digraphs: alternate glyph string in include

Allow the digraph include to specify string overrides in cases where a
glyph should not be shown literally.  These are:

- Combining characters: prepend a placeholder.
  Dead chars are invalid on their own in fact.
- ASCII control characters: substitude display symbols at U+24xx.
  Though browsers usually show a character placeholder, it's not very
  nice to send control chars directly.
- Other control characters: show the replacement character U+FFFD.
  Actually with some (Linux) fonts, the anonymous code point fallback is
  more descriptive, but better to be on the safe side (they still have
  semantic value after all).

diff --git a/digraphs.inc.pl b/digraphs.inc.pl
index 4b4fcaeec1888384e221575bf0159d92c9499765..bca585596610830494204f6b5046fce988cb9fbf 100644 (file)
--- a/digraphs.inc.pl
+++ b/digraphs.inc.pl
@@ -14,31 +14,31 @@ q{!b}=>[664,'LATIN LETTER BILABIAL CLICK','Ll Xz','Latin'],
 q{!c}=>[448,'LATIN LETTER DENTAL CLICK','Lo Xz','Latin'],
 q{!q}=>[451,'LATIN LETTER RETROFLEX CLICK','Lo Xz','Latin'],
 q{!x}=>[449,'LATIN LETTER LATERAL CLICK','Lo Xz','Latin'],
-q{"!}=>[768,'COMBINING GRAVE ACCENT','Mn','Inherited'],
-q{""}=>[779,'COMBINING DOUBLE ACUTE ACCENT','Mn','Inherited'],
-q{"'}=>[769,'COMBINING ACUTE ACCENT','Mn','Inherited'],
-q{"(}=>[774,'COMBINING BREVE','Mn','Inherited'],
-q{"+}=>[1612,'ARABIC DAMMATAN','Mn','Inherited'],
-q{",}=>[807,'COMBINING CEDILLA','Mn','Inherited'],
-q{"-}=>[772,'COMBINING MACRON','Mn','Inherited'],
-q{".}=>[775,'COMBINING DOT ABOVE','Mn','Inherited'],
-q{"/}=>[824,'COMBINING LONG SOLIDUS OVERLAY','Mn','Inherited'],
-q{"0}=>[778,'COMBINING RING ABOVE','Mn','Inherited'],
-q{"1}=>[836,'COMBINING GREEK DIALYTIKA TONOS','Mn','Inherited'],
-q{"3}=>[9216,'<NULL>','Cc Xa','Common'],
+q{"!}=>[768,'COMBINING GRAVE ACCENT','Mn','Inherited','◌̀'],
+q{""}=>[779,'COMBINING DOUBLE ACUTE ACCENT','Mn','Inherited','◌̋'],
+q{"'}=>[769,'COMBINING ACUTE ACCENT','Mn','Inherited','◌́'],
+q{"(}=>[774,'COMBINING BREVE','Mn','Inherited','◌̆'],
+q{"+}=>[1612,'ARABIC DAMMATAN','Mn','Inherited','◌ٌ'],
+q{",}=>[807,'COMBINING CEDILLA','Mn','Inherited','◌̧'],
+q{"-}=>[772,'COMBINING MACRON','Mn','Inherited','◌̄'],
+q{".}=>[775,'COMBINING DOT ABOVE','Mn','Inherited','◌̇'],
+q{"/}=>[824,'COMBINING LONG SOLIDUS OVERLAY','Mn','Inherited','◌̸'],
+q{"0}=>[778,'COMBINING RING ABOVE','Mn','Inherited','◌̊'],
+q{"1}=>[836,'COMBINING GREEK DIALYTIKA TONOS','Mn','Inherited','◌̈́'],
+q{"3}=>[0,'<NULL>','Cc Xa','Common','␀'],
 q{"5}=>[12443,'KATAKANA-HIRAGANA VOICED SOUND MARK','Sk','Common'],
 q{"6}=>[8220,'LEFT DOUBLE QUOTATION MARK','Pi','Common'],
 q{"9}=>[8221,'RIGHT DOUBLE QUOTATION MARK','Pf','Common'],
-q{":}=>[776,'COMBINING DIAERESIS','Mn','Inherited'],
-q{";}=>[808,'COMBINING OGONEK','Mn','Inherited'],
-q{"<}=>[780,'COMBINING CARON','Mn','Inherited'],
