Update transliteration support to Unicode 7.0.0.

The transliteration files are now autogenerated from upstream Unicode
data.

1 files changed, 571 insertions, 7 deletions

diff --git a/localedata/locales/translit_compat b/localedata/locales/translit_compat
index bb9d660d05..bf8d19181b 100644
--- a/localedata/locales/translit_compat
+++ b/localedata/locales/translit_compat
@@ -2,18 +2,24 @@ escape_char /
 comment_char %
 
 % Transliterations of compatibility characters and ligatures.
-% Generated through
-%   $ grep '^[^;]*;[^;]*;[^;]*;[^;]*;[^;]*;<compat>[^;]*;' UnicodeData.txt | \
-%     sed -e 's/^\([^;]*\);\([^;]*\);[^;]*;[^;]*;[^;]*;<compat> \([^;]*\);.*$/<U\1> "<U\3>"% \2/' | grep -v '0020 03[0-6][0-9A-F]' | sed -e 'h' -e 's/^\([^%]*\)% .*$/\1/' -e 's/\([0-9A-F]\) \([0-9A-F]\)/\1><U\2/g' -e 'x' -e 's/^[^%]*\(% .*\)$/\1/' -e 'G'
-% and
-%   $ grep '[^;]*;[^;]*LIGATURE[^;]*;' UnicodeData.txt
+% Generated automatically from UnicodeData.txt by gen_translit_compat.py on 2015-12-09 for Unicode 7.0.0.
 
 LC_CTYPE
 
 translit_start
 
+% FEMININE ORDINAL INDICATOR
+<U00AA> "<U0061>"
+% SUPERSCRIPT TWO
+<U00B2> "<U0032>"
+% SUPERSCRIPT THREE
+<U00B3> "<U0033>"
 % MICRO SIGN
-<U00B5> "<U03BC>";<U0075>
+<U00B5> "<U03BC>";"<U0075>"
+% SUPERSCRIPT ONE
+<U00B9> "<U0031>"
+% MASCULINE ORDINAL INDICATOR
+<U00BA> "<U006F>"
 % LATIN CAPITAL LIGATURE IJ
 <U0132> "<U0049><U004A>"
 % LATIN SMALL LIGATURE IJ
@@ -54,6 +60,38 @@ translit_start
 <U01F2> "<U0044><U007A>"
 % LATIN SMALL LETTER DZ
 <U01F3> "<U0064><U007A>"
+% MODIFIER LETTER SMALL H
+<U02B0> "<U0068>"
+% MODIFIER LETTER SMALL H WITH HOOK
+<U02B1> "<U0266>"
+% MODIFIER LETTER SMALL J
+<U02B2> "<U006A>"
+% MODIFIER LETTER SMALL R
+<U02B3> "<U0072>"
+% MODIFIER LETTER SMALL TURNED R
+<U02B4> "<U0279>"
+% MODIFIER LETTER SMALL TURNED R WITH HOOK
+<U02B5> "<U027B>"
+% MODIFIER LETTER SMALL CAPITAL INVERTED R
+<U02B6> "<U0281>"
+% MODIFIER LETTER SMALL W
+<U02B7> "<U0077>"
+% MODIFIER LETTER SMALL Y
+<U02B8> "<U0079>"
+% MODIFIER LETTER APOSTROPHE
+<U02BC> "<U0027>"
+% MODIFIER LETTER SMALL GAMMA
+<U02E0> "<U0263>"
+% MODIFIER LETTER SMALL L
+<U02E1> "<U006C>"
+% MODIFIER LETTER SMALL S
+<U02E2> "<U0073>"
+% MODIFIER LETTER SMALL X
+<U02E3> "<U0078>"
+% MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
+<U02E4> "<U0295>"
+% GREEK SMALL LETTER MU
+<U03BC> "<U0075>"
 % GREEK BETA SYMBOL
 <U03D0> "<U03B2>"
 % GREEK THETA SYMBOL
@@ -74,6 +112,20 @@ translit_start
 <U03F4> "<U0398>"
 % GREEK LUNATE EPSILON SYMBOL
 <U03F5> "<U03B5>"
+% GREEK CAPITAL LUNATE SIGMA SYMBOL
+<U03F9> "<U03A3>"
+% CYRILLIC CAPITAL LIGATURE EN GHE
