Add git-update-cache --replace option.

When "path" exists as a file or a symlink in the index, an
attempt to add "path/file" is refused because it results in file
vs directory conflict.  Similarly when "path/file1",
"path/file2", etc. exist, an attempt to add "path" as a file or
a symlink is refused.  With git-update-cache --replace, these
existing entries that conflict with the entry being added are
automatically removed from the cache, with warning messages.

Signed-off-by: Junio C Hamano <junkio@cox.net>

5 files changed, 65 insertions, 23 deletions

diff --git a/Documentation/core-git.txt b/Documentation/core-git.txt
index 014b97964e..5e702fd832 100644
--- a/Documentation/core-git.txt
+++ b/Documentation/core-git.txt
@@ -1098,7 +1098,7 @@ returns the name of the temporary file in the following format:
 ################################################################
 git-update-cache
 	git-update-cache
-	     [--add] [--remove] [--refresh]
+	     [--add] [--remove] [--refresh] [--replace]
 	     [--ignore-missing]
 	     [--force-remove <file>]
 	     [--cacheinfo <mode> <object> <file>]*
@@ -1135,6 +1135,14 @@ using the various options:
 	Remove the file from the index even when the working directory
 	still has such a file.
 
+--replace
+	By default, when a file "path" exists in the index,
+	git-update-cache refuses an attempt to add "path/file".
+	Similarly if a file "path/file" exists, a file "path"
+	cannot be added.  With --replace flag, existing entries
+	that conflicts with the entry being added are
+	automatically removed with warning messages.
+
 --
 	Do not interpret any more arguments as options.
 
diff --git a/cache.h b/cache.h
index 314ee0dd0f..7a656c70d3 100644
--- a/cache.h
+++ b/cache.h
@@ -116,7 +116,9 @@ unsigned int active_nr, active_alloc, active_cache_changed;
 extern int read_cache(void);
 extern int write_cache(int newfd, struct cache_entry **cache, int entries);
 extern int cache_name_pos(const char *name, int namelen);
-extern int add_cache_entry(struct cache_entry *ce, int ok_to_add);
+#define ADD_CACHE_OK_TO_ADD 1		/* Ok to add */
+#define ADD_CACHE_OK_TO_REPLACE 2	/* Ok to replace file/directory */
+extern int add_cache_entry(struct cache_entry *ce, int option);
 extern int remove_entry_at(int pos);
 extern int remove_file_from_cache(char *path);
 extern int same_name(struct cache_entry *a, struct cache_entry *b);
diff --git a/read-cache.c b/read-cache.c
index 327888b8ad..47aa2d4469 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -127,10 +127,15 @@ int same_name(struct cache_entry *a, struct cache_entry *b)
  * is being added, or we already have path and path/file is being
  * added.  Either one would result in a nonsense tree that has path
  * twice when git-write-tree tries to write it out.  Prevent it.
+ * 
+ * If ok-to-replace is specified, we remove the conflicting entries
+ * from the cache so the caller should recompute the insert position.
+ * When this happens, we return non-zero.
  */
-static int check_file_directory_conflict(const struct cache_entry *ce)
+static int check_file_directory_conflict(const struct cache_entry *ce,
+					 int ok_to_replace)
 {
-	int pos;
+	int pos, replaced = 0;
 	const char *path = ce->name;
 	int namelen = strlen(path);
 	int stage = ce_stage(ce);
@@ -157,8 +162,13 @@ static int check_file_directory_conflict(const struct cache_entry *ce)
 			 * and we are trying to make it a directory.  This is
 			 * bad.
 			 */
-			free(pathbuf);
-			return -1;
+			if (!ok_to_replace) {
+				free(pathbuf);
+				return -1;
+			}
+			fprintf(stderr, "removing file '%s' to replace it with a directory to create '%s'.\n", pathbuf, path);
+			remove_entry_at(pos);
+			replaced = 1;
 		}
 		*ep = '/';  /* then restore it and go downwards */
 		cp = ep + 1;
@@ -185,30 +195,40 @@ static int check_file_directory_conflict(const struct cache_entry *ce)
 	 *
 	 *        1 path
 	 * pos->  3 path
-	 *        2 path/file
-	 *        3 path/file
+	 *        2 path/file1
+	 *        3 path/file1
+	 *        2 path/file2
+	 *        2 patho
 	 *
 	 * We need to examine pos, ignore it because it is at different
 	 * stage, examine next to find the path/file at stage 2, and
-	 * complain.
+	 * complain.  We need to do this until we are not the leading
+	 * path of an existing entry anymore.
 	 */
 
 	while (pos < active_nr) {
 		struct cache_entry *other = active_cache[pos];
 		if (strncmp(other->name, path, namelen))
 			break; /* it is not our "subdirectory" anymore */
-		if ((ce_stage(other) == stage) && other->name[namelen] == '/')
-			return -1;
+		if ((ce_stage(other) == stage) &&
+		    other->name[namelen] == '/') {
+			if (!ok_to_replace)
+				return -1;
+			fprintf(stderr, "removing file '%s' under '%s' to be replaced with a file\n", other->name, path);
+			remove_entry_at(pos);
+			replaced = 1;
+			continue; /* cycle without updating pos */
+		}
 		pos++;
 	}
-
-	return 0;
+	return replaced;
 }
 
