diff: teach diff to read gitattribute diff-algorithm

It can be useful to specify diff algorithms per file type. For example,
one may want to use the minimal diff algorithm for .json files, another
for .c files, etc.

Teach the diff machinery to check attributes for a diff driver. Also
teach the diff driver parser a new type "algorithm" to look for in the
config, which will be used if a driver has been specified through the
attributes.

Enforce precedence of diff algorithm by favoring the command line option,
then looking at the driver attributes & config combination, then finally
the diff.algorithm config.

To enforce precedence order, use the `xdl_opts_command_line` member
during options pasing to indicate the diff algorithm was set via command
line args.

Signed-off-by: John Cai <johncai86@gmail.com>

Documentation/gitattributes.txt

@@ -736,7 +736,6 @@ String::
 	by the configuration variables in the "diff.foo" section of the
 	Git config file.
 
-
 Defining an external diff driver
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
@@ -758,6 +757,46 @@ with the above configuration, i.e. `j-c-diff`, with 7
 parameters, just like `GIT_EXTERNAL_DIFF` program is called.
 See linkgit:git[1] for details.
 
+Setting the internal diff algorithm
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+The diff algorithm can be set through the `diff.algorithm` config key, but
+sometimes it may be helpful to set the diff algorithm by path. For example, one
+might wish to set a diff algorithm automatically for all `.json` files such that
+the user would not need to pass in a separate command line `--diff-algorithm` flag each
+time.
+
+First, in `.gitattributes`, you would assign the `diff` attribute for paths.
+
+*Git attributes*
+------------------------
+*.json diff=<name>
+------------------------
+
+Then, you would define a "diff.<name>.algorithm" configuration to specify the
+diff algorithm, choosing from `meyers`, `patience`, `minimal`, and `histogram`.
+
+*Git config*
+
+----------------------------------------------------------------
+[diff "<name>"]
+  algorithm = histogram
+----------------------------------------------------------------
+
+This diff algorithm applies to git-diff(1), including the `--stat` output.
+
+NOTE: If the `command` key also exists, then Git will treat this as an external
+diff and attempt to use the value set for `command` as an external program. For
+instance, the following config, combined with the above `.gitattributes` file,
+will result in `command` favored over `algorithm`.
+
+*Git config*
+
+----------------------------------------------------------------
+[diff "<name>"]
+  command = j-c-diff
+  algorithm = histogram
+----------------------------------------------------------------
 
 Defining a custom hunk-header
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

diff.c

@@ -5166,6 +5166,8 @@ static int diff_opt_diff_algorithm_no_arg(const struct option *opt,
 
 	options->xdl_opts_command_line = 1;
 
+	options->xdl_opts_command_line = 1;
+
 	return 0;
 }
 

diff.h

@@ -333,6 +333,8 @@ struct diff_options {
 	int prefix_length;
 	const char *stat_sep;
 	int xdl_opts;
+	/* If xdl_opts has been set via the command line. */
+	int xdl_opts_command_line;
 
 	/* see Documentation/diff-options.txt */
 	char **anchors;

t/lib-diff-alternative.sh

@@ -105,10 +105,46 @@ index $file1..$file2 100644
  }
 EOF
 
+	cat >expect_diffstat <<EOF
+ file1 => file2 | 21 ++++++++++-----------
+ 1 file changed, 10 insertions(+), 11 deletions(-)
+EOF
+
 	STRATEGY=$1
 
+	test_expect_success "$STRATEGY diff from attributes" '
+		echo "file* diff=driver" >.gitattributes &&
+		git config diff.driver.algorithm "$STRATEGY" &&
+		test_must_fail git diff --no-index file1 file2 > output &&
+		cat expect &&
+		cat output &&
+		test_cmp expect output
+	'
+
+	test_expect_success "$STRATEGY diff from attributes has valid diffstat" '
+		echo "file* diff=driver" >.gitattributes &&
+		git config diff.driver.algorithm "$STRATEGY" &&
+		test_must_fail git diff --stat --no-index file1 file2 > output &&
+		test_cmp expect_diffstat output
+	'
+
 	test_expect_success "$STRATEGY diff" '
-		test_must_fail git diff --no-index "--$STRATEGY" file1 file2 > output &&
+		test_must_fail git diff --no-index "--diff-algorithm=$STRATEGY" file1 file2 > output &&
+		test_cmp expect output
+	'
+
+	test_expect_success "$STRATEGY diff command line precedence before attributes" '
+		echo "file* diff=driver" >.gitattributes &&
+		git config diff.driver.algorithm meyers &&
+		test_must_fail git diff --no-index "--diff-algorithm=$STRATEGY" file1 file2 > output &&
+		test_cmp expect output
+	'
+
+	test_expect_success "$STRATEGY diff attributes precedence before config" '
+		git config diff.algorithm default &&
+		echo "file* diff=driver" >.gitattributes &&
+		git config diff.driver.algorithm "$STRATEGY" &&
+		test_must_fail git diff --no-index file1 file2 > output &&
 		test_cmp expect output
 	'
 

userdiff.c

@@ -293,7 +293,7 @@ PATTERNS("scheme",
 	 "|([^][)(}{[ \t])+"),
 PATTERNS("tex", "^(\\\\((sub)*section|chapter|part)\\*{0,1}\\{.*)$",
 	 "\\\\[a-zA-Z@]+|\\\\.|[a-zA-Z0-9\x80-\xff]+"),
-{ "default", NULL, -1, { NULL, 0 } },
+{ "default", NULL, NULL, -1, { NULL, 0 } },
 };
 #undef PATTERNS
 #undef IPATTERN
@@ -394,6 +394,8 @@ int userdiff_config(const char *k, const char *v)
 		return parse_bool(&drv->textconv_want_cache, k, v);
 	if (!strcmp(type, "wordregex"))
 		return git_config_string(&drv->word_regex, k, v);
+	if (!strcmp(type, "algorithm"))
+		return git_config_string(&drv->algorithm, k, v);
 
 	return 0;
 }

userdiff.h

@@ -14,6 +14,7 @@ struct userdiff_funcname {
 struct userdiff_driver {
 	const char *name;
 	const char *external;
+	const char *algorithm;
 	int binary;
 	struct userdiff_funcname funcname;
 	const char *word_regex;