Partial clone part 1: object filtering

index 1d17b80..1962374 100644
@@ -220,6 +220,57 @@ int within_depth(const char *name, int namelen,
 	return 1;
 }
 
+/*
+ * Read the contents of the blob with the given OID into a buffer.
+ * Append a trailing LF to the end if the last line doesn't have one.
+ *
+ * Returns:
+ *    -1 when the OID is invalid or unknown or does not refer to a blob.
+ *     0 when the blob is empty.
+ *     1 along with { data, size } of the (possibly augmented) buffer
+ *       when successful.
+ *
+ * Optionally updates the given sha1_stat with the given OID (when valid).
+ */
+static int do_read_blob(const struct object_id *oid,
+			struct sha1_stat *sha1_stat,
+			size_t *size_out,
+			char **data_out)
+{
+	enum object_type type;
+	unsigned long sz;
+	char *data;
+
+	*size_out = 0;
+	*data_out = NULL;
+
+	data = read_sha1_file(oid->hash, &type, &sz);
+	if (!data || type != OBJ_BLOB) {
+		free(data);
+		return -1;
+	}
+
+	if (sha1_stat) {
+		memset(&sha1_stat->stat, 0, sizeof(sha1_stat->stat));
+		hashcpy(sha1_stat->sha1, oid->hash);
+	}
+
+	if (sz == 0) {
+		free(data);
+		return 0;
+	}
+
+	if (data[sz - 1] != '\n') {
+		data = xrealloc(data, st_add(sz, 1));
+		data[sz++] = '\n';
+	}
+
+	*size_out = xsize_t(sz);
+	*data_out = data;
+
+	return 1;
+}
+
 #define DO_MATCH_EXCLUDE   (1<<0)
 #define DO_MATCH_DIRECTORY (1<<1)
 #define DO_MATCH_SUBMODULE (1<<2)

@@ -600,32 +651,22 @@ void add_exclude(const char *string, const char *base,
 	x->el = el;
 }
 
-static void *read_skip_worktree_file_from_index(const struct index_state *istate,
-						const char *path, size_t *size,
-						struct sha1_stat *sha1_stat)
+static int read_skip_worktree_file_from_index(const struct index_state *istate,
+					      const char *path,
+					      size_t *size_out,
+					      char **data_out,
+					      struct sha1_stat *sha1_stat)
 {
 	int pos, len;
-	unsigned long sz;
-	enum object_type type;
-	void *data;
 
 	len = strlen(path);
 	pos = index_name_pos(istate, path, len);
 	if (pos < 0)
-		return NULL;
+		return -1;
 	if (!ce_skip_worktree(istate->cache[pos]))
-		return NULL;
-	data = read_sha1_file(istate->cache[pos]->oid.hash, &type, &sz);
-	if (!data || type != OBJ_BLOB) {
-		free(data);
-		return NULL;
-	}
-	*size = xsize_t(sz);
-	if (sha1_stat) {
-		memset(&sha1_stat->stat, 0, sizeof(sha1_stat->stat));
-		hashcpy(sha1_stat->sha1, istate->cache[pos]->oid.hash);
-	}
-	return data;
+		return -1;
+
+	return do_read_blob(&istate->cache[pos]->oid, sha1_stat, size_out, data_out);
 }
 
 /*

@@ -739,6 +780,10 @@ static void invalidate_directory(struct untracked_cache *uc,
 		dir->dirs[i]->recurse = 0;
 }
 
+static int add_excludes_from_buffer(char *buf, size_t size,
+				    const char *base, int baselen,
+				    struct exclude_list *el);
+
 /*
  * Given a file with name "fname", read it (either from disk, or from
  * an index if 'istate' is non-null), parse it and store the

@@ -754,9 +799,10 @@ static int add_excludes(const char *fname, const char *base, int baselen,
 			struct sha1_stat *sha1_stat)
 {
 	struct stat st;
-	int fd, i, lineno = 1;
+	int r;
+	int fd;
 	size_t size = 0;
-	char *buf, *entry;
+	char *buf;
 
 	fd = open(fname, O_RDONLY);
 	if (fd < 0 || fstat(fd, &st) < 0) {

@@ -764,17 +810,13 @@ static int add_excludes(const char *fname, const char *base, int baselen,
 			warn_on_fopen_errors(fname);
 		else
 			close(fd);
-		if (!istate ||
-		    (buf = read_skip_worktree_file_from_index(istate, fname, &size, sha1_stat)) == NULL)
+		if (!istate)
 			return -1;
-		if (size == 0) {
-			free(buf);
-			return 0;
-		}
-		if (buf[size-1] != '\n') {
-			buf = xrealloc(buf, st_add(size, 1));
-			buf[size++] = '\n';
-		}
+		r = read_skip_worktree_file_from_index(istate, fname,
+						       &size, &buf,
+						       sha1_stat);
+		if (r != 1)
+			return r;
 	} else {
 		size = xsize_t(st.st_size);
 		if (size == 0) {

