-sub flush_diff ($$$) {
- my ($dst, $ctx, $linkify) = @_;
- my $diff = $ctx->{-diff};
- my $spfx = $ctx->{-spfx};
- my $state = DSTATE_INIT;
- my $dctx = { Q => '' }; # {}, keys: oid_a, oid_b, path_a, path_b
-
- foreach my $s (@$diff) {
- if ($s =~ /^---$/) {
- to_state($dst, $state, DSTATE_STAT);
- $$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);
- }
- $$dst .= to_html($linkify, $s);
- } elsif ($s =~ /^-- $/) { # email signature begins
- $state == DSTATE_INIT or
- to_state($dst, $state, DSTATE_INIT);
- $$dst .= $s;
- } elsif ($s =~ m!^diff --git ($PATH_A) ($PATH_B)$!) {
- my ($pa, $pb) = ($1, $2);
- if ($state != DSTATE_HEAD) {
- 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, $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 => '' };
- $$dst .= to_html($linkify, $s) ;
- } elsif ($s =~ s/^index ($OID_BLOB)(\.\.$OID_NULL)\b//o) {
- $$dst .= 'index ' . oid($dctx, $spfx, $1) . $2;
- $dctx = { Q => '' };
- $$dst .= to_html($linkify, $s);
- } elsif ($s =~ /^index ($OID_BLOB)\.\.($OID_BLOB)/o) {
- $dctx->{oid_a} = $1;
- $dctx->{oid_b} = $2;
- $$dst .= to_html($linkify, $s);
- } elsif ($s =~ s/^@@ (\S+) (\S+) @@//) {
- $$dst .= '</span>' if $state2class[$state];
- $$dst .= qq(<span\nclass="hunk">);
- $$dst .= diff_hunk($dctx, $spfx, $1, $2);
- $$dst .= '</span>';
- $state = DSTATE_CTX;
- $$dst .= to_html($linkify, $s);
- } elsif ($s =~ m!^--- (?:$PATH_A)! ||
- $s =~ m!^\+{3} (?:$PATH_B)!) {
- # color only (no oid link) if missing dctx->{oid_*}
- $state <= DSTATE_STAT and
- to_state($dst, $state, DSTATE_HEAD);
- $$dst .= to_html($linkify, $s);
- } elsif ($s =~ /^\+/) {
- if ($state != DSTATE_ADD && $state > DSTATE_STAT) {
- to_state($dst, $state, DSTATE_ADD);
- }
- $$dst .= to_html($linkify, $s);
- } elsif ($s =~ /^-/) {
- if ($state != DSTATE_DEL && $state > DSTATE_STAT) {
- to_state($dst, $state, DSTATE_DEL);
+sub diff_before_or_after ($$) {
+ 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), # $3 /^ \d+ files? /
+ qq(<a href="$ch">changed</a>,),
+ ascii_html(pop @x), # insertions/deletions
+ $lnk->to_html(@x); # notes, commit message, etc
+ } else {
+ print { $ctx->{zfh} } $ctx->{-linkify}->to_html($$x);
+ }
+}
+
+# callers must do CRLF => LF conversion before calling this
+sub flush_diff ($$) {
+ my ($ctx, $cur) = @_;
+
+ my @top = split($EXTRACT_DIFFS, $$cur);
+ undef $$cur; # free memory
+
+ 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] =~ $IS_OID &&
+ $top[0] =~ $IS_OID) {
+ $dctx = diff_header(\$x, $ctx, \@top);
+ } elsif ($dctx) {
+ 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)) {
+ print $afh $s;
+ } elsif ($s =~ s/\A@@ (\S+) (\S+) @@//) {
+ 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;
+ 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);
+ }