2017-06-15 16:30:55 +00:00
|
|
|
package DiffHighlight;
|
2011-10-18 04:52:20 +00:00
|
|
|
|
2015-04-03 22:15:14 +00:00
|
|
|
use 5.008;
|
2012-02-13 22:28:10 +00:00
|
|
|
use warnings FATAL => 'all';
|
|
|
|
use strict;
|
|
|
|
|
2018-10-31 14:58:00 +00:00
|
|
|
# Use the correct value for both UNIX and Windows (/dev/null vs nul)
|
|
|
|
use File::Spec;
|
|
|
|
|
|
|
|
my $NULL = File::Spec->devnull();
|
|
|
|
|
2011-10-18 04:52:20 +00:00
|
|
|
# Highlight by reversing foreground and background. You could do
|
|
|
|
# other things like bold or underline if you prefer.
|
2014-11-20 15:29:18 +00:00
|
|
|
my @OLD_HIGHLIGHT = (
|
|
|
|
color_config('color.diff-highlight.oldnormal'),
|
|
|
|
color_config('color.diff-highlight.oldhighlight', "\x1b[7m"),
|
|
|
|
color_config('color.diff-highlight.oldreset', "\x1b[27m")
|
|
|
|
);
|
|
|
|
my @NEW_HIGHLIGHT = (
|
|
|
|
color_config('color.diff-highlight.newnormal', $OLD_HIGHLIGHT[0]),
|
|
|
|
color_config('color.diff-highlight.newhighlight', $OLD_HIGHLIGHT[1]),
|
|
|
|
color_config('color.diff-highlight.newreset', $OLD_HIGHLIGHT[2])
|
|
|
|
);
|
|
|
|
|
|
|
|
my $RESET = "\x1b[m";
|
2011-10-18 04:52:20 +00:00
|
|
|
my $COLOR = qr/\x1b\[[0-9;]*m/;
|
2012-02-13 22:32:47 +00:00
|
|
|
my $BORING = qr/$COLOR|\s/;
|
2011-10-18 04:52:20 +00:00
|
|
|
|
2012-02-13 22:36:36 +00:00
|
|
|
my @removed;
|
|
|
|
my @added;
|
|
|
|
my $in_hunk;
|
diff-highlight: detect --graph by indent
This patch fixes a corner case where diff-highlight may
scramble some diffs when combined with --graph.
Commit 7e4ffb4c17 (diff-highlight: add support for --graph
output, 2016-08-29) taught diff-highlight to skip past the
graph characters at the start of each line with this regex:
($COLOR?\|$COLOR?\s+)*
I.e., any series of pipes separated by and followed by
arbitrary whitespace. We need to match more than just a
single space because the commit in question may be indented
to accommodate other parts of the graph drawing. E.g.:
* commit 1234abcd
| ...
| diff --git ...
has only a single space, but for the last commit before a
fork:
| | |
| * | commit 1234abcd
| |/ ...
| | diff --git
the diff lines have more spaces between the pipes and the
start of the diff.
However, when we soak up all of those spaces with the
$GRAPH regex, we may accidentally include the leading space
for a context line. That means we may consider the actual
contents of a context line as part of the diff syntax. In
other words, something like this:
normal context line
-old line
+new line
-this is a context line with a leading dash
would cause us to see that final context line as a removal
line, and we'd end up showing the hunk in the wrong order:
normal context line
-old line
-this is a context line with a leading dash
+new line
Instead, let's a be a little more clever about parsing the
graph. We'll look for the actual "*" line that marks the
start of a commit, and record the indentation we see there.
Then we can skip past that indentation when checking whether
the line is a hunk header, removal, addition, etc.
There is one tricky thing: the indentation in bytes may be
different for various lines of the graph due to coloring.
E.g., the "*" on a commit line is generally shown without
color, but on the actual diff lines, it will be replaced
with a colorized "|" character, adding several bytes. We
work around this here by counting "visible" bytes. This is
unfortunately a bit more expensive, making us about twice as
slow to handle --graph output. But since this is meant to be
used interactively anyway, it's tolerably fast (and the
non-graph case is unaffected).