@@ -813,6 +855,17 @@ static int add_excludes(const char *fname, const char *base, int baselen,
 		}
 	}
 
+	add_excludes_from_buffer(buf, size, base, baselen, el);
+	return 0;
+}
+
+static int add_excludes_from_buffer(char *buf, size_t size,
+				    const char *base, int baselen,
+				    struct exclude_list *el)
+{
+	int i, lineno = 1;
+	char *entry;
+
 	el->filebuf = buf;
 
 	if (skip_utf8_bom(&buf, size))

@@ -841,6 +894,23 @@ int add_excludes_from_file_to_list(const char *fname, const char *base,
 	return add_excludes(fname, base, baselen, el, istate, NULL);
 }
 
+int add_excludes_from_blob_to_list(
+	struct object_id *oid,
+	const char *base, int baselen,
+	struct exclude_list *el)
+{
+	char *buf;
+	size_t size;
+	int r;
+
+	r = do_read_blob(oid, NULL, &size, &buf);
+	if (r != 1)
+		return r;
+
+	add_excludes_from_buffer(buf, size, base, baselen, el);
+	return 0;
+}
+
 struct exclude_list *add_exclude_list(struct dir_struct *dir,
 				      int group_type, const char *src)
 {

index e371705..1bcf391 100644
@@ -256,6 +256,9 @@ extern struct exclude_list *add_exclude_list(struct dir_struct *dir,
 extern int add_excludes_from_file_to_list(const char *fname, const char *base, int baselen,
 					  struct exclude_list *el, struct  index_state *istate);
 extern void add_excludes_from_file(struct dir_struct *, const char *fname);
+extern int add_excludes_from_blob_to_list(struct object_id *oid,
+					  const char *base, int baselen,
+					  struct exclude_list *el);
 extern void parse_exclude_pattern(const char **string, int *patternlen, unsigned *flags, int *nowildcardlen);
 extern void add_exclude(const char *string, const char *base,
 			int baselen, struct exclude_list *el, int srcpos);

index 18f54cd..d3cd2bb 100644
@@ -65,4 +65,26 @@ extern void *oidmap_put(struct oidmap *map, void *entry);
  */
 extern void *oidmap_remove(struct oidmap *map, const struct object_id *key);
 
+
+struct oidmap_iter {
+	struct hashmap_iter h_iter;
+};
+
+static inline void oidmap_iter_init(struct oidmap *map, struct oidmap_iter *iter)
+{
+	hashmap_iter_init(&map->map, &iter->h_iter);
+}
+
+static inline void *oidmap_iter_next(struct oidmap_iter *iter)
+{
+	return hashmap_iter_next(&iter->h_iter);
+}
+
+static inline void *oidmap_iter_first(struct oidmap *map,
+				      struct oidmap_iter *iter)
+{
+	oidmap_iter_init(map, iter);
+	return oidmap_iter_next(iter);
+}
+
 #endif

index f1f874a..454c54f 100644
@@ -24,6 +24,16 @@ int oidset_insert(struct oidset *set, const struct object_id *oid)
 	return 0;
 }
 
+int oidset_remove(struct oidset *set, const struct object_id *oid)
+{
+	struct oidmap_entry *entry;
+
+	entry = oidmap_remove(&set->map, oid);
+	free(entry);
+
+	return (entry != NULL);
+}
+
 void oidset_clear(struct oidset *set)
 {
 	oidmap_free(&set->map, 1);

index f4c9e0f..783abce 100644
@@ -24,6 +24,12 @@ struct oidset {
 
 #define OIDSET_INIT { OIDMAP_INIT }
 
+
+static inline void oidset_init(struct oidset *set, size_t initial_size)
+{
+	return oidmap_init(&set->map, initial_size);
+}
+
 /**
  * Returns true iff `set` contains `oid`.
  */

@@ -39,9 +45,39 @@ int oidset_contains(const struct oidset *set, const struct object_id *oid);
 int oidset_insert(struct oidset *set, const struct object_id *oid);
 
 /**
+ * Remove the oid from the set.
+ *
+ * Returns 1 if the oid was present in the set, 0 otherwise.
+ */
+int oidset_remove(struct oidset *set, const struct object_id *oid);
+
+/**
  * Remove all entries from the oidset, freeing any resources associated with
  * it.
  */
 void oidset_clear(struct oidset *set);
 
