-# Copyright (C) 2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2019-2020 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
# show any VCS object, similar to "git show"
package PublicInbox::ViewVCS;
use strict;
use warnings;
-use Encode qw(find_encoding);
+use bytes (); # only for bytes::length
use PublicInbox::SolverGit;
use PublicInbox::WwwStream;
use PublicInbox::Linkify;
+use PublicInbox::Tmpfile;
use PublicInbox::Hval qw(ascii_html to_filename);
+my $hl = eval {
+ require PublicInbox::HlMod;
+ PublicInbox::HlMod->new;
+};
+
my %QP_MAP = ( A => 'oid_a', B => 'oid_b', a => 'path_a', b => 'path_b' );
-my $max_size = 1024 * 1024; # TODO: configurable
-my $enc_utf8 = find_encoding('UTF-8');
+our $MAX_SIZE = 1024 * 1024; # TODO: configurable
+my $BIN_DETECT = 8000; # same as git
+
+sub html_i { # WwwStream::getline callback
+ my ($nr, $ctx) = @_;
+ $nr == 1 ? ${delete $ctx->{obuf}} : undef;
+}
sub html_page ($$$) {
my ($ctx, $code, $strref) = @_;
+ my $wcb = delete $ctx->{-wcb};
$ctx->{-upfx} = '../../'; # from "/$INBOX/$OID/s/"
- PublicInbox::WwwStream->response($ctx, $code, sub {
- my ($nr, undef) = @_;
- $nr == 1 ? $$strref : undef;
- });
+ $ctx->{obuf} = $strref;
+ my $res = PublicInbox::WwwStream->response($ctx, $code, \&html_i);
+ $wcb ? $wcb->($res) : $res;
}
-sub show ($$;$) {
- my ($ctx, $oid_b, $fn) = @_;
- my $ibx = $ctx->{-inbox};
- my $inboxes = [ $ibx ];
- my $solver = PublicInbox::SolverGit->new($ibx->{-repo_objs}, $inboxes);
- my $qp = $ctx->{qp};
- my $hints = {};
- while (my ($from, $to) = each %QP_MAP) {
- defined(my $v = $qp->{$from}) or next;
- $hints->{$to} = $v;
+sub stream_blob_parse_hdr { # {parse_hdr} for Qspawn
+ my ($r, $bref, $ctx) = @_;
+ my ($res, $logref) = delete @$ctx{qw(-res -logref)};
+ my ($git, $oid, $type, $size, $di) = @$res;
+ my @cl = ('Content-Length', $size);
+ if (!defined $r) { # error
+ html_page($ctx, 500, $logref);
+ } elsif (index($$bref, "\0") >= 0) {
+ [200, [qw(Content-Type application/octet-stream), @cl] ];
+ } else {
+ my $n = bytes::length($$bref);
+ if ($n >= $BIN_DETECT || $n == $size) {
+ return [200, [ 'Content-Type',
+ 'text/plain; charset=UTF-8', @cl ] ];
+ }
+ if ($r == 0) {
+ warn "premature EOF on $oid $$logref\n";
+ return html_page($ctx, 500, $logref);
+ }
+ undef; # bref keeps growing
+ }
+}
+
+sub stream_large_blob ($$$$) {
+ my ($ctx, $res, $logref, $fn) = @_;
+ $ctx->{-logref} = $logref;
+ $ctx->{-res} = $res;
+ my ($git, $oid, $type, $size, $di) = @$res;
+ my $cmd = ['git', "--git-dir=$git->{git_dir}", 'cat-file', $type, $oid];
+ my $qsp = PublicInbox::Qspawn->new($cmd);
+ my $env = $ctx->{env};
+ $env->{'qspawn.wcb'} = delete $ctx->{-wcb};
+ $qsp->psgi_return($env, undef, \&stream_blob_parse_hdr, $ctx);
+}
+
+sub show_other_result ($$) {
+ my ($bref, $ctx) = @_;
+ my ($qsp, $logref) = delete @$ctx{qw(-qsp -logref)};
+ if (my $err = $qsp->{err}) {
+ utf8::decode($$err);
+ $$logref .= "git show error: $err";
+ return html_page($ctx, 500, $logref);
+ }
+ my $l = PublicInbox::Linkify->new;
+ utf8::decode($$bref);
+ $$bref = '<pre>'. $l->to_html($$bref);
+ $$bref .= '</pre><hr>' . $$logref;
+ html_page($ctx, 200, $bref);
+}
+
+sub show_other ($$$$) {
+ my ($ctx, $res, $logref, $fn) = @_;
+ my ($git, $oid, $type, $size) = @$res;
+ if ($size > $MAX_SIZE) {
+ $$logref = "$oid is too big to show\n" . $$logref;
+ return html_page($ctx, 200, $logref);
}
+ my $cmd = ['git', "--git-dir=$git->{git_dir}",
+ qw(show --encoding=UTF-8 --no-color --no-abbrev), $oid ];
+ my $qsp = PublicInbox::Qspawn->new($cmd);
+ my $env = $ctx->{env};
+ $ctx->{-qsp} = $qsp;
+ $ctx->{-logref} = $logref;
+ $qsp->psgi_qx($env, undef, \&show_other_result, $ctx);
+}
- open my $log, '+>', undef or die "open: $!";
- my $res = $solver->solve($log, $oid_b, $hints);
+# user_cb for SolverGit, called as: user_cb->($result_or_error, $uarg)
+sub solve_result {
+ my ($res, $ctx) = @_;
+ my ($log, $hints, $fn) = delete @$ctx{qw(log hints fn)};
- seek($log, 0, 0) or die "seek: $!";
+ unless (seek($log, 0, 0)) {
+ $ctx->{env}->{'psgi.errors'}->print("seek(log): $!\n");
+ return html_page($ctx, 500, \'seek error');
+ }
$log = do { local $/; <$log> };
+ my $ref = ref($res);
my $l = PublicInbox::Linkify->new;
- $l->linkify_1($log);
$log = '<pre>debug log:</pre><hr /><pre>' .