+<U04A4> "<U041D><U0413>"
+% CYRILLIC SMALL LIGATURE EN GHE
+<U04A5> "<U043D><U0433>"
+% CYRILLIC CAPITAL LIGATURE TE TSE
+<U04B4> "<U0422><U0426>"
+% CYRILLIC SMALL LIGATURE TE TSE
+<U04B5> "<U0442><U0446>"
+% CYRILLIC CAPITAL LIGATURE A IE
+<U04D4> "<U0410><U0415>"
+% CYRILLIC SMALL LIGATURE A IE
+<U04D5> "<U0430><U0435>"
 % ARMENIAN SMALL LIGATURE ECH YIWN
 <U0587> "<U0565><U0582>"
 % HEBREW LIGATURE YIDDISH DOUBLE VAV
@@ -102,6 +154,204 @@ translit_start
 <U0F77> "<U0FB2><U0F81>"
 % TIBETAN VOWEL SIGN VOCALIC LL
 <U0F79> "<U0FB3><U0F81>"
+% MODIFIER LETTER GEORGIAN NAR
+<U10FC> "<U10DC>"
+% MODIFIER LETTER CAPITAL A
+<U1D2C> "<U0041>"
+% MODIFIER LETTER CAPITAL AE
+<U1D2D> "<U00C6>"
+% MODIFIER LETTER CAPITAL B
+<U1D2E> "<U0042>"
+% MODIFIER LETTER CAPITAL D
+<U1D30> "<U0044>"
+% MODIFIER LETTER CAPITAL E
+<U1D31> "<U0045>"
+% MODIFIER LETTER CAPITAL REVERSED E
+<U1D32> "<U018E>"
+% MODIFIER LETTER CAPITAL G
+<U1D33> "<U0047>"
+% MODIFIER LETTER CAPITAL H
+<U1D34> "<U0048>"
+% MODIFIER LETTER CAPITAL I
+<U1D35> "<U0049>"
+% MODIFIER LETTER CAPITAL J
+<U1D36> "<U004A>"
+% MODIFIER LETTER CAPITAL K
+<U1D37> "<U004B>"
+% MODIFIER LETTER CAPITAL L
+<U1D38> "<U004C>"
+% MODIFIER LETTER CAPITAL M
+<U1D39> "<U004D>"
+% MODIFIER LETTER CAPITAL N
+<U1D3A> "<U004E>"
+% MODIFIER LETTER CAPITAL O
+<U1D3C> "<U004F>"
+% MODIFIER LETTER CAPITAL OU
+<U1D3D> "<U0222>"
+% MODIFIER LETTER CAPITAL P
+<U1D3E> "<U0050>"
+% MODIFIER LETTER CAPITAL R
+<U1D3F> "<U0052>"
+% MODIFIER LETTER CAPITAL T
+<U1D40> "<U0054>"
+% MODIFIER LETTER CAPITAL U
+<U1D41> "<U0055>"
+% MODIFIER LETTER CAPITAL W
+<U1D42> "<U0057>"
+% MODIFIER LETTER SMALL A
+<U1D43> "<U0061>"
+% MODIFIER LETTER SMALL TURNED A
+<U1D44> "<U0250>"
+% MODIFIER LETTER SMALL ALPHA
+<U1D45> "<U0251>"
+% MODIFIER LETTER SMALL TURNED AE
+<U1D46> "<U1D02>"
+% MODIFIER LETTER SMALL B
+<U1D47> "<U0062>"
+% MODIFIER LETTER SMALL D
+<U1D48> "<U0064>"
+% MODIFIER LETTER SMALL E
+<U1D49> "<U0065>"
+% MODIFIER LETTER SMALL SCHWA
+<U1D4A> "<U0259>"
+% MODIFIER LETTER SMALL OPEN E
+<U1D4B> "<U025B>"
+% MODIFIER LETTER SMALL TURNED OPEN E
+<U1D4C> "<U025C>"
+% MODIFIER LETTER SMALL G
+<U1D4D> "<U0067>"
+% MODIFIER LETTER SMALL K
+<U1D4F> "<U006B>"
+% MODIFIER LETTER SMALL M
+<U1D50> "<U006D>"
+% MODIFIER LETTER SMALL ENG
+<U1D51> "<U014B>"
+% MODIFIER LETTER SMALL O
+<U1D52> "<U006F>"
+% MODIFIER LETTER SMALL OPEN O
+<U1D53> "<U0254>"
+% MODIFIER LETTER SMALL TOP HALF O
+<U1D54> "<U1D16>"
+% MODIFIER LETTER SMALL BOTTOM HALF O
+<U1D55> "<U1D17>"
+% MODIFIER LETTER SMALL P
+<U1D56> "<U0070>"
