X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FViewDiff.pm;h=be0c0452d198112599fa593f9aab368097ad1103;hb=02cdbe1c1638ba8e80351b39029c08343fab018b;hp=a8045687ef48b59c0755f4e7b8f750aa722a07d3;hpb=cf439203c31836e4c48f632f902aa58db6924972;p=public-inbox.git
diff --git a/lib/PublicInbox/ViewDiff.pm b/lib/PublicInbox/ViewDiff.pm
index a8045687..be0c0452 100644
--- a/lib/PublicInbox/ViewDiff.pm
+++ b/lib/PublicInbox/ViewDiff.pm
@@ -12,15 +12,19 @@ use warnings;
use base qw(Exporter);
our @EXPORT_OK = qw(flush_diff);
use URI::Escape qw(uri_escape_utf8);
-use PublicInbox::Hval qw(ascii_html);
+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 } # TODO
+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
@@ -37,10 +41,8 @@ my $OID_BLOB = '[a-f0-9]{7,40}';
my $PATH_A = '"?a/.+|/dev/null';
my $PATH_B = '"?b/.+|/dev/null';
-sub to_html ($$) {
- $_[0]->linkify_1($_[1]);
- $_[0]->linkify_2(ascii_html($_[1]));
-}
+# cf. git diff.c :: get_compact_summary
+my $DIFFSTAT_COMMENT = qr/\((?:new|gone|(?:(?:new|mode) [\+\-][lx]))\)/;
# link to line numbers in blobs
sub diff_hunk ($$$$) {
@@ -51,12 +53,12 @@ sub diff_hunk ($$$$) {
(defined($spfx) && defined($oid_a) && defined($oid_b)) or
return "@@ $ca $cb @@";
- my ($n) = ($ca =~ /^-(\d+)/);
+ my ($n) = ($ca =~ /^-([0-9]+)/);
$n = defined($n) ? do { ++$n; "#n$n" } : '';
my $rv = qq(@@ {Q}$n">$ca);
- ($n) = ($cb =~ /^\+(\d+)/);
+ ($n) = ($cb =~ /^\+([0-9]+)/);
$n = defined($n) ? do { ++$n; "#n$n" } : '';
$rv .= qq( {Q}$n">$cb @@);
@@ -75,82 +77,149 @@ sub to_state ($$$) {
$$dst .= qq();
}
-sub flush_diff ($$$$) {
- my ($dst, $spfx, $linkify, $diff) = @_;
+sub anchor0 ($$$$$) {
+ my ($dst, $ctx, $linkify, $fn, $rest) = @_;
+
+ my $orig = $fn;
+
+ # normal git diffstat output is impossible to parse reliably
+ # without --numstat, and that isn't the default for format-patch.
+ # So only do best-effort handling of renames for common cases;
+ # which works well in practice. If projects put "=>", or trailing
+ # spaces in filenames, oh well :P
+ $fn =~ s/(?: *$DIFFSTAT_COMMENT)? *\z//so;
+ $fn =~ s/{(?:.+) => (.+)}/$1/ or $fn =~ s/.* => (.+)/$1/;
+ $fn = git_unquote($fn);
+
+ # long filenames will require us to walk backwards in anchor1
+ if ($fn =~ s!\A\.\.\./?!!) {
+ my $lp = $ctx->{-long_path} ||= {};
+ $lp->{$fn} = qr/\Q$fn\E\z/s;
+ }
+
+ if (my $attr = to_attr($ctx->{-apfx}.$fn)) {
+ $ctx->{-anchors}->{$attr} = 1;
+ my $spaces = ($orig =~ s/( +)\z//) ? $1 : '';
+ $$dst .= " " .
+ ascii_html($orig) . '' . $spaces .
