in other libraries, like ICU) and I did
not think it would be standardized. So I have defined them as _NL_ABALTMON_*
(as a forever private GNU extension). However, the idea has been filed
as a POSIX update proposal only on October 27, 2017. [1] I don't think
it will be accepted and published soon.
So, do you guys want me to use a different naming pattern already?
> OK with the test case changes to write UTF-8 directly in the test case string.
A question about it below.
> Reviewed-by: Carlos O'Donell <carlos@redhat.com>
I am going to publish another set of patches, mostly due to the changes
in ChangeLog and commit messages. Does this Reviewed-by tag apply to the
new patches as well?
> > [...]
> > +/* Some Cyrillic letters in UTF-8. */
> > +#define CYR_n "\xd0\xbd"
> > +#define CYR_o "\xd0\xbe"
> > +#define CYR_ya "\xd1\x8f"
>
> Please encode the UTF-8 directly into the test case.
>
> Developers have to use UTF-8 capable editors, and fonts.
A question about it below.
> > [...]
> > static const struct
> > {
> > const char *locale;
> > @@ -57,6 +62,14 @@ static const struct
> > { "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 },
> > + { "pl_PL.UTF-8", "25 lis 2017", "%d %Ob %Y", 6, 328, 10, 25 },
> > + { "ru_RU.UTF-8", "26 " CYR_n CYR_o CYR_ya " 2017", "%d %b %Y",
> > + 0, 329, 10, 26 },
>
Do I understand correctly, should I use lines like these?
+ /* ноя - pronounce: 'noya' - "Nov" (abbreviated "November") in Russian. */
+ { "ru_RU.UTF-8", "26 ноя 2017", "%d %b %Y", 0, 329, 10, 26 },
Regards,
Rafal
[1] https://sourceware.org/ml/libc-alpha/2017-10/msg01307.html
On 01/11/2018 11:04 AM, Rafal Luzynski wrote:
> 11.01.2018 06:01 Carlos O'Donell <carlos@redhat.com> wrote:
>>
>>
>> On 01/08/2018 04:01 PM, Rafal Luzynski wrote:
>>> [...]
>>> * locale/langinfo.h: New public symbols _NL_ABALTMON_1,
>>> _NL_ABALTMON_2, _NL_ABALTMON_3, _NL_ABALTMON_4, _NL_ABALTMON_5,
>>> _NL_ABALTMON_6, _NL_ABALTMON_7, _NL_ABALTMON_8, _NL_ABALTMON_9,
>>> _NL_ABALTMON_10, _NL_ABALTMON_11, _NL_ABALTMON_12,
>>> _NL_WABALTMON_1, _NL_WABALTMON_2, _NL_WABALTMON_3, _NL_WABALTMON_4,
>>> _NL_WABALTMON_5, _NL_WABALTMON_6, _NL_WABALTMON_7, _NL_WABALTMON_8,
>>> _NL_WABALTMON_9, _NL_WABALTMON_10, _NL_WABALTMON_11, _NL_WABALTMON_12.
>>> [...]
>>
>> Why is there no ABALTMON_* via #ifdef __USE_GNU like there is for ALTMON_*?
>> It is OK without them, but seems like a missing useful feature.
>
> Short answer: the idea to define ABALTMON_* did not yet exist when
> I was implementing this. And even now I'm not sure this is the right
> moment to add this already.
>
> Long answer: the reason behind defining ALTMON_ via #ifdef __USE_GNU is
> that this standard already exists somewhere (in BSD and as accepted but
> not yet published future change in POSIX) but while it is not yet officially
> specified by POSIX we treat it as a GNU extension (hence #ifdef __USE_GNU)
> while __ALTMON_* symbols are defined unconditionally. But the idea of
> introducing abbreviated alternative month names to glibc is originally
> mine (although it already exists in other libraries, like ICU) and I did
> not think it would be standardized. So I have defined them as _NL_ABALTMON_*
> (as a forever private GNU extension). However, the idea has been filed
> as a POSIX update proposal only on October 27, 2017. [1] I don't think
> it will be accepted and published soon.
>
> So, do you guys want me to use a different naming pattern already?
