sparse-index: convert from full to sparse

If we have a full index, then we can convert it to a sparse index by
replacing directories outside of the sparse cone with sparse directory
entries. The convert_to_sparse() method does this, when the situation is
appropriate.

For now, we avoid converting the index to a sparse index if:

 1. the index is split.
 2. the index is already sparse.
 3. sparse-checkout is disabled.
 4. sparse-checkout does not use cone mode.

Finally, we currently limit the conversion to when the
GIT_TEST_SPARSE_INDEX environment variable is enabled. A mode using Git
config will be added in a later change.

The trickiest thing about this conversion is that we might not be able
to mark a directory as a sparse directory just because it is outside the
sparse cone. There might be unmerged files within that directory, so we
need to look for those. Also, if there is some strange reason why a file
is not marked with CE_SKIP_WORKTREE, then we should give up on
converting that directory. There is still hope that some of its
subdirectories might be able to convert to sparse, so we keep looking
deeper.

The conversion process is assisted by the cache-tree extension. This is
calculated from the full index if it does not already exist. We then
abandon the cache-tree as it no longer applies to the newly-sparse
index. Thus, this cache-tree will be recalculated in every
sparse-full-sparse round-trip until we integrate the cache-tree
extension with the sparse index.

Some Git commands use the index after writing it. For example, 'git add'
will update the index, then write it to disk, then read its entries to
report information. To keep the in-memory index in a full state after
writing, we re-expand it to a full one after the write. This is wasteful
for commands that only write the index and do not read from it again,
but that is only the case until we make those commands "sparse aware."

We can compare the behavior of the sparse-index in
t1092-sparse-checkout-compability.sh by using GIT_TEST_SPARSE_INDEX=1
when operating on the 'sparse-index' repo. We can also compare the two
sparse repos directly, such as comparing their indexes (when expanded to
full in the case of the 'sparse-index' repo). We also verify that the
index is actually populated with sparse directory entries.

The 'checkout and reset (mixed)' test is marked for failure when
comparing a sparse repo to a full repo, but we can compare the two
sparse-checkout cases directly to ensure that we are not changing the
behavior when using a sparse index.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 139 insertions, 0 deletions

diff --git a/sparse-index.c b/sparse-index.c
index 7095378..619ff7c 100644
--- a/sparse-index.c
+++ b/sparse-index.c
@@ -4,6 +4,145 @@
 #include "tree.h"
 #include "pathspec.h"
 #include "trace2.h"
+#include "cache-tree.h"
+#include "config.h"
+#include "dir.h"
+#include "fsmonitor.h"
+
+static struct cache_entry *construct_sparse_dir_entry(
+				struct index_state *istate,
+				const char *sparse_dir,
+				struct cache_tree *tree)
+{
+	struct cache_entry *de;
+
+	de = make_cache_entry(istate, S_IFDIR, &tree->oid, sparse_dir, 0, 0);
+
+	de->ce_flags |= CE_SKIP_WORKTREE;
+	return de;
+}
+
+/*
+ * Returns the number of entries "inserted" into the index.
+ */
+static int convert_to_sparse_rec(struct index_state *istate,
+				 int num_converted,
+				 int start, int end,
+				 const char *ct_path, size_t ct_pathlen,
+				 struct cache_tree *ct)
+{
+	int i, can_convert = 1;
+	int start_converted = num_converted;
+	enum pattern_match_result match;
+	int dtype;
+	struct strbuf child_path = STRBUF_INIT;
+	struct pattern_list *pl = istate->sparse_checkout_patterns;
+
+	/*
+	 * Is the current path outside of the sparse cone?
+	 * Then check if the region can be replaced by a sparse
+	 * directory entry (everything is sparse and merged).
+	 */
+	match = path_matches_pattern_list(ct_path, ct_pathlen,
+					  NULL, &dtype, pl, istate);
+	if (match != NOT_MATCHED)
+		can_convert = 0;
+
+	for (i = start; can_convert && i < end; i++) {
+		struct cache_entry *ce = istate->cache[i];
+
+		if (ce_stage(ce) ||
+		    !(ce->ce_flags & CE_SKIP_WORKTREE))
+			can_convert = 0;
+	}
+
+	if (can_convert) {
+		struct cache_entry *se;
+		se = construct_sparse_dir_entry(istate, ct_path, ct);
+
+		istate->cache[num_converted++] = se;
+		return 1;
+	}
+
+	for (i = start; i < end; ) {
+		int count, span, pos = -1;
+		const char *base, *slash;
+		struct cache_entry *ce = istate->cache[i];
+
+		/*
+		 * Detect if this is a normal entry outside of any subtree
+		 * entry.
+		 */
+		base = ce->name + ct_pathlen;
+		slash = strchr(base, '/');
+
+		if (slash)
+			pos = cache_tree_subtree_pos(ct, base, slash - base);
+
+		if (pos < 0) {
+			istate->cache[num_converted++] = ce;
+			i++;
+			continue;
+		}
+
+		strbuf_setlen(&child_path, 0);
+		strbuf_add(&child_path, ce->name, slash - ce->name + 1);
+
+		span = ct->down[pos]->cache_tree->entry_count;
+		count = convert_to_sparse_rec(istate,
+					      num_converted, i, i + span,
+					      child_path.buf, child_path.len,
+					      ct->down[pos]->cache_tree);
+		num_converted += count;
+		i += span;
+	}
+
+	strbuf_release(&child_path);
+	return num_converted - start_converted;
+}
+
+int convert_to_sparse(struct index_state *istate)
+{
+	if (istate->split_index || istate->sparse_index ||
+	    !core_apply_sparse_checkout || !core_sparse_checkout_cone)
+		return 0;
+
+	/*
+	 * For now, only create a sparse index with the
+	 * GIT_TEST_SPARSE_INDEX environment variable. We will relax
+	 * this once we have a proper way to opt-in (and later still,
+	 * opt-out).
+	 */
+	if (!git_env_bool("GIT_TEST_SPARSE_INDEX", 0))
+		return 0;
+
+	if (!istate->sparse_checkout_patterns) {
+		istate->sparse_checkout_patterns = xcalloc(1, sizeof(struct pattern_list));
+		if (get_sparse_checkout_patterns(istate->sparse_checkout_patterns) < 0)
+			return 0;
+	}
+
+	if (!istate->sparse_checkout_patterns->use_cone_patterns) {
+		warning(_("attempting to use sparse-index without cone mode"));
+		return -1;
+	}
+
+	if (cache_tree_update(istate, 0)) {
+		warning(_("unable to update cache-tree, staying full"));
+		return -1;
+	}
+
+	remove_fsmonitor(istate);
+
+	trace2_region_enter("index", "convert_to_sparse", istate->repo);
+	istate->cache_nr = convert_to_sparse_rec(istate,
+						 0, 0, istate->cache_nr,
+						 "", 0, istate->cache_tree);
+	istate->drop_cache_tree = 1;
+	istate->sparse_index = 1;
+	trace2_region_leave("index", "convert_to_sparse", istate->repo);
+	return 0;
+}
 
 static void set_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
 {