X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FViewVCS.pm;h=fdca70cb283fbc20bc9d67361ed4699edd3e79ce;hb=256d049b7ac24f40bb1df691fe014853b75bf491;hp=61f4debadda6dc5257e703fd4807fc2a0a9f269e;hpb=f82593fc84a6773cd6fcb0633fdcca4cee92859f;p=public-inbox.git diff --git a/lib/PublicInbox/ViewVCS.pm b/lib/PublicInbox/ViewVCS.pm index 61f4deba..fdca70cb 100644 --- a/lib/PublicInbox/ViewVCS.pm +++ b/lib/PublicInbox/ViewVCS.pm @@ -16,54 +16,131 @@ 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($$bref); + $l->linkify_1($$bref); + $$bref = '
'. $l->linkify_2(ascii_html($$bref)); + $$bref .= '
debug log:
' . $l->linkify_2(ascii_html($log)) . ''; $res or return html_page($ctx, 404, \$log); + $ref eq 'ARRAY' or return html_page($ctx, 500, \$log); my ($git, $oid, $type, $size, $di) = @$res; - if ($size > $max_size) { - # TODO: stream the raw file if it's gigantic, at least - $log = '
Too big to show' . $log; - return html_page($ctx, 500, \$log); + return show_other($ctx, $res, \$log, $fn) if $type ne 'blob'; + my $path = to_filename($di->{path_b} || $hints->{path_b} || 'blob'); + my $raw_link = "(raw)"; + if ($size > $MAX_SIZE) { + return stream_large_blob($ctx, $res, \$log, $fn) if defined $fn; + $log = "
Too big to show, download available\n" . + "$oid $type $size bytes $raw_link" . $log; + return html_page($ctx, 200, \$log); } my $blob = $git->cat_file($oid); @@ -74,25 +151,32 @@ sub show ($$;$) { return html_page($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 $raw_link = "(raw)"; - if ($binary) { + if ($bin) { $log = "
$oid $type $size bytes (binary)" . " $raw_link" . $log; return html_page($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 = "
$oid $type $size bytes $raw_link" . "
|