Merge branch 'mh/diff-indent-heuristic'

Output from "git diff" can be made easier to read by selecting
which lines are common and which lines are added/deleted
intelligently when the lines before and after the changed section
are the same.  A command line option is added to help with the
experiment to find a good heuristics.

* mh/diff-indent-heuristic:
  blame: honor the diff heuristic options and config
  parse-options: add parse_opt_unknown_cb()
  diff: improve positioning of add/delete blocks in diffs
  xdl_change_compact(): introduce the concept of a change group
  recs_match(): take two xrecord_t pointers as arguments
  is_blank_line(): take a single xrecord_t as argument
  xdl_change_compact(): only use heuristic if group can't be matched
  xdl_change_compact(): fix compaction heuristic to adjust ixo

Documentation/diff-config.txt

@@ -171,10 +171,11 @@ diff.tool::
 
 include::mergetools-diff.txt[]
 
+diff.indentHeuristic::
 diff.compactionHeuristic::
-	Set this option to `true` to enable an experimental heuristic that
-	shifts the hunk boundary in an attempt to make the resulting
-	patch easier to read.
+	Set one of these options to `true` to enable one of two
+	experimental heuristics that shift diff hunk boundaries to
+	make patches easier to read.
 
 diff.algorithm::
 	Choose a diff algorithm.  The variants are as follows:

Documentation/diff-heuristic-options.txt

@@ -0,0 +1,7 @@
+--indent-heuristic::
+--no-indent-heuristic::
+--compaction-heuristic::
+--no-compaction-heuristic::
+	These are to help debugging and tuning experimental heuristics
+	(which are off by default) that shift diff hunk boundaries to
+	make patches easier to read.

Documentation/diff-options.txt

@@ -63,12 +63,7 @@ ifndef::git-format-patch[]
 	Synonym for `-p --raw`.
 endif::git-format-patch[]
 
---compaction-heuristic::
---no-compaction-heuristic::
-	These are to help debugging and tuning an experimental
-	heuristic (which is off by default) that shifts the hunk
-	boundary in an attempt to make the resulting patch easier
-	to read.
+include::diff-heuristic-options.txt[]
 
 --minimal::
 	Spend extra time to make sure the smallest possible

Documentation/git-annotate.txt

@@ -23,6 +23,7 @@ familiar command name for people coming from other SCM systems.
 OPTIONS
 -------
 include::blame-options.txt[]
+include::diff-heuristic-options.txt[]
 
 SEE ALSO
 --------

Documentation/git-blame.txt

@@ -89,6 +89,8 @@ include::blame-options.txt[]
 	abbreviated object name, use <n>+1 digits. Note that 1 column
 	is used for a caret to mark the boundary commit.
 
+include::diff-heuristic-options.txt[]
+
 
 THE PORCELAIN FORMAT
 --------------------

builtin/blame.c

@@ -2220,6 +2220,8 @@ static int git_blame_config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
+	if (git_diff_heuristic_config(var, value, cb) < 0)
+		return -1;
 	if (userdiff_config(var, value) < 0)
 		return -1;
 
@@ -2550,6 +2552,15 @@ int cmd_blame(int argc, const char **argv, const char *prefix)
 		OPT_BIT('s', NULL, &output_option, N_("Suppress author name and timestamp (Default: off)"), OUTPUT_NO_AUTHOR),
 		OPT_BIT('e', "show-email", &output_option, N_("Show author email instead of name (Default: off)"), OUTPUT_SHOW_EMAIL),
 		OPT_BIT('w', NULL, &xdl_opts, N_("Ignore whitespace differences"), XDF_IGNORE_WHITESPACE),
+
+		/*
+		 * The following two options are parsed by parse_revision_opt()
+		 * and are only included here to get included in the "-h"
+		 * output:
+		 */
+		{ OPTION_LOWLEVEL_CALLBACK, 0, "indent-heuristic", NULL, NULL, N_("Use an experimental indent-based heuristic to improve diffs"), PARSE_OPT_NOARG, parse_opt_unknown_cb },
+		{ OPTION_LOWLEVEL_CALLBACK, 0, "compaction-heuristic", NULL, NULL, N_("Use an experimental blank-line-based heuristic to improve diffs"), PARSE_OPT_NOARG, parse_opt_unknown_cb },
+
 		OPT_BIT(0, "minimal", &xdl_opts, N_("Spend extra cycles to find better match"), XDF_NEED_MINIMAL),
 		OPT_STRING('S', NULL, &revs_file, N_("file"), N_("Use revisions from <file> instead of calling git-rev-list")),
 		OPT_STRING(0, "contents", &contents_from, N_("file"), N_("Use <file>'s contents as the final image")),
@@ -2596,6 +2607,7 @@ int cmd_blame(int argc, const char **argv, const char *prefix)
 	}
 parse_done:
 	no_whole_file_rename = !DIFF_OPT_TST(&revs.diffopt, FOLLOW_RENAMES);
+	xdl_opts |= revs.diffopt.xdl_opts & (XDF_COMPACTION_HEURISTIC | XDF_INDENT_HEURISTIC);
 	DIFF_OPT_CLR(&revs.diffopt, FOLLOW_RENAMES);
 	argc = parse_options_end(&ctx);
 

diff.c

@@ -27,6 +27,7 @@
 #endif
 
 static int diff_detect_rename_default;
+static int diff_indent_heuristic; /* experimental */
 static int diff_compaction_heuristic; /* experimental */
 static int diff_rename_limit_default = 400;
 static int diff_suppress_blank_empty;
@@ -177,6 +178,21 @@ void init_diff_ui_defaults(void)
 	diff_detect_rename_default = 1;
 }
 
