[PATCH 0/3] Teach git-blame about renames

@@ -569,11 +569,26 @@ int count_parents(struct commit * commit
         return count;
 }
 
+void default_setter(struct commit* c, void* data)
+{
+	c->object.util = data;
+}
+
+void* default_getter(struct commit* c)
+{
+	return c->object.util;
+}
+
 /*
  * Performs an in-place topological sort on the list supplied.
  */
 void sort_in_topological_order(struct commit_list ** list, int lifo)
 {
+	sort_in_topological_order_fun(list, lifo, default_setter, default_getter);
+}
+
+void sort_in_topological_order_fun(struct commit_list ** list, int lifo, set_fn_t setter, get_fn_t getter)
+{
 	struct commit_list * next = *list;
 	struct commit_list * work = NULL, **insert;
 	struct commit_list ** pptr = list;

@@ -596,7 +611,7 @@ void sort_in_topological_order(struct co
 	next=*list;
 	while (next) {
 		next_nodes->list_item = next;
-		next->item->object.util = next_nodes;
+		setter(next->item, next_nodes);
 		next_nodes++;
 		next = next->next;
 	}

@@ -606,7 +621,7 @@ void sort_in_topological_order(struct co
 		struct commit_list * parents = next->item->parents;
 		while (parents) {
 			struct commit * parent=parents->item;
-			struct sort_node * pn = (struct sort_node *)parent->object.util;
+			struct sort_node * pn = (struct sort_node *) getter(parent);
 			
 			if (pn)
 				pn->indegree++;

@@ -624,7 +639,7 @@ void sort_in_topological_order(struct co
 	next=*list;
 	insert = &work;
 	while (next) {
-		struct sort_node * node = (struct sort_node *)next->item->object.util;
+		struct sort_node * node = (struct sort_node *) getter(next->item);
 
 		if (node->indegree == 0) {
 			insert = &commit_list_insert(next->item, insert)->next;

@@ -637,12 +652,12 @@ void sort_in_topological_order(struct co
 		sort_by_date(&work);
 	while (work) {
 		struct commit * work_item = pop_commit(&work);
-		struct sort_node * work_node = (struct sort_node *)work_item->object.util;
+		struct sort_node * work_node = (struct sort_node *) getter(work_item);
 		struct commit_list * parents = work_item->parents;
 
 		while (parents) {
 			struct commit * parent=parents->item;
-			struct sort_node * pn = (struct sort_node *)parent->object.util;
+			struct sort_node * pn = (struct sort_node *) getter(parent);
 			
 			if (pn) {
 				/* 

@@ -667,7 +682,7 @@ void sort_in_topological_order(struct co
 		*pptr = work_node->list_item;
 		pptr = &(*pptr)->next;
 		*pptr = NULL;
-		work_item->object.util = NULL;
+		setter(work_item, NULL);
 	}
 	free(nodes);
 }

@@ -76,4 +76,13 @@ int count_parents(struct commit * commit
  *   sorted in the dates order.
  */
 void sort_in_topological_order(struct commit_list ** list, int lifo);
+
+typedef void (*set_fn_t)(struct commit*, void* data);
+typedef void* (*get_fn_t)(struct commit*);
+
+void default_setter(struct commit* c, void* data);
+void* default_getter(struct commit* c);
+
+void sort_in_topological_order(struct commit_list ** list, int lifo);
+void sort_in_topological_order_fun(struct commit_list ** list, int lifo, set_fn_t, get_fn_t);
 #endif /* COMMIT_H */

@@ -190,7 +190,7 @@ static int count_distance(struct commit_
 
 		if (commit->object.flags & (UNINTERESTING | COUNTED))
 			break;
-		if (!revs.paths || (commit->object.flags & TREECHANGE))
+		if (!revs.prune_data || (commit->object.flags & TREECHANGE))
 			nr++;
 		commit->object.flags |= COUNTED;
 		p = commit->parents;

@@ -224,7 +224,7 @@ static struct commit_list *find_bisectio
 	nr = 0;
 	p = list;
 	while (p) {
-		if (!revs.paths || (p->item->object.flags & TREECHANGE))
+		if (!revs.prune_data || (p->item->object.flags & TREECHANGE))
 			nr++;
 		p = p->next;
 	}

@@ -234,7 +234,7 @@ static struct commit_list *find_bisectio
 	for (p = list; p; p = p->next) {
 		int distance;
 
