Merge branch 'master' into js/merge-base

This is to pull in the object-hash clean-up from the master branch.

13 files changed, 163 insertions, 95 deletions

diff --git a/Documentation/git-commit.txt b/Documentation/git-commit.txt
index 0fe66f2d0c..517a86b238 100644
--- a/Documentation/git-commit.txt
+++ b/Documentation/git-commit.txt
@@ -15,9 +15,9 @@ SYNOPSIS
 DESCRIPTION
 -----------
 Updates the index file for given paths, or all modified files if
-'-a' is specified, and makes a commit object.  The command
-VISUAL and EDITOR environment variables to edit the commit log
-message.
+'-a' is specified, and makes a commit object.  The command specified
+by either the VISUAL or EDITOR environment variables are used to edit
+the commit log message.
 
 Several environment variable are used during commits.  They are
 documented in gitlink:git-commit-tree[1].
diff --git a/Makefile b/Makefile
index cde619c498..76abcc473b 100644
--- a/Makefile
+++ b/Makefile
@@ -587,11 +587,11 @@ git-ssh-push$X: rsh.o
 git-imap-send$X: imap-send.o $(LIB_FILE)
 
 http.o http-fetch.o http-push.o: http.h
-git-http-fetch$X: fetch.o http.o http-fetch.o $(LIB_FILE)
+git-http-fetch$X: fetch.o http.o http-fetch.o $(GITLIBS)
 	$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \
 		$(LIBS) $(CURL_LIBCURL) $(EXPAT_LIBEXPAT)
 
-git-http-push$X: revision.o http.o http-push.o $(LIB_FILE)
+git-http-push$X: revision.o http.o http-push.o $(GITLIBS)
 	$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \
 		$(LIBS) $(CURL_LIBCURL) $(EXPAT_LIBEXPAT)
 
diff --git a/connect.c b/connect.c
index cb4656d79d..9a87bd999a 100644
--- a/connect.c
+++ b/connect.c
@@ -328,7 +328,7 @@ static enum protocol get_protocol(const char *name)
  */
 static int git_tcp_connect_sock(char *host)
 {
-	int sockfd = -1;
+	int sockfd = -1, saved_errno = 0;
 	char *colon, *end;
 	const char *port = STR(DEFAULT_GIT_PORT);
 	struct addrinfo hints, *ai0, *ai;
@@ -362,9 +362,12 @@ static int git_tcp_connect_sock(char *host)
 	for (ai0 = ai; ai; ai = ai->ai_next) {
 		sockfd = socket(ai->ai_family,
 				ai->ai_socktype, ai->ai_protocol);
-		if (sockfd < 0)
+		if (sockfd < 0) {
+			saved_errno = errno;
 			continue;
+		}
 		if (connect(sockfd, ai->ai_addr, ai->ai_addrlen) < 0) {
+			saved_errno = errno;
 			close(sockfd);
 			sockfd = -1;
 			continue;
@@ -375,7 +378,7 @@ static int git_tcp_connect_sock(char *host)
 	freeaddrinfo(ai0);
 
 	if (sockfd < 0)
-		die("unable to connect a socket (%s)", strerror(errno));
+		die("unable to connect a socket (%s)", strerror(saved_errno));
 
 	return sockfd;
 }
@@ -387,7 +390,7 @@ static int git_tcp_connect_sock(char *host)
  */
 static int git_tcp_connect_sock(char *host)
 {
-	int sockfd = -1;
+	int sockfd = -1, saved_errno = 0;
 	char *colon, *end;
 	char *port = STR(DEFAULT_GIT_PORT), *ep;
 	struct hostent *he;
@@ -426,8 +429,10 @@ static int git_tcp_connect_sock(char *host)
 
 	for (ap = he->h_addr_list; *ap; ap++) {
 		sockfd = socket(he->h_addrtype, SOCK_STREAM, 0);
-		if (sockfd < 0)
+		if (sockfd < 0) {
+			saved_errno = errno;
 			continue;
+		}
 
 		memset(&sa, 0, sizeof sa);
 		sa.sin_family = he->h_addrtype;
@@ -435,6 +440,7 @@ static int git_tcp_connect_sock(char *host)
 		memcpy(&sa.sin_addr, *ap, he->h_length);
 
