From 853d36ee92abf93a736421691c4f76a261c47be8 Mon Sep 17 00:00:00 2001 From: Karl Berry Date: Tue, 13 Aug 2019 20:54:10 +0000 Subject: unicode-data (13aug19) git-svn-id: svn://tug.org/texlive/trunk@51871 c570f23f-e606-0410-a88d-b1316a301751 --- .../texmf-dist/doc/generic/unicode-data/README.md | 8 +- .../tex/generic/unicode-data/BidiBrackets.txt | 185 ++ .../tex/generic/unicode-data/CaseFolding.txt | 4 +- .../tex/generic/unicode-data/EastAsianWidth.txt | 6 +- .../tex/generic/unicode-data/LineBreak.txt | 6 +- .../tex/generic/unicode-data/ScriptExtensions.txt | 573 ++++ .../tex/generic/unicode-data/Scripts.txt | 2838 ++++++++++++++++++++ .../tex/generic/unicode-data/SpecialCasing.txt | 4 +- .../tex/generic/unicode-data/UnicodeData.txt | 1 + .../tex/generic/unicode-data/load-unicode-data.tex | 10 +- .../unicode-data/load-unicode-math-classes.tex | 2 +- .../unicode-data/load-unicode-xetex-classes.tex | 2 +- 12 files changed, 3621 insertions(+), 18 deletions(-) create mode 100644 Master/texmf-dist/tex/generic/unicode-data/BidiBrackets.txt create mode 100644 Master/texmf-dist/tex/generic/unicode-data/ScriptExtensions.txt create mode 100644 Master/texmf-dist/tex/generic/unicode-data/Scripts.txt (limited to 'Master') diff --git a/Master/texmf-dist/doc/generic/unicode-data/README.md b/Master/texmf-dist/doc/generic/unicode-data/README.md index a81262542a5..f673ea45996 100644 --- a/Master/texmf-dist/doc/generic/unicode-data/README.md +++ b/Master/texmf-dist/doc/generic/unicode-data/README.md @@ -96,15 +96,18 @@ Data files The following data files are included here with permission of the Unicode Consortium (see below): - `UnicodeData.txt` +- `BidiBrackets.txt` - `CaseFolding.txt` - `EastAsianWidth.txt` - `LineBreak.txt` - `MathClass.txt` - `SpecialCasing.txt` +- `Scripts.txt` +- `ScriptExtension.txt` With the exception of `MathClass.txt`, which is currently not formally part of the Unicode Character Database, all of the -data files here are for Unicode 10.0.0. +data files here are for Unicode 12.1.0. Requests to include additional Unicode data files in this bundle are welcome. Ideally this bundle will act as a single location for all @@ -159,6 +162,9 @@ Changes - Update data files to Unicode release 11.0.0 - v1.8 (2019-03-09) - Update data files to Unicode release 12.0.0 +- v1.9 (2019-08-13) + - Update data files to Unicode release 12.1.0 + - Add `BidiBrackets.txt`, `Scripts.txt` and `ScriptExtension.txt` License and permission ====================== diff --git a/Master/texmf-dist/tex/generic/unicode-data/BidiBrackets.txt b/Master/texmf-dist/tex/generic/unicode-data/BidiBrackets.txt new file mode 100644 index 00000000000..782f9f25305 --- /dev/null +++ b/Master/texmf-dist/tex/generic/unicode-data/BidiBrackets.txt @@ -0,0 +1,185 @@ +# BidiBrackets-12.1.0.txt +# Date: 2019-03-08, 23:59:00 GMT [AG, LI, KW] +# © 2019 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ +# +# Bidi_Paired_Bracket and Bidi_Paired_Bracket_Type Properties +# +# This file is a normative contributory data file in the Unicode +# Character Database. +# +# Bidi_Paired_Bracket is a normative property of type Miscellaneous, +# which establishes