-		if (revs.paths && !(p->item->object.flags & TREECHANGE))
+		if (revs.prune_data && !(p->item->object.flags & TREECHANGE))
 			continue;
 
 		distance = count_distance(p);

@@ -197,9 +197,6 @@ static int everybody_uninteresting(struc
 	return 1;
 }
 
-#define TREE_SAME	0
-#define TREE_NEW	1
-#define TREE_DIFFERENT	2
 static int tree_difference = TREE_SAME;
 
 static void file_add_remove(struct diff_options *options,

@@ -241,7 +238,7 @@ static struct diff_options diff_opt = {
 	.change = file_change,
 };
 
-static int compare_tree(struct tree *t1, struct tree *t2)
+int compare_tree(struct tree *t1, struct tree *t2)
 {
 	if (!t1)
 		return TREE_NEW;

@@ -253,7 +250,7 @@ static int compare_tree(struct tree *t1,
 	return tree_difference;
 }
 
-static int same_tree_as_empty(struct tree *t1)
+int same_tree_as_empty(struct tree *t1)
 {
 	int retval;
 	void *tree;

@@ -321,6 +318,7 @@ static void try_to_simplify_commit(struc
 	commit->object.flags |= TREECHANGE;
 }
 
+
 static void add_parents_to_list(struct rev_info *revs, struct commit *commit, struct commit_list **list)
 {
 	struct commit_list *parent = commit->parents;

@@ -358,8 +356,11 @@ static void add_parents_to_list(struct r
 	 * simplify the commit history and find the parent
 	 * that has no differences in the path set if one exists.
 	 */
-	if (revs->paths)
+	/* if (revs->paths)
 		try_to_simplify_commit(revs, commit);
+	*/
+	if (revs->prune_fn)
+		revs->prune_fn(revs, commit);
 
 	parent = commit->parents;
 	while (parent) {

@@ -381,9 +382,6 @@ static void limit_list(struct rev_info *
 	struct commit_list *newlist = NULL;
 	struct commit_list **p = &newlist;
 
-	if (revs->paths)
-		diff_tree_setup_paths(revs->paths);
-
 	while (list) {
 		struct commit_list *entry = list;
 		struct commit *commit = list->item;

@@ -435,6 +433,24 @@ static void handle_all(struct rev_info *
 	for_each_ref(handle_one_ref);
 }
 
+
+void init_revisions(struct rev_info *revs)
+{
+	memset(revs, 0, sizeof(*revs));
+	revs->lifo = 1;
+	revs->dense = 1;
+	revs->prefix = setup_git_directory();
+	revs->max_age = -1;
+	revs->min_age = -1;
+	revs->max_count = -1;
+
+	revs->prune_fn = NULL;
+	revs->prune_data = NULL;
+
+	revs->topo_setter = default_setter;
+	revs->topo_getter = default_getter;
+}
+
 /*
  * Parse revision information, filling in the "rev_info" structure,
  * and removing the used arguments from the argument list.

@@ -448,14 +464,8 @@ int setup_revisions(int argc, const char
 	const char **unrecognized = argv + 1;
 	int left = 1;
 
-	memset(revs, 0, sizeof(*revs));
-	revs->lifo = 1;
-	revs->dense = 1;
-	revs->prefix = setup_git_directory();
-	revs->max_age = -1;
-	revs->min_age = -1;
-	revs->max_count = -1;
-
+	init_revisions(revs);
+	
 	/* First, search for "--" */
 	seen_dashdash = 0;
 	for (i = 1; i < argc; i++) {

@@ -464,7 +474,7 @@ int setup_revisions(int argc, const char
 			continue;
 		argv[i] = NULL;
 		argc = i;
-		revs->paths = get_pathspec(revs->prefix, argv + i + 1);
+		revs->prune_data = get_pathspec(revs->prefix, argv + i + 1);
 		seen_dashdash = 1;
 		break;
 	}

@@ -628,7 +638,7 @@ int setup_revisions(int argc, const char
 				if (lstat(argv[j], &st) < 0)
 					die("'%s': %s", arg, strerror(errno));
 			}
-			revs->paths = get_pathspec(revs->prefix, argv + i);
+			revs->prune_data = get_pathspec(revs->prefix, argv + i);
 			break;
 		}
 		commit = get_commit_reference(revs, arg, sha1, flags ^ local_flags);

