digraphs: control character names

Control characters are all named <control>, which is useless to discern
them (especially since these glyphs aren't very descriptive either).
Substitute the old Unicode 1.0 names for good identification purposes.
In the few (latin1) cases where there's no name, at least add the code
point.

diff --git a/digraphs.inc.pl b/digraphs.inc.pl
index cfa65d235f24182a655b3a4effb5dd5a6f864a9d..271d46490d4a75514a15de257c704aee8319b6ee 100644 (file)
--- a/digraphs.inc.pl
+++ b/digraphs.inc.pl
@@ -375,9 +375,9 @@ 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,'<control>','Cc Xl','Common'],
+q{AC}=>[159,'<APPLICATION PROGRAM COMMAND>','Cc Xl','Common'],
 q{AE}=>[198,'LATIN CAPITAL LETTER AE','Lu Xl','Latin'],
-q{AK}=>[6,'<control>','Cc Xa','Common'],
+q{AK}=>[9222,'<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'],
@@ -390,9 +390,9 @@ 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,'<control>','Cc Xl','Common'],
-q{BL}=>[7,'<control>','Cc Xa','Common'],
-q{BS}=>[8,'<control>','Cc Xa','Common'],
+q{BH}=>[130,'<BREAK PERMITTED HERE>','Cc Xl','Common'],
+q{BL}=>[9223,'<BELL>','Cc Xa','Common'],
+q{BS}=>[9224,'<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'],
@@ -410,11 +410,11 @@ 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,'<control>','Cc Xl','Common'],
+q{CC}=>[148,'<CANCEL CHARACTER>','Cc Xl','Common'],
 q{CG}=>[8766,'INVERTED LAZY S','Sm','Common'],
-q{CI}=>[155,'<control>','Cc Xl','Common'],
-q{CN}=>[24,'<control>','Cc Xa','Common'],
-q{CR}=>[13,'<control>','Cc Xa','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{Ca}=>[8248,'CARET','Po','Common'],
 q{Ci}=>[57372,'','Co','Common'],
 q{Co}=>[169,'COPYRIGHT SIGN','So Xl','Common'],
@@ -427,19 +427,19 @@ 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}=>[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{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{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,'<control>','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{DL}=>[16,'<control>','Cc Xa','Common'],
+q{DL}=>[9232,'<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'],
@@ -478,15 +478,15 @@ 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}=>[23,'<control>','Cc Xa','Common'],
-q{EC}=>[27,'<control>','Cc Xa','Common'],
+q{EB}=>[9239,'<END OF TRANSMISSION BLOCK>','Cc Xa','Common'],
+q{EC}=>[9243,'<ESCAPE>','Cc Xa','Common'],
 q{ED}=>[439,'LATIN CAPITAL LETTER EZH','Lu','Latin'],
-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{EG}=>[151,'<END OF GUARDED AREA>','Cc Xl','Common'],
+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{EZ}=>[494,'LATIN CAPITAL LETTER EZH WITH CARON','Lu','Latin'],
 q{Eh}=>[8962,'HOUSE','So','Common'],
 q{Eu}=>[8364,'EURO SIGN','Sc Xz','Common'],
@@ -498,9 +498,9 @@ 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 Xa','Common'],
+q{FF}=>[9228,'<FORM FEED (FF)>','Cc Xa','Common'],
 q{FI}=>[8498,'TURNED CAPITAL F','So Xz','Common'],
-q{FS}=>[28,'<control>','Cc Xa','Common'],
+q{FS}=>[9244,'<INFORMATION SEPARATOR FOUR>','Cc Xa','Common'],
 q{Fd}=>[9698,'BLACK LOWER RIGHT TRIANGLE','So','Common'],
 q{Fl}=>[57379,'','Co','Common'],
 q{Fm}=>[9792,'FEMALE SIGN','So','Common'],
@@ -518,9 +518,9 @@ 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 Xl','Common'],
+q{GC}=>[153,'<control U+0099>','Cc Xl','Common'],
 q{GF}=>[57380,'','Co','Common'],
-q{GS}=>[29,'<control>','Cc Xa','Common'],
+q{GS}=>[9245,'<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'],
@@ -537,10 +537,10 @@ 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,'<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{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{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'],
@@ -569,7 +569,7 @@ 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>','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'],
