-# Copyright (C) 2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 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"
-# FIXME: we only show blobs for now
#
# This can use a "solver" to reconstruct blobs based on git
# patches (with abbreviated OIDs in the header). However, the
package PublicInbox::ViewVCS;
use strict;
-use warnings;
-use Encode qw(find_encoding);
+use v5.10.1;
+use File::Temp 0.19 (); # newdir
use PublicInbox::SolverGit;
-use PublicInbox::WwwStream;
+use PublicInbox::WwwStream qw(html_oneshot);
use PublicInbox::Linkify;
+use PublicInbox::Tmpfile;
+use PublicInbox::ViewDiff qw(flush_diff);
use PublicInbox::Hval qw(ascii_html to_filename);
-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');
+my $hl = eval {
+ require PublicInbox::HlMod;
+ PublicInbox::HlMod->new;
+};
+
+my %QP_MAP = ( A => 'oid_a', a => 'path_a', b => 'path_b' );
+our $MAX_SIZE = 1024 * 1024; # TODO: configurable
+my $BIN_DETECT = 8000; # same as git
+my $SHOW_FMT = '--pretty=format:'.join('%n', '%H', '%T', '%P', '%s',
+ '%an <%ae>%x09%ai', '%cn <%ce>%x09%ci', '%b%x00');
sub html_page ($$$) {
my ($ctx, $code, $strref) = @_;
my $wcb = delete $ctx->{-wcb};
$ctx->{-upfx} = '../../'; # from "/$INBOX/$OID/s/"
- my $res = PublicInbox::WwwStream->response($ctx, $code, sub {
- my ($nr, undef) = @_;
- $nr == 1 ? $$strref : undef;
- });
- $wcb->($res);
+ my $res = html_oneshot($ctx, $code, $strref);
+ $wcb ? $wcb->($res) : $res;
+}
+
+sub stream_blob_parse_hdr { # {parse_hdr} for Qspawn
+ my ($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($$bref, "\0") >= 0) {
+ [200, [qw(Content-Type application/octet-stream), @cl] ];
+ } else {
+ my $n = length($$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 $$logref";
+ return html_page($ctx, 500, $logref);
+ }
+ @$ctx{qw(-res -logref)} = ($res, $logref);
+ undef; # bref keeps growing
+ }
+}
+
+sub stream_large_blob ($$$$) {
+ my ($ctx, $res, $logref, $fn) = @_;
+ $ctx->{-logref} = $logref;
+ $ctx->{-res} = $res;
+ my ($git, $oid, $type, $size, $di) = @$res;
+ my $cmd = ['git', "--git-dir=$git->{git_dir}", 'cat-file', $type, $oid];
+ my $qsp = PublicInbox::Qspawn->new($cmd);
+ my $env = $ctx->{env};
+ $env->{'qspawn.wcb'} = delete $ctx->{-wcb};
+ $qsp->psgi_return($env, undef, \&stream_blob_parse_hdr, $ctx);
+}
+
+sub show_other_result ($$) {
+ my ($bref, $ctx) = @_;
+ my ($qsp_err, $logref) = delete @$ctx{qw(-qsp_err -logref)};
+ if ($qsp_err) {
+ $$logref .= "git show error:$qsp_err";
+ return html_page($ctx, 500, $logref);
+ }
+ my $l = PublicInbox::Linkify->new;
+ utf8::decode($$bref);
+ $$bref = '<pre>'. $l->to_html($$bref);
+ $$bref .= '</pre><hr>' . $$logref;
+ html_page($ctx, 200, $bref);
+}
+
+sub show_commit_result ($$) {
+ my ($bref, $ctx) = @_;
+ my ($qsp_err, $logref, $tmp) = @$ctx{qw(-qsp_err -logref -tmp)};
+ if ($qsp_err) {
+ $$logref .= "git show/patch-id error:$qsp_err";
+ return html_page($ctx, 500, $logref);
+ }
+ my $upfx = $ctx->{-upfx} = '../../'; # from "/$INBOX/$OID/s/"
+ my $patchid = (split(/ /, $$bref))[0]; # ignore commit
+ if (defined $patchid) {
+ $ctx->{-q_value_html} = "patchid:$patchid";
+ $patchid = "\n patchid $patchid";
+ } else {
+ $patchid = '';
+ }
+ my $l = $ctx->{-linkify} = PublicInbox::Linkify->new;
+ open my $fh, '<:utf8', "$tmp/h" or die "open $tmp/h: $!";
+ chop(my $buf = do { local $/ = "\0"; <$fh> });
+ my ($H, $T, $P, $s, $au, $co, $bdy) = split(/\n/, $buf, 7);
+ chomp $bdy;
+ # try to keep author and committer dates lined up
+ my $x = length($au) - length($co);
+ if ($x > 0) {
+ $x = ' ' x $x;
+ $co =~ s/\t/$x\t/;
+ } elsif ($x < 0) {
+ $x = ' ' x (-$x);
+ $au =~ s/\t/$x\t/;
+ }
+ $_ = ascii_html($_) for ($au, $co);
+ $_ = $l->to_html($_) for ($s, $bdy);
+ $ctx->{-title_html} = $s;
+ my @p = split(/ /, $P);
+ if (@p == 1) {
+ $P = qq(\n parent <a href="$upfx$P/s/">$P</a>);
+ } elsif (@p > 1) {
+ $P = qq(\n parents <a href="$upfx$p[0]/s/">$p[0]</a>\n);
+ shift @p;
+ $P .= qq( <a href="$upfx$_/s/">$_</a>\n) for @p;
+ chop $P;
+ } else { # root commit
+ $P = ' (root commit)';
+ }
+ PublicInbox::WwwStream::html_init($ctx);
+ $ctx->zmore(<<EOM);
+<pre> commit $H$P
+ tree <a href="$upfx$T/s/">$T</a>
+ author $au
+committer $co$patchid
+
+<b>$s</b>\n
+EOM
+ $ctx->zmore($bdy);
+ open $fh, '<', "$tmp/p" or die "open $tmp/p: $!";
+ if (-s $fh > $MAX_SIZE) {
+ $ctx->zmore("---\n patch is too large to show\n");
+ } else { # prepare flush_diff:
+ $buf = '';
+ $ctx->{obuf} = \$buf;
+ $ctx->{-apfx} = $ctx->{-spfx} = $upfx;
+ $ctx->{-anchors} = {};
+ $bdy = '';
+ read($fh, $bdy, -s _);
+ $bdy =~ s/\r?\n/\n/gs;
+ flush_diff($ctx, \$bdy);
+ $ctx->zmore($buf);
+ }
+ $x = $ctx->zflush($ctx->_html_end);
+ my $res_hdr = delete $ctx->{-res_hdr};
+ push @$res_hdr, 'Content-Length', length($x);
+ delete($ctx->{env}->{'qspawn.wcb'})->([200, $res_hdr, [$x]]);
+}
+
+sub show_commit ($$$$) {
+ my ($ctx, $res, $logref, $fn) = @_;
+ my ($git, $oid) = @$res;
+ # patch-id needs two passes, and we use the initial show to ensure
+ # a patch embedded inside the commit message body doesn't get fed
+ # to patch-id:
+ my $cmd = [ '/bin/sh', '-c',
+ "git show '$SHOW_FMT' -z --no-notes --no-patch $oid >h && ".
