aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorAlexandre Oliva <aoliva@redhat.com>2015-02-20 20:14:59 -0200
committerAlexandre Oliva <aoliva@redhat.com>2015-02-20 20:14:59 -0200
commit4a4839c94a4c93ffc0d5b95c69a08b02a57007f2 (patch)
treed60950243872d9beb0993b12173e6bbf998d779d
parente4a399dc3dbb3228eb39af230ad11bc42a018c93 (diff)
downloadglibc-4a4839c94a4c93ffc0d5b95c69a08b02a57007f2.tar.xz
glibc-4a4839c94a4c93ffc0d5b95c69a08b02a57007f2.zip
Unicode 7.0.0 update; added generator scripts.
for localedata/ChangeLog [BZ #17588] [BZ #13064] [BZ #14094] [BZ #17998] * unicode-gen/Makefile: New. * unicode-gen/unicode-license.txt: New, from Unicode. * unicode-gen/UnicodeData.txt: New, from Unicode. * unicode-gen/DerivedCoreProperties.txt: New, from Unicode. * unicode-gen/EastAsianWidth.txt: New, from Unicode. * unicode-gen/gen_unicode_ctype.py: New generator, from Mike FABIAN <mfabian@redhat.com>. * unicode-gen/ctype_compatibility.py: New verifier, from Pravin Satpute <psatpute@redhat.com> and Mike FABIAN. * unicode-gen/ctype_compatibility_test_cases.py: New verifier module, from Mike FABIAN. * unicode-gen/utf8_gen.py: New generator, from Pravin Satpute and Mike FABIAN. * unicode-gen/utf8_compatibility.py: New verifier, from Pravin Satpute and Mike FABIAN. * charmaps/UTF-8: Update. * locales/i18n: Update. * gen-unicode-ctype.c: Remove. * tst-ctype-de_DE.ISO-8859-1.in: Adjust, islower now returns true for ordinal indicators.
-rw-r--r--NEWS11
-rw-r--r--localedata/ChangeLog27
-rw-r--r--localedata/charmaps/UTF-811946
-rw-r--r--localedata/gen-unicode-ctype.c784
-rw-r--r--localedata/locales/i18n2652
-rw-r--r--localedata/tst-ctype-de_DE.ISO-8859-1.in2
-rw-r--r--localedata/unicode-gen/DerivedCoreProperties.txt10794
-rw-r--r--localedata/unicode-gen/EastAsianWidth.txt2121
-rw-r--r--localedata/unicode-gen/Makefile99
-rw-r--r--localedata/unicode-gen/UnicodeData.txt27268
-rwxr-xr-xlocaledata/unicode-gen/ctype_compatibility.py546
-rw-r--r--localedata/unicode-gen/ctype_compatibility_test_cases.py951
-rwxr-xr-xlocaledata/unicode-gen/gen_unicode_ctype.py751
-rw-r--r--localedata/unicode-gen/unicode-license.txt50
-rwxr-xr-xlocaledata/unicode-gen/utf8_compatibility.py399
-rwxr-xr-xlocaledata/unicode-gen/utf8_gen.py286
16 files changed, 53305 insertions, 5382 deletions
diff --git a/NEWS b/NEWS
index 8d2c51bc10..5eb79d2802 100644
--- a/NEWS
+++ b/NEWS
@@ -9,8 +9,15 @@ Version 2.22
* The following bugs are resolved with this release:
- 4719, 15319, 15467, 15790, 16560, 17569, 17792, 17912, 17932, 17944,
- 17949, 17964, 17965, 17967, 17969, 17978, 17987, 17991, 17996, 17999.
+ 4719, 13064, 14094, 15319, 15467, 15790, 16560, 17569, 17588, 17792,
+ 17912, 17932, 17944, 17949, 17964, 17965, 17967, 17969, 17978, 17987,
+ 17991, 17996, 17998, 17999.
+
+* Character encoding and ctype tables were updated to Unicode 7.0.0, using
+ new generator scripts contributed by Pravin Satpute and Mike FABIAN (Red
+ Hat). These updates cause user visible changes, such as the fix for bug
+ 17998.
+
Version 2.21
diff --git a/localedata/ChangeLog b/localedata/ChangeLog
index 9c2c2c8a32..58063e0bbd 100644
--- a/localedata/ChangeLog
+++ b/localedata/ChangeLog
@@ -1,3 +1,30 @@
+2015-02-20 Alexandre Oliva <aoliva@redhat.com>
+
+ [BZ #17588]
+ [BZ #13064]
+ [BZ #14094]
+ [BZ #17998]
+ * unicode-gen/Makefile: New.
