Use Unicode 9.0

This includes regenerating the files that depend on the Unicode 9 data
files

Author: Unicode Consortium

charclass_invlists.h

@@ -19,7 +19,7 @@ use Test::More;
 
 use Unicode::UCD qw(charinfo charprop charprops_all);
 
-my $expected_version = '8.0.0';
+my $expected_version = '9.0.0';
 my $current_version = Unicode::UCD::UnicodeVersion;
 my $v_unicode_version = pack "C*", split /\./, $current_version;
 my $unknown_script = ($v_unicode_version lt v5.0.0)

lib/Unicode/UCD.t

@@ -1,23 +1,23 @@
-# ArabicShaping-8.0.0.txt
-# Date: 2015-02-17, 23:33:00 GMT [RP]
+# ArabicShaping-9.0.0.txt
+# Date: 2016-02-24, 22:25:00 GMT [RP]
+# © 2016 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
 #
 # This file is a normative contributory data file in the
 # Unicode Character Database.
 #
-# Copyright (c) 1991-2014 Unicode, Inc.
-# For terms of use, see http://www.unicode.org/terms_of_use.html
-#
 # This file defines the Joining_Type and Joining_Group property
 # values for Arabic, Syriac, N'Ko, Mandaic, and Manichaean positional
 # shaping, repeating in machine readable form the information
 # exemplified in Tables 9-3, 9-8, 9-9, 9-10, 9-14, 9-15, 9-16, 9-19,
 # 9-20, 10-4, 10-5, 10-6, 10-7, and 19-5 of The Unicode Standard core
 # specification. This file also defines Joining_Type values for
-# Mongolian, Phags-pa, and Psalter Pahlavi positional shaping, which
-# are not listed in tables in the standard.
+# Mongolian, Phags-pa, Psalter Pahlavi, and Adlam positional shaping,
+# which are not listed in tables in the standard.
 #
-# See Sections 9.2, 9.3, 9.5, 10.5, 10.6, 13.4, 14.3, 19.4 of
-# The Unicode Standard core specification for more information.
+# See Sections 9.2, 9.3, 9.5, 10.5, 10.6, 13.4, 14.3, 19.4, and 19.9
+# of The Unicode Standard core specification for more information.
 #
 # Each line contains four fields, separated by a semicolon.
 #
@@ -50,8 +50,8 @@
 # Field 3: defines the joining group (property name: Joining_Group)
 #
 # The values of the joining group are based schematically on character
-# names. Where a schematic character name consists of two or more parts separated
-# by spaces, the formal Joining_Group property value, as specified in
+# names. Where a schematic character name consists of two or more parts
+# separated by spaces, the formal Joining_Group property value, as specified in
 # PropertyValueAliases.txt, consists of the same name parts joined by
 # underscores. Hence, the entry:
 #
@@ -90,7 +90,7 @@
 #   have joining type T.
 # - All others not explicitly listed have joining type U.
 #
-# For an explicit listing of characters of joining type T, see
+# For an explicit listing of all characters of joining type T, see
 # the derived property file DerivedJoiningType.txt.
 #
 # #############################################################
@@ -436,6 +436,15 @@
 08B2; REH WITH DOT AND INVERTED V ABOVE; R; REH
 08B3; AIN WITH 3 DOTS BELOW; D; AIN
 08B4; KAF WITH DOT BELOW; D; KAF
+08B6; BEH WITH MEEM ABOVE; D; BEH
+08B7; DOTLESS BEH WITH 3 DOTS BELOW AND MEEM ABOVE; D; BEH
+08B8; DOTLESS BEH WITH TEH ABOVE; D; BEH
+08B9; REH WITH NOON ABOVE; R; REH
+08BA; YEH WITH NOON ABOVE; D; YEH
+08BB; AFRICAN FEH; D; AFRICAN FEH
+08BC; AFRICAN QAF; D; AFRICAN QAF
+08BD; AFRICAN NOON; D; AFRICAN NOON
+08E2; ARABIC DISPUTED END OF AYAH; U; No_Joining_Group
 