@@ -642,8 +652,13 @@ int setup_revisions(int argc, const char
 		commit = get_commit_reference(revs, def, sha1, 0);
 		add_one_commit(commit, revs);
 	}
-	if (revs->paths)
+
+	if (revs->prune_data) {
+		diff_tree_setup_paths(revs->prune_data);
+		revs->prune_fn = try_to_simplify_commit;
 		revs->limited = 1;
+	}
+
 	return left;
 }
 

@@ -653,7 +668,7 @@ void prepare_revision_walk(struct rev_in
 	if (revs->limited)
 		limit_list(revs);
 	if (revs->topo_order)
-		sort_in_topological_order(&revs->commits, revs->lifo);
+		sort_in_topological_order_fun(&revs->commits, revs->lifo, revs->topo_setter, revs->topo_getter);
 }
 
 static int rewrite_one(struct commit **pp)

@@ -709,7 +724,7 @@ struct commit *get_revision(struct rev_i
 			return NULL;
 		if (revs->no_merges && commit->parents && commit->parents->next)
 			goto next;
-		if (revs->paths && revs->dense) {
+		if (revs->prune_fn && revs->dense) {
 			if (!(commit->object.flags & TREECHANGE))
 				goto next;
 			rewrite_parents(commit);

@@ -7,6 +7,10 @@
 #define SHOWN		(1u<<3)
 #define TMP_MARK	(1u<<4) /* for isolated cases; clean after use */
 
+struct rev_info;
+
+typedef void (prune_fn_t)(struct rev_info *revs, struct commit *commit);
+
 struct rev_info {
 	/* Starting list */
 	struct commit_list *commits;

@@ -14,7 +18,9 @@ struct rev_info {
 
 	/* Basic information */
 	const char *prefix;
-	const char **paths;
+
+	void* prune_data;
+	prune_fn_t* prune_fn;
 
 	/* Traversal flags */
 	unsigned int	dense:1,

@@ -33,9 +39,21 @@ struct rev_info {
 	int max_count;
 	unsigned long max_age;
 	unsigned long min_age;
+
+	set_fn_t topo_setter;
+	get_fn_t topo_getter;
 };
 
+#define TREE_SAME	0
+#define TREE_NEW	1
+#define TREE_DIFFERENT	2
+
 /* revision.c */
+extern int same_tree_as_empty(struct tree *t1);
+extern int compare_tree(struct tree *t1, struct tree *t2);
+
+
+extern void init_revisions(struct rev_info *revs);
 extern int setup_revisions(int argc, const char **argv, struct rev_info *revs, const char *def);
 extern void prepare_revision_walk(struct rev_info *revs);
 extern struct commit *get_revision(struct rev_info *revs);

@@ -14,6 +14,7 @@
 #include "tree.h"
 #include "blob.h"
 #include "diff.h"
+#include "diffcore.h"
 #include "revision.h"
 
 #define DEBUG 0

@@ -34,7 +35,9 @@ struct util_info {
 	char *buf;
 	unsigned long size;
 	int num_lines;
-//    const char* path;
+	const char* pathname;
+
+	void* topo_data;
 };
 
 struct chunk {

@@ -342,25 +345,34 @@ static int map_line(struct commit *commi
 	return info->line_map[line];
 }
 
-static int fill_util_info(struct commit *commit, const char *path)
+static struct util_info* get_util(struct commit *commit)
 {
-	struct util_info *util;
-	if (commit->object.util)
-		return 0;
+	struct util_info *util = commit->object.util;
+
+	if(util)
+		return util;
 
 	util = xmalloc(sizeof(struct util_info));
+	util->buf = NULL;
+	util->size = 0;
+	util->line_map = NULL;
+	util->num_lines = -1;
+	util->pathname = NULL;
+	commit->object.util = util;
+	return util;
+}
+
+static int fill_util_info(struct commit *commit)
+{
+	struct util_info *util = commit->object.util;
 
-	if (get_blob_sha1(commit->tree, path, util->sha1)) {
-		free(util);
+	assert(util);
+	assert(util->pathname);
+	
+	if (get_blob_sha1(commit->tree, util->pathname, util->sha1))
 		return 1;
-	} else {
-		util->buf = NULL;
-		util->size = 0;
-		util->line_map = NULL;
-		util->num_lines = -1;
-		commit->object.util = util;
+	else
 		return 0;
-	}
 }
 
 static void alloc_line_map(struct commit *commit)