+ * unicode-gen/unicode-license.txt: New, from Unicode.
+ * unicode-gen/UnicodeData.txt: New, from Unicode.
+ * unicode-gen/DerivedCoreProperties.txt: New, from Unicode.
+ * unicode-gen/EastAsianWidth.txt: New, from Unicode.
+ * unicode-gen/gen_unicode_ctype.py: New generator, from Mike
+ FABIAN <mfabian@redhat.com>.
+ * unicode-gen/ctype_compatibility.py: New verifier, from
+ Pravin Satpute <psatpute@redhat.com> and Mike FABIAN.
+ * unicode-gen/ctype_compatibility_test_cases.py: New verifier
+ module, from Mike FABIAN.
+ * unicode-gen/utf8_gen.py: New generator, from Pravin Satpute
+ and Mike FABIAN.
+ * unicode-gen/utf8_compatibility.py: New verifier, from Pravin
+ Satpute and Mike FABIAN.
+ * charmaps/UTF-8: Update.
+ * locales/i18n: Update.
+ * gen-unicode-ctype.c: Remove.
+ * tst-ctype-de_DE.ISO-8859-1.in: Adjust, islower now returns
+ true for ordinal indicators.
+
2015-01-21 Marek Polacek <polacek@redhat.com>
* tests-mbwc/tst_wcscpy.c (tst_wcscpy): Fix condition.
diff --git a/localedata/charmaps/UTF-8 b/localedata/charmaps/UTF-8
index f9fad114ee..1f33c5512f 100644
--- a/localedata/charmaps/UTF-8
+++ b/localedata/charmaps/UTF-8
@@ -4,6 +4,7 @@
<mb_cur_min> 1
<mb_cur_max> 6
+% CHARMAP generated using utf8_gen.py
% alias ISO-10646/UTF-8
CHARMAP
<U0000> /x00 NULL
@@ -15,11 +16,11 @@ CHARMAP
<U0006> /x06 ACKNOWLEDGE
<U0007> /x07 BELL
<U0008> /x08 BACKSPACE
-<U0009> /x09 HORIZONTAL TABULATION
-<U000A> /x0a LINE FEED
-<U000B> /x0b VERTICAL TABULATION
-<U000C> /x0c FORM FEED
-<U000D> /x0d CARRIAGE RETURN
+<U0009> /x09 CHARACTER TABULATION
+<U000A> /x0a LINE FEED (LF)
+<U000B> /x0b LINE TABULATION
+<U000C> /x0c FORM FEED (FF)
+<U000D> /x0d CARRIAGE RETURN (CR)
<U000E> /x0e SHIFT OUT
<U000F> /x0f SHIFT IN
<U0010> /x10 DATA LINK ESCAPE
@@ -34,10 +35,10 @@ CHARMAP
<U0019> /x19 END OF MEDIUM
<U001A> /x1a SUBSTITUTE
<U001B> /x1b ESCAPE
-<U001C> /x1c FILE SEPARATOR
-<U001D> /x1d GROUP SEPARATOR
-<U001E> /x1e RECORD SEPARATOR
-<U001F> /x1f UNIT SEPARATOR
+<U001C> /x1c INFORMATION SEPARATOR FOUR
+<U001D> /x1d INFORMATION SEPARATOR THREE
+<U001E> /x1e INFORMATION SEPARATOR TWO
+<U001F> /x1f INFORMATION SEPARATOR ONE
<U0020> /x20 SPACE
<U0021> /x21 EXCLAMATION MARK
<U0022> /x22 QUOTATION MARK
@@ -134,38 +135,38 @@ CHARMAP
<U007D> /x7d RIGHT CURLY BRACKET
<U007E> /x7e TILDE
<U007F> /x7f DELETE
-<U0080> /xc2/x80 PADDING CHARACTER (PAD)
-<U0081> /xc2/x81 HIGH OCTET PRESET (HOP)
