In perl.git, the branch blead has been updated <http://perl5.git.perl.org/perl.git/commitdiff/fce4ebb4e9a0c0906dd2b524bed097426fbb34d4?hp=4de305e1db7089f455038c15ad7ead8660f90618>
- Log ----------------------------------------------------------------- commit fce4ebb4e9a0c0906dd2b524bed097426fbb34d4 Author: Karl Williamson <k...@cpan.org> Date: Tue Jun 20 17:41:00 2017 -0600 Use Unicode 10.0 The new file from Unicode "extracted/DerivedName.txt" is not delivered here, as Perl doesn't need it, as it duplicates information in other files. M MANIFEST M charclass_invlists.h M lib/Unicode/UCD.t M lib/unicore/ArabicShaping.txt M lib/unicore/BidiBrackets.txt M lib/unicore/BidiMirroring.txt M lib/unicore/Blocks.txt M lib/unicore/CJKRadicals.txt M lib/unicore/CaseFolding.txt M lib/unicore/CompositionExclusions.txt M lib/unicore/DAge.txt M lib/unicore/DCoreProperties.txt M lib/unicore/DNormalizationProps.txt M lib/unicore/EastAsianWidth.txt M lib/unicore/EmojiSources.txt M lib/unicore/HangulSyllableType.txt M lib/unicore/Index.txt M lib/unicore/IndicPositionalCategory.txt M lib/unicore/IndicSyllabicCategory.txt M lib/unicore/Jamo.txt M lib/unicore/LineBreak.txt M lib/unicore/NameAliases.txt M lib/unicore/NamedSequences.txt M lib/unicore/NamedSqProv.txt M lib/unicore/NamesList.txt M lib/unicore/NormalizationCorrections.txt M lib/unicore/PropList.txt M lib/unicore/PropValueAliases.txt M lib/unicore/PropertyAliases.txt M lib/unicore/README.perl M lib/unicore/ReadMe.txt M lib/unicore/ScriptExtensions.txt M lib/unicore/Scripts.txt M lib/unicore/SpecialCasing.txt M lib/unicore/StandardizedVariants.txt M lib/unicore/UnicodeData.txt A lib/unicore/VerticalOrientation.txt M lib/unicore/auxiliary/GCBTest.txt M lib/unicore/auxiliary/GraphemeBreakProperty.txt M lib/unicore/auxiliary/LBTest.txt M lib/unicore/auxiliary/SBTest.txt M lib/unicore/auxiliary/SentenceBreakProperty.txt M lib/unicore/auxiliary/WBTest.txt M lib/unicore/auxiliary/WordBreakProperty.txt M lib/unicore/extracted/DBidiClass.txt M lib/unicore/extracted/DBinaryProperties.txt M lib/unicore/extracted/DCombiningClass.txt M lib/unicore/extracted/DDecompositionType.txt M lib/unicore/extracted/DEastAsianWidth.txt M lib/unicore/extracted/DGeneralCategory.txt M lib/unicore/extracted/DJoinGroup.txt M lib/unicore/extracted/DJoinType.txt M lib/unicore/extracted/DLineBreak.txt M lib/unicore/extracted/DNumType.txt M lib/unicore/extracted/DNumValues.txt M lib/unicore/version M regcharclass.h M unicode_constants.h commit c492f156708438ef285e754e02f85d4c0a9ef50e Author: Karl Williamson <k...@cpan.org> Date: Tue Jun 20 16:49:27 2017 -0600 Prepare for Unicode 10.0 This informs mktables of the new files in 10.0, and updates some comments in other files to reflect new Unicode terminology. M charclass_invlists.h M lib/unicore/mktables M regcharclass.h M regen/mk_invlists.pl M regexec.c ----------------------------------------------------------------------- Summary of changes: MANIFEST | 1 + charclass_invlists.h | 3457 ++++++++++++++++++----- lib/Unicode/UCD.t | 2 +- lib/unicore/ArabicShaping.txt | 22 +- lib/unicore/BidiBrackets.txt | 8 +- lib/unicore/BidiMirroring.txt | 24 +- lib/unicore/Blocks.txt | 17 +- lib/unicore/CJKRadicals.txt | 6 +- lib/unicore/CaseFolding.txt | 8 +- lib/unicore/CompositionExclusions.txt | 6 +- lib/unicore/DAge.txt | 57 +- lib/unicore/DCoreProperties.txt | 328 ++- lib/unicore/DNormalizationProps.txt | 6 +- lib/unicore/EastAsianWidth.txt | 90 +- lib/unicore/EmojiSources.txt | 23 +- lib/unicore/HangulSyllableType.txt | 6 +- lib/unicore/Index.txt | 22 + lib/unicore/IndicPositionalCategory.txt | 52 +- lib/unicore/IndicSyllabicCategory.txt | 109 +- lib/unicore/Jamo.txt | 8 +- lib/unicore/LineBreak.txt | 147 +- lib/unicore/NameAliases.txt | 13 +- lib/unicore/NamedSequences.txt | 26 +- lib/unicore/NamedSqProv.txt | 27 +- lib/unicore/NamesList.txt | 2518 +++++++++++++---- lib/unicore/NormalizationCorrections.txt | 10 +- lib/unicore/PropList.txt | 83 +- lib/unicore/PropValueAliases.txt | 42 +- lib/unicore/PropertyAliases.txt | 10 +- lib/unicore/README.perl | 1 + lib/unicore/ReadMe.txt | 9 +- lib/unicore/ScriptExtensions.txt | 21 +- lib/unicore/Scripts.txt | 129 +- lib/unicore/SpecialCasing.txt | 8 +- lib/unicore/StandardizedVariants.txt | 585 +--- lib/unicore/UnicodeData.txt | 1028 ++++++- lib/unicore/VerticalOrientation.txt | 2199 ++++++++++++++ lib/unicore/auxiliary/GCBTest.txt | 175 +- lib/unicore/auxiliary/GraphemeBreakProperty.txt | 78 +- lib/unicore/auxiliary/LBTest.txt | 23 +- lib/unicore/auxiliary/SBTest.txt | 17 +- lib/unicore/auxiliary/SentenceBreakProperty.txt | 66 +- lib/unicore/auxiliary/WBTest.txt | 263 +- lib/unicore/auxiliary/WordBreakProperty.txt | 105 +- lib/unicore/extracted/DBidiClass.txt | 142 +- lib/unicore/extracted/DBinaryProperties.txt | 6 +- lib/unicore/extracted/DCombiningClass.txt | 108 +- lib/unicore/extracted/DDecompositionType.txt | 6 +- lib/unicore/extracted/DEastAsianWidth.txt | 97 +- lib/unicore/extracted/DGeneralCategory.txt | 176 +- lib/unicore/extracted/DJoinGroup.txt | 72 +- lib/unicore/extracted/DJoinType.txt | 37 +- lib/unicore/extracted/DLineBreak.txt | 168 +- lib/unicore/extracted/DNumType.txt | 9 +- lib/unicore/extracted/DNumValues.txt | 36 +- lib/unicore/mktables | 17 +- lib/unicore/version | 2 +- regcharclass.h | 89 +- regen/mk_invlists.pl | 4 +- regexec.c | 6 +- unicode_constants.h | 4 +- 61 files changed, 10029 insertions(+), 2785 deletions(-) create mode 100644 lib/unicore/VerticalOrientation.txt diff --git a/MANIFEST b/MANIFEST index a775b92702..9c8f985b7c 100644 --- a/MANIFEST +++ b/MANIFEST @@ -4714,6 +4714,7 @@ lib/unicore/SpecialCasing.txt Unicode character database lib/unicore/StandardizedVariants.txt Unicode character database lib/unicore/UnicodeData.txt Unicode character database lib/unicore/version The version of the Unicode +lib/unicore/VerticalOrientation.txt Unicode character database lib/UNIVERSAL.pm Base class for ALL classes lib/User/grent.pm By-name interface to Perl's builtin getgr* lib/User/grent.t See if User::grwent works diff --git a/charclass_invlists.h b/charclass_invlists.h index 4b3d6cc363..ed7bf466ce 100644 --- a/charclass_invlists.h +++ b/charclass_invlists.h @@ -43,7 +43,7 @@ static const UV ASCII_invlist[] = { /* for ASCII/Latin1 */ }; static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ - 1276, /* Number of elements */ + 1298, /* Number of elements */ 148565664, /* Version and data structure type */ 0, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -93,6 +93,8 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x85C, 0x85E, 0x85F, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -124,7 +126,7 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x9DF, 0x9E4, 0x9E6, - 0x9FC, + 0x9FE, 0xA01, 0xA04, 0xA05, @@ -184,7 +186,7 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0xAE6, 0xAF2, 0xAF9, - 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -297,15 +299,13 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, 0xD0E, 0xD11, 0xD12, - 0xD3B, - 0xD3D, 0xD45, 0xD46, 0xD49, @@ -518,11 +518,9 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x1CC0, 0x1CC8, 0x1CD0, - 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1F16, 0x1F18, @@ -564,14 +562,12 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x2090, 0x209D, 0x20A0, - 0x20BF, + 0x20C0, 0x20D0, 0x20F1, 0x2100, 0x218C, 0x2190, - 0x23FF, - 0x2400, 0x2427, 0x2440, 0x244B, @@ -584,7 +580,7 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x2BBD, 0x2BC9, 0x2BCA, - 0x2BD2, + 0x2BD3, 0x2BEC, 0x2BF0, 0x2C00, @@ -622,7 +618,7 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x2DD8, 0x2DDF, 0x2DE0, - 0x2E45, + 0x2E4A, 0x2E80, 0x2E9A, 0x2E9B, @@ -638,7 +634,7 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x3099, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x3190, @@ -652,7 +648,7 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x3300, 0x4DB6, 0x4DC0, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA490, @@ -811,7 +807,7 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x102FC, 0x10300, 0x10324, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -1019,6 +1015,14 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x118F3, 0x118FF, 0x11900, + 0x11A00, + 0x11A48, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A9D, + 0x11A9E, + 0x11AA3, 0x11AC0, 0x11AF9, 0x11C00, @@ -1035,6 +1039,20 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -1076,13 +1094,15 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x16F8F, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -1267,12 +1287,14 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x1F249, 0x1F250, 0x1F252, + 0x1F260, + 0x1F266, 0x1F300, - 0x1F6D3, + 0x1F6D5, 0x1F6E0, 0x1F6ED, 0x1F6F0, - 0x1F6F7, + 0x1F6F9, 0x1F700, 0x1F774, 0x1F780, @@ -1287,22 +1309,20 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x1F888, 0x1F890, 0x1F8AE, + 0x1F900, + 0x1F90C, 0x1F910, - 0x1F91F, - 0x1F920, - 0x1F928, - 0x1F930, - 