digraphs: mark latin/ascii characters

Add classes if characters belong to the 'Basic Latin' or 'Latin-1 Supplement'
blocks (i.e. are ASCII or latin1), and indicate these on the digraphs page.

diff --git a/digraphs.inc.pl b/digraphs.inc.pl
index 228a2f914c6a1fb00ec979fd0389cbe816791560..748134d118755bd42bc1be50c30f7e1cc59f19f7 100644 (file)
--- a/digraphs.inc.pl
+++ b/digraphs.inc.pl
@@ -1,13 +1,13 @@
 {
-q{!!}=>[124,'VERTICAL LINE','Sm','Common'],
-q{!)}=>[125,'RIGHT CURLY BRACKET','Pe','Common'],
+q{!!}=>[124,'VERTICAL LINE','Sm Xa','Common'],
+q{!)}=>[125,'RIGHT CURLY BRACKET','Pe Xa','Common'],
 q{!*}=>[57382,'','Co','Common'],
 q{!2}=>[8214,'DOUBLE VERTICAL LINE','Po','Common'],
 q{!:}=>[7942,'GREEK SMALL LETTER ALPHA WITH PSILI AND PERISPOMENI','Ll','Greek'],
 q{!<}=>[8814,'NOT LESS-THAN','Sm','Common'],
 q{!=}=>[8800,'NOT EQUAL TO','Sm','Common'],
 q{!>}=>[8815,'NOT GREATER-THAN','Sm','Common'],
-q{!I}=>[161,'INVERTED EXCLAMATION MARK','Po','Common'],
+q{!I}=>[161,'INVERTED EXCLAMATION MARK','Po Xl','Common'],
 q{"!}=>[57350,'','Co','Common'],
 q{""}=>[57359,'','Co','Common'],
 q{"'}=>[57351,'','Co','Common'],
@@ -36,27 +36,27 @@ q{"p}=>[57368,'','Co','Common'],
 q{%"}=>[1068,'CYRILLIC CAPITAL LETTER SOFT SIGN','Lu','Cyrillic'],
 q{%'}=>[1100,'CYRILLIC SMALL LETTER SOFT SIGN','Ll','Cyrillic'],
 q{%0}=>[8240,'PER MILLE SIGN','Po','Common'],
-q{'!}=>[96,'GRAVE ACCENT','Sk','Common'],
+q{'!}=>[96,'GRAVE ACCENT','Sk Xa','Common'],
 q{'"}=>[733,'DOUBLE ACUTE ACCENT','Sk','Common'],
 q{'%}=>[1012,'GREEK CAPITAL THETA SYMBOL','Lu','Greek'],
-q{''}=>[180,'ACUTE ACCENT','Sk','Common'],
+q{''}=>[180,'ACUTE ACCENT','Sk Xl','Common'],
 q{'(}=>[728,'BREVE','Sk','Common'],
 q{'+}=>[1615,'ARABIC DAMMA','Mn','Inherited'],
-q{',}=>[184,'CEDILLA','Sk','Common'],
+q{',}=>[184,'CEDILLA','Sk Xl','Common'],
 q{'-}=>[8254,'OVERLINE','Po','Common'],
 q{'.}=>[729,'DOT ABOVE','Sk','Common'],
 q{'0}=>[730,'RING ABOVE','Sk','Common'],
 q{'6}=>[8216,'LEFT SINGLE QUOTATION MARK','Pi','Common'],
 q{'9}=>[8217,'RIGHT SINGLE QUOTATION MARK','Pf','Common'],
-q{':}=>[168,'DIAERESIS','Sk','Common'],
+q{':}=>[168,'DIAERESIS','Sk Xl','Common'],
 q{';}=>[731,'OGONEK','Sk','Common'],
 q{'<}=>[711,'CARON','Lm','Common'],
-q{'>}=>[94,'CIRCUMFLEX ACCENT','Sk','Common'],
-q{'?}=>[126,'TILDE','Sm','Common'],
+q{'>}=>[94,'CIRCUMFLEX ACCENT','Sk Xa','Common'],
+q{'?}=>[126,'TILDE','Sm Xa','Common'],
 q{'G}=>[984,'GREEK LETTER ARCHAIC KOPPA','Lu','Greek'],
-q{'m}=>[175,'MACRON','Sk','Common'],
+q{'m}=>[175,'MACRON','Sk Xl','Common'],
 q{'n}=>[329,'LATIN SMALL LETTER N PRECEDED BY APOSTROPHE','Ll','Latin'],
-q{(!}=>[123,'LEFT CURLY BRACKET','Ps','Common'],
+q{(!}=>[123,'LEFT CURLY BRACKET','Ps Xa','Common'],
 q{("}=>[12304,'LEFT BLACK LENTICULAR BRACKET','Ps','Common'],
 q{('}=>[12308,'LEFT TORTOISE SHELL BRACKET','Ps','Common'],
 q{(-}=>[8712,'ELEMENT OF','Sm','Common'],
@@ -69,7 +69,7 @@ q{(_}=>[8838,'SUBSET OF OR EQUAL TO','Sm','Common'],
 q{(s}=>[8333,'SUBSCRIPT LEFT PARENTHESIS','Ps','Common'],
 q{)"}=>[12305,'RIGHT BLACK LENTICULAR BRACKET','Pe','Common'],
 q{)'}=>[12309,'RIGHT TORTOISE SHELL BRACKET','Pe','Common'],
-q{)>}=>[93,'RIGHT SQUARE BRACKET','Pe','Common'],
+q{)>}=>[93,'RIGHT SQUARE BRACKET','Pe Xa','Common'],
 q{)C}=>[8835,'SUPERSET OF','Sm','Common'],
 q{)I}=>[12311,'RIGHT WHITE LENTICULAR BRACKET','Pe','Common'],
 q{)S}=>[8318,'SUPERSCRIPT RIGHT PARENTHESIS','Pe','Common'],
@@ -83,12 +83,12 @@ q{*5}=>[12445,'HIRAGANA ITERATION MARK','Lm','Hiragana'],
 q{*6}=>[12541,'KATAKANA ITERATION MARK','Lm','Katakana'],
 q{*>}=>[8811,'MUCH GREATER-THAN','Sm','Common'],
 q{*P}=>[8719,'N-ARY PRODUCT','Sm','Common'],
-q{*X}=>[215,'MULTIPLICATION SIGN','Sm','Common'],
+q{*X}=>[215,'MULTIPLICATION SIGN','Sm Xl','Common'],
 q{*_}=>[12293,'IDEOGRAPHIC ITERATION MARK','Lm','Han'],
 q{*s}=>[962,'GREEK SMALL LETTER FINAL SIGMA','Ll','Greek'],
 q{+"}=>[12291,'DITTO MARK','Po','Common'],
 q{++}=>[1600,'ARABIC TATWEEL','Lm','Common'],
-q{+-}=>[177,'PLUS-MINUS SIGN','Sm','Common'],
+q{+-}=>[177,'PLUS-MINUS SIGN','Sm Xl','Common'],
 q{+5}=>[12446,'HIRAGANA VOICED ITERATION MARK','Lm','Hiragana'],
 q{+6}=>[12542,'KATAKANA VOICED ITERATION MARK','Lm','Katakana'],
 q{+S}=>[8314,'SUPERSCRIPT PLUS SIGN','Sm','Common'],
@@ -104,12 +104,12 @@ q{,_}=>[12289,'IDEOGRAPHIC COMMA','Po','Common'],
 q{-!}=>[8593,'UPWARDS ARROW','Sm','Common'],
 q{-)}=>[8715,'CONTAINS AS MEMBER','Sm','Common'],
 q{-+}=>[8723,'MINUS-OR-PLUS SIGN','Sm','Common'],
-q{--}=>[173,'SOFT HYPHEN','Cf','Common'],
+q{--}=>[173,'SOFT HYPHEN','Cf Xl','Common'],
 q{-1}=>[8208,'HYPHEN','Pd','Common'],
 q{-2}=>[8722,'MINUS SIGN','Sm','Common'],
 q{-3}=>[8213,'HORIZONTAL BAR','Pd','Common'],
 q{-6}=>[12540,'KATAKANA-HIRAGANA PROLONGED SOUND MARK','Lm','Common'],
-q{-:}=>[247,'DIVISION SIGN','Sm','Common'],
+q{-:}=>[247,'DIVISION SIGN','Sm Xl','Common'],
 q{->}=>[8594,'RIGHTWARDS ARROW','Sm','Common'],
 q{-?}=>[12316,'WAVE DASH','Pd','Common'],
 q{-L}=>[8735,'RIGHT ANGLE','Sm','Common'],
@@ -119,8 +119,8 @@ q{-S}=>[8315,'SUPERSCRIPT MINUS','Sm','Common'],
 q{-T}=>[8869,'UP TACK','Sm','Common'],
 q{-V}=>[8736,'ANGLE','Sm','Common'],
 q{-X}=>[10016,'MALTESE CROSS','So','Common'],
-q{-a}=>[170,'FEMININE ORDINAL INDICATOR','Ll','Latin'],
-q{-o}=>[186,'MASCULINE ORDINAL INDICATOR','Ll','Latin'],
+q{-a}=>[170,'FEMININE ORDINAL INDICATOR','Ll Xl','Latin'],
+q{-o}=>[186,'MASCULINE ORDINAL INDICATOR','Ll Xl','Latin'],
 q{-s}=>[8331,'SUBSCRIPT MINUS','Sm','Common'],
 q{-v}=>[8595,'DOWNWARDS ARROW','Sm','Common'],
 q{..}=>[8229,'TWO DOT LEADER','Po','Common'],
@@ -128,13 +128,13 @@ q{.3}=>[8943,'MIDLINE HORIZONTAL ELLIPSIS','Sm','Common'],
 q{.6}=>[12539,'KATAKANA MIDDLE DOT','Po','Common'],
 q{.9}=>[8218,'SINGLE LOW-9 QUOTATION MARK','Ps','Common'],
 q{.:}=>[8756,'THEREFORE','Sm','Common'],
-q{.M}=>[183,'MIDDLE DOT','Po','Common'],
+q{.M}=>[183,'MIDDLE DOT','Po Xl','Common'],
 q{.P}=>[8901,'DOT OPERATOR','Sm','Common'],
 q{.S}=>[9617,'LIGHT SHADE','So','Common'],
 q{._}=>[12290,'IDEOGRAPHIC FULL STOP','Po','Common'],
 q{/+}=>[1614,'ARABIC FATHA','Mn','Inherited'],
 q{/-}=>[8224,'DAGGER','Po','Common'],
-q{//}=>[92,'REVERSE SOLIDUS','Po','Common'],
+q{//}=>[92,'REVERSE SOLIDUS','Po Xa','Common'],
 q{/0}=>[8709,'EMPTY SET','Sm','Common'],
 q{/=}=>[8225,'DOUBLE DAGGER','Po','Common'],
 q{/>}=>[9002,'RIGHT-POINTING ANGLE BRACKET','Pe','Common'],
@@ -161,9 +161,9 @@ q{1"}=>[8245,'REVERSED PRIME','Po','Common'],
 q{1'}=>[8242,'PRIME','Po','Common'],
 q{1+}=>[1616,'ARABIC KASRA','Mn','Inherited'],
 q{1.}=>[9352,'DIGIT ONE FULL STOP','No','Common'],
-q{12}=>[189,'VULGAR FRACTION ONE HALF','No','Common'],