-q{"=}=>[819,'COMBINING DOUBLE LOW LINE','Mn','Inherited'],
-q{">}=>[770,'COMBINING CIRCUMFLEX ACCENT','Mn','Inherited'],
-q{"?}=>[771,'COMBINING TILDE','Mn','Inherited'],
-q{"_}=>[818,'COMBINING LOW LINE','Mn','Inherited'],
-q{"d}=>[788,'COMBINING REVERSED COMMA ABOVE','Mn','Inherited'],
-q{"i}=>[837,'COMBINING GREEK YPOGEGRAMMENI','Mn','Inherited'],
-q{"p}=>[787,'COMBINING COMMA ABOVE','Mn','Inherited'],
+q{":}=>[776,'COMBINING DIAERESIS','Mn','Inherited','◌̈'],
+q{";}=>[808,'COMBINING OGONEK','Mn','Inherited','◌̨'],
+q{"<}=>[780,'COMBINING CARON','Mn','Inherited','◌̌'],
+q{"=}=>[819,'COMBINING DOUBLE LOW LINE','Mn','Inherited','◌̳'],
+q{">}=>[770,'COMBINING CIRCUMFLEX ACCENT','Mn','Inherited','◌̂'],
+q{"?}=>[771,'COMBINING TILDE','Mn','Inherited','◌̃'],
+q{"_}=>[818,'COMBINING LOW LINE','Mn','Inherited','◌̲'],
+q{"d}=>[788,'COMBINING REVERSED COMMA ABOVE','Mn','Inherited','◌̔'],
+q{"i}=>[837,'COMBINING GREEK YPOGEGRAMMENI','Mn','Inherited','◌ͅ'],
+q{"p}=>[787,'COMBINING COMMA ABOVE','Mn','Inherited','◌̓'],
 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'],
@@ -50,7 +50,7 @@ q{'"}=>[733,'DOUBLE ACUTE ACCENT','Sk','Common'],
 q{'%}=>[1012,'GREEK CAPITAL THETA SYMBOL','Lu','Greek'],
 q{''}=>[180,'ACUTE ACCENT','Sk Xl','Common'],
 q{'(}=>[728,'BREVE','Sk','Common'],
-q{'+}=>[1615,'ARABIC DAMMA','Mn','Inherited'],
+q{'+}=>[1615,'ARABIC DAMMA','Mn','Inherited','◌ُ'],
 q{',}=>[184,'CEDILLA','Sk Xl','Common'],
 q{'-}=>[8254,'OVERLINE','Po','Common'],
 q{'.}=>[729,'DOT ABOVE','Sk','Common'],
@@ -144,16 +144,16 @@ 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{/+}=>[1614,'ARABIC FATHA','Mn','Inherited','◌َ'],
 q{/-}=>[8224,'DAGGER','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'],
-q{/c}=>[9216,'<NULL>','Cc Xa','Common'],
+q{/c}=>[0,'<NULL>','Cc Xa','Common','␀'],
 q{/f}=>[8260,'FRACTION SLASH','Sm','Common'],
 q{0(}=>[8733,'PROPORTIONAL TO','Sm','Common'],
-q{0+}=>[1618,'ARABIC SUKUN','Mn','Inherited'],
+q{0+}=>[1618,'ARABIC SUKUN','Mn','Inherited','◌ْ'],
 q{0.}=>[8857,'CIRCLED DOT OPERATOR','Sm','Common'],
 q{00}=>[8734,'INFINITY','Sm','Common'],
 q{02}=>[8858,'CIRCLED RING OPERATOR','Sm','Common'],
@@ -172,7 +172,7 @@ q{0s}=>[8320,'SUBSCRIPT ZERO','No','Common'],
 q{0u}=>[9786,'WHITE SMILING FACE','So','Common'],
 q{1"}=>[8245,'REVERSED PRIME','Po','Common'],
 q{1'}=>[8242,'PRIME','Po','Common'],
-q{1+}=>[1616,'ARABIC KASRA','Mn','Inherited'],
+q{1+}=>[1616,'ARABIC KASRA','Mn','Inherited','◌ِ'],
 q{1.}=>[9352,'DIGIT ONE FULL STOP','No','Common'],
 q{12}=>[189,'VULGAR FRACTION ONE HALF','No Xl','Common'],
 q{13}=>[8531,'VULGAR FRACTION ONE THIRD','No','Common'],
@@ -211,7 +211,7 @@ q{3!}=>[9478,'BOX DRAWINGS LIGHT TRIPLE DASH VERTICAL','So','Common'],
 q{3"}=>[8247,'REVERSED TRIPLE PRIME','Po','Common'],
 q{3'}=>[8244,'TRIPLE PRIME','Po','Common'],
 q{3*}=>[8258,'ASTERISM','Po Xz','Common'],
