X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FViewDiff.pm;h=5d23881b55c1e9a2c74b2d6afd3c1b0c04954488;hb=ab9c03ff4aa369b397dc1a8c8936153c8565fd05;hp=604b1f23e5dbe9d509416b28914444005adece2b;hpb=7efca6c8a2b98d97056fc933165df82e4b825725;p=public-inbox.git diff --git a/lib/PublicInbox/ViewDiff.pm b/lib/PublicInbox/ViewDiff.pm index 604b1f23..5d23881b 100644 --- a/lib/PublicInbox/ViewDiff.pm +++ b/lib/PublicInbox/ViewDiff.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2019-2020 all contributors +# Copyright (C) all contributors # License: AGPL-3.0+ # # used by PublicInbox::View @@ -7,39 +7,57 @@ # (or reconstruct) blobs. package PublicInbox::ViewDiff; -use 5.010_001; use strict; -use warnings; -use base qw(Exporter); -our @EXPORT_OK = qw(flush_diff); +use v5.10.1; +use parent qw(Exporter); +our @EXPORT_OK = qw(flush_diff uri_escape_path); use URI::Escape qw(uri_escape_utf8); use PublicInbox::Hval qw(ascii_html to_attr); 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; +our $EXTRACT_DIFFS = qr/( + (?: # begin header stuff, don't capture filenames, here, + # but instead wait for the --- and +++ lines. + (?:^diff\x20--git\x20$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; +our $IS_OID = qr/\A$OID_BLOB\z/s; + +sub uri_escape_path { + # '/' + $URI::Escape::Unsafe{RFC3986} + uri_escape_utf8($_[0], "^A-Za-z0-9\-\._~/"); +} # link to line numbers in blobs -sub diff_hunk ($$$$) { - my ($dst, $dctx, $ca, $cb) = @_; +sub diff_hunk ($$$) { + my ($dctx, $ca, $cb) = @_; my ($oid_a, $oid_b, $spfx) = @$dctx{qw(oid_a oid_b spfx)}; if (defined($spfx) && defined($oid_a) && defined($oid_b)) { - my ($n) = ($ca =~ /^-([0-9]+)/); - $n = defined($n) ? do { ++$n; "#n$n" } : ''; + my $n = ($ca =~ /^-([0-9]+)/) ? "#n$1" : ''; + my $x = qq(@@ {Q}$n">$ca); - $$dst .= qq(@@ {Q}$n">$ca); - - ($n) = ($cb =~ /^\+([0-9]+)/); - $n = defined($n) ? do { ++$n; "#n$n" } : ''; - $$dst .= qq( {Q}$n">$cb @@); + $n = ($cb =~ /^\+([0-9]+)/) ? "#n$1" : ''; + $x .= qq( {Q}$n">$cb @@); } else { - $$dst .= "@@ $ca $cb @@"; + "@@ $ca $cb @@"; } } @@ -49,8 +67,8 @@ sub oid ($$$) { } # returns true if diffstat anchor written, false otherwise -sub anchor0 ($$$$) { - my ($dst, $ctx, $fn, $rest) = @_; +sub anchor0 ($$$) { + my ($ctx, $fn, $rest) = @_; my $orig = $fn; @@ -59,66 +77,58 @@ sub anchor0 ($$$$) { # So only do best-effort handling of renames for common cases; # which works well in practice. If projects put "=>", or trailing # spaces in filenames, oh well :P - $fn =~ s/(?: *$DIFFSTAT_COMMENT)? *\z//so; - $fn =~ s/{(?:.+) => (.+)}/$1/ or $fn =~ s/.* => (.+)/$1/; + $fn =~ s/$DIFFSTAT_COMMENT//; + $fn =~ s/\{(?:.+) => (.+)\}/$1/ or $fn =~ s/.* => (.+)/$1/; $fn = git_unquote($fn); - # long filenames will require us to walk backwards in anchor1 - if ($fn =~ s!\A\.\.\./?!!) { - $ctx->{-long_path}->{$fn} = qr/\Q$fn\E\z/s; - } + # long filenames will require us to check in anchor1() + push(@{$ctx->{-long_path}}, $fn) if $fn =~ s!\A\.\.\./?!!; - if (my $attr = to_attr($ctx->{-apfx}.$fn)) { - $ctx->{-anchors}->{$attr} = 1; - my $spaces = ($orig =~ s/( +)\z//) ? $1 : ''; - $$dst .