+q{12}=>[189,'VULGAR FRACTION ONE HALF','No Xl','Common'],
 q{13}=>[8531,'VULGAR FRACTION ONE THIRD','No','Common'],
-q{14}=>[188,'VULGAR FRACTION ONE QUARTER','No','Common'],
+q{14}=>[188,'VULGAR FRACTION ONE QUARTER','No Xl','Common'],
 q{15}=>[8533,'VULGAR FRACTION ONE FIFTH','No','Common'],
 q{16}=>[8537,'VULGAR FRACTION ONE SIXTH','No','Common'],
 q{18}=>[8539,'VULGAR FRACTION ONE EIGHTH','No','Common'],
@@ -171,7 +171,7 @@ q{1H}=>[8202,'HAIR SPACE','Zs','Common'],
 q{1M}=>[8195,'EM SPACE','Zs','Common'],
 q{1N}=>[8194,'EN SPACE','Zs','Common'],
 q{1R}=>[8544,'ROMAN NUMERAL ONE','Nl','Common'],
-q{1S}=>[185,'SUPERSCRIPT ONE','No','Common'],
+q{1S}=>[185,'SUPERSCRIPT ONE','No Xl','Common'],
 q{1T}=>[8201,'THIN SPACE','Zs','Common'],
 q{1a}=>[1777,'EXTENDED ARABIC-INDIC DIGIT ONE','Nd','Arabic'],
 q{1c}=>[12832,'PARENTHESIZED IDEOGRAPH ONE','No','Common'],
@@ -185,7 +185,7 @@ q{2.}=>[9353,'DIGIT TWO FULL STOP','No','Common'],
 q{23}=>[8532,'VULGAR FRACTION TWO THIRDS','No','Common'],
 q{25}=>[8534,'VULGAR FRACTION TWO FIFTHS','No','Common'],
 q{2R}=>[8545,'ROMAN NUMERAL TWO','Nl','Common'],
-q{2S}=>[178,'SUPERSCRIPT TWO','No','Common'],
+q{2S}=>[178,'SUPERSCRIPT TWO','No Xl','Common'],
 q{2a}=>[1778,'EXTENDED ARABIC-INDIC DIGIT TWO','Nd','Arabic'],
 q{2c}=>[12833,'PARENTHESIZED IDEOGRAPH TWO','No','Common'],
 q{2h}=>[9282,'OCR FORK','So','Common'],
@@ -199,12 +199,12 @@ q{3+}=>[1617,'ARABIC SHADDA','Mn','Inherited'],
 q{3-}=>[9476,'BOX DRAWINGS LIGHT TRIPLE DASH HORIZONTAL','So','Common'],
 q{3.}=>[9354,'DIGIT THREE FULL STOP','No','Common'],
 q{3/}=>[9479,'BOX DRAWINGS HEAVY TRIPLE DASH VERTICAL','So','Common'],
-q{34}=>[190,'VULGAR FRACTION THREE QUARTERS','No','Common'],
+q{34}=>[190,'VULGAR FRACTION THREE QUARTERS','No Xl','Common'],
 q{35}=>[8535,'VULGAR FRACTION THREE FIFTHS','No','Common'],
 q{38}=>[8540,'VULGAR FRACTION THREE EIGHTHS','No','Common'],
 q{3M}=>[8196,'THREE-PER-EM SPACE','Zs','Common'],
 q{3R}=>[8546,'ROMAN NUMERAL THREE','Nl','Common'],
-q{3S}=>[179,'SUPERSCRIPT THREE','No','Common'],
+q{3S}=>[179,'SUPERSCRIPT THREE','No Xl','Common'],
 q{3_}=>[9477,'BOX DRAWINGS HEAVY TRIPLE DASH HORIZONTAL','So','Common'],
 q{3a}=>[1779,'EXTENDED ARABIC-INDIC DIGIT THREE','Nd','Arabic'],
 q{3c}=>[12834,'PARENTHESIZED IDEOGRAPH THREE','No','Common'],
@@ -286,14 +286,14 @@ q{;S}=>[703,'MODIFIER LETTER LEFT HALF RING','Lm','Common'],
 q{;_}=>[12294,'IDEOGRAPHIC CLOSING MARK','Lo','Common'],
 q{<"}=>[12302,'LEFT WHITE CORNER BRACKET','Ps','Common'],
 q{<'}=>[12300,'LEFT CORNER BRACKET','Ps','Common'],
-q{<(}=>[91,'LEFT SQUARE BRACKET','Ps','Common'],
+q{<(}=>[91,'LEFT SQUARE BRACKET','Ps Xa','Common'],
 q{<*}=>[8810,'MUCH LESS-THAN','Sm','Common'],
 q{<+}=>[12298,'LEFT DOUBLE ANGLE BRACKET','Ps','Common'],
 q{<-}=>[8592,'LEFTWARDS ARROW','Sm','Common'],
 q{</}=>[9001,'LEFT-POINTING ANGLE BRACKET','Ps','Common'],
 q{<1}=>[8249,'SINGLE LEFT-POINTING ANGLE QUOTATION MARK','Pi','Common'],
 q{<7}=>[8968,'LEFT CEILING','Sm','Common'],
-q{<<}=>[171,'LEFT-POINTING DOUBLE ANGLE QUOTATION MARK','Pi','Common'],
+q{<<}=>[171,'LEFT-POINTING DOUBLE ANGLE QUOTATION MARK','Pi Xl','Common'],
 q{<=}=>[8656,'LEFTWARDS DOUBLE ARROW','So','Common'],
 q{<>}=>[8596,'LEFT RIGHT ARROW','Sm','Common'],
 q{<H}=>[9756,'WHITE LEFT POINTING INDEX','So','Common'],
@@ -316,7 +316,7 @@ q{>+}=>[12299,'RIGHT DOUBLE ANGLE BRACKET','Pe','Common'],
 q{>1}=>[8250,'SINGLE RIGHT-POINTING ANGLE QUOTATION MARK','Pf','Common'],
 q{>7}=>[8969,'RIGHT CEILING','Sm','Common'],
 q{>=}=>[8805,'GREATER-THAN OR EQUAL TO','Sm','Common'],
-q{>>}=>[187,'RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK','Pf','Common'],
+q{>>}=>[187,'RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK','Pf Xl','Common'],
 q{>H}=>[9758,'WHITE RIGHT POINTING INDEX','So','Common'],
 q{>V}=>[57381,'','Co','Common'],
 q{?*}=>[57383,'','Co','Common'],
@@ -328,11 +328,11 @@ q{?2}=>[8776,'ALMOST EQUAL TO','Sm','Common'],
 q{?:}=>[7943,'GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI','Ll','Greek'],
 q{?;}=>[7940,'GREEK SMALL LETTER ALPHA WITH PSILI AND OXIA','Ll','Greek'],
 q{?=}=>[8773,'APPROXIMATELY EQUAL TO','Sm','Common'],
-q{?I}=>[191,'INVERTED QUESTION MARK','Po','Common'],
+q{?I}=>[191,'INVERTED QUESTION MARK','Po Xl','Common'],
 q{?S}=>[9619,'DARK SHADE','So','Common'],
-q{A!}=>[192,'LATIN CAPITAL LETTER A WITH GRAVE','Lu','Latin'],
+q{A!}=>[192,'LATIN CAPITAL LETTER A WITH GRAVE','Lu Xl','Latin'],
 q{A%}=>[902,'GREEK CAPITAL LETTER ALPHA WITH TONOS','Lu','Greek'],
-q{A'}=>[193,'LATIN CAPITAL LETTER A WITH ACUTE','Lu','Latin'],
+q{A'}=>[193,'LATIN CAPITAL LETTER A WITH ACUTE','Lu Xl','Latin'],
 q{A(}=>[258,'LATIN CAPITAL LETTER A WITH BREVE','Lu','Latin'],
 q{A*}=>[913,'GREEK CAPITAL LETTER ALPHA','Lu','Greek'],
 q{A+}=>[1488,'HEBREW LETTER ALEF','Lo','Hebrew'],
@@ -343,28 +343,28 @@ q{A3}=>[482,'LATIN CAPITAL LETTER AE WITH MACRON','Lu','Latin'],
 q{A5}=>[12353,'HIRAGANA LETTER SMALL A','Lo','Hiragana'],
 q{A6}=>[12450,'KATAKANA LETTER A','Lo','Katakana'],
 q{A7}=>[480,'LATIN CAPITAL LETTER A WITH DOT ABOVE AND MACRON','Lu','Latin'],
-q{A:}=>[196,'LATIN CAPITAL LETTER A WITH DIAERESIS','Lu','Latin'],
+q{A:}=>[196,'LATIN CAPITAL LETTER A WITH DIAERESIS','Lu Xl','Latin'],
 q{A;}=>[260,'LATIN CAPITAL LETTER A WITH OGONEK','Lu','Latin'],
 q{A<}=>[461,'LATIN CAPITAL LETTER A WITH CARON','Lu','Latin'],
 q{A=}=>[1040,'CYRILLIC CAPITAL LETTER A','Lu','Cyrillic'],
-q{A>}=>[194,'LATIN CAPITAL LETTER A WITH CIRCUMFLEX','Lu','Latin'],
-q{A?}=>[195,'LATIN CAPITAL LETTER A WITH TILDE','Lu','Latin'],
-q{AA}=>[197,'LATIN CAPITAL LETTER A WITH RING ABOVE','Lu','Latin'],
-q{AC}=>[159,'<control>','Cc','Common'],
-q{AE}=>[198,'LATIN CAPITAL LETTER AE','Lu','Latin'],
-q{AK}=>[6,'<control>','Cc','Common'],
+q{A>}=>[194,'LATIN CAPITAL LETTER A WITH CIRCUMFLEX','Lu Xl','Latin'],
+q{A?}=>[195,'LATIN CAPITAL LETTER A WITH TILDE','Lu Xl','Latin'],
+q{AA}=>[197,'LATIN CAPITAL LETTER A WITH RING ABOVE','Lu Xl','Latin'],
+q{AC}=>[159,'<control>','Cc Xl','Common'],
+q{AE}=>[198,'LATIN CAPITAL LETTER AE','Lu Xl','Latin'],
+q{AK}=>[6,'<control>','Cc Xa','Common'],
 q{AN}=>[8743,'LOGICAL AND','Sm','Common'],
 q{AO}=>[8491,'ANGSTROM SIGN','Lu','Latin'],
-q{At}=>[64,'COMMERCIAL AT','Po','Common'],
+q{At}=>[64,'COMMERCIAL AT','Po Xa','Common'],
 q{B*}=>[914,'GREEK CAPITAL LETTER BETA','Lu','Greek'],
 q{B+}=>[1489,'HEBREW LETTER BET','Lo','Hebrew'],
 q{B.}=>[7682,'LATIN CAPITAL LETTER B WITH DOT ABOVE','Lu','Latin'],
 q{B=}=>[1041,'CYRILLIC CAPITAL LETTER BE','Lu','Cyrillic'],
-q{BB}=>[166,'BROKEN BAR','So','Common'],
+q{BB}=>[166,'BROKEN BAR','So Xl','Common'],