-q{3+}=>[1617,'ARABIC SHADDA','Mn','Inherited'],
+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'],
@@ -290,7 +290,7 @@ q{9r}=>[8568,'SMALL ROMAN NUMERAL NINE','Nl','Common'],
 q{9s}=>[8329,'SUBSCRIPT NINE','No','Common'],
 q{:(}=>[9785,'WHITE FROWNING FACE','So Xz','Common'],
 q{:)}=>[9786,'WHITE SMILING FACE','So Xz','Common'],
-q{:+}=>[1611,'ARABIC FATHATAN','Mn','Inherited'],
+q{:+}=>[1611,'ARABIC FATHATAN','Mn','Inherited','◌ً'],
 q{:.}=>[8757,'BECAUSE','Sm','Common'],
 q{:3}=>[8942,'VERTICAL ELLIPSIS','Sm','Common'],
 q{:9}=>[8222,'DOUBLE LOW-9 QUOTATION MARK','Ps','Common'],
@@ -320,7 +320,7 @@ q{<>}=>[8596,'LEFT RIGHT ARROW','Sm','Common'],
 q{<H}=>[9756,'WHITE LEFT POINTING INDEX','So','Common'],
 q{="}=>[1066,'CYRILLIC CAPITAL LETTER HARD SIGN','Lu','Cyrillic'],
 q{='}=>[1098,'CYRILLIC SMALL LETTER HARD SIGN','Ll','Cyrillic'],
-q{=+}=>[1613,'ARABIC KASRATAN','Mn','Inherited'],
+q{=+}=>[1613,'ARABIC KASRATAN','Mn','Inherited','◌ٍ'],
 q{=2}=>[8215,'DOUBLE LOW LINE','Po','Common'],
 q{=3}=>[8801,'IDENTICAL TO','Sm','Common'],
 q{=<}=>[8804,'LESS-THAN OR EQUAL TO','Sm','Common'],
@@ -340,7 +340,7 @@ 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 Xl','Common'],
 q{>H}=>[9758,'WHITE RIGHT POINTING INDEX','So','Common'],
-q{>V}=>[8407,'COMBINING RIGHT ARROW ABOVE','Mn','Inherited'],
+q{>V}=>[8407,'COMBINING RIGHT ARROW ABOVE','Mn','Inherited','◌⃗'],
 q{?!}=>[8253,'INTERROBANG','Po Xz','Common'],
 q{?*}=>[8128,'GREEK PERISPOMENI','Sk','Greek'],
 q{?+}=>[1567,'ARABIC QUESTION MARK','Po','Common'],
@@ -379,10 +379,10 @@ q{A=}=>[1040,'CYRILLIC CAPITAL LETTER A','Lu','Cyrillic'],
 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,'<APPLICATION PROGRAM COMMAND>','Cc Xl','Common'],
+q{AC}=>[159,'<APPLICATION PROGRAM COMMAND>','Cc Xl','Common','�'],
 q{AE}=>[198,'LATIN CAPITAL LETTER AE','Lu Xl','Latin'],
 q{AJ}=>[12624,'HANGUL LETTER AE','Lo Xz','Hangul'],
-q{AK}=>[9222,'<ACKNOWLEDGE>','Cc Xa','Common'],
+q{AK}=>[6,'<ACKNOWLEDGE>','Cc Xa','Common','␆'],
 q{AN}=>[8743,'LOGICAL AND','Sm','Common'],
 q{AO}=>[8491,'ANGSTROM SIGN','Lu','Latin'],
 q{At}=>[64,'COMMERCIAL AT','Po Xa','Common'],
@@ -395,10 +395,10 @@ q{B2}=>[385,'LATIN CAPITAL LETTER B WITH HOOK','Lu Xz','Latin'],
 q{B=}=>[1041,'CYRILLIC CAPITAL LETTER BE','Lu','Cyrillic'],
 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,'<BREAK PERMITTED HERE>','Cc Xl','Common'],
+q{BH}=>[130,'<BREAK PERMITTED HERE>','Cc Xl','Common','�'],
 q{BJ}=>[12611,'HANGUL LETTER SSANGPIEUP','Lo Xz','Hangul'],
-q{BL}=>[9223,'<BELL>','Cc Xa','Common'],
-q{BS}=>[9224,'<BACKSPACE>','Cc Xa','Common'],
+q{BL}=>[7,'<BELL>','Cc Xa','Common','␇'],
+q{BS}=>[8,'<BACKSPACE>','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'],
@@ -416,11 +416,11 @@ 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,'<CANCEL CHARACTER>','Cc Xl','Common'],
+q{CC}=>[148,'<CANCEL CHARACTER>','Cc Xl','Common','�'],
