1 files changed, 88 insertions, 14 deletions

diff --git a/read-cache.c b/read-cache.c
index 5a907af..1b3c2eb 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -25,6 +25,7 @@
 #include "fsmonitor.h"
 #include "thread-utils.h"
 #include "progress.h"
+#include "sparse-index.h"
 
 /* Mask for the name length in ce_flags in the on-disk index */
 
@@ -47,6 +48,7 @@
 #define CACHE_EXT_FSMONITOR 0x46534D4E	  /* "FSMN" */
 #define CACHE_EXT_ENDOFINDEXENTRIES 0x454F4945	/* "EOIE" */
 #define CACHE_EXT_INDEXENTRYOFFSETTABLE 0x49454F54 /* "IEOT" */
+#define CACHE_EXT_SPARSE_DIRECTORIES 0x73646972 /* "sdir" */
 
 /* changes that can be kept in $GIT_DIR/index (basically all extensions) */
 #define EXTMASK (RESOLVE_UNDO_CHANGED | CACHE_TREE_CHANGED | \
@@ -101,6 +103,9 @@ static const char *alternate_index_output;
 
 static void set_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
 {
+	if (S_ISSPARSEDIR(ce->ce_mode))
+		istate->sparse_index = 1;
+
 	istate->cache[nr] = ce;
 	add_name_hash(istate, ce);
 }
@@ -544,7 +549,7 @@ int cache_name_stage_compare(const char *name1, int len1, int stage1, const char
 	return 0;
 }
 
-static int index_name_stage_pos(const struct index_state *istate, const char *name, int namelen, int stage)
+static int index_name_stage_pos(struct index_state *istate, const char *name, int namelen, int stage)
 {
 	int first, last;
 
@@ -562,10 +567,31 @@ static int index_name_stage_pos(const struct index_state *istate, const char *na
 		}
 		first = next+1;
 	}
+
+	if (istate->sparse_index &&
+	    first > 0) {
+		/* Note: first <= istate->cache_nr */
+		struct cache_entry *ce = istate->cache[first - 1];
+
+		/*
+		 * If we are in a sparse-index _and_ the entry before the
+		 * insertion position is a sparse-directory entry that is
+		 * an ancestor of 'name', then we need to expand the index
+		 * and search again. This will only trigger once, because
+		 * thereafter the index is fully expanded.
+		 */
+		if (S_ISSPARSEDIR(ce->ce_mode) &&
+		    ce_namelen(ce) < namelen &&
+		    !strncmp(name, ce->name, ce_namelen(ce))) {
+			ensure_full_index(istate);
+			return index_name_stage_pos(istate, name, namelen, stage);
+		}
+	}
+
 	return -first-1;
 }
 
-int index_name_pos(const struct index_state *istate, const char *name, int namelen)
+int index_name_pos(struct index_state *istate, const char *name, int namelen)
 {
 	return index_name_stage_pos(istate, name, namelen, 0);
 }
@@ -813,8 +839,11 @@ struct cache_entry *make_empty_cache_entry(struct index_state *istate, size_t le
 	return mem_pool__ce_calloc(find_mem_pool(istate), len);
 }
 
-struct cache_entry *make_empty_transient_cache_entry(size_t len)
+struct cache_entry *make_empty_transient_cache_entry(size_t len,
+						     struct mem_pool *ce_mem_pool)
 {
+	if (ce_mem_pool)
+		return mem_pool__ce_calloc(ce_mem_pool, len);
 	return xcalloc(1, cache_entry_size(len));
 }
 
@@ -848,8 +877,11 @@ struct cache_entry *make_cache_entry(struct index_state *istate,
 	return ret;
 }
 