a mapping between characters that are treated as +# bracket pairs by the Unicode Bidirectional Algorithm. +# +# Bidi_Paired_Bracket_Type is a normative property of type Enumeration, +# which classifies characters into opening and closing paired brackets +# for the purposes of the Unicode Bidirectional Algorithm. +# +# This file lists the set of code points with Bidi_Paired_Bracket_Type +# property values Open and Close. The set is derived from the character +# properties General_Category (gc), Bidi_Class (bc), Bidi_Mirrored (Bidi_M), +# and Bidi_Mirroring_Glyph (bmg), as follows: two characters, A and B, +# form a bracket pair if A has gc=Ps and B has gc=Pe, both have bc=ON and +# Bidi_M=Y, and bmg of A is B. Bidi_Paired_Bracket (bpb) maps A to B and +# vice versa, and their Bidi_Paired_Bracket_Type (bpt) property values are +# Open (o) and Close (c), respectively. +# +# The brackets with ticks U+298D LEFT SQUARE BRACKET WITH TICK IN TOP CORNER +# through U+2990 RIGHT SQUARE BRACKET WITH TICK IN TOP CORNER are paired the +# same way their glyphs form mirror pairs, according to their bmg property +# values. They are not paired on the basis of a diagonal or antidiagonal +# matching of the corner ticks inferred from code point order. +# +# For legacy reasons, the characters U+FD3E ORNATE LEFT PARENTHESIS and +# U+FD3F ORNATE RIGHT PARENTHESIS do not mirror in bidirectional display +# and therefore do not form a bracket pair. +# +# The Unicode property value stability policy guarantees that characters +# which have bpt=o or bpt=c also have bc=ON and Bidi_M=Y. As a result, an +# implementation can optimize the lookup of the Bidi_Paired_Bracket_Type +# property values Open and Close by restricting the processing to characters +# with bc=ON. +# +# The format of the file is three fields separated by a semicolon. +# Field 0: Unicode code point value, represented as a hexadecimal value +# Field 1: Bidi_Paired_Bracket property value, a code point value or +# Field 2: Bidi_Paired_Bracket_Type property value, one of the following: +# o Open +# c Close +# n None +# The names of the characters in field 0 are given in comments at the end +# of each line. +# +# For information on bidirectional paired brackets, see UAX #9: Unicode +# Bidirectional Algorithm, at http://www.unicode.org/unicode/reports/tr9/ +# +# This file was originally created by Andrew Glass and Laurentiu Iancu +# for Unicode 6.3. + +0028; 0029; o # LEFT PARENTHESIS +0029; 0028; c # RIGHT PARENTHESIS +005B; 005D; o # LEFT SQUARE BRACKET +005D; 005B; c # RIGHT SQUARE BRACKET +007B; 007D; o # LEFT CURLY BRACKET +007D; 007B; c # RIGHT CURLY BRACKET +0F3A; 0F3B; o # TIBETAN MARK GUG RTAGS GYON +0F3B; 0F3A; c # TIBETAN MARK GUG RTAGS GYAS +0F3C; 0F3D; o # TIBETAN MARK ANG KHANG GYON +0F3D; 0F3C; c # TIBETAN MARK ANG KHANG GYAS +169B; 169C; o # OGHAM FEATHER MARK +169C; 169B; c # OGHAM REVERSED FEATHER MARK +2045; 2046; o # LEFT SQUARE BRACKET WITH QUILL +2046; 2045; c # RIGHT SQUARE BRACKET WITH QUILL +207D; 207E; o # SUPERSCRIPT LEFT PARENTHESIS +207E; 207D; c # SUPERSCRIPT RIGHT PARENTHESIS +208D; 208E; o # SUBSCRIPT LEFT PARENTHESIS +208E; 208D; c # SUBSCRIPT RIGHT PARENTHESIS +2308; 2309; o # LEFT CEILING +2309; 2308; c # RIGHT CEILING +230A; 230B; o # LEFT FLOOR +230B; 230A; c # RIGHT FLOOR +2329; 232A; o # LEFT-POINTING ANGLE BRACKET +232A; 2329; c # RIGHT-POINTING ANGLE BRACKET +2768; 2769; o # MEDIUM LEFT PARENTHESIS ORNAMENT +2769; 2768; c # MEDIUM RIGHT PARENTHESIS ORNAMENT +276A; 276B; o # MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT +276B; 276A; c # MEDIUM FLATTENED RIGHT PARENTHESIS ORNAMENT +276C; 276D; o # MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT +276D; 276C; c # MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT +276E; 276F; o # HEAVY LEFT-POINTING ANGLE QUOTATION MARK ORNAMENT +276F; 276E; c # HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT +2770; 2771; o # HEAVY LEFT-POINTING ANGLE BRACKET ORNAMENT +2771; 2770; c # HEAVY RIGHT-POINTING ANGLE BRACKET ORNAMENT +2772; 2773; o # LIGHT LEFT TORTOISE SHELL BRACKET ORNAMENT +2773; 2772; c # LIGHT RIGHT TORTOISE SHELL BRACKET ORNAMENT +2774; 2775; o # MEDIUM LEFT CURLY BRACKET ORNAMENT +2775; 2774; c # MEDIUM RIGHT CURLY BRACKET ORNAMENT +27C5; 27C6; o # LEFT S-SHAPED BAG DELIMITER +27C6; 27C5; c # RIGHT S-SHAPED BAG DELIMITER +27E6; 27E7; o # MATHEMATICAL LEFT WHITE SQUARE BRACKET +27E7; 27E6; c # MATHEMATICAL RIGHT WHITE SQUARE BRACKET +27E8; 27E9; o # MATHEMATICAL LEFT ANGLE BRACKET +27E9; 27E8; c # MATHEMATICAL RIGHT ANGLE BRACKET +27EA; 27EB; o # MATHEMATICAL LEFT DOUBLE ANGLE BRACKET +27EB; 27EA; c # MATHEMATICAL RIGHT DOUBLE ANGLE BRACKET +27EC; 27ED; o # MATHEMATICAL LEFT WHITE TORTOISE SHELL BRACKET +27ED; 27EC; c # MATHEMATICAL RIGHT WHITE TORTOISE SHELL BRACKET +27EE; 27EF; o # MATHEMATICAL LEFT FLATTENED PARENTHESIS +27EF; 27EE; c # MATHEMATICAL RIGHT FLATTENED PARENTHESIS +2983; 2984; o # LEFT WHITE CURLY BRACKET +2984; 2983; c # RIGHT WHITE CURLY BRACKET +2985; 2986; o # LEFT WHITE PARENTHESIS +2986; 2985; c # RIGHT WHITE PARENTHESIS +2987; 2988; o # Z NOTATION LEFT IMAGE BRACKET +2988; 2987; c # Z NOTATION RIGHT IMAGE BRACKET +2989; 298A; o # Z NOTATION LEFT BINDING BRACKET +298A; 2989; c # Z NOTATION RIGHT BINDING BRACKET +298B; 298C; o # LEFT SQUARE BRACKET WITH UNDERBAR +298C; 298B; c # RIGHT SQUARE BRACKET WITH UNDERBAR +298D; 2990; o # LEFT SQUARE BRACKET WITH TICK IN TOP CORNER +298E; 298F; c # RIGHT SQUARE BRACKET WITH TICK IN BOTTOM CORNER +298F; 298E; o # LEFT SQUARE BRACKET WITH TICK IN BOTTOM CORNER +2990; 298D; c # RIGHT SQUARE BRACKET WITH TICK IN TOP CORNER +2991; 2992; o # LEFT ANGLE BRACKET WITH DOT +2992; 2991; c # RIGHT ANGLE BRACKET WITH DOT +2993; 2994; o # LEFT ARC LESS-THAN BRACKET +2994; 2993; c # RIGHT ARC GREATER-THAN BRACKET +2995; 2996; o # DOUBLE LEFT ARC GREATER-THAN BRACKET +2996; 2995; c # DOUBLE RIGHT ARC LESS-THAN BRACKET +2997; 2998; o # LEFT BLACK TORTOISE SHELL BRACKET +2998; 2997; c # RIGHT BLACK TORTOISE SHELL BRACKET +29D8; 29D9; o # LEFT WIGGLY FENCE +29D9; 29D8; c # RIGHT WIGGLY FENCE +29DA; 29DB; o # LEFT DOUBLE WIGGLY FENCE +29DB; 29DA; c # RIGHT DOUBLE WIGGLY FENCE +29FC; 29FD; o # LEFT-POINTING CURVED ANGLE BRACKET +29FD; 29FC; c # RIGHT-POINTING CURVED ANGLE BRACKET +2E22; 2E23; o # TOP LEFT