Merge branch 'lt/abbrev-auto'

Allow the default abbreviation length, which has historically been
7, to scale as the repository grows.  The logic suggests to use 12
hexdigits for the Linux kernel, and 9 to 10 for Git itself.

* lt/abbrev-auto:
  abbrev: auto size the default abbreviation
  abbrev: prepare for new world order
  abbrev: add FALLBACK_DEFAULT_ABBREV to prepare for auto sizing

7 files changed, 40 insertions, 7 deletions

diff --git a/builtin/fetch.c b/builtin/fetch.c
index 74c0546362..b2e113d387 100644
--- a/builtin/fetch.c
+++ b/builtin/fetch.c
@@ -17,6 +17,9 @@
 #include "argv-array.h"
 #include "utf8.h"
 
+#define TRANSPORT_SUMMARY(x) \
+	(int)(TRANSPORT_SUMMARY_WIDTH + strlen(x) - gettext_width(x)), (x)
+
 static const char * const builtin_fetch_usage[] = {
 	N_("git fetch [<options>] [<repository> [<refspec>...]]"),
 	N_("git fetch [<options>] <group>"),
diff --git a/builtin/rev-parse.c b/builtin/rev-parse.c
index 4da1f1da25..cfb0f1510c 100644
--- a/builtin/rev-parse.c
+++ b/builtin/rev-parse.c
@@ -671,8 +671,9 @@ int cmd_rev_parse(int argc, const char **argv, const char *prefix)
 				filter &= ~(DO_FLAGS|DO_NOREV);
 				verify = 1;
 				abbrev = DEFAULT_ABBREV;
-				if (arg[7] == '=')
-					abbrev = strtoul(arg + 8, NULL, 10);
+				if (!arg[7])
+					continue;
+				abbrev = strtoul(arg + 8, NULL, 10);
 				if (abbrev < MINIMUM_ABBREV)
 					abbrev = MINIMUM_ABBREV;
 				else if (40 <= abbrev)
diff --git a/cache.h b/cache.h
index f7ee414563..446d4cb632 100644
--- a/cache.h
+++ b/cache.h
@@ -1190,6 +1190,9 @@ static inline int hex2chr(const char *s)
 #define MINIMUM_ABBREV minimum_abbrev
 #define DEFAULT_ABBREV default_abbrev
 
+/* used when the code does not know or care what the default abbrev is */
+#define FALLBACK_DEFAULT_ABBREV 7
+
 struct object_context {
 	unsigned char tree[20];
 	char path[PATH_MAX];
@@ -1208,6 +1211,7 @@ struct object_context {
 #define GET_SHA1_TREEISH          020
 #define GET_SHA1_BLOB             040
 #define GET_SHA1_FOLLOW_SYMLINKS 0100
+#define GET_SHA1_AUTOMATIC	 0200
 #define GET_SHA1_ONLY_TO_DIE    04000
 
 #define GET_SHA1_DISAMBIGUATORS \
diff --git a/diff.c b/diff.c
index ae87888d1f..5a4e9b31ef 100644
--- a/diff.c
+++ b/diff.c
@@ -3468,7 +3468,7 @@ void diff_setup_done(struct diff_options *options)
 			 */
 			read_cache();
 	}
-	if (options->abbrev <= 0 || 40 < options->abbrev)
+	if (40 < options->abbrev)
 		options->abbrev = 40; /* full */
 
 	/*
diff --git a/environment.c b/environment.c
index cdc097f80c..0935ec696e 100644
--- a/environment.c
+++ b/environment.c
@@ -16,7 +16,7 @@ int trust_executable_bit = 1;
 int trust_ctime = 1;
 int check_stat = 1;
 int has_symlinks = 1;
-int minimum_abbrev = 4, default_abbrev = 7;
+int minimum_abbrev = 4, default_abbrev = -1;
 int ignore_case;
 int assume_unchanged;
 int prefer_symlink_refs;
diff --git a/sha1_name.c b/sha1_name.c
index 4092836146..84662a6804 100644
--- a/sha1_name.c
+++ b/sha1_name.c
@@ -15,6 +15,7 @@ typedef int (*disambiguate_hint_fn)(const unsigned char *, void *);
 
 struct disambiguate_state {
 	int len; /* length of prefix in hex chars */
+	unsigned int nrobjects;
 	char hex_pfx[GIT_SHA1_HEXSZ + 1];
 	unsigned char bin_pfx[GIT_SHA1_RAWSZ];
 