 q{BD}=>[9586,'BOX DRAWINGS LIGHT DIAGONAL UPPER LEFT TO LOWER RIGHT','So','Common'],
-q{BH}=>[130,'<control>','Cc','Common'],
-q{BL}=>[7,'<control>','Cc','Common'],
-q{BS}=>[8,'<control>','Cc','Common'],
+q{BH}=>[130,'<control>','Cc Xl','Common'],
+q{BL}=>[7,'<control>','Cc Xa','Common'],
+q{BS}=>[8,'<control>','Cc Xa','Common'],
 q{B_}=>[7686,'LATIN CAPITAL LETTER B WITH LINE BELOW','Lu','Latin'],
 q{Ba}=>[12496,'KATAKANA LETTER BA','Lo','Katakana'],
 q{Bd}=>[9699,'BLACK LOWER LEFT TRIANGLE','So','Common'],
@@ -375,45 +375,45 @@ q{Bu}=>[12502,'KATAKANA LETTER BU','Lo','Katakana'],
 q{C%}=>[1063,'CYRILLIC CAPITAL LETTER CHE','Lu','Cyrillic'],
 q{C'}=>[262,'LATIN CAPITAL LETTER C WITH ACUTE','Lu','Latin'],
 q{C*}=>[926,'GREEK CAPITAL LETTER XI','Lu','Greek'],
-q{C,}=>[199,'LATIN CAPITAL LETTER C WITH CEDILLA','Lu','Latin'],
+q{C,}=>[199,'LATIN CAPITAL LETTER C WITH CEDILLA','Lu Xl','Latin'],
 q{C.}=>[266,'LATIN CAPITAL LETTER C WITH DOT ABOVE','Lu','Latin'],
 q{C3}=>[1152,'CYRILLIC CAPITAL LETTER KOPPA','Lu','Cyrillic'],
 q{C<}=>[268,'LATIN CAPITAL LETTER C WITH CARON','Lu','Latin'],
 q{C=}=>[1062,'CYRILLIC CAPITAL LETTER TSE','Lu','Cyrillic'],
 q{C>}=>[264,'LATIN CAPITAL LETTER C WITH CIRCUMFLEX','Lu','Latin'],
-q{CC}=>[148,'<control>','Cc','Common'],
+q{CC}=>[148,'<control>','Cc Xl','Common'],
 q{CG}=>[8766,'INVERTED LAZY S','Sm','Common'],
-q{CI}=>[155,'<control>','Cc','Common'],
-q{CN}=>[24,'<control>','Cc','Common'],
-q{CR}=>[13,'<control>','Cc','Common'],
+q{CI}=>[155,'<control>','Cc Xl','Common'],
+q{CN}=>[24,'<control>','Cc Xa','Common'],
+q{CR}=>[13,'<control>','Cc Xa','Common'],
 q{Ca}=>[8248,'CARET','Po','Common'],
 q{Ci}=>[57372,'','Co','Common'],
-q{Co}=>[169,'COPYRIGHT SIGN','So','Common'],
-q{Ct}=>[162,'CENT SIGN','Sc','Common'],
-q{Cu}=>[164,'CURRENCY SIGN','Sc','Common'],
+q{Co}=>[169,'COPYRIGHT SIGN','So Xl','Common'],
+q{Ct}=>[162,'CENT SIGN','Sc Xl','Common'],
+q{Cu}=>[164,'CURRENCY SIGN','Sc Xl','Common'],
 q{D%}=>[1026,'CYRILLIC CAPITAL LETTER DJE','Lu','Cyrillic'],
 q{D*}=>[916,'GREEK CAPITAL LETTER DELTA','Lu','Greek'],
 q{D+}=>[1491,'HEBREW LETTER DALET','Lo','Hebrew'],
 q{D,}=>[7696,'LATIN CAPITAL LETTER D WITH CEDILLA','Lu','Latin'],
-q{D-}=>[208,'LATIN CAPITAL LETTER ETH','Lu','Latin'],
+q{D-}=>[208,'LATIN CAPITAL LETTER ETH','Lu Xl','Latin'],
 q{D.}=>[7690,'LATIN CAPITAL LETTER D WITH DOT ABOVE','Lu','Latin'],
 q{D/}=>[272,'LATIN CAPITAL LETTER D WITH STROKE','Lu','Latin'],
-q{D1}=>[17,'<control>','Cc','Common'],
-q{D2}=>[18,'<control>','Cc','Common'],
-q{D3}=>[19,'<control>','Cc','Common'],
-q{D4}=>[20,'<control>','Cc','Common'],
+q{D1}=>[17,'<control>','Cc Xa','Common'],
+q{D2}=>[18,'<control>','Cc Xa','Common'],
+q{D3}=>[19,'<control>','Cc Xa','Common'],
+q{D4}=>[20,'<control>','Cc Xa','Common'],
 q{D<}=>[270,'LATIN CAPITAL LETTER D WITH CARON','Lu','Latin'],
 q{D=}=>[1044,'CYRILLIC CAPITAL LETTER DE','Lu','Cyrillic'],
-q{DC}=>[144,'<control>','Cc','Common'],
+q{DC}=>[144,'<control>','Cc Xl','Common'],
 q{DE}=>[8710,'INCREMENT','Sm','Common'],
-q{DG}=>[176,'DEGREE SIGN','So','Common'],
+q{DG}=>[176,'DEGREE SIGN','So Xl','Common'],
 q{DH}=>[9523,'BOX DRAWINGS HEAVY DOWN AND HORIZONTAL','So','Common'],
 q{DI}=>[8748,'DOUBLE INTEGRAL','Sm','Common'],
-q{DL}=>[16,'<control>','Cc','Common'],
-q{DO}=>[36,'DOLLAR SIGN','Sc','Common'],
+q{DL}=>[16,'<control>','Cc Xa','Common'],
+q{DO}=>[36,'DOLLAR SIGN','Sc Xa','Common'],
 q{DR}=>[9487,'BOX DRAWINGS HEAVY DOWN AND RIGHT','So','Common'],
 q{DS}=>[1029,'CYRILLIC CAPITAL LETTER DZE','Lu','Cyrillic'],
-q{DT}=>[127,'<control>','Cc','Common'],
+q{DT}=>[127,'<control>','Cc Xa','Common'],
 q{DZ}=>[1039,'CYRILLIC CAPITAL LETTER DZHE','Lu','Cyrillic'],
 q{D_}=>[7694,'LATIN CAPITAL LETTER D WITH LINE BELOW','Lu','Latin'],
 q{Da}=>[12480,'KATAKANA LETTER DA','Lo','Katakana'],
@@ -427,9 +427,9 @@ q{Dr}=>[9486,'BOX DRAWINGS DOWN HEAVY AND RIGHT LIGHT','So','Common'],
 q{Dt}=>[9660,'BLACK DOWN-POINTING TRIANGLE','So','Common'],
 q{Du}=>[12485,'KATAKANA LETTER DU','Lo','Katakana'],
 q{Dw}=>[9671,'WHITE DIAMOND','So','Common'],
-q{E!}=>[200,'LATIN CAPITAL LETTER E WITH GRAVE','Lu','Latin'],
+q{E!}=>[200,'LATIN CAPITAL LETTER E WITH GRAVE','Lu Xl','Latin'],
 q{E%}=>[904,'GREEK CAPITAL LETTER EPSILON WITH TONOS','Lu','Greek'],
-q{E'}=>[201,'LATIN CAPITAL LETTER E WITH ACUTE','Lu','Latin'],
+q{E'}=>[201,'LATIN CAPITAL LETTER E WITH ACUTE','Lu Xl','Latin'],
 q{E(}=>[276,'LATIN CAPITAL LETTER E WITH BREVE','Lu','Latin'],
 q{E*}=>[917,'GREEK CAPITAL LETTER EPSILON','Lu','Greek'],
 q{E+}=>[1506,'HEBREW LETTER AYIN','Lo','Hebrew'],
@@ -438,21 +438,21 @@ q{E.}=>[278,'LATIN CAPITAL LETTER E WITH DOT ABOVE','Lu','Latin'],
 q{E2}=>[7866,'LATIN CAPITAL LETTER E WITH HOOK ABOVE','Lu','Latin'],
 q{E5}=>[12359,'HIRAGANA LETTER SMALL E','Lo','Hiragana'],
 q{E6}=>[12456,'KATAKANA LETTER E','Lo','Katakana'],
-q{E:}=>[203,'LATIN CAPITAL LETTER E WITH DIAERESIS','Lu','Latin'],
+q{E:}=>[203,'LATIN CAPITAL LETTER E WITH DIAERESIS','Lu Xl','Latin'],
 q{E;}=>[280,'LATIN CAPITAL LETTER E WITH OGONEK','Lu','Latin'],
 q{E<}=>[282,'LATIN CAPITAL LETTER E WITH CARON','Lu','Latin'],
 q{E=}=>[1045,'CYRILLIC CAPITAL LETTER IE','Lu','Cyrillic'],
-q{E>}=>[202,'LATIN CAPITAL LETTER E WITH CIRCUMFLEX','Lu','Latin'],
+q{E>}=>[202,'LATIN CAPITAL LETTER E WITH CIRCUMFLEX','Lu Xl','Latin'],
 q{E?}=>[7868,'LATIN CAPITAL LETTER E WITH TILDE','Lu','Latin'],
-q{EB}=>[23,'<control>','Cc','Common'],
-q{EC}=>[27,'<control>','Cc','Common'],
+q{EB}=>[23,'<control>','Cc Xa','Common'],
+q{EC}=>[27,'<control>','Cc Xa','Common'],
 q{ED}=>[439,'LATIN CAPITAL LETTER EZH','Lu','Latin'],
-q{EG}=>[151,'<control>','Cc','Common'],
-q{EM}=>[25,'<control>','Cc','Common'],
-q{EQ}=>[5,'<control>','Cc','Common'],
-q{ES}=>[135,'<control>','Cc','Common'],
-q{ET}=>[4,'<control>','Cc','Common'],
-q{EX}=>[3,'<control>','Cc','Common'],
+q{EG}=>[151,'<control>','Cc Xl','Common'],
+q{EM}=>[25,'<control>','Cc Xa','Common'],
+q{EQ}=>[5,'<control>','Cc Xa','Common'],
+q{ES}=>[135,'<control>','Cc Xl','Common'],
+q{ET}=>[4,'<control>','Cc Xa','Common'],
+q{EX}=>[3,'<control>','Cc Xa','Common'],
 q{EZ}=>[494,'LATIN CAPITAL LETTER EZH WITH CARON','Lu','Latin'],
 q{Eh}=>[8962,'HOUSE','So','Common'],
 q{F*}=>[934,'GREEK CAPITAL LETTER PHI','Lu','Greek'],
@@ -462,8 +462,8 @@ q{F=}=>[1060,'CYRILLIC CAPITAL LETTER EF','Lu','Cyrillic'],
 q{FA}=>[8704,'FOR ALL','Sm','Common'],
 q{FB}=>[9608,'FULL BLOCK','So','Common'],
 q{FD}=>[9585,'BOX DRAWINGS LIGHT DIAGONAL UPPER RIGHT TO LOWER LEFT','So','Common'],
-q{FF}=>[12,'<control>','Cc','Common'],
-q{FS}=>[28,'<control>','Cc','Common'],
+q{FF}=>[12,'<control>','Cc Xa','Common'],