-<U0082> /xc2/x82 BREAK PERMITTED HERE (BPH)
-<U0083> /xc2/x83 NO BREAK HERE (NBH)
-<U0084> /xc2/x84 INDEX (IND)
+<U0080> /xc2/x80 <control>
+<U0081> /xc2/x81 <control>
+<U0082> /xc2/x82 BREAK PERMITTED HERE
+<U0083> /xc2/x83 NO BREAK HERE
+<U0084> /xc2/x84 <control>
<U0085> /xc2/x85 NEXT LINE (NEL)
-<U0086> /xc2/x86 START OF SELECTED AREA (SSA)
-<U0087> /xc2/x87 END OF SELECTED AREA (ESA)
-<U0088> /xc2/x88 CHARACTER TABULATION SET (HTS)
-<U0089> /xc2/x89 CHARACTER TABULATION WITH JUSTIFICATION (HTJ)
-<U008A> /xc2/x8a LINE TABULATION SET (VTS)
-<U008B> /xc2/x8b PARTIAL LINE FORWARD (PLD)
-<U008C> /xc2/x8c PARTIAL LINE BACKWARD (PLU)
-<U008D> /xc2/x8d REVERSE LINE FEED (RI)
-<U008E> /xc2/x8e SINGLE-SHIFT TWO (SS2)
-<U008F> /xc2/x8f SINGLE-SHIFT THREE (SS3)
-<U0090> /xc2/x90 DEVICE CONTROL STRING (DCS)
-<U0091> /xc2/x91 PRIVATE USE ONE (PU1)
-<U0092> /xc2/x92 PRIVATE USE TWO (PU2)
-<U0093> /xc2/x93 SET TRANSMIT STATE (STS)
-<U0094> /xc2/x94 CANCEL CHARACTER (CCH)
-<U0095> /xc2/x95 MESSAGE WAITING (MW)
-<U0096> /xc2/x96 START OF GUARDED AREA (SPA)
-<U0097> /xc2/x97 END OF GUARDED AREA (EPA)
-<U0098> /xc2/x98 START OF STRING (SOS)
-<U0099> /xc2/x99 SINGLE GRAPHIC CHARACTER INTRODUCER (SGCI)
-<U009A> /xc2/x9a SINGLE CHARACTER INTRODUCER (SCI)
-<U009B> /xc2/x9b CONTROL SEQUENCE INTRODUCER (CSI)
-<U009C> /xc2/x9c STRING TERMINATOR (ST)
-<U009D> /xc2/x9d OPERATING SYSTEM COMMAND (OSC)
-<U009E> /xc2/x9e PRIVACY MESSAGE (PM)
-<U009F> /xc2/x9f APPLICATION PROGRAM COMMAND (APC)
+<U0086> /xc2/x86 START OF SELECTED AREA
+<U0087> /xc2/x87 END OF SELECTED AREA
+<U0088> /xc2/x88 CHARACTER TABULATION SET
+<U0089> /xc2/x89 CHARACTER TABULATION WITH JUSTIFICATION
+<U008A> /xc2/x8a LINE TABULATION SET
+<U008B> /xc2/x8b PARTIAL LINE FORWARD
+<U008C> /xc2/x8c PARTIAL LINE BACKWARD
+<U008D> /xc2/x8d REVERSE LINE FEED
+<U008E> /xc2/x8e SINGLE SHIFT TWO
+<U008F> /xc2/x8f SINGLE SHIFT THREE
+<U0090> /xc2/x90 DEVICE CONTROL STRING
+<U0091> /xc2/x91 PRIVATE USE ONE
+<U0092> /xc2/x92 PRIVATE USE TWO
+<U0093> /xc2/x93 SET TRANSMIT STATE
+<U0094> /xc2/x94 CANCEL CHARACTER
+<U0095> /xc2/x95 MESSAGE WAITING
+<U0096> /xc2/x96 START OF GUARDED AREA
+<U0097> /xc2/x97 END OF GUARDED AREA
+<U0098> /xc2/x98 START OF STRING
+<U0099> /xc2/x99 <control>
+<U009A> /xc2/x9a SINGLE CHARACTER INTRODUCER
+<U009B> /xc2/x9b CONTROL SEQUENCE INTRODUCER
+<U009C> /xc2/x9c STRING TERMINATOR