+int git_diff_heuristic_config(const char *var, const char *value, void *cb)
+{
+	if (!strcmp(var, "diff.indentheuristic")) {
+		diff_indent_heuristic = git_config_bool(var, value);
+		if (diff_indent_heuristic)
+			diff_compaction_heuristic = 0;
+	}
+	if (!strcmp(var, "diff.compactionheuristic")) {
+		diff_compaction_heuristic = git_config_bool(var, value);
+		if (diff_compaction_heuristic)
+			diff_indent_heuristic = 0;
+	}
+	return 0;
+}
+
 int git_diff_ui_config(const char *var, const char *value, void *cb)
 {
 	if (!strcmp(var, "diff.color") || !strcmp(var, "color.diff")) {
@@ -193,10 +209,6 @@ 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;
@@ -237,6 +249,8 @@ int git_diff_ui_config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
+	if (git_diff_heuristic_config(var, value, cb) < 0)
+		return -1;
 	if (git_color_config(var, value, cb) < 0)
 		return -1;
 
@@ -3296,7 +3310,9 @@ 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)
+	if (diff_indent_heuristic)
+		DIFF_XDL_SET(options, INDENT_HEURISTIC);
+	else if (diff_compaction_heuristic)
 		DIFF_XDL_SET(options, COMPACTION_HEURISTIC);
 
 	options->orderfile = diff_order_file_cfg;
@@ -3818,9 +3834,15 @@ 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"))
+	else if (!strcmp(arg, "--indent-heuristic")) {
+		DIFF_XDL_SET(options, INDENT_HEURISTIC);
+		DIFF_XDL_CLR(options, COMPACTION_HEURISTIC);
+	} else if (!strcmp(arg, "--no-indent-heuristic"))
+		DIFF_XDL_CLR(options, INDENT_HEURISTIC);
+	else if (!strcmp(arg, "--compaction-heuristic")) {
 		DIFF_XDL_SET(options, COMPACTION_HEURISTIC);
-	else if (!strcmp(arg, "--no-compaction-heuristic"))
+		DIFF_XDL_CLR(options, INDENT_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);

diff.h

@@ -273,6 +273,7 @@ extern int parse_long_opt(const char *opt, const char **argv,
 			 const char **optarg);
 
 extern int git_diff_basic_config(const char *var, const char *value, void *cb);
+extern int git_diff_heuristic_config(const char *var, const char *value, void *cb);
 extern void init_diff_ui_defaults(void);
 extern int git_diff_ui_config(const char *var, const char *value, void *cb);
 extern void diff_setup(struct diff_options *);

git-add--interactive.perl

@@ -45,6 +45,7 @@
 my $normal_color = $repo->get_color("", "reset");
 
 my $diff_algorithm = $repo->config('diff.algorithm');
+my $diff_indent_heuristic = $repo->config_bool('diff.indentheuristic');
 my $diff_compaction_heuristic = $repo->config_bool('diff.compactionheuristic');
 my $diff_filter = $repo->config('interactive.difffilter');
 
@@ -750,7 +751,9 @@ sub parse_diff {
 	if (defined $diff_algorithm) {
 		splice @diff_cmd, 1, 0, "--diff-algorithm=${diff_algorithm}";
 	}
-	if ($diff_compaction_heuristic) {
+	if ($diff_indent_heuristic) {
+		splice @diff_cmd, 1, 0, "--indent-heuristic";
+	} elsif ($diff_compaction_heuristic) {
 		splice @diff_cmd, 1, 0, "--compaction-heuristic";
 	}
 	if (defined $patch_mode_revision) {

parse-options-cb.c

@@ -158,6 +158,18 @@ int parse_opt_noop_cb(const struct option *opt, const char *arg, int unset)
 	return 0;
 }
 
+/**
+ * Report that the option is unknown, so that other code can handle
+ * it. This can be used as a callback together with
+ * OPTION_LOWLEVEL_CALLBACK to allow an option to be documented in the
+ * "-h" output even if it's not being handled directly by
+ * parse_options().
+ */
+int parse_opt_unknown_cb(const struct option *opt, const char *arg, int unset)
+{
+	return -2;
+}
+
 /**
  * Recreates the command-line option in the strbuf.
  */

parse-options.h

@@ -228,6 +228,7 @@ extern int parse_opt_commits(const struct option *, const char *, int);
 extern int parse_opt_tertiary(const struct option *, const char *, int);
 extern int parse_opt_string_list(const struct option *, const char *, int);
 extern int parse_opt_noop_cb(const struct option *, const char *, int);
+extern int parse_opt_unknown_cb(const struct option *, const char *, int);
 extern int parse_opt_passthru(const struct option *, const char *, int);
 extern int parse_opt_passthru_argv(const struct option *, const char *, int);