- $l->linkify_2(ascii_html($log)) . '</pre>';
+ $l->to_html($log) . '</pre>';
$res or return html_page($ctx, 404, \$log);
+ $ref eq 'ARRAY' or return html_page($ctx, 500, \$log);
my ($git, $oid, $type, $size, $di) = @$res;
- if ($size > $max_size) {
- # TODO: stream the raw file if it's gigantic, at least
- $log = '<pre><b>Too big to show</b></pre>' . $log;
- return html_page($ctx, 500, \$log);
+ return show_other($ctx, $res, \$log, $fn) if $type ne 'blob';
+ my $path = to_filename($di->{path_b} || $hints->{path_b} || 'blob');
+ my $raw_link = "(<a\nhref=$path>raw</a>)";
+ if ($size > $MAX_SIZE) {
+ return stream_large_blob($ctx, $res, \$log, $fn) if defined $fn;
+ $log = "<pre><b>Too big to show, download available</b>\n" .
+ "$oid $type $size bytes $raw_link</pre>" . $log;
+ return html_page($ctx, 200, \$log);
}
my $blob = $git->cat_file($oid);
return html_page($ctx, 500, \$log);
}
- my $binary = index($$blob, "\0") >= 0;
- if ($fn) {
+ my $bin = index(substr($$blob, 0, $BIN_DETECT), "\0") >= 0;
+ if (defined $fn) {
my $h = [ 'Content-Length', $size, 'Content-Type' ];
- push(@$h, ($binary ? 'application/octet-stream' : 'text/plain'));
- return [ 200, $h, [ $$blob ]];
+ push(@$h, ($bin ? 'application/octet-stream' : 'text/plain'));
+ return delete($ctx->{-wcb})->([200, $h, [ $$blob ]]);
}
- my $path = to_filename($di->{path_b} || $hints->{path_b} || 'blob');
- my $raw_link = "(<a\nhref=$path>raw</a>)";
- if ($binary) {
+ if ($bin) {
$log = "<pre>$oid $type $size bytes (binary)" .
" $raw_link</pre>" . $log;
return html_page($ctx, 200, \$log);
}
- $$blob = $enc_utf8->decode($$blob);
+ # TODO: detect + convert to ensure validity
+ utf8::decode($$blob);
my $nl = ($$blob =~ tr/\n/\n/);
my $pad = length($nl);
+ $l->linkify_1($$blob);
+ my $ok = $hl->do_hl($blob, $path) if $hl;
+ if ($ok) {
+ $blob = $ok;
+ } else {
+ $$blob = ascii_html($$blob);
+ }
+
# using some of the same CSS class names and ids as cgit
$log = "<pre>$oid $type $size bytes $raw_link</pre>" .
"<hr /><table\nclass=blob>".
sprintf("<a id=n$_ href=#n$_>% ${pad}u</a>\n", $_)
} (1..$nl)) . '</pre></td>' .
'<td><pre> </pre></td>'. # pad for non-CSS users
- "<td\nclass=lines><pre><code>" . ascii_html($$blob) .
+ "<td\nclass=lines><pre\nstyle='white-space:pre'><code>" .
+ $l->linkify_2($$blob) .
'</code></pre></td></tr></table>' . $log;
html_page($ctx, 200, \$log);
}
+sub show ($$;$) {
+ my ($ctx, $oid_b, $fn) = @_;
+ my $qp = $ctx->{qp};
+ my $hints = $ctx->{hints} = {};
+ while (my ($from, $to) = each %QP_MAP) {
+ defined(my $v = $qp->{$from}) or next;
+ $hints->{$to} = $v;
+ }
+
+ $ctx->{'log'} = tmpfile("solve.$oid_b");
+ $ctx->{fn} = $fn;
+ my $solver = PublicInbox::SolverGit->new($ctx->{-inbox},
+ \&solve_result, $ctx);
+ # PSGI server will call this immediately and give us a callback (-wcb)
+ sub {
+ $ctx->{-wcb} = $_[0]; # HTTP write callback
+ $solver->solve($ctx->{env}, $ctx->{log}, $oid_b, $hints);
+ };
+}
+
1;