2 # Copyright (C) 2014-2021 all contributors <meta@public-inbox.org>
3 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
5 # Stupid script to make HTML from preformatted, utf-8 text versions,
6 # only generating links for http(s). Markdown does too much
7 # and requires indentation to output preformatted text.
10 use PublicInbox::Linkify;
11 use PublicInbox::Hval qw(ascii_html);
18 lei-forget-external(1)
24 public-inbox-compact(1)
25 public-inbox-config(5)
26 public-inbox-convert(1)
27 public-inbox-daemon(8)
36 public-inbox-overview(7)
38 public-inbox-v1-format(5)
39 public-inbox-v2-format(5)
43 my ($n) = (/([\w\-\.]+)/);
44 $xurls{$_} = "$n.html";
45 $xurls{$n} = "$n.html";
48 for (qw[copydatabase(1) xapian-compact(1)]) {
49 my ($n) = (/([\w\-\.]+)/);
50 $xurls{$_} = ".$n.1.html"
53 for (qw[make(1) flock(2) setrlimit(2) vfork(2) tmpfs(5)]) {
54 my ($n, $s) = (/([\w\-]+)\((\d)\)/);
55 $xurls{$_} = "http://www.man7.org/linux/man-pages/man$s/$n.$s.html";
73 gitrepository-layout(5)
75 my ($n) = (/([\w\-\.]+)/);
76 $xurls{$_} = "https://kernel.org/pub/software/scm/git/docs/$n.html"
85 my ($n) = (/([\w\-\.]+)/);
86 $xurls{$_} = "https://www.freedesktop.org/software/systemd/man/$n.html";
89 $xurls{'netrc(5)'} = 'https://manpages.debian.org/stable/ftp/netrc.5.en.html';
91 'https://manpages.debian.org/stable/isync/mbsync.1.en.html';
92 $xurls{'offlineimap(1)'} =
93 'https://manpages.debian.org/stable/offlineimap/offlineimap.1.en.html';
95 'https://spamassassin.apache.org/full/3.4.x/doc/spamc.html';
97 'https://git.kernel.org/pub/scm/utils/grokmirror/grokmirror.git' .
98 '/tree/man/grok-pull.1.rst';
99 $xurls{'git-filter-repo(1)'} = 'https://github.com/newren/git-filter-repo'.
100 '/blob/master/Documentation/git-filter-repo.txt';
101 $xurls{'ssoma(1)'} = 'https://ssoma.public-inbox.org/ssoma.txt';
102 $xurls{'cgitrc(5)'} = 'https://git.zx2c4.com/cgit/tree/cgitrc.5.txt';
103 $xurls{'prove(1)'} = 'https://perldoc.perl.org/prove.html';
105 my $str = do { local $/; <STDIN> };
106 my ($title) = ($str =~ /\A([^\n]+)/);
107 if ($str =~ /^NAME\n\s+([^\n]+)/sm) {
108 # don't link to ourselves
110 if ($title =~ /([\w\.\-]+)/) {
114 $title = ascii_html($title);
115 my $l = PublicInbox::Linkify->new;
116 $str = $l->linkify_1($str);
117 $str = ascii_html($str);
119 # longest matches, first
120 my @keys = sort { length($b) <=> length($a) } keys %xurls;
121 my $xkeys = join('|', map { quotemeta } @keys);
122 $str =~ s,(?<![>\w_])($xkeys)(?!(?:[\w<\-]|\.html)),
123 qq(<a\nhref=").$xurls{$1}.qq(">$1).($2//'').'</a>',sge;
125 $str = $l->linkify_2($str);
127 print '<html><head>',
128 qq(<meta\nhttp-equiv="Content-Type"\ncontent="text/html; charset=utf-8"\n/>),
129 "<title>$title</title>",
130 "</head><body><pre>", $str , '</pre></body></html>';
133 # keep mtime on website consistent so clients can cache
134 if (-f STDIN && -f STDOUT) {
135 my @st = stat(STDIN);
136 utime($st[8], $st[9], \*STDOUT);