@@ -111,6 +112,14 @@ static void find_short_object_filename(struct disambiguate_state *ds)
 
 			if (strlen(de->d_name) != 38)
 				continue;
+
+			/*
+			 * We only look at the one subdirectory, and we assume
+			 * each subdirectory is roughly similar, so each
+			 * object we find probably has 255 other objects in
+			 * the other fan-out directories.
+			 */
+			ds->nrobjects += 256;
 			if (memcmp(de->d_name, ds->hex_pfx + 2, ds->len - 2))
 				continue;
 			memcpy(hex + 2, de->d_name, 38);
@@ -144,6 +153,7 @@ static void unique_in_pack(struct packed_git *p,
 
 	open_pack_index(p);
 	num = p->num_objects;
+	ds->nrobjects += num;
 	last = num;
 	while (first < last) {
 		uint32_t mid = (first + last) / 2;
@@ -373,6 +383,9 @@ static int show_ambiguous_object(const unsigned char *sha1, void *data)
 	return 0;
 }
 
+/* start from our historical default before the automatic abbreviation */
+static int default_automatic_abbrev = FALLBACK_DEFAULT_ABBREV;
+
 static int get_short_sha1(const char *name, int len, unsigned char *sha1,
 			  unsigned flags)
 {
@@ -419,6 +432,14 @@ static int get_short_sha1(const char *name, int len, unsigned char *sha1,
 		for_each_abbrev(ds.hex_pfx, show_ambiguous_object, &ds);
 	}
 
+	if (len < 16 && !status && (flags & GET_SHA1_AUTOMATIC)) {
+		unsigned int expect_collision = 1 << (len * 2);
+		if (ds.nrobjects > expect_collision) {
+			default_automatic_abbrev = len+1;
+			return SHORT_NAME_AMBIGUOUS;
+		}
+	}
+
 	return status;
 }
 
@@ -451,14 +472,19 @@ int for_each_abbrev(const char *prefix, each_abbrev_fn fn, void *cb_data)
 int find_unique_abbrev_r(char *hex, const unsigned char *sha1, int len)
 {
 	int status, exists;
+	int flags = GET_SHA1_QUIETLY;
 
+	if (len < 0) {
+		flags |= GET_SHA1_AUTOMATIC;
+		len = default_automatic_abbrev;
+	}
 	sha1_to_hex_r(hex, sha1);
 	if (len == 40 || !len)
 		return 40;
 	exists = has_sha1_file(sha1);
 	while (len < 40) {
 		unsigned char sha1_ret[20];
-		status = get_short_sha1(hex, len, sha1_ret, GET_SHA1_QUIETLY);
+		status = get_short_sha1(hex, len, sha1_ret, flags);
 		if (exists
 		    ? !status
 		    : status == SHORT_NAME_NOT_FOUND) {
diff --git a/transport.h b/transport.h
index 68669f14d0..5624c0218c 100644
--- a/transport.h
+++ b/transport.h
@@ -147,8 +147,7 @@ struct transport {
 #define TRANSPORT_PUSH_ATOMIC 8192
 #define TRANSPORT_PUSH_OPTIONS 16384
 
-#define TRANSPORT_SUMMARY_WIDTH (2 * DEFAULT_ABBREV + 3)
-#define TRANSPORT_SUMMARY(x) (int)(TRANSPORT_SUMMARY_WIDTH + strlen(x) - gettext_width(x)), (x)
+#define TRANSPORT_SUMMARY_WIDTH (2 * FALLBACK_DEFAULT_ABBREV + 3)
 
 /* Returns a transport suitable for the url */
 struct transport *transport_get(struct remote *, const char *);