From 7b1ec6a05ceac76efca999ebab515afc4caaa5e9 Mon Sep 17 00:00:00 2001 From: Alexandre Oliva Date: Mon, 23 Feb 2015 11:22:37 -0300 Subject: Amendments to Unicode 7 update. for ChangeLog * include/stdc-predef.h (__STDC_ISO_10646__): Update to 201304L, for Unicode 7. for localedata/ChangeLog * unicode-gen/ctype_compatibility.py: Use date ranges in copyright notice. * unicode-gen/ctype_compatibility_test_cases.py: Likewise. * unicode-gen/gen_unicode_ctype.py: Likewise. * unicode-gen/utf8_compatibility.py: Likewise. * unicode-gen/utf8_gen.py: Likewise. Use upper case for global variables, use tuples for global constant arrays. From Mike FABIAN. Suggested by Mike Frysinger . --- ChangeLog | 5 +++++ include/stdc-predef.h | 11 ++++++++--- localedata/ChangeLog | 11 +++++++++++ localedata/unicode-gen/ctype_compatibility.py | 2 +- .../unicode-gen/ctype_compatibility_test_cases.py | 2 +- localedata/unicode-gen/gen_unicode_ctype.py | 2 +- localedata/unicode-gen/utf8_compatibility.py | 2 +- localedata/unicode-gen/utf8_gen.py | 20 ++++++++++---------- 8 files changed, 38 insertions(+), 17 deletions(-) diff --git a/ChangeLog b/ChangeLog index 0a059097e4..0aa5e1c7e1 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,8 @@ +2015-02-23 Alexandre Oliva + + * include/stdc-predef.h (__STDC_ISO_10646__): Update to + 201304L, for Unicode 7. + 2015-02-23 H.J. Lu [BZ #17836] diff --git a/include/stdc-predef.h b/include/stdc-predef.h index 1d6a4eb39d..e5f1139003 100644 --- a/include/stdc-predef.h +++ b/include/stdc-predef.h @@ -49,9 +49,14 @@ # define __STDC_IEC_559_COMPLEX__ 1 #endif -/* wchar_t uses ISO/IEC 10646 (2nd ed., published 2011-03-15) / - Unicode 6.0. */ -#define __STDC_ISO_10646__ 201103L +/* wchar_t uses Unicode 7.0.0. Version 7.0 of the Unicode Standard is + synchronized with ISO/IEC 10646:2012, plus Amendments 1 (published + on April, 2013) and 2 (not yet published as of February, 2015). + Additionally, it includes the accelerated publication of U+20BD + RUBLE SIGN. Therefore Unicode 7.0.0 is between 10646:2012 and + 10646:2014, and so we use the date ISO/IEC 10646:2012 Amd.1 was + published. */ +#define __STDC_ISO_10646__ 201304L /* We do not support C11 . */ #define __STDC_NO_THREADS__ 1 diff --git a/localedata/ChangeLog b/localedata/ChangeLog index 58063e0bbd..ceb373f1be 100644 --- a/localedata/ChangeLog +++ b/localedata/ChangeLog @@ -1,3 +1,14 @@ +2015-02-23 Alexandre Oliva + + * unicode-gen/ctype_compatibility.py: Use date ranges in + copyright notice. + * unicode-gen/ctype_compatibility_test_cases.py: Likewise. + * unicode-gen/gen_unicode_ctype.py: Likewise. + * unicode-gen/utf8_compatibility.py: Likewise. + * unicode-gen/utf8_gen.py: Likewise. Use upper case for + global variables, use tuples for global constant arrays. From + Mike FABIAN. Suggested by Mike Frysinger . + 2015-02-20 Alexandre Oliva [BZ #17588] diff --git a/localedata/unicode-gen/ctype_compatibility.py b/localedata/unicode-gen/ctype_compatibility.py index 19e9ee5176..0d67f29186 100755 --- a/localedata/unicode-gen/ctype_compatibility.py +++ b/localedata/unicode-gen/ctype_compatibility.py @@ -1,6 +1,6 @@ #!