 q{CG}=>[8766,'INVERTED LAZY S','Sm','Common'],
-q{CI}=>[155,'<CONTROL SEQUENCE INTRODUCER>','Cc Xl','Common'],
-q{CN}=>[9240,'<CANCEL>','Cc Xa','Common'],
-q{CR}=>[9229,'<CARRIAGE RETURN (CR)>','Cc Xa','Common'],
+q{CI}=>[155,'<CONTROL SEQUENCE INTRODUCER>','Cc Xl','Common','�'],
+q{CN}=>[24,'<CANCEL>','Cc Xa','Common','␘'],
+q{CR}=>[13,'<CARRIAGE RETURN (CR)>','Cc Xa','Common','␍'],
 q{Ca}=>[8248,'CARET','Po','Common'],
 q{Ci}=>[9675,'WHITE CIRCLE','So','Common'],
 q{Co}=>[169,'COPYRIGHT SIGN','So Xl','Common'],
@@ -433,24 +433,24 @@ q{D,}=>[7696,'LATIN CAPITAL LETTER D WITH CEDILLA','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}=>[9233,'<DEVICE CONTROL ONE>','Cc Xa','Common'],
-q{D2}=>[9234,'<DEVICE CONTROL TWO>','Cc Xa','Common'],
-q{D3}=>[9235,'<DEVICE CONTROL THREE>','Cc Xa','Common'],
-q{D4}=>[9236,'<DEVICE CONTROL FOUR>','Cc Xa','Common'],
+q{D1}=>[17,'<DEVICE CONTROL ONE>','Cc Xa','Common','␑'],
+q{D2}=>[18,'<DEVICE CONTROL TWO>','Cc Xa','Common','␒'],
+q{D3}=>[19,'<DEVICE CONTROL THREE>','Cc Xa','Common','␓'],
+q{D4}=>[20,'<DEVICE CONTROL FOUR>','Cc Xa','Common','␔'],
 q{D;}=>[393,'LATIN CAPITAL LETTER AFRICAN D','Lu Xz','Latin'],
 q{D<}=>[270,'LATIN CAPITAL LETTER D WITH CARON','Lu','Latin'],
 q{D=}=>[1044,'CYRILLIC CAPITAL LETTER DE','Lu','Cyrillic'],
-q{DC}=>[144,'<DEVICE CONTROL STRING>','Cc Xl','Common'],
+q{DC}=>[144,'<DEVICE CONTROL STRING>','Cc Xl','Common','�'],
 q{DE}=>[8710,'INCREMENT','Sm','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{DJ}=>[12600,'HANGUL LETTER SSANGTIKEUT','Lo Xz','Hangul'],
-q{DL}=>[9232,'<DATA LINK ESCAPE>','Cc Xa','Common'],
+q{DL}=>[16,'<DATA LINK ESCAPE>','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 Xa','Common'],
+q{DT}=>[127,'<DELETE>','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'],
@@ -485,17 +485,17 @@ 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 Xl','Latin'],
 q{E?}=>[7868,'LATIN CAPITAL LETTER E WITH TILDE','Lu','Latin'],
-q{EB}=>[9239,'<END OF TRANSMISSION BLOCK>','Cc Xa','Common'],
-q{EC}=>[9243,'<ESCAPE>','Cc Xa','Common'],
+q{EB}=>[23,'<END OF TRANSMISSION BLOCK>','Cc Xa','Common','␗'],
+q{EC}=>[27,'<ESCAPE>','Cc Xa','Common','␛'],
 q{ED}=>[439,'LATIN CAPITAL LETTER EZH','Lu','Latin'],
-q{EG}=>[151,'<END OF GUARDED AREA>','Cc Xl','Common'],
+q{EG}=>[151,'<END OF GUARDED AREA>','Cc Xl','Common','�'],
 q{EJ}=>[12628,'HANGUL LETTER E','Lo Xz','Hangul'],
 q{EK}=>[12630,'HANGUL LETTER YE','Lo Xz','Hangul'],
-q{EM}=>[9241,'<END OF MEDIUM>','Cc Xa','Common'],
-q{EQ}=>[9221,'<ENQUIRY>','Cc Xa','Common'],
-q{ES}=>[135,'<END OF SELECTED AREA>','Cc Xl','Common'],
-q{ET}=>[9220,'<END OF TRANSMISSION>','Cc Xa','Common'],
-q{EX}=>[9219,'<END OF TEXT>','Cc Xa','Common'],
+q{EM}=>[25,'<END OF MEDIUM>','Cc Xa','Common','␙'],
+q{EQ}=>[5,'<ENQUIRY>','Cc Xa','Common','␅'],
+q{ES}=>[135,'<END OF SELECTED AREA>','Cc Xl','Common','�'],