One alternative would be to search for hunk header lines and
use their indentation (since they'd have the same colors as
the diff lines which follow). But that just opens up
different corner cases. If we see:
| | @@ 1,2 1,3 @@
we cannot know if this is a real diff that has been
indented due to the graph, or if it's a context line that
happens to look like a diff header. We can only be sure of
the indent on the "*" lines, since we know those don't
contain arbitrary data (technically the user could include a
bunch of extra indentation via --format, but that's rare
enough to disregard).
Reported-by: Phillip Wood <phillip.wood@dunelm.org.uk>
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-03-21 05:59:01 +00:00
|
|
|
my $graph_indent = 0;
|
2011-10-18 04:52:20 +00:00
|
|
|
|
2017-06-15 16:30:55 +00:00
|
|
|
our $line_cb = sub { print @_ };
|
|
|
|
our $flush_cb = sub { local $| = 1 };
|
|
|
|
|
diff-highlight: detect --graph by indent
This patch fixes a corner case where diff-highlight may
scramble some diffs when combined with --graph.
Commit 7e4ffb4c17 (diff-highlight: add support for --graph
output, 2016-08-29) taught diff-highlight to skip past the
graph characters at the start of each line with this regex:
($COLOR?\|$COLOR?\s+)*
I.e., any series of pipes separated by and followed by
arbitrary whitespace. We need to match more than just a
single space because the commit in question may be indented
to accommodate other parts of the graph drawing. E.g.:
* commit 1234abcd
| ...
| diff --git ...
has only a single space, but for the last commit before a
fork:
| | |
| * | commit 1234abcd
| |/ ...
| | diff --git
the diff lines have more spaces between the pipes and the
start of the diff.
However, when we soak up all of those spaces with the
$GRAPH regex, we may accidentally include the leading space
for a context line. That means we may consider the actual
contents of a context line as part of the diff syntax. In
other words, something like this:
normal context line
-old line
+new line
-this is a context line with a leading dash
would cause us to see that final context line as a removal
line, and we'd end up showing the hunk in the wrong order:
normal context line
-old line
-this is a context line with a leading dash
+new line
Instead, let's a be a little more clever about parsing the
graph. We'll look for the actual "*" line that marks the
start of a commit, and record the indentation we see there.
Then we can skip past that indentation when checking whether
the line is a hunk header, removal, addition, etc.
There is one tricky thing: the indentation in bytes may be
different for various lines of the graph due to coloring.
E.g., the "*" on a commit line is generally shown without
color, but on the actual diff lines, it will be replaced
with a colorized "|" character, adding several bytes. We
work around this here by counting "visible" bytes. This is
unfortunately a bit more expensive, making us about twice as
slow to handle --graph output. But since this is meant to be
used interactively anyway, it's tolerably fast (and the
non-graph case is unaffected).
One alternative would be to search for hunk header lines and
use their indentation (since they'd have the same colors as
the diff lines which follow). But that just opens up
different corner cases. If we see:
| | @@ 1,2 1,3 @@
we cannot know if this is a real diff that has been
indented due to the graph, or if it's a context line that
happens to look like a diff header. We can only be sure of
the indent on the "*" lines, since we know those don't
contain arbitrary data (technically the user could include a
bunch of extra indentation via --format, but that's rare
enough to disregard).
Reported-by: Phillip Wood <phillip.wood@dunelm.org.uk>
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-03-21 05:59:01 +00:00
|
|
|
# Count the visible width of a string, excluding any terminal color sequences.
|
|
|
|
sub visible_width {
|
2017-06-15 16:30:55 +00:00
|
|
|
local $_ = shift;
|
diff-highlight: detect --graph by indent
This patch fixes a corner case where diff-highlight may
scramble some diffs when combined with --graph.
Commit 7e4ffb4c17 (diff-highlight: add support for --graph
output, 2016-08-29) taught diff-highlight to skip past the
graph characters at the start of each line with this regex:
($COLOR?\|$COLOR?\s+)*
I.e., any series of pipes separated by and followed by
arbitrary whitespace. We need to match more than just a
single space because the commit in question may be indented
to accommodate other parts of the graph drawing. E.g.:
* commit 1234abcd
| ...
| diff --git ...
has only a single space, but for the last commit before a
fork:
| | |
| * | commit 1234abcd
| |/ ...
| | diff --git
the diff lines have more spaces between the pipes and the
start of the diff.
