# used for displaying help texts and other non-mail content
package PublicInbox::WwwText;
use strict;
use warnings;
use bytes (); # only for bytes::length
use PublicInbox::Linkify;
use PublicInbox::WwwStream;
use PublicInbox::Hval qw(ascii_html);
use URI::Escape qw(uri_escape_utf8);
use PublicInbox::GzipFilter qw(gzf_maybe);
our $QP_URL = 'https://xapian.org/docs/queryparser.html';
our $WIKI_URL = 'https://en.wikipedia.org/wiki';
my $hl = eval {
require PublicInbox::HlMod;
PublicInbox::HlMod->new
};
# /$INBOX/_/text/$KEY/ # KEY may contain slashes
# For now, "help" is the only supported $KEY
sub get_text {
my ($ctx, $key) = @_;
my $code = 200;
$key = 'help' if !defined $key; # this 302s to _/text/help/
# get the raw text the same way we get mboxrds
my $raw = ($key =~ s!/raw\z!!);
my $have_tslash = ($key =~ s!/\z!!) if !$raw;
my $txt = '';
my $hdr = [ 'Content-Type', 'text/plain', 'Content-Length', undef ];
if (!_default_text($ctx, $key, $hdr, \$txt)) {
$code = 404;
$txt = "404 Not Found ($key)\n";
}
my $env = $ctx->{env};
if ($raw) {
if ($code == 200) {
my $gzf = gzf_maybe($hdr, $env);
$txt = $gzf->translate($txt);
$txt .= $gzf->zflush;
}
$hdr->[3] = bytes::length($txt);
return [ $code, $hdr, [ $txt ] ]
}
# enforce trailing slash for "wget -r" compatibility
if (!$have_tslash && $code == 200) {
my $url = $ctx->{-inbox}->base_url($env);
$url .= "_/text/$key/";
return [ 302, [ 'Content-Type', 'text/plain',
'Location', $url ],
[ "Redirecting to $url\n" ] ];
}
# Follow git commit message conventions,
# first line is the Subject/title
my ($title) = ($txt =~ /\A([^\n]*)/s);
$ctx->{-title_html} = ascii_html($title);
my $nslash = ($key =~ tr!/!/!);
$ctx->{-upfx} = '../../../' . ('../' x $nslash);
my $l = PublicInbox::Linkify->new;
$l->linkify_1($txt);
if ($hl) {
$hl->do_hl_text(\$txt);
} else {
$txt = ascii_html($txt);
}
$txt = '' . $l->linkify_2($txt) . '
';
PublicInbox::WwwStream::html_oneshot($ctx, $code, \$txt);
}
sub _srch_prefix ($$) {
my ($srch, $txt) = @_;
my $pad = 0;
my $htxt = '';
my $help = $srch->help;
my $i;
for ($i = 0; $i < @$help; $i += 2) {
my $pfx = $help->[$i];
my $n = length($pfx);
$pad = $n if $n > $pad;
$htxt .= $pfx . "\0";
$htxt .= $help->[$i + 1];
$htxt .= "\f\n";
}
$pad += 2;
my $padding = ' ' x ($pad + 8);
$htxt =~ s/^/$padding/gms;
$htxt =~ s/^$padding(\S+)\0/" $1".
(' ' x ($pad - length($1)))/egms;
$htxt =~ s/\f\n/\n/gs;
$$txt .= $htxt;
1;
}
sub _colors_help ($$) {
my ($ctx, $txt) = @_;
my $ibx = $ctx->{-inbox};
my $env = $ctx->{env};
my $base_url = $ibx->base_url($env);
$$txt .= "color customization for $base_url\n";
$$txt .= <{-inbox};
push @$hdr, 'Content-Disposition', 'inline; filename=inbox.config';
my $name = dq_escape($ibx->{name});
my $inboxdir = '/path/to/top-level-inbox';
my $base_url = $ibx->base_url($ctx->{env});
$$txt .= <{$k}) or next;
$$txt .= "\t$k = $_\n" for @$v;
}
if (my $altid = $ibx->{altid}) {
my $altid_map = $ibx->altid_map;
$$txt .= <{$k}) or next;
$$txt .= "\t$k = $v\n";
}
$$txt .= "\tnntpmirror = $_\n" for (@{$ibx->nntp_url});
# note: this doesn't preserve cgitrc layout, since we parse cgitrc
# and drop the original structure
if (defined(my $cr = $ibx->{coderepo})) {
$$txt .= "\tcoderepo = $_\n" for @$cr;
$$txt .= <<'EOF';
; `coderepo' entries allows blob reconstruction via patch emails if
; the inbox is indexed with Xapian. `@@ @@'
; line number ranges in `[PATCH]' emails link to /$INBOX_NAME/$OID/s/,
; an HTTP endpoint which reconstructs git blobs via git-apply(1).
EOF
my $pi_config = $ctx->{www}->{pi_config};
for my $cr_name (@$cr) {
my $urls = $pi_config->{"coderepo.$cr_name.cgiturl"};
my $path = "/path/to/$cr_name";
$cr_name = dq_escape($cr_name);
$$txt .= qq([coderepo "$cr_name"]\n);
if ($urls && scalar(@$urls)) {
$$txt .= "\t; ";
$$txt .= join(" ||\n\t;\t", map {;
my $dst = $path;
if ($path !~ m![a-z0-9_/\.\-]!i) {
$dst = '"'.dq_escape($dst).'"';
}
qq(git clone $_ $dst);
} @$urls);
$$txt .= "\n";
}
$$txt .= "\tdir = $path\n";
$$txt .= "\tcgiturl = https://example.com/";
$$txt .= uri_escape_utf8($cr_name, URI_PATH)."\n";
}
}
1;
}
sub _default_text ($$$$) {
my ($ctx, $key, $hdr, $txt) = @_;
return _colors_help($ctx, $txt) if $key eq 'color';
return inbox_config($ctx, $hdr, $txt) if $key eq 'config';
return if $key ne 'help'; # TODO more keys?
my $ibx = $ctx->{-inbox};
my $base_url = $ibx->base_url($ctx->{env});
$$txt .= "public-inbox help for $base_url\n";
$$txt .= <') into the URL.
Forward slash ('/') characters in the Message-IDs
need to be escaped as "%2F" (without quotes).
Thus, it is possible to retrieve any message by its
Message-ID by going to:
$base_url/
(without the '<' or '>')
Message-IDs are described at:
$WIKI_URL/Message-ID
EOF
# n.b. we use the Xapian DB for any regeneratable,
# order-of-arrival-independent data.
my $srch = $ibx->search;
if ($srch) {
$$txt .= <over;
if ($over) {
$$txt .= </T/#u
Loads the thread belonging to the given
in flat chronological order. The "#u" anchor
focuses the browser on the given .
* $base_url/t/#u
Loads the thread belonging to the given
in threaded order with nesting. For deep threads,
this requires a wide display or horizontal scrolling.
Both of these HTML endpoints are suitable for offline reading
using the thread overview at the bottom of each page.
Users of feed readers may follow a particular thread using:
* $base_url/t.atom
Which loads the thread in Atom Syndication Standard
described at Wikipedia and RFC4287:
$WIKI_URL/Atom_(standard)
https://tools.ietf.org/html/rfc4287
Atom Threading Extensions (RFC4685) is supported:
https://tools.ietf.org/html/rfc4685
Finally, the gzipped mbox for a thread is available for
downloading and importing into your favorite mail client:
* $base_url/t.mbox.gz
We use the mboxrd variant of the mbox format described
at:
$WIKI_URL/Mbox
EOF
} # $over
$$txt .= <