@@ -389,10 +401,11 @@ static void alloc_line_map(struct commit
 
 static void init_first_commit(struct commit* commit, const char* filename)
 {
-	struct util_info* util;
+	struct util_info* util = commit->object.util;
 	int i;
 
-	if (fill_util_info(commit, filename))
+	util->pathname = filename;
+	if (fill_util_info(commit))
 		die("fill_util_info failed");
 
 	alloc_line_map(commit);

@@ -453,7 +466,7 @@ static void process_commits(struct rev_i
 		if(num_parents == 0)
 			*initial = commit;
 
-		if(fill_util_info(commit, path))
+		if(fill_util_info(commit))
 			continue;
 
 		alloc_line_map(commit);

@@ -471,7 +484,7 @@ static void process_commits(struct rev_i
 				printf("parent: %s\n",
 				       sha1_to_hex(parent->object.sha1));
 
-			if(fill_util_info(parent, path)) {
+			if(fill_util_info(parent)) {
 				num_parents--;
 				continue;
 			}

@@ -511,6 +524,135 @@ static void process_commits(struct rev_i
 	} while ((commit = get_revision(rev)) != NULL);
 }
 
+
+static int compare_tree_path(struct rev_info* revs,
+			     struct commit* c1, struct commit* c2)
+{
+	const char* paths[2];
+	struct util_info* util = c2->object.util;
+	paths[0] = util->pathname;
+	paths[1] = NULL;
+
+	diff_tree_setup_paths(get_pathspec(revs->prefix, paths));
+	return compare_tree(c1->tree, c2->tree);
+}
+
+
+static int same_tree_as_empty_path(struct rev_info *revs, struct tree* t1,
+				   const char* path)
+{
+	const char* paths[2];
+	paths[0] = path;
+	paths[1] = NULL;
+
+	diff_tree_setup_paths(get_pathspec(revs->prefix, paths));
+	return same_tree_as_empty(t1);
+}
+
+static const char* find_rename(struct commit* commit, struct commit* parent)
+{
+	struct util_info* cutil = commit->object.util;
+	struct diff_options diff_opts;
+	const char *paths[1];
+	int i;
+
+	if(DEBUG) {
+		printf("find_rename commit: %s ",
+		       sha1_to_hex(commit->object.sha1));
+		puts(sha1_to_hex(parent->object.sha1));
+	}
+
+	diff_setup(&diff_opts);
+	diff_opts.recursive = 1;
+	diff_opts.detect_rename = DIFF_DETECT_RENAME;
+	paths[0] = NULL;
+	diff_tree_setup_paths(paths);
+	if(diff_setup_done(&diff_opts) < 0)
+		die("diff_setup_done failed");
+
+	diff_tree_sha1(commit->tree->object.sha1, parent->tree->object.sha1,
+		       "", &diff_opts);
+	diffcore_std(&diff_opts);
+
+	for(i = 0; i < diff_queued_diff.nr; i++) {
+		struct diff_filepair *p = diff_queued_diff.queue[i];
+
+		if(p->status == 'R' && !strcmp(p->one->path, cutil->pathname)) {
+			if(DEBUG)
+				printf("rename %s -> %s\n", p->one->path, p->two->path);
+			return p->two->path;
+		}
+	}
+
+	return 0;
+}
+
+static void simplify_commit(struct rev_info *revs, struct commit *commit)
+{
+	struct commit_list **pp, *parent;
+
+	if (!commit->tree)
+		return;
+
+	if (!commit->parents) {
+		struct util_info* util = commit->object.util;
+		if (!same_tree_as_empty_path(revs, commit->tree,
+					     util->pathname))
+			commit->object.flags |= TREECHANGE;
+		return;
+	}
+
+	pp = &commit->parents;
+	while ((parent = *pp) != NULL) {
+		struct commit *p = parent->item;
+
+		if (p->object.flags & UNINTERESTING) {
+			pp = &parent->next;
+			continue;
+		}
+
+		parse_commit(p);
+		switch (compare_tree_path(revs, p, commit)) {
+		case TREE_SAME:
+			parent->next = NULL;
+			commit->parents = parent;
+			get_util(p)->pathname = get_util(commit)->pathname;
+			return;
+
+		case TREE_NEW:
+		{
+			
+			struct util_info* util = commit->object.util;
+			if (revs->remove_empty_trees &&
+			    same_tree_as_empty_path(revs, p->tree,
+						    util->pathname)) {
+				const char* new_name = find_rename(commit, p);
+				if(new_name) {
+					struct util_info* putil = get_util(p);
+					if(!putil->pathname)
+						putil->pathname = strdup(new_name);
+				} else {
+					*pp = parent->next;
+					continue;
+				}
+			}
+		}
+
+		/* fallthrough */
+		case TREE_DIFFERENT:
+			pp = &parent->next;
+			if(!get_util(p)->pathname)
+				get_util(p)->pathname =
+					get_util(commit)->pathname;
+			continue;
+		}
+		die("bad tree compare for commit %s",
+		    sha1_to_hex(commit->object.sha1));
+	}
+	commit->object.flags |= TREECHANGE;
+}
+
+
 struct commit_info
 {
 	char* author;