+% MODIFIER LETTER SMALL T
+<U1D57> "<U0074>"
+% MODIFIER LETTER SMALL U
+<U1D58> "<U0075>"
+% MODIFIER LETTER SMALL SIDEWAYS U
+<U1D59> "<U1D1D>"
+% MODIFIER LETTER SMALL TURNED M
+<U1D5A> "<U026F>"
+% MODIFIER LETTER SMALL V
+<U1D5B> "<U0076>"
+% MODIFIER LETTER SMALL AIN
+<U1D5C> "<U1D25>"
+% MODIFIER LETTER SMALL BETA
+<U1D5D> "<U03B2>"
+% MODIFIER LETTER SMALL GREEK GAMMA
+<U1D5E> "<U03B3>"
+% MODIFIER LETTER SMALL DELTA
+<U1D5F> "<U03B4>"
+% MODIFIER LETTER SMALL GREEK PHI
+<U1D60> "<U03C6>"
+% MODIFIER LETTER SMALL CHI
+<U1D61> "<U03C7>"
+% LATIN SUBSCRIPT SMALL LETTER I
+<U1D62> "<U0069>"
+% LATIN SUBSCRIPT SMALL LETTER R
+<U1D63> "<U0072>"
+% LATIN SUBSCRIPT SMALL LETTER U
+<U1D64> "<U0075>"
+% LATIN SUBSCRIPT SMALL LETTER V
+<U1D65> "<U0076>"
+% GREEK SUBSCRIPT SMALL LETTER BETA
+<U1D66> "<U03B2>"
+% GREEK SUBSCRIPT SMALL LETTER GAMMA
+<U1D67> "<U03B3>"
+% GREEK SUBSCRIPT SMALL LETTER RHO
+<U1D68> "<U03C1>"
+% GREEK SUBSCRIPT SMALL LETTER PHI
+<U1D69> "<U03C6>"
+% GREEK SUBSCRIPT SMALL LETTER CHI
+<U1D6A> "<U03C7>"
+% MODIFIER LETTER CYRILLIC EN
+<U1D78> "<U043D>"
+% MODIFIER LETTER SMALL TURNED ALPHA
+<U1D9B> "<U0252>"
+% MODIFIER LETTER SMALL C
+<U1D9C> "<U0063>"
+% MODIFIER LETTER SMALL C WITH CURL
+<U1D9D> "<U0255>"
+% MODIFIER LETTER SMALL ETH
+<U1D9E> "<U00F0>"
+% MODIFIER LETTER SMALL REVERSED OPEN E
+<U1D9F> "<U025C>"
+% MODIFIER LETTER SMALL F
+<U1DA0> "<U0066>"
+% MODIFIER LETTER SMALL DOTLESS J WITH STROKE
+<U1DA1> "<U025F>"
+% MODIFIER LETTER SMALL SCRIPT G
+<U1DA2> "<U0261>"
+% MODIFIER LETTER SMALL TURNED H
+<U1DA3> "<U0265>"
+% MODIFIER LETTER SMALL I WITH STROKE
+<U1DA4> "<U0268>"
+% MODIFIER LETTER SMALL IOTA
+<U1DA5> "<U0269>"
+% MODIFIER LETTER SMALL CAPITAL I
+<U1DA6> "<U026A>"
+% MODIFIER LETTER SMALL CAPITAL I WITH STROKE
+<U1DA7> "<U1D7B>"
+% MODIFIER LETTER SMALL J WITH CROSSED-TAIL
+<U1DA8> "<U029D>"
+% MODIFIER LETTER SMALL L WITH RETROFLEX HOOK
+<U1DA9> "<U026D>"
+% MODIFIER LETTER SMALL L WITH PALATAL HOOK
+<U1DAA> "<U1D85>"
+% MODIFIER LETTER SMALL CAPITAL L
+<U1DAB> "<U029F>"
+% MODIFIER LETTER SMALL M WITH HOOK
+<U1DAC> "<U0271>"
+% MODIFIER LETTER SMALL TURNED M WITH LONG LEG
+<U1DAD> "<U0270>"
+% MODIFIER LETTER SMALL N WITH LEFT HOOK
+<U1DAE> "<U0272>"
+% MODIFIER LETTER SMALL N WITH RETROFLEX HOOK
+<U1DAF> "<U0273>"
+% MODIFIER LETTER SMALL CAPITAL N
+<U1DB0> "<U0274>"
+% MODIFIER LETTER SMALL BARRED O
+<U1DB1> "<U0275>"
+% MODIFIER LETTER SMALL PHI
+<U1DB2> "<U0278>"
+% MODIFIER LETTER SMALL S WITH HOOK
+<U1DB3> "<U0282>"
+% MODIFIER LETTER SMALL ESH
+<U1DB4> "<U0283>"
+% MODIFIER LETTER SMALL T WITH PALATAL HOOK