= " " . - ascii_html($orig) . '' . $spaces . + my $attr = to_attr($ctx->{-apfx}.$fn) // return; + $ctx->{-anchors}->{$attr} = 1; + my $spaces = ($orig =~ s/( +)\z//) ? $1 : ''; + print { $ctx->{zfh} } " ", + ascii_html($orig), '', $spaces, $ctx->{-linkify}->to_html($rest); - return 1; - } - undef; } # returns "diff --git" anchor destination, undef otherwise sub anchor1 ($$) { my ($ctx, $pb) = @_; - my $attr = to_attr($ctx->{-apfx}.$pb) or return; + my $attr = to_attr($ctx->{-apfx}.$pb) // return; my $ok = delete $ctx->{-anchors}->{$attr}; - # unlikely, check the end of all long path names we captured: + # unlikely, check the end of long path names we captured, + # assume diffstat and diff output follow the same order, + # and ignore different ordering (could be malicious input) unless ($ok) { - my $lp = $ctx->{-long_path} or return; - foreach my $fn (keys %$lp) { - $pb =~ $lp->{$fn} or next; - - delete $lp->{$fn}; - $attr = to_attr($ctx->{-apfx}.$fn) or return; - $ok = delete $ctx->{-anchors}->{$attr} or return; - last; - } + my $fn = shift(@{$ctx->{-long_path}}) // return; + $pb =~ /\Q$fn\E\z/s or return; + $attr = to_attr($ctx->{-apfx}.$fn) // return; + $ok = delete $ctx->{-anchors}->{$attr} // return; } $ok ? "diff --git" : undef } -sub diff_header ($$$$) { - my ($dst, $x, $ctx, $top) = @_; +sub diff_header ($$$) { + 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 }; # get rid of leading "a/" or "b/" (or whatever --{src,dst}-prefix are) - $pa = (split('/', git_unquote($pa), 2))[1] if $pa ne '/dev/null'; - $pb = (split('/', git_unquote($pb), 2))[1] if $pb ne '/dev/null'; + $pa = (split(m'/', git_unquote($pa), 2))[1] if $pa ne '/dev/null'; + $pb = (split(m'/', git_unquote($pb), 2))[1] if $pb ne '/dev/null'; if ($pa eq $pb && $pb ne '/dev/null') { - $dctx->{Q} = "?b=".uri_escape_utf8($pb, UNSAFE); + $dctx->{Q} = '?b='.uri_escape_path($pb); } else { my @q; if ($pb ne '/dev/null') { - push @q, 'b='.uri_escape_utf8($pb, UNSAFE); + push @q, 'b='.uri_escape_path($pb); } if ($pa ne '/dev/null') { - push @q, 'a='.uri_escape_utf8($pa, UNSAFE); + push @q, 'a='.uri_escape_path($pa); } $dctx->{Q} = '?'.join('&', @q); } @@ -129,101 +139,108 @@ 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 ($$x =~ s/$NULL_TO_BLOB/$1 . oid($dctx, $spfx, $2)/e) { + push @{$ctx->{-qry}->{dfpost}}, $2; + } elsif ($$x =~ s/$BLOB_TO_NULL/'index '.oid($dctx, $spfx, $1).$2/e) { + push @{$ctx->{-qry}->{dfpre}}, $1; + } elsif ($$x =~ $BLOB_TO_BLOB) { # modification-only, not add/delete: # linkify hunk headers later using oid_a and oid_b @$dctx{qw(oid_a oid_b)} = ($1, $2); + push @{$ctx->{-qry}->{dfpre}}, $1; + push @{$ctx->{-qry}->{dfpost}}, $2; } else { warn "BUG? <$$x> had no ^index line"; } - $$x =~ s!^diff --git!anchor1($ctx, $pb) // 'diff --git'!emos; - $$dst .= qq(); - $$dst .= $$x; - $$dst .= ''; + $$x =~ s!^diff --git!anchor1($ctx, $pb) // 'diff --git'!ems; + print { $ctx->{zfh} } qq(), $$x, ''; $dctx; } -sub diff_before_or_after ($$$) { - my ($dst, $ctx, $x) = @_; - my $linkify = $ctx->{-linkify}; - for my $y (split(/(^---\r?