+ $linkify->to_html($rest);
+ return 1;
+ }
+ undef;
+}
+
+sub anchor1 ($$$$$) {
+ my ($dst, $ctx, $linkify, $pb, $s) = @_;
+ my $attr = to_attr($ctx->{-apfx}.$pb) or return;
+ my $line = $linkify->to_html($s);
+
+ my $ok = delete $ctx->{-anchors}->{$attr};
+
+ # unlikely, check the end of all long path names we captured:
+ unless ($ok) {
+ my $lp = $ctx->{-long_path} or return;
+ foreach my $fn (keys %$lp) {
+ $pb =~ $lp->{$fn} or next;
+
+ delete $lp->{$fn};
+ $attr = to_attr($ctx->{-apfx}.$fn) or return;
+ $ok = delete $ctx->{-anchors}->{$attr} or return;
+ last;
+ }
+ }
+ if ($ok && $line =~ s/^diff //) {
+ $$dst .= "diff ".$line;
+ return 1;
+ }
+ undef
+}
+
+sub flush_diff ($$$) {
+ my ($dst, $ctx, $linkify) = @_;
+ my $diff = $ctx->{-diff};
+ my $spfx = $ctx->{-spfx};
my $state = DSTATE_INIT;
my $dctx = { Q => '' }; # {}, keys: oid_a, oid_b, path_a, path_b
foreach my $s (@$diff) {
- if ($s =~ /^ /) {
- if ($state2class[$state]) {
+ if ($s =~ /^---$/) {
+ to_state($dst, $state, DSTATE_STAT);
+ $$dst .= $s;
+ } elsif ($s =~ /^ / || ($s =~ /^$/ && $state >= DSTATE_CTX)) {
+ # works for common cases, but not weird/long filenames
+ if ($state == DSTATE_STAT &&
+ $s =~ /^ (.+)( +\| .*\z)/s) {
+ anchor0($dst, $ctx, $linkify, $1, $2) and next;
+ } elsif ($state2class[$state]) {
to_state($dst, $state, DSTATE_CTX);
}
- $$dst .= to_html($linkify, $s);
+ $$dst .= $linkify->to_html($s);
} elsif ($s =~ /^-- $/) { # email signature begins
$state == DSTATE_INIT or
to_state($dst, $state, DSTATE_INIT);
$$dst .= $s;
- } elsif ($s =~ m!^diff --git ($PATH_A) ($PATH_B)$!) {
+ } elsif ($s =~ m!^diff --git ($PATH_A) ($PATH_B)$!o) {
+ my ($pa, $pb) = ($1, $2);
if ($state != DSTATE_HEAD) {
- my ($pa, $pb) = ($1, $2);
to_state($dst, $state, DSTATE_HEAD);
- $pa = (split('/', git_unquote($pa), 2))[1];
- $pb = (split('/', git_unquote($pb), 2))[1];
- $dctx = {
- Q => "?b=".uri_escape_utf8($pb, UNSAFE),
- };
- if ($pa ne $pb) {
- $dctx->{Q} .=
- "&a=".uri_escape_utf8($pa, UNSAFE);
- }
}
- $$dst .= to_html($linkify, $s);
+ $pa = (split('/', git_unquote($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;
+ $$dst .= $linkify->to_html($s);
} elsif ($s =~ s/^(index $OID_NULL\.\.)($OID_BLOB)\b//o) {
$$dst .= $1 . oid($dctx, $spfx, $2);
$dctx = { Q => '' };
- $$dst .= to_html($linkify, $s) ;
+ $$dst .= $linkify->to_html($s) ;
} elsif ($s =~ s/^index ($OID_BLOB)(\.\.$OID_NULL)\b//o) {
$$dst .= 'index ' . oid($dctx, $spfx, $1) . $2;
$dctx = { Q => '' };
- $$dst .= to_html($linkify, $s);
+ $$dst .= $linkify->to_html($s);
} elsif ($s =~ /^index ($OID_BLOB)\.\.($OID_BLOB)/o) {
$dctx->{oid_a} = $1;
$dctx->{oid_b} = $2;
- $$dst .= to_html($linkify, $s);
+ $$dst .= $linkify->to_html($s);
} elsif ($s =~ s/^@@ (\S+) (\S+) @@//) {
$$dst .= '' if $state2class[$state];
$$dst .= qq();
$$dst .= diff_hunk($dctx, $spfx, $1, $2);
$$dst .= '';
$state = DSTATE_CTX;
- $$dst .= to_html($linkify, $s);
- } elsif ($s =~ m!^--- $PATH_A! ||
- $s =~ m!^\+{3} $PATH_B!) {
- # color only (no oid link)
- $state == DSTATE_INIT and
+ $$dst .= $linkify->to_html($s);
+ } elsif ($s =~ m!^--- (?:$PATH_A)!o ||
+ $s =~ m!^\+{3} (?:$PATH_B)!o) {
+ # color only (no oid link) if missing dctx->{oid_*}
+ $state <= DSTATE_STAT and
to_state($dst, $state, DSTATE_HEAD);
- $$dst .= to_html($linkify, $s);
+ $$dst .= $linkify->to_html($s);
} elsif ($s =~ /^\+/) {
- if ($state != DSTATE_ADD && $state != DSTATE_INIT) {
+ if ($state != DSTATE_ADD && $state > DSTATE_STAT) {
to_state($dst, $state, DSTATE_ADD);
}
- $$dst .= to_html($linkify, $s);
+ $$dst .= $linkify->to_html($s);
} elsif ($s =~ /^-/) {
- if ($state != DSTATE_DEL && $state != DSTATE_INIT) {
+ if ($state != DSTATE_DEL && $state > DSTATE_STAT) {
to_state($dst, $state, DSTATE_DEL);
}
- $$dst .= to_html($linkify, $s);
+ $$dst .= $linkify->to_html($s);
# ignore the following lines in headers:
} elsif ($s =~ /^(?:dis)similarity index/ ||
$s =~ /^(?:old|new) mode/ ||
$s =~ /^(?:deleted|new) file mode/ ||
$s =~ /^(?:copy|rename) (?:from|to) / ||
$s =~ /^(?:dis)?similarity index /) {
- $$dst .= to_html($linkify, $s);
+ $$dst .= $linkify->to_html($s);
} else {
- $state == DSTATE_INIT or
+ $state <= DSTATE_STAT or
to_state($dst, $state, DSTATE_INIT);
- $$dst .= to_html($linkify, $s);
+ $$dst .= $linkify->to_html($s);
}
}
@$diff = ();