+struct oidset_iter {
+	struct oidmap_iter m_iter;
+};
+
+static inline void oidset_iter_init(struct oidset *set,
+				    struct oidset_iter *iter)
+{
+	oidmap_iter_init(&set->map, &iter->m_iter);
+}
+
+static inline struct object_id *oidset_iter_next(struct oidset_iter *iter)
+{
+	struct oidmap_entry *e = oidmap_iter_next(&iter->m_iter);
+	return e ? &e->oid : NULL;
+}
+
+static inline struct object_id *oidset_iter_first(struct oidset *set,
+						  struct oidset_iter *iter)
+{
+	oidset_iter_init(set, iter);
+	return oidset_iter_next(iter);
+}
+
 #endif /* OIDSET_H */

148 lines not on this page · raw message

50 lines not on this page · raw message

401 lines not on this page · raw message

77 lines not on this page · raw message

182 lines not on this page · raw message

index 0cebf85..aa618d7 100644
@@ -8,4 +8,15 @@ void traverse_commit_list(struct rev_info *, show_commit_fn, show_object_fn, voi
 typedef void (*show_edge_fn)(struct commit *);
 void mark_edges_uninteresting(struct rev_info *, show_edge_fn);
 
-#endif
+struct oidset;
+struct list_objects_filter_options;
+
+void traverse_commit_list_filtered(
+	struct list_objects_filter_options *filter_options,
+	struct rev_info *revs,
+	show_commit_fn show_commit,
+	show_object_fn show_object,
+	void *show_data,
+	struct oidset *omitted);
+
+#endif /* LIST_OBJECTS_H */

index df8abe9..f34461d 100644
@@ -38,6 +38,7 @@ struct object_array {
  * http-push.c:                            16-----19
  * commit.c:                               16-----19
  * sha1_name.c:                                     20
+ * list-objects-filter.c:                             21
  * builtin/fsck.c:  0--3
  */
 #define FLAG_BITS  27

118 lines not on this page · raw message

index 6e77dfd..e16722f 100644
@@ -15,6 +15,8 @@
 #include "diff.h"
 #include "revision.h"
 #include "list-objects.h"
+#include "list-objects-filter.h"
+#include "list-objects-filter-options.h"
 #include "pack-objects.h"
 #include "progress.h"
 #include "refs.h"

@@ -79,6 +81,9 @@ static unsigned long cache_max_small_delta_size = 1000;
 
 static unsigned long window_memory_limit = 0;
 
+static struct list_objects_filter_options filter_options;
+static int arg_ignore_missing;
+
 /*
  * stats
  */

@@ -2547,6 +2552,15 @@ static void show_commit(struct commit *commit, void *data)
 
 static void show_object(struct object *obj, const char *name, void *data)
 {
+	/*
+	 * Quietly ignore missing objects when they are expected.  This
+	 * avoids staging them and getting an odd error later.  If we are
+	 * not expecting them, stage it and let the normal error handling
+	 * deal with it.
+	 */
+	if (arg_ignore_missing && !has_object_file(&obj->oid))
+		return;
+
 	add_preferred_base_object(name);
 	add_object_entry(obj->oid.hash, obj->type, name, 0);
 	obj->flags |= OBJECT_ADDED;

@@ -2816,7 +2830,10 @@ static void get_object_list(int ac, const char **av)
 	if (prepare_revision_walk(&revs))
 		die("revision walk setup failed");
 	mark_edges_uninteresting(&revs, show_edge);
-	traverse_commit_list(&revs, show_commit, show_object, NULL);
+
+	traverse_commit_list_filtered(&filter_options, &revs,
+				      show_commit, show_object, NULL,
+				      NULL);
 
 	if (unpack_unreachable_expiration) {
 		revs.ignore_missing_links = 1;

@@ -2952,6 +2969,9 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 			 N_("use a bitmap index if available to speed up counting objects")),
 		OPT_BOOL(0, "write-bitmap-index", &write_bitmap_index,
 			 N_("write a bitmap index together with the pack index")),
+		OPT_PARSE_LIST_OBJECTS_FILTER(&filter_options),
+		OPT_BOOL(0, "filter-ignore-missing", &arg_ignore_missing,
+			 N_("ignore and omit missing objects from packfile")),
 		OPT_END(),
 	};
 

@@ -3028,6 +3048,12 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 	if (!rev_list_all || !rev_list_reflog || !rev_list_index)
 		unpack_unreachable_expiration = 0;
 
+	if (filter_options.choice) {
+		if (!pack_to_stdout)
+			die("cannot use filtering with an indexable pack.");
+		use_bitmap_index = 0;
+	}
+
 	/*
 	 * "soft" reasons not to use bitmaps - for on-disk repack by default we want
 	 *