+<U009D> /xc2/x9d OPERATING SYSTEM COMMAND
+<U009E> /xc2/x9e PRIVACY MESSAGE
+<U009F> /xc2/x9f APPLICATION PROGRAM COMMAND
<U00A0> /xc2/xa0 NO-BREAK SPACE
<U00A1> /xc2/xa1 INVERTED EXCLAMATION MARK
<U00A2> /xc2/xa2 CENT SIGN
@@ -899,6 +900,7 @@ CHARMAP
<U037C> /xcd/xbc GREEK SMALL DOTTED LUNATE SIGMA SYMBOL
<U037D> /xcd/xbd GREEK SMALL REVERSED DOTTED LUNATE SIGMA SYMBOL
<U037E> /xcd/xbe GREEK QUESTION MARK
+<U037F> /xcd/xbf GREEK CAPITAL LETTER YOT
<U0384> /xce/x84 GREEK TONOS
<U0385> /xce/x85 GREEK DIALYTIKA TONOS
<U0386> /xce/x86 GREEK CAPITAL LETTER ALPHA WITH TONOS
@@ -1316,6 +1318,14 @@ CHARMAP
<U0525> /xd4/xa5 CYRILLIC SMALL LETTER PE WITH DESCENDER
<U0526> /xd4/xa6 CYRILLIC CAPITAL LETTER SHHA WITH DESCENDER
<U0527> /xd4/xa7 CYRILLIC SMALL LETTER SHHA WITH DESCENDER
+<U0528> /xd4/xa8 CYRILLIC CAPITAL LETTER EN WITH LEFT HOOK
+<U0529> /xd4/xa9 CYRILLIC SMALL LETTER EN WITH LEFT HOOK
+<U052A> /xd4/xaa CYRILLIC CAPITAL LETTER DZZHE
+<U052B> /xd4/xab CYRILLIC SMALL LETTER DZZHE
+<U052C> /xd4/xac CYRILLIC CAPITAL LETTER DCHE
+<U052D> /xd4/xad CYRILLIC SMALL LETTER DCHE
+<U052E> /xd4/xae CYRILLIC CAPITAL LETTER EL WITH DESCENDER
+<U052F> /xd4/xaf CYRILLIC SMALL LETTER EL WITH DESCENDER
<U0531> /xd4/xb1 ARMENIAN CAPITAL LETTER AYB
<U0532> /xd4/xb2 ARMENIAN CAPITAL LETTER BEN
<U0533> /xd4/xb3 ARMENIAN CAPITAL LETTER GIM
@@ -1402,6 +1412,9 @@ CHARMAP
<U0587> /xd6/x87 ARMENIAN SMALL LIGATURE ECH YIWN
<U0589> /xd6/x89 ARMENIAN FULL STOP
<U058A> /xd6/x8a ARMENIAN HYPHEN
+<U058D> /xd6/x8d RIGHT-FACING ARMENIAN ETERNITY SIGN
+<U058E> /xd6/x8e LEFT-FACING ARMENIAN ETERNITY SIGN
+<U058F> /xd6/x8f ARMENIAN DRAM SIGN
<U0591> /xd6/x91 HEBREW ACCENT ETNAHTA
<U0592> /xd6/x92 HEBREW ACCENT SEGOL
<U0593> /xd6/x93 HEBREW ACCENT SHALSHELET
@@ -1493,6 +1506,8 @@ CHARMAP
<U0601> /xd8/x81 ARABIC SIGN SANAH
<U0602> /xd8/x82 ARABIC FOOTNOTE MARKER
<U0603> /xd8/x83 ARABIC SIGN SAFHA
+<U0604> /xd8/x84 ARABIC SIGN SAMVAT
+<U0605> /xd8/x85 ARABIC NUMBER MARK ABOVE
<U0606> /xd8/x86 ARABIC-INDIC CUBE ROOT
<U0607> /xd8/x87 ARABIC-INDIC FOURTH ROOT
<U0608> /xd8/x88 ARABIC RAY
@@ -1515,6 +1530,7 @@ CHARMAP
<U0619> /xd8/x99 ARABIC SMALL DAMMA
<U061A> /xd8/x9a ARABIC SMALL KASRA
<U061B> /xd8/x9b ARABIC SEMICOLON
+<U061C> /xd8/x9c ARABIC LETTER MARK
<U061E> /xd8/x9e ARABIC TRIPLE DOT PUNCTUATION MARK
<U061F> /xd8/x9f ARABIC QUESTION MARK
<U0620> /xd8/xa0 ARABIC LETTER KASHMIRI YEH
@@ -2065,6 +2081,53 @@ CHARMAP
