X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSolverGit.pm;h=dd95f40043b14c3cf230393845ed812bf898d489;hb=38226be5fd4c24885658e00d4ce87ccee663063d;hp=3e3a5899f25523ca58605d5710207dcb5cfa1c1f;hpb=3eafdb33697581b8d797bf7c664a53a311725075;p=public-inbox.git diff --git a/lib/PublicInbox/SolverGit.pm b/lib/PublicInbox/SolverGit.pm index 3e3a5899..dd95f400 100644 --- a/lib/PublicInbox/SolverGit.pm +++ b/lib/PublicInbox/SolverGit.pm @@ -1,19 +1,19 @@ -# Copyright (C) 2019 all contributors +# Copyright (C) 2019-2020 all contributors # License: AGPL-3.0+ # "Solve" blobs which don't exist in git code repositories by # searching inboxes for post-image blobs. # this emits a lot of debugging/tracing information which may be -# publically viewed over HTTP(S). Be careful not to expose +# publicly viewed over HTTP(S). Be careful not to expose # local filesystem layouts in the process. package PublicInbox::SolverGit; use strict; -use warnings; -use File::Temp 0.19 (); +use v5.10.1; +use File::Temp 0.19 (); # 0.19 for ->newdir use Fcntl qw(SEEK_SET); use PublicInbox::Git qw(git_unquote git_quote); -use PublicInbox::MsgIter qw(msg_iter msg_part_text); +use PublicInbox::MsgIter qw(msg_part_text); use PublicInbox::Qspawn; use PublicInbox::Tmpfile; use URI::Escape qw(uri_escape_utf8); @@ -33,24 +33,26 @@ my $OID_MIN = 7; # work fairly. Other PSGI servers may have trouble, though. my $MAX_PATCH = 9999; +my $LF = qr!\r?\n!; +my $ANY = qr![^\r\n]+!; +my $MODE = '100644|120000|100755'; +my $FN = qr!(?:("?[^/\n]+/[^\r\n]+)|/dev/null)!; +my %BAD_COMPONENT = ('' => 1, '.' => 1, '..' => 1); + # di = diff info / a hashref with information about a diff ($di): # { # oid_a => abbreviated pre-image oid, # oid_b => abbreviated post-image oid, # tmp => anonymous file handle with the diff, -# hdr_lines => arrayref of various header lines for mode information +# hdr_lines => string of various header lines for mode information # mode_a => original mode of oid_a (string, not integer), # ibx => PublicInbox::Inbox object containing the diff -# smsg => PublicInbox::SearchMsg object containing diff +# smsg => PublicInbox::Smsg object containing diff # path_a => pre-image path # path_b => post-image path # n => numeric path of the patch (relative to worktree) # } -# don't bother if somebody sends us a patch with these path components, -# it's junk at best, an attack attempt at worse: -my %bad_component = map { $_ => 1 } ('', '.', '..'); - sub dbg ($$) { print { $_[0]->{out} } $_[1], "\n" or ERR($_[0], "print(dbg): $!"); } @@ -100,14 +102,11 @@ sub solve_existing ($$) { sub extract_diff ($$) { my ($p, $arg) = @_; - my ($self, $diffs, $re, $ibx, $smsg) = @$arg; + my ($self, $diffs, $pre, $post, $ibx, $smsg) = @$arg; my ($part) = @$p; # ignore $depth and @idx; - my $hdr_lines; # diff --git a/... b/... - my $tmp; my $ct = $part->content_type || 'text/plain'; my ($s, undef) = msg_part_text($part, $ct); defined $s or return; - my $di = {}; # Email::MIME::Encodings forces QP to be CRLF upon decoding, # change it back to LF: @@ -116,66 +115,82 @@ sub extract_diff ($$) { $s =~ s/\r\n/\n/sg; } - foreach my $l (split(/^/m, $s)) { - if ($l =~ $re) { - $di->{oid_a} = $1; - $di->{oid_b} = $2; - if (defined($3)) { - my $mode_a = $3; - if ($mode_a =~ /\A(?:100644|120000|100755)\z/) { - $di->{mode_a} = $mode_a; - } - } - - - # start writing the diff out to a tempfile - my $path = ++$self->{tot}; - $di->{n} = $path; - open($tmp, '>', $self->{tmp}->dirname . "/$path") or - die "open(tmp): $!"; - - push @$hdr_lines, $l; - $di->{hdr_lines} = $hdr_lines; - utf8::encode($_) for @$hdr_lines; - print $tmp @$hdr_lines or die "print(tmp): $!"; - - # for debugging/diagnostics: - $di->{ibx} = $ibx; - $di->{smsg} = $smsg; - } elsif ($l =~ m!