diff --git a/contrib/diff-highlight/README b/contrib/diff-highlight/README index 1b7b6df8eb..4a58579779 100644 --- a/contrib/diff-highlight/README +++ b/contrib/diff-highlight/README @@ -14,13 +14,15 @@ Instead, this script post-processes the line-oriented diff, finds pairs of lines, and highlights the differing segments. It's currently very simple and stupid about doing these tasks. In particular: - 1. It will only highlight a pair of lines if they are the only two - lines in a hunk. It could instead try to match up "before" and - "after" lines for a given hunk into pairs of similar lines. - However, this may end up visually distracting, as the paired - lines would have other highlighted lines in between them. And in - practice, the lines which most need attention called to their - small, hard-to-see changes are touching only a single line. + 1. It will only highlight hunks in which the number of removed and + added lines is the same, and it will pair lines within the hunk by + position (so the first removed line is compared to the first added + line, and so forth). This is simple and tends to work well in + practice. More complex changes don't highlight well, so we tend to + exclude them due to the "same number of removed and added lines" + restriction. Or even if we do try to highlight them, they end up + not highlighting because of our "don't highlight if the whole line + would be highlighted" rule. 2. It will find the common prefix and suffix of two lines, and consider everything in the middle to be "different". It could diff --git a/contrib/diff-highlight/diff-highlight b/contrib/diff-highlight/diff-highlight index 279d21181e..c4404d49c9 100755 --- a/contrib/diff-highlight/diff-highlight +++ b/contrib/diff-highlight/diff-highlight @@ -10,23 +10,28 @@ my $UNHIGHLIGHT = "\x1b[27m"; my $COLOR = qr/\x1b\[[0-9;]*m/; my $BORING = qr/$COLOR|\s/; -my @window; +my @removed; +my @added; +my $in_hunk; while (<>) { - # We highlight only single-line changes, so we need - # a 4-line window to make a decision on whether - # to highlight. - push @window, $_; - next if @window < 4; - if ($window[0] =~ /^$COLOR*(\@| )/ && - $window[1] =~ /^$COLOR*-/ && - $window[2] =~ /^$COLOR*\+/ && - $window[3] !~ /^$COLOR*\+/) { - print shift @window; - show_hunk(shift @window, shift @window); + if (!$in_hunk) { + print; + $in_hunk = /^$COLOR*\@/; + } + elsif (/^$COLOR*-/) { + push @removed, $_; + } + elsif (/^$COLOR*\+/) { + push @added, $_; } else { - print shift @window; + show_hunk(\@removed, \@added); + @removed = (); + @added = (); + + print; + $in_hunk = /^$COLOR*[\@ ]/; } # Most of the time there is enough output to keep things streaming, @@ -42,26 +47,37 @@ while (<>) { } } -# Special case a single-line hunk at the end of file. -if (@window == 3 && - $window[0] =~ /^$COLOR*(\@| )/ && - $window[1] =~ /^$COLOR*-/ && - $window[2] =~ /^$COLOR*\+/) { - print shift @window; - show_hunk(shift @window, shift @window); -} - -# And then flush any remaining lines. -while (@window) { - print shift @window; -} +# Flush any queued hunk (this can happen when there is no trailing context in +# the final diff of the input). +show_hunk(\@removed, \@added); exit 0; sub show_hunk { my ($a, $b) = @_; - print highlight_pair($a, $b); + # If one side is empty, then there is nothing to compare or highlight. + if (!@$a || !@$b) { + print @$a, @$b; + return; + } + + # If we have mismatched numbers of lines on each side, we could try to + # be clever and match up similar lines. But for now we are simple and + # stupid, and only handle multi-line hunks that remove and add the same + # number of lines. + if (@$a != @$b) { + print @$a, @$b; + return; + } + + my @queue; + for (my $i = 0; $i < @$a; $i++) { + my ($rm, $add) = highlight_pair($a->[$i], $b->[$i]); + print $rm; + push @queue, $add; + } + print @queue; } sub highlight_pair {