0x1F931, - 0x1F933, 0x1F93F, 0x1F940, - 0x1F94C, + 0x1F94D, 0x1F950, - 0x1F95F, + 0x1F96C, 0x1F980, - 0x1F992, + 0x1F998, 0x1F9C0, 0x1F9C1, + 0x1F9D0, + 0x1F9E7, 0x20000, 0x2A6D7, 0x2A700, @@ -1311,6 +1331,8 @@ static const UV Assigned_invlist[] = { /* for ASCII/Latin1 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E, 0xE0001, @@ -1990,7 +2012,7 @@ static const UV _Perl_Folds_To_Multi_Char_invlist[] = { /* for ASCII/Latin1 */ #if defined(PERL_IN_PERL_C) static const UV _Perl_GCB_invlist[] = { /* for ASCII/Latin1 */ - 1615, /* Number of elements */ + 1690, /* Number of elements */ 148565664, /* Version and data structure type */ 0, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -2128,6 +2150,8 @@ static const UV _Perl_GCB_invlist[] = { /* for ASCII/Latin1 */ 0xACE, 0xAE2, 0xAE4, + 0xAFA, + 0xB00, 0xB01, 0xB02, 0xB04, @@ -2195,9 +2219,11 @@ static const UV _Perl_GCB_invlist[] = { /* for ASCII/Latin1 */ 0xCD7, 0xCE2, 0xCE4, - 0xD01, + 0xD00, 0xD02, 0xD04, + 0xD3B, + 0xD3D, 0xD3E, 0xD3F, 0xD41, @@ -2400,10 +2426,11 @@ static const UV _Perl_GCB_invlist[] = { /* for ASCII/Latin1 */ 0x1CF2, 0x1CF4, 0x1CF5, + 0x1CF7, 0x1CF8, 0x1CFA, 0x1DC0, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1E00, 0x200B, @@ -2419,8 +2446,16 @@ static const UV _Perl_GCB_invlist[] = { /* for ASCII/Latin1 */ 0x20F1, 0x261D, 0x261E, + 0x2640, + 0x2641, + 0x2642, + 0x2643, + 0x2695, + 0x2697, 0x26F9, 0x26FA, + 0x2708, + 0x2709, 0x270A, 0x270E, 0x2764, @@ -3474,6 +3509,26 @@ static const UV _Perl_GCB_invlist[] = { /* for ASCII/Latin1 */ 0x11726, 0x11727, 0x1172C, + 0x11A01, + 0x11A07, + 0x11A09, + 0x11A0B, + 0x11A33, + 0x11A39, + 0x11A3A, + 0x11A3B, + 0x11A3F, + 0x11A47, + 0x11A48, + 0x11A51, + 0x11A57, + 0x11A59, + 0x11A5C, + 0x11A86, + 0x11A8A, + 0x11A97, + 0x11A98, + 0x11A9A, 0x11C2F, 0x11C30, 0x11C37, @@ -3490,6 +3545,16 @@ static const UV _Perl_GCB_invlist[] = { /* for ASCII/Latin1 */ 0x11CB4, 0x11CB5, 0x11CB7, + 0x11D31, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D46, + 0x11D47, + 0x11D48, 0x16AF0, 0x16AF5, 0x16B30, @@ -3545,12 +3610,30 @@ static const UV _Perl_GCB_invlist[] = { /* for ASCII/Latin1 */ 0x1E94B, 0x1F1E6, 0x1F200, + 0x1F308, + 0x1F309, + 0x1F33E, + 0x1F33F, + 0x1F373, + 0x1F374, 0x1F385, 0x1F386, - 0x1F3C3, + 0x1F393, + 0x1F394, + 0x1F3A4, + 0x1F3A5, + 0x1F3A8, + 0x1F3A9, + 0x1F3C2, 0x1F3C5, + 0x1F3C7, + 0x1F3C8, 0x1F3CA, - 0x1F3CC, + 0x1F3CD, + 0x1F3EB, + 0x1F3EC, + 0x1F3ED, + 0x1F3EE, 0x1F3FB, 0x1F400, 0x1F442, @@ -3573,7 +3656,13 @@ static const UV _Perl_GCB_invlist[] = { /* for ASCII/Latin1 */ 0x1F48C, 0x1F4AA, 0x1F4AB, - 0x1F575, + 0x1F4BB, + 0x1F4BD, + 0x1F527, + 0x1F528, + 0x1F52C, + 0x1F52D, + 0x1F574, 0x1F576, 0x1F57A, 0x1F57B, @@ -3587,22 +3676,30 @@ static const UV _Perl_GCB_invlist[] = { /* for ASCII/Latin1 */ 0x1F648, 0x1F64B, 0x1F650, + 0x1F680, + 0x1F681, + 0x1F692, + 0x1F693, 0x1F6A3, 0x1F6A4, 0x1F6B4, 0x1F6B7, 0x1F6C0, 0x1F6C1, + 0x1F6CC, + 0x1F6CD, 0x1F918, - 0x1F91F, + 0x1F91D, + 0x1F91E, + 0x1F920, 0x1F926, 0x1F927, 0x1F930, - 0x1F931, - 0x1F933, 0x1F93A, - 0x1F93C, + 0x1F93D, 0x1F93F, + 0x1F9D1, + 0x1F9DE, 0xE0000, 0xE0020, 0xE0080, @@ -3775,6 +3872,8 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for ASCII/Latin1 */ GCB_Extend, GCB_Other, GCB_Extend, + GCB_Other, + GCB_Extend, GCB_SpacingMark, GCB_Other, GCB_Extend, @@ -3845,6 +3944,8 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for ASCII/Latin1 */ GCB_SpacingMark, GCB_Other, GCB_Extend, + GCB_Other, + GCB_Extend, GCB_SpacingMark, GCB_Extend, GCB_Other, @@ -4046,6 +4147,7 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for ASCII/Latin1 */ GCB_SpacingMark, GCB_Extend, GCB_Other, + GCB_SpacingMark, GCB_Extend, GCB_Other, GCB_Extend, @@ -4065,8 +4167,16 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for ASCII/Latin1 */ GCB_Other, GCB_E_Base, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Base, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Base, GCB_Other, GCB_Glue_After_Zwj, @@ -5120,23 +5230,53 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for ASCII/Latin1 */ GCB_SpacingMark, GCB_Extend, GCB_Other, + GCB_Extend, GCB_SpacingMark, GCB_Extend, GCB_Other, GCB_Extend, GCB_SpacingMark, + GCB_Prepend, GCB_Extend, GCB_Other, GCB_Extend, GCB_Other, + GCB_Extend, GCB_SpacingMark, GCB_Extend, + GCB_Other, + GCB_Prepend, + GCB_Extend, GCB_SpacingMark, GCB_Extend, + GCB_Other, GCB_SpacingMark, GCB_Extend, GCB_Other, GCB_Extend, + GCB_SpacingMark, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_Other, + GCB_SpacingMark, + GCB_Extend, + GCB_SpacingMark, + GCB_Extend, + GCB_SpacingMark, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_Other, + GCB_Extend, + GCB_Prepend, + GCB_Extend, + GCB_Other, + GCB_Extend, GCB_Other, GCB_Extend, GCB_Other, @@ -5191,12 +5331,30 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for ASCII/Latin1 */ GCB_Other, GCB_Regional_Indicator, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Base, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Base, GCB_Other, GCB_E_Base, GCB_Other, + GCB_E_Base, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Modifier, GCB_Other, GCB_E_Base, @@ -5219,6 +5377,12 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for ASCII/Latin1 */ GCB_Other, GCB_E_Base, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, GCB_E_Base, GCB_Other, GCB_E_Base, @@ -5233,6 +5397,14 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for ASCII/Latin1 */ GCB_Other, GCB_E_Base, GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_Glue_After_Zwj, + GCB_Other, + GCB_E_Base, + GCB_Other, + GCB_E_Base, + GCB_Other, GCB_E_Base, GCB_Other, GCB_E_Base, @@ -5262,7 +5434,7 @@ static const GCB_enum _Perl_GCB_invmap[] = { /* for ASCII/Latin1 */ #if defined(PERL_IN_UTF8_C) static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ - 1367, /* Number of elements */ + 1393, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -5365,6 +5537,8 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0x82E, 0x840, 0x85C, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -5403,6 +5577,8 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0x9E4, 0x9E6, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -5462,7 +5638,7 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0xAE6, 0xAF0, 0xAF9, - 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -5577,15 +5753,13 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, 0xD0E, 0xD11, 0xD12, - 0xD3B, - 0xD3D, 0xD45, 0xD46, 0xD49, @@ -5832,11 +6006,9 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0x1CD0, 0x1CD3, 0x1CD4, - 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1F16, 0x1F18, @@ -5976,7 +6148,7 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -5986,7 +6158,7 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -6175,7 +6347,7 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0x102E1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -6381,6 +6553,14 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0x118EA, 0x118FF, 0x11900, + 0x11A00, + 0x11A3F, + 0x11A47, + 0x11A48, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A9A, 0x11AC0, 0x11AF9, 0x11C00, @@ -6397,6 +6577,20 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -6434,13 +6628,15 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0x16F8F, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -6629,6 +6825,8 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E, 0xE0100, @@ -6636,7 +6834,7 @@ static const UV _Perl_IDCont_invlist[] = { /* for ASCII/Latin1 */ }; static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ - 1161, /* Number of elements */ + 1189, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -6739,6 +6937,8 @@ static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ 0x829, 0x840, 0x859, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -6775,6 +6975,8 @@ static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ 0x9E2, 0x9F0, 0x9F2, + 0x9FC, + 0x9FD, 0xA05, 0xA0B, 0xA0F, @@ -7234,7 +7436,7 @@ static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -7244,7 +7446,7 @@ static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -7439,7 +7641,7 @@ static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ 0x102D1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x10376, @@ -7605,6 +7807,18 @@ static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ 0x118E0, 0x118FF, 0x11900, + 0x11A00, + 0x11A01, + 0x11A0B, + 0x11A33, + 0x11A3A, + 0x11A3B, + 0x11A50, + 0x11A51, + 0x11A5C, + 0x11A84, + 0x11A86, + 0x11A8A, 0x11AC0, 0x11AF9, 0x11C00, @@ -7615,6 +7829,14 @@ static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ 0x11C41, 0x11C72, 0x11C90, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D31, + 0x11D46, + 0x11D47, 0x12000, 0x1239A, 0x12400, @@ -7646,13 +7868,15 @@ static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ 0x16F93, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -7799,6 +8023,8 @@ static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E }; @@ -7808,7 +8034,7 @@ static const UV _Perl_IDStart_invlist[] = { /* for ASCII/Latin1 */ #if defined(PERL_IN_PERL_C) static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ - 2267, /* Number of elements */ + 2313, /* Number of elements */ 148565664, /* Version and data structure type */ 0, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -8023,6 +8249,8 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0xAF0, 0xAF1, 0xAF2, + 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB3C, @@ -8083,8 +8311,10 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0xCE4, 0xCE6, 0xCF0, - 0xD01, + 0xD00, 0xD04, + 0xD3B, + 0xD3D, 0xD3E, 0xD45, 0xD46, @@ -8315,10 +8545,10 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0x1CEE, 0x1CF2, 0x1CF5, - 0x1CF8, + 0x1CF7, 0x1CFA, 0x1DC0, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1E00, 0x1FFD, @@ -8557,7 +8787,7 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0x2E40, 0x2E42, 0x2E43, - 0x2E45, + 0x2E4A, 0x2E80, 0x2E9A, 0x2E9B, @@ -8652,7 +8882,7 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0x30FF, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x3190, @@ -9852,6 +10082,26 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0x1173F, 0x118E0, 0x118EA, + 0x11A01, + 0x11A0B, + 0x11A33, + 0x11A3A, + 0x11A3B, + 0x11A3F, + 0x11A40, + 0x11A41, + 0x11A45, + 0x11A46, + 0x11A47, + 0x11A48, + 0x11A51, + 0x11A5C, + 0x11A8A, + 0x11A9A, + 0x11A9D, + 0x11A9E, + 0x11AA1, + 0x11AA3, 0x11C2F, 0x11C37, 0x11C38, @@ -9867,6 +10117,18 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D31, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D46, + 0x11D47, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12470, 0x12475, 0x13258, @@ -9904,13 +10166,15 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0x16F8F, 0x16F93, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC9D, 0x1BC9F, 0x1BCA0, @@ -9978,10 +10242,12 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0x1F3B7, 0x1F3BC, 0x1F3BD, - 0x1F3C3, + 0x1F3C2, 0x1F3C5, + 0x1F3C7, + 0x1F3C8, 0x1F3CA, - 0x1F3CC, + 0x1F3CD, 0x1F3FB, 0x1F400, 0x1F442, @@ -10018,7 +10284,7 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0x1F525, 0x1F532, 0x1F54A, - 0x1F575, + 0x1F574, 0x1F576, 0x1F57A, 0x1F57B, @@ -10044,6 +10310,8 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0x1F6B7, 0x1F6C0, 0x1F6C1, + 0x1F6CC, + 0x1F6CD, 0x1F700, 0x1F774, 0x1F780, @@ -10058,16 +10326,20 @@ static const UV _Perl_LB_invlist[] = { /* for ASCII/Latin1 */ 0x1F888, 0x1F890, 0x1F8AE, + 0x1F900, + 0x1F90C, 0x1F918, - 0x1F91F, + 0x1F91D, + 0x1F91E, + 0x1F920, 0x1F926, 0x1F927, 0x1F930, - 0x1F931, - 0x1F933, 0x1F93A, - 0x1F93C, + 0x1F93D, 0x1F93F, + 0x1F9D1, + 0x1F9DE, 0x1FFFE, 0x20000, 0x2FFFE, @@ -10355,6 +10627,8 @@ static const LB_enum _Perl_LB_invmap[] = { /* for ASCII/Latin1 */ LB_Alphabetic, LB_Combining_Mark, LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, LB_Numeric, LB_Alphabetic, LB_Combining_Mark, @@ -10413,6 +10687,8 @@ static const LB_enum _Perl_LB_invmap[] = { /* for ASCII/Latin1 */ LB_Alphabetic, LB_Combining_Mark, LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, LB_Numeric, LB_Alphabetic, LB_Postfix_Numeric, @@ -12174,6 +12450,26 @@ static const LB_enum _Perl_LB_invmap[] = { /* for ASCII/Latin1 */ LB_Alphabetic, LB_Combining_Mark, LB_Alphabetic, + LB_Combining_Mark, + LB_Break_Before, + LB_Alphabetic, + LB_Break_After, + LB_Break_Before, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Break_After, + LB_Alphabetic, + LB_Break_Before, + LB_Break_After, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, LB_Break_After, LB_Alphabetic, LB_Numeric, @@ -12185,6 +12481,18 @@ static const LB_enum _Perl_LB_invmap[] = { /* for ASCII/Latin1 */ LB_Alphabetic, LB_Combining_Mark, LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Combining_Mark, + LB_Alphabetic, + LB_Numeric, + LB_Alphabetic, LB_Break_After, LB_Alphabetic, LB_Open_Punctuation, @@ -12229,6 +12537,8 @@ static const LB_enum _Perl_LB_invmap[] = { /* for ASCII/Latin1 */ LB_Alphabetic, LB_Ideographic, LB_Alphabetic, + LB_Ideographic, + LB_Alphabetic, LB_Combining_Mark, LB_Break_After, LB_Combining_Mark, @@ -12300,6 +12610,8 @@ static const LB_enum _Perl_LB_invmap[] = { /* for ASCII/Latin1 */ LB_Ideographic, LB_E_Base, LB_Ideographic, + LB_E_Base, + LB_Ideographic, LB_E_Modifier, LB_Ideographic, LB_E_Base, @@ -12362,6 +12674,8 @@ static const LB_enum _Perl_LB_invmap[] = { /* for ASCII/Latin1 */ LB_Ideographic, LB_E_Base, LB_Ideographic, + LB_E_Base, + LB_Ideographic, LB_Alphabetic, LB_Ideographic, LB_Alphabetic, @@ -12376,6 +12690,10 @@ static const LB_enum _Perl_LB_invmap[] = { /* for ASCII/Latin1 */ LB_Ideographic, LB_Alphabetic, LB_Ideographic, + LB_Alphabetic, + LB_Ideographic, + LB_E_Base, + LB_Ideographic, LB_E_Base, LB_Ideographic, LB_E_Base, @@ -12404,7 +12722,7 @@ static const LB_enum _Perl_LB_invmap[] = { /* for ASCII/Latin1 */ #if defined(PERL_IN_PERL_C) static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ - 2957, /* Number of elements */ + 3002, /* Number of elements */ 148565664, /* Version and data structure type */ 0, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -13109,6 +13427,8 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0x840, 0x859, 0x85C, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -13161,6 +13481,8 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0x9E6, 0x9F0, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -13227,6 +13549,7 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0xAF0, 0xAF9, 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -13351,7 +13674,7 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, @@ -13692,11 +14015,10 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0x1CF2, 0x1CF5, 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, 0x1DC0, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1E00, 0x1E01, @@ -14306,7 +14628,7 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -14316,7 +14638,7 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -14794,7 +15116,7 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0x102E1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x10376, @@ -15055,6 +15377,26 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0x118EA, 0x118FF, 0x11900, + 0x11A00, + 0x11A01, + 0x11A0B, + 0x11A33, + 0x11A3A, + 0x11A3B, + 0x11A3F, + 0x11A42, + 0x11A44, + 0x11A47, + 0x11A48, + 0x11A50, + 0x11A51, + 0x11A5C, + 0x11A84, + 0x11A86, + 0x11A8A, + 0x11A9A, + 0x11A9B, + 0x11A9D, 0x11AC0, 0x11AF9, 0x11C00, @@ -15074,6 +15416,23 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D31, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D46, + 0x11D47, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -15119,13 +15478,15 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0x16F93, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x17000, 0x187ED, 0x18800, 0x18AF3, 0x1B000, - 0x1B002, + 0x1B11F, + 0x1B170, + 0x1B2FC, 0x1BC00, 0x1BC6B, 0x1BC70, @@ -15357,6 +15718,8 @@ static const UV _Perl_SB_invlist[] = { /* for ASCII/Latin1 */ 0x2B81E, 0x2B820, 0x2CEA2, + 0x2CEB0, + 0x2EBE1, 0x2F800, 0x2FA1E, 0xE0001, @@ -16098,6 +16461,8 @@ static const SB_enum _Perl_SB_invmap[] = { /* for ASCII/Latin1 */ SB_Other, SB_OLetter, SB_Other, + SB_OLetter, + SB_Other, SB_Extend, SB_Format, SB_Extend, @@ -16146,6 +16511,8 @@ static const SB_enum _Perl_SB_invmap[] = { /* for ASCII/Latin1 */ SB_Numeric, SB_OLetter, SB_Other, + SB_OLetter, + SB_Other, SB_Extend, SB_Other, SB_OLetter, @@ -16211,6 +16578,7 @@ static const SB_enum _Perl_SB_invmap[] = { /* for ASCII/Latin1 */ SB_Numeric, SB_Other, SB_OLetter, + SB_Extend, SB_Other, SB_Extend, SB_Other, @@ -16343,7 +16711,7 @@ static const SB_enum _Perl_SB_invmap[] = { /* for ASCII/Latin1 */ SB_OLetter, SB_Other, SB_OLetter, - SB_Other, + SB_Extend, SB_OLetter, SB_Extend, SB_Other, @@ -16676,7 +17044,6 @@ static const SB_enum _Perl_SB_invmap[] = { /* for ASCII/Latin1 */ SB_OLetter, SB_Extend, SB_OLetter, - SB_Other, SB_Extend, SB_Other, SB_Lower, @@ -18041,6 +18408,26 @@ static const SB_enum _Perl_SB_invmap[] = { /* for ASCII/Latin1 */ SB_OLetter, SB_Other, SB_OLetter, + SB_Extend, + SB_OLetter, + SB_Extend, + SB_OLetter, + SB_Extend, + SB_Other, + SB_STerm, + SB_Other, + SB_Extend, + SB_Other, + SB_OLetter, + SB_Extend, + SB_OLetter, + SB_Other, + SB_OLetter, + SB_Extend, + SB_Other, + SB_STerm, + SB_Other, + SB_OLetter, SB_Other, SB_OLetter, SB_Other, @@ -18064,6 +18451,23 @@ static const SB_enum _Perl_SB_invmap[] = { /* for ASCII/Latin1 */ SB_OLetter, SB_Other, SB_OLetter, + SB_Extend, + SB_Other, + SB_Extend, + SB_Other, + SB_Extend, + SB_Other, + SB_Extend, + SB_OLetter, + SB_Extend, + SB_Other, + SB_Numeric, + SB_Other, + SB_OLetter, + SB_Other, + SB_OLetter, + SB_Other, + SB_OLetter, SB_Other, SB_OLetter, SB_Other, @@ -18119,6 +18523,8 @@ static const SB_enum _Perl_SB_invmap[] = { /* for ASCII/Latin1 */ SB_Other, SB_OLetter, SB_Other, + SB_OLetter, + SB_Other, SB_Extend, SB_STerm, SB_Format, @@ -18344,6 +18750,8 @@ static const SB_enum _Perl_SB_invmap[] = { /* for ASCII/Latin1 */ SB_Other, SB_OLetter, SB_Other, + SB_OLetter, + SB_Other, SB_Format, SB_Other, SB_Extend, @@ -18357,7 +18765,7 @@ static const SB_enum _Perl_SB_invmap[] = { /* for ASCII/Latin1 */ #if defined(PERL_IN_PERL_C) static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ - 1657, /* Number of elements */ + 1721, /* Number of elements */ 148565664, /* Version and data structure type */ 0, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -18406,17 +18814,10 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0xD8, 0xF7, 0xF8, - 0x2C2, - 0x2C6, - 0x2D2, - 0x2D7, 0x2D8, - 0x2E0, + 0x2DE, 0x2E5, 0x2EC, - 0x2ED, - 0x2EE, - 0x2EF, 0x300, 0x370, 0x375, @@ -18530,6 +18931,8 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x840, 0x859, 0x85C, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -18582,6 +18985,8 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x9E6, 0x9F0, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -18648,6 +19053,7 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0xAF0, 0xAF9, 0xAFA, + 0xB00, 0xB01, 0xB04, 0xB05, @@ -18772,7 +19178,7 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, @@ -19044,11 +19450,10 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x1CF2, 0x1CF5, 0x1CF7, - 0x1CF8, 0x1CFA, 0x1D00, 0x1DC0, - 0x1DF6, + 0x1DFA, 0x1DFB, 0x1E00, 0x1F16, @@ -19154,8 +19559,16 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x24EA, 0x261D, 0x261E, + 0x2640, + 0x2641, + 0x2642, + 0x2643, + 0x2695, + 0x2697, 0x26F9, 0x26FA, + 0x2708, + 0x2709, 0x270A, 0x270E, 0x2764, @@ -19221,7 +19634,7 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -19253,10 +19666,6 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0xA6F0, 0xA6F2, 0xA717, - 0xA720, - 0xA722, - 0xA789, - 0xA78B, 0xA7AF, 0xA7B0, 0xA7B8, @@ -19343,8 +19752,6 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0xAB28, 0xAB2F, 0xAB30, - 0xAB5B, - 0xAB5C, 0xAB66, 0xAB70, 0xABE3, @@ -19467,7 +19874,7 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x102E1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x10376, @@ -19702,6 +20109,22 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x118EA, 0x118FF, 0x11900, + 0x11A00, + 0x11A01, + 0x11A0B, + 0x11A33, + 0x11A3A, + 0x11A3B, + 0x11A3F, + 0x11A47, + 0x11A48, + 0x11A50, + 0x11A51, + 0x11A5C, + 0x11A84, + 0x11A86, + 0x11A8A, + 0x11A9A, 0x11AC0, 0x11AF9, 0x11C00, @@ -19720,6 +20143,23 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D31, + 0x11D37, + 0x11D3A, + 0x11D3B, + 0x11D3C, + 0x11D3E, + 0x11D3F, + 0x11D46, + 0x11D47, + 0x11D48, + 0x11D50, + 0x11D5A, 0x12000, 0x1239A, 0x12400, @@ -19760,7 +20200,7 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x16F93, 0x16FA0, 0x16FE0, - 0x16FE1, + 0x16FE2, 0x1B000, 0x1B001, 0x1BC00, @@ -19954,12 +20394,30 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x1F18A, 0x1F1E6, 0x1F200, + 0x1F308, + 0x1F309, + 0x1F33E, + 0x1F33F, + 0x1F373, + 0x1F374, 0x1F385, 0x1F386, - 0x1F3C3, + 0x1F393, + 0x1F394, + 0x1F3A4, + 0x1F3A5, + 0x1F3A8, + 0x1F3A9, + 0x1F3C2, 0x1F3C5, + 0x1F3C7, + 0x1F3C8, 0x1F3CA, - 0x1F3CC, + 0x1F3CD, + 0x1F3EB, + 0x1F3EC, + 0x1F3ED, + 0x1F3EE, 0x1F3FB, 0x1F400, 0x1F442, @@ -19982,7 +20440,13 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x1F48C, 0x1F4AA, 0x1F4AB, - 0x1F575, + 0x1F4BB, + 0x1F4BD, + 0x1F527, + 0x1F528, + 0x1F52C, + 0x1F52D, + 0x1F574, 0x1F576, 0x1F57A, 0x1F57B, @@ -19996,22 +20460,30 @@ static const UV _Perl_WB_invlist[] = { /* for ASCII/Latin1 */ 0x1F648, 0x1F64B, 0x1F650, + 0x1F680, + 0x1F681, + 0x1F692, + 0x1F693, 0x1F6A3, 0x1F6A4, 0x1F6B4, 0x1F6B7, 0x1F6C0, 0x1F6C1, + 0x1F6CC, + 0x1F6CD, 0x1F918, - 0x1F91F, + 0x1F91D, + 0x1F91E, + 0x1F920, 0x1F926, 0x1F927, 0x1F930, - 0x1F931, - 0x1F933, 0x1F93A, - 0x1F93C, + 0x1F93D, 0x1F93F, + 0x1F9D1, + 0x1F9DE, 0xE0001, 0xE0002, 0xE0020, @@ -20103,14 +20575,7 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_Other, WB_ALetter, WB_Other, - WB_MidLetter, - WB_Other, - WB_ALetter, - WB_Other, - WB_ALetter, - WB_Other, WB_ALetter, - WB_Other, WB_Extend, WB_ALetter, WB_Other, @@ -20228,6 +20693,8 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_Other, WB_ALetter, WB_Other, + WB_ALetter, + WB_Other, WB_Extend, WB_Format, WB_Extend, @@ -20276,6 +20743,8 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_Numeric, WB_ALetter, WB_Other, + WB_ALetter, + WB_Other, WB_Extend, WB_Other, WB_ALetter, @@ -20341,6 +20810,7 