X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FViewDiff.pm;h=8fe7261ff2909220b7e3e28c6f7f07b97c9e173f;hb=af0b0fb7a454470a32c452119d0392e0dedb3fe1;hp=57a1b5d66dd9dda27de87c3106da22fb3f385355;hpb=a7c58d0ce022671c9170401054a1131b9ec15bfa;p=public-inbox.git diff --git a/lib/PublicInbox/ViewDiff.pm b/lib/PublicInbox/ViewDiff.pm index 57a1b5d6..8fe7261f 100644 --- a/lib/PublicInbox/ViewDiff.pm +++ b/lib/PublicInbox/ViewDiff.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2019-2020 all contributors +# Copyright (C) 2019-2021 all contributors # License: AGPL-3.0+ # # used by PublicInbox::View @@ -18,14 +18,30 @@ use PublicInbox::Git qw(git_unquote); sub UNSAFE () { "^A-Za-z0-9\-\._~/" } -my $OID_NULL = '0{7,40}'; -my $OID_BLOB = '[a-f0-9]{7,40}'; +my $OID_NULL = '0{7,}'; +my $OID_BLOB = '[a-f0-9]{7,}'; my $LF = qr!\n!; my $ANY = qr![^\n]!; my $FN = qr!(?:"?[^/\n]+/[^\n]+|/dev/null)!; # cf. git diff.c :: get_compact_summary -my $DIFFSTAT_COMMENT = qr/\((?:new|gone|(?:(?:new|mode) [\+\-][lx]))\)/; +my $DIFFSTAT_COMMENT = + qr/(?: *\((?:new|gone|(?:(?:new|mode) [\+\-][lx]))\))? *\z/s; +my $NULL_TO_BLOB = qr/^(index $OID_NULL\.\.)($OID_BLOB)\b/ms; +my $BLOB_TO_NULL = qr/^index ($OID_BLOB)(\.\.$OID_NULL)\b/ms; +my $BLOB_TO_BLOB = qr/^index ($OID_BLOB)\.\.($OID_BLOB)/ms; +my $EXTRACT_DIFFS = qr/( + (?: # begin header stuff, don't capture filenames, here, + # but instead wait for the --- and +++ lines. + (?:^diff\x20--git\x20$FN\x20$FN$LF) + + # old mode || new mode || copy|rename|deleted|... + (?:^[a-z]$ANY+$LF)* + )? # end of optional stuff, everything below is required + ^index\x20($OID_BLOB)\.\.($OID_BLOB)$ANY*$LF + ^---\x20($FN)$LF + ^\+{3}\x20($FN)$LF)/msx; +my $IS_OID = qr/\A$OID_BLOB\z/s; # link to line numbers in blobs sub diff_hunk ($$$$) { @@ -34,12 +50,12 @@ sub diff_hunk ($$$$) { if (defined($spfx) && defined($oid_a) && defined($oid_b)) { my ($n) = ($ca =~ /^-([0-9]+)/); - $n = defined($n) ? do { ++$n; "#n$n" } : ''; + $n = defined($n) ? "#n$n" : ''; $$dst .= qq(@@ {Q}$n">$ca); ($n) = ($cb =~ /^\+([0-9]+)/); - $n = defined($n) ? do { ++$n; "#n$n" } : ''; + $n = defined($n) ? "#n$n" : ''; $$dst .= qq( {Q}$n">$cb @@); } else { $$dst .= "@@ $ca $cb @@"; @@ -62,14 +78,12 @@ sub anchor0 ($$$$) { # So only do best-effort handling of renames for common cases; # which works well in practice. If projects put "=>", or trailing # spaces in filenames, oh well :P - $fn =~ s/(?: *$DIFFSTAT_COMMENT)? *\z//so; + $fn =~ s/$DIFFSTAT_COMMENT//; $fn =~ s/{(?:.+) => (.+)}/$1/ or $fn =~ s/.* => (.+)/$1/; $fn = git_unquote($fn); - # long filenames will require us to walk backwards in anchor1 - if ($fn =~ s!\A\.\.\./?!!) { - $ctx->{-long_path}->{$fn} = qr/\Q$fn\E\z/s; - } + # long filenames will require us to check in anchor1() + push(@{$ctx->{-long_path}}, $fn) if $fn =~ s!\A\.\.\./?!!; if (my $attr = to_attr($ctx->{-apfx}.$fn)) { $ctx->{-anchors}->{$attr} = 1; @@ -89,23 +103,20 @@ sub anchor1 ($$) { my $ok = delete $ctx->{-anchors}->{$attr}; - # unlikely, check the end of all long path names we captured: + # unlikely, check the end of long path names we captured, + # assume diffstat and diff output follow the same order, + # and ignore different ordering (could be malicious input) unless ($ok) { - my $lp = $ctx->{-long_path} or return; - foreach my $fn (keys %$lp) { - $pb =~ $lp->{$fn} or next; - - delete $lp->{$fn}; - $attr = to_attr($ctx->{-apfx}.$fn) or return; - $ok = delete $ctx->{-anchors}->{$attr} or return; - last; - } + my $fn = shift(@{$ctx->{-long_path}}) or return; + $pb =~ /\Q$fn\E\z/s or return; + $attr = to_attr($ctx->{-apfx}.