+q{ET}=>[4,'<END OF TRANSMISSION>','Cc Xa','Common','␄'],
+q{EX}=>[3,'<END OF TEXT>','Cc Xa','Common','␃'],
 q{EZ}=>[494,'LATIN CAPITAL LETTER EZH WITH CARON','Lu','Latin'],
 q{Eh}=>[8962,'HOUSE','So','Common'],
 q{Eu}=>[8364,'EURO SIGN','Sc Xz','Common'],
@@ -507,11 +507,11 @@ 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}=>[9228,'<FORM FEED (FF)>','Cc Xa','Common'],
+q{FF}=>[12,'<FORM FEED (FF)>','Cc Xa','Common','␌'],
 q{FI}=>[8498,'TURNED CAPITAL F','So Xz','Common'],
-q{FS}=>[9244,'<INFORMATION SEPARATOR FOUR>','Cc Xa','Common'],
+q{FS}=>[28,'<INFORMATION SEPARATOR FOUR>','Cc Xa','Common','␜'],
 q{Fd}=>[9698,'BLACK LOWER RIGHT TRIANGLE','So','Common'],
-q{Fl}=>[9216,'<NULL>','Cc Xa','Common'],
+q{Fl}=>[0,'<NULL>','Cc Xa','Common','␀'],
 q{Fm}=>[9792,'FEMALE SIGN','So','Common'],
 q{G%}=>[1027,'CYRILLIC CAPITAL LETTER GJE','Lu','Cyrillic'],
 q{G'}=>[500,'LATIN CAPITAL LETTER G WITH ACUTE','Lu','Latin'],
@@ -527,10 +527,10 @@ 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 U+0099>','Cc Xl','Common'],
+q{GC}=>[153,'<control U+0099>','Cc Xl','Common','�'],
 q{GF}=>[915,'GREEK CAPITAL LETTER GAMMA','Lu','Greek'],
 q{GJ}=>[12594,'HANGUL LETTER SSANGKIYEOK','Lo Xz','Hangul'],
-q{GS}=>[9245,'<INFORMATION SEPARATOR THREE>','Cc Xa','Common'],
+q{GS}=>[29,'<INFORMATION SEPARATOR THREE>','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'],
@@ -547,10 +547,10 @@ 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,'<CHARACTER TABULATION WITH JUSTIFICATION>','Cc Xl','Common'],
-q{HO}=>[129,'<control U+0081>','Cc Xl','Common'],
-q{HS}=>[136,'<CHARACTER TABULATION SET>','Cc Xl','Common'],
-q{HT}=>[9225,'<CHARACTER TABULATION>','Cc Xa','Common'],
+q{HJ}=>[137,'<CHARACTER TABULATION WITH JUSTIFICATION>','Cc Xl','Common','�'],
+q{HO}=>[129,'<control U+0081>','Cc Xl','Common','�'],
+q{HS}=>[136,'<CHARACTER TABULATION SET>','Cc Xl','Common','�'],
+q{HT}=>[9,'<CHARACTER TABULATION>','Cc Xa','Common','␉'],
 q{HW}=>[502,'LATIN CAPITAL LETTER HWAIR','Lu Xz','Latin'],
 q{Ha}=>[12495,'KATAKANA LETTER HA','Lo','Katakana'],
 q{He}=>[12504,'KATAKANA LETTER HE','Lo','Katakana'],
@@ -579,7 +579,7 @@ 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 U+0084>','Cc Xl','Common'],
+q{IN}=>[132,'<control U+0084>','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'],
@@ -627,7 +627,7 @@ q{L=}=>[1051,'CYRILLIC CAPITAL LETTER EL','Lu','Cyrillic'],
 q{L?}=>[11362,'','Xn Xz',''],
 q{LB}=>[9604,'LOWER HALF BLOCK','So','Common'],
 q{LD}=>[9491,'BOX DRAWINGS HEAVY DOWN AND LEFT','So','Common'],
-q{LF}=>[9226,'<LINE FEED (LF)>','Cc Xa','Common'],
+q{LF}=>[10,'<LINE FEED (LF)>','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'],
@@ -642,7 +642,7 @@ 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{MI}=>[412,'LATIN CAPITAL LETTER TURNED M','Lu Xz','Latin'],
-q{MW}=>[149,'<MESSAGE WAITING>','Cc Xl','Common'],