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_Numeric, WB_Other, WB_ALetter, + WB_Extend, WB_Other, WB_Extend, WB_Other, @@ -20473,7 +20943,7 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_ALetter, WB_Other, WB_ALetter, - WB_Other, + WB_Extend, WB_ALetter, WB_Extend, WB_Other, @@ -20737,7 +21207,6 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_ALetter, WB_Extend, WB_ALetter, - WB_Other, WB_Extend, WB_Other, WB_ALetter, @@ -20848,8 +21317,16 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_Other, WB_E_Base, WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Base, WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Base, WB_Other, WB_Glue_After_Zwj, @@ -20951,10 +21428,6 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_ALetter, WB_Other, WB_ALetter, - WB_Other, - WB_ALetter, - WB_Other, - WB_ALetter, WB_Extend, WB_ALetter, WB_Extend, @@ -21039,8 +21512,6 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_ALetter, WB_Other, WB_ALetter, - WB_Other, - WB_ALetter, WB_Extend, WB_Other, WB_Extend, @@ -21397,6 +21868,22 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_ALetter, WB_Other, WB_ALetter, + WB_Extend, + WB_ALetter, + WB_Extend, + WB_ALetter, + WB_Extend, + WB_Other, + WB_Extend, + WB_Other, + WB_ALetter, + WB_Extend, + WB_ALetter, + WB_Other, + WB_ALetter, + WB_Extend, + WB_Other, + WB_ALetter, WB_Other, WB_ALetter, WB_Other, @@ -21419,6 +21906,23 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_ALetter, WB_Other, WB_ALetter, + WB_Extend, + WB_Other, + WB_Extend, + WB_Other, + WB_Extend, + WB_Other, + WB_Extend, + WB_ALetter, + WB_Extend, + WB_Other, + WB_Numeric, + WB_Other, + WB_ALetter, + WB_Other, + WB_ALetter, + WB_Other, + WB_ALetter, WB_Other, WB_ALetter, WB_Other, @@ -21648,12 +22152,30 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_Other, WB_Regional_Indicator, WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_E_Base, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Base, WB_Other, WB_E_Base, WB_Other, WB_E_Base, WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Modifier, WB_Other, WB_E_Base, @@ -21676,16 +22198,30 @@ static const WB_enum _Perl_WB_invmap[] = { /* for ASCII/Latin1 */ WB_Other, WB_E_Base, WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_Glue_After_Zwj, + WB_Other, + WB_E_Base, + WB_Other, + WB_E_Base, + WB_Other, WB_E_Base, WB_Other, WB_E_Base, WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Base, WB_Other, WB_E_Base, WB_Other, WB_Glue_After_Zwj, WB_Other, + WB_Glue_After_Zwj, + WB_Other, WB_E_Base, WB_Other, WB_E_Base, @@ -21775,7 +22311,7 @@ static const UV XPerlSpace_invlist[] = { /* for ASCII/Latin1 */ }; static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ - 1357, /* Number of elements */ + 1391, /* Number of elements */ 148565664, /* Version and data structure type */ 1, /* 0 if the list starts at 0; 1 if it starts at the element beyond 0 */ @@ -21882,6 +22418,8 @@ static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ 0x82D, 0x840, 0x859, + 0x860, + 0x86B, 0x8A0, 0x8B5, 0x8B6, @@ -21930,6 +22468,8 @@ static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ 0x9E4, 0x9E6, 0x9F2, + 0x9FC, + 0x9FD, 0xA01, 0xA04, 0xA05, @@ -21987,7 +22527,7 @@ static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ 0xAE6, 0xAF0, 0xAF9, - 0xAFA, + 0xAFD, 0xB01, 0xB04, 0xB05, @@ -22102,7 +22642,7 @@ static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ 0xCF0, 0xCF1, 0xCF3, - 0xD01, + 0xD00, 0xD04, 0xD05, 0xD0D, @@ -22507,7 +23047,7 @@ static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ 0x30FC, 0x3100, 0x3105, - 0x312E, + 0x312F, 0x3131, 0x318F, 0x31A0, @@ -22517,7 +23057,7 @@ static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ 0x3400, 0x4DB6, 0x4E00, - 0x9FD6, + 0x9FEB, 0xA000, 0xA48D, 0xA4D0, @@ -22696,7 +23236,7 @@ static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ 0x102D1, 0x10300, 0x10320, - 0x10330, + 0x1032D, 0x1034B, 0x10350, 0x1037B, @@ -22904,6 +23444,14 @@ static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ 0x118EA, 0x118FF, 0x11900, + 0x11A00, + 0x11A33, + 0x11A35, + 0x11A3F, + 0x11A50, + 0x11A84, + 0x11A86, + 0x11A98, 0x11AC0, 0x11AF9, 0x11C00, @@ -22922,6 +23470,24 @@ static const UV XPosixAlnum_invlist[] = { /* for ASCII/Latin1 */ 0x11CA8, 0x11CA9, 0x11CB7, + 0x11D00, + 0x11D07, + 0x11D08, + 0x11D0A, + 0x11D0B, + 0x11D37, + 0x11D3A, + 0x11D3B, **** PATCH TRUNCATED AT 2000 LINES -- 23244 NOT SHOWN **** -- Perl5 Master Repository