use base qw(Exporter);
our @EXPORT_OK = qw(flush_diff);
use URI::Escape qw(uri_escape_utf8);
-use PublicInbox::Hval qw(ascii_html to_attr from_attr);
+use PublicInbox::Hval qw(ascii_html to_attr);
use PublicInbox::Git qw(git_unquote);
+# keep track of state so we can avoid redundant HTML tags for
+# identically-classed lines
sub DSTATE_INIT () { 0 }
sub DSTATE_STAT () { 1 }
sub DSTATE_HEAD () { 2 } # /^diff --git /, /^index /, /^--- /, /^\+\+\+ /
sub DSTATE_CTX () { 3 } # /^ /
sub DSTATE_ADD () { 4 } # /^\+/
sub DSTATE_DEL () { 5 } # /^\-/
+
+# maps the DSTATE_* to CSS class names compatible with what cgit uses:
my @state2class = (
'', # init
'', # stat
my $PATH_A = '"?a/.+|/dev/null';
my $PATH_B = '"?b/.+|/dev/null';
+# cf. git diff.c :: get_compact_summary
+my $DIFFSTAT_COMMENT = qr/\((?:new|gone|(?:(?:new|mode) [\+\-][lx]))\)/;
+
sub to_html ($$) {
$_[0]->linkify_1($_[1]);
$_[0]->linkify_2(ascii_html($_[1]));
(defined($spfx) && defined($oid_a) && defined($oid_b)) or
return "@@ $ca $cb @@";
- my ($n) = ($ca =~ /^-(\d+)/);
+ my ($n) = ($ca =~ /^-([0-9]+)/);
$n = defined($n) ? do { ++$n; "#n$n" } : '';
my $rv = qq(@@ <a\nhref="$spfx$oid_a/s/$dctx->{Q}$n">$ca</a>);
- ($n) = ($cb =~ /^\+(\d+)/);
+ ($n) = ($cb =~ /^\+([0-9]+)/);
$n = defined($n) ? do { ++$n; "#n$n" } : '';
$rv .= qq( <a\nhref="$spfx$oid_b/s/$dctx->{Q}$n">$cb</a> @@);
}
sub anchor0 ($$$$$) {
- my ($dst, $anchors, $linkify, $fn, $rest) = @_;
- if (my $attr = to_attr($fn)) {
- $anchors->{$attr} = 1;
- $$dst .= " <a\nhref=#$attr>" .
- ascii_html($fn) . '</a>'.
+ my ($dst, $ctx, $linkify, $fn, $rest) = @_;
+
+ my $orig = $fn;
+
+ # normal git diffstat output is impossible to parse reliably
+ # without --numstat, and that isn't the default for format-patch.
+ # 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/;
+ $fn = git_unquote($fn);
+
+ # long filenames will require us to walk backwards in anchor1
+ if ($fn =~ s!\A\.\.\./?!!) {
+ my $lp = $ctx->{-long_path} ||= {};
+ $lp->{$fn} = qr/\Q$fn\E\z/s;
+ }
+
+ if (my $attr = to_attr($ctx->{-apfx}.$fn)) {
+ $ctx->{-anchors}->{$attr} = 1;
+ my $spaces = ($orig =~ s/( +)\z//) ? $1 : '';
+ $$dst .= " <a\nid=i$attr\nhref=#$attr>" .
+ ascii_html($orig) . '</a>' . $spaces .