Please keep the code as-is. Thank you for explaining the situation, it clarifies
the point. The code is OK to go in as-is.
>> OK with the test case changes to write UTF-8 directly in the test case string.
>
> A question about it below.
>
>> Reviewed-by: Carlos O'Donell <carlos@redhat.com>
>
> I am going to publish another set of patches, mostly due to the changes
> in ChangeLog and commit messages. Does this Reviewed-by tag apply to the
> new patches as well?
Yes, it applies also to the new patches, as long as no substantive changes
are made to the code. I don't count the ChangeLog as being substantive.
>>> [...]
>>> +/* Some Cyrillic letters in UTF-8. */
>>> +#define CYR_n "\xd0\xbd"
>>> +#define CYR_o "\xd0\xbe"
>>> +#define CYR_ya "\xd1\x8f"
>>
>> Please encode the UTF-8 directly into the test case.
>>
>> Developers have to use UTF-8 capable editors, and fonts.
>
> A question about it below.
>
>>> [...]
>>> static const struct
>>> {
>>> const char *locale;
>>> @@ -57,6 +62,14 @@ static const struct
>>> { "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 },
>>> + { "pl_PL.UTF-8", "25 lis 2017", "%d %Ob %Y", 6, 328, 10, 25 },
>>> + { "ru_RU.UTF-8", "26 " CYR_n CYR_o CYR_ya " 2017", "%d %b %Y",
>>> + 0, 329, 10, 26 },
>>
>
> Do I understand correctly, should I use lines like these?
>
> + /* ноя - pronounce: 'noya' - "Nov" (abbreviated "November") in Russian. */
> + { "ru_RU.UTF-8", "26 ноя 2017", "%d %b %Y", 0, 329, 10, 26 },
Yes, exactly like this.
> Regards,
>
> Rafal
>
>
> [1] https://sourceware.org/ml/libc-alpha/2017-10/msg01307.html
>
11.01.2018 20:14 Carlos O'Donell <carlos@redhat.com> wrote:
>
>
> On 01/11/2018 11:04 AM, Rafal Luzynski wrote:
> > [...]
> > So, do you guys want me to use a different naming pattern already?
>
> Please keep the code as-is. Thank you for explaining the situation, it
> clarifies
> the point. The code is OK to go in as-is.
OK
> >> OK with the test case changes to write UTF-8 directly in the test case
> >> string.
> >
> > A question about it below.
> >
> >> Reviewed-by: Carlos O'Donell <carlos@redhat.com>
> >
> > I am going to publish another set of patches, mostly due to the changes
> > in ChangeLog and commit messages. Does this Reviewed-by tag apply to the
> > new patches as well?
>
> Yes, it applies also to the new patches, as long as no substantive changes
> are made to the code. I don't count the ChangeLog as being substantive.
OK, great.
> >>> [...]
> >>> static const struct
> >>> {
> >>> const char *locale;
> >>> @@ -57,6 +62,14 @@ static const struct
> >>> { "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 },
> >>> + { "pl_PL.UTF-8", "25 lis 2017", "%d %Ob %Y", 6, 328, 10, 25 },
> >>> + { "ru_RU.UTF-8", "26 " CYR_n CYR_o CYR_ya " 2017", "%d %b %Y",
> >>> + 0, 329, 10, 26 },
> >>
> >
> > Do I understand correctly, should I use lines like these?
> >
> > + /* ноя - pronounce: 'noya' - "Nov" (abbreviated "November") in Russian. */
> > + { "ru_RU.UTF-8", "26 ноя 2017", "%d %b %Y", 0, 329, 10, 26 },
>
> Yes, exactly like this.
OK, done locally.
