Merge branch 'jk/diff-compact-heuristic'

Patch output from "git diff" and friends has been tweaked to be
more readable by using a blank line as a strong hint that the
contents before and after it belong to a logically separate unit.

* jk/diff-compact-heuristic:
  diff: undocument the compaction heuristic knobs for experimentation
  xdiff: implement empty line chunk heuristic
  xdiff: add recs_match helper function

3 files changed, 49 insertions, 4 deletions

diff --git a/diff.c b/diff.c
index 4dfe6609d0..d3734d3181 100644
--- a/diff.c
+++ b/diff.c
@@ -26,6 +26,7 @@
 #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;
@@ -189,6 +190,10 @@ 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;
@@ -3278,6 +3283,8 @@ 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;
 
@@ -3798,6 +3805,10 @@ int diff_opt_parse(struct diff_options *options,
 		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"))
diff --git a/xdiff/xdiff.h b/xdiff/xdiff.h
index 4fb7e79410..7423f77fc8 100644
--- a/xdiff/xdiff.h
+++ b/xdiff/xdiff.h
@@ -41,6 +41,8 @@ extern "C" {
 
 #define XDF_IGNORE_BLANK_LINES (1 << 7)
 
+#define XDF_COMPACTION_HEURISTIC (1 << 8)
+
 #define XDL_EMIT_FUNCNAMES (1 << 0)
 #define XDL_EMIT_FUNCCONTEXT (1 << 2)
 
diff --git a/xdiff/xdiffi.c b/xdiff/xdiffi.c
index 2358a2d632..b3c6848875 100644
--- a/xdiff/xdiffi.c
+++ b/xdiff/xdiffi.c
@@ -400,9 +400,23 @@ static xdchange_t *xdl_add_change(xdchange_t *xscr, long i1, long i2, long chg1,
 }
 
 
+static int is_blank_line(xrecord_t **recs, long ix, long flags)
+{
+	return xdl_blankline(recs[ix]->ptr, recs[ix]->size, flags);
+}
+
+static int recs_match(xrecord_t **recs, long ixs, long ix, long flags)
+{
+	return (recs[ixs]->ha == recs[ix]->ha &&
+		xdl_recmatch(recs[ixs]->ptr, recs[ixs]->size,
+			     recs[ix]->ptr, recs[ix]->size,
+			     flags));
+}
+
 int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) {
 	long ix, ixo, ixs, ixref, grpsiz, nrec = xdf->nrec;
 	char *rchg = xdf->rchg, *rchgo = xdfo->rchg;
+	unsigned int blank_lines;
 	xrecord_t **recs = xdf->recs;
 
 	/*
@@ -436,14 +450,14 @@ int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) {
 
 		do {
 			grpsiz = ix - ixs;
+			blank_lines = 0;
 
 			/*
 			 * If the line before the current change group, is equal to
 			 * the last line of the current change group, shift backward
 			 * the group.
 			 */
-			while (ixs > 0 && recs[ixs - 1]->ha == recs[ix - 1]->ha &&
-			       xdl_recmatch(recs[ixs - 1]->ptr, recs[ixs - 1]->size, recs[ix - 1]->ptr, recs[ix - 1]->size, flags)) {
+			while (ixs > 0 && recs_match(recs, ixs - 1, ix - 1, flags)) {
 				rchg[--ixs] = 1;
 				rchg[--ix] = 0;
 
@@ -470,8 +484,9 @@ int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) {
 			 * the line next of the current change group, shift forward
 			 * the group.
 			 */
-			while (ix < nrec && recs[ixs]->ha == recs[ix]->ha &&
-			       xdl_recmatch(recs[ixs]->ptr, recs[ixs]->size, recs[ix]->ptr, recs[ix]->size, flags)) {
+			while (ix < nrec && recs_match(recs, ixs, ix, flags)) {
+				blank_lines += is_blank_line(recs, ix, flags);
+
 				rchg[ixs++] = 0;
 				rchg[ix++] = 1;
 
@@ -498,6 +513,23 @@ int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) {
 			rchg[--ix] = 0;
 			while (rchgo[--ixo]);
 		}
+
+		/*
+		 * If a group can be moved back and forth, see if there is a
+		 * blank line in the moving space. If there is a blank line,
+		 * make sure the last blank line is the end of the group.
+		 *
+		 * As we already shifted the group forward as far as possible
+		 * in the earlier loop, we need to shift it back only if at all.
+		 */
+		if ((flags & XDF_COMPACTION_HEURISTIC) && blank_lines) {
+			while (ixs > 0 &&
+			       !is_blank_line(recs, ix - 1, flags) &&
+			       recs_match(recs, ixs - 1, ix - 1, flags)) {
+				rchg[--ixs] = 1;
+				rchg[--ix] = 0;
+			}
+		}
 	}
 
 	return 0;