+q{MW}=>[149,'<MESSAGE WAITING>','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'],
@@ -669,14 +669,14 @@ q{N=}=>[1053,'CYRILLIC CAPITAL LETTER EN','Lu','Cyrillic'],
 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,'<NO BREAK HERE>','Cc Xl','Common'],
+q{NH}=>[131,'<NO BREAK HERE>','Cc Xl','Common','�'],
 q{NI}=>[8976,'REVERSED NOT SIGN','So','Common'],
 q{NJ}=>[1034,'CYRILLIC CAPITAL LETTER NJE','Lu','Cyrillic'],
-q{NK}=>[9237,'<NEGATIVE ACKNOWLEDGE>','Cc Xa','Common'],
-q{NL}=>[133,'<NEXT LINE (NEL)>','Cc Xl','Common'],
+q{NK}=>[21,'<NEGATIVE ACKNOWLEDGE>','Cc Xa','Common','␕'],
+q{NL}=>[133,'<NEXT LINE (NEL)>','Cc Xl','Common','�'],
 q{NO}=>[172,'NOT SIGN','Sm Xl','Common'],
 q{NS}=>[160,'NO-BREAK SPACE','Zs Xl','Common'],
-q{NU}=>[9216,'<NULL>','Cc Xa','Common'],
+q{NU}=>[0,'<NULL>','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 Xa','Common'],
@@ -707,7 +707,7 @@ 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 Xl','Latin'],
 q{O?}=>[213,'LATIN CAPITAL LETTER O WITH TILDE','Lu Xl','Latin'],
-q{OC}=>[157,'<OPERATING SYSTEM COMMAND>','Cc Xl','Common'],
+q{OC}=>[157,'<OPERATING SYSTEM COMMAND>','Cc Xl','Common','�'],
 q{OE}=>[338,'LATIN CAPITAL LIGATURE OE','Lu','Latin'],
 q{OI}=>[418,'LATIN CAPITAL LETTER OI','Lu','Latin'],
 q{OJ}=>[12634,'HANGUL LETTER OE','Lo Xz','Hangul'],
@@ -723,19 +723,19 @@ 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{P/}=>[11363,'','Xn Xz',''],
-q{P1}=>[145,'<PRIVATE USE ONE>','Cc Xl','Common'],
-q{P2}=>[146,'<PRIVATE USE TWO>','Cc Xl','Common'],
+q{P1}=>[145,'<PRIVATE USE ONE>','Cc Xl','Common','�'],
+q{P2}=>[146,'<PRIVATE USE TWO>','Cc Xl','Common','�'],
 q{P3}=>[992,'GREEK LETTER SAMPI','Lu','Greek'],
 q{P=}=>[1055,'CYRILLIC CAPITAL LETTER PE','Lu','Cyrillic'],
-q{PA}=>[128,'<control U+0080>','Cc Xl','Common'],
-q{PD}=>[139,'<PARTIAL LINE FORWARD>','Cc Xl','Common'],
+q{PA}=>[128,'<control U+0080>','Cc Xl','Common','�'],
+q{PD}=>[139,'<PARTIAL LINE FORWARD>','Cc Xl','Common','�'],
 q{PI}=>[182,'PILCROW SIGN','So Xl','Common'],
 q{PL}=>[9664,'BLACK LEFT-POINTING TRIANGLE','So','Common'],
-q{PM}=>[158,'<PRIVACY MESSAGE>','Cc Xl','Common'],
+q{PM}=>[158,'<PRIVACY MESSAGE>','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,'<PARTIAL LINE BACKWARD>','Cc Xl','Common'],
+q{PU}=>[140,'<PARTIAL LINE BACKWARD>','Cc Xl','Common','�'],
 q{Pa}=>[12497,'KATAKANA LETTER PA','Lo','Katakana'],
 q{Pd}=>[163,'POUND SIGN','Sc Xl','Common'],
 q{Pe}=>[12506,'KATAKANA LETTER PE','Lo','Katakana'],
@@ -760,10 +760,10 @@ 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,'<REVERSE LINE FEED>','Cc Xl','Common'],
+q{RI}=>[141,'<REVERSE LINE FEED>','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}=>[9246,'<INFORMATION SEPARATOR TWO>','Cc Xa','Common'],
+q{RS}=>[30,'<INFORMATION SEPARATOR TWO>','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'],
