# (or reconstruct) blobs.
package PublicInbox::ViewDiff;
-use strict;
-use v5.10.1;
+use v5.12;
use parent qw(Exporter);
-our @EXPORT_OK = qw(flush_diff);
+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);
-my $UNSAFE = "^A-Za-z0-9\-\._~/"; # '/' + $URI::Escape::Unsafe{RFC3986}
my $OID_NULL = '0{7,}';
my $OID_BLOB = '[a-f0-9]{7,}';
my $LF = qr!\n!;
^\+{3}\x20($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) ? "#n$n" : '';
-
- $$dst .= qq(@@ <a\nhref="$spfx$oid_a/s/$dctx->{Q}$n">$ca</a>);
+ my $n = ($ca =~ /^-([0-9]+)/) ? "#n$1" : '';
+ my $x = qq(@@ <a\nhref="$spfx$oid_a/s/$dctx->{Q}$n">$ca</a>);
- ($n) = ($cb =~ /^\+([0-9]+)/);
- $n = defined($n) ? "#n$n" : '';
- $$dst .= qq( <a\nhref="$spfx$oid_b/s/$dctx->{Q}$n">$cb</a> @@);
+ $n = ($cb =~ /^\+([0-9]+)/) ? "#n$1" : '';
+ $x .= qq( <a\nhref="$spfx$oid_b/s/$dctx->{Q}$n">$cb</a> @@);
} else {
- $$dst .= "@@ $ca $cb @@";
+ "@@ $ca $cb @@";
}
}
}
# returns true if diffstat anchor written, false otherwise
-sub anchor0 ($$$$) {
- my ($dst, $ctx, $fn, $rest) = @_;
+sub anchor0 ($$$) {
+ my ($ctx, $fn, $rest) = @_;
my $orig = $fn;
# long filenames will require us to check in anchor1()
push(@{$ctx->{-long_path}}, $fn) if $fn =~ s!\A\.\.\./?!!;
- if (defined(my $attr = to_attr($ctx->{-apfx}.$fn))) {
- $ctx->{-anchors}->{$attr} = 1;
- my $spaces = ($orig =~ s/( +)\z//) ? $1 : '';
- $$dst .= " <a\nid=i$attr\nhref=#$attr>" .
- ascii_html($orig) . '</a>' . $spaces .
+ my $attr = to_attr($ctx->{-apfx}.$fn) // return;
+ $ctx->{-anchors}->{$attr} = 1;
+ my $spaces = ($orig =~ s/( +)\z//) ? $1 : '';
+ print { $ctx->{zfh} } " <a\nid=i$attr\nhref=#$attr>",
+ ascii_html($orig), '</a>', $spaces,
$ctx->{-linkify}->to_html($rest);
- return 1;
- }
- undef;
}
# returns "diff --git" anchor destination, undef otherwise
$pa = (split(m'/', git_unquote($pa), 2))[1] if $pa ne '/dev/null';
$pb = (split(m'/', git_unquote($pb), 2))[1] if $pb ne '/dev/null';
if ($pa eq $pb && $pb ne '/dev/null') {
- $dctx->{Q} = "?b=".uri_escape_utf8($pb, $UNSAFE);
+ $dctx->{Q} = '?b='.uri_escape_path($pb);
} else {
my @q;
- if ($pb ne '/dev/null') {
- push @q, 'b='.uri_escape_utf8($pb, $UNSAFE);
- }
- if ($pa ne '/dev/null') {
- push @q, 'a='.uri_escape_utf8($pa, $UNSAFE);
- }
+ push @q, 'b='.uri_escape_path($pb) if $pb ne '/dev/null';
+ push @q, 'a='.uri_escape_path($pa) if $pa ne '/dev/null';
$dctx->{Q} = '?'.join('&', @q);
}
warn "BUG? <$$x> had no ^index line";
}
$$x =~ s!^diff --git!anchor1($ctx, $pb) // 'diff --git'!ems;
- my $dst = $ctx->{obuf};
- $$dst .= qq(<span\nclass="head">);
- $$dst .= $$x;
- $$dst .= '</span>';
+ print { $ctx->{zfh} } qq(<span\nclass="head">), $$x, '</span>';
$dctx;
}
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) {
- $$dst .= "---\n"; # all HTML is "\r\n" => "\n"
- $anchors |= 2;
- } elsif ($anchors == 3 && $y =~ /^ [0-9]+ files? changed, /sm) {
