Attachment 10739 Details for Bug 10871 – Also implement abbreviated alternative month names and %Ob (v12)

[patch] Also implement abbreviated alternative month names and %Ob (v12)

v12-0003-Abbreviated-alternative-month-names-Ob-also-adde.patch (text/plain), 14.97 KB, created by Rafal Luzynski on 2018-01-13 10:56:21 UTC

(hide)

Description:

Filename:

MIME Type:

Creator: Rafal Luzynski

Created: 2018-01-13 10:56:21 UTC

Size: 14.97 KB

patch

obsolete

>From cdaa4f267a7aa465b75e2b42571c8a3b1c4977a4 Mon Sep 17 00:00:00 2001
>From: Rafal Luzynski <digitalfreak@lingonborough.com>
>Date: Tue, 14 Nov 2017 02:22:38 +0100
>Subject: [PATCH v12 03/16] Abbreviated alternative month names (%Ob) also
> added (bug 10871).
>
>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 (_nl_C_LC_TIME): Add abbreviated alternative month
>	names, define them as the same as abbreviated month names explicitly.
>	* locale/categories.def (LC_TIME): Add ab_alt_mon and wide-ab_alt_mon.
>	* locale/langinfo.h: (_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): New enum constants.
>	* locale/programs/ld-time.c (struct locale_time_t): Add ab_alt_mon,
>	wab_alt_mon, and ab_alt_mon_defined members.
>	(time_output): Output ab_alt_mon and wab_alt_mon members.
>	(time_read): Read them, initialize them as copies of abmon and wabmon
>	respectively if they are missing, initialize ab_alt_mon_defined.
>	* locale/programs/locfile-kw.gperf (ab_alt_mon): Define.
>	* locale/programs/locfile-token.h (tok_ab_alt_mon): New enum constant.
>	* time/Makefile [$(run-built-tests) = yes] (LOCALES): Add es_ES.UTF-8
>	and ru_RU.UTF-8.
>	* time/strftime_l.c (a_altmonth, aam_len): New macros.
>	[!COMPILE_WIDE] (ABALTMON_1): New macro.
>	(__strftime_internal): Handle %Ob and %Oh formats.
>	* time/strptime_l.c [_LIBC] (ab_alt_month_name): New macro.
>	(__strptime_internal): Handle %Ob and %Oh formats.
>	* time/tst-strptime.c (day_tests): 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                    |  2 +-
> time/strftime_l.c                | 14 ++++++++++++--
> time/strptime_l.c                | 18 ++++++++++++++++++
> time/tst-strptime.c              |  9 +++++++++
> 10 files changed, 125 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,
>   {
>     { .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" }
>   }
> };
>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, 12)
>   ), NO_POSTLOAD)
> 
> 
>diff --git a/locale/langinfo.h b/locale/langinfo.h
>index 65374dd..a50cc9b 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
>+     is a 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
>+     is a 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.
>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;
>   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:
>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,
>   tok_lc_messages,
>   tok_yesexpr,
>   tok_noexpr,
>diff --git a/time/Makefile b/time/Makefile
>index 2deb025..0db1206 100644
>--- a/time/Makefile
>+++ b/time/Makefile
>@@ -49,7 +49,7 @@ include ../Rules
> 
> ifeq ($(run-built-tests),yes)
> LOCALES := de_DE.ISO-8859-1 en_US.ISO-8859-1 ja_JP.EUC-JP fr_FR.UTF-8 \
>-	   pl_PL.UTF-8
>+	   es_ES.UTF-8 pl_PL.UTF-8 ru_RU.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 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
> 
> # 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;
>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)
> # 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;
>diff --git a/time/tst-strptime.c b/time/tst-strptime.c
>index 62ecb7c..2eac5a2 100644
>--- a/time/tst-strptime.c
>+++ b/time/tst-strptime.c
>@@ -56,6 +56,7 @@ static const struct
>   { "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 },
>+  { "es_ES.UTF-8", "20 de nov de 2017", "%d de %Ob de %Y", 1, 323, 10, 20 },
>   /* 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 },
>@@ -63,6 +64,14 @@ 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 },
>+  /* Ð½Ð¾Ñ - pronounce: 'noya' - "Nov" (abbreviated "November") in Russian.  */
>+  { "ru_RU.UTF-8", "26 Ð½Ð¾Ñ 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).
>+   */
> };
> 
> 
>-- 
>2.7.5
>

Actions: View | Diff

Attachments on bug 10871: 8795 | 8874 | 8875 | 8876 | 8877 | 8878 | 8879 | 8880 | 9122 | 9123 | 9124 | 9125 | 9126 | 9127 | 9569 | 9570 | 9571 | 9572 | 9573 | 9574 | 9575 | 9576 | 9577 | 9578 | 9579 | 9595 | 9596 | 9597 | 9598 | 9599 | 9709 | 9710 | 9711 | 9712 | 9713 | 9714 | 9715 | 9716 | 9717 | 9718 | 9719 | 9720 | 9721 | 9908 | 9909 | 9910 | 9911 | 9912 | 9913 | 9914 | 9915 | 9916 | 9917 | 9918 | 9919 | 10063 | 10064 | 10065 | 10225 | 10226 | 10227 | 10228 | 10229 | 10230 | 10231 | 10425 | 10426 | 10427 | 10428 | 10429 | 10430 | 10592 | 10593 | 10594 | 10595 | 10596 | 10597 | 10598 | 10599 | 10600 | 10601 | 10602 | 10731 | 10732 | 10733 | 10734 | 10735 | 10736 | 10737 | 10738 | 10739 | 10740 | 10741 | 10742