+q{FS}=>[28,'<control>','Cc Xa','Common'],
 q{Fd}=>[9698,'BLACK LOWER RIGHT TRIANGLE','So','Common'],
 q{Fl}=>[57379,'','Co','Common'],
 q{Fm}=>[9792,'FEMALE SIGN','So','Common'],
@@ -480,9 +480,9 @@ q{G3}=>[1168,'CYRILLIC CAPITAL LETTER GHE WITH UPTURN','Lu','Cyrillic'],
 q{G<}=>[486,'LATIN CAPITAL LETTER G WITH CARON','Lu','Latin'],
 q{G=}=>[1043,'CYRILLIC CAPITAL LETTER GHE','Lu','Cyrillic'],
 q{G>}=>[284,'LATIN CAPITAL LETTER G WITH CIRCUMFLEX','Lu','Latin'],
-q{GC}=>[153,'<control>','Cc','Common'],
+q{GC}=>[153,'<control>','Cc Xl','Common'],
 q{GF}=>[57380,'','Co','Common'],
-q{GS}=>[29,'<control>','Cc','Common'],
+q{GS}=>[29,'<control>','Cc Xa','Common'],
 q{Ga}=>[12460,'KATAKANA LETTER GA','Lo','Katakana'],
 q{Ge}=>[12466,'KATAKANA LETTER GE','Lo','Katakana'],
 q{Gi}=>[12462,'KATAKANA LETTER GI','Lo','Katakana'],
@@ -499,18 +499,18 @@ q{H=}=>[1061,'CYRILLIC CAPITAL LETTER HA','Lu','Cyrillic'],
 q{H>}=>[292,'LATIN CAPITAL LETTER H WITH CIRCUMFLEX','Lu','Latin'],
 q{HH}=>[9473,'BOX DRAWINGS HEAVY HORIZONTAL','So','Common'],
 q{HI}=>[8787,'IMAGE OF OR APPROXIMATELY EQUAL TO','Sm','Common'],
-q{HJ}=>[137,'<control>','Cc','Common'],
-q{HO}=>[129,'<control>','Cc','Common'],
-q{HS}=>[136,'<control>','Cc','Common'],
-q{HT}=>[9,'<control>','Cc','Common'],
+q{HJ}=>[137,'<control>','Cc Xl','Common'],
+q{HO}=>[129,'<control>','Cc Xl','Common'],
+q{HS}=>[136,'<control>','Cc Xl','Common'],
+q{HT}=>[9,'<control>','Cc Xa','Common'],
 q{Ha}=>[12495,'KATAKANA LETTER HA','Lo','Katakana'],
 q{He}=>[12504,'KATAKANA LETTER HE','Lo','Katakana'],
 q{Hi}=>[12498,'KATAKANA LETTER HI','Lo','Katakana'],
 q{Ho}=>[12507,'KATAKANA LETTER HO','Lo','Katakana'],
 q{Hu}=>[12501,'KATAKANA LETTER HU','Lo','Katakana'],
-q{I!}=>[204,'LATIN CAPITAL LETTER I WITH GRAVE','Lu','Latin'],
+q{I!}=>[204,'LATIN CAPITAL LETTER I WITH GRAVE','Lu Xl','Latin'],
 q{I%}=>[906,'GREEK CAPITAL LETTER IOTA WITH TONOS','Lu','Greek'],
-q{I'}=>[205,'LATIN CAPITAL LETTER I WITH ACUTE','Lu','Latin'],
+q{I'}=>[205,'LATIN CAPITAL LETTER I WITH ACUTE','Lu Xl','Latin'],
 q{I(}=>[300,'LATIN CAPITAL LETTER I WITH BREVE','Lu','Latin'],
 q{I*}=>[921,'GREEK CAPITAL LETTER IOTA','Lu','Greek'],
 q{I-}=>[298,'LATIN CAPITAL LETTER I WITH MACRON','Lu','Latin'],
@@ -518,16 +518,16 @@ q{I.}=>[304,'LATIN CAPITAL LETTER I WITH DOT ABOVE','Lu','Latin'],
 q{I2}=>[7880,'LATIN CAPITAL LETTER I WITH HOOK ABOVE','Lu','Latin'],
 q{I5}=>[12355,'HIRAGANA LETTER SMALL I','Lo','Hiragana'],
 q{I6}=>[12452,'KATAKANA LETTER I','Lo','Katakana'],
-q{I:}=>[207,'LATIN CAPITAL LETTER I WITH DIAERESIS','Lu','Latin'],
+q{I:}=>[207,'LATIN CAPITAL LETTER I WITH DIAERESIS','Lu Xl','Latin'],
 q{I;}=>[302,'LATIN CAPITAL LETTER I WITH OGONEK','Lu','Latin'],
 q{I<}=>[463,'LATIN CAPITAL LETTER I WITH CARON','Lu','Latin'],
 q{I=}=>[1048,'CYRILLIC CAPITAL LETTER I','Lu','Cyrillic'],
-q{I>}=>[206,'LATIN CAPITAL LETTER I WITH CIRCUMFLEX','Lu','Latin'],
+q{I>}=>[206,'LATIN CAPITAL LETTER I WITH CIRCUMFLEX','Lu Xl','Latin'],
 q{I?}=>[296,'LATIN CAPITAL LETTER I WITH TILDE','Lu','Latin'],
 q{IE}=>[1028,'CYRILLIC CAPITAL LETTER UKRAINIAN IE','Lu','Cyrillic'],
 q{II}=>[1030,'CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I','Lu','Cyrillic'],
 q{IJ}=>[306,'LATIN CAPITAL LIGATURE IJ','Lu','Latin'],
-q{IN}=>[132,'<control>','Cc','Common'],
+q{IN}=>[132,'<control>','Cc Xl','Common'],
 q{IO}=>[1025,'CYRILLIC CAPITAL LETTER IO','Lu','Cyrillic'],
 q{IS}=>[12288,'IDEOGRAPHIC SPACE','Zs','Common'],
 q{Ic}=>[9689,'INVERSE WHITE CIRCLE','So','Common'],
@@ -571,7 +571,7 @@ q{L<}=>[317,'LATIN CAPITAL LETTER L WITH CARON','Lu','Latin'],
 q{L=}=>[1051,'CYRILLIC CAPITAL LETTER EL','Lu','Cyrillic'],
 q{LB}=>[9604,'LOWER HALF BLOCK','So','Common'],
 q{LD}=>[9491,'BOX DRAWINGS HEAVY DOWN AND LEFT','So','Common'],
-q{LF}=>[10,'<control>','Cc','Common'],
+q{LF}=>[10,'<control>','Cc Xa','Common'],
 q{LJ}=>[1033,'CYRILLIC CAPITAL LETTER LJE','Lu','Cyrillic'],
 q{LZ}=>[9674,'LOZENGE','So','Common'],
 q{L_}=>[7738,'LATIN CAPITAL LETTER L WITH LINE BELOW','Lu','Latin'],
@@ -585,7 +585,7 @@ q{M2}=>[9835,'BEAMED EIGHTH NOTES','So','Common'],
 q{M3}=>[988,'GREEK LETTER DIGAMMA','Lu','Greek'],
 q{M8}=>[9834,'EIGHTH NOTE','So','Common'],
 q{M=}=>[1052,'CYRILLIC CAPITAL LETTER EM','Lu','Cyrillic'],
-q{MW}=>[149,'<control>','Cc','Common'],
+q{MW}=>[149,'<control>','Cc Xl','Common'],
 q{MX}=>[9839,'MUSIC SHARP SIGN','Sm','Common'],
 q{Ma}=>[12510,'KATAKANA LETTER MA','Lo','Katakana'],
 q{Mb}=>[9837,'MUSIC FLAT SIGN','So','Common'],
@@ -596,7 +596,7 @@ q{Ml}=>[9794,'MALE SIGN','So','Common'],
 q{Mo}=>[12514,'KATAKANA LETTER MO','Lo','Katakana'],
 q{Mu}=>[12512,'KATAKANA LETTER MU','Lo','Katakana'],
 q{Mx}=>[9838,'MUSIC NATURAL SIGN','So','Common'],
-q{My}=>[181,'MICRO SIGN','Ll','Common'],
+q{My}=>[181,'MICRO SIGN','Ll Xl','Common'],
 q{N%}=>[1503,'HEBREW LETTER FINAL NUN','Lo','Hebrew'],
 q{N'}=>[323,'LATIN CAPITAL LETTER N WITH ACUTE','Lu','Latin'],
 q{N*}=>[925,'GREEK CAPITAL LETTER NU','Lu','Greek'],
@@ -607,45 +607,45 @@ q{N0}=>[8470,'NUMERO SIGN','So','Common'],
 q{N6}=>[12531,'KATAKANA LETTER N','Lo','Katakana'],
 q{N<}=>[327,'LATIN CAPITAL LETTER N WITH CARON','Lu','Latin'],
 q{N=}=>[1053,'CYRILLIC CAPITAL LETTER EN','Lu','Cyrillic'],
-q{N?}=>[209,'LATIN CAPITAL LETTER N WITH TILDE','Lu','Latin'],
+q{N?}=>[209,'LATIN CAPITAL LETTER N WITH TILDE','Lu Xl','Latin'],
 q{NB}=>[8711,'NABLA','Sm','Common'],
 q{NG}=>[330,'LATIN CAPITAL LETTER ENG','Lu','Latin'],
-q{NH}=>[131,'<control>','Cc','Common'],
+q{NH}=>[131,'<control>','Cc Xl','Common'],
 q{NI}=>[8976,'REVERSED NOT SIGN','So','Common'],
 q{NJ}=>[1034,'CYRILLIC CAPITAL LETTER NJE','Lu','Cyrillic'],
-q{NK}=>[21,'<control>','Cc','Common'],
-q{NL}=>[133,'<control>','Cc','Common'],
-q{NO}=>[172,'NOT SIGN','Sm','Common'],
-q{NS}=>[160,'NO-BREAK SPACE','Zs','Common'],
-q{NU}=>[0,'<control>','Cc','Common'],
+q{NK}=>[21,'<control>','Cc Xa','Common'],
+q{NL}=>[133,'<control>','Cc Xl','Common'],
+q{NO}=>[172,'NOT SIGN','Sm Xl','Common'],
+q{NS}=>[160,'NO-BREAK SPACE','Zs Xl','Common'],
+q{NU}=>[0,'<control>','Cc Xa','Common'],
 q{N_}=>[7752,'LATIN CAPITAL LETTER N WITH LINE BELOW','Lu','Latin'],
 q{Na}=>[12490,'KATAKANA LETTER NA','Lo','Katakana'],
-q{Nb}=>[35,'NUMBER SIGN','Po','Common'],
+q{Nb}=>[35,'NUMBER SIGN','Po Xa','Common'],
 q{Ne}=>[12493,'KATAKANA LETTER NE','Lo','Katakana'],
 q{Ni}=>[12491,'KATAKANA LETTER NI','Lo','Katakana'],
 q{No}=>[12494,'KATAKANA LETTER NO','Lo','Katakana'],
 q{Nu}=>[12492,'KATAKANA LETTER NU','Lo','Katakana'],
-q{O!}=>[210,'LATIN CAPITAL LETTER O WITH GRAVE','Lu','Latin'],
+q{O!}=>[210,'LATIN CAPITAL LETTER O WITH GRAVE','Lu Xl','Latin'],