- # ok, looks like a diffstat, go line-by-line:
- for my $l (split(/^/m, $y)) {
- if ($l =~ /^ (.+)( +\| .*\z)/s) {
- anchor0($dst, $ctx, $1, $2) or
- $$dst .= $linkify->to_html($l);
- } elsif ($l =~ s/^( [0-9]+ files? )changed,//) {
- $$dst .= $1;
- my $end = $ctx->{end_id} // 'related';
- $$dst .= "<a href=#$end>changed</a>,";
- $$dst .= ascii_html($l);
- } else {
- $$dst .= $linkify->to_html($l);
- }
- }
- } else { # commit message, notes, etc
- $$dst .= $linkify->to_html($y);
+ if (exists $ctx->{-anchors} && $$x =~ # diffstat lines:
+ /((?:^\x20(?:[^\n]+?)(?:\x20+\|\x20[^\n]*\n))+)
+ (\x20[0-9]+\x20files?\x20)changed,/msx) {
+ my $pre = substr($$x, 0, $-[0]); # (likely) short prefix
+ substr($$x, 0, $+[0], ''); # sv_chop on $$x ($$x may be long)
+ my @x = ($2, $1);
+ my $lnk = $ctx->{-linkify};
+ my $zfh = $ctx->{zfh};
+ # uninteresting prefix
+ print $zfh $lnk->to_html($pre);
+ 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), # $3 /^ \d+ files? /
+ qq(<a href="$ch">changed</a>,),
+ # insertions/deletions, notes, commit message, etc:
+ $lnk->to_html($$x);
+ } else {
+ print { $ctx->{zfh} } $ctx->{-linkify}->to_html($$x);
}
}
my @top = split($EXTRACT_DIFFS, $$cur);
undef $$cur; # free memory
- my $linkify = $ctx->{-linkify};
- my $dst = $ctx->{obuf};
+ 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[0] =~ $IS_OID) {
$dctx = diff_header(\$x, $ctx, \@top);
} elsif ($dctx) {
- my $after = '';
+ open(my $afh, '>>:utf8', \(my $after='')) or
+ die "open: $!";
# Quiet "Complex regular subexpression recursion limit"
# warning. Perl will truncate matches upon hitting
for my $s (split(/((?:(?:^\+[^\n]*\n)+)|
(?:(?:^-[^\n]*\n)+)|
(?:^@@ [^\n]+\n))/xsm, $x)) {
+ undef $x;
if (!defined($dctx)) {
- $after .= $s;
+ print $afh $s;
} elsif ($s =~ s/\A@@ (\S+) (\S+) @@//) {
- $$dst .= qq(<span\nclass="hunk">);
- diff_hunk($dst, $dctx, $1, $2);
- $$dst .= $linkify->to_html($s);
- $$dst .= '</span>';
- } elsif ($s =~ /\A\+/) {
- $$dst .= qq(<span\nclass="add">);
- $$dst .= $linkify->to_html($s);
- $$dst .= '</span>';
+ print $zfh qq(<span\nclass="hunk">),
+ diff_hunk($dctx, $1, $2),
+ $lnk->to_html($s),
+ '</span>';
+ } elsif ($s =~ /\A\+/) { # $s may be huge
+ print $zfh qq(<span\nclass="add">),
+ $lnk->to_html($s),
+ '</span>';
} elsif ($s =~ /\A-- $/sm) { # email sig starts
$dctx = undef;
- $after .= $s;
- } elsif ($s =~ /\A-/) {
- $$dst .= qq(<span\nclass="del">);
- $$dst .= $linkify->to_html($s);
- $$dst .= '</span>';
- } else {
- $$dst .= $linkify->to_html($s);
+ print $afh $s;
+ } elsif ($s =~ /\A-/) { # $s may be huge
+ print $zfh qq(<span\nclass="del">),
+ $lnk->to_html($s),
+ '</span>';
+ } else { # $s may be huge
+ print $zfh $lnk->to_html($s);
}
}
- diff_before_or_after($ctx, \$after) unless $dctx;
+ if (!$dctx) {
+ utf8::decode($after);
+ diff_before_or_after($ctx, \$after);
+ }
} else {
diff_before_or_after($ctx, \$x);
}