However, when we soak up all of those spaces with the
$GRAPH regex, we may accidentally include the leading space
for a context line. That means we may consider the actual
contents of a context line as part of the diff syntax. In
other words, something like this:
normal context line
-old line
+new line
-this is a context line with a leading dash
would cause us to see that final context line as a removal
line, and we'd end up showing the hunk in the wrong order:
normal context line
-old line
-this is a context line with a leading dash
+new line
Instead, let's a be a little more clever about parsing the
graph. We'll look for the actual "*" line that marks the
start of a commit, and record the indentation we see there.
Then we can skip past that indentation when checking whether
the line is a hunk header, removal, addition, etc.
There is one tricky thing: the indentation in bytes may be
different for various lines of the graph due to coloring.
E.g., the "*" on a commit line is generally shown without
color, but on the actual diff lines, it will be replaced
with a colorized "|" character, adding several bytes. We
work around this here by counting "visible" bytes. This is
unfortunately a bit more expensive, making us about twice as
slow to handle --graph output. But since this is meant to be
used interactively anyway, it's tolerably fast (and the
non-graph case is unaffected).
One alternative would be to search for hunk header lines and
use their indentation (since they'd have the same colors as
the diff lines which follow). But that just opens up
different corner cases. If we see:
| | @@ 1,2 1,3 @@
we cannot know if this is a real diff that has been
indented due to the graph, or if it's a context line that
happens to look like a diff header. We can only be sure of
the indent on the "*" lines, since we know those don't
contain arbitrary data (technically the user could include a
bunch of extra indentation via --format, but that's rare
enough to disregard).
Reported-by: Phillip Wood <phillip.wood@dunelm.org.uk>
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-03-21 05:59:01 +00:00
|
|
|
my $ret = 0;
|
|
|
|
while (length) {
|
|
|
|
if (s/^$COLOR//) {
|
|
|
|
# skip colors
|
|
|
|
} elsif (s/^.//) {
|
|
|
|
$ret++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return $ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
# Return a substring of $str, omitting $len visible characters from the
|
|
|
|
# beginning, where terminal color sequences do not count as visible.
|
|
|
|
sub visible_substr {
|
|
|
|
my ($str, $len) = @_;
|
|
|
|
while ($len > 0) {
|
|
|
|
if ($str =~ s/^$COLOR//) {
|
|
|
|
next
|
|
|
|
}
|
|
|
|
$str =~ s/^.//;
|
|
|
|
$len--;
|
|
|
|
}
|
|
|
|
return $str;
|
|
|
|
}
|
|
|
|
|
|
|
|
sub handle_line {
|
|
|
|
my $orig = shift;
|
|
|
|
local $_ = $orig;
|
|
|
|
|
|
|
|
# match a graph line that begins a commit
|
|
|
|
if (/^(?:$COLOR?\|$COLOR?[ ])* # zero or more leading "|" with space
|
|
|
|
$COLOR?\*$COLOR?[ ] # a "*" with its trailing space
|
|
|
|
(?:$COLOR?\|$COLOR?[ ])* # zero or more trailing "|"
|
|
|
|
[ ]* # trailing whitespace for merges
|
|
|
|
/x) {
|
|
|
|
my $graph_prefix = $&;
|
|
|
|
|
|
|
|
# We must flush before setting graph indent, since the
|
|
|
|
# new commit may be indented differently from what we
|
|
|
|
# queued.
|
|
|
|
flush();
|
|
|
|
$graph_indent = visible_width($graph_prefix);
|
|
|
|
|
|
|
|
} elsif ($graph_indent) {
|
|
|
|
if (length($_) < $graph_indent) {
|
|
|
|
$graph_indent = 0;
|
|
|
|
} else {
|
|
|
|
$_ = visible_substr($_, $graph_indent);
|
|
|
|
}
|
|
|
|
}
|
2014-11-04 20:01:12 +00:00
|
|
|
|
2012-02-13 22:36:36 +00:00
|
|
|
if (!$in_hunk) {
|
diff-highlight: detect --graph by indent
This patch fixes a corner case where diff-highlight may
scramble some diffs when combined with --graph.