Regards,
Rafal
@@ -30,7 +30,7 @@ const struct __locale_data _nl_C_LC_TIME attribute_hidden =
{ NULL, }, /* no cached data */
UNDELETABLE,
0,
- 135,
+ 159,
{
{ .string = "Sun" },
{ .string = "Mon" },
@@ -166,6 +166,30 @@ const struct __locale_data _nl_C_LC_TIME attribute_hidden =
{ .wstr = (const uint32_t *) L"September" },
{ .wstr = (const uint32_t *) L"October" },
{ .wstr = (const uint32_t *) L"November" },
- { .wstr = (const uint32_t *) L"December" }
+ { .wstr = (const uint32_t *) L"December" },
+ { .string = "Jan" },
+ { .string = "Feb" },
+ { .string = "Mar" },
+ { .string = "Apr" },
+ { .string = "May" },
+ { .string = "Jun" },
+ { .string = "Jul" },
+ { .string = "Aug" },
+ { .string = "Sep" },
+ { .string = "Oct" },
+ { .string = "Nov" },
+ { .string = "Dec" },
+ { .wstr = (const uint32_t *) L"Jan" },
+ { .wstr = (const uint32_t *) L"Feb" },
+ { .wstr = (const uint32_t *) L"Mar" },
+ { .wstr = (const uint32_t *) L"Apr" },
+ { .wstr = (const uint32_t *) L"May" },
+ { .wstr = (const uint32_t *) L"Jun" },
+ { .wstr = (const uint32_t *) L"Jul" },
+ { .wstr = (const uint32_t *) L"Aug" },
+ { .wstr = (const uint32_t *) L"Sep" },
+ { .wstr = (const uint32_t *) L"Oct" },
+ { .wstr = (const uint32_t *) L"Nov" },
+ { .wstr = (const uint32_t *) L"Dec" }
}
};
@@ -249,8 +249,10 @@ DEFINE_CATEGORY
DEFINE_ELEMENT (_DATE_FMT, "date_fmt", opt, string)
DEFINE_ELEMENT (_NL_W_DATE_FMT, "wide-date_fmt", opt,
wstring)
DEFINE_ELEMENT (_NL_TIME_CODESET, "time-codeset", std, string)
- DEFINE_ELEMENT (ALTMON_1, "alt_mon", opt, stringarray, 12, 12)
- DEFINE_ELEMENT (_NL_WALTMON_1, "wide-alt_mon", opt, wstringarray, 12, 12)
+ DEFINE_ELEMENT (ALTMON_1, "alt_mon", opt, stringarray, 12,
12)
+ DEFINE_ELEMENT (_NL_WALTMON_1, "wide-alt_mon", opt, wstringarray, 12,
12)
+ DEFINE_ELEMENT (_NL_ABALTMON_1, "ab_alt_mon", opt, stringarray, 12,
12)
+ DEFINE_ELEMENT (_NL_WABALTMON_1, "wide-ab_alt_mon", opt, wstringarray, 12,
12)
), NO_POSTLOAD)
@@ -74,7 +74,8 @@ enum
DAY_7, /* Saturday */
#define DAY_7 DAY_7
- /* Abbreviated month names. */
+ /* Abbreviated month names, in the grammatical form used when the month
+ forms part of a complete date. */
ABMON_1, /* Jan */
#define ABMON_1 ABMON_1
ABMON_2,
@@ -176,7 +177,8 @@ enum
_NL_WDAY_6, /* Friday */
_NL_WDAY_7, /* Saturday */
- /* Abbreviated month names. */
+ /* Abbreviated month names, in the grammatical form used when the month
+ forms part of a complete date. */
_NL_WABMON_1, /* Jan */
_NL_WABMON_2,
_NL_WABMON_3,
@@ -277,6 +279,36 @@ enum
_NL_WALTMON_11,
_NL_WALTMON_12,
+ /* Abbreviated month names, in the grammatical form used when the month
+ is named by itself. */
+ _NL_ABALTMON_1, /* Jan */
+ _NL_ABALTMON_2,
+ _NL_ABALTMON_3,
+ _NL_ABALTMON_4,
+ _NL_ABALTMON_5,
+ _NL_ABALTMON_6,
+ _NL_ABALTMON_7,
+ _NL_ABALTMON_8,
+ _NL_ABALTMON_9,
+ _NL_ABALTMON_10,
+ _NL_ABALTMON_11,
+ _NL_ABALTMON_12,
+
+ /* Abbreviated month names, in the grammatical form used when the month
+ is named by itself. */
+ _NL_WABALTMON_1, /* Jan */
+ _NL_WABALTMON_2,
+ _NL_WABALTMON_3,
+ _NL_WABALTMON_4,
+ _NL_WABALTMON_5,
+ _NL_WABALTMON_6,
+ _NL_WABALTMON_7,
+ _NL_WABALTMON_8,
+ _NL_WABALTMON_9,
+ _NL_WABALTMON_10,
+ _NL_WABALTMON_11,
+ _NL_WABALTMON_12,
+
_NL_NUM_LC_TIME, /* Number of indices in LC_TIME category. */
/* LC_COLLATE category: text sorting.