+<U1DB5> "<U01AB>"
+% MODIFIER LETTER SMALL U BAR
+<U1DB6> "<U0289>"
+% MODIFIER LETTER SMALL UPSILON
+<U1DB7> "<U028A>"
+% MODIFIER LETTER SMALL CAPITAL U
+<U1DB8> "<U1D1C>"
+% MODIFIER LETTER SMALL V WITH HOOK
+<U1DB9> "<U028B>"
+% MODIFIER LETTER SMALL TURNED V
+<U1DBA> "<U028C>"
+% MODIFIER LETTER SMALL Z
+<U1DBB> "<U007A>"
+% MODIFIER LETTER SMALL Z WITH RETROFLEX HOOK
+<U1DBC> "<U0290>"
+% MODIFIER LETTER SMALL Z WITH CURL
+<U1DBD> "<U0291>"
+% MODIFIER LETTER SMALL EZH
+<U1DBE> "<U0292>"
+% MODIFIER LETTER SMALL THETA
+<U1DBF> "<U03B8>"
 % LATIN SMALL LETTER A WITH RIGHT HALF RING
 <U1E9A> "<U0061><U02BE>"
 % EN SPACE
@@ -146,6 +396,90 @@ translit_start
 <U2057> "<U2032><U2032><U2032><U2032>"
 % MEDIUM MATHEMATICAL SPACE
 <U205F> "<U0020>"
+% SUPERSCRIPT ZERO
+<U2070> "<U0030>"
+% SUPERSCRIPT LATIN SMALL LETTER I
+<U2071> "<U0069>"
+% SUPERSCRIPT FOUR
+<U2074> "<U0034>"
+% SUPERSCRIPT FIVE
+<U2075> "<U0035>"
+% SUPERSCRIPT SIX
+<U2076> "<U0036>"
+% SUPERSCRIPT SEVEN
+<U2077> "<U0037>"
+% SUPERSCRIPT EIGHT
+<U2078> "<U0038>"
+% SUPERSCRIPT NINE
+<U2079> "<U0039>"
+% SUPERSCRIPT PLUS SIGN
+<U207A> "<U002B>"
+% SUPERSCRIPT MINUS
+<U207B> "<U2212>"
+% SUPERSCRIPT EQUALS SIGN
+<U207C> "<U003D>"
+% SUPERSCRIPT LEFT PARENTHESIS
+<U207D> "<U0028>"
+% SUPERSCRIPT RIGHT PARENTHESIS
+<U207E> "<U0029>"
+% SUPERSCRIPT LATIN SMALL LETTER N
+<U207F> "<U006E>"
+% SUBSCRIPT ZERO
+<U2080> "<U0030>"
+% SUBSCRIPT ONE
+<U2081> "<U0031>"
+% SUBSCRIPT TWO
+<U2082> "<U0032>"
+% SUBSCRIPT THREE
+<U2083> "<U0033>"
+% SUBSCRIPT FOUR
+<U2084> "<U0034>"
+% SUBSCRIPT FIVE
+<U2085> "<U0035>"
+% SUBSCRIPT SIX
+<U2086> "<U0036>"
+% SUBSCRIPT SEVEN
+<U2087> "<U0037>"
+% SUBSCRIPT EIGHT
+<U2088> "<U0038>"
+% SUBSCRIPT NINE
+<U2089> "<U0039>"
+% SUBSCRIPT PLUS SIGN
+<U208A> "<U002B>"
+% SUBSCRIPT MINUS
+<U208B> "<U2212>"
+% SUBSCRIPT EQUALS SIGN
+<U208C> "<U003D>"
+% SUBSCRIPT LEFT PARENTHESIS
+<U208D> "<U0028>"
+% SUBSCRIPT RIGHT PARENTHESIS
+<U208E> "<U0029>"
+% LATIN SUBSCRIPT SMALL LETTER A
+<U2090> "<U0061>"
+% LATIN SUBSCRIPT SMALL LETTER E
+<U2091> "<U0065>"
+% LATIN SUBSCRIPT SMALL LETTER O
+<U2092> "<U006F>"
+% LATIN SUBSCRIPT SMALL LETTER X
+<U2093> "<U0078>"
+% LATIN SUBSCRIPT SMALL LETTER SCHWA
+<U2094> "<U0259>"
+% LATIN SUBSCRIPT SMALL LETTER H
+<U2095> "<U0068>"
+% LATIN SUBSCRIPT SMALL LETTER K
+<U2096> "<U006B>"
+% LATIN SUBSCRIPT SMALL LETTER L
+<U2097> "<U006C>"
+% LATIN SUBSCRIPT SMALL LETTER M
+<U2098> "<U006D>"
+% LATIN SUBSCRIPT SMALL LETTER N
+<U2099> "<U006E>"
+% LATIN SUBSCRIPT SMALL LETTER P
+<U209A> "<U0070>"
+% LATIN SUBSCRIPT SMALL LETTER S
