digraphs: separate rfc parser from include generator

[sheet.git] / tools / mkcharinfo

diff --git a/tools/mkcharinfo b/tools/mkcharinfo
index 27c11d93bcf53b34c50fdc3d895900cc1579c16c..23154959e50b654ff454ce50d8e6da1b5e842523 100755 (executable)
--- a/tools/mkcharinfo
+++ b/tools/mkcharinfo
@@ -11,9 +11,13 @@ use Data::Dump 'pp';
 our $VERSION = '1.00';
 
 my %info = (
+       # prepare presentational string for some control(lish) entries
        "\xAD"     => {string => '-'},
        "\x{200E}" => {string => '→'},
        "\x{200F}" => {string => '←'},
+       "\x{200B}" => {string => '␣'},
+       "\x{200C}" => {string => '|'}, # ISO-9995-7-081 lookalike (alt: ∣ ⊺ ⟙)
+       "\x{200D}" => {string => '⁀'}, # join (alt: ∤ |ͯ ⨝)
 );
 $info{chr $_} //= {} for 32 .. 126;
 
@@ -115,6 +119,7 @@ for my $chr (keys %info) {
 }
 
 # output perl code of hash
+say "# automatically generated by $0";
 say 'use utf8;';
 say '+{';
 for my $cp (sort keys %info) {