@@ -569,6 +711,18 @@ static const char* format_time(unsigned 
 	return time_buf;
 }
 
+static void topo_setter(struct commit* c, void* data)
+{
+	struct util_info* util = c->object.util;
+	util->topo_data = data;
+}
+
+static void* topo_getter(struct commit* c)
+{
+	struct util_info* util = c->object.util;
+	return util->topo_data;
+}
+
 int main(int argc, const char **argv)
 {
 	int i;

@@ -580,8 +734,8 @@ int main(int argc, const char **argv)
 	int sha1_len = 8;
 	int compability = 0;
 	int options = 1;
+	struct commit* start_commit;
 
-	int num_args;
 	const char* args[10];
 	struct rev_info rev;
 

@@ -634,28 +788,29 @@ int main(int argc, const char **argv)
 		strcpy(filename_buf, filename);
 	filename = filename_buf;
 
-	{
-		struct commit* c;
-		if (get_sha1(commit, sha1))
-			die("get_sha1 failed, commit '%s' not found", commit);
-		c = lookup_commit_reference(sha1);
-
-		if (fill_util_info(c, filename)) {
-			printf("%s not found in %s\n", filename, commit);
-			return 1;
-		}
+	if (get_sha1(commit, sha1))
+		die("get_sha1 failed, commit '%s' not found", commit);	
+	start_commit = lookup_commit_reference(sha1);
+	get_util(start_commit)->pathname = filename;
+	if (fill_util_info(start_commit)) {
+		printf("%s not found in %s\n", filename, commit);
+		return 1;
 	}
 
-	num_args = 0;
-	args[num_args++] = NULL;
-	args[num_args++] = "--topo-order";
-	args[num_args++] = "--remove-empty";
-	args[num_args++] = commit;
-	args[num_args++] = "--";
-	args[num_args++] = filename;
-	args[num_args] = NULL;
 
-	setup_revisions(num_args, args, &rev, "HEAD");
+	init_revisions(&rev);	
+	rev.remove_empty_trees = 1;
+	rev.topo_order = 1;
+	rev.prune_fn = simplify_commit;
+	rev.topo_setter = topo_setter;
+	rev.topo_getter = topo_getter;
+	rev.limited = 1;
+
+	commit_list_insert(start_commit, &rev.commits);
+	
+	args[0] = filename;
+	args[1] = NULL;
+	diff_tree_setup_paths(args);
 	prepare_revision_walk(&rev);
 	process_commits(&rev, filename, &initial);
 

@@ -665,17 +820,21 @@ int main(int argc, const char **argv)
 
 	for (i = 0; i < num_blame_lines; i++) {
 		struct commit *c = blame_lines[i];
+		struct util_info* u;
+
 		if (!c)
 			c = initial;
 
+		u = c->object.util;
 		get_commit_info(c, &ci);
 		fwrite(sha1_to_hex(c->object.sha1), sha1_len, 1, stdout);
 		if(compability)
 			printf("\t(%10s\t%10s\t%d)", ci.author,
 			       format_time(ci.author_time, ci.author_tz), i+1);
 		else
-			printf(" (%-15.15s %10s %*d) ", ci.author,
-			       format_time(ci.author_time, ci.author_tz),
+			printf(" %s (%-15.15s %10s %*d) ", u->pathname,
+			       ci.author, format_time(ci.author_time,
+						      ci.author_tz),
 			       max_digits, i+1);
 
 		if(i == num_blame_lines - 1) {