+ "git show --pretty=format:%n -M --stat -p $oid >p && ".
+ "git patch-id --stable <p" ];
+ my $xenv = { GIT_DIR => $git->{git_dir} };
+ my $tmp = File::Temp->newdir("show-$oid-XXXX", TMPDIR => 1);
+ my $qsp = PublicInbox::Qspawn->new($cmd, $xenv, { -C => "$tmp" });
+ $qsp->{qsp_err} = \($ctx->{-qsp_err} = '');
+ $ctx->{-logref} = $logref;
+ $ctx->{-tmp} = $tmp;
+ $ctx->{env}->{'qspawn.wcb'} = delete $ctx->{-wcb};
+ $qsp->psgi_qx($ctx->{env}, undef, \&show_commit_result, $ctx);
+}
+
+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);
+ $qsp->{qsp_err} = \($ctx->{-qsp_err} = '');
+ $ctx->{-logref} = $logref;
+ $qsp->psgi_qx($ctx->{env}, undef, \&show_other_result, $ctx);
}
+# user_cb for SolverGit, called as: user_cb->($result_or_error, $uarg)
sub solve_result {
- my ($ctx, $res, $log, $hints, $fn) = @_;
+ my ($res, $ctx) = @_;
+ my ($log, $hints, $fn) = delete @$ctx{qw(log hints fn)};
unless (seek($log, 0, 0)) {
- $ctx->{env}->{'psgi.errors'}->print("seek(log): $!\n");
+ warn "seek(log): $!";
return html_page($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);
+ ref($res) eq 'ARRAY' or return html_page($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_commit($ctx, $res, \$log, $fn) if $type eq 'commit';
+ return show_other($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);
if (!$blob) { # WTF?
my $e = "Failed to retrieve generated blob ($oid)";
- $ctx->{env}->{'psgi.errors'}->print("$e ($git->{git_dir})\n");
+ warn "$e ($git->{git_dir})";
$log = "<pre><b>$e</b></pre>" . $log;
return html_page($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, ($binary ? 'application/octet-stream' : 'text/plain'));
+ push(@$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($$blob);
- my $nl = ($$blob =~ tr/\n/\n/);
+ # TODO: detect + convert to ensure validity
+ utf8::decode($$blob);
+ my $nl = ($$blob =~ s/\r?\n/\n/sg);
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($$blob);
+ }
+
# using some of the same CSS class names and ids as cgit
$log = "<pre>$oid $type $size bytes $raw_link</pre>" .
"<hr /><table\nclass=blob>".
} (1..$nl)) . '</pre></td>' .
'<td><pre> </pre></td>'. # pad for non-CSS users
"<td\nclass=lines><pre\nstyle='white-space:pre'><code>" .
- ascii_html($$blob) .
+ $l->linkify_2($$blob) .
'</code></pre></td></tr></table>' . $log;
html_page($ctx, 200, \$log);
}
+# GET /$INBOX/$GIT_OBJECT_ID/s/
+# GET /$INBOX/$GIT_OBJECT_ID/s/$FILENAME
sub show ($$;$) {
my ($ctx, $oid_b, $fn) = @_;
my $qp = $ctx->{qp};
- my $hints = {};
+ my $hints = $ctx->{hints} = {};
while (my ($from, $to) = each %QP_MAP) {
defined(my $v = $qp->{$from}) or next;
- $hints->{$to} = $v;
+ $hints->{$to} = $v if $v ne '';
}
- open my $log, '+>', undef or die "open: $!";
- my $solver = PublicInbox::SolverGit->new($ctx->{-inbox}, sub {
- solve_result($ctx, $_[0], $log, $hints, $fn);
- });
-
- # PSGI server will call this and give us a callback
+ $ctx->{'log'} = tmpfile("solve.$oid_b") // die "tmpfile: $!";
+ $ctx->{fn} = $fn;
+ my $solver = PublicInbox::SolverGit->new($ctx->{ibx},
+ \&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}, $log, $oid_b, $hints);
+ $solver->solve($ctx->{env}, $ctx->{log}, $oid_b, $hints);
};
}