to_html($linkify, $rest);
return 1;
}
}
sub anchor1 ($$$$$) {
- my ($dst, $anchors, $linkify, $pb, $s) = @_;
- my $attr = to_attr($pb) or return;
+ my ($dst, $ctx, $linkify, $pb, $s) = @_;
+ my $attr = to_attr($ctx->{-apfx}.$pb) or return;
my $line = to_html($linkify, $s);
- if (delete $anchors->{$attr} && $line =~ s/^diff //) {
- $$dst .= "<a\nhref=#ds\nid=$attr>diff</a> ".$line;
+ my $ok = delete $ctx->{-anchors}->{$attr};
+
+ # unlikely, check the end of all long path names we captured:
+ 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;
+ }
+ }
+ if ($ok && $line =~ s/^diff //) {
+ $$dst .= "<a\nhref=#i$attr\nid=$attr>diff</a> ".$line;
return 1;
}
undef
}
-sub flush_diff ($$$$) {
- my ($dst, $spfx, $linkify, $diff) = @_;
+sub flush_diff ($$$) {
+ my ($dst, $ctx, $linkify) = @_;
+ my $diff = $ctx->{-diff};
+ my $spfx = $ctx->{-spfx};
my $state = DSTATE_INIT;
my $dctx = { Q => '' }; # {}, keys: oid_a, oid_b, path_a, path_b
- my $anchors = {}; # attr => filename
foreach my $s (@$diff) {
if ($s =~ /^---$/) {
to_state($dst, $state, DSTATE_STAT);
- $$dst .= "<span\nid=ds>" . $s . '</span>';
- } elsif ($s =~ /^ /) {
+ $$dst .= $s;
+ } elsif ($s =~ /^ / || ($s =~ /^$/ && $state >= DSTATE_CTX)) {
# works for common cases, but not weird/long filenames
if ($state == DSTATE_STAT &&
- $s =~ /^ (\S+)(\s+\|.*\z)/s) {
- anchor0($dst, $anchors, $linkify, $1, $2)
- and next;
+ $s =~ /^ (.+)( +\| .*\z)/s) {
+ anchor0($dst, $ctx, $linkify, $1, $2) and next;
} elsif ($state2class[$state]) {
to_state($dst, $state, DSTATE_CTX);
}
$state == DSTATE_INIT or
to_state($dst, $state, DSTATE_INIT);
$$dst .= $s;
- } elsif ($s =~ m!^diff --git ($PATH_A) ($PATH_B)$!) {
+ } elsif ($s =~ m!^diff --git ($PATH_A) ($PATH_B)$!o) {
+ my ($pa, $pb) = ($1, $2);
if ($state != DSTATE_HEAD) {
- my ($pa, $pb) = ($1, $2);
to_state($dst, $state, DSTATE_HEAD);
- $pa = (split('/', git_unquote($pa), 2))[1];
- $pb = (split('/', git_unquote($pb), 2))[1];
- $dctx = {
- Q => "?b=".uri_escape_utf8($pb, UNSAFE),
- };
- if ($pa ne $pb) {
- $dctx->{Q} .=
- "&a=".uri_escape_utf8($pa, UNSAFE);
- }
- anchor1($dst, $anchors, $linkify, $pb, $s)
- and next;
}
+ $pa = (split('/', git_unquote($pa), 2))[1];
+ $pb = (split('/', git_unquote($pb), 2))[1];
+ $dctx = {
+ Q => "?b=".uri_escape_utf8($pb, UNSAFE),
+ };
+ if ($pa ne $pb) {
+ $dctx->{Q} .= '&a='.
+ uri_escape_utf8($pa, UNSAFE);
+ }
+ anchor1($dst, $ctx, $linkify, $pb, $s) and next;
$$dst .= to_html($linkify, $s);
} elsif ($s =~ s/^(index $OID_NULL\.\.)($OID_BLOB)\b//o) {
$$dst .= $1 . oid($dctx, $spfx, $2);
$$dst .= '</span>';
$state = DSTATE_CTX;
$$dst .= to_html($linkify, $s);
- } elsif ($s =~ m!^--- $PATH_A! ||
- $s =~ m!^\+{3} $PATH_B!) {
- # color only (no oid link)
+ } elsif ($s =~ m!^--- (?:$PATH_A)!o ||
+ $s =~ m!^\+{3} (?:$PATH_B)!o) {
+ # color only (no oid link) if missing dctx->{oid_*}
$state <= DSTATE_STAT and
to_state($dst, $state, DSTATE_HEAD);
$$dst .= to_html($linkify, $s);