-struct cache_entry *make_transient_cache_entry(unsigned int mode, const struct object_id *oid,
-					       const char *path, int stage)
+struct cache_entry *make_transient_cache_entry(unsigned int mode,
+					       const struct object_id *oid,
+					       const char *path,
+					       int stage,
+					       struct mem_pool *ce_mem_pool)
 {
 	struct cache_entry *ce;
 	int len;
@@ -860,7 +892,7 @@ struct cache_entry *make_transient_cache_entry(unsigned int mode, const struct o
 	}
 
 	len = strlen(path);
-	ce = make_empty_transient_cache_entry(len);
+	ce = make_empty_transient_cache_entry(len, ce_mem_pool);
 
 	oidcpy(&ce->oid, oid);
 	memcpy(ce->name, path, len);
@@ -985,7 +1017,7 @@ inside:
 				}
 			}
 			if (protect_ntfs) {
-#ifdef GIT_WINDOWS_NATIVE
+#if defined GIT_WINDOWS_NATIVE || defined __CYGWIN__
 				if (c == '\\')
 					return 0;
 #endif
@@ -999,8 +1031,14 @@ inside:
 
 			c = *path++;
 			if ((c == '.' && !verify_dotfile(path, mode)) ||
-			    is_dir_sep(c) || c == '\0')
+			    is_dir_sep(c))
 				return 0;
+			/*
+			 * allow terminating directory separators for
+			 * sparse directory entries.
+			 */
+			if (c == '\0')
+				return S_ISDIR(mode);
 		} else if (c == '\\' && protect_ntfs) {
 			if (is_ntfs_dotgit(path))
 				return 0;
@@ -1514,6 +1552,7 @@ int refresh_index(struct index_state *istate, unsigned int flags,
 	int quiet = (flags & REFRESH_QUIET) != 0;
 	int not_new = (flags & REFRESH_IGNORE_MISSING) != 0;
 	int ignore_submodules = (flags & REFRESH_IGNORE_SUBMODULES) != 0;
+	int ignore_skip_worktree = (flags & REFRESH_IGNORE_SKIP_WORKTREE) != 0;
 	int first = 1;
 	int in_porcelain = (flags & REFRESH_IN_PORCELAIN);
 	unsigned int options = (CE_MATCH_REFRESH |
@@ -1545,6 +1584,8 @@ int refresh_index(struct index_state *istate, unsigned int flags,
 	 */
 	preload_index(istate, pathspec, 0);
 	trace2_region_enter("index", "refresh", NULL);
+	/* TODO: audit for interaction with sparse-index. */
+	ensure_full_index(istate);
 	for (i = 0; i < istate->cache_nr; i++) {
 		struct cache_entry *ce, *new_entry;
 		int cache_errno = 0;
@@ -1556,6 +1597,8 @@ int refresh_index(struct index_state *istate, unsigned int flags,
 		ce = istate->cache[i];
 		if (ignore_submodules && S_ISGITLINK(ce->ce_mode))
 			continue;
+		if (ignore_skip_worktree && ce_skip_worktree(ce))
+			continue;
 
 		if (pathspec && !ce_path_match(istate, ce, pathspec, seen))
 			filtered = 1;
@@ -1760,6 +1803,10 @@ static int read_index_extension(struct index_state *istate,
 	case CACHE_EXT_INDEXENTRYOFFSETTABLE:
 		/* already handled in do_read_index() */
 		break;
+	case CACHE_EXT_SPARSE_DIRECTORIES:
+		/* no content, only an indicator */
+		istate->sparse_index = 1;
+		break;
 	default:
 		if (*ext < 'A' || 'Z' < *ext)
 			return error(_("index uses %.4s extension, which we do not understand"),
@@ -1845,7 +1892,7 @@ static struct cache_entry *create_from_disk(struct mem_pool *ce_mem_pool,
 	ce->ce_flags = flags & ~CE_NAMEMASK;
 	ce->ce_namelen = len;
 	ce->index = 0;
-	hashcpy(ce->oid.hash, ondisk->data);
+	oidread(&ce->oid, ondisk->data);
 	memcpy(ce->name, name, len);
 	ce->name[len] = '\0';
 
@@ -2195,7 +2242,7 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
 	if (verify_hdr(hdr, mmap_size) < 0)
 		goto unmap;
 