Commit 7e4ffb4c17 (diff-highlight: add support for --graph
output, 2016-08-29) taught diff-highlight to skip past the
graph characters at the start of each line with this regex:
($COLOR?\|$COLOR?\s+)*
I.e., any series of pipes separated by and followed by
arbitrary whitespace. We need to match more than just a
single space because the commit in question may be indented
to accommodate other parts of the graph drawing. E.g.:
* commit 1234abcd
| ...
| diff --git ...
has only a single space, but for the last commit before a
fork:
| | |
| * | commit 1234abcd
| |/ ...
| | diff --git
the diff lines have more spaces between the pipes and the
start of the diff.
However, when we soak up all of those spaces with the
$GRAPH regex, we may accidentally include the leading space
for a context line. That means we may consider the actual
contents of a context line as part of the diff syntax. In
other words, something like this:
normal context line
-old line
+new line
-this is a context line with a leading dash
would cause us to see that final context line as a removal
line, and we'd end up showing the hunk in the wrong order:
normal context line
-old line
-this is a context line with a leading dash
+new line
Instead, let's a be a little more clever about parsing the
graph. We'll look for the actual "*" line that marks the
start of a commit, and record the indentation we see there.
Then we can skip past that indentation when checking whether
the line is a hunk header, removal, addition, etc.
There is one tricky thing: the indentation in bytes may be
different for various lines of the graph due to coloring.
E.g., the "*" on a commit line is generally shown without
color, but on the actual diff lines, it will be replaced
with a colorized "|" character, adding several bytes. We
work around this here by counting "visible" bytes. This is
unfortunately a bit more expensive, making us about twice as
slow to handle --graph output. But since this is meant to be
used interactively anyway, it's tolerably fast (and the
non-graph case is unaffected).
One alternative would be to search for hunk header lines and
use their indentation (since they'd have the same colors as
the diff lines which follow). But that just opens up
different corner cases. If we see:
| | @@ 1,2 1,3 @@
we cannot know if this is a real diff that has been
indented due to the graph, or if it's a context line that
happens to look like a diff header. We can only be sure of
the indent on the "*" lines, since we know those don't
contain arbitrary data (technically the user could include a
bunch of extra indentation via --format, but that's rare
enough to disregard).
Reported-by: Phillip Wood <phillip.wood@dunelm.org.uk>
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-03-21 05:59:01 +00:00
|
|
|
$line_cb->($orig);
|
|
|
|
$in_hunk = /^$COLOR*\@\@ /;
|
2012-02-13 22:36:36 +00:00
|
|
|
}
|
diff-highlight: detect --graph by indent
This patch fixes a corner case where diff-highlight may
scramble some diffs when combined with --graph.
Commit 7e4ffb4c17 (diff-highlight: add support for --graph
output, 2016-08-29) taught diff-highlight to skip past the
graph characters at the start of each line with this regex:
($COLOR?\|$COLOR?\s+)*
I.e., any series of pipes separated by and followed by
arbitrary whitespace. We need to match more than just a
single space because the commit in question may be indented
to accommodate other parts of the graph drawing. E.g.:
* commit 1234abcd
| ...
| diff --git ...
has only a single space, but for the last commit before a
fork:
| | |
| * | commit 1234abcd
| |/ ...
| | diff --git
the diff lines have more spaces between the pipes and the
start of the diff.
However, when we soak up all of those spaces with the
$GRAPH regex, we may accidentally include the leading space
for a context line. That means we may consider the actual
contents of a context line as part of the diff syntax. In
other words, something like this:
normal context line
-old line
+new line
-this is a context line with a leading dash
would cause us to see that final context line as a removal
line, and we'd end up showing the hunk in the wrong order:
normal context line
-old line
-this is a context line with a leading dash
+new line
Instead, let's a be a little more clever about parsing the
graph. We'll look for the actual "*" line that marks the
start of a commit, and record the indentation we see there.
Then we can skip past that indentation when checking whether
the line is a hunk header, removal, addition, etc.
