unicode: Update to Unicode 6.2

git-svn-id: svn://vcs.exim.org/pcre/code/trunk@1050 2f5784b3-3f2a-0410-8824-cb99058d5e15

7 files changed, 40 insertions, 29 deletions

diff --git a/maint/GenerateUtt.py b/maint/GenerateUtt.py
index e8190ae..92adf47 100755
--- a/maint/GenerateUtt.py
+++ b/maint/GenerateUtt.py
@@ -16,6 +16,8 @@
 # Modified by PH 01-March-2010 to add new scripts for Unicode 5.2.0.
 # Modified by PH 04-May-2010 to add new "X.." special categories.
 # Modified by PH 30-April-2011 to add new scripts for Unicode 6.0.0
+# Modified by ChPe 30-September-2012 to add this note; no other changes were
+# necessary for Unicode 6.2.0 support.
 
 script_names = ['Arabic', 'Armenian', 'Bengali', 'Bopomofo', 'Braille', 'Buginese', 'Buhid', 'Canadian_Aboriginal', \
  'Cherokee', 'Common', 'Coptic', 'Cypriot', 'Cyrillic', 'Deseret', 'Devanagari', 'Ethiopic', 'Georgian', \
@@ -101,6 +103,6 @@ for utt in utt_table:
 		value = 'ucp_' + utt[0]
 	if utt == utt_table[-1]:
 		last = ''
-	print '  { %3d, %s, %s }%s ' % (offset, utt[1], value, last)
+	print '  { %3d, %s, %s }%s' % (offset, utt[1], value, last)
 	offset += len(utt[0]) + 1
 print '};'
diff --git a/maint/MultiStage2.py b/maint/MultiStage2.py
index 1c5fce7..ed68f23 100755
--- a/maint/MultiStage2.py
+++ b/maint/MultiStage2.py
@@ -107,6 +107,7 @@
 #                      not much bigger than before.
 # 18-September-2012: Added code for multiple caseless sets. This uses the
 #                      final hole in the structure.
+# 30-September-2012: Added RegionalIndicator break property from Unicode 6.2.0
 ##############################################################################
 
 
@@ -304,8 +305,8 @@ category_names = ['Cc', 'Cf', 'Cn', 'Co', 'Cs', 'Ll', 'Lm', 'Lo', 'Lt', 'Lu',
   'Mc', 'Me', 'Mn', 'Nd', 'Nl', 'No', 'Pc', 'Pd', 'Pe', 'Pf', 'Pi', 'Po', 'Ps',
   'Sc', 'Sk', 'Sm', 'So', 'Zl', 'Zp', 'Zs' ]
 
-break_property_names = ['CR', 'LF', 'Control', 'Extend', 'Prepend', 
-  'SpacingMark', 'L', 'V', 'T', 'LV', 'LVT', 'Other' ]
+break_property_names = ['CR', 'LF', 'Control', 'Extend', 'Prepend',
+  'SpacingMark', 'L', 'V', 'T', 'LV', 'LVT', 'Regional_Indicator', 'Other' ]
 
 test_record_size()
 
diff --git a/maint/Unicode.tables/CaseFolding.txt b/maint/Unicode.tables/CaseFolding.txt
index 0d9a409..df1813d 100644
--- a/maint/Unicode.tables/CaseFolding.txt
+++ b/maint/Unicode.tables/CaseFolding.txt
@@ -1,8 +1,8 @@
-# CaseFolding-6.1.0.txt
-# Date: 2011-07-25, 21:21:56 GMT [MD]
+# CaseFolding-6.2.0.txt
+# Date: 2012-08-14, 17:54:49 GMT [MD]
 #
 # Unicode Character Database
-# Copyright (c) 1991-2011 Unicode, Inc.
+# Copyright (c) 1991-2012 Unicode, Inc.
 # For terms of use, see http://www.unicode.org/terms_of_use.html
 # For documentation, see http://www.unicode.org/reports/tr44/
 #
@@ -1222,3 +1222,5 @@ FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z
 10425; C; 1044D; # DESERET CAPITAL LETTER ENG
 10426; C; 1044E; # DESERET CAPITAL LETTER OI
 10427; C; 1044F; # DESERET CAPITAL LETTER EW
+#
+# EOF
diff --git a/maint/Unicode.tables/DerivedGeneralCategory.txt b/maint/Unicode.tables/DerivedGeneralCategory.txt
index 12a346f..546a677 100644
--- a/maint/Unicode.tables/DerivedGeneralCategory.txt
+++ b/maint/Unicode.tables/DerivedGeneralCategory.txt
@@ -1,8 +1,8 @@
-# DerivedGeneralCategory-6.1.0.txt
-# Date: 2011-11-27, 05:10:22 GMT [MD]
+# DerivedGeneralCategory-6.2.0.txt
+# Date: 2012-05-20, 00:42:34 GMT [MD]
 #
 # Unicode Character Database
-# Copyright (c) 1991-2011 Unicode, Inc.
+# Copyright (c) 1991-2012 Unicode, Inc.
 # For terms of use, see http://www.unicode.org/terms_of_use.html
 # For documentation, see http://www.unicode.org/reports/tr44/
 