 		if (connect(sockfd, (struct sockaddr *)&sa, sizeof sa) < 0) {
+			saved_errno = errno;
 			close(sockfd);
 			sockfd = -1;
 			continue;
@@ -443,7 +449,7 @@ static int git_tcp_connect_sock(char *host)
 	}
 
 	if (sockfd < 0)
-		die("unable to connect a socket (%s)", strerror(errno));
+		die("unable to connect a socket (%s)", strerror(saved_errno));
 
 	return sockfd;
 }
diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl
index b3d3f479da..1e19aa19b2 100755
--- a/contrib/git-svn/git-svn.perl
+++ b/contrib/git-svn/git-svn.perl
@@ -264,9 +264,19 @@ when you have upgraded your tools and habits to use refs/remotes/$GIT_SVN
 }
 
 sub init {
-	$SVN_URL = shift or die "SVN repository location required " .
+	my $url = shift or die "SVN repository location required " .
 				"as a command-line argument\n";
-	$SVN_URL =~ s!/+$!!; # strip trailing slash
+	$url =~ s!/+$!!; # strip trailing slash
+
+	if (my $repo_path = shift) {
+		unless (-d $repo_path) {
+			mkpath([$repo_path]);
+		}
+		$GIT_DIR = $ENV{GIT_DIR} = $repo_path . "/.git";
+		init_vars();
+	}
+
+	$SVN_URL = $url;
 	unless (-d $GIT_DIR) {
 		my @init_db = ('git-init-db');
 		push @init_db, "--template=$_template" if defined $_template;
diff --git a/fsck-objects.c b/fsck-objects.c
index 769bb2a6a7..ef54a8a411 100644
--- a/fsck-objects.c
+++ b/fsck-objects.c
@@ -60,12 +60,13 @@ static int objwarning(struct object *obj, const char *err, ...)
 
 static void check_connectivity(void)
 {
-	int i;
+	int i, max;
 
 	/* Look up all the requirements, warn about missing objects.. */
-	for (i = 0; i < obj_allocs; i++) {
+	max = get_max_object_index();
+	for (i = 0; i < max; i++) {
 		const struct object_refs *refs;
-		struct object *obj = objs[i];
+		struct object *obj = get_indexed_object(i);
 
 		if (!obj)
 			continue;
diff --git a/git-commit.sh b/git-commit.sh
index 7e50cf399b..22c4ce86c3 100755
--- a/git-commit.sh
+++ b/git-commit.sh
@@ -29,7 +29,7 @@ THIS_INDEX="$GIT_DIR/index"
 NEXT_INDEX="$GIT_DIR/next-index$$"
 rm -f "$NEXT_INDEX"
 save_index () {
-	cp "$THIS_INDEX" "$NEXT_INDEX"
+	cp -p "$THIS_INDEX" "$NEXT_INDEX"
 }
 
 report () {
diff --git a/git-svnimport.perl b/git-svnimport.perl
index 38ac732ca9..26dc454795 100755
--- a/git-svnimport.perl
+++ b/git-svnimport.perl
@@ -534,7 +534,7 @@ sub commit {
 	my($author_name,$author_email,$dest);
 	my(@old,@new,@parents);
 
-	if (not defined $author) {
+	if (not defined $author or $author eq "") {
 		$author_name = $author_email = "unknown";
 	} elsif (defined $users_file) {
 		die "User $author is not listed in $users_file\n"
diff --git a/name-rev.c b/name-rev.c
index 3a5ac35d16..6a23f2d8a2 100644
--- a/name-rev.c
+++ b/name-rev.c
@@ -234,12 +234,15 @@ int main(int argc, char **argv)
 				fwrite(p_start, p - p_start, 1, stdout);
 		}
 	} else if (all) {
-		int i;
+		int i, max;
 
-		for (i = 0; i < obj_allocs; i++)
-			if (objs[i])
-				printf("%s %s\n", sha1_to_hex(objs[i]->sha1),
-						get_rev_name(objs[i]));
+		max = get_max_object_index();
+		for (i = 0; i < max; i++) {
+			struct object * obj = get_indexed_object(i);
+			if (!obj)
+				continue;
+			printf("%s %s\n", sha1_to_hex(obj->sha1), get_rev_name(obj));
+		}
 	} else {
 		int i;
 		for (i = 0; i < revs.nr; i++)
diff --git a/object.c b/object.c
index 9caba4fac8..1c36759715 100644
--- a/object.c
+++ b/object.c
@@ -5,79 +5,97 @@
 #include "commit.h"
 #include "tag.h"
 