There is one tricky thing: the indentation in bytes may be
different for various lines of the graph due to coloring.
E.g., the "*" on a commit line is generally shown without
color, but on the actual diff lines, it will be replaced
with a colorized "|" character, adding several bytes. We
work around this here by counting "visible" bytes. This is
unfortunately a bit more expensive, making us about twice as
slow to handle --graph output. But since this is meant to be
used interactively anyway, it's tolerably fast (and the
non-graph case is unaffected).
One alternative would be to search for hunk header lines and
use their indentation (since they'd have the same colors as
the diff lines which follow). But that just opens up
different corner cases. If we see:
| | @@ 1,2 1,3 @@
we cannot know if this is a real diff that has been
indented due to the graph, or if it's a context line that
happens to look like a diff header. We can only be sure of
the indent on the "*" lines, since we know those don't
contain arbitrary data (technically the user could include a
bunch of extra indentation via --format, but that's rare
enough to disregard).
Reported-by: Phillip Wood <phillip.wood@dunelm.org.uk>
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-03-21 05:59:01 +00:00
|
|
|
elsif (/^$COLOR*-/) {
|
|
|
|
push @removed, $orig;
|
2012-02-13 22:36:36 +00:00
|
|
|
}
|
diff-highlight: detect --graph by indent
This patch fixes a corner case where diff-highlight may
scramble some diffs when combined with --graph.
Commit 7e4ffb4c17 (diff-highlight: add support for --graph
output, 2016-08-29) taught diff-highlight to skip past the
graph characters at the start of each line with this regex:
($COLOR?\|$COLOR?\s+)*
I.e., any series of pipes separated by and followed by
arbitrary whitespace. We need to match more than just a
single space because the commit in question may be indented
to accommodate other parts of the graph drawing. E.g.:
* commit 1234abcd
| ...
| diff --git ...
has only a single space, but for the last commit before a
fork:
| | |
| * | commit 1234abcd
| |/ ...
| | diff --git
the diff lines have more spaces between the pipes and the
start of the diff.
However, when we soak up all of those spaces with the
$GRAPH regex, we may accidentally include the leading space
for a context line. That means we may consider the actual
contents of a context line as part of the diff syntax. In
other words, something like this:
normal context line
-old line
+new line
-this is a context line with a leading dash
would cause us to see that final context line as a removal
line, and we'd end up showing the hunk in the wrong order:
normal context line
-old line
-this is a context line with a leading dash
+new line
Instead, let's a be a little more clever about parsing the
graph. We'll look for the actual "*" line that marks the
start of a commit, and record the indentation we see there.
Then we can skip past that indentation when checking whether
the line is a hunk header, removal, addition, etc.
There is one tricky thing: the indentation in bytes may be
different for various lines of the graph due to coloring.
E.g., the "*" on a commit line is generally shown without
color, but on the actual diff lines, it will be replaced
with a colorized "|" character, adding several bytes. We
work around this here by counting "visible" bytes. This is
unfortunately a bit more expensive, making us about twice as
slow to handle --graph output. But since this is meant to be
used interactively anyway, it's tolerably fast (and the
non-graph case is unaffected).
One alternative would be to search for hunk header lines and
use their indentation (since they'd have the same colors as
the diff lines which follow). But that just opens up
different corner cases. If we see:
| | @@ 1,2 1,3 @@
we cannot know if this is a real diff that has been
indented due to the graph, or if it's a context line that
happens to look like a diff header. We can only be sure of
the indent on the "*" lines, since we know those don't
contain arbitrary data (technically the user could include a
bunch of extra indentation via --format, but that's rare
enough to disregard).
Reported-by: Phillip Wood <phillip.wood@dunelm.org.uk>
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-03-21 05:59:01 +00:00
|
|
|
elsif (/^$COLOR*\+/) {
|
|
|
|
push @added, $orig;
|
2011-10-18 04:52:20 +00:00
|
|
|
}
|
|
|
|
else {
|
2018-03-21 05:56:37 +00:00
|
|
|
flush();
|
diff-highlight: detect --graph by indent
This patch fixes a corner case where diff-highlight may
scramble some diffs when combined with --graph.
