xdiff: implement empty line chunk heuristic

In order to produce the smallest possible diff and combine several diff
hunks together, we implement a heuristic from GNU Diff which moves diff
hunks forward as far as possible when we find common context above and
below a diff hunk. This sometimes produces less readable diffs when
writing C, Shell, or other programming languages, ie:

...
 /*
+ *
+ *
+ */
+
+/*
...

instead of the more readable equivalent of

...
+/*
+ *
+ *
+ */
+
 /*
...

Implement the following heuristic to (optionally) produce the desired
output.

  If there are diff chunks which can be shifted around, shift each hunk
  such that the last common empty line is below the chunk with the rest
  of the context above.

This heuristic appears to resolve the above example and several other
common issues without producing significantly weird results. However, as
with any heuristic it is not really known whether this will always be
more optimal. Thus, it can be disabled via diff.compactionHeuristic.

Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 11 insertions, 0 deletions

diff --git a/diff.c b/diff.c
index f62b7f7..05ca3ce 100644
--- a/diff.c
+++ b/diff.c
@@ -25,6 +25,7 @@
 #endif
 
 static int diff_detect_rename_default;
+static int diff_compaction_heuristic = 1;
 static int diff_rename_limit_default = 400;
 static int diff_suppress_blank_empty;
 static int diff_use_color_default = -1;
@@ -183,6 +184,10 @@ int git_diff_ui_config(const char *var, const char *value, void *cb)
 		diff_detect_rename_default = git_config_rename(var, value);
 		return 0;
 	}
+	if (!strcmp(var, "diff.compactionheuristic")) {
+		diff_compaction_heuristic = git_config_bool(var, value);
+		return 0;
+	}
 	if (!strcmp(var, "diff.autorefreshindex")) {
 		diff_auto_refresh_index = git_config_bool(var, value);
 		return 0;
@@ -3235,6 +3240,8 @@ void diff_setup(struct diff_options *options)
 	options->use_color = diff_use_color_default;
 	options->detect_rename = diff_detect_rename_default;
 	options->xdl_opts |= diff_algorithm;
+	if (diff_compaction_heuristic)
+		DIFF_XDL_SET(options, COMPACTION_HEURISTIC);
 
 	options->orderfile = diff_order_file_cfg;
 
@@ -3712,6 +3719,10 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 		DIFF_XDL_SET(options, IGNORE_WHITESPACE_AT_EOL);
 	else if (!strcmp(arg, "--ignore-blank-lines"))
 		DIFF_XDL_SET(options, IGNORE_BLANK_LINES);
+	else if (!strcmp(arg, "--compaction-heuristic"))
+		DIFF_XDL_SET(options, COMPACTION_HEURISTIC);
+	else if (!strcmp(arg, "--no-compaction-heuristic"))
+		DIFF_XDL_CLR(options, COMPACTION_HEURISTIC);
 	else if (!strcmp(arg, "--patience"))
 		options->xdl_opts = DIFF_WITH_ALG(options, PATIENCE_DIFF);
 	else if (!strcmp(arg, "--histogram"))