HALF BRACKET +2E23; 2E22; c # TOP RIGHT HALF BRACKET +2E24; 2E25; o # BOTTOM LEFT HALF BRACKET +2E25; 2E24; c # BOTTOM RIGHT HALF BRACKET +2E26; 2E27; o # LEFT SIDEWAYS U BRACKET +2E27; 2E26; c # RIGHT SIDEWAYS U BRACKET +2E28; 2E29; o # LEFT DOUBLE PARENTHESIS +2E29; 2E28; c # RIGHT DOUBLE PARENTHESIS +3008; 3009; o # LEFT ANGLE BRACKET +3009; 3008; c # RIGHT ANGLE BRACKET +300A; 300B; o # LEFT DOUBLE ANGLE BRACKET +300B; 300A; c # RIGHT DOUBLE ANGLE BRACKET +300C; 300D; o # LEFT CORNER BRACKET +300D; 300C; c # RIGHT CORNER BRACKET +300E; 300F; o # LEFT WHITE CORNER BRACKET +300F; 300E; c # RIGHT WHITE CORNER BRACKET +3010; 3011; o # LEFT BLACK LENTICULAR BRACKET +3011; 3010; c # RIGHT BLACK LENTICULAR BRACKET +3014; 3015; o # LEFT TORTOISE SHELL BRACKET +3015; 3014; c # RIGHT TORTOISE SHELL BRACKET +3016; 3017; o # LEFT WHITE LENTICULAR BRACKET +3017; 3016; c # RIGHT WHITE LENTICULAR BRACKET +3018; 3019; o # LEFT WHITE TORTOISE SHELL BRACKET +3019; 3018; c # RIGHT WHITE TORTOISE SHELL BRACKET +301A; 301B; o # LEFT WHITE SQUARE BRACKET +301B; 301A; c # RIGHT WHITE SQUARE BRACKET +FE59; FE5A; o # SMALL LEFT PARENTHESIS +FE5A; FE59; c # SMALL RIGHT PARENTHESIS +FE5B; FE5C; o # SMALL LEFT CURLY BRACKET +FE5C; FE5B; c # SMALL RIGHT CURLY BRACKET +FE5D; FE5E; o # SMALL LEFT TORTOISE SHELL BRACKET +FE5E; FE5D; c # SMALL RIGHT TORTOISE SHELL BRACKET +FF08; FF09; o # FULLWIDTH LEFT PARENTHESIS +FF09; FF08; c # FULLWIDTH RIGHT PARENTHESIS +FF3B; FF3D; o # FULLWIDTH LEFT SQUARE BRACKET +FF3D; FF3B; c # FULLWIDTH RIGHT SQUARE BRACKET +FF5B; FF5D; o # FULLWIDTH LEFT CURLY BRACKET +FF5D; FF5B; c # FULLWIDTH RIGHT CURLY BRACKET +FF5F; FF60; o # FULLWIDTH LEFT WHITE PARENTHESIS +FF60; FF5F; c # FULLWIDTH RIGHT WHITE PARENTHESIS +FF62; FF63; o # HALFWIDTH LEFT CORNER BRACKET +FF63; FF62; c # HALFWIDTH RIGHT CORNER BRACKET + +# EOF diff --git a/Master/texmf-dist/tex/generic/unicode-data/CaseFolding.txt b/Master/texmf-dist/tex/generic/unicode-data/CaseFolding.txt index 47949f0f995..7eeb915abfd 100644 --- a/Master/texmf-dist/tex/generic/unicode-data/CaseFolding.txt +++ b/Master/texmf-dist/tex/generic/unicode-data/CaseFolding.txt @@ -1,5 +1,5 @@ -# CaseFolding-12.0.0.txt -# Date: 2019-01-22, 08:18:22 GMT +# CaseFolding-12.1.0.txt +# Date: 2019-03-10, 10:53:00 GMT # © 2019 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html diff --git a/Master/texmf-dist/tex/generic/unicode-data/EastAsianWidth.txt b/Master/texmf-dist/tex/generic/unicode-data/EastAsianWidth.txt index 424735913b7..94d55d6654a 100644 --- a/Master/texmf-dist/tex/generic/unicode-data/EastAsianWidth.txt +++ b/Master/texmf-dist/tex/generic/unicode-data/EastAsianWidth.txt @@ -1,5 +1,5 @@ -# EastAsianWidth-12.0.0.txt -# Date: 2019-01-21, 14:12:58 GMT [KW, LI] +# EastAsianWidth-12.1.0.txt +# Date: 2019-03-31, 22:01:58 GMT [KW, LI] # © 2019 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html @@ -1477,7 +1477,7 @@ 3280..3289;W # No [10] CIRCLED IDEOGRAPH ONE..CIRCLED IDEOGRAPH TEN 328A..32B0;W # So [39] CIRCLED IDEOGRAPH MOON..CIRCLED IDEOGRAPH NIGHT 32B1..32BF;W # No [15] CIRCLED NUMBER THIRTY SIX..CIRCLED NUMBER FIFTY -32C0..32FE;W # So [63] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..CIRCLED KATAKANA WO +32C0..32FF;W # So [64] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..SQUARE ERA NAME REIWA 3300..33FF;W # So [256] SQUARE APAATO..SQUARE GAL 3400..4DB5;W # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 4DB6..4DBF;W # Cn [10] .. diff --git a/Master/texmf-dist/tex/generic/unicode-data/LineBreak.txt b/Master/texmf-dist/tex/generic/unicode-data/LineBreak.txt index 098334da1f2..9728582ab1e 100644 --- a/Master/texmf-dist/tex/generic/unicode-data/LineBreak.txt +++ b/Master/texmf-dist/tex/generic/unicode-data/LineBreak.txt @@ -1,5 +1,5 @@ -# LineBreak-12.0.0.txt -# Date: 2019-01-21, 14:17:37 GMT [KW, LI] +# LineBreak-12.1.0.txt +# Date: 2019-03-31, 22:04:15 GMT [KW, LI] # © 2019 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see http://www.unicode.org/terms_of_use.html @@ -1501,7 +1501,7 @@ 3280..3289;ID # No [10] CIRCLED IDEOGRAPH ONE..CIRCLED IDEOGRAPH TEN 328A..32B0;ID # So [39] CIRCLED IDEOGRAPH MOON..CIRCLED IDEOGRAPH NIGHT 32B1..32BF;ID # No [15] CIRCLED NUMBER THIRTY SIX..CIRCLED NUMBER FIFTY -32C0..32FE;ID # So [63] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..CIRCLED KATAKANA WO +32C0..32FF;ID # So [64] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..SQUARE ERA NAME REIWA 3300..33FF;ID # So [256] SQUARE APAATO..SQUARE GAL 3400..4DB5;ID # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 4DB6..4DBF;ID # Cn [10] .. diff --git a/Master/texmf-dist/tex/generic/unicode-data/ScriptExtensions.txt b/Master/texmf-dist/tex/generic/unicode-data/ScriptExtensions.txt new file mode 100644 index 00000000000..ce98cba767e --- /dev/null +++ b/Master/texmf-dist/tex/generic/unicode-data/ScriptExtensions.txt @@ -0,0 +1,573 @@ +# ScriptExtensions-12.1.0.txt +# Date: 2019-04-01, 09:10:42 GMT +# © 2019 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ +# +# The Script_Extensions property indicates which characters are commonly used +# with more than one script, but with a limited number of scripts. +# For each code point, there is one or more property values. Each such value is a Script property value. +# For more information, see: +# UAX #24, Unicode Script Property: http://www.unicode.org/reports/tr24/ +# Especially the sections: +# http://www.unicode.org/reports/tr24/#Assignment_Script_Values +# http://www.unicode.org/reports/tr24/#Assignment_ScriptX_Values +# +# Each Script_Extensions value in this file consists of a set +# of one or more abbreviated Script property values. The ordering of the +# values in that set is not material, but for stability in presentation +# it is given here as alphabetical. +# +# The Script_Extensions values are presented in sorted order in the file. +# They are sorted first by the number of Script property values in their sets, +# and then alphabetically by first differing Script property value. +# +# Following each distinct Script_Extensions value is the list of code +# points associated with that value, listed in code point order. +# +# All code points not explicitly listed for Script_Extensions +# have as their value the corresponding Script property value +# +# @missing: 0000..10FFFF;