Commit 7e4ffb4c17 (diff-highlight: add support for --graph
output, 2016-08-29) taught diff-highlight to skip past the
graph characters at the start of each line with this regex:
($COLOR?\|$COLOR?\s+)*
I.e., any series of pipes separated by and followed by
arbitrary whitespace. We need to match more than just a
single space because the commit in question may be indented
to accommodate other parts of the graph drawing. E.g.:
* commit 1234abcd
| ...
| diff --git ...
has only a single space, but for the last commit before a
fork:
| | |
| * | commit 1234abcd
| |/ ...
| | diff --git
the diff lines have more spaces between the pipes and the
start of the diff.
However, when we soak up all of those spaces with the
$GRAPH regex, we may accidentally include the leading space
for a context line. That means we may consider the actual
contents of a context line as part of the diff syntax. In
other words, something like this:
normal context line
-old line
+new line
-this is a context line with a leading dash
would cause us to see that final context line as a removal
line, and we'd end up showing the hunk in the wrong order:
normal context line
-old line
-this is a context line with a leading dash
+new line
Instead, let's a be a little more clever about parsing the
graph. We'll look for the actual "*" line that marks the
start of a commit, and record the indentation we see there.
Then we can skip past that indentation when checking whether
the line is a hunk header, removal, addition, etc.
There is one tricky thing: the indentation in bytes may be
different for various lines of the graph due to coloring.
E.g., the "*" on a commit line is generally shown without
color, but on the actual diff lines, it will be replaced
with a colorized "|" character, adding several bytes. We
work around this here by counting "visible" bytes. This is
unfortunately a bit more expensive, making us about twice as
slow to handle --graph output. But since this is meant to be
used interactively anyway, it's tolerably fast (and the
non-graph case is unaffected).
One alternative would be to search for hunk header lines and
use their indentation (since they'd have the same colors as
the diff lines which follow). But that just opens up
different corner cases. If we see:
| | @@ 1,2 1,3 @@
we cannot know if this is a real diff that has been
indented due to the graph, or if it's a context line that
happens to look like a diff header. We can only be sure of
the indent on the "*" lines, since we know those don't
contain arbitrary data (technically the user could include a
bunch of extra indentation via --format, but that's rare
enough to disregard).
Reported-by: Phillip Wood <phillip.wood@dunelm.org.uk>
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-03-21 05:59:01 +00:00
|
|
|
$line_cb->($orig);
|
|
|
|
$in_hunk = /^$COLOR*[\@ ]/;
|
2011-10-18 04:52:20 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
# 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) {
|
2017-06-15 16:30:55 +00:00
|
|
|
$flush_cb->();
|
2011-10-18 04:52:20 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2017-06-15 16:30:55 +00:00
|
|
|
sub flush {
|
|
|
|
# Flush any queued hunk (this can happen when there is no trailing
|
|
|
|
# context in the final diff of the input).
|
|
|
|
show_hunk(\@removed, \@added);
|
2018-03-21 05:56:37 +00:00
|
|
|
@removed = ();
|
|
|
|
@added = ();
|
2017-06-15 16:30:55 +00:00
|
|
|
}
|
2011-10-18 04:52:20 +00:00
|
|
|
|
2017-06-15 16:30:55 +00:00
|
|
|
sub highlight_stdin {
|
|
|
|
while (<STDIN>) {
|
|
|
|
handle_line($_);
|
|
|
|
}
|
|
|
|
flush();