/usr/bin/python3 # -*- coding: utf-8 -*- -# Copyright (C) 2014, 2015 Free Software Foundation, Inc. +# Copyright (C) 2014-2015 Free Software Foundation, Inc. # This file is part of the GNU C Library. # # The GNU C Library is free software; you can redistribute it and/or diff --git a/localedata/unicode-gen/ctype_compatibility_test_cases.py b/localedata/unicode-gen/ctype_compatibility_test_cases.py index ab7f6ddc87..34e6de4f40 100644 --- a/localedata/unicode-gen/ctype_compatibility_test_cases.py +++ b/localedata/unicode-gen/ctype_compatibility_test_cases.py @@ -1,5 +1,5 @@ # -*- coding: utf-8 -*- -# Copyright (C) 2014, 2015 Free Software Foundation, Inc. +# Copyright (C) 2014-2015 Free Software Foundation, Inc. # This file is part of the GNU C Library. # # The GNU C Library is free software; you can redistribute it and/or diff --git a/localedata/unicode-gen/gen_unicode_ctype.py b/localedata/unicode-gen/gen_unicode_ctype.py index 559af7957a..0c74f2a849 100755 --- a/localedata/unicode-gen/gen_unicode_ctype.py +++ b/localedata/unicode-gen/gen_unicode_ctype.py @@ -1,7 +1,7 @@ #!/usr/bin/python3 # # Generate a Unicode conforming LC_CTYPE category from a UnicodeData file. -# Copyright (C) 2014, 2015 Free Software Foundation, Inc. +# Copyright (C) 2014-2015 Free Software Foundation, Inc. # This file is part of the GNU C Library. # Based on gen-unicode-ctype.c by Bruno Haible , 2000. # diff --git a/localedata/unicode-gen/utf8_compatibility.py b/localedata/unicode-gen/utf8_compatibility.py index e11327ba82..b84a1eb3de 100755 --- a/localedata/unicode-gen/utf8_compatibility.py +++ b/localedata/unicode-gen/utf8_compatibility.py @@ -1,6 +1,6 @@ #!/usr/bin/python3 # -*- coding: utf-8 -*- -# Copyright (C) 2014, 2015 Free Software Foundation, Inc. +# Copyright (C) 2014-2015 Free Software Foundation, Inc. # This file is part of the GNU C Library. # # The GNU C Library is free software; you can redistribute it and/or diff --git a/localedata/unicode-gen/utf8_gen.py b/localedata/unicode-gen/utf8_gen.py index 670a628d2e..f1b88f5b29 100755 --- a/localedata/unicode-gen/utf8_gen.py +++ b/localedata/unicode-gen/utf8_gen.py @@ -1,6 +1,6 @@ #!/usr/bin/python3 # -*- coding: utf-8 -*- -# Copyright (C) 2014, 2015 Free Software Foundation, Inc. +# Copyright (C) 2014-2015 Free Software Foundation, Inc. # This file is part of the GNU C Library. # # The GNU C Library is free software; you can redistribute it and/or @@ -33,21 +33,21 @@ import re # Auxiliary tables for Hangul syllable names, see the Unicode 3.0 book, # sections 3.11 and 4.4. -jamo_initial_short_name = [ +JAMO_INITIAL_SHORT_NAME = ( 'G', 'GG', 'N', 'D', 'DD', 'R', 'M', 'B', 'BB', 'S', 'SS', '', 'J', 'JJ', 'C', 'K', 'T', 'P', 'H' -] +) -jamo_medial_short_name = [ +JAMO_MEDIAL_SHORT_NAME = ( 'A', 'AE', 'YA', 'YAE', 'EO', 'E', 'YEO', 'YE', 'O', 'WA', 'WAE', 'OE', 'YO', 'U', 'WEO', 'WE', 'WI', 'YU', 'EU', 'YI', 'I' -] +) -jamo_final_short_name = [ +JAMO_FINAL_SHORT_NAME = ( '', 'G', 'GG', 'GS', 'N', 'NI', 'NH', 'D', 'L', 'LG', 'LM', 'LB', 'LS', 'LT', 'LP', 'LH', 'M', 'B', 'BS', 'S', 'SS', 'NG', 'J', 'C', 'K', 'T', 'P', 'H' -] +) def ucs_symbol(code_point): '''Return the UCS symbol string for a Unicode character.''' @@ -74,9 +74,9 @@ def process_range(start, end, outfile, name): index2, index3 = divmod(i - 0xaC00, 28) index1, index2 = divmod(index2, 21) hangul_syllable_name = 'HANGUL SYLLABLE ' \ - + jamo_initial_short_name[index1] \ - + jamo_medial_short_name[index2] \ - + jamo_final_short_name[index3] + + JAMO_INITIAL_SHORT_NAME[index1] \ + + JAMO_MEDIAL_SHORT_NAME[index2] \ + + JAMO_FINAL_SHORT_NAME[index3] outfile.write('{:<11s} {:<12s} {:s}\n'.format( ucs_symbol(i), convert_to_hex(i), hangul_syllable_name)) -- cgit 1.4.1