@@ -783,27 +783,27 @@ 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,'<SINGLE SHIFT TWO>','Cc Xl','Common'],
-q{S3}=>[143,'<SINGLE SHIFT THREE>','Cc Xl','Common'],
+q{S2}=>[142,'<SINGLE SHIFT TWO>','Cc Xl','Common','�'],
+q{S3}=>[143,'<SINGLE SHIFT THREE>','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,'<START OF SELECTED AREA>','Cc Xl','Common'],
-q{SB}=>[9242,'<SUBSTITUTE>','Cc Xa','Common'],
-q{SC}=>[154,'<SINGLE CHARACTER INTRODUCER>','Cc Xl','Common'],
+q{SA}=>[134,'<START OF SELECTED AREA>','Cc Xl','Common','�'],
+q{SB}=>[26,'<SUBSTITUTE>','Cc Xa','Common','␚'],
+q{SC}=>[154,'<SINGLE CHARACTER INTRODUCER>','Cc Xl','Common','�'],
 q{SE}=>[167,'SECTION SIGN','So Xl','Common'],
-q{SG}=>[150,'<START OF GUARDED AREA>','Cc Xl','Common'],
-q{SH}=>[9217,'<START OF HEADING>','Cc Xa','Common'],
-q{SI}=>[9231,'<SHIFT IN>','Cc Xa','Common'],
+q{SG}=>[150,'<START OF GUARDED AREA>','Cc Xl','Common','�'],
+q{SH}=>[1,'<START OF HEADING>','Cc Xa','Common','␁'],
+q{SI}=>[15,'<SHIFT IN>','Cc Xa','Common','␏'],
 q{SJ}=>[12614,'HANGUL LETTER SSANGSIOS','Lo Xz','Hangul'],
 q{SM}=>[8480,'SERVICE MARK','So','Common'],
-q{SO}=>[9230,'<SHIFT OUT>','Cc Xa','Common'],
+q{SO}=>[14,'<SHIFT OUT>','Cc Xa','Common','␎'],
 q{SR}=>[9644,'BLACK RECTANGLE','So','Common'],
-q{SS}=>[152,'<START OF STRING>','Cc Xl','Common'],
-q{ST}=>[156,'<STRING TERMINATOR>','Cc Xl','Common'],
+q{SS}=>[152,'<START OF STRING>','Cc Xl','Common','�'],
+q{ST}=>[156,'<STRING TERMINATOR>','Cc Xl','Common','�'],
 q{SU}=>[9788,'WHITE SUN WITH RAYS','So','Common'],
-q{SX}=>[9218,'<START OF TEXT>','Cc Xa','Common'],
-q{SY}=>[9238,'<SYNCHRONOUS IDLE>','Cc Xa','Common'],
+q{SX}=>[2,'<START OF TEXT>','Cc Xa','Common','␂'],
+q{SY}=>[22,'<SYNCHRONOUS IDLE>','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'],
@@ -828,7 +828,7 @@ q{TE}=>[8707,'THERE EXISTS','Sm','Common'],
 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,'<SET TRANSMIT STATE>','Cc Xl','Common'],
+q{TS}=>[147,'<SET TRANSMIT STATE>','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'],
@@ -869,7 +869,7 @@ q{UJ}=>[12637,'HANGUL LETTER WEO','Lo Xz','Hangul'],
 q{UK}=>[12684,'HANGUL LETTER YU-I','Lo Xz','Hangul'],
 q{UL}=>[9499,'BOX DRAWINGS HEAVY UP AND LEFT','So','Common'],
 q{UR}=>[9495,'BOX DRAWINGS HEAVY UP AND RIGHT','So','Common'],
-q{US}=>[9247,'<INFORMATION SEPARATOR ONE>','Cc Xa','Common'],
+q{US}=>[31,'<INFORMATION SEPARATOR ONE>','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'],
@@ -885,8 +885,8 @@ q{VI}=>[581,'','Xn Xz',''],
 q{VJ}=>[12638,'HANGUL LETTER WE','Lo Xz','Hangul'],
 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,'<LINE TABULATION SET>','Cc Xl','Common'],
-q{VT}=>[9227,'<LINE TABULATION>','Cc Xa','Common'],
+q{VS}=>[138,'<LINE TABULATION SET>','Cc Xl','Common','�'],
+q{VT}=>[11,'<LINE TABULATION>','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'],