|
|
|
|
}
|
2011-10-18 04:52:20 +00:00
|
|
|
|
2014-11-20 15:29:18 +00:00
|
|
|
# Ideally we would feed the default as a human-readable color to
|
|
|
|
# git-config as the fallback value. But diff-highlight does
|
|
|
|
# not otherwise depend on git at all, and there are reports
|
|
|
|
# of it being used in other settings. Let's handle our own
|
|
|
|
# fallback, which means we will work even if git can't be run.
|
|
|
|
sub color_config {
|
|
|
|
my ($key, $default) = @_;
|
2018-10-31 14:58:00 +00:00
|
|
|
my $s = `git config --get-color $key 2>$NULL`;
|
2014-11-20 15:29:18 +00:00
|
|
|
return length($s) ? $s : $default;
|
|
|
|
}
|
|
|
|
|
2012-02-13 22:33:10 +00:00
|
|
|
sub show_hunk {
|
|
|
|
my ($a, $b) = @_;
|
|
|
|
|
2012-02-13 22:36:36 +00:00
|
|
|
# If one side is empty, then there is nothing to compare or highlight.
|
|
|
|
if (!@$a || !@$b) {
|
2017-06-15 16:30:55 +00:00
|
|
|
$line_cb->(@$a, @$b);
|
2012-02-13 22:36:36 +00:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
# If we have mismatched numbers of lines on each side, we could try to
|
|
|
|
# be clever and match up similar lines. But for now we are simple and
|
|
|
|
# stupid, and only handle multi-line hunks that remove and add the same
|
|
|
|
# number of lines.
|
|
|
|
if (@$a != @$b) {
|
2017-06-15 16:30:55 +00:00
|
|
|
$line_cb->(@$a, @$b);
|
2012-02-13 22:36:36 +00:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
my @queue;
|
|
|
|
for (my $i = 0; $i < @$a; $i++) {
|
|
|
|
my ($rm, $add) = highlight_pair($a->[$i], $b->[$i]);
|
2017-06-15 16:30:55 +00:00
|
|
|
$line_cb->($rm);
|
2012-02-13 22:36:36 +00:00
|
|
|
push @queue, $add;
|
|
|
|
}
|
2017-06-15 16:30:55 +00:00
|
|
|
$line_cb->(@queue);
|
2012-02-13 22:33:10 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
sub highlight_pair {
|
2011-10-18 04:52:20 +00:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2012-02-13 22:32:47 +00:00
|
|
|
if (is_pair_interesting(\@a, $pa, $sa, \@b, $pb, $sb)) {
|
2014-11-20 15:29:18 +00:00
|
|
|
return highlight_line(\@a, $pa, $sa, \@OLD_HIGHLIGHT),
|
|
|
|
highlight_line(\@b, $pb, $sb, \@NEW_HIGHLIGHT);
|
2012-02-13 22:32:47 +00:00
|
|
|
}
|
|
|
|
else {
|
2012-02-13 22:33:10 +00:00
|
|
|
return join('', @a),
|
|
|
|
join('', @b);
|
2012-02-13 22:32:47 +00:00
|
|
|
}
|
2011-10-18 04:52:20 +00:00
|
|
|
}
|
|
|
|
|
2016-08-29 17:33:47 +00:00
|
|
|
# we split either by $COLOR or by character. This has the side effect of
|
|
|
|
# leaving in graph cruft. It works because the graph cruft does not contain "-"
|
|
|
|
# or "+"
|
2011-10-18 04:52:20 +00:00
|
|
|
sub split_line {
|
|
|
|
local $_ = shift;
|
2015-04-03 22:15:14 +00:00
|
|
|
return utf8::decode($_) ?
|
|
|
|
map { utf8::encode($_); $_ }
|
|
|
|
map { /$COLOR/ ? $_ : (split //) }
|
|
|
|
split /($COLOR+)/ :
|
|
|
|
map { /$COLOR/ ? $_ : (split //) }
|
|
|
|
split /($COLOR+)/;
|
2011-10-18 04:52:20 +00:00
|
|
|
}
|
|
|
|
|
2012-02-13 22:33:10 +00:00
|
|
|
sub highlight_line {
|
2014-11-20 15:29:18 +00:00
|
|
|
my ($line, $prefix, $suffix, $theme) = @_;
|
|
|
|
|
|
|
|
my $start = join('', @{$line}[0..($prefix-1)]);
|
|
|
|
my $mid = join('', @{$line}[$prefix..$suffix]);
|
|
|
|
my $end = join('', @{$line}[($suffix+1)..$#$line]);