@@ -275,7 +275,7 @@
 2072..2073    ; Cn #   [2] <reserved-2072>..<reserved-2073>
 208F          ; Cn #       <reserved-208F>
 209D..209F    ; Cn #   [3] <reserved-209D>..<reserved-209F>
-20BA..20CF    ; Cn #  [22] <reserved-20BA>..<reserved-20CF>
+20BB..20CF    ; Cn #  [21] <reserved-20BB>..<reserved-20CF>
 20F1..20FF    ; Cn #  [15] <reserved-20F1>..<reserved-20FF>
 218A..218F    ; Cn #   [6] <reserved-218A>..<reserved-218F>
 23F4..23FF    ; Cn #  [12] <reserved-23F4>..<reserved-23FF>
@@ -554,7 +554,7 @@ E01F0..EFFFF  ; Cn # [65040] <reserved-E01F0>..<noncharacter-EFFFF>
 FFFFE..FFFFF  ; Cn #   [2] <noncharacter-FFFFE>..<noncharacter-FFFFF>
 10FFFE..10FFFF; Cn #   [2] <noncharacter-10FFFE>..<noncharacter-10FFFF>
 
-# Total code points: 864415
+# Total code points: 864414
 
 # ================================================
 
@@ -3230,7 +3230,7 @@ FFE9..FFEC    ; Sm #   [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS ARROW
 0BF9          ; Sc #       TAMIL RUPEE SIGN
 0E3F          ; Sc #       THAI CURRENCY SYMBOL BAHT
 17DB          ; Sc #       KHMER CURRENCY SYMBOL RIEL
-20A0..20B9    ; Sc #  [26] EURO-CURRENCY SIGN..INDIAN RUPEE SIGN
+20A0..20BA    ; Sc #  [27] EURO-CURRENCY SIGN..TURKISH LIRA SIGN
 A838          ; Sc #       NORTH INDIC RUPEE MARK
 FDFC          ; Sc #       RIAL SIGN
 FE69          ; Sc #       SMALL DOLLAR SIGN
@@ -3238,7 +3238,7 @@ FF04          ; Sc #       FULLWIDTH DOLLAR SIGN
 FFE0..FFE1    ; Sc #   [2] FULLWIDTH CENT SIGN..FULLWIDTH POUND SIGN
 FFE5..FFE6    ; Sc #   [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN
 
-# Total code points: 48
+# Total code points: 49
 
 # ================================================
 
diff --git a/maint/Unicode.tables/GraphemeBreakProperty.txt b/maint/Unicode.tables/GraphemeBreakProperty.txt
index d3f480d..948faa9 100644
--- a/maint/Unicode.tables/GraphemeBreakProperty.txt
+++ b/maint/Unicode.tables/GraphemeBreakProperty.txt
@@ -1,8 +1,8 @@
-# GraphemeBreakProperty-6.1.0.txt
-# Date: 2011-12-05, 16:44:15 GMT [MD]
+# GraphemeBreakProperty-6.2.0.txt
+# Date: 2012-08-13, 19:12:02 GMT [MD]
 #
 # Unicode Character Database
-# Copyright (c) 1991-2011 Unicode, Inc.
+# Copyright (c) 1991-2012 Unicode, Inc.
 # For terms of use, see http://www.unicode.org/terms_of_use.html
 # For documentation, see http://www.unicode.org/reports/tr44/
 
@@ -308,6 +308,12 @@ E0100..E01EF  ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 
 # ================================================
 