 q{O"}=>[336,'LATIN CAPITAL LETTER O WITH DOUBLE ACUTE','Lu','Latin'],
 q{O%}=>[908,'GREEK CAPITAL LETTER OMICRON WITH TONOS','Lu','Greek'],
-q{O'}=>[211,'LATIN CAPITAL LETTER O WITH ACUTE','Lu','Latin'],
+q{O'}=>[211,'LATIN CAPITAL LETTER O WITH ACUTE','Lu Xl','Latin'],
 q{O(}=>[334,'LATIN CAPITAL LETTER O WITH BREVE','Lu','Latin'],
 q{O*}=>[927,'GREEK CAPITAL LETTER OMICRON','Lu','Greek'],
 q{O-}=>[332,'LATIN CAPITAL LETTER O WITH MACRON','Lu','Latin'],
-q{O/}=>[216,'LATIN CAPITAL LETTER O WITH STROKE','Lu','Latin'],
+q{O/}=>[216,'LATIN CAPITAL LETTER O WITH STROKE','Lu Xl','Latin'],
 q{O1}=>[492,'LATIN CAPITAL LETTER O WITH OGONEK AND MACRON','Lu','Latin'],
 q{O2}=>[7886,'LATIN CAPITAL LETTER O WITH HOOK ABOVE','Lu','Latin'],
 q{O3}=>[1130,'CYRILLIC CAPITAL LETTER BIG YUS','Lu','Cyrillic'],
 q{O5}=>[12361,'HIRAGANA LETTER SMALL O','Lo','Hiragana'],
 q{O6}=>[12458,'KATAKANA LETTER O','Lo','Katakana'],
 q{O9}=>[416,'LATIN CAPITAL LETTER O WITH HORN','Lu','Latin'],
-q{O:}=>[214,'LATIN CAPITAL LETTER O WITH DIAERESIS','Lu','Latin'],
+q{O:}=>[214,'LATIN CAPITAL LETTER O WITH DIAERESIS','Lu Xl','Latin'],
 q{O;}=>[490,'LATIN CAPITAL LETTER O WITH OGONEK','Lu','Latin'],
 q{O<}=>[465,'LATIN CAPITAL LETTER O WITH CARON','Lu','Latin'],
 q{O=}=>[1054,'CYRILLIC CAPITAL LETTER O','Lu','Cyrillic'],
-q{O>}=>[212,'LATIN CAPITAL LETTER O WITH CIRCUMFLEX','Lu','Latin'],
-q{O?}=>[213,'LATIN CAPITAL LETTER O WITH TILDE','Lu','Latin'],
-q{OC}=>[157,'<control>','Cc','Common'],
+q{O>}=>[212,'LATIN CAPITAL LETTER O WITH CIRCUMFLEX','Lu Xl','Latin'],
+q{O?}=>[213,'LATIN CAPITAL LETTER O WITH TILDE','Lu Xl','Latin'],
+q{OC}=>[157,'<control>','Cc Xl','Common'],
 q{OE}=>[338,'LATIN CAPITAL LIGATURE OE','Lu','Latin'],
 q{OI}=>[418,'LATIN CAPITAL LETTER OI','Lu','Latin'],
 q{OK}=>[10003,'CHECK MARK','So','Common'],
@@ -659,21 +659,21 @@ q{P'}=>[7764,'LATIN CAPITAL LETTER P WITH ACUTE','Lu','Latin'],
 q{P*}=>[928,'GREEK CAPITAL LETTER PI','Lu','Greek'],
 q{P+}=>[1508,'HEBREW LETTER PE','Lo','Hebrew'],
 q{P.}=>[7766,'LATIN CAPITAL LETTER P WITH DOT ABOVE','Lu','Latin'],
-q{P1}=>[145,'<control>','Cc','Common'],
-q{P2}=>[146,'<control>','Cc','Common'],
+q{P1}=>[145,'<control>','Cc Xl','Common'],
+q{P2}=>[146,'<control>','Cc Xl','Common'],
 q{P3}=>[992,'GREEK LETTER SAMPI','Lu','Greek'],
 q{P=}=>[1055,'CYRILLIC CAPITAL LETTER PE','Lu','Cyrillic'],
-q{PA}=>[128,'<control>','Cc','Common'],
-q{PD}=>[139,'<control>','Cc','Common'],
-q{PI}=>[182,'PILCROW SIGN','So','Common'],
+q{PA}=>[128,'<control>','Cc Xl','Common'],
+q{PD}=>[139,'<control>','Cc Xl','Common'],
+q{PI}=>[182,'PILCROW SIGN','So Xl','Common'],
 q{PL}=>[9664,'BLACK LEFT-POINTING TRIANGLE','So','Common'],
-q{PM}=>[158,'<control>','Cc','Common'],
+q{PM}=>[158,'<control>','Cc Xl','Common'],
 q{PO}=>[8471,'SOUND RECORDING COPYRIGHT','So','Common'],
 q{PP}=>[8741,'PARALLEL TO','Sm','Common'],
 q{PR}=>[9654,'BLACK RIGHT-POINTING TRIANGLE','So','Common'],
-q{PU}=>[140,'<control>','Cc','Common'],
+q{PU}=>[140,'<control>','Cc Xl','Common'],
 q{Pa}=>[12497,'KATAKANA LETTER PA','Lo','Katakana'],
-q{Pd}=>[163,'POUND SIGN','Sc','Common'],
+q{Pd}=>[163,'POUND SIGN','Sc Xl','Common'],
 q{Pe}=>[12506,'KATAKANA LETTER PE','Lo','Katakana'],
 q{Pi}=>[12500,'KATAKANA LETTER PI','Lo','Katakana'],
 q{Po}=>[12509,'KATAKANA LETTER PO','Lo','Katakana'],
@@ -691,10 +691,10 @@ q{R=}=>[1056,'CYRILLIC CAPITAL LETTER ER','Lu','Cyrillic'],
 q{RB}=>[9616,'RIGHT HALF BLOCK','So','Common'],
 q{RF}=>[9636,'SQUARE WITH HORIZONTAL FILL','So','Common'],
 q{RH}=>[9638,'SQUARE WITH ORTHOGONAL CROSSHATCH FILL','So','Common'],
-q{RI}=>[141,'<control>','Cc','Common'],
+q{RI}=>[141,'<control>','Cc Xl','Common'],
 q{RK}=>[9640,'SQUARE WITH UPPER RIGHT TO LOWER LEFT FILL','So','Common'],
 q{RO}=>[9634,'WHITE SQUARE WITH ROUNDED CORNERS','So','Common'],
-q{RS}=>[30,'<control>','Cc','Common'],
+q{RS}=>[30,'<control>','Cc Xa','Common'],
 q{RT}=>[8730,'SQUARE ROOT','Sm','Common'],
 q{RX}=>[9641,'SQUARE WITH DIAGONAL CROSSHATCH FILL','So','Common'],
 q{RY}=>[9637,'SQUARE WITH VERTICAL FILL','So','Common'],
@@ -702,7 +702,7 @@ q{RZ}=>[9639,'SQUARE WITH UPPER LEFT TO LOWER RIGHT FILL','So','Common'],
 q{R_}=>[7774,'LATIN CAPITAL LETTER R WITH LINE BELOW','Lu','Latin'],
 q{Ra}=>[12521,'KATAKANA LETTER RA','Lo','Katakana'],
 q{Re}=>[12524,'KATAKANA LETTER RE','Lo','Katakana'],
-q{Rg}=>[174,'REGISTERED SIGN','So','Common'],
+q{Rg}=>[174,'REGISTERED SIGN','So Xl','Common'],
 q{Ri}=>[12522,'KATAKANA LETTER RI','Lo','Katakana'],
 q{Ro}=>[12525,'KATAKANA LETTER RO','Lo','Katakana'],
 q{Rr}=>[9635,'WHITE SQUARE CONTAINING BLACK SMALL SQUARE','So','Common'],
@@ -714,26 +714,26 @@ q{S*}=>[931,'GREEK CAPITAL LETTER SIGMA','Lu','Greek'],
 q{S+}=>[1505,'HEBREW LETTER SAMEKH','Lo','Hebrew'],
 q{S,}=>[350,'LATIN CAPITAL LETTER S WITH CEDILLA','Lu','Latin'],
 q{S.}=>[7776,'LATIN CAPITAL LETTER S WITH DOT ABOVE','Lu','Latin'],
-q{S2}=>[142,'<control>','Cc','Common'],
-q{S3}=>[143,'<control>','Cc','Common'],
+q{S2}=>[142,'<control>','Cc Xl','Common'],
+q{S3}=>[143,'<control>','Cc Xl','Common'],
 q{S<}=>[352,'LATIN CAPITAL LETTER S WITH CARON','Lu','Latin'],
 q{S=}=>[1057,'CYRILLIC CAPITAL LETTER ES','Lu','Cyrillic'],
 q{S>}=>[348,'LATIN CAPITAL LETTER S WITH CIRCUMFLEX','Lu','Latin'],
-q{SA}=>[134,'<control>','Cc','Common'],
-q{SB}=>[26,'<control>','Cc','Common'],
-q{SC}=>[154,'<control>','Cc','Common'],
-q{SE}=>[167,'SECTION SIGN','So','Common'],
-q{SG}=>[150,'<control>','Cc','Common'],
-q{SH}=>[1,'<control>','Cc','Common'],
-q{SI}=>[15,'<control>','Cc','Common'],
+q{SA}=>[134,'<control>','Cc Xl','Common'],
+q{SB}=>[26,'<control>','Cc Xa','Common'],
+q{SC}=>[154,'<control>','Cc Xl','Common'],
+q{SE}=>[167,'SECTION SIGN','So Xl','Common'],
+q{SG}=>[150,'<control>','Cc Xl','Common'],
+q{SH}=>[1,'<control>','Cc Xa','Common'],
+q{SI}=>[15,'<control>','Cc Xa','Common'],
 q{SM}=>[8480,'SERVICE MARK','So','Common'],
-q{SO}=>[14,'<control>','Cc','Common'],
+q{SO}=>[14,'<control>','Cc Xa','Common'],
 q{SR}=>[9644,'BLACK RECTANGLE','So','Common'],
-q{SS}=>[152,'<control>','Cc','Common'],
-q{ST}=>[156,'<control>','Cc','Common'],
+q{SS}=>[152,'<control>','Cc Xl','Common'],
+q{ST}=>[156,'<control>','Cc Xl','Common'],
 q{SU}=>[9788,'WHITE SUN WITH RAYS','So','Common'],
-q{SX}=>[2,'<control>','Cc','Common'],
-q{SY}=>[22,'<control>','Cc','Common'],
+q{SX}=>[2,'<control>','Cc Xa','Common'],
+q{SY}=>[22,'<control>','Cc Xa','Common'],
 q{Sa}=>[12469,'KATAKANA LETTER SA','Lo','Katakana'],
 q{Sb}=>[8729,'BULLET OPERATOR','Sm','Common'],
 q{Sc}=>[1065,'CYRILLIC CAPITAL LETTER SHCHA','Lu','Cyrillic'],
@@ -753,10 +753,10 @@ q{T<}=>[356,'LATIN CAPITAL LETTER T WITH CARON','Lu','Latin'],
