Re: Linux man-pages PDF book

[Alejandro Colomar <alx@kernel.org>]

[-- Attachment #1: Type: text/plain, Size: 5128 bytes --]

Hi Deri,

On Tue, Apr 16, 2024 at 01:14:12AM +0100, Deri wrote:
> diff --git a/share/mk/build/pdf/book/prepare.pl b/share/mk/build/pdf/book/prepare.pl
> index e23f149c6..bc922bd88 100755
> --- a/share/mk/build/pdf/book/prepare.pl
> +++ b/share/mk/build/pdf/book/prepare.pl
> @@ -1,4 +1,4 @@
> -#!/usr/bin/perl -w
> +#!/usr/bin/perl -wd
>  #
>  #	BuildLinuxMan.pl		: Build Linux manpages book
>  #	Deri James (& Brian Inglis)	: 15 Dec 2022
> @@ -49,16 +49,16 @@ my $dir2=$dir;
>  $dir2=~tr[.][_];
>  my %files;
>  my %aliases;
> -my %target;
> +my %revalias;
>  
>  foreach my $al (`find "$dir"/man*/ -type f \\
>  		| grep "\\.[[:digit:]]\\([[:alpha:]][[:alnum:]]*\\)\\?\\>\$" \\
>  		| xargs grep '^\\.so' /dev/null;`)
>  {
>  	#$al=~tr[.][_];
> -	$al=~m/^$dir\/man\d[a-z]*\/(.*):\.\s*so\s*man\d[a-z]*\/(.*)/o;
> +	$al=~m/^$dir\/man\d[a-z]*\/(.*):\.\s*so\s*man\d[a-z]*\/(.*?)\.(.*)/o;

Your annotation said:

	-	$al=~m/^$dir\/man\d[a-z]*\/(.*):\.\s*so\s*man\d[a-z]*\/(.*)/o;
	+	$al=~m/^$dir\/man\d[a-z]*\/(.*):\.\s*so\s*man\d[a-z]*\/(.*?)\.(.*)/o;
	Example:-
	./man2/rt_sigaction.2:.so man2/sigaction.2
	==============
	========= =
	$1
	$2
	$3
	Capture the file name extension in $3.

But the regex is wrong, I think.  Consider this part of the regex:

	(.*?)\.(.*)

For a page like gai.conf.5, the section would be 'conf.5'.  The '?' is
spurious, I think.

>  
> -	$aliases{$1}=$2;
> +	$aliases{$1}="$2($3)";
>  }
>  
>  while (my ($k,$v)=each %aliases)
> @@ -68,13 +68,18 @@ while (my ($k,$v)=each %aliases)
>  	}
>  }
>  
> +while (my ($k,$v)=each %aliases)
> +{
> +	push(@{$revalias{$v}},$k);
> +}
> +
>  foreach my $fn (`find "$dir"/man*/ -type f \\
>  		| grep "\\.[[:digit:]]\\([[:alpha:]][[:alnum:]]*\\)\\?\\>\$";`)
>  {
>  	$fn=~s/\n//;
>  
>  	my ($nm,$sec)=GetNmSec($fn,qr/\.\d[a-z]*/);
> -	$files{"${nm}.$sec"}=[$fn,(exists($aliases{"${nm}.$sec"}))?$aliases{"${nm}.$sec"}:"${nm}.$sec"];
> +	$files{"${nm}.$sec"}=[$fn,(exists($aliases{"${nm}.$sec"}))?$aliases{"${nm}.$sec"}:"${nm}($sec)"];
>  }
>  
>  my $Section='';
> @@ -97,7 +102,7 @@ sub BuildPage
>  	my $fn=$files{$bkmark}->[0];
>  	my ($nm,$sec,$srt)=GetNmSec($bkmark,qr/\.[\da-z]+/);
>  
> -	my $title= "$nm\\($sec\\)";
> +	my $title= "$nm($sec)";
>  
>  	print ".\\\" >>>>>> $nm($sec) <<<<<<\n.lf 0 $bkmark\n";
>  
> @@ -112,8 +117,10 @@ sub BuildPage
>  		$Section=$sec;
>  	}
>  
> -	if (exists($aliases{$bkmark})) {
> +	if (exists($aliases{$bkmark}))
> +	{
>  		print ".eo\n.device ps:exec [/Dest /$aliases{$bkmark} /Title ($title) /Level 2 /OUT pdfmark\n.ec\n.fl\n";
> +# 		print ".pdfbookmark 2 $nm($sec)";
>  		return;
>  	}
>  
> @@ -137,7 +144,7 @@ sub BuildPage
>  
>  			s/\\-/-/g if /^\.[BM]R\s+/;
>  
> -			if (m/^\.BR\s+([-\w\\.]+)\s+\((.+?)\)(.*)/ or m/^\.MR\s+([-\w\\.]+)\s+(\w+)\s+(.*)/ or m/^\\fB([-\w\\.]+)\\fR\((.+?)\)(.*)$/) {
> +			if (m/^\.BR\s+([-\w\\.]+)\s+\(([\d\w]+?)\)(.*)/ or m/^\.MR\s+([-\w\\.]+)\s+(\w+)\s+(.*)/ or m/^\\fB([-\w\\.]+)\\fR\((.+?)\)(.*)$/) {