 # Mongolian Characters
 
@@ -536,8 +545,8 @@
 1882; MONGOLIAN ALI GALI DAMARU; U; No_Joining_Group
 1883; MONGOLIAN ALI GALI UBADAMA; U; No_Joining_Group
 1884; MONGOLIAN ALI GALI INVERTED UBADAMA; U; No_Joining_Group
-1885; MONGOLIAN ALI GALI BALUDA; U; No_Joining_Group
-1886; MONGOLIAN ALI GALI THREE BALUDA; U; No_Joining_Group
+1885; MONGOLIAN ALI GALI BALUDA; T; No_Joining_Group
+1886; MONGOLIAN ALI GALI THREE BALUDA; T; No_Joining_Group
 1887; MONGOLIAN ALI GALI A; D; No_Joining_Group
 1888; MONGOLIAN ALI GALI I; D; No_Joining_Group
 1889; MONGOLIAN ALI GALI KA; D; No_Joining_Group
@@ -578,6 +587,7 @@
 
 200C; ZERO WIDTH NON-JOINER; U; No_Joining_Group
 200D; ZERO WIDTH JOINER; C; No_Joining_Group
+202F; NARROW NO-BREAK SPACE; U; No_Joining_Group
 2066; LEFT-TO-RIGHT ISOLATE; U; No_Joining_Group
 2067; RIGHT-TO-LEFT ISOLATE; U; No_Joining_Group
 2068; FIRST STRONG ISOLATE; U; No_Joining_Group
@@ -711,4 +721,75 @@ A873; PHAGS-PA CANDRABINDU; U; No_Joining_Group
 10BAE; PSALTER PAHLAVI TWENTY; D; No_Joining_Group
 10BAF; PSALTER PAHLAVI HUNDRED; U; No_Joining_Group
 
+# Adlam Characters
+
+1E900;ADLAM CAPITAL ALIF; D; No_Joining_Group
+1E901;ADLAM CAPITAL DAALI; D; No_Joining_Group
+1E902;ADLAM CAPITAL LAAM; D; No_Joining_Group
+1E903;ADLAM CAPITAL MIIM; D; No_Joining_Group
+1E904;ADLAM CAPITAL BA; D; No_Joining_Group
+1E905;ADLAM CAPITAL SINNYIIYHE; D; No_Joining_Group
+1E906;ADLAM CAPITAL PE; D; No_Joining_Group
+1E907;ADLAM CAPITAL BHE; D; No_Joining_Group
+1E908;ADLAM CAPITAL RA; D; No_Joining_Group
+1E909;ADLAM CAPITAL E; D; No_Joining_Group
+1E90A;ADLAM CAPITAL FA; D; No_Joining_Group
+1E90B;ADLAM CAPITAL I; D; No_Joining_Group
+1E90C;ADLAM CAPITAL O; D; No_Joining_Group
+1E90D;ADLAM CAPITAL DHA; D; No_Joining_Group
+1E90E;ADLAM CAPITAL YHE; D; No_Joining_Group
+1E90F;ADLAM CAPITAL WAW; D; No_Joining_Group
+1E910;ADLAM CAPITAL NUN; D; No_Joining_Group
+1E911;ADLAM CAPITAL KAF; D; No_Joining_Group
+1E912;ADLAM CAPITAL YA; D; No_Joining_Group
+1E913;ADLAM CAPITAL U; D; No_Joining_Group
+1E914;ADLAM CAPITAL JIIM; D; No_Joining_Group
+1E915;ADLAM CAPITAL CHI; D; No_Joining_Group
+1E916;ADLAM CAPITAL HA; D; No_Joining_Group
+1E917;ADLAM CAPITAL QAAF; D; No_Joining_Group
+1E918;ADLAM CAPITAL GA; D; No_Joining_Group
+1E919;ADLAM CAPITAL NYA; D; No_Joining_Group
+1E91A;ADLAM CAPITAL TU; D; No_Joining_Group
+1E91B;ADLAM CAPITAL NHA; D; No_Joining_Group
+1E91C;ADLAM CAPITAL VA; D; No_Joining_Group
+1E91D;ADLAM CAPITAL KHA; D; No_Joining_Group
+1E91E;ADLAM CAPITAL GBE; D; No_Joining_Group
+1E91F;ADLAM CAPITAL ZAL; D; No_Joining_Group
+1E920;ADLAM CAPITAL KPO; D; No_Joining_Group
+1E921;ADLAM CAPITAL SHA; D; No_Joining_Group
+1E922;ADLAM SMALL ALIF; D; No_Joining_Group
+1E923;ADLAM SMALL DAALI; D; No_Joining_Group
+1E924;ADLAM SMALL LAAM; D; No_Joining_Group
+1E925;ADLAM SMALL MIIM; D; No_Joining_Group
+1E926;ADLAM SMALL BA; D; No_Joining_Group
+1E927;ADLAM SMALL SINNYIIYHE; D; No_Joining_Group
+1E928;ADLAM SMALL PE; D; No_Joining_Group
+1E929;ADLAM SMALL BHE; D; No_Joining_Group
+1E92A;ADLAM SMALL RA; D; No_Joining_Group
+1E92B;ADLAM SMALL E; D; No_Joining_Group
+1E92C;ADLAM SMALL FA; D; No_Joining_Group
+1E92D;ADLAM SMALL I; D; No_Joining_Group
+1E92E;ADLAM SMALL O; D; No_Joining_Group
+1E92F;ADLAM SMALL DHA; D; No_Joining_Group
+1E930;ADLAM SMALL YHE; D; No_Joining_Group
+1E931;ADLAM SMALL WAW; D; No_Joining_Group
+1E932;ADLAM SMALL NUN; D; No_Joining_Group
+1E933;ADLAM SMALL KAF; D; No_Joining_Group
+1E934;ADLAM SMALL YA; D; No_Joining_Group
+1E935;ADLAM SMALL U; D; No_Joining_Group
+1E936;ADLAM SMALL JIIM; D; No_Joining_Group
+1E937;ADLAM SMALL CHI; D; No_Joining_Group
+1E938;ADLAM SMALL HA; D; No_Joining_Group
+1E939;ADLAM SMALL QAAF; D; No_Joining_Group
+1E93A;ADLAM SMALL GA; D; No_Joining_Group
+1E93B;ADLAM SMALL NYA; D; No_Joining_Group
+1E93C;ADLAM SMALL TU; D; No_Joining_Group
+1E93D;ADLAM SMALL NHA; D; No_Joining_Group
+1E93E;ADLAM SMALL VA; D; No_Joining_Group
+1E93F;ADLAM SMALL KHA; D; No_Joining_Group
+1E940;ADLAM SMALL GBE; D; No_Joining_Group
+1E941;ADLAM SMALL ZAL; D; No_Joining_Group
+1E942;ADLAM SMALL KPO; D; No_Joining_Group
+1E943;ADLAM SMALL SHA; D; No_Joining_Group
+
 # EOF