<U085A> /xe0/xa1/x9a MANDAIC VOCALIZATION MARK
<U085B> /xe0/xa1/x9b MANDAIC GEMINATION MARK
<U085E> /xe0/xa1/x9e MANDAIC PUNCTUATION
+<U08A0> /xe0/xa2/xa0 ARABIC LETTER BEH WITH SMALL V BELOW
+<U08A1> /xe0/xa2/xa1 ARABIC LETTER BEH WITH HAMZA ABOVE
+<U08A2> /xe0/xa2/xa2 ARABIC LETTER JEEM WITH TWO DOTS ABOVE
+<U08A3> /xe0/xa2/xa3 ARABIC LETTER TAH WITH TWO DOTS ABOVE
+<U08A4> /xe0/xa2/xa4 ARABIC LETTER FEH WITH DOT BELOW AND THREE DOTS ABOVE
+<U08A5> /xe0/xa2/xa5 ARABIC LETTER QAF WITH DOT BELOW
+<U08A6> /xe0/xa2/xa6 ARABIC LETTER LAM WITH DOUBLE BAR
+<U08A7> /xe0/xa2/xa7 ARABIC LETTER MEEM WITH THREE DOTS ABOVE
+<U08A8> /xe0/xa2/xa8 ARABIC LETTER YEH WITH TWO DOTS BELOW AND HAMZA ABOVE
+<U08A9> /xe0/xa2/xa9 ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE
+<U08AA> /xe0/xa2/xaa ARABIC LETTER REH WITH LOOP
+<U08AB> /xe0/xa2/xab ARABIC LETTER WAW WITH DOT WITHIN
+<U08AC> /xe0/xa2/xac ARABIC LETTER ROHINGYA YEH
+<U08AD> /xe0/xa2/xad ARABIC LETTER LOW ALEF
+<U08AE> /xe0/xa2/xae ARABIC LETTER DAL WITH THREE DOTS BELOW
+<U08AF> /xe0/xa2/xaf ARABIC LETTER SAD WITH THREE DOTS BELOW
+<U08B0> /xe0/xa2/xb0 ARABIC LETTER GAF WITH INVERTED STROKE
+<U08B1> /xe0/xa2/xb1 ARABIC LETTER STRAIGHT WAW
+<U08B2> /xe0/xa2/xb2 ARABIC LETTER ZAIN WITH INVERTED V ABOVE
+<U08E4> /xe0/xa3/xa4 ARABIC CURLY FATHA
+<U08E5> /xe0/xa3/xa5 ARABIC CURLY DAMMA
+<U08E6> /xe0/xa3/xa6 ARABIC CURLY KASRA
+<U08E7> /xe0/xa3/xa7 ARABIC CURLY FATHATAN
+<U08E8> /xe0/xa3/xa8 ARABIC CURLY DAMMATAN
+<U08E9> /xe0/xa3/xa9 ARABIC CURLY KASRATAN
+<U08EA> /xe0/xa3/xaa ARABIC TONE ONE DOT ABOVE
+<U08EB> /xe0/xa3/xab ARABIC TONE TWO DOTS ABOVE
+<U08EC> /xe0/xa3/xac ARABIC TONE LOOP ABOVE
+<U08ED> /xe0/xa3/xad ARABIC TONE ONE DOT BELOW
+<U08EE> /xe0/xa3/xae ARABIC TONE TWO DOTS BELOW
+<U08EF> /xe0/xa3/xaf ARABIC TONE LOOP BELOW
+<U08F0> /xe0/xa3/xb0 ARABIC OPEN FATHATAN
+<U08F1> /xe0/xa3/xb1 ARABIC OPEN DAMMATAN
+<U08F2> /xe0/xa3/xb2 ARABIC OPEN KASRATAN
+<U08F3> /xe0/xa3/xb3 ARABIC SMALL HIGH WAW
+<U08F4> /xe0/xa3/xb4 ARABIC FATHA WITH RING
+<U08F5> /xe0/xa3/xb5 ARABIC FATHA WITH DOT ABOVE
+<U08F6> /xe0/xa3/xb6 ARABIC KASRA WITH DOT BELOW
+<U08F7> /xe0/xa3/xb7 ARABIC LEFT ARROWHEAD ABOVE
+<U08F8> /xe0/xa3/xb8 ARABIC RIGHT ARROWHEAD ABOVE
+<U08F9> /xe0/xa3/xb9 ARABIC LEFT ARROWHEAD BELOW
+<U08FA> /xe0/xa3/xba ARABIC RIGHT ARROWHEAD BELOW
+<U08FB> /xe0/xa3/xbb ARABIC DOUBLE RIGHT ARROWHEAD ABOVE