 q{T=}=>[1058,'CYRILLIC CAPITAL LETTER TE','Lu','Cyrillic'],
 q{TB}=>[9600,'UPPER HALF BLOCK','So','Common'],
 q{TE}=>[8707,'THERE EXISTS','Sm','Common'],
-q{TH}=>[222,'LATIN CAPITAL LETTER THORN','Lu','Latin'],
+q{TH}=>[222,'LATIN CAPITAL LETTER THORN','Lu Xl','Latin'],
 q{TM}=>[8482,'TRADE MARK SIGN','So','Common'],
 q{TR}=>[8981,'TELEPHONE RECORDER','So','Common'],
-q{TS}=>[147,'<control>','Cc','Common'],
+q{TS}=>[147,'<control>','Cc Xl','Common'],
 q{TU}=>[12483,'KATAKANA LETTER SMALL TU','Lo','Katakana'],
 q{T_}=>[7790,'LATIN CAPITAL LETTER T WITH LINE BELOW','Lu','Latin'],
 q{Ta}=>[12479,'KATAKANA LETTER TA','Lo','Katakana'],
@@ -768,10 +768,10 @@ q{To}=>[12488,'KATAKANA LETTER TO','Lo','Katakana'],
 q{Tr}=>[9655,'WHITE RIGHT-POINTING TRIANGLE','Sm','Common'],
 q{Ts}=>[1035,'CYRILLIC CAPITAL LETTER TSHE','Lu','Cyrillic'],
 q{Tu}=>[12484,'KATAKANA LETTER TU','Lo','Katakana'],
-q{U!}=>[217,'LATIN CAPITAL LETTER U WITH GRAVE','Lu','Latin'],
+q{U!}=>[217,'LATIN CAPITAL LETTER U WITH GRAVE','Lu Xl','Latin'],
 q{U"}=>[368,'LATIN CAPITAL LETTER U WITH DOUBLE ACUTE','Lu','Latin'],
 q{U%}=>[910,'GREEK CAPITAL LETTER UPSILON WITH TONOS','Lu','Greek'],
-q{U'}=>[218,'LATIN CAPITAL LETTER U WITH ACUTE','Lu','Latin'],
+q{U'}=>[218,'LATIN CAPITAL LETTER U WITH ACUTE','Lu Xl','Latin'],
 q{U(}=>[364,'LATIN CAPITAL LETTER U WITH BREVE','Lu','Latin'],
 q{U*}=>[933,'GREEK CAPITAL LETTER UPSILON','Lu','Greek'],
 q{U-}=>[362,'LATIN CAPITAL LETTER U WITH MACRON','Lu','Latin'],
@@ -780,11 +780,11 @@ q{U2}=>[7910,'LATIN CAPITAL LETTER U WITH HOOK ABOVE','Lu','Latin'],
 q{U5}=>[12357,'HIRAGANA LETTER SMALL U','Lo','Hiragana'],
 q{U6}=>[12454,'KATAKANA LETTER U','Lo','Katakana'],
 q{U9}=>[431,'LATIN CAPITAL LETTER U WITH HORN','Lu','Latin'],
-q{U:}=>[220,'LATIN CAPITAL LETTER U WITH DIAERESIS','Lu','Latin'],
+q{U:}=>[220,'LATIN CAPITAL LETTER U WITH DIAERESIS','Lu Xl','Latin'],
 q{U;}=>[370,'LATIN CAPITAL LETTER U WITH OGONEK','Lu','Latin'],
 q{U<}=>[467,'LATIN CAPITAL LETTER U WITH CARON','Lu','Latin'],
 q{U=}=>[1059,'CYRILLIC CAPITAL LETTER U','Lu','Cyrillic'],
-q{U>}=>[219,'LATIN CAPITAL LETTER U WITH CIRCUMFLEX','Lu','Latin'],
+q{U>}=>[219,'LATIN CAPITAL LETTER U WITH CIRCUMFLEX','Lu Xl','Latin'],
 q{U?}=>[360,'LATIN CAPITAL LETTER U WITH TILDE','Lu','Latin'],
 q{UA}=>[57346,'','Co','Common'],
 q{UB}=>[57347,'','Co','Common'],
@@ -792,7 +792,7 @@ q{UD}=>[8597,'UP DOWN ARROW','So','Common'],
 q{UH}=>[9531,'BOX DRAWINGS HEAVY UP AND HORIZONTAL','So','Common'],
 q{UL}=>[9499,'BOX DRAWINGS HEAVY UP AND LEFT','So','Common'],
 q{UR}=>[9495,'BOX DRAWINGS HEAVY UP AND RIGHT','So','Common'],
-q{US}=>[31,'<control>','Cc','Common'],
+q{US}=>[31,'<control>','Cc Xa','Common'],
 q{UT}=>[9650,'BLACK UP-POINTING TRIANGLE','So','Common'],
 q{Uh}=>[9528,'BOX DRAWINGS UP HEAVY AND HORIZONTAL LIGHT','So','Common'],
 q{Ul}=>[9498,'BOX DRAWINGS UP HEAVY AND LEFT LIGHT','So','Common'],
@@ -805,8 +805,8 @@ q{V?}=>[7804,'LATIN CAPITAL LETTER V WITH TILDE','Lu','Latin'],
 q{VH}=>[9547,'BOX DRAWINGS HEAVY VERTICAL AND HORIZONTAL','So','Common'],
 q{VL}=>[9515,'BOX DRAWINGS HEAVY VERTICAL AND LEFT','So','Common'],
 q{VR}=>[9507,'BOX DRAWINGS HEAVY VERTICAL AND RIGHT','So','Common'],
-q{VS}=>[138,'<control>','Cc','Common'],
-q{VT}=>[11,'<control>','Cc','Common'],
+q{VS}=>[138,'<control>','Cc Xl','Common'],
+q{VT}=>[11,'<control>','Cc Xa','Common'],
 q{VV}=>[9475,'BOX DRAWINGS HEAVY VERTICAL','So','Common'],
 q{Va}=>[12535,'KATAKANA LETTER VA','Lo','Katakana'],
 q{Ve}=>[12537,'KATAKANA LETTER VE','Lo','Katakana'],
@@ -838,7 +838,7 @@ q{X:}=>[7820,'LATIN CAPITAL LETTER X WITH DIAERESIS','Lu','Latin'],
 q{XX}=>[10007,'BALLOT X','So','Common'],
 q{Y!}=>[7922,'LATIN CAPITAL LETTER Y WITH GRAVE','Lu','Latin'],
 q{Y%}=>[905,'GREEK CAPITAL LETTER ETA WITH TONOS','Lu','Greek'],
-q{Y'}=>[221,'LATIN CAPITAL LETTER Y WITH ACUTE','Lu','Latin'],
+q{Y'}=>[221,'LATIN CAPITAL LETTER Y WITH ACUTE','Lu Xl','Latin'],
 q{Y*}=>[919,'GREEK CAPITAL LETTER ETA','Lu','Greek'],
 q{Y.}=>[7822,'LATIN CAPITAL LETTER Y WITH DOT ABOVE','Lu','Latin'],
 q{Y2}=>[7926,'LATIN CAPITAL LETTER Y WITH HOOK ABOVE','Lu','Latin'],
@@ -852,7 +852,7 @@ q{YI}=>[1031,'CYRILLIC CAPITAL LETTER YI','Lu','Cyrillic'],
 q{YO}=>[12519,'KATAKANA LETTER SMALL YO','Lo','Katakana'],
 q{YU}=>[12517,'KATAKANA LETTER SMALL YU','Lo','Katakana'],
 q{Ya}=>[12516,'KATAKANA LETTER YA','Lo','Katakana'],
-q{Ye}=>[165,'YEN SIGN','Sc','Common'],
+q{Ye}=>[165,'YEN SIGN','Sc Xl','Common'],
 q{Yo}=>[12520,'KATAKANA LETTER YO','Lo','Katakana'],
 q{Yu}=>[12518,'KATAKANA LETTER YU','Lo','Katakana'],
 q{Z%}=>[1046,'CYRILLIC CAPITAL LETTER ZHE','Lu','Cyrillic'],
@@ -872,9 +872,9 @@ q{Zi}=>[12472,'KATAKANA LETTER ZI','Lo','Katakana'],
 q{Zj}=>[1509,'HEBREW LETTER FINAL TSADI','Lo','Hebrew'],
 q{Zo}=>[12478,'KATAKANA LETTER ZO','Lo','Katakana'],
 q{Zu}=>[12474,'KATAKANA LETTER ZU','Lo','Katakana'],
-q{a!}=>[224,'LATIN SMALL LETTER A WITH GRAVE','Ll','Latin'],
+q{a!}=>[224,'LATIN SMALL LETTER A WITH GRAVE','Ll Xl','Latin'],
 q{a%}=>[940,'GREEK SMALL LETTER ALPHA WITH TONOS','Ll','Greek'],
-q{a'}=>[225,'LATIN SMALL LETTER A WITH ACUTE','Ll','Latin'],
+q{a'}=>[225,'LATIN SMALL LETTER A WITH ACUTE','Ll Xl','Latin'],
 q{a(}=>[259,'LATIN SMALL LETTER A WITH BREVE','Ll','Latin'],
 q{a*}=>[945,'GREEK SMALL LETTER ALPHA','Ll','Greek'],
 q{a+}=>[1575,'ARABIC LETTER ALEF','Lo','Arabic'],
@@ -886,19 +886,19 @@ q{a4}=>[12570,'BOPOMOFO LETTER A','Lo','Bopomofo'],
 q{a5}=>[12354,'HIRAGANA LETTER A','Lo','Hiragana'],
 q{a6}=>[12449,'KATAKANA LETTER SMALL A','Lo','Katakana'],
 q{a7}=>[481,'LATIN SMALL LETTER A WITH DOT ABOVE AND MACRON','Ll','Latin'],
-q{a:}=>[228,'LATIN SMALL LETTER A WITH DIAERESIS','Ll','Latin'],
+q{a:}=>[228,'LATIN SMALL LETTER A WITH DIAERESIS','Ll Xl','Latin'],
 q{a;}=>[261,'LATIN SMALL LETTER A WITH OGONEK','Ll','Latin'],
 q{a<}=>[462,'LATIN SMALL LETTER A WITH CARON','Ll','Latin'],
 q{a=}=>[1072,'CYRILLIC SMALL LETTER A','Ll','Cyrillic'],
-q{a>}=>[226,'LATIN SMALL LETTER A WITH CIRCUMFLEX','Ll','Latin'],
-q{a?}=>[227,'LATIN SMALL LETTER A WITH TILDE','Ll','Latin'],
+q{a>}=>[226,'LATIN SMALL LETTER A WITH CIRCUMFLEX','Ll Xl','Latin'],
+q{a?}=>[227,'LATIN SMALL LETTER A WITH TILDE','Ll Xl','Latin'],
 q{aH}=>[1571,'ARABIC LETTER ALEF WITH HAMZA ABOVE','Lo','Arabic'],
 q{aM}=>[1570,'ARABIC LETTER ALEF WITH MADDA ABOVE','Lo','Arabic'],
 q{aN}=>[12580,'BOPOMOFO LETTER ANG','Lo','Bopomofo'],
 q{aR}=>[8553,'ROMAN NUMERAL TEN','Nl','Common'],
 q{aS}=>[1648,'ARABIC LETTER SUPERSCRIPT ALEF','Mn','Inherited'],
-q{aa}=>[229,'LATIN SMALL LETTER A WITH RING ABOVE','Ll','Latin'],
-q{ae}=>[230,'LATIN SMALL LETTER AE','Ll','Latin'],