-struct object **objs;
-static int nr_objs;
-int obj_allocs;
+static struct object **obj_hash;
+static int nr_objs, obj_hash_size;
+
+unsigned int get_max_object_index(void)
+{
+	return obj_hash_size;
+}
+
+struct object *get_indexed_object(unsigned int idx)
+{
+	return obj_hash[idx];
+}
 
 const char *type_names[] = {
 	"none", "blob", "tree", "commit", "bad"
 };
 
+static unsigned int hash_obj(struct object *obj, unsigned int n)
+{
+	unsigned int hash = *(unsigned int *)obj->sha1;
+	return hash % n;
+}
+
+static void insert_obj_hash(struct object *obj, struct object **hash, unsigned int size)
+{
+	int j = hash_obj(obj, size);
+
+	while (hash[j]) {
+		j++;
+		if (j >= size)
+			j = 0;
+	}
+	hash[j] = obj;
+}
+
 static int hashtable_index(const unsigned char *sha1)
 {
 	unsigned int i;
 	memcpy(&i, sha1, sizeof(unsigned int));
-	return (int)(i % obj_allocs);
+	return (int)(i % obj_hash_size);
 }
 
-static int find_object(const unsigned char *sha1)
+struct object *lookup_object(const unsigned char *sha1)
 {
 	int i;
+	struct object *obj;
 
-	if (!objs)
-		return -1;
+	if (!obj_hash)
+		return NULL;
 
 	i = hashtable_index(sha1);
-	while (objs[i]) {
-		if (memcmp(sha1, objs[i]->sha1, 20) == 0)
-			return i;
+	while ((obj = obj_hash[i]) != NULL) {
+		if (!memcmp(sha1, obj->sha1, 20))
+			break;
 		i++;
-		if (i == obj_allocs)
+		if (i == obj_hash_size)
 			i = 0;
 	}
-	return -1 - i;
+	return obj;
 }
 
-struct object *lookup_object(const unsigned char *sha1)
+static void grow_object_hash(void)
 {
-	int pos = find_object(sha1);
-	if (pos >= 0)
-		return objs[pos];
-	return NULL;
+	int i;
+	int new_hash_size = obj_hash_size < 32 ? 32 : 2 * obj_hash_size;
+	struct object **new_hash;
+
+	new_hash = calloc(new_hash_size, sizeof(struct object *));
+	for (i = 0; i < obj_hash_size; i++) {
+		struct object *obj = obj_hash[i];
+		if (!obj)
+			continue;
+		insert_obj_hash(obj, new_hash, new_hash_size);
+	}
+	free(obj_hash);
+	obj_hash = new_hash;
+	obj_hash_size = new_hash_size;
 }
 
 void created_object(const unsigned char *sha1, struct object *obj)
 {
-	int pos;
-
 	obj->parsed = 0;
-	memcpy(obj->sha1, sha1, 20);
-	obj->type = TYPE_NONE;
 	obj->used = 0;
+	obj->type = TYPE_NONE;
+	obj->flags = 0;
+	memcpy(obj->sha1, sha1, 20);
 
-	if (obj_allocs - 1 <= nr_objs * 2) {
-		int i, count = obj_allocs;
-		obj_allocs = (obj_allocs < 32 ? 32 : 2 * obj_allocs);
-		objs = xrealloc(objs, obj_allocs * sizeof(struct object *));
-		memset(objs + count, 0, (obj_allocs - count)
-				* sizeof(struct object *));
-		for (i = 0; i < obj_allocs; i++)
-			if (objs[i]) {
-				int j = find_object(objs[i]->sha1);
-				if (j != i) {
-					j = -1 - j;
-					objs[j] = objs[i];
-					objs[i] = NULL;
-				}
-			}
-	}
-
-	pos = find_object(sha1);
-	if (pos >= 0)
-		die("Inserting %s twice\n", sha1_to_hex(sha1));
-	pos = -pos-1;
+	if (obj_hash_size - 1 <= nr_objs * 2)
+		grow_object_hash();
 
-	objs[pos] = obj;
+	insert_obj_hash(obj, obj_hash, obj_hash_size);
 	nr_objs++;
 }
 
@@ -222,7 +240,7 @@ void clear_object_marks(unsigned mark)
 {
 	int i;
 