\n)/sm, $$x)) { - if ($y =~ /\A---\r?\n\z/s) { - $$dst .= "---\n"; # all HTML is "\r\n" => "\n" - } elsif ($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) { - anchor0($dst, $ctx, $1, $2) and next; - } - $$dst .= $linkify->to_html($l); - } - } else { # commit message, notes, etc - $$dst .= $linkify->to_html($y); +sub diff_before_or_after ($$) { + my ($ctx, $x) = @_; + if (exists $ctx->{-anchors} && $$x =~ /\A(.*?) # likely "---\n" # \$1 + # diffstat lines: + ((?:^\x20(?:[^\n]+?)(?:\x20+\|\x20[^\n]*\n))+) + (\x20[0-9]+\x20files?\x20)changed,([^\n]+\n) + (.*?)\z/msx) { # notes, commit message, etc + my @x = ($5, $4, $3, $2, $1); + undef $$x; + my $lnk = $ctx->{-linkify}; + my $zfh = $ctx->{zfh}; + print $zfh $lnk->to_html(pop @x); # $1 uninteresting prefix + for my $l (split(/^/m, pop(@x))) { # $2 per-file stat lines + $l =~ /^ (.+)( +\| .*\z)/s and + anchor0($ctx, $1, $2) and next; + print $zfh $lnk->to_html($l); } + my $ch = $ctx->{changed_href} // '#related'; + print $zfh pop(@x), # $3 /^ \d+ files? / + qq(changed,), + ascii_html(pop @x), # insertions/deletions + $lnk->to_html(@x); # notes, commit message, etc + } else { + print { $ctx->{zfh} } $ctx->{-linkify}->to_html($$x); } } -sub flush_diff ($$$) { - my ($dst, $ctx, $cur) = @_; - state $LF = qr!\r?\n!; - state $ANY = qr![^\r\n]!; - state $FN = qr!(?:"?[^/\n]+/[^\r\n]+|/dev/null)!; - - my @top = split(/( - (?: # begin header stuff, don't capture filenames, here, - # but instead wait for the --- and +++ lines. - (?:^diff\x20--git\x20$FN\x20$FN$LF) +# callers must do CRLF => LF conversion before calling this +sub flush_diff ($$) { + my ($ctx, $cur) = @_; - # old mode || new mode || copy|rename|deleted|... - (?:^[a-z]$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 $lnk = $ctx->{-linkify}; my $dctx; # {}, keys: Q, oid_a, oid_b + my $zfh = $ctx->zfh; 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 = ''; + open(my $afh, '>>', \(my $after='')) or die "open: $!"; + + # 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, $x)) { if (!defined($dctx)) { - $after .= $s; + print $afh $s; } elsif ($s =~ s/\A@@ (\S+) (\S+) @@//) { - $$dst .= qq(); - diff_hunk($dst, $dctx, $1, $2); - $$dst .= $linkify->to_html($s); - $$dst .= ''; - } elsif ($s =~ /\A\+/) { - $$dst .= qq(); - $$dst .= $linkify->to_html($s); - $$dst .= ''; + print $zfh qq(), + diff_hunk($dctx, $1, $2), + $lnk->to_html($s), + ''; + } elsif ($s =~ /\A\+/) { # $s may be huge + print $zfh qq(), + $lnk->to_html($s), + ''; } elsif ($s =~ /\A-- $/sm) { # email sig starts $dctx = undef; - $after .= $s; - } elsif ($s =~ /\A-/) { - $$dst .= qq(); - $$dst .= $linkify->to_html($s); - $$dst .= ''; - } else { - $$dst .= $linkify->to_html($s); + print $afh $s; + } elsif ($s =~ /\A-/) { # $s may be huge + print $zfh qq(), + $lnk->to_html($s), + ''; + } else { # $s may be huge + print $zfh $lnk->to_html($s); } } - diff_before_or_after($dst, $ctx, \$after) unless $dctx; + diff_before_or_after($ctx, \$after) if !$dctx; } else { - diff_before_or_after($dst, $ctx, \$x); + diff_before_or_after($ctx, \$x); } } }