\Adiff --git ("?[^/]+/.+) ("?[^/]+/.+)$!) { - last if $tmp; # got our blob, done! - - my ($path_a, $path_b) = ($1, $2); - - # diff header lines won't have \r because git - # will quote them, but Email::MIME gives CRLF - # for quoted-printable: - $path_b =~ tr/\r//d; - - # don't care for leading 'a/' and 'b/' - my (undef, @a) = split(m{/}, git_unquote($path_a)); - my (undef, @b) = split(m{/}, git_unquote($path_b)); - - # get rid of path-traversal attempts and junk patches: - foreach (@a, @b) { - return if $bad_component{$_}; - } - - $di->{path_a} = join('/', @a); - $di->{path_b} = join('/', @b); - $hdr_lines = [ $l ]; - } elsif ($tmp) { - utf8::encode($l); - print $tmp $l or die "print(tmp): $!"; - } elsif ($hdr_lines) { - push @$hdr_lines, $l; - if ($l =~ /\Anew file mode (100644|120000|100755)$/) { - $di->{mode_a} = $1; - } - } - } - return undef unless $tmp; + + $s =~ m!( # $1 start header lines we save for debugging: + + # everything before ^index is optional, but we don't + # want to match ^(old|copy|rename|deleted|...) unless + # we match /^diff --git/ first: + (?: # begin optional stuff: + + # try to get the pre-and-post filenames as $2 and $3 + (?:^diff\x20--git\x20$FN\x20$FN$LF) + + (?:^(?: # pass all this to git-apply: + # old mode $4 + (?:old\x20mode\x20($MODE)) + | + # new mode (possibly new file) ($5) + (?:new\x20(?:file\x20)?mode\x20($MODE)) + | + (?:(?:copy|rename|deleted| + dissimilarity|similarity)$ANY) + )$LF)* + + )? # end of optional stuff, everything below is required + + # match the pre and post-image OIDs as $6 $7 + ^index\x20(${pre}[a-f0-9]*)\.\.(${post}[a-f0-9]*) + # mode if unchanged $8 + (?:\x20(100644|120000|100755))?$LF + ) # end of header lines ($1) + ( # $9 is the patch body + # "--- a/foo.c" sets pre-filename ($10) in case + # $2 is missing + (?:^---\x20$FN$LF) + + # "+++ b/foo.c" sets post-filename ($11) in case + # $3 is missing + (?:^\+{3}\x20$FN$LF) + + # the meat of the diff, including "^\\No newline ..." + # We also allow for totally blank lines w/o leading spaces, + # because git-apply(1) handles that case, too + (?:^(?:[\@\+\x20\-\\][^\n]*|)$LF)+ + )!smx or return; + + my $di = { + hdr_lines => $1, + oid_a => $6, + oid_b => $7, + mode_a => $5 // $8 // $4, # new (file) // unchanged // old + }; + my $path_a = $2 // $10; + my $path_b = $3 // $11; + my $patch = $9; + + # don't care for leading 'a/' and 'b/' + my (undef, @a) = split(m{/}, git_unquote($path_a)) if defined($path_a); + my (undef, @b) = split(m{/}, git_unquote($path_b)); + + # get rid of path-traversal attempts and junk patches: + # it's junk at best, an attack attempt at worse: + foreach (@a, @b) { return if $BAD_COMPONENT{$_} } + + $di->{path_a} = join('/', @a) if @a; + $di->{path_b} = join('/', @b); + + my $path = ++$self->{tot}; + $di->{n} = $path; + open(my $tmp, '>:utf8', $self->{tmp}->dirname . "/$path") or + die "open(tmp): $!"; + print $tmp $di->{hdr_lines}, $patch or die "print(tmp): $!"; close $tmp or die "close(tmp): $!"; + + # for debugging/diagnostics: + $di->{ibx} = $ibx; + $di->{smsg} = $smsg; + push @$diffs, $di; } @@ -213,14 +228,12 @@ sub find_extract_diffs ($$$) { } } - my $msgs = $srch->query($q, { relevance => 1 }); - my $re = qr/\Aindex ($pre[a-f0-9]*)\.