-	for (i = 0; i < obj_allocs; i++)
-		if (objs[i])
-			objs[i]->flags &= ~mark;
+	for (i = 0; i < obj_hash_size; i++)
+		if (obj_hash[i])
+			obj_hash[i]->flags &= ~mark;
 }
diff --git a/object.h b/object.h
index 7ac10111c6..d8a76ea935 100644
--- a/object.h
+++ b/object.h
@@ -40,10 +40,11 @@ struct object {
 };
 
 extern int track_object_refs;
-extern int obj_allocs;
-extern struct object **objs;
 extern const char *type_names[];
 
+extern unsigned int get_max_object_index(void);
+extern struct object *get_indexed_object(unsigned int);
+
 static inline const char *typename(unsigned int type)
 {
 	return type_names[type > TYPE_TAG ? TYPE_BAD : type];
diff --git a/pack-objects.c b/pack-objects.c
index bed2497b79..b486ea528a 100644
--- a/pack-objects.c
+++ b/pack-objects.c
@@ -970,11 +970,12 @@ struct unpacked {
  * one.
  */
 static int try_delta(struct unpacked *trg, struct unpacked *src,
-		     struct delta_index *src_index, unsigned max_depth)
+		     unsigned max_depth)
 {
 	struct object_entry *trg_entry = trg->entry;
 	struct object_entry *src_entry = src->entry;
-	unsigned long size, src_size, delta_size, sizediff, max_size;
+	unsigned long trg_size, src_size, delta_size, sizediff, max_size, sz;
+	char type[10];
 	void *delta_buf;
 
 	/* Don't bother doing diffs between different types */
@@ -988,6 +989,14 @@ static int try_delta(struct unpacked *trg, struct unpacked *src,
 		return -1;
 
 	/*
+	 * We do not bother to try a delta that we discarded
+	 * on an earlier try, but only when reusing delta data.
+	 */
+	if (!no_reuse_delta && trg_entry->in_pack &&
+	    trg_entry->in_pack == src_entry->in_pack)
+		return 0;
+
+	/*
 	 * If the current object is at pack edge, take the depth the
 	 * objects that depend on the current object into account --
 	 * otherwise they would become too deep.
@@ -1001,19 +1010,38 @@ static int try_delta(struct unpacked *trg, struct unpacked *src,
 		return 0;
 
 	/* Now some size filtering heuristics. */
-	size = trg_entry->size;
-	max_size = size/2 - 20;
+	trg_size = trg_entry->size;
+	max_size = trg_size/2 - 20;
 	max_size = max_size * (max_depth - src_entry->depth) / max_depth;
 	if (max_size == 0)
 		return 0;
 	if (trg_entry->delta && trg_entry->delta_size <= max_size)
 		max_size = trg_entry->delta_size-1;
 	src_size = src_entry->size;
-	sizediff = src_size < size ? size - src_size : 0;
+	sizediff = src_size < trg_size ? trg_size - src_size : 0;
 	if (sizediff >= max_size)
 		return 0;
 
-	delta_buf = create_delta(src_index, trg->data, size, &delta_size, max_size);
+	/* Load data if not already done */
+	if (!trg->data) {
+		trg->data = read_sha1_file(trg_entry->sha1, type, &sz);
+		if (sz != trg_size)
+			die("object %s inconsistent object length (%lu vs %lu)",
+			    sha1_to_hex(trg_entry->sha1), sz, trg_size);
+	}
+	if (!src->data) {
+		src->data = read_sha1_file(src_entry->sha1, type, &sz);
+		if (sz != src_size)
+			die("object %s inconsistent object length (%lu vs %lu)",
+			    sha1_to_hex(src_entry->sha1), sz, src_size);
+	}
+	if (!src->index) {
+		src->index = create_delta_index(src->data, src_size);
+		if (!src->index)
+			die("out of memory");
+	}
+
+	delta_buf = create_delta(src->index, trg->data, trg_size, &delta_size, max_size);
 	if (!delta_buf)
 		return 0;
 
