--- /dev/null
+diff-highlight
+==============
+
+Line oriented diffs are great for reviewing code, because for most
+hunks, you want to see the old and the new segments of code next to each
+other. Sometimes, though, when an old line and a new line are very
+similar, it's hard to immediately see the difference.
+
+You can use "--color-words" to highlight only the changed portions of
+lines. However, this can often be hard to read for code, as it loses
+the line structure, and you end up with oddly formatted bits.
+
+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.
+
+ 2. It will find the common prefix and suffix of two lines, and
+ consider everything in the middle to be "different". It could
+ instead do a real diff of the characters between the two lines and
+ find common subsequences. However, the point of the highlight is to
+ call attention to a certain area. Even if some small subset of the
+ highlighted area actually didn't change, that's OK. In practice it
+ ends up being more readable to just have a single blob on the line
+ showing the interesting bit.
+
+The goal of the script is therefore not to be exact about highlighting
+changes, but to call attention to areas of interest without being
+visually distracting. Non-diff lines and existing diff coloration is
+preserved; the intent is that the output should look exactly the same as
+the input, except for the occasional highlight.
+
+Use
+---
+
+You can try out the diff-highlight program with:
+
+---------------------------------------------
+git log -p --color | /path/to/diff-highlight
+---------------------------------------------
+
+If you want to use it all the time, drop it in your $PATH and put the
+following in your git configuration:
+
+---------------------------------------------
+[pager]
+ log = diff-highlight | less
+ show = diff-highlight | less
+ diff = diff-highlight | less
+---------------------------------------------
--- /dev/null
+#!/usr/bin/perl
+
+# Highlight by reversing foreground and background. You could do
+# other things like bold or underline if you prefer.
+my $HIGHLIGHT = "\x1b[7m";
+my $UNHIGHLIGHT = "\x1b[27m";
+my $COLOR = qr/\x1b\[[0-9;]*m/;
+
+my @window;
+
+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_pair(shift @window, shift @window);
+ }
+ else {
+ print shift @window;
+ }
+
+ # Most of the time there is enough output to keep things streaming,
+ # but for something like "git log -Sfoo", you can get one early
+ # commit and then many seconds of nothing. We want to show
+ # that one commit as soon as possible.
+ #
+ # Since we can receive arbitrary input, there's no optimal
+ # place to flush. Flushing on a blank line is a heuristic that
+ # happens to match git-log output.
+ if (!length) {
+ local $| = 1;
+ }
+}
+
+# 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_pair(shift @window, shift @window);
+}
+
+# And then flush any remaining lines.
+while (@window) {
+ print shift @window;
+}
+
+exit 0;
+
+sub show_pair {
+ my @a = split_line(shift);
+ my @b = split_line(shift);
+
+ # Find common prefix, taking care to skip any ansi
+ # color codes.
+ my $seen_plusminus;
+ my ($pa, $pb) = (0, 0);
+ while ($pa < @a && $pb < @b) {
+ if ($a[$pa] =~ /$COLOR/) {
+ $pa++;
+ }
+ elsif ($b[$pb] =~ /$COLOR/) {
+ $pb++;
+ }
+ elsif ($a[$pa] eq $b[$pb]) {
+ $pa++;
+ $pb++;
+ }
+ elsif (!$seen_plusminus && $a[$pa] eq '-' && $b[$pb] eq '+') {
+ $seen_plusminus = 1;
+ $pa++;
+ $pb++;
+ }
+ else {
+ last;
+ }
+ }
+
+ # Find common suffix, ignoring colors.
+ my ($sa, $sb) = ($#a, $#b);
+ while ($sa >= $pa && $sb >= $pb) {
+ if ($a[$sa] =~ /$COLOR/) {
+ $sa--;
+ }
+ elsif ($b[$sb] =~ /$COLOR/) {
+ $sb--;
+ }
+ elsif ($a[$sa] eq $b[$sb]) {
+ $sa--;
+ $sb--;
+ }
+ else {
+ last;
+ }
+ }
+
+ print highlight(\@a, $pa, $sa);
+ print highlight(\@b, $pb, $sb);
+}
+
+sub split_line {
+ local $_ = shift;
+ return map { /$COLOR/ ? $_ : (split //) }
+ split /($COLOR*)/;
+}
+
+sub highlight {
+ my ($line, $prefix, $suffix) = @_;
+
+ return join('',
+ @{$line}[0..($prefix-1)],
+ $HIGHLIGHT,
+ @{$line}[$prefix..$suffix],
+ $UNHIGHLIGHT,
+ @{$line}[($suffix+1)..$#$line]
+ );
+}