\.($post[a-f0-9]*)(?: ([0-9]+))?/; + my $mset = $srch->mset($q, { relevance => 1 }); my $diffs = []; - foreach my $smsg (@$msgs) { - $ibx->smsg_mime($smsg) or next; - my $mime = delete $smsg->{mime}; - msg_iter($mime, \&extract_diff, - [$self, $diffs, $re, $ibx, $smsg]); + for my $smsg (@{$srch->mset_to_smsg($ibx, $mset)}) { + my $eml = $ibx->smsg_eml($smsg) or next; + $eml->each_part(\&extract_diff, + [$self, $diffs, $pre, $post, $ibx, $smsg], 1); } @$diffs ? $diffs : undef; } @@ -251,12 +264,12 @@ sub prepare_index ($) { my $oid_full = $existing->[1]; my $path_a = $di->{path_a} or die "BUG: path_a missing for $oid_full"; - my $mode_a = $di->{mode_a} || extract_old_mode($di); + my $mode_a = $di->{mode_a} // '100644'; my $in = tmpfile("update-index.$oid_full") or die "tmpfile: $!"; print $in "$mode_a $oid_full\t$path_a\0" or die "print: $!"; $in->flush or die "flush: $!"; - sysseek($in, 0, 0) or die "seek: $!"; + sysseek($in, 0, SEEK_SET) or die "seek: $!"; dbg($self, 'preparing index'); my $rdr = { 0 => $in }; @@ -307,15 +320,6 @@ EOF prepare_index($self); } -sub extract_old_mode ($) { - my ($di) = @_; - if (join('', @{$di->{hdr_lines}}) =~ - /^old mode (100644|100755|120000)\b/) { - return $1; - } - '100644'; -} - sub do_finish ($) { my ($self) = @_; my ($found, $oid_want) = @$self{qw(found oid_want)}; @@ -484,7 +488,7 @@ sub do_git_apply ($) { my $i = ++$self->{nr}; $di = shift @$patches; dbg($self, "\napplying [$i/$total] " . di_url($self, $di) . - "\n" . join('', @{$di->{hdr_lines}})); + "\n" . $di->{hdr_lines}); my $path = $di->{n}; $len += length($path) + 1; push @cmd, $path; @@ -492,7 +496,7 @@ sub do_git_apply ($) { } while (@$patches && $len < $ARG_SIZE_MAX && !oids_same_ish($patches->[0]->{oid_b}, $prv_oid_b)); - my $opt = { 2 => 1, -C => $dn }; + my $opt = { 2 => 1, -C => $dn, quiet => 1 }; my $qsp = PublicInbox::Qspawn->new(\@cmd, $self->{git_env}, $opt); $self->{-cur_di} = $di; $self->{-qsp} = $qsp; @@ -525,7 +529,8 @@ sub resolve_patch ($$) { if (my $existing = solve_existing($self, $want)) { my ($found_git, undef, $type, undef) = @$existing; dbg($self, "found $cur_want in " . - join("\n", $found_git->pub_urls($self->{psgi_env}))); + join(" ||\n\t", + $found_git->pub_urls($self->{psgi_env}))); if ($cur_want eq $self->{oid_want} || $type ne 'blob') { eval { done($self, $existing) }; @@ -543,7 +548,7 @@ sub resolve_patch ($$) { unshift @{$self->{patches}}, @$diffs; dbg($self, "found $cur_want in ". - join("\n\t", map { di_url($self, $_) } @$diffs)); + join(" ||\n\t", map { di_url($self, $_) } @$diffs)); # good, we can find a path to the oid we $want, now # lets see if we need to apply more patches: @@ -587,7 +592,7 @@ sub new { } # recreate $oid_want using $hints -# hints keys: path_a, path_b, oid_a +# hints keys: path_a, path_b, oid_a (note: `oid_b' is NOT a hint) # Calls {user_cb} with: [ ::Git object, oid_full, type, size, di (diff_info) ] # with found object, or undef if nothing was found # Calls {user_cb} with a string error on fatal errors