-	hashcpy(istate->oid.hash, (const unsigned char *)hdr + mmap_size - the_hash_algo->rawsz);
+	oidread(&istate->oid, (const unsigned char *)hdr + mmap_size - the_hash_algo->rawsz);
 	istate->version = ntohl(hdr->hdr_version);
 	istate->cache_nr = ntohl(hdr->hdr_entries);
 	istate->cache_alloc = alloc_nr(istate->cache_nr);
@@ -2273,6 +2320,12 @@ int do_read_index(struct index_state *istate, const char *path, int must_exist)
 	trace2_data_intmax("index", the_repository, "read/cache_nr",
 			   istate->cache_nr);
 
+	if (!istate->repo)
+		istate->repo = the_repository;
+	prepare_repo_settings(istate->repo);
+	if (istate->repo->settings.command_requires_full_index)
+		ensure_full_index(istate);
+
 	return istate->cache_nr;
 
 unmap:
@@ -2457,6 +2510,8 @@ int repo_index_has_changes(struct repository *repo,
 		diff_flush(&opt);
 		return opt.flags.has_changes != 0;
 	} else {
+		/* TODO: audit for interaction with sparse-index. */
+		ensure_full_index(istate);
 		for (i = 0; sb && i < istate->cache_nr; i++) {
 			if (i)
 				strbuf_addch(sb, ' ');
@@ -3012,6 +3067,10 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile,
 		if (err)
 			return -1;
 	}
+	if (istate->sparse_index) {
+		if (write_index_ext_header(&c, &eoie_c, newfd, CACHE_EXT_SPARSE_DIRECTORIES, 0) < 0)
+			return -1;
+	}
 
 	/*
 	 * CACHE_EXT_ENDOFINDEXENTRIES must be written as the last entry before the SHA1
@@ -3071,6 +3130,14 @@ static int do_write_locked_index(struct index_state *istate, struct lock_file *l
 				 unsigned flags)
 {
 	int ret;
+	int was_full = !istate->sparse_index;
+
+	ret = convert_to_sparse(istate);
+
+	if (ret) {
+		warning(_("failed to convert to a sparse-index"));
+		return ret;
+	}
 
 	/*
 	 * TODO trace2: replace "the_repository" with the actual repo instance
@@ -3082,6 +3149,9 @@ static int do_write_locked_index(struct index_state *istate, struct lock_file *l
 	trace2_region_leave_printf("index", "do_write_index", the_repository,
 				   "%s", get_lock_file_path(lock));
 
+	if (was_full)
+		ensure_full_index(istate);
+
 	if (ret)
 		return ret;
 	if (flags & COMMIT_LOCK)
@@ -3172,9 +3242,10 @@ static int write_shared_index(struct index_state *istate,
 			      struct tempfile **temp)
 {
 	struct split_index *si = istate->split_index;
-	int ret;
+	int ret, was_full = !istate->sparse_index;
 
 	move_cache_to_base_index(istate);
+	convert_to_sparse(istate);
 
 	trace2_region_enter_printf("index", "shared/do_write_index",
 				   the_repository, "%s", get_tempfile_path(*temp));
@@ -3182,6 +3253,9 @@ static int write_shared_index(struct index_state *istate,
 	trace2_region_leave_printf("index", "shared/do_write_index",
 				   the_repository, "%s", get_tempfile_path(*temp));
 
+	if (was_full)
+		ensure_full_index(istate);
+
 	if (ret)
 		return ret;
 	ret = adjust_shared_perm(get_tempfile_path(*temp));
@@ -3350,8 +3424,8 @@ int repo_read_index_unmerged(struct repository *repo)
  * We helpfully remove a trailing "/" from directories so that
  * the output of read_directory can be used as-is.
  */
-int index_name_is_other(const struct index_state *istate, const char *name,
-		int namelen)
+int index_name_is_other(struct index_state *istate, const char *name,
+			int namelen)
 {
 	int pos;
 	if (namelen && name[namelen - 1] == '/')
@@ -3369,7 +3443,7 @@ int index_name_is_other(const struct index_state *istate, const char *name,
 	return 1;
 }
 
-void *read_blob_data_from_index(const struct index_state *istate,
+void *read_blob_data_from_index(struct index_state *istate,
 				const char *path, unsigned long *size)
 {
 	int pos, len;