@@ -94,6 +94,9 @@ struct locale_time_t
const char *alt_mon[12];
const uint32_t *walt_mon[12];
int alt_mon_defined;
+ const char *ab_alt_mon[12];
+ const uint32_t *wab_alt_mon[12];
+ int ab_alt_mon_defined;
unsigned char week_ndays;
uint32_t week_1stday;
unsigned char week_1stweek;
@@ -651,6 +654,14 @@ time_output (struct localedef_t *locale, const struct
charmap_t *charmap,
for (n = 0; n < 12; ++n)
add_locale_wstring (&file, time->walt_mon[n] ?: empty_wstr);
+ /* The ab'alt'mons. */
+ for (n = 0; n < 12; ++n)
+ add_locale_string (&file, time->ab_alt_mon[n] ?: "");
+
+ /* The wide character ab'alt'mons. */
+ for (n = 0; n < 12; ++n)
+ add_locale_wstring (&file, time->wab_alt_mon[n] ?: empty_wstr);
+
write_locale_data (output_path, LC_TIME, "LC_TIME", &file);
}
@@ -795,6 +806,7 @@ time_read (struct linereader *ldfile, struct localedef_t
*result,
STRARR_ELEM (am_pm, 2, 2);
STRARR_ELEM (alt_digits, 0, 100);
STRARR_ELEM (alt_mon, 12, 12);
+ STRARR_ELEM (ab_alt_mon, 12, 12);
case tok_era:
/* Ignore the rest of the line if we don't need the input of
@@ -955,6 +967,13 @@ time_read (struct linereader *ldfile, struct localedef_t
*result,
memcpy (time->walt_mon, time->wmon, sizeof (time->wmon));
time->alt_mon_defined = 1;
}
+ /* The same for abbreviated versions. */
+ if (!ignore_content && !time->ab_alt_mon_defined)
+ {
+ memcpy (time->ab_alt_mon, time->abmon, sizeof (time->abmon));
+ memcpy (time->wab_alt_mon, time->wabmon, sizeof (time->wabmon));
+ time->ab_alt_mon_defined = 1;
+ }
return;
default:
@@ -149,6 +149,7 @@ cal_direction, tok_cal_direction, 0
timezone, tok_timezone, 0
date_fmt, tok_date_fmt, 0
alt_mon, tok_alt_mon, 0
+ab_alt_mon, tok_ab_alt_mon, 0
LC_MESSAGES, tok_lc_messages, 0
yesexpr, tok_yesexpr, 0
noexpr, tok_noexpr, 0
@@ -187,6 +187,7 @@ enum token_t
tok_timezone,
tok_date_fmt,
tok_alt_mon,
+ tok_ab_alt_mon,
tok_lc_messages,
tok_yesexpr,
tok_noexpr,
@@ -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 pl_PL.UTF-8
+LOCALES := de_DE.ISO-8859-1 en_US.ISO-8859-1 ja_JP.EUC-JP pl_PL.UTF-8 \
+ ru_RU.UTF-8
include ../gen-locales.mk
$(objpfx)tst-ftime_l.out: $(gen-locales)
@@ -106,6 +106,7 @@ extern char *tzname[];
# define UCHAR_T unsigned char
# define L_(Str) Str
# define NLW(Sym) Sym
+# define ABALTMON_1 _NL_ABALTMON_1
# if !defined STDC_HEADERS && !defined HAVE_MEMCPY
# define MEMCPY(d, s, n) bcopy ((s), (d), (n))
@@ -492,6 +493,9 @@ __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 a_altmonth \
+ ((const CHAR_T *) (tp->tm_mon < 0 || tp->tm_mon > 11 \
+ ? "?" : _NL_CURRENT (LC_TIME, NLW(ABALTMON_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)))
@@ -501,6 +505,7 @@ __strftime_internal (CHAR_T *s, size_t maxsize, const CHAR_T
*format,