lib/unicore/ArabicShaping.txt

@@ -1,14 +1,17 @@
-# BidiBrackets-8.0.0.txt
-# Date: 2015-01-20, 19:00:00 GMT [AG, LI, KW]
+# BidiBrackets-9.0.0.txt
+# Date: 2016-06-07, 22:30:00 GMT [AG, LI, KW]
+# © 2016 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.
 #
-# Copyright (c) 1991-2015 Unicode, Inc.
-# For terms of use, see http://www.unicode.org/terms_of_use.html
-#
 # 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.
@@ -26,6 +29,12 @@
 # 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.

lib/unicore/BidiBrackets.txt

@@ -1,19 +1,21 @@
-# BidiMirroring-8.0.0.txt
-# Date: 2015-01-20, 18:30:00 GMT [KW, LI]
+# BidiMirroring-9.0.0.txt
+# Date: 2016-01-21, 22:00:00 GMT [KW, LI]
+# © 2016 Unicode®, Inc.
+# 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_Mirroring_Glyph Property
 # 
 # This file is an informative contributory data file in the
 # Unicode Character Database.
 #
-# Copyright (c) 1991-2015 Unicode, Inc.
-# For terms of use, see http://www.unicode.org/terms_of_use.html
-#
 # This data file lists characters that have the Bidi_Mirrored=Yes property
 # value, for which there is another Unicode character that typically has a glyph
 # that is the mirror image of the original character's glyph.
 #
-# The repertoire covered by the file is Unicode 8.0.0.
+# The repertoire covered by the file is Unicode 9.0.0.
 # 
 # The file contains a list of lines with mappings from one code point
 # to another one for character-based mirroring.