@@ -616,7 +616,7 @@ 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}=>[10,'<control>','Cc Xa','Common'],
+q{LF}=>[9226,'<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'],
@@ -631,7 +631,7 @@ 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,'<control>','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'],
@@ -658,14 +658,14 @@ 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,'<control>','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}=>[21,'<control>','Cc Xa','Common'],
-q{NL}=>[133,'<control>','Cc Xl','Common'],
+q{NK}=>[9237,'<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}=>[0,'<control>','Cc Xa','Common'],
+q{NU}=>[9216,'<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'],
@@ -696,7 +696,7 @@ 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,'<control>','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{OK}=>[10003,'CHECK MARK','So','Common'],
@@ -711,19 +711,19 @@ 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,'<control>','Cc Xl','Common'],
-q{P2}=>[146,'<control>','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>','Cc Xl','Common'],
-q{PD}=>[139,'<control>','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,'<control>','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,'<control>','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'],
@@ -748,10 +748,10 @@ 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 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}=>[30,'<control>','Cc Xa','Common'],
+q{RS}=>[9246,'<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'],
@@ -771,26 +771,26 @@ 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 Xl','Common'],
-q{S3}=>[143,'<control>','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,'<control>','Cc Xl','Common'],
-q{SB}=>[26,'<control>','Cc Xa','Common'],
-q{SC}=>[154,'<control>','Cc Xl','Common'],
+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{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{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{SM}=>[8480,'SERVICE MARK','So','Common'],
-q{SO}=>[14,'<control>','Cc Xa','Common'],
+q{SO}=>[9230,'<SHIFT OUT>','Cc Xa','Common'],
 q{SR}=>[9644,'BLACK RECTANGLE','So','Common'],
-q{SS}=>[152,'<control>','Cc Xl','Common'],
-q{ST}=>[156,'<control>','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}=>[2,'<control>','Cc Xa','Common'],
-q{SY}=>[22,'<control>','Cc Xa','Common'],
+q{SX}=>[9218,'<START OF TEXT>','Cc Xa','Common'],
+q{SY}=>[9238,'<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'],
@@ -815,7 +815,7 @@ 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,'<control>','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'],
@@ -854,7 +854,7 @@ 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 Xa','Common'],
+q{US}=>[9247,'<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'],
@@ -869,8 +869,8 @@ q{VH}=>[9547,'BOX DRAWINGS HEAVY VERTICAL AND HORIZONTAL','So','Common'],
 q{VI}=>[581,'','Xn Xz',''],
 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 Xl','Common'],
-q{VT}=>[11,'<control>','Cc Xa','Common'],
+q{VS}=>[138,'<LINE TABULATION SET>','Cc Xl','Common'],
+q{VT}=>[9227,'<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'],

diff --git a/rfc1345convert b/rfc1345convert
index 412bac14cbbd7cc50afc017301d627f158733dbe..d33377fc5cbd413c4b43f816dc15861357b1f4d0 100644 (file)
--- a/rfc1345convert
+++ b/rfc1345convert
@@ -77,6 +77,17 @@ for (values %info) {
 # mark unofficial extras as such
 $info{$_}->{category} .= ' Xz' for @extra;
 
+for (keys %di) {
+       # find control characters (first 32 chars from 0 and 128)
+       next if $di{$_} & ~0b1001_1111;
+       # 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;
+}
+
 # output perl code of hash
 # (assume no backslashes or curlies, so we can just q{} w/o escaping)
 print "{\n";