+q{aa}=>[229,'LATIN SMALL LETTER A WITH RING ABOVE','Ll Xl','Latin'],
+q{ae}=>[230,'LATIN SMALL LETTER AE','Ll Xl','Latin'],
 q{ah}=>[1573,'ARABIC LETTER ALEF WITH HAMZA BELOW','Lo','Arabic'],
 q{ai}=>[12574,'BOPOMOFO LETTER AI','Lo','Bopomofo'],
 q{am}=>[57375,'','Co','Common'],
@@ -923,7 +923,7 @@ q{c%}=>[1095,'CYRILLIC SMALL LETTER CHE','Ll','Cyrillic'],
 q{c'}=>[263,'LATIN SMALL LETTER C WITH ACUTE','Ll','Latin'],
 q{c*}=>[958,'GREEK SMALL LETTER XI','Ll','Greek'],
 q{c+}=>[1589,'ARABIC LETTER SAD','Lo','Arabic'],
-q{c,}=>[231,'LATIN SMALL LETTER C WITH CEDILLA','Ll','Latin'],
+q{c,}=>[231,'LATIN SMALL LETTER C WITH CEDILLA','Ll Xl','Latin'],
 q{c.}=>[267,'LATIN SMALL LETTER C WITH DOT ABOVE','Ll','Latin'],
 q{c3}=>[1153,'CYRILLIC SMALL LETTER KOPPA','Ll','Cyrillic'],
 q{c4}=>[12568,'BOPOMOFO LETTER C','Lo','Bopomofo'],
@@ -942,7 +942,7 @@ q{d%}=>[1106,'CYRILLIC SMALL LETTER DJE','Ll','Cyrillic'],
 q{d*}=>[948,'GREEK SMALL LETTER DELTA','Ll','Greek'],
 q{d+}=>[1583,'ARABIC LETTER DAL','Lo','Arabic'],
 q{d,}=>[7697,'LATIN SMALL LETTER D WITH CEDILLA','Ll','Latin'],
-q{d-}=>[240,'LATIN SMALL LETTER ETH','Ll','Latin'],
+q{d-}=>[240,'LATIN SMALL LETTER ETH','Ll Xl','Latin'],
 q{d.}=>[7691,'LATIN SMALL LETTER D WITH DOT ABOVE','Ll','Latin'],
 q{d/}=>[273,'LATIN SMALL LETTER D WITH STROKE','Ll','Latin'],
 q{d4}=>[12553,'BOPOMOFO LETTER D','Lo','Bopomofo'],
@@ -966,9 +966,9 @@ q{dr}=>[9484,'BOX DRAWINGS LIGHT DOWN AND RIGHT','So','Common'],
 q{ds}=>[1109,'CYRILLIC SMALL LETTER DZE','Ll','Cyrillic'],
 q{du}=>[12389,'HIRAGANA LETTER DU','Lo','Hiragana'],
 q{dz}=>[1119,'CYRILLIC SMALL LETTER DZHE','Ll','Cyrillic'],
-q{e!}=>[232,'LATIN SMALL LETTER E WITH GRAVE','Ll','Latin'],
+q{e!}=>[232,'LATIN SMALL LETTER E WITH GRAVE','Ll Xl','Latin'],
 q{e%}=>[941,'GREEK SMALL LETTER EPSILON WITH TONOS','Ll','Greek'],
-q{e'}=>[233,'LATIN SMALL LETTER E WITH ACUTE','Ll','Latin'],
+q{e'}=>[233,'LATIN SMALL LETTER E WITH ACUTE','Ll Xl','Latin'],
 q{e(}=>[277,'LATIN SMALL LETTER E WITH BREVE','Ll','Latin'],
 q{e*}=>[949,'GREEK SMALL LETTER EPSILON','Ll','Greek'],
 q{e+}=>[1593,'ARABIC LETTER AIN','Lo','Arabic'],
@@ -978,11 +978,11 @@ q{e2}=>[7867,'LATIN SMALL LETTER E WITH HOOK ABOVE','Ll','Latin'],
 q{e4}=>[12572,'BOPOMOFO LETTER E','Lo','Bopomofo'],
 q{e5}=>[12360,'HIRAGANA LETTER E','Lo','Hiragana'],
 q{e6}=>[12455,'KATAKANA LETTER SMALL E','Lo','Katakana'],
-q{e:}=>[235,'LATIN SMALL LETTER E WITH DIAERESIS','Ll','Latin'],
+q{e:}=>[235,'LATIN SMALL LETTER E WITH DIAERESIS','Ll Xl','Latin'],
 q{e;}=>[281,'LATIN SMALL LETTER E WITH OGONEK','Ll','Latin'],
 q{e<}=>[283,'LATIN SMALL LETTER E WITH CARON','Ll','Latin'],
 q{e=}=>[1077,'CYRILLIC SMALL LETTER IE','Ll','Cyrillic'],
-q{e>}=>[234,'LATIN SMALL LETTER E WITH CIRCUMFLEX','Ll','Latin'],
+q{e>}=>[234,'LATIN SMALL LETTER E WITH CIRCUMFLEX','Ll Xl','Latin'],
 q{e?}=>[7869,'LATIN SMALL LETTER E WITH TILDE','Ll','Latin'],
 q{eN}=>[12581,'BOPOMOFO LETTER ENG','Lo','Bopomofo'],
 q{ed}=>[57374,'','Co','Common'],
@@ -1040,9 +1040,9 @@ q{hi}=>[12402,'HIRAGANA LETTER HI','Lo','Hiragana'],
 q{hk}=>[1581,'ARABIC LETTER HAH','Lo','Arabic'],
 q{ho}=>[12411,'HIRAGANA LETTER HO','Lo','Hiragana'],
 q{hu}=>[12405,'HIRAGANA LETTER HU','Lo','Hiragana'],
-q{i!}=>[236,'LATIN SMALL LETTER I WITH GRAVE','Ll','Latin'],
+q{i!}=>[236,'LATIN SMALL LETTER I WITH GRAVE','Ll Xl','Latin'],
 q{i%}=>[943,'GREEK SMALL LETTER IOTA WITH TONOS','Ll','Greek'],
-q{i'}=>[237,'LATIN SMALL LETTER I WITH ACUTE','Ll','Latin'],
+q{i'}=>[237,'LATIN SMALL LETTER I WITH ACUTE','Ll Xl','Latin'],
 q{i(}=>[301,'LATIN SMALL LETTER I WITH BREVE','Ll','Latin'],
 q{i*}=>[953,'GREEK SMALL LETTER IOTA','Ll','Greek'],
 q{i+}=>[1594,'ARABIC LETTER GHAIN','Lo','Arabic'],
@@ -1053,11 +1053,11 @@ q{i3}=>[912,'GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS','Ll','Greek'],
 q{i4}=>[12583,'BOPOMOFO LETTER I','Lo','Bopomofo'],
 q{i5}=>[12356,'HIRAGANA LETTER I','Lo','Hiragana'],
 q{i6}=>[12451,'KATAKANA LETTER SMALL I','Lo','Katakana'],
-q{i:}=>[239,'LATIN SMALL LETTER I WITH DIAERESIS','Ll','Latin'],
+q{i:}=>[239,'LATIN SMALL LETTER I WITH DIAERESIS','Ll Xl','Latin'],
 q{i;}=>[303,'LATIN SMALL LETTER I WITH OGONEK','Ll','Latin'],
 q{i<}=>[464,'LATIN SMALL LETTER I WITH CARON','Ll','Latin'],
 q{i=}=>[1080,'CYRILLIC SMALL LETTER I','Ll','Cyrillic'],
-q{i>}=>[238,'LATIN SMALL LETTER I WITH CIRCUMFLEX','Ll','Latin'],
+q{i>}=>[238,'LATIN SMALL LETTER I WITH CIRCUMFLEX','Ll Xl','Latin'],
 q{i?}=>[297,'LATIN SMALL LETTER I WITH TILDE','Ll','Latin'],
 q{ie}=>[1108,'CYRILLIC SMALL LETTER UKRAINIAN IE','Ll','Cyrillic'],
 q{ii}=>[1110,'CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I','Ll','Cyrillic'],
@@ -1124,7 +1124,7 @@ q{n4}=>[12555,'BOPOMOFO LETTER N','Lo','Bopomofo'],
 q{n5}=>[12435,'HIRAGANA LETTER N','Lo','Hiragana'],
 q{n<}=>[328,'LATIN SMALL LETTER N WITH CARON','Ll','Latin'],
 q{n=}=>[1085,'CYRILLIC SMALL LETTER EN','Ll','Cyrillic'],
-q{n?}=>[241,'LATIN SMALL LETTER N WITH TILDE','Ll','Latin'],
+q{n?}=>[241,'LATIN SMALL LETTER N WITH TILDE','Ll Xl','Latin'],
 q{nG}=>[12587,'BOPOMOFO LETTER NG','Lo','Bopomofo'],
 q{nS}=>[8319,'SUPERSCRIPT LATIN SMALL LETTER N','Ll','Latin'],
 q{n_}=>[7753,'LATIN SMALL LETTER N WITH LINE BELOW','Ll','Latin'],
@@ -1135,14 +1135,14 @@ q{ni}=>[12395,'HIRAGANA LETTER NI','Lo','Hiragana'],
 q{nj}=>[1114,'CYRILLIC SMALL LETTER NJE','Ll','Cyrillic'],
 q{no}=>[12398,'HIRAGANA LETTER NO','Lo','Hiragana'],
 q{nu}=>[12396,'HIRAGANA LETTER NU','Lo','Hiragana'],
-q{o!}=>[242,'LATIN SMALL LETTER O WITH GRAVE','Ll','Latin'],
+q{o!}=>[242,'LATIN SMALL LETTER O WITH GRAVE','Ll Xl','Latin'],
 q{o"}=>[337,'LATIN SMALL LETTER O WITH DOUBLE ACUTE','Ll','Latin'],
 q{o%}=>[972,'GREEK SMALL LETTER OMICRON WITH TONOS','Ll','Greek'],
-q{o'}=>[243,'LATIN SMALL LETTER O WITH ACUTE','Ll','Latin'],
+q{o'}=>[243,'LATIN SMALL LETTER O WITH ACUTE','Ll Xl','Latin'],
 q{o(}=>[335,'LATIN SMALL LETTER O WITH BREVE','Ll','Latin'],
 q{o*}=>[959,'GREEK SMALL LETTER OMICRON','Ll','Greek'],
 q{o-}=>[333,'LATIN SMALL LETTER O WITH MACRON','Ll','Latin'],
-q{o/}=>[248,'LATIN SMALL LETTER O WITH STROKE','Ll','Latin'],
+q{o/}=>[248,'LATIN SMALL LETTER O WITH STROKE','Ll Xl','Latin'],
 q{o1}=>[493,'LATIN SMALL LETTER O WITH OGONEK AND MACRON','Ll','Latin'],
 q{o2}=>[7887,'LATIN SMALL LETTER O WITH HOOK ABOVE','Ll','Latin'],
 q{o3}=>[1131,'CYRILLIC SMALL LETTER BIG YUS','Ll','Cyrillic'],
@@ -1150,12 +1150,12 @@ q{o4}=>[12571,'BOPOMOFO LETTER O','Lo','Bopomofo'],
 q{o5}=>[12362,'HIRAGANA LETTER O','Lo','Hiragana'],
 q{o6}=>[12457,'KATAKANA LETTER SMALL O','Lo','Katakana'],
 q{o9}=>[417,'LATIN SMALL LETTER O WITH HORN','Ll','Latin'],