+<U08FC> /xe0/xa3/xbc ARABIC DOUBLE RIGHT ARROWHEAD ABOVE WITH DOT
+<U08FD> /xe0/xa3/xbd ARABIC RIGHT ARROWHEAD ABOVE WITH DOT
+<U08FE> /xe0/xa3/xbe ARABIC DAMMA WITH DOT
+<U08FF> /xe0/xa3/xbf ARABIC MARK SIDEWAYS NOON GHUNNA
<U0900> /xe0/xa4/x80 DEVANAGARI SIGN INVERTED CANDRABINDU
<U0901> /xe0/xa4/x81 DEVANAGARI SIGN CANDRABINDU
<U0902> /xe0/xa4/x82 DEVANAGARI SIGN ANUSVARA
@@ -2185,6 +2248,7 @@ CHARMAP
<U0975> /xe0/xa5/xb5 DEVANAGARI LETTER AW
<U0976> /xe0/xa5/xb6 DEVANAGARI LETTER UE
<U0977> /xe0/xa5/xb7 DEVANAGARI LETTER UUE
+<U0978> /xe0/xa5/xb8 DEVANAGARI LETTER MARWARI DDA
<U0979> /xe0/xa5/xb9 DEVANAGARI LETTER ZHA
<U097A> /xe0/xa5/xba DEVANAGARI LETTER HEAVY YA
<U097B> /xe0/xa5/xbb DEVANAGARI LETTER GGA
@@ -2192,6 +2256,7 @@ CHARMAP
<U097D> /xe0/xa5/xbd DEVANAGARI LETTER GLOTTAL STOP
<U097E> /xe0/xa5/xbe DEVANAGARI LETTER DDDA
<U097F> /xe0/xa5/xbf DEVANAGARI LETTER BBA
+<U0980> /xe0/xa6/x80 BENGALI ANJI
<U0981> /xe0/xa6/x81 BENGALI SIGN CANDRABINDU
<U0982> /xe0/xa6/x82 BENGALI SIGN ANUSVARA
<U0983> /xe0/xa6/x83 BENGALI SIGN VISARGA
@@ -2445,6 +2510,7 @@ CHARMAP
<U0AED> /xe0/xab/xad GUJARATI DIGIT SEVEN
<U0AEE> /xe0/xab/xae GUJARATI DIGIT EIGHT
<U0AEF> /xe0/xab/xaf GUJARATI DIGIT NINE
+<U0AF0> /xe0/xab/xb0 GUJARATI ABBREVIATION SIGN
<U0AF1> /xe0/xab/xb1 GUJARATI RUPEE SIGN
<U0B01> /xe0/xac/x81 ORIYA SIGN CANDRABINDU
<U0B02> /xe0/xac/x82 ORIYA SIGN ANUSVARA
@@ -2608,6 +2674,7 @@ CHARMAP
<U0BF8> /xe0/xaf/xb8 TAMIL AS ABOVE SIGN
<U0BF9> /xe0/xaf/xb9 TAMIL RUPEE SIGN
<U0BFA> /xe0/xaf/xba TAMIL NUMBER SIGN
+<U0C00> /xe0/xb0/x80 TELUGU SIGN COMBINING CANDRABINDU ABOVE
<U0C01> /xe0/xb0/x81 TELUGU SIGN CANDRABINDU
<U0C02> /xe0/xb0/x82 TELUGU SIGN ANUSVARA
<U0C03> /xe0/xb0/x83 TELUGU SIGN VISARGA
@@ -2655,6 +2722,7 @@ CHARMAP
<U0C31> /xe0/xb0/xb1 TELUGU LETTER RRA
<U0C32> /xe0/xb0/xb2 TELUGU LETTER LA
<U0C33> /xe0/xb0/xb3 TELUGU LETTER LLA
+<U0C34> /xe0/xb0/xb4 TELUGU LETTER LLLA
<U0C35> /xe0/xb0/xb5 TELUGU LETTER VA
<U0C36> /xe0/xb0/xb6 TELUGU LETTER SHA
<U0C37> /xe0/xb0/xb7 TELUGU LETTER SSA
@@ -2701,6 +2769,7 @@ CHARMAP
<U0C7D> /xe0/xb1/xbd TELUGU FRACTION DIGIT TWO FOR EVEN POWERS OF FOUR
<U0C7E> /xe0/xb1/xbe TELUGU FRACTION DIGIT THREE FOR EVEN POWERS OF FOUR
<U0C7F> /xe0/xb1/xbf TELUGU SIGN TUUMU
+<U0C81> /xe0/xb2/x81 KANNADA SIGN CANDRABINDU
<U0C82> /xe0/xb2/x82 KANNADA SIGN ANUSVARA
<U0C83> /xe0/xb2/x83 KANNADA SIGN VISARGA
<U0C85> /xe0/xb2/x85 KANNADA LETTER A
