diff-highlight: split code into module

The diff-so-fancy project is also written in perl, and most
of its users pipe diffs through both diff-highlight and
diff-so-fancy. It would be nice if this could be done in a
single script. So let's pull most of diff-highlight's code
into its own module which can be used by diff-so-fancy.

In addition, we'll abstract a few basic items like reading
from stdio so that a script using the module can do more
processing before or after diff-highlight handles the lines.
See the README update for more details.

One small downside is that the diff-highlight script must
now be built using the Makefile. There are ways around this,
but it quickly gets into perl arcana. Let's go with the
simple solution. As a bonus, our Makefile now respects the
PERL_PATH variable if it is set.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

contrib/diff-highlight/.gitignore

@@ -0,0 +1,2 @@
+shebang.perl
+diff-highlight

contrib/diff-highlight/diff-highlight → contrib/diff-highlight/DiffHighlight.pm

@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+package DiffHighlight;
 
 use 5.008;
 use warnings FATAL => 'all';
@@ -29,13 +29,14 @@ my @removed;
 my @added;
 my $in_hunk;
 
-# Some scripts may not realize that SIGPIPE is being ignored when launching the
-# pager--for instance scripts written in Python.
-$SIG{PIPE} = 'DEFAULT';
+our $line_cb = sub { print @_ };
+our $flush_cb = sub { local $| = 1 };
+
+sub handle_line {
+	local $_ = shift;
 
-while (<>) {
 	if (!$in_hunk) {
-		print;
+		$line_cb->($_);
 		$in_hunk = /^$GRAPH*$COLOR*\@\@ /;
 	}
 	elsif (/^$GRAPH*$COLOR*-/) {
@@ -49,7 +50,7 @@ while (<>) {
 		@removed = ();
 		@added = ();
 
-		print;
+		$line_cb->($_);
 		$in_hunk = /^$GRAPH*$COLOR*[\@ ]/;
 	}
 
@@ -62,15 +63,22 @@ while (<>) {
 	# place to flush. Flushing on a blank line is a heuristic that
 	# happens to match git-log output.
 	if (!length) {
-		local $| = 1;
+		$flush_cb->();
 	}
 }
 
-# Flush any queued hunk (this can happen when there is no trailing context in
-# the final diff of the input).
-show_hunk(\@removed, \@added);
+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);
+}
 
-exit 0;
+sub highlight_stdin {
+	while (<STDIN>) {
+		handle_line($_);
+	}
+	flush();
+}
 
 # Ideally we would feed the default as a human-readable color to
 # git-config as the fallback value. But diff-highlight does
@@ -88,7 +96,7 @@ sub show_hunk {
 
 	# If one side is empty, then there is nothing to compare or highlight.
 	if (!@$a || !@$b) {
-		print @$a, @$b;
+		$line_cb->(@$a, @$b);
 		return;
 	}
 
@@ -97,17 +105,17 @@ sub show_hunk {
 	# stupid, and only handle multi-line hunks that remove and add the same
 	# number of lines.
 	if (@$a != @$b) {
-		print @$a, @$b;
+		$line_cb->(@$a, @$b);
 		return;
 	}
 
 	my @queue;
 	for (my $i = 0; $i < @$a; $i++) {
 		my ($rm, $add) = highlight_pair($a->[$i], $b->[$i]);
-		print $rm;
+		$line_cb->($rm);
 		push @queue, $add;
 	}
-	print @queue;
+	$line_cb->(@queue);
 }
 
 sub highlight_pair {

contrib/diff-highlight/Makefile

@@ -1,5 +1,20 @@
-# nothing to build
-all:
+all: diff-highlight
 
-test:
+PERL_PATH = /usr/bin/perl
+-include ../../config.mak
+
+PERL_PATH_SQ = $(subst ','\'',$(PERL_PATH))
+
+diff-highlight: shebang.perl DiffHighlight.pm diff-highlight.perl
+	cat $^ >$@+
+	chmod +x $@+
+	mv $@+ $@
+
+shebang.perl: FORCE
+	@echo '#!$(PERL_PATH_SQ)' >$@+
+	@cmp $@+ $@ >/dev/null 2>/dev/null || mv $@+ $@
+
+test: all
 	$(MAKE) -C t
+
+.PHONY: FORCE

contrib/diff-highlight/README

@@ -99,6 +99,36 @@ newHighlight = "black #aaffaa"
 ---------------------------------------------
 
 
+Using diff-highlight as a module
+--------------------------------
+
+If you want to pre- or post- process the highlighted lines as part of
+another perl script, you can use the DiffHighlight module. You can
+either "require" it or just cat the module together with your script (to
+avoid run-time dependencies).
+
+Your script may set up one or more of the following variables:
+
+  - $DiffHighlight::line_cb - this should point to a function which is
+    called whenever DiffHighlight has lines (which may contain
+    highlights) to output. The default function prints each line to
+    stdout. Note that the function may be called with multiple lines.
+
+  - $DiffHighlight::flush_cb - this should point to a function which
+    flushes the output (because DiffHighlight believes it has completed
+    processing a logical chunk of input). The default function flushes
+    stdout.
+
+The script may then feed lines, one at a time, to DiffHighlight::handle_line().
+When lines are done processing, they will be fed to $line_cb. Note that
+DiffHighlight may queue up many input lines (to analyze a whole hunk)
+before calling $line_cb. After providing all lines, call
+DiffHighlight::flush() to flush any unprocessed lines.
+
+If you just want to process stdin, DiffHighlight::highlight_stdin()
+is a convenience helper which will loop and flush for you.
+
+
 Bugs
 ----
 

contrib/diff-highlight/diff-highlight.perl

@@ -0,0 +1,8 @@
+package main;
+
+# Some scripts may not realize that SIGPIPE is being ignored when launching the
+# pager--for instance scripts written in Python.
+$SIG{PIPE} = 'DEFAULT';
+
+DiffHighlight::highlight_stdin();
+exit 0;