+<U209B> "<U0073>"
+% LATIN SUBSCRIPT SMALL LETTER T
+<U209C> "<U0074>"
 % RUPEE SIGN
 <U20A8> "<U0052><U0073>"
 % ACCOUNT OF
@@ -164,8 +498,12 @@ translit_start
 <U2109> "<U00B0><U0046>"
 % NUMERO SIGN
 <U2116> "<U004E><U006F>"
+% SERVICE MARK
+<U2120> "<U0053><U004D>"
 % TELEPHONE SIGN
 <U2121> "<U0054><U0045><U004C>"
+% TRADE MARK SIGN
+<U2122> "<U0054><U004D>"
 % ALEF SYMBOL
 <U2135> "<U05D0>"
 % BET SYMBOL
@@ -174,6 +512,8 @@ translit_start
 <U2137> "<U05D2>"
 % DALET SYMBOL
 <U2138> "<U05D3>"
+% FACSIMILE SIGN
+<U213B> "<U0046><U0041><U0058>"
 % ROMAN NUMERAL ONE
 <U2160> "<U0049>"
 % ROMAN NUMERAL TWO
@@ -386,6 +726,12 @@ translit_start
 <U2A75> "<U003D><U003D>"
 % THREE CONSECUTIVE EQUALS SIGNS
 <U2A76> "<U003D><U003D><U003D>"
+% LATIN SUBSCRIPT SMALL LETTER J
+<U2C7C> "<U006A>"
+% MODIFIER LETTER CAPITAL V
+<U2C7D> "<U0056>"
+% TIFINAGH MODIFIER LETTER LABIALIZATION MARK
+<U2D6F> "<U2D61>"
 % CJK RADICAL MOTHER
 <U2E9F> "<U6BCD>"
 % CJK RADICAL C-SIMPLIFIED TURTLE
@@ -830,6 +1176,10 @@ translit_start
 <U309B> "<U0020><U3099>"
 % KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
 <U309C> "<U0020><U309A>"
+% HIRAGANA DIGRAPH YORI
+<U309F> "<U3088><U308A>"
+% KATAKANA DIGRAPH KOTO
+<U30FF> "<U30B3><U30C8>"
 % HANGUL LETTER KIYEOK
 <U3131> "<U1100>"
 % HANGUL LETTER SSANGKIYEOK
@@ -1018,6 +1368,34 @@ translit_start
 <U318D> "<U119E>"
 % HANGUL LETTER ARAEAE
 <U318E> "<U11A1>"
+% IDEOGRAPHIC ANNOTATION ONE MARK
+<U3192> "<U4E00>"
+% IDEOGRAPHIC ANNOTATION TWO MARK
+<U3193> "<U4E8C>"
+% IDEOGRAPHIC ANNOTATION THREE MARK
+<U3194> "<U4E09>"
+% IDEOGRAPHIC ANNOTATION FOUR MARK
+<U3195> "<U56DB>"
+% IDEOGRAPHIC ANNOTATION TOP MARK
+<U3196> "<U4E0A>"
+% IDEOGRAPHIC ANNOTATION MIDDLE MARK
+<U3197> "<U4E2D>"
+% IDEOGRAPHIC ANNOTATION BOTTOM MARK
+<U3198> "<U4E0B>"
+% IDEOGRAPHIC ANNOTATION FIRST MARK
+<U3199> "<U7532>"
+% IDEOGRAPHIC ANNOTATION SECOND MARK
+<U319A> "<U4E59>"
+% IDEOGRAPHIC ANNOTATION THIRD MARK
+<U319B> "<U4E19>"
+% IDEOGRAPHIC ANNOTATION FOURTH MARK
+<U319C> "<U4E01>"
+% IDEOGRAPHIC ANNOTATION HEAVEN MARK
+<U319D> "<U5929>"
+% IDEOGRAPHIC ANNOTATION EARTH MARK
+<U319E> "<U5730>"
+% IDEOGRAPHIC ANNOTATION MAN MARK
+<U319F> "<U4EBA>"
 % PARENTHESIZED HANGUL KIYEOK
 <U3200> "<U0028><U1100><U0029>"
 % PARENTHESIZED HANGUL NIEUN
@@ -1076,6 +1454,10 @@ translit_start
 <U321B> "<U0028><U1112><U1161><U0029>"
 % PARENTHESIZED HANGUL CIEUC U
 <U321C> "<U0028><U110C><U116E><U0029>"
+% PARENTHESIZED KOREAN CHARACTER OJEON
+<U321D> "<U0028><U110B><U1169><U110C><U1165><U11AB><U0029>"
+% PARENTHESIZED KOREAN CHARACTER O HU