-q{o:}=>[246,'LATIN SMALL LETTER O WITH DIAERESIS','Ll','Latin'],
+q{o:}=>[246,'LATIN SMALL LETTER O WITH DIAERESIS','Ll Xl','Latin'],
 q{o;}=>[491,'LATIN SMALL LETTER O WITH OGONEK','Ll','Latin'],
 q{o<}=>[466,'LATIN SMALL LETTER O WITH CARON','Ll','Latin'],
 q{o=}=>[1086,'CYRILLIC SMALL LETTER O','Ll','Cyrillic'],
-q{o>}=>[244,'LATIN SMALL LETTER O WITH CIRCUMFLEX','Ll','Latin'],
-q{o?}=>[245,'LATIN SMALL LETTER O WITH TILDE','Ll','Latin'],
+q{o>}=>[244,'LATIN SMALL LETTER O WITH CIRCUMFLEX','Ll Xl','Latin'],
+q{o?}=>[245,'LATIN SMALL LETTER O WITH TILDE','Ll Xl','Latin'],
 q{oC}=>[8451,'DEGREE CELSIUS','So','Common'],
 q{oF}=>[8457,'DEGREE FAHRENHEIT','So','Common'],
 q{oe}=>[339,'LATIN SMALL LIGATURE OE','Ll','Latin'],
@@ -1209,7 +1209,7 @@ q{sh}=>[12565,'BOPOMOFO LETTER SH','Lo','Bopomofo'],
 q{si}=>[12375,'HIRAGANA LETTER SI','Lo','Hiragana'],
 q{sn}=>[1588,'ARABIC LETTER SHEEN','Lo','Arabic'],
 q{so}=>[12381,'HIRAGANA LETTER SO','Lo','Hiragana'],
-q{ss}=>[223,'LATIN SMALL LETTER SHARP S','Ll','Latin'],
+q{ss}=>[223,'LATIN SMALL LETTER SHARP S','Ll Xl','Latin'],
 q{st}=>[64262,'LATIN SMALL LIGATURE ST','Ll','Latin'],
 q{su}=>[12377,'HIRAGANA LETTER SU','Lo','Hiragana'],
 q{t*}=>[964,'GREEK SMALL LETTER TAU','Ll','Greek'],
@@ -1226,7 +1226,7 @@ q{tU}=>[12387,'HIRAGANA LETTER SMALL TU','Lo','Hiragana'],
 q{t_}=>[7791,'LATIN SMALL LETTER T WITH LINE BELOW','Ll','Latin'],
 q{ta}=>[12383,'HIRAGANA LETTER TA','Lo','Hiragana'],
 q{te}=>[12390,'HIRAGANA LETTER TE','Lo','Hiragana'],
-q{th}=>[254,'LATIN SMALL LETTER THORN','Ll','Latin'],
+q{th}=>[254,'LATIN SMALL LETTER THORN','Ll Xl','Latin'],
 q{ti}=>[12385,'HIRAGANA LETTER TI','Lo','Hiragana'],
 q{tj}=>[1591,'ARABIC LETTER TAH','Lo','Arabic'],
 q{tk}=>[1579,'ARABIC LETTER THEH','Lo','Arabic'],
@@ -1234,10 +1234,10 @@ q{tm}=>[1577,'ARABIC LETTER TEH MARBUTA','Lo','Arabic'],
 q{to}=>[12392,'HIRAGANA LETTER TO','Lo','Hiragana'],
 q{ts}=>[1115,'CYRILLIC SMALL LETTER TSHE','Ll','Cyrillic'],
 q{tu}=>[12388,'HIRAGANA LETTER TU','Lo','Hiragana'],
-q{u!}=>[249,'LATIN SMALL LETTER U WITH GRAVE','Ll','Latin'],
+q{u!}=>[249,'LATIN SMALL LETTER U WITH GRAVE','Ll Xl','Latin'],
 q{u"}=>[369,'LATIN SMALL LETTER U WITH DOUBLE ACUTE','Ll','Latin'],
 q{u%}=>[973,'GREEK SMALL LETTER UPSILON WITH TONOS','Ll','Greek'],
-q{u'}=>[250,'LATIN SMALL LETTER U WITH ACUTE','Ll','Latin'],
+q{u'}=>[250,'LATIN SMALL LETTER U WITH ACUTE','Ll Xl','Latin'],
 q{u(}=>[365,'LATIN SMALL LETTER U WITH BREVE','Ll','Latin'],
 q{u*}=>[965,'GREEK SMALL LETTER UPSILON','Ll','Greek'],
 q{u-}=>[363,'LATIN SMALL LETTER U WITH MACRON','Ll','Latin'],
@@ -1248,11 +1248,11 @@ q{u4}=>[12584,'BOPOMOFO LETTER U','Lo','Bopomofo'],
 q{u5}=>[12358,'HIRAGANA LETTER U','Lo','Hiragana'],
 q{u6}=>[12453,'KATAKANA LETTER SMALL U','Lo','Katakana'],
 q{u9}=>[432,'LATIN SMALL LETTER U WITH HORN','Ll','Latin'],
-q{u:}=>[252,'LATIN SMALL LETTER U WITH DIAERESIS','Ll','Latin'],
+q{u:}=>[252,'LATIN SMALL LETTER U WITH DIAERESIS','Ll Xl','Latin'],
 q{u;}=>[371,'LATIN SMALL LETTER U WITH OGONEK','Ll','Latin'],
 q{u<}=>[468,'LATIN SMALL LETTER U WITH CARON','Ll','Latin'],
 q{u=}=>[1091,'CYRILLIC SMALL LETTER U','Ll','Cyrillic'],
-q{u>}=>[251,'LATIN SMALL LETTER U WITH CIRCUMFLEX','Ll','Latin'],
+q{u>}=>[251,'LATIN SMALL LETTER U WITH CIRCUMFLEX','Ll Xl','Latin'],
 q{u?}=>[361,'LATIN SMALL LETTER U WITH TILDE','Ll','Latin'],
 q{uH}=>[9527,'BOX DRAWINGS UP LIGHT AND HORIZONTAL HEAVY','So','Common'],
 q{uL}=>[9497,'BOX DRAWINGS UP LIGHT AND LEFT HEAVY','So','Common'],
@@ -1298,14 +1298,14 @@ q{x4}=>[12562,'BOPOMOFO LETTER X','Lo','Bopomofo'],
 q{x:}=>[7821,'LATIN SMALL LETTER X WITH DIAERESIS','Ll','Latin'],
 q{y!}=>[7923,'LATIN SMALL LETTER Y WITH GRAVE','Ll','Latin'],
 q{y%}=>[942,'GREEK SMALL LETTER ETA WITH TONOS','Ll','Greek'],
-q{y'}=>[253,'LATIN SMALL LETTER Y WITH ACUTE','Ll','Latin'],
+q{y'}=>[253,'LATIN SMALL LETTER Y WITH ACUTE','Ll Xl','Latin'],
 q{y*}=>[951,'GREEK SMALL LETTER ETA','Ll','Greek'],
 q{y+}=>[1610,'ARABIC LETTER YEH','Lo','Arabic'],
 q{y.}=>[7823,'LATIN SMALL LETTER Y WITH DOT ABOVE','Ll','Latin'],
 q{y0}=>[7833,'LATIN SMALL LETTER Y WITH RING ABOVE','Ll','Latin'],
 q{y2}=>[7927,'LATIN SMALL LETTER Y WITH HOOK ABOVE','Ll','Latin'],
 q{y3}=>[1123,'CYRILLIC SMALL LETTER YAT','Ll','Cyrillic'],
-q{y:}=>[255,'LATIN SMALL LETTER Y WITH DIAERESIS','Ll','Latin'],
+q{y:}=>[255,'LATIN SMALL LETTER Y WITH DIAERESIS','Ll Xl','Latin'],
 q{y=}=>[1099,'CYRILLIC SMALL LETTER YERU','Ll','Cyrillic'],
 q{y>}=>[375,'LATIN SMALL LETTER Y WITH CIRCUMFLEX','Ll','Latin'],
 q{y?}=>[7929,'LATIN SMALL LETTER Y WITH TILDE','Ll','Latin'],

diff --git a/digraphs.plp b/digraphs.plp
index 67d2a1a130f1370a2696d5bbd797321a076745ba..4a150cf77dd2a56feca0b2a2cd6ab5867e38aa35 100644 (file)
--- a/digraphs.plp
+++ b/digraphs.plp
@@ -77,10 +77,10 @@ td.Cc {background: #BBB; color: #666} /* control */
 td.Zs {background: #ACB} /* space */
 td.Zs span {background: #EEE}
 
-td.Xa {color: #040} /* ascii */
-td.Xl {color: #080} /* latin1 */
+td.Xa {color: #0A0} /* ascii */
+td.Xl {color: #070} /* latin1 */
 td.Co {color: #800} /* private */
-td.Xz {color: #F00} /* proposed */
+td.Xz {color: #D00} /* proposed */
 
 tr:hover td {
        background: #FF8;
@@ -160,8 +160,8 @@ print "</table>\n";
 
        <table><tr>
        <td class="X">unicode
-       <td class="X Xa">ascii
        <td class="X Xl">latin1
+       <td class="X Xa">ascii
        <td class="X Co">private
        <td class="X Xz">proposed
        </table>

diff --git a/rfc1345convert b/rfc1345convert
index 8b29b8048b821846b23a9886f22beb3a49754a66..6edfa7445083ea4588365224c05927102eb6f0a2 100644 (file)
--- a/rfc1345convert
+++ b/rfc1345convert
@@ -47,18 +47,24 @@ for (@t) {
 }
 
 # optionally get unicode character information
-my %charinfo = eval {
+my %info = eval {
        require Unicode::UCD;
        map { $_ => Unicode::UCD::charinfo($di{$_}) } keys %di;
 };
 
+# add custom categories for certain blocks
+for (values %info) {
+       $_->{category} .= ' Xa' if $_->{block} eq 'Basic Latin';
+       $_->{category} .= ' Xl' if $_->{block} eq 'Latin-1 Supplement';
+}
+
 # output perl code of hash
 # (assume no backslashes or curlies, so we can just q{} w/o escaping)
 print "{\n";
 printf "q{%s}=>[%s],\n", $_, join(',',
        $di{$_},       # glyph code point
-       $charinfo{$_}  # optional additional arguments
-               ? map {"'$_'"} @{ $charinfo{$_} }{qw/name category script/}
+       $info{$_}  # optional additional arguments
+               ? map {"'$_'"} @{ $info{$_} }{qw/name category script/}
                : ()
 ) for sort keys %di;
 print "}\n";