diff options
| author | Karl Williamson <public@khwilliamson.com> | 2012-09-02 16:48:14 -0600 |
|---|---|---|
| committer | Karl Williamson <public@khwilliamson.com> | 2012-09-13 21:14:02 -0600 |
| commit | 5e6c6c1e0c9ebf171541d4b160a124670d0d46d2 (patch) | |
| tree | 6916ef652abc796ff806fb5ce73d4c03a64af177 /regen/regcharclass.pl | |
| parent | 765ec46cc8c8533a1aed8a26490b879042d7fff3 (diff) | |
| download | perl-5e6c6c1e0c9ebf171541d4b160a124670d0d46d2.tar.gz | |
regen/regcharclass.pl: Allow comments in input
Lines whose first non-blank character is a '#' are now considered to be
comments, and ignored. This allows the moving of some lines that have
been commented out back to after the __DATA__ where they really belong.
Diffstat (limited to 'regen/regcharclass.pl')
| -rwxr-xr-x | regen/regcharclass.pl | 16 |
1 files changed, 8 insertions, 8 deletions
diff --git a/regen/regcharclass.pl b/regen/regcharclass.pl index 6225697c3e..e870df9409 100755 --- a/regen/regcharclass.pl +++ b/regen/regcharclass.pl @@ -303,10 +303,8 @@ sub new { } } next; - } elsif ( /\S/ ) { - die "Unparsable line: $txt\n"; } else { - next; + die "Unparsable line: $txt\n"; } my ( $cp, $low, $latin1, $utf8 )= __uni_latin1( $str ); my $UTF8= $low || $utf8; @@ -708,7 +706,7 @@ if ( !caller ) { }; while ( <DATA> ) { - s/^\s*#//; + s/^ \s* (?: \# .* ) ? $ //x; # squeeze out comment and blanks next unless /\S/; chomp; if ( /^([A-Z]+)/ ) { @@ -744,12 +742,16 @@ if ( !caller ) { # Accepts a single Unicode code point per line, prefaced by '0x' # or a range of two code points separated by a minus (and optional space) # or a single \p{} per line. +# A blank line or one whose first non-blank character is '#' is a comment # # If run on a non-ASCII platform will automatically convert the Unicode input # to native # -# This is no longer used, but retained in case it is needed some day. Put the -# lines below under __DATA__ + +1; # in the unlikely case we are being used as a module + +__DATA__ +# This is no longer used, but retained in case it is needed some day. # TRICKYFOLD: Problematic fold case letters. When adding to this list, also should add them to regcomp.c and fold_grind.t # => generic cp generic-cp generic-both :fast safe # 0x00DF # LATIN SMALL LETTER SHARP S @@ -759,9 +761,7 @@ if ( !caller ) { # 0x1FD3 # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA; maps same as 0390 # 0x1FE3 # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA; maps same as 03B0 -1; # in the unlikely case we are being used as a module -__DATA__ LNBREAK: Line Break: \R => generic UTF8 LATIN1 :fast safe "\x0D\x0A" # CRLF - Network (Windows) line ending |