# define aw_len STRLEN (a_wkday)
# define am_len STRLEN (a_month)
+# define aam_len STRLEN (a_altmonth)
# define ap_len STRLEN (ampm)
#else
# if !HAVE_STRFTIME
@@ -510,11 +515,13 @@ __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 a_altmonth a_month
# define f_altmonth f_month
# define ampm (L_("AMPM") + 2 * (tp->tm_hour > 11))
size_t aw_len = 3;
size_t am_len = 3;
+ size_t aam_len = 3;
size_t ap_len = 2;
# endif
#endif
@@ -779,10 +786,13 @@ __strftime_internal (CHAR_T *s, size_t maxsize, const
CHAR_T *format,
to_uppcase = 1;
to_lowcase = 0;
}
- if (modifier != 0)
+ if (modifier == L_('E'))
goto bad_format;
#if defined _NL_CURRENT || !HAVE_STRFTIME
- cpy (am_len, a_month);
+ if (modifier == L_('O'))
+ cpy (aam_len, a_altmonth);
+ else
+ cpy (am_len, a_month);
break;
#else
goto underlying_strftime;
@@ -126,6 +126,8 @@ extern const struct __locale_data _nl_C_LC_TIME
attribute_hidden;
# 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 ab_alt_month_name \
+ (&_nl_C_LC_TIME.values[_NL_ITEM_INDEX (_NL_ABALTMON_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)
@@ -437,6 +439,18 @@ __strptime_internal (const char *rp, const char *fmt,
struct tm *tmp,
alt_month_name[cnt]))
decided_longest = loc;
}
+ trp = rp;
+ if (match_string (_NL_CURRENT (LC_TIME, _NL_ABALTMON_1 + cnt),
+ trp)
+ && trp > rp_longest)
+ {
+ rp_longest = trp;
+ cnt_longest = cnt;
+ if (s.decided == not
+ && strcmp (_NL_CURRENT (LC_TIME, _NL_ABALTMON_1 + cnt),
+ alt_month_name[cnt]))
+ decided_longest = loc;
+ }
#endif
}
#endif
@@ -448,6 +462,8 @@ __strptime_internal (const char *rp, const char *fmt, struct
tm *tmp,
#ifdef _LIBC
|| ((trp = rp, match_string (alt_month_name[cnt], trp))
&& trp > rp_longest)
+ || ((trp = rp, match_string (ab_alt_month_name[cnt], trp))
+ && trp > rp_longest)
#endif
))
{
@@ -1035,7 +1051,9 @@ __strptime_internal (const char *rp, const char *fmt,
struct tm *tmp,
case 'O':
switch (*fmt++)
{
+ case 'b':
case 'B':
+ case 'h':
/* Match month name. Reprocess as plain 'B'. */
fmt--;
goto start_over;
@@ -24,6 +24,11 @@
#include <time.h>
+/* Some Cyrillic letters in UTF-8. */
+#define CYR_n "\xd0\xbd"
+#define CYR_o "\xd0\xbe"
+#define CYR_ya "\xd1\x8f"
+
static const struct
{
const char *locale;
@@ -57,6 +62,14 @@ static const struct
{ "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 },
+ { "pl_PL.UTF-8", "25 lis 2017", "%d %Ob %Y", 6, 328, 10, 25 },
+ { "ru_RU.UTF-8", "26 " CYR_n CYR_o CYR_ya " 2017", "%d %b %Y",
+ 0, 329, 10, 26 },
+ /* TODO: Add an example of "may"/"maya" (5th month, May) using %Ob in
+ Russian when the localedata is updated. Without the genitive forms
+ in localedata the word "maya" is ambiguous and may be mistaken for
+ "mart" (March).
+ */
};