$fn) or return; + $ok = delete $ctx->{-anchors}->{$attr} or return; } $ok ? "diff --git" : undef } -sub diff_header ($$$$) { - my ($dst, $x, $ctx, $top) = @_; +sub diff_header ($$$) { + my ($x, $ctx, $top) = @_; my (undef, undef, $pa, $pb) = splice(@$top, 0, 4); # ignore oid_{a,b} my $spfx = $ctx->{-spfx}; my $dctx = { spfx => $spfx }; @@ -132,31 +143,34 @@ sub diff_header ($$$$) { # no need to capture oid_a and oid_b on add/delete, # we just linkify OIDs directly via s///e in conditional - if (($$x =~ s/^(index $OID_NULL\.\.)($OID_BLOB)\b/ - $1 . oid($dctx, $spfx, $2)/emos) || - ($$x =~ s/^index ($OID_BLOB)(\.\.$OID_NULL)\b/ - 'index ' . oid($dctx, $spfx, $1) . $2/emos)) { - } elsif ($$x =~ /^index ($OID_BLOB)\.\.($OID_BLOB)/mos) { + if (($$x =~ s/$NULL_TO_BLOB/$1 . oid($dctx, $spfx, $2)/e) || + ($$x =~ s/$BLOB_TO_NULL/ + 'index ' . oid($dctx, $spfx, $1) . $2/e)) { + } elsif ($$x =~ $BLOB_TO_BLOB) { # modification-only, not add/delete: # linkify hunk headers later using oid_a and oid_b @$dctx{qw(oid_a oid_b)} = ($1, $2); } else { warn "BUG? <$$x> had no ^index line"; } - $$x =~ s!^diff --git!anchor1($ctx, $pb) // 'diff --git'!emos; + $$x =~ s!^diff --git!anchor1($ctx, $pb) // 'diff --git'!ems; + my $dst = $ctx->{obuf}; $$dst .= qq(); $$dst .= $$x; $$dst .= ''; $dctx; } -sub diff_before_or_after ($$$) { - my ($dst, $ctx, $x) = @_; +sub diff_before_or_after ($$) { + my ($ctx, $x) = @_; my $linkify = $ctx->{-linkify}; + my $dst = $ctx->{obuf}; + my $anchors = exists($ctx->{-anchors}) ? 1 : 0; for my $y (split(/(^---\n)/sm, $$x)) { if ($y =~ /\A---\n\z/s) { $$dst .= "---\n"; # all HTML is "\r\n" => "\n" - } elsif ($y =~ /^ [0-9]+ files? changed, /sm) { + $anchors |= 2; + } elsif ($anchors == 3 && $y =~ /^ [0-9]+ files? changed, /sm) { # ok, looks like a diffstat, go line-by-line: for my $l (split(/^/m, $y)) { if ($l =~ /^ (.+)( +\| .*\z)/s) { @@ -171,32 +185,34 @@ sub diff_before_or_after ($$$) { } # callers must do CRLF => LF conversion before calling this -sub flush_diff ($$$) { - my ($dst, $ctx, $cur) = @_; +sub flush_diff ($$) { + my ($ctx, $cur) = @_; - my @top = split(/( - (?: # begin header stuff, don't capture filenames, here, - # but instead wait for the --- and +++ lines. - (?:^diff\x20--git\x20$FN\x20$FN$LF) - - # old mode || new mode || copy|rename|deleted|... - (?:^[a-z]$ANY+$LF)* - )? # end of optional stuff, everything below is required - ^index\x20($OID_BLOB)\.\.($OID_BLOB)$ANY*$LF - ^---\x20($FN)$LF - ^\+{3}\x20($FN)$LF)/smxo, $$cur); - $$cur = undef; + my @top = split($EXTRACT_DIFFS, $$cur); + undef $$cur; # free memory my $linkify = $ctx->{-linkify}; + my $dst = $ctx->{obuf}; my $dctx; # {}, keys: Q, oid_a, oid_b while (defined(my $x = shift @top)) { if (scalar(@top) >= 4 && - $top[1] =~ /\A$OID_BLOB\z/os && - $top[0] =~ /\A$OID_BLOB\z/os) { - $dctx = diff_header($dst, \$x, $ctx, \@top); + $top[1] =~ $IS_OID && + $top[0] =~ $IS_OID) { + $dctx = diff_header(\$x, $ctx, \@top); } elsif ($dctx) { my $after = ''; + + # Quiet "Complex regular subexpression recursion limit" + # warning. Perl will truncate matches upon hitting + # that limit, giving us more (and shorter) scalars than + # would be ideal, but otherwise it's harmless. + # + # We could replace the `+' metacharacter with `{1,100}' + # to limit the matches ourselves to 100, but we can + # let Perl do it for us, quietly. + no warnings 'regexp'; + for my $s (split(/((?:(?:^\+[^\n]*\n)+)| (?:(?:^-[^\n]*\n)+)| (?:^@@ [^\n]+\n))/xsm, $x)) { @@ -222,9 +238,9 @@ sub flush_diff ($$$) { $$dst .= $linkify->to_html($s); } } - diff_before_or_after($dst, $ctx, \$after) unless $dctx; + diff_before_or_after($ctx, \$after) unless $dctx; } else { - diff_before_or_after($dst, $ctx, \$x); + diff_before_or_after($ctx, \$x); } } }