+<U321E> "<U0028><U110B><U1169><U1112><U116E><U0029>"
 % PARENTHESIZED IDEOGRAPH ONE
 <U3220> "<U0028><U4E00><U0029>"
 % PARENTHESIZED IDEOGRAPH TWO
@@ -1284,6 +1666,24 @@ translit_start
 <U33FD> "<U0033><U0030><U65E5>"
 % IDEOGRAPHIC TELEGRAPH SYMBOL FOR DAY THIRTY-ONE
 <U33FE> "<U0033><U0031><U65E5>"
+% MODIFIER LETTER CYRILLIC HARD SIGN
+<UA69C> "<U044A>"
+% MODIFIER LETTER CYRILLIC SOFT SIGN
+<UA69D> "<U044C>"
+% MODIFIER LETTER US
+<UA770> "<UA76F>"
+% MODIFIER LETTER CAPITAL H WITH STROKE
+<UA7F8> "<U0126>"
+% MODIFIER LETTER SMALL LIGATURE OE
+<UA7F9> "<U0153>"
+% MODIFIER LETTER SMALL HENG
+<UAB5C> "<UA727>"
+% MODIFIER LETTER SMALL L WITH INVERTED LAZY S
+<UAB5D> "<UAB37>"
+% MODIFIER LETTER SMALL L WITH MIDDLE TILDE
+<UAB5E> "<U026B>"
+% MODIFIER LETTER SMALL U WITH LEFT HOOK
+<UAB5F> "<UAB52>"
 % LATIN SMALL LIGATURE FF
 <UFB00> "<U0066><U0066>"
 % LATIN SMALL LIGATURE FI
@@ -1295,7 +1695,7 @@ translit_start
 % LATIN SMALL LIGATURE FFL
 <UFB04> "<U0066><U0066><U006C>"
 % LATIN SMALL LIGATURE LONG S T
-<UFB05> "<U017F><U0074>"
+<UFB05> "<U0073><U0074>"
 % LATIN SMALL LIGATURE ST
 <UFB06> "<U0073><U0074>"
 % ARMENIAN SMALL LIGATURE MEN NOW
@@ -1310,6 +1710,72 @@ translit_start
 <UFB17> "<U0574><U056D>"
 % HEBREW LIGATURE ALEF LAMED
 <UFB4F> "<U05D0><U05DC>"
+% PRESENTATION FORM FOR VERTICAL COMMA
+<UFE10> "<U002C>"
+% PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC COMMA
+<UFE11> "<U3001>"
+% PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC FULL STOP
+<UFE12> "<U3002>"
+% PRESENTATION FORM FOR VERTICAL COLON
+<UFE13> "<U003A>"
+% PRESENTATION FORM FOR VERTICAL SEMICOLON
+<UFE14> "<U003B>"
+% PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK
+<UFE15> "<U0021>"
+% PRESENTATION FORM FOR VERTICAL QUESTION MARK
+<UFE16> "<U003F>"
+% PRESENTATION FORM FOR VERTICAL LEFT WHITE LENTICULAR BRACKET
+<UFE17> "<U3016>"
+% PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRAKCET
+<UFE18> "<U3017>"
+% PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS
+<UFE19> "<U002E><U002E><U002E>"
+% PRESENTATION FORM FOR VERTICAL TWO DOT LEADER
+<UFE30> "<U002E><U002E>"
+% PRESENTATION FORM FOR VERTICAL EM DASH
+<UFE31> "<U2014>"
+% PRESENTATION FORM FOR VERTICAL EN DASH
+<UFE32> "<U2013>"
+% PRESENTATION FORM FOR VERTICAL LOW LINE
+<UFE33> "<U005F>"
+% PRESENTATION FORM FOR VERTICAL WAVY LOW LINE
+<UFE34> "<U005F>"
+% PRESENTATION FORM FOR VERTICAL LEFT PARENTHESIS
+<UFE35> "<U0028>"
+% PRESENTATION FORM FOR VERTICAL RIGHT PARENTHESIS
+<UFE36> "<U0029>"
+% PRESENTATION FORM FOR VERTICAL LEFT CURLY BRACKET
+<UFE37> "<U007B>"