+1F1E6..1F1FF  ; Regional_Indicator # So  [26] REGIONAL INDICATOR SYMBOL LETTER A..REGIONAL INDICATOR SYMBOL LETTER Z
+
+# Total code points: 26
+
+# ================================================
+
 0903          ; SpacingMark # Mc       DEVANAGARI SIGN VISARGA
 093B          ; SpacingMark # Mc       DEVANAGARI VOWEL SIGN OOE
 093E..0940    ; SpacingMark # Mc   [3] DEVANAGARI VOWEL SIGN AA..DEVANAGARI VOWEL SIGN II
diff --git a/maint/Unicode.tables/Scripts.txt b/maint/Unicode.tables/Scripts.txt
index 2516f88..1a8e722 100644
--- a/maint/Unicode.tables/Scripts.txt
+++ b/maint/Unicode.tables/Scripts.txt
@@ -1,8 +1,8 @@
-# Scripts-6.1.0.txt
-# Date: 2011-11-27, 05:10:50 GMT [MD]
+# Scripts-6.2.0.txt
+# Date: 2012-06-04, 17:21:29 GMT [MD]
 #
 # Unicode Character Database
-# Copyright (c) 1991-2011 Unicode, Inc.
+# Copyright (c) 1991-2012 Unicode, Inc.
 # For terms of use, see http://www.unicode.org/terms_of_use.html
 # For documentation, see http://www.unicode.org/reports/tr44/
 
@@ -146,7 +146,7 @@
 208A..208C    ; Common # Sm   [3] SUBSCRIPT PLUS SIGN..SUBSCRIPT EQUALS SIGN
 208D          ; Common # Ps       SUBSCRIPT LEFT PARENTHESIS
 208E          ; Common # Pe       SUBSCRIPT RIGHT PARENTHESIS
-20A0..20B9    ; Common # Sc  [26] EURO-CURRENCY SIGN..INDIAN RUPEE SIGN
+20A0..20BA    ; Common # Sc  [27] EURO-CURRENCY SIGN..TURKISH LIRA SIGN
 2100..2101    ; Common # So   [2] ACCOUNT OF..ADDRESSED TO THE SUBJECT
 2102          ; Common # L&       DOUBLE-STRUCK CAPITAL C
 2103..2106    ; Common # So   [4] DEGREE CELSIUS..CADA UNA
@@ -576,7 +576,7 @@ FFFC..FFFD    ; Common # So   [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR
 E0001         ; Common # Cf       LANGUAGE TAG
 E0020..E007F  ; Common # Cf  [96] TAG SPACE..CANCEL TAG
 
-# Total code points: 6412
+# Total code points: 6413
 
 # ================================================
 
@@ -760,7 +760,7 @@ FB46..FB4F    ; Hebrew # Lo  [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU
 061E          ; Arabic # Po       ARABIC TRIPLE DOT PUNCTUATION MARK
 0620..063F    ; Arabic # Lo  [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE
 0641..064A    ; Arabic # Lo  [10] ARABIC LETTER FEH..ARABIC LETTER YEH
-0656..065E    ; Arabic # Mn   [9] ARABIC SUBSCRIPT ALEF..ARABIC FATHA WITH TWO DOTS
+0656..065F    ; Arabic # Mn  [10] ARABIC SUBSCRIPT ALEF..ARABIC WAVY HAMZA BELOW
 066A..066D    ; Arabic # Po   [4] ARABIC PERCENT SIGN..ARABIC FIVE POINTED STAR
 066E..066F    ; Arabic # Lo   [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF
 0671..06D3    ; Arabic # Lo  [99] ARABIC LETTER ALEF WASLA..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE
@@ -827,7 +827,7 @@ FE76..FEFC    ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA
 1EEAB..1EEBB  ; Arabic # Lo  [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
 1EEF0..1EEF1  ; Arabic # Sm   [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL
 
-# Total code points: 1234
+# Total code points: 1235
 
 # ================================================
 
@@ -1477,7 +1477,6 @@ A490..A4C6    ; Yi # So  [55] YI RADICAL QOT..YI RADICAL KE
 0300..036F    ; Inherited # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X
 0485..0486    ; Inherited # Mn   [2] COMBINING CYRILLIC DASIA PNEUMATA..COMBINING CYRILLIC PSILI PNEUMATA
 064B..0655    ; Inherited # Mn  [11] ARABIC FATHATAN..ARABIC HAMZA BELOW
-065F          ; Inherited # Mn       ARABIC WAVY HAMZA BELOW
 0670          ; Inherited # Mn       ARABIC LETTER SUPERSCRIPT ALEF
 0951..0952    ; Inherited # Mn   [2] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI STRESS SIGN ANUDATTA
 1CD0..1CD2    ; Inherited # Mn   [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA
@@ -1504,7 +1503,7 @@ FE20..FE26    ; Inherited # Mn   [7] COMBINING LIGATURE LEFT HALF..COMBINING CON
 1D1AA..1D1AD  ; Inherited # Mn   [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
 E0100..E01EF  ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 
-# Total code points: 524
+# Total code points: 523
 
