X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FViewDiff.pm;h=a773e385a33b8e9fcdc351e1a10cb460026e95de;hb=3a2f21e2cb2e054be70505fae522a71627391610;hp=45d28e37792146cbdfd2d4e3c3e93e92241a251c;hpb=0fe405673ec45fed1be5898f3bb938ce09f304dd;p=public-inbox.git

diff --git a/lib/PublicInbox/ViewDiff.pm b/lib/PublicInbox/ViewDiff.pm
index 45d28e37..a773e385 100644
--- a/lib/PublicInbox/ViewDiff.pm
+++ b/lib/PublicInbox/ViewDiff.pm
@@ -12,11 +12,11 @@ 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 from_attr);
 use PublicInbox::Git qw(git_unquote);
 
 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 } # /^\+/
@@ -75,14 +75,79 @@ sub to_state ($$$) {
 	$$dst .= qq(<span\nclass="$class">);
 }
 
-sub flush_diff ($$$$) {
-	my ($dst, $spfx, $linkify, $diff) = @_;
+sub anchor0 ($$$$$) {
+	my ($dst, $ctx, $linkify, $fn, $rest) = @_;
+
+	my $orig = $fn;
+
+	# normal git diffstat output is impossible to parse reliably
+	# without --numstat, and that isn't the default for format-patch.
+	# So only do best-effort handling of renames for common cases;
+	# which works well in practice. If projects put "=>", or trailing
+	# spaces in filenames, oh well :P
+	$fn =~ s/ +\z//s;
+	$fn =~ s/{(?:.+) => (.+)}/$1/ or $fn =~ s/.* => (.+)/$1/;
+	$fn = git_unquote($fn);
+
+	# long filenames will require us to walk backwards in anchor1
+	if ($fn =~ s!\A\.\.\./?!!) {
+		my $lp = $ctx->{-long_path} ||= {};
+		$lp->{$fn} = qr/\Q$fn\E\z/s;
+	}
+
+	if (my $attr = to_attr($ctx->{-apfx}.$fn)) {
+		$ctx->{-anchors}->{$attr} = 1;
+		$$dst .= " <a\nid=i$attr\nhref=#$attr>" .
+			ascii_html($orig) . '</a>'.
+			to_html($linkify, $rest);
+		return 1;
+	}
+	undef;
+}
+
+sub anchor1 ($$$$$) {
+	my ($dst, $ctx, $linkify, $pb, $s) = @_;
+	my $attr = to_attr($ctx->{-apfx}.$pb) or return;
+	my $line = to_html($linkify, $s);
+
+	my $ok = delete $ctx->{-anchors}->{$attr};
+
+	# unlikely, check the end of all long path names we captured:
+	unless ($ok) {
+		my $lp = $ctx->{-long_path} or return;
+		foreach my $fn (keys %$lp) {
+			$pb =~ $lp->{$fn} or next;
+
+			delete $lp->{$fn};
+			$attr = to_attr($ctx->{-apfx}.$fn) or return;
+			$ok = delete $ctx->{-anchors}->{$attr} or return;
+			last;
+		}
+	}
+	if ($ok && $line =~ s/^diff //) {
+		$$dst .= "<a\nhref=#i$attr\nid=$attr>diff</a> ".$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);
+			$$dst .= $s;
+		} elsif ($s =~ /^ /) {
+			# works for common cases, but not weird/long filenames
+			if ($state == DSTATE_STAT &&
+					$s =~ /^ (.+)( +\| .*\z)/s) {
+				anchor0($dst, $ctx, $linkify, $1, $2) and next;
+			} elsif ($state2class[$state]) {
 				to_state($dst, $state, DSTATE_CTX);
 			}
 			$$dst .= to_html($linkify, $s);
@@ -91,25 +156,28 @@ sub flush_diff ($$$$) {
 				to_state($dst, $state, DSTATE_INIT);
 			$$dst .= $s;
 		} elsif ($s =~ m!^diff --git ($PATH_A) ($PATH_B)$!) {
+			my ($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);
-				}
 			}
+			$pa = (split('/', git_unquote($pa), 2))[1];
+			$pb = (split('/', git_unquote($pb), 2))[1];
+			$dctx = {
+				Q => "?b=".uri_escape_utf8($pb, UNSAFE),
+			};
+			if ($pa ne $pb) {
+				$dctx->{Q} .= '&amp;a='.
+					uri_escape_utf8($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);
+			$dctx = { Q => '' };
 			$$dst .= to_html($linkify, $s) ;
-		} elsif ($s =~ s/^index ($OID_NULL)(\.\.$OID_BLOB)\b//o) {
+		} elsif ($s =~ s/^index ($OID_BLOB)(\.\.$OID_NULL)\b//o) {
 			$$dst .= 'index ' . oid($dctx, $spfx, $1) . $2;
+			$dctx = { Q => '' };
 			$$dst .= to_html($linkify, $s);
 		} elsif ($s =~ /^index ($OID_BLOB)\.\.($OID_BLOB)/o) {
 			$dctx->{oid_a} = $1;
@@ -122,19 +190,19 @@ sub flush_diff ($$$$) {
 			$$dst .= '</span>';
 			$state = DSTATE_CTX;
 			$$dst .= to_html($linkify, $s);
-		} elsif ($s =~ m!^--- $PATH_A! ||
-		         $s =~ m!^\+{3} $PATH_B!)  {
-			# color only (no oid link)
-			$state == DSTATE_INIT and
+		} elsif ($s =~ m!^--- (?:$PATH_A)! ||
+		         $s =~ m!^\+{3} (?:$PATH_B)!)  {
+			# color only (no oid link) if missing dctx->{oid_*}
+			$state <= DSTATE_STAT and
 				to_state($dst, $state, DSTATE_HEAD);
 			$$dst .= to_html($linkify, $s);
 		} elsif ($s =~ /^\+/) {
-			if ($state != DSTATE_ADD && $state != DSTATE_INIT) {
+			if ($state != DSTATE_ADD && $state > DSTATE_STAT) {
 				to_state($dst, $state, DSTATE_ADD);
 			}
 			$$dst .= to_html($linkify, $s);
 		} elsif ($s =~ /^-/) {
-			if ($state != DSTATE_DEL && $state != DSTATE_INIT) {
+			if ($state != DSTATE_DEL && $state > DSTATE_STAT) {
 				to_state($dst, $state, DSTATE_DEL);
 			}
 			$$dst .= to_html($linkify, $s);
@@ -146,7 +214,7 @@ sub flush_diff ($$$$) {
 			 $s =~ /^(?:dis)?similarity index /) {
 			$$dst .= to_html($linkify, $s);
 		} else {
-			$state == DSTATE_INIT or
+			$state <= DSTATE_STAT or
 				to_state($dst, $state, DSTATE_INIT);
 			$$dst .= to_html($linkify, $s);
 		}