-int add_cache_entry(struct cache_entry *ce, int ok_to_add)
+int add_cache_entry(struct cache_entry *ce, int option)
 {
 	int pos;
-
+	int ok_to_add = option & ADD_CACHE_OK_TO_ADD;
+	int ok_to_replace = option & ADD_CACHE_OK_TO_REPLACE;
 	pos = cache_name_pos(ce->name, htons(ce->ce_flags));
 
 	/* existing match? Just replace it */
@@ -234,8 +254,12 @@ int add_cache_entry(struct cache_entry *ce, int ok_to_add)
 	if (!ok_to_add)
 		return -1;
 
-	if (check_file_directory_conflict(ce))
-		return -1;
+	if (check_file_directory_conflict(ce, ok_to_replace)) {
+		if (!ok_to_replace)
+			return -1;
+		pos = cache_name_pos(ce->name, htons(ce->ce_flags));
+		pos = -pos-1;
+	}
 
 	/* Make sure the array is big enough .. */
 	if (active_nr == active_alloc) {
diff --git a/tree.c b/tree.c
index d9777bf810..a978c53a30 100644
--- a/tree.c
+++ b/tree.c
@@ -18,7 +18,7 @@ static int read_one_entry(unsigned char *sha1, const char *base, int baselen, co
 	memcpy(ce->name, base, baselen);
 	memcpy(ce->name + baselen, pathname, len+1);
 	memcpy(ce->sha1, sha1, 20);
-	return add_cache_entry(ce, 1);
+	return add_cache_entry(ce, ADD_CACHE_OK_TO_ADD);
 }
 
 static int read_tree_recursive(void *buffer, unsigned long size,
diff --git a/update-cache.c b/update-cache.c
index 735d19920d..1e4e62cc4c 100644
--- a/update-cache.c
+++ b/update-cache.c
@@ -13,7 +13,7 @@
  * like "update-cache *" and suddenly having all the object
  * files be revision controlled.
  */
-static int allow_add = 0, allow_remove = 0, not_new = 0;
+static int allow_add = 0, allow_remove = 0, allow_replace = 0, not_new = 0;
 
 /* Three functions to allow overloaded pointer return; see linux/err.h */
 static inline void *ERR_PTR(long error)
@@ -53,7 +53,7 @@ static void fill_stat_cache_info(struct cache_entry *ce, struct stat *st)
 
 static int add_file_to_cache(char *path)
 {
-	int size, namelen;
+	int size, namelen, option;
 	struct cache_entry *ce;
 	struct stat st;
 	int fd;
@@ -95,7 +95,9 @@ static int add_file_to_cache(char *path)
 	default:
 		return -1;
 	}
-	return add_cache_entry(ce, allow_add);
+	option = allow_add ? ADD_CACHE_OK_TO_ADD : 0;
+	option |= allow_replace ? ADD_CACHE_OK_TO_REPLACE : 0;
+	return add_cache_entry(ce, option);
 }
 
 static int match_data(int fd, void *buffer, unsigned long size)
@@ -273,7 +275,7 @@ inside:
 
 static int add_cacheinfo(char *arg1, char *arg2, char *arg3)
 {
-	int size, len;
+	int size, len, option;
 	unsigned int mode;
 	unsigned char sha1[20];
 	struct cache_entry *ce;
@@ -294,7 +296,9 @@ static int add_cacheinfo(char *arg1, char *arg2, char *arg3)
 	memcpy(ce->name, arg3, len);
 	ce->ce_flags = htons(len);
 	ce->ce_mode = create_ce_mode(mode);
-	return add_cache_entry(ce, allow_add);
+	option = allow_add ? ADD_CACHE_OK_TO_ADD : 0;
+	option |= allow_replace ? ADD_CACHE_OK_TO_REPLACE : 0;
+	return add_cache_entry(ce, option);
 }
 
 static const char *lockfile_name = NULL;
@@ -343,6 +347,10 @@ int main(int argc, char **argv)
 				allow_add = 1;
 				continue;
 			}
+			if (!strcmp(path, "--replace")) {
+				allow_replace = 1;
+				continue;
+			}
 			if (!strcmp(path, "--remove")) {
 				allow_remove = 1;
 				continue;