split-index: strip pathname of on-disk replaced entries

We know the positions of replaced entries via the replace bitmap in
"link" extension, so the "name" path does not have to be stored (it's
still in the shared index). With this, we also have a way to
distinguish additions vs replacements at load time and can catch
broken "link" extensions.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 23 insertions, 2 deletions

diff --git a/cache.h b/cache.h
index 70fd8ed462..ddb7cd26d1 100644
--- a/cache.h
+++ b/cache.h
@@ -170,6 +170,7 @@ struct cache_entry {
 #define CE_MATCHED           (1 << 26)
 
 #define CE_UPDATE_IN_BASE    (1 << 27)
+#define CE_STRIP_NAME        (1 << 28)
 
 /*
  * Extended on-disk flags
diff --git a/read-cache.c b/read-cache.c
index d5f70a08b9..af475dc58c 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -1787,9 +1787,15 @@ static int ce_write_entry(git_SHA_CTX *c, int fd, struct cache_entry *ce,
 {
 	int size;
 	struct ondisk_cache_entry *ondisk;
+	int saved_namelen = saved_namelen; /* compiler workaround */
 	char *name;
 	int result;
 
+	if (ce->ce_flags & CE_STRIP_NAME) {
+		saved_namelen = ce_namelen(ce);
+		ce->ce_namelen = 0;
+	}
+
 	if (!previous_name) {
 		size = ondisk_ce_size(ce);
 		ondisk = xcalloc(1, size);
@@ -1821,6 +1827,10 @@ static int ce_write_entry(git_SHA_CTX *c, int fd, struct cache_entry *ce,
 		strbuf_splice(previous_name, common, to_remove,
 			      ce->name + common, ce_namelen(ce) - common);
 	}
+	if (ce->ce_flags & CE_STRIP_NAME) {
+		ce->ce_namelen = saved_namelen;
+		ce->ce_flags &= ~CE_STRIP_NAME;
+	}
 
 	result = ce_write(c, fd, ondisk, size);
 	free(ondisk);
diff --git a/split-index.c b/split-index.c
index 33c0c4b698..ee3246f391 100644
--- a/split-index.c
+++ b/split-index.c
@@ -89,6 +89,7 @@ static void replace_entry(size_t pos, void *data)
 	struct index_state *istate = data;
 	struct split_index *si = istate->split_index;
 	struct cache_entry *dst, *src;
+
 	if (pos >= istate->cache_nr)
 		die("position for replacement %d exceeds base index size %d",
 		    (int)pos, istate->cache_nr);
@@ -100,10 +101,14 @@ static void replace_entry(size_t pos, void *data)
 		die("entry %d is marked as both replaced and deleted",
 		    (int)pos);
 	src = si->saved_cache[si->nr_replacements];
+	if (ce_namelen(src))
+		die("corrupt link extension, entry %d should have "
+		    "zero length name", (int)pos);
 	src->index = pos + 1;
 	src->ce_flags |= CE_UPDATE_IN_BASE;
-	free(dst);
-	dst = src;
+	src->ce_namelen = dst->ce_namelen;
+	copy_cache_entry(dst, src);
+	free(src);
 	si->nr_replacements++;
 }
 
@@ -131,6 +136,9 @@ void merge_base_index(struct index_state *istate)
 		remove_marked_cache_entries(istate);
 
 	for (i = si->nr_replacements; i < si->saved_cache_nr; i++) {
+		if (!ce_namelen(si->saved_cache[i]))
+			die("corrupt link extension, entry %d should "
+			    "have non-zero length name", i);
 		add_index_entry(istate, si->saved_cache[i],
 				ADD_CACHE_OK_TO_ADD |
 				ADD_CACHE_KEEP_CACHE_TREE |
@@ -213,6 +221,7 @@ void prepare_to_write_split_index(struct index_state *istate)
 				ewah_set(si->delete_bitmap, i);
 			else if (ce->ce_flags & CE_UPDATE_IN_BASE) {
 				ewah_set(si->replace_bitmap, i);
+				ce->ce_flags |= CE_STRIP_NAME;
 				ALLOC_GROW(entries, nr_entries+1, nr_alloc);
 				entries[nr_entries++] = ce;
 			}
@@ -222,6 +231,7 @@ void prepare_to_write_split_index(struct index_state *istate)
 	for (i = 0; i < istate->cache_nr; i++) {
 		ce = istate->cache[i];
 		if ((!si->base || !ce->index) && !(ce->ce_flags & CE_REMOVE)) {
+			assert(!(ce->ce_flags & CE_STRIP_NAME));
 			ALLOC_GROW(entries, nr_entries+1, nr_alloc);
 			entries[nr_entries++] = ce;
 		}