Use the "Unicode 1.0" name field for control characters,

as suggested by Mark Davis.  Note that Unicode 3.2 will
require some more legwork on this because of certain
alternative names.

p4raw-id: //depot/perl@14617

diff --git a/lib/unicore/Name.pl b/lib/unicore/Name.pl
index 27e37eb..3a753dd 100644 (file)
--- a/lib/unicore/Name.pl
+++ b/lib/unicore/Name.pl
@@ -3,7 +3,38 @@
 # Any changes made here will be lost!
 
 return <<'END';
-0000   001F    <control>
+0000           NULL
+0001           START OF HEADING
+0002           START OF TEXT
+0003           END OF TEXT
+0004           END OF TRANSMISSION
+0005           ENQUIRY
+0006           ACKNOWLEDGE
+0007           BELL
+0008           BACKSPACE
+0009           HORIZONTAL TABULATION
+000A           LINE FEED
+000B           VERTICAL TABULATION
+000C           FORM FEED
+000D           CARRIAGE RETURN
+000E           SHIFT OUT
+000F           SHIFT IN
+0010           DATA LINK ESCAPE
+0011           DEVICE CONTROL ONE
+0012           DEVICE CONTROL TWO
+0013           DEVICE CONTROL THREE
+0014           DEVICE CONTROL FOUR
+0015           NEGATIVE ACKNOWLEDGE
+0016           SYNCHRONOUS IDLE
+0017           END OF TRANSMISSION BLOCK
+0018           CANCEL
+0019           END OF MEDIUM
+001A           SUBSTITUTE
+001B           ESCAPE
+001C           FILE SEPARATOR
+001D           GROUP SEPARATOR
+001E           RECORD SEPARATOR
+001F           UNIT SEPARATOR
 0020           SPACE
 0021           EXCLAMATION MARK
 0022           QUOTATION MARK
@@ -99,7 +130,38 @@ return <<'END';
 007C           VERTICAL LINE
 007D           RIGHT CURLY BRACKET
 007E           TILDE
-007F   009F    <control>
+007F           DELETE
+0080   0081    <control>
+0082           BREAK PERMITTED HERE
+0083           NO BREAK HERE
+0084           <control>
+0085           NEXT LINE
+0086           START OF SELECTED AREA
+0087           END OF SELECTED AREA
+0088           CHARACTER TABULATION SET
+0089           CHARACTER TABULATION WITH JUSTIFICATION
+008A           LINE TABULATION SET
+008B           PARTIAL LINE DOWN
+008C           PARTIAL LINE UP
+008D           REVERSE LINE FEED
+008E           SINGLE SHIFT TWO
+008F           SINGLE SHIFT THREE
+0090           DEVICE CONTROL STRING
+0091           PRIVATE USE ONE
+0092           PRIVATE USE TWO
+0093           SET TRANSMIT STATE
+0094           CANCEL CHARACTER
+0095           MESSAGE WAITING
+0096           START OF GUARDED AREA
+0097           END OF GUARDED AREA
+0098           START OF STRING
+0099           <control>
+009A           SINGLE CHARACTER INTRODUCER
+009B           CONTROL SEQUENCE INTRODUCER
+009C           STRING TERMINATOR
+009D           OPERATING SYSTEM COMMAND
+009E           PRIVACY MESSAGE
+009F           APPLICATION PROGRAM COMMAND
 00A0           NO-BREAK SPACE
 00A1           INVERTED EXCLAMATION MARK
 00A2           CENT SIGN

diff --git a/lib/unicore/mktables b/lib/unicore/mktables
index 5f2cc82..0ca6dcd 100644 (file)
--- a/lib/unicore/mktables
+++ b/lib/unicore/mktables
@@ -706,6 +706,11 @@ sub UnicodeData_Txt()
             $title,     ## titlecase mapping
               ) = split(/\s*;\s*/);
 
+       # Note that in Unicode 3.2 there will be names like
+       # LINE FEED (LF), which probably means that \N{} needs
+       # to cope also with LINE FEED and LF.
+       $name = $unicode10 if $name eq '<control>' && $unicode10 ne '';
+
         my $code = hex($hexcode);
 
         if ($comb and $comb == 230) {