diff options
Diffstat (limited to 'contrib/diff-highlight')
| -rw-r--r-- | contrib/diff-highlight/README | 152 | ||||
| -rwxr-xr-x | contrib/diff-highlight/diff-highlight | 173 |
2 files changed, 325 insertions, 0 deletions
diff --git a/contrib/diff-highlight/README b/contrib/diff-highlight/README new file mode 100644 index 0000000000..502e03b305 --- /dev/null +++ b/contrib/diff-highlight/README @@ -0,0 +1,152 @@ +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 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 + 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 +--------------------------------------------- + +Bugs +---- + +Because diff-highlight relies on heuristics to guess which parts of +changes are important, there are some cases where the highlighting is +more distracting than useful. Fortunately, these cases are rare in +practice, and when they do occur, the worst case is simply a little +extra highlighting. This section documents some cases known to be +sub-optimal, in case somebody feels like working on improving the +heuristics. + +1. Two changes on the same line get highlighted in a blob. For example, + highlighting: + +---------------------------------------------- +-foo(buf, size); ++foo(obj->buf, obj->size); +---------------------------------------------- + + yields (where the inside of "+{}" would be highlighted): + +---------------------------------------------- +-foo(buf, size); ++foo(+{obj->buf, obj->}size); +---------------------------------------------- + + whereas a more semantically meaningful output would be: + +---------------------------------------------- +-foo(buf, size); ++foo(+{obj->}buf, +{obj->}size); +---------------------------------------------- + + Note that doing this right would probably involve a set of + content-specific boundary patterns, similar to word-diff. Otherwise + you get junk like: + +----------------------------------------------------- +-this line has some -{i}nt-{ere}sti-{ng} text on it ++this line has some +{fa}nt+{a}sti+{c} text on it +----------------------------------------------------- + + which is less readable than the current output. + +2. The multi-line matching assumes that lines in the pre- and post-image + match by position. This is often the case, but can be fooled when a + line is removed from the top and a new one added at the bottom (or + vice versa). Unless the lines in the middle are also changed, diffs + will show this as two hunks, and it will not get highlighted at all + (which is good). But if the lines in the middle are changed, the + highlighting can be misleading. Here's a pathological case: + +----------------------------------------------------- +-one +-two +-three +-four ++two 2 ++three 3 ++four 4 ++five 5 +----------------------------------------------------- + + which gets highlighted as: + +----------------------------------------------------- +-one +-t-{wo} +-three +-f-{our} ++two 2 ++t+{hree 3} ++four 4 ++f+{ive 5} +----------------------------------------------------- + + because it matches "two" to "three 3", and so forth. It would be + nicer as: + +----------------------------------------------------- +-one +-two +-three +-four ++two +{2} ++three +{3} ++four +{4} ++five 5 +----------------------------------------------------- + + which would probably involve pre-matching the lines into pairs + according to some heuristic. diff --git a/contrib/diff-highlight/diff-highlight b/contrib/diff-highlight/diff-highlight new file mode 100755 index 0000000000..c4404d49c9 --- /dev/null +++ b/contrib/diff-highlight/diff-highlight @@ -0,0 +1,173 @@ +#!/usr/bin/perl + +use warnings FATAL => 'all'; +use strict; + +# 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 $BORING = qr/$COLOR|\s/; + +my @removed; +my @added; +my $in_hunk; + +while (<>) { + if (!$in_hunk) { + print; + $in_hunk = /^$COLOR*\@/; + } + elsif (/^$COLOR*-/) { + push @removed, $_; + } + elsif (/^$COLOR*\+/) { + push @added, $_; + } + else { + show_hunk(\@removed, \@added); + @removed = (); + @added = (); + + print; + $in_hunk = /^$COLOR*[\@ ]/; + } + + # 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 $| = 1; + } +} + +# Flush any queued hunk (this can happen when there is no trailing context in +# the final diff of the input). +show_hunk(\@removed, \@added); + +exit 0; + +sub show_hunk { + my ($a, $b) = @_; + + # If one side is empty, then there is nothing to compare or highlight. + if (!@$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 { + 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; + } + } + + if (is_pair_interesting(\@a, $pa, $sa, \@b, $pb, $sb)) { + return highlight_line(\@a, $pa, $sa), + highlight_line(\@b, $pb, $sb); + } + else { + return join('', @a), + join('', @b); + } +} + +sub split_line { + local $_ = shift; + return map { /$COLOR/ ? $_ : (split //) } + split /($COLOR*)/; +} + +sub highlight_line { + my ($line, $prefix, $suffix) = @_; + + return join('', + @{$line}[0..($prefix-1)], + $HIGHLIGHT, + @{$line}[$prefix..$suffix], + $UNHIGHLIGHT, + @{$line}[($suffix+1)..$#$line] + ); +} + +# Pairs are interesting to highlight only if we are going to end up +# highlighting a subset (i.e., not the whole line). Otherwise, the highlighting +# is just useless noise. We can detect this by finding either a matching prefix +# or suffix (disregarding boring bits like whitespace and colorization). +sub is_pair_interesting { + my ($a, $pa, $sa, $b, $pb, $sb) = @_; + my $prefix_a = join('', @$a[0..($pa-1)]); + my $prefix_b = join('', @$b[0..($pb-1)]); + my $suffix_a = join('', @$a[($sa+1)..$#$a]); + my $suffix_b = join('', @$b[($sb+1)..$#$b]); + + return $prefix_a !~ /^$COLOR*-$BORING*$/ || + $prefix_b !~ /^$COLOR*\+$BORING*$/ || + $suffix_a !~ /^$BORING*$/ || + $suffix_b !~ /^$BORING*$/; +} |