@@ -1046,8 +1074,6 @@ static void find_deltas(struct object_entry **list, int window, int depth)
 	while (--i >= 0) {
 		struct object_entry *entry = list[i];
 		struct unpacked *n = array + idx;
-		unsigned long size;
-		char type[10];
 		int j;
 
 		if (!entry->preferred_base)
@@ -1074,11 +1100,8 @@ static void find_deltas(struct object_entry **list, int window, int depth)
 		free_delta_index(n->index);
 		n->index = NULL;
 		free(n->data);
+		n->data = NULL;
 		n->entry = entry;
-		n->data = read_sha1_file(entry->sha1, type, &size);
-		if (size != entry->size)
-			die("object %s inconsistent object length (%lu vs %lu)",
-			    sha1_to_hex(entry->sha1), size, entry->size);
 
 		j = window;
 		while (--j > 0) {
@@ -1089,7 +1112,7 @@ static void find_deltas(struct object_entry **list, int window, int depth)
 			m = array + other_idx;
 			if (!m->entry)
 				break;
-			if (try_delta(n, m, m->index, depth) < 0)
+			if (try_delta(n, m, depth) < 0)
 				break;
 		}
 		/* if we made n a delta, and if n is already at max
@@ -1099,10 +1122,6 @@ static void find_deltas(struct object_entry **list, int window, int depth)
 		if (entry->delta && depth <= entry->depth)
 			continue;
 
-		n->index = create_delta_index(n->data, size);
-		if (!n->index)
-			die("out of memory");
-
 		idx++;
 		if (idx >= window)
 			idx = 0;
diff --git a/revision.c b/revision.c
index 27fc1e3075..56bc4ff0e8 100644
--- a/revision.c
+++ b/revision.c
@@ -280,7 +280,7 @@ int rev_same_tree_as_empty(struct rev_info *revs, struct tree *t1)
 static void try_to_simplify_commit(struct rev_info *revs, struct commit *commit)
 {
 	struct commit_list **pp, *parent;
-	int tree_changed = 0;
+	int tree_changed = 0, tree_same = 0;
 
 	if (!commit->tree)
 		return;
@@ -298,6 +298,7 @@ static void try_to_simplify_commit(struct rev_info *revs, struct commit *commit)
 		parse_commit(p);
 		switch (rev_compare_tree(revs, p->tree, commit->tree)) {
 		case REV_TREE_SAME:
+			tree_same = 1;
 			if (!revs->simplify_history || (p->object.flags & UNINTERESTING)) {
 				/* Even if a merge with an uninteresting
 				 * side branch brought the entire change
@@ -334,7 +335,7 @@ static void try_to_simplify_commit(struct rev_info *revs, struct commit *commit)
 		}
 		die("bad tree compare for commit %s", sha1_to_hex(commit->object.sha1));
 	}
-	if (tree_changed)
+	if (tree_changed && !tree_same)
 		commit->object.flags |= TREECHANGE;
 }
 
@@ -926,6 +927,8 @@ static int rewrite_one(struct rev_info *revs, struct commit **pp)
 		struct commit *p = *pp;
 		if (!revs->limited)
 			add_parents_to_list(revs, p, &revs->commits);
+		if (p->parents && p->parents->next)
+			return 0;
 		if (p->object.flags & (TREECHANGE | UNINTERESTING))
 			return 0;
 		if (!p->parents)
@@ -1018,8 +1021,15 @@ struct commit *get_revision(struct rev_info *revs)
 		    commit->parents && commit->parents->next)
 			continue;
 		if (revs->prune_fn && revs->dense) {
-			if (!(commit->object.flags & TREECHANGE))
-				continue;
+			/* Commit without changes? */
+			if (!(commit->object.flags & TREECHANGE)) {
+				/* drop merges unless we want parenthood */
+				if (!revs->parents)
+					continue;
+				/* non-merge - always ignore it */
+				if (!commit->parents || !commit->parents->next)
+					continue;
+			}
 			if (revs->parents)
 				rewrite_parents(revs, commit);
 		}
diff --git a/upload-pack.c b/upload-pack.c
index 2b70c3dcb4..b18eb9ba0d 100644
--- a/upload-pack.c
+++ b/upload-pack.c
@@ -1,3 +1,6 @@
+#include <signal.h>
+#include <sys/wait.h>
+#include <sys/poll.h>
 #include "cache.h"
 #include "refs.h"
 #include "pkt-line.h"
@@ -5,9 +8,6 @@
 #include "object.h"
 #include "commit.h"
 #include "exec_cmd.h"
-#include <signal.h>
-#include <sys/poll.h>
-#include <sys/wait.h>
 
 static const char upload_pack_usage[] = "git-upload-pack [--strict] [--timeout=nn] <dir>";