 # ================================================
 
diff --git a/maint/Unicode.tables/UnicodeData.txt b/maint/Unicode.tables/UnicodeData.txt
index 9f20405..086379e 100644
--- a/maint/Unicode.tables/UnicodeData.txt
+++ b/maint/Unicode.tables/UnicodeData.txt
@@ -7190,6 +7190,7 @@
 20B7;SPESMILO SIGN;Sc;0;ET;;;;;N;;;;;
 20B8;TENGE SIGN;Sc;0;ET;;;;;N;;;;;
 20B9;INDIAN RUPEE SIGN;Sc;0;ET;;;;;N;;;;;
+20BA;TURKISH LIRA SIGN;Sc;0;ET;;;;;N;;;;;
 20D0;COMBINING LEFT HARPOON ABOVE;Mn;230;NSM;;;;;N;NON-SPACING LEFT HARPOON ABOVE;;;;
 20D1;COMBINING RIGHT HARPOON ABOVE;Mn;230;NSM;;;;;N;NON-SPACING RIGHT HARPOON ABOVE;;;;
 20D2;COMBINING LONG VERTICAL LINE OVERLAY;Mn;1;NSM;;;;;N;NON-SPACING LONG VERTICAL BAR OVERLAY;;;;
@@ -18703,8 +18704,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
 1242F;CUNEIFORM NUMERIC SIGN THREE SHARU VARIANT FORM;Nl;0;L;;;;3;N;;;;;
 12430;CUNEIFORM NUMERIC SIGN FOUR SHARU;Nl;0;L;;;;4;N;;;;;
 12431;CUNEIFORM NUMERIC SIGN FIVE SHARU;Nl;0;L;;;;5;N;;;;;
-12432;CUNEIFORM NUMERIC SIGN SHAR2 TIMES GAL PLUS DISH;Nl;0;L;;;;;N;;;;;
-12433;CUNEIFORM NUMERIC SIGN SHAR2 TIMES GAL PLUS MIN;Nl;0;L;;;;;N;;;;;
+12432;CUNEIFORM NUMERIC SIGN SHAR2 TIMES GAL PLUS DISH;Nl;0;L;;;;216000;N;;;;;
+12433;CUNEIFORM NUMERIC SIGN SHAR2 TIMES GAL PLUS MIN;Nl;0;L;;;;432000;N;;;;;
 12434;CUNEIFORM NUMERIC SIGN ONE BURU;Nl;0;L;;;;1;N;;;;;
 12435;CUNEIFORM NUMERIC SIGN TWO BURU;Nl;0;L;;;;2;N;;;;;
 12436;CUNEIFORM NUMERIC SIGN THREE BURU;Nl;0;L;;;;3;N;;;;;
@@ -18739,8 +18740,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
 12453;CUNEIFORM NUMERIC SIGN FOUR BAN2 VARIANT FORM;Nl;0;L;;;;4;N;;;;;
 12454;CUNEIFORM NUMERIC SIGN FIVE BAN2;Nl;0;L;;;;5;N;;;;;
 12455;CUNEIFORM NUMERIC SIGN FIVE BAN2 VARIANT FORM;Nl;0;L;;;;5;N;;;;;
-12456;CUNEIFORM NUMERIC SIGN NIGIDAMIN;Nl;0;L;;;;;N;;;;;
-12457;CUNEIFORM NUMERIC SIGN NIGIDAESH;Nl;0;L;;;;;N;;;;;
+12456;CUNEIFORM NUMERIC SIGN NIGIDAMIN;Nl;0;L;;;;-1;N;;;;;
+12457;CUNEIFORM NUMERIC SIGN NIGIDAESH;Nl;0;L;;;;-1;N;;;;;
 12458;CUNEIFORM NUMERIC SIGN ONE ESHE3;Nl;0;L;;;;1;N;;;;;
 12459;CUNEIFORM NUMERIC SIGN TWO ESHE3;Nl;0;L;;;;2;N;;;;;
 1245A;CUNEIFORM NUMERIC SIGN ONE THIRD DISH;Nl;0;L;;;;1/3;N;;;;;