@@ -990,7 +990,7 @@ q{aJ}=>[12623,'HANGUL LETTER A','Lo Xz','Hangul'],
 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{aS}=>[1648,'ARABIC LETTER SUPERSCRIPT ALEF','Mn','Inherited','◌ٰ'],
 q{aa}=>[229,'LATIN SMALL LETTER A WITH RING ABOVE','Ll Xl','Latin'],
 q{ac}=>[8448,'ACCOUNT OF','So Xz','Common'],
 q{ae}=>[230,'LATIN SMALL LETTER AE','Ll Xl','Latin'],

diff --git a/digraphs.plp b/digraphs.plp
index a8f681d959b80a8b450ba7b62188dcd28e5c2663..ab04efd454afcc3b26bae5b94a8ebd5fc3193448 100644 (file)
--- a/digraphs.plp
+++ b/digraphs.plp
@@ -61,9 +61,9 @@ for my $c1group (@chars) {
                                printf '<td class="X Xr" title="%s">', quote($mnem);
                                next;
                        }
-                       my ($codepoint, $name, $prop, $script) = @{ $di->{$mnem} };
+                       my ($codepoint, $name, $prop, $script, $string) = @{ $di->{$mnem} };
 
-                       my $glyph = chr $codepoint;
+                       my $glyph = $string || chr $codepoint;
                        utf8::upgrade($glyph);  # prevent latin1 output
                        my $desc = $mnem . ($name && " ($name)");
                        my @class = ('X', grep {$_} $prop, $script);

diff --git a/rfc1345convert b/rfc1345convert
index c6131ad9f4034fdd93bde939c878deaa34f717e8..cf2d9379513ef43fb3f2874015b0c7bc5e928eed 100644 (file)
--- a/rfc1345convert
+++ b/rfc1345convert
@@ -124,14 +124,15 @@ for (values %info) {
 $info{$_}->{category} .= ' Xz' for @extra;
 
 for (keys %di) {
+       $info{$_}->{string} = chr(9676) . chr($di{$_}) if $info{$_}->{combining};
        # find control characters (first 32 chars from 0 and 128)
-       next if $di{$_} & ~0b1001_1111;
+       next unless ($di{$_} & ~0b1001_1111) == 0 or $di{$_} == 127;
        # rename to something more descriptive
        $info{$_}->{name} = $info{$_}->{unicode10}
                ? '<'.$info{$_}->{unicode10}.'>'  # the old name was much more useful
                : sprintf('<control U+%04X>', $di{$_});  # at least identify by value
        # show descriptive symbols instead of control chars themselves
-       $di{$_} += 0x2400 if $di{$_} < 32;
+       $info{$_}->{string} = $di{$_} < 32 ? chr($di{$_} + 0x2400) : chr(0xFFFD);
 }
 
 # output perl code of hash
@@ -141,9 +142,10 @@ printf '(map {$_=>0} qw{%s}),'."\n", join(' ',
        map { substr($_, 1, 1).substr($_, 0, 1) } sort keys %di
 );
 printf "q{%s}=>[%s],\n", $_, join(',',
-       $di{$_},       # glyph code point
+       $di{$_},   # original code point
        $info{$_}  # optional additional arguments
-               ? map {"'$_'"} @{ $info{$_} }{qw/name category script/}
+               ? map {"'$_'"} @{ $info{$_} }{qw/name category script/},
+                       $info{$_}->{string} || ()
                : ()
 ) for sort keys %di;
 print "}\n";