@@ -2787,6 +2856,7 @@ CHARMAP
<U0CEF> /xe0/xb3/xaf KANNADA DIGIT NINE
<U0CF1> /xe0/xb3/xb1 KANNADA SIGN JIHVAMULIYA
<U0CF2> /xe0/xb3/xb2 KANNADA SIGN UPADHMANIYA
+<U0D01> /xe0/xb4/x81 MALAYALAM SIGN CANDRABINDU
<U0D02> /xe0/xb4/x82 MALAYALAM SIGN ANUSVARA
<U0D03> /xe0/xb4/x83 MALAYALAM SIGN VISARGA
<U0D05> /xe0/xb4/x85 MALAYALAM LETTER A
@@ -2962,6 +3032,16 @@ CHARMAP
<U0DDD> /xe0/xb7/x9d SINHALA VOWEL SIGN KOMBUVA HAA DIGA AELA-PILLA
<U0DDE> /xe0/xb7/x9e SINHALA VOWEL SIGN KOMBUVA HAA GAYANUKITTA
<U0DDF> /xe0/xb7/x9f SINHALA VOWEL SIGN GAYANUKITTA
+<U0DE6> /xe0/xb7/xa6 SINHALA LITH DIGIT ZERO
+<U0DE7> /xe0/xb7/xa7 SINHALA LITH DIGIT ONE
+<U0DE8> /xe0/xb7/xa8 SINHALA LITH DIGIT TWO
+<U0DE9> /xe0/xb7/xa9 SINHALA LITH DIGIT THREE
+<U0DEA> /xe0/xb7/xaa SINHALA LITH DIGIT FOUR
+<U0DEB> /xe0/xb7/xab SINHALA LITH DIGIT FIVE
+<U0DEC> /xe0/xb7/xac SINHALA LITH DIGIT SIX
+<U0DED> /xe0/xb7/xad SINHALA LITH DIGIT SEVEN
+<U0DEE> /xe0/xb7/xae SINHALA LITH DIGIT EIGHT
+<U0DEF> /xe0/xb7/xaf SINHALA LITH DIGIT NINE
<U0DF2> /xe0/xb7/xb2 SINHALA VOWEL SIGN DIGA GAETTA-PILLA
<U0DF3> /xe0/xb7/xb3 SINHALA VOWEL SIGN DIGA GAYANUKITTA
<U0DF4> /xe0/xb7/xb4 SINHALA PUNCTUATION KUNDDALIYA
@@ -3117,6 +3197,8 @@ CHARMAP
<U0ED9> /xe0/xbb/x99 LAO DIGIT NINE
<U0EDC> /xe0/xbb/x9c LAO HO NO
<U0EDD> /xe0/xbb/x9d LAO HO MO
+<U0EDE> /xe0/xbb/x9e LAO LETTER KHMU GO
+<U0EDF> /xe0/xbb/x9f LAO LETTER KHMU NYO
<U0F00> /xe0/xbc/x80 TIBETAN SYLLABLE OM
<U0F01> /xe0/xbc/x81 TIBETAN MARK GTER YIG MGO TRUNCATED A
<U0F02> /xe0/xbc/x82 TIBETAN MARK GTER YIG MGO -UM RNAM BCAD MA
@@ -3526,6 +3608,8 @@ CHARMAP
<U10C3> /xe1/x83/x83 GEORGIAN CAPITAL LETTER WE
<U10C4> /xe1/x83/x84 GEORGIAN CAPITAL LETTER HAR
<U10C5> /xe1/x83/x85 GEORGIAN CAPITAL LETTER HOE
+<U10C7> /xe1/x83/x87 GEORGIAN CAPITAL LETTER YN
+<U10CD> /xe1/x83/x8d GEORGIAN CAPITAL LETTER AEN
<U10D0> /xe1/x83/x90 GEORGIAN LETTER AN
<U10D1> /xe1/x83/x91 GEORGIAN LETTER BAN
<U10D2> /xe1/x83/x92 GEORGIAN LETTER GAN
@@ -3571,6 +3655,9 @@ CHARMAP
<U10FA> /xe1/x83/xba GEORGIAN LETTER AIN
<U10FB> /xe1/x83/xbb GEORGIAN PARAGRAPH SEPARATOR
<U10FC> /xe1/x83/xbc MODIFIER LETTER GEORGIAN NAR
+<U10FD> /xe1/x83/xbd GEORGIAN LETTER AEN
+<U10FE> /xe1/x83/xbe GEORGIAN LETTER HARD SIGN
+<U10FF> /xe1/x83/xbf GEORGIAN LETTER LABIAL SIGN
<U1100> /xe1/x84/x80 HANGUL CHOSEONG KIYEOK
<U1101> /xe1/x84/x81 HANGUL CHOSEONG SSANGKIYEOK
<U1102> /xe1/x84/x82 HANGUL CHOSEONG NIEUN