+% PRESENTATION FORM FOR VERTICAL RIGHT CURLY BRACKET
+<UFE38> "<U007D>"
+% PRESENTATION FORM FOR VERTICAL LEFT TORTOISE SHELL BRACKET
+<UFE39> "<U3014>"
+% PRESENTATION FORM FOR VERTICAL RIGHT TORTOISE SHELL BRACKET
+<UFE3A> "<U3015>"
+% PRESENTATION FORM FOR VERTICAL LEFT BLACK LENTICULAR BRACKET
+<UFE3B> "<U3010>"
+% PRESENTATION FORM FOR VERTICAL RIGHT BLACK LENTICULAR BRACKET
+<UFE3C> "<U3011>"
+% PRESENTATION FORM FOR VERTICAL LEFT DOUBLE ANGLE BRACKET
+<UFE3D> "<U300A>"
+% PRESENTATION FORM FOR VERTICAL RIGHT DOUBLE ANGLE BRACKET
+<UFE3E> "<U300B>"
+% PRESENTATION FORM FOR VERTICAL LEFT ANGLE BRACKET
+<UFE3F> "<U3008>"
+% PRESENTATION FORM FOR VERTICAL RIGHT ANGLE BRACKET
+<UFE40> "<U3009>"
+% PRESENTATION FORM FOR VERTICAL LEFT CORNER BRACKET
+<UFE41> "<U300C>"
+% PRESENTATION FORM FOR VERTICAL RIGHT CORNER BRACKET
+<UFE42> "<U300D>"
+% PRESENTATION FORM FOR VERTICAL LEFT WHITE CORNER BRACKET
+<UFE43> "<U300E>"
+% PRESENTATION FORM FOR VERTICAL RIGHT WHITE CORNER BRACKET
+<UFE44> "<U300F>"
+% PRESENTATION FORM FOR VERTICAL LEFT SQUARE BRACKET
+<UFE47> "<U005B>"
+% PRESENTATION FORM FOR VERTICAL RIGHT SQUARE BRACKET
+<UFE48> "<U005D>"
 % DASHED OVERLINE
 <UFE49> "<U203E>"
 % CENTRELINE OVERLINE
@@ -1324,6 +1790,104 @@ translit_start
 <UFE4E> "<U005F>"
 % WAVY LOW LINE
 <UFE4F> "<U005F>"
+% DIGIT ZERO FULL STOP
+<U0001F100> "<U0030><U002E>"
+% DIGIT ZERO COMMA
+<U0001F101> "<U0030><U002C>"
+% DIGIT ONE COMMA
+<U0001F102> "<U0031><U002C>"
+% DIGIT TWO COMMA
+<U0001F103> "<U0032><U002C>"
+% DIGIT THREE COMMA
+<U0001F104> "<U0033><U002C>"
+% DIGIT FOUR COMMA
+<U0001F105> "<U0034><U002C>"
+% DIGIT FIVE COMMA
+<U0001F106> "<U0035><U002C>"
+% DIGIT SIX COMMA
+<U0001F107> "<U0036><U002C>"
+% DIGIT SEVEN COMMA
+<U0001F108> "<U0037><U002C>"
+% DIGIT EIGHT COMMA
+<U0001F109> "<U0038><U002C>"
+% DIGIT NINE COMMA
+<U0001F10A> "<U0039><U002C>"
+% PARENTHESIZED LATIN CAPITAL LETTER A
+<U0001F110> "<U0028><U0041><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER B
+<U0001F111> "<U0028><U0042><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER C
+<U0001F112> "<U0028><U0043><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER D
+<U0001F113> "<U0028><U0044><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER E
+<U0001F114> "<U0028><U0045><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER F
+<U0001F115> "<U0028><U0046><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER G
+<U0001F116> "<U0028><U0047><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER H
+<U0001F117> "<U0028><U0048><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER I