|
|
|
|
|
|
|
|
# If we have a "normal" color specified, then take over the whole line.
|
|
|
|
# Otherwise, we try to just manipulate the highlighted bits.
|
|
|
|
if (defined $theme->[0]) {
|
|
|
|
s/$COLOR//g for ($start, $mid, $end);
|
|
|
|
chomp $end;
|
|
|
|
return join('',
|
|
|
|
$theme->[0], $start, $RESET,
|
|
|
|
$theme->[1], $mid, $RESET,
|
|
|
|
$theme->[0], $end, $RESET,
|
|
|
|
"\n"
|
|
|
|
);
|
|
|
|
} else {
|
|
|
|
return join('',
|
|
|
|
$start,
|
|
|
|
$theme->[1], $mid, $theme->[2],
|
|
|
|
$end
|
|
|
|
);
|
|
|
|
}
|
2011-10-18 04:52:20 +00:00
|
|
|
}
|
2012-02-13 22:32:47 +00:00
|
|
|
|
|
|
|
# Pairs are interesting to highlight only if we are going to end up
|
|
|
|
# highlighting a subset (i.e., not the whole line). Otherwise, the highlighting
|
|
|
|
# is just useless noise. We can detect this by finding either a matching prefix
|
|
|
|
# or suffix (disregarding boring bits like whitespace and colorization).
|
|
|
|
sub is_pair_interesting {
|
|
|
|
my ($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[($sb+1)..$#$b]);
|
|
|
|
|
diff-highlight: detect --graph by indent
This patch fixes a corner case where diff-highlight may
scramble some diffs when combined with --graph.
Commit 7e4ffb4c17 (diff-highlight: add support for --graph
output, 2016-08-29) taught diff-highlight to skip past the
graph characters at the start of each line with this regex:
($COLOR?\|$COLOR?\s+)*
I.e., any series of pipes separated by and followed by
arbitrary whitespace. We need to match more than just a
single space because the commit in question may be indented
to accommodate other parts of the graph drawing. E.g.:
* commit 1234abcd
| ...
| diff --git ...
has only a single space, but for the last commit before a
fork:
| | |
| * | commit 1234abcd
| |/ ...
| | diff --git
the diff lines have more spaces between the pipes and the
start of the diff.
However, when we soak up all of those spaces with the
$GRAPH regex, we may accidentally include the leading space
for a context line. That means we may consider the actual
contents of a context line as part of the diff syntax. In
other words, something like this:
normal context line
-old line
+new line
-this is a context line with a leading dash
would cause us to see that final context line as a removal
line, and we'd end up showing the hunk in the wrong order:
normal context line
-old line
-this is a context line with a leading dash
+new line
Instead, let's a be a little more clever about parsing the
graph. We'll look for the actual "*" line that marks the
start of a commit, and record the indentation we see there.
Then we can skip past that indentation when checking whether
the line is a hunk header, removal, addition, etc.
There is one tricky thing: the indentation in bytes may be
different for various lines of the graph due to coloring.
E.g., the "*" on a commit line is generally shown without
color, but on the actual diff lines, it will be replaced
with a colorized "|" character, adding several bytes. We
work around this here by counting "visible" bytes. This is
unfortunately a bit more expensive, making us about twice as
slow to handle --graph output. But since this is meant to be
used interactively anyway, it's tolerably fast (and the
non-graph case is unaffected).
One alternative would be to search for hunk header lines and
use their indentation (since they'd have the same colors as
the diff lines which follow). But that just opens up
different corner cases. If we see:
| | @@ 1,2 1,3 @@
we cannot know if this is a real diff that has been
indented due to the graph, or if it's a context line that
happens to look like a diff header. We can only be sure of
the indent on the "*" lines, since we know those don't
contain arbitrary data (technically the user could include a
bunch of extra indentation via --format, but that's rare
enough to disregard).
Reported-by: Phillip Wood <phillip.wood@dunelm.org.uk>
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-03-21 05:59:01 +00:00
|
|
|
return visible_substr($prefix_a, $graph_indent) !~ /^$COLOR*-$BORING*$/ ||
|
|
|
|
visible_substr($prefix_b, $graph_indent) !~ /^$COLOR*\+$BORING*$/ ||
|
2012-02-13 22:32:47 +00:00
|
|
|
$suffix_a !~ /^$BORING*$/ ||
|
|
|
|
$suffix_b !~ /^$BORING*$/;
|
|
|
|
}
|