@@ -5046,6 +5133,14 @@ CHARMAP
<U16EE> /xe1/x9b/xae RUNIC ARLAUG SYMBOL
<U16EF> /xe1/x9b/xaf RUNIC TVIMADUR SYMBOL
<U16F0> /xe1/x9b/xb0 RUNIC BELGTHOR SYMBOL
+<U16F1> /xe1/x9b/xb1 RUNIC LETTER K
+<U16F2> /xe1/x9b/xb2 RUNIC LETTER SH
+<U16F3> /xe1/x9b/xb3 RUNIC LETTER OO
+<U16F4> /xe1/x9b/xb4 RUNIC LETTER FRANKS CASKET OS
+<U16F5> /xe1/x9b/xb5 RUNIC LETTER FRANKS CASKET IS
+<U16F6> /xe1/x9b/xb6 RUNIC LETTER FRANKS CASKET EH
+<U16F7> /xe1/x9b/xb7 RUNIC LETTER FRANKS CASKET AC
+<U16F8> /xe1/x9b/xb8 RUNIC LETTER FRANKS CASKET AESC
<U1700> /xe1/x9c/x80 TAGALOG LETTER A
<U1701> /xe1/x9c/x81 TAGALOG LETTER I
<U1702> /xe1/x9c/x82 TAGALOG LETTER U
@@ -5496,6 +5591,8 @@ CHARMAP
<U191A> /xe1/xa4/x9a LIMBU LETTER SSA
<U191B> /xe1/xa4/x9b LIMBU LETTER SA
<U191C> /xe1/xa4/x9c LIMBU LETTER HA
+<U191D> /xe1/xa4/x9d LIMBU LETTER GYAN
+<U191E> /xe1/xa4/x9e LIMBU LETTER TRA
<U1920> /xe1/xa4/xa0 LIMBU VOWEL SIGN A
<U1921> /xe1/xa4/xa1 LIMBU VOWEL SIGN I
<U1922> /xe1/xa4/xa2 LIMBU VOWEL SIGN U
@@ -5840,6 +5937,21 @@ CHARMAP
<U1AAB> /xe1/xaa/xab TAI THAM SIGN SATKAANKUU
<U1AAC> /xe1/xaa/xac TAI THAM SIGN HANG
<U1AAD> /xe1/xaa/xad TAI THAM SIGN CAANG
+<U1AB0> /xe1/xaa/xb0 COMBINING DOUBLED CIRCUMFLEX ACCENT
+<U1AB1> /xe1/xaa/xb1 COMBINING DIAERESIS-RING
+<U1AB2> /xe1/xaa/xb2 COMBINING INFINITY
+<U1AB3> /xe1/xaa/xb3 COMBINING DOWNWARDS ARROW
+<U1AB4> /xe1/xaa/xb4 COMBINING TRIPLE DOT
+<U1AB5> /xe1/xaa/xb5 COMBINING X-X BELOW
+<U1AB6> /xe1/xaa/xb6 COMBINING WIGGLY LINE BELOW
+<U1AB7> /xe1/xaa/xb7 COMBINING OPEN MARK BELOW
+<U1AB8> /xe1/xaa/xb8 COMBINING DOUBLE OPEN MARK BELOW
+<U1AB9> /xe1/xaa/xb9 COMBINING LIGHT CENTRALIZATION STROKE BELOW
+<U1ABA> /xe1/xaa/xba COMBINING STRONG CENTRALIZATION STROKE BELOW
+<U1ABB> /xe1/xaa/xbb COMBINING PARENTHESES ABOVE
+<U1ABC> /xe1/xaa/xbc COMBINING DOUBLE PARENTHESES ABOVE
+<U1ABD> /xe1/xaa/xbd COMBINING PARENTHESES BELOW
+<U1ABE> /xe1/xaa/xbe COMBINING PARENTHESES OVERLAY
<U1B00> /xe1/xac/x80 BALINESE SIGN ULU RICEM
<U1B01> /xe1/xac/x81 BALINESE SIGN ULU CANDRA
<U1B02> /xe1/xac/x82 BALINESE SIGN CECEK
@@ -6004,6 +6116,9 @@ CHARMAP
<U1BA8> /xe1/xae/xa8 SUNDANESE VOWEL SIGN PAMEPET
<U1BA9> /xe1/xae/xa9 SUNDANESE VOWEL SIGN PANEULEUNG
<U1BAA> /xe1/xae/xaa SUNDANESE SIGN PAMAAEH
+<U1BAB> /xe1/xae/xab SUNDANESE SIGN VIRAMA
+<U1BAC> /xe1/xae/xac SUNDANESE CONSONANT SIGN PASANGAN MA
+<U1BAD> /xe1/xae/xad SUNDANESE CONSONANT SIGN PASANGAN WA
<U1BAE> /xe1/xae/xa