lib/unicore/BidiMirroring.txt

@@ -1,9 +1,9 @@
-# Blocks-8.0.0.txt
-# Date: 2014-11-10, 23:04:00 GMT [KW]
+# Blocks-9.0.0.txt
+# Date: 2016-02-05, 23:48:00 GMT [KW]
+# © 2016 Unicode®, Inc.
+# For terms of use, see http://www.unicode.org/terms_of_use.html
 #
 # Unicode Character Database
-# Copyright (c) 1991-2014 Unicode, Inc.
-# For terms of use, see http://www.unicode.org/terms_of_use.html
 # For documentation, see http://www.unicode.org/reports/tr44/
 #
 # Format:
@@ -93,6 +93,7 @@
 1BC0..1BFF; Batak
 1C00..1C4F; Lepcha
 1C50..1C7F; Ol Chiki
+1C80..1C8F; Cyrillic Extended-C
 1CC0..1CCF; Sundanese Supplement
 1CD0..1CFF; Vedic Extensions
 1D00..1D7F; Phonetic Extensions
@@ -209,6 +210,7 @@ FFF0..FFFF; Specials
 10400..1044F; Deseret
 10450..1047F; Shavian
 10480..104AF; Osmanya
+104B0..104FF; Osage
 10500..1052F; Elbasan
 10530..1056F; Caucasian Albanian
 10600..1077F; Linear A
@@ -243,13 +245,17 @@ FFF0..FFFF; Specials
 11280..112AF; Multani
 112B0..112FF; Khudawadi
 11300..1137F; Grantha
+11400..1147F; Newa
 11480..114DF; Tirhuta
 11580..115FF; Siddham
 11600..1165F; Modi
+11660..1167F; Mongolian Supplement
 11680..116CF; Takri
 11700..1173F; Ahom
 118A0..118FF; Warang Citi
 11AC0..11AFF; Pau Cin Hau
+11C00..11C6F; Bhaiksuki
+11C70..11CBF; Marchen
 12000..123FF; Cuneiform
 12400..1247F; Cuneiform Numbers and Punctuation
 12480..1254F; Early Dynastic Cuneiform
@@ -260,6 +266,9 @@ FFF0..FFFF; Specials
 16AD0..16AFF; Bassa Vah
 16B00..16B8F; Pahawh Hmong
 16F00..16F9F; Miao
+16FE0..16FFF; Ideographic Symbols and Punctuation
+17000..187FF; Tangut
+18800..18AFF; Tangut Components
 1B000..1B0FF; Kana Supplement
 1BC00..1BC9F; Duployan
 1BCA0..1BCAF; Shorthand Format Controls
@@ -270,7 +279,9 @@ FFF0..FFFF; Specials
 1D360..1D37F; Counting Rod Numerals
 1D400..1D7FF; Mathematical Alphanumeric Symbols
 1D800..1DAAF; Sutton SignWriting
+1E000..1E02F; Glagolitic Supplement
 1E800..1E8DF; Mende Kikakui
+1E900..1E95F; Adlam
 1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
 1F000..1F02F; Mahjong Tiles
 1F030..1F09F; Domino Tiles

lib/unicore/Blocks.txt

@@ -1,28 +1,30 @@
-# CJKRadicals-8.0.0.txt
-# Date: 2015-02-19, 00:30:00 GMT [RC, KW, LI]
+# CJKRadicals-9.0.0.txt
+# Date: 2016-01-22, 06:00:00 GMT [RC, KW, LI]
+# © 2016 Unicode®, Inc.
+# For terms of use, see http://www.unicode.org/terms_of_use.html
 #
 # Unicode Character Database
-# Copyright (c) 1991-2015 Unicode, Inc.
-# For terms of use, see http://www.unicode.org/terms_of_use.html
-# For documentation, see UAX #38: Unicode Han Database (Unihan),
-# at http://www.unicode.org/reports/tr38/
+# For documentation, see http://www.unicode.org/reports/tr44/
 #
-# Mapping from radical numbers to characters.
+# Mapping from CJK radical numbers to characters
 #
-# This data file provides a mapping from the radical numbers used
+# This data file provides a mapping from the CJK radical numbers used
 # in the kRSUnicode property to the corresponding character in
 # the Kangxi Radicals block or the CJK Radicals Supplement block,
 # as well as to a CJK unified ideograph which is formed from that
 # radical only.
 #
-# There is one line per radical number. Each line contains three
+# There is one line per CJK radical number. Each line contains three
 # fields, separated by a semicolon (';'). The first field is the
-# radical number. The second field is the CJK radical character.
+# CJK radical number. The second field is the CJK radical character.
 # The third field is the CJK unified ideograph.
 #
-# Radical numbers match the regular expression [1-9][0-9]{0,2}\'?
+# CJK radical numbers match the regular expression [1-9][0-9]{0,2}\'?
 # and in particular they can end with a U+0027 ' APOSTROPHE.
 #
+# For more information, see UAX #38: Unicode Han Database (Unihan),
+# at http://www.unicode.org/reports/tr38/
+#
 # This file was created for Unicode 5.2 by Richard Cook.
 # Updated for Unicode 6.0 by Richard Cook.
 # Updated for Unicode 6.1 and 6.2 by Ken Whistler,