[PATCH v4 3/4] cache-tree: fix writing cache-tree when CE_REMOVE is present

["Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>]

entry_count is used in update_one() for two purposes:

1. to skip through the number of processed entries in in-memory index
2. to record the number of entries this cache-tree covers on disk

Unfortunately when CE_REMOVE is present these numbers are not the same
because CE_REMOVE entries are automatically removed before writing to
disk but entry_count is not adjusted and still counts CE_REMOVE
entries.

Separate the two use cases into two different variables. #1 is taken
care by the new field count in struct cache_tree_sub and entry_count
is prepared for #2.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 cache-tree.c | 30 +++++++++++++++++++++++-------
 cache-tree.h |  1 +
 2 files changed, 24 insertions(+), 7 deletions(-)

diff --git a/cache-tree.c b/cache-tree.c
index 44eed28..2c10b2e 100644
--- a/cache-tree.c
+++ b/cache-tree.c
@@ -238,6 +238,7 @@ static int update_one(struct cache_tree *it,
 		      int entries,
 		      const char *base,
 		      int baselen,
+		      int *skip_count,
 		      int flags)
 {
 	struct strbuf buffer;
@@ -245,6 +246,8 @@ static int update_one(struct cache_tree *it,
 	int dryrun = flags & WRITE_TREE_DRY_RUN;
 	int i;
 
+	*skip_count = 0;
+
 	if (0 <= it->entry_count && has_sha1_file(it->sha1))
 		return it->entry_count;
 
@@ -264,7 +267,7 @@ static int update_one(struct cache_tree *it,
 		struct cache_entry *ce = cache[i];
 		struct cache_tree_sub *sub;
 		const char *path, *slash;
-		int pathlen, sublen, subcnt;
+		int pathlen, sublen, subcnt, subskip;
 
 		path = ce->name;
 		pathlen = ce_namelen(ce);
@@ -289,10 +292,13 @@ static int update_one(struct cache_tree *it,
 				    cache + i, entries - i,
 				    path,
 				    baselen + sublen + 1,
+				    &subskip,
 				    flags);
 		if (subcnt < 0)
 			return subcnt;
 		i += subcnt;
+		sub->count = subcnt; /* to be used in the next loop */
+		*skip_count += subskip;
 		sub->used = 1;
 	}
 
@@ -324,7 +330,7 @@ static int update_one(struct cache_tree *it,
 			if (!sub)
 				die("cache-tree.c: '%.*s' in '%s' not found",
 				    entlen, path + baselen, path);
-			i += sub->cache_tree->entry_count;
+			i += sub->count;
 			sha1 = sub->cache_tree->sha1;
 			mode = S_IFDIR;
 		}
@@ -340,8 +346,18 @@ static int update_one(struct cache_tree *it,
 				mode, sha1_to_hex(sha1), entlen+baselen, path);
 		}
 
-		if (ce->ce_flags & (CE_REMOVE | CE_INTENT_TO_ADD))
-			continue; /* entry being removed or placeholder */
+		/*
+		 * CE_REMOVE entries are removed before the index is
+		 * written to disk. Skip them to remain consistent
+		 * with the future on-disk index.
+		 */
+		if (ce->ce_flags & CE_REMOVE) {
+			*skip_count = *skip_count + 1;
+			continue;
+		}
+
+		if (ce->ce_flags & CE_INTENT_TO_ADD)
+			continue;
 
 		strbuf_grow(&buffer, entlen + 100);
 		strbuf_addf(&buffer, "%o %.*s%c", mode, entlen, path + baselen, '\0');
@@ -361,7 +377,7 @@ static int update_one(struct cache_tree *it,
 	}
 
 	strbuf_release(&buffer);
-	it->entry_count = i;
+	it->entry_count = i - *skip_count;
 #if DEBUG
 	fprintf(stderr, "cache-tree update-one (%d ent, %d subtree) %s\n",
 		it->entry_count, it->subtree_nr,
@@ -375,11 +391,11 @@ int cache_tree_update(struct cache_tree *it,
 		      int entries,
 		      int flags)
 {
-	int i;
+	int i, skip;
 	i = verify_cache(cache, entries, flags);
 	if (i)
 		return i;
-	i = update_one(it, cache, entries, "", 0, flags);
+	i = update_one(it, cache, entries, "", 0, &skip, flags);
 	if (i < 0)
 		return i;
 	return 0;
diff --git a/cache-tree.h b/cache-tree.h
index d8cb2e9..55d0f59 100644
--- a/cache-tree.h
+++ b/cache-tree.h
@@ -7,6 +7,7 @@
 struct cache_tree;
 struct cache_tree_sub {
 	struct cache_tree *cache_tree;
+	int count;		/* internally used by update_one() */
 	int namelen;
 	int used;
 	char name[FLEX_ARRAY];
-- 
1.8.0.rc2.23.g1fb49df