This regex might have similar issues (although they aren't being
introduced now).  And there might be others too.

BTW, your annotation was:

	Not completely sure if this change is necessary, just nervous
	about (.+?) as a pattern.

Agree; but there are more (.+?) in the same regex.


Have a lovely night!
Alex

>  				my $bkmark="$1";
>  				my $sec=$2;
>  				my $after=$3;
> @@ -145,12 +152,7 @@ sub BuildPage
>  				my $dest=$bkmark;
>  				$dest=~s/\\-/-/g;
>  
> -				if (exists($files{"${bkmark}.$sec"})) {
> -					my $dest=$files{"${bkmark}.$sec"}->[1];
> -					$_=".pdfhref L -D \"$dest\" -A \"$after\" -- \\fI$bkmark\\fP($sec)";
> -				} else {
> -					$_=".IR $bkmark ($sec)\\c\n$after";
> -				}
> +				$_=".MR \"$bkmark\" $sec $after";
>  			}
>  
>  			s/^\.BI \\fB/.BI /;
> @@ -175,16 +177,20 @@ sub BuildPage
>  				s/\n\n/\n/g;
>  			}
>  
> -			s/\\&\././ if m/^.TH /;
> -
> -			if (m/^\.TH\s+"?([-\w\\.]+)"?\s+"?(\w+)"?/) {
> -
> -				print "$_\n";
> -
> -				# Add a level two bookmark. We don't set it in the TH macro since the name passed
> -				# may be different from the filename, i.e. file = unimplemented.2, TH = UNIMPLEMENTED 2
> -
> -				print ".pdfbookmark -T $bkmark 2 $nm($sec)\n";
> +# 			s/\\&\././ if m/^.TH /;
> +#
> + 			if (m/^\.TH\s+"?([-\w\\.]+)"?\s+"?(\w+)"?(.*)/)
> + 			{
> +				print ".TH \"$nm\" \"$2\" $3\n";
> +
> +				if (exists($revalias{"$nm($sec)"}))
> +				{
> +					foreach my $dest (@{$revalias{"$nm($sec)"}})
> +					{
> +						my ($nm,$sec,$srt)=GetNmSec($dest,qr/\.[\da-z]+/);
> +						print ".pdfhref M -D $nm($sec)\n";
> +					}
> +				}
>  
>  				next;
>  			}
> @@ -199,11 +205,8 @@ sub doMR
>  	my $nm=shift;
>  	my $sec=shift;
>  
> -	if (exists($files{"${nm}.$sec"})) {
> -		return("\n.pdfhref L -D \"$files{\"${nm}.$sec\"}->[1]\" -A \"\\c\" -- \\fI$nm\\fP($sec)\n");
> -	} else {
> -		return("\\fI$nm\\fP($sec)");
> -	}
> +	return "\n.MR $nm $sec";
> +
>  }
>  
>  sub GetNmSec


-- 
<https://www.alejandro-colomar.es/>

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]