+<U0001F118> "<U0028><U0049><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER J
+<U0001F119> "<U0028><U004A><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER K
+<U0001F11A> "<U0028><U004B><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER L
+<U0001F11B> "<U0028><U004C><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER M
+<U0001F11C> "<U0028><U004D><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER N
+<U0001F11D> "<U0028><U004E><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER O
+<U0001F11E> "<U0028><U004F><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER P
+<U0001F11F> "<U0028><U0050><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER Q
+<U0001F120> "<U0028><U0051><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER R
+<U0001F121> "<U0028><U0052><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER S
+<U0001F122> "<U0028><U0053><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER T
+<U0001F123> "<U0028><U0054><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER U
+<U0001F124> "<U0028><U0055><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER V
+<U0001F125> "<U0028><U0056><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER W
+<U0001F126> "<U0028><U0057><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER X
+<U0001F127> "<U0028><U0058><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER Y
+<U0001F128> "<U0028><U0059><U0029>"
+% PARENTHESIZED LATIN CAPITAL LETTER Z
+<U0001F129> "<U0028><U005A><U0029>"
+% TORTOISE SHELL BRACKETED LATIN CAPITAL LETTER S
+<U0001F12A> "<U3014><U0053><U3015>"
+% RAISED MC SIGN
+<U0001F16A> "<U004D><U0043>"
+% RAISED MD SIGN
+<U0001F16B> "<U004D><U0044>"
+% TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C
+<U0001F240> "<U3014><U672C><U3015>"
+% TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-4E09
+<U0001F241> "<U3014><U4E09><U3015>"
+% TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-4E8C
+<U0001F242> "<U3014><U4E8C><U3015>"
+% TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-5B89
+<U0001F243> "<U3014><U5B89><U3015>"
+% TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-70B9
+<U0001F244> "<U3014><U70B9><U3015>"
+% TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6253
+<U0001F245> "<U3014><U6253><U3015>"
+% TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-76D7
+<U0001F246> "<U3014><U76D7><U3015>"
+% TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-52DD
+<U0001F247> "<U3014><U52DD><U3015>"
+% TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557
+<U0001F248> "<U3014><U6557><U3015>"
 
 translit_end