diff: introduce diff.<driver>.binary

The "diff" gitattribute is somewhat overloaded right now. It
can say one of three things:

  1. this file is definitely binary, or definitely not
     (i.e., diff or !diff)
  2. this file should use an external diff engine (i.e.,
     diff=foo, diff.foo.command = custom-script)
  3. this file should use particular funcname patterns
     (i.e., diff=foo, diff.foo.(x?)funcname = some-regex)

Most of the time, there is no conflict between these uses,
since using one implies that the other is irrelevant (e.g.,
an external diff engine will decide for itself whether the
file is binary).

However, there is at least one conflicting situation: there
is no way to say "use the regular rules to determine whether
this file is binary, but if we do diff it textually, use
this funcname pattern." That is, currently setting diff=foo
indicates that the file is definitely text.

This patch introduces a "binary" config option for a diff
driver, so that one can explicitly set diff.foo.binary. We
default this value to "don't know". That is, setting a diff
attribute to "foo" and using "diff.foo.funcname" will have
no effect on the binaryness of a file. To get the current
behavior, one can set diff.foo.binary to true.

This patch also has one additional advantage: it cleans up
the interface to the userdiff code a bit. Before, calling
code had to know more about whether attributes were false,
true, or unset to determine binaryness. Now that binaryness
is a property of a driver, we can represent these situations
just by passing back a driver struct.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Shawn O. Pearce <spearce@spearce.org>

1 files changed, 16 insertions, 3 deletions

diff --git a/userdiff.c b/userdiff.c
index 80e2857abb..58478a6912 100644
--- a/userdiff.c
+++ b/userdiff.c
@@ -7,7 +7,7 @@ static int ndrivers;
 static int drivers_alloc;
 
 #define FUNCNAME(name, pattern) \
-	{ name, NULL, { pattern, REG_EXTENDED } }
+	{ name, NULL, -1, { pattern, REG_EXTENDED } }
 static struct userdiff_driver builtin_drivers[] = {
 FUNCNAME("html", "^[ \t]*(<[Hh][1-6][ \t].*>.*)$"),
 FUNCNAME("java",
@@ -32,22 +32,23 @@ FUNCNAME("python", "^[ \t]*((class|def)[ \t].*)$"),
 FUNCNAME("ruby", "^[ \t]*((class|module|def)[ \t].*)$"),
 FUNCNAME("bibtex", "(@[a-zA-Z]{1,}[ \t]*\\{{0,1}[ \t]*[^ \t\"@',\\#}{~%]*).*$"),
 FUNCNAME("tex", "^(\\\\((sub)*section|chapter|part)\\*{0,1}\\{.*)$"),
+{ "default", NULL, -1, { NULL, 0 } },
 };
 #undef FUNCNAME
 
 static struct userdiff_driver driver_true = {
 	"diff=true",
 	NULL,
+	0,
 	{ NULL, 0 }
 };
-struct userdiff_driver *USERDIFF_ATTR_TRUE = &driver_true;
 
 static struct userdiff_driver driver_false = {
 	"!diff",
 	NULL,
+	1,
 	{ NULL, 0 }
 };
-struct userdiff_driver *USERDIFF_ATTR_FALSE = &driver_false;
 
 static struct userdiff_driver *userdiff_find_by_namelen(const char *k, int len)
 {
@@ -89,6 +90,7 @@ static struct userdiff_driver *parse_driver(const char *var,
 		drv = &drivers[ndrivers++];
 		memset(drv, 0, sizeof(*drv));
 		drv->name = xmemdupz(name, namelen);
+		drv->binary = -1;
 	}
 	return drv;
 }
@@ -109,6 +111,15 @@ static int parse_string(const char **d, const char *k, const char *v)
 	return 1;
 }
 
+static int parse_tristate(int *b, const char *k, const char *v)
+{
+	if (v && !strcasecmp(v, "auto"))
+		*b = -1;
+	else
+		*b = git_config_bool(k, v);
+	return 1;
+}
+
 int userdiff_config_basic(const char *k, const char *v)
 {
 	struct userdiff_driver *drv;
@@ -117,6 +128,8 @@ int userdiff_config_basic(const char *k, const char *v)
 		return parse_funcname(&drv->funcname, k, v, 0);
 	if ((drv = parse_driver(k, v, "xfuncname")))
 		return parse_funcname(&drv->funcname, k, v, REG_EXTENDED);
+	if ((drv = parse_driver(k, v, "binary")))
+		return parse_tristate(&drv->binary, k, v);
 
 	return 0;
 }