Merge branch 'backfill-revs' into cache-server

Author: derrickstolee

Documentation/git-backfill.adoc

@@ -63,9 +63,12 @@ OPTIONS
 	current sparse-checkout. If the sparse-checkout feature is enabled,
 	then `--sparse` is assumed and can be disabled with `--no-sparse`.
 
+You may also specify the commit limiting options from linkgit:git-rev-list[1].
+
 SEE ALSO
 --------
 linkgit:git-clone[1].
+linkgit:git-rev-list[1].
 
 GIT
 ---

builtin/backfill.c

@@ -35,6 +35,7 @@ struct backfill_context {
 	struct oid_array current_batch;
 	size_t min_batch_size;
 	int sparse;
+	struct rev_info revs;
 };
 
 static void backfill_context_clear(struct backfill_context *ctx)
@@ -80,7 +81,6 @@ static int fill_missing_blobs(const char *path UNUSED,
 
 static int do_backfill(struct backfill_context *ctx)
 {
-	struct rev_info revs;
 	struct path_walk_info info = PATH_WALK_INFO_INIT;
 	int ret;
 
@@ -92,13 +92,14 @@ static int do_backfill(struct backfill_context *ctx)
 		}
 	}
 
-	repo_init_revisions(ctx->repo, &revs, "");
-	handle_revision_arg("HEAD", &revs, 0, 0);
+	/* Walk from HEAD if otherwise unspecified. */
+	if (!ctx->revs.pending.nr)
+		handle_revision_arg("HEAD", &ctx->revs, 0, 0);
 
 	info.blobs = 1;
 	info.tags = info.commits = info.trees = 0;
 
-	info.revs = &revs;
+	info.revs = &ctx->revs;
 	info.path_fn = fill_missing_blobs;
 	info.path_fn_data = ctx;
 
@@ -109,7 +110,6 @@ static int do_backfill(struct backfill_context *ctx)
 		download_batch(ctx);
 
 	path_walk_info_clear(&info);
-	release_revisions(&revs);
 	return ret;
 }
 
@@ -121,6 +121,7 @@ int cmd_backfill(int argc, const char **argv, const char *prefix, struct reposit
 		.current_batch = OID_ARRAY_INIT,
 		.min_batch_size = 50000,
 		.sparse = 0,
+		.revs = REV_INFO_INIT,
 	};
 	struct option options[] = {
 		OPT_UNSIGNED(0, "min-batch-size", &ctx.min_batch_size,
@@ -134,7 +135,12 @@ int cmd_backfill(int argc, const char **argv, const char *prefix, struct reposit
 					 builtin_backfill_usage, options);
 
 	argc = parse_options(argc, argv, prefix, options, builtin_backfill_usage,
-			     0);
+			     PARSE_OPT_KEEP_UNKNOWN_OPT |
+			     PARSE_OPT_KEEP_ARGV0 |
+			     PARSE_OPT_KEEP_DASHDASH);
+
+	repo_init_revisions(repo, &ctx.revs, prefix);
+	argc = setup_revisions(argc, argv, &ctx.revs, NULL);
 
 	repo_config(repo, git_default_config, NULL);
 
@@ -143,5 +149,6 @@ int cmd_backfill(int argc, const char **argv, const char *prefix, struct reposit
 
 	result = do_backfill(&ctx);
 	backfill_context_clear(&ctx);
+	release_revisions(&ctx.revs);
 	return result;
 }

path-walk.c

@@ -62,6 +62,8 @@ struct path_walk_context {
 	 */
 	struct prio_queue path_stack;
 	struct strset path_stack_pushed;
+
+	unsigned exact_pathspecs:1;
 };
 
 static int compare_by_type(const void *one, const void *two, void *cb_data)
@@ -206,6 +208,49 @@ static int add_tree_entries(struct path_walk_context *ctx,
 				 match != MATCHED)
 				continue;
 		}
+		if (ctx->revs->prune_data.nr && ctx->exact_pathspecs) {
+			struct pathspec *pd = &ctx->revs->prune_data;
+			bool found = false;
+
+			for (int i = 0; i < pd->nr; i++) {
+				struct pathspec_item *item = &pd->items[i];
+
+				/*
+				 * Is this path a parent directory of
+				 * the pathspec item?
+				 */
+				if (path.len < (size_t)item->len &&
+				    !strncmp(path.buf, item->match, path.len) &&
+				    item->match[path.len - 1] == '/') {
+					found = true;
+					break;
+				}
+
+				/*
+				 * Or, is the pathspec an exact match?
+				 */
+				if (path.len == (size_t)item->len &&
+				    !strcmp(path.buf, item->match)) {
+					found = true;
+					break;
+				}
+
+				/*
+				 * Or, is the pathspec a directory prefix
+				 * match?
+				 */
+				if (path.len > (size_t)item->len &&
+				    !strncmp(path.buf, item->match, item->len) &&
+				    path.buf[item->len] == '/') {
+					found = true;
+					break;
+				}
+			}
+
+			/* Skip paths that do not match the prefix. */
+			if (!found)
+				continue;
+		}
 
 		add_path_to_list(ctx, path.buf, type, &entry.oid,
 				 !(o->flags & UNINTERESTING));
@@ -274,6 +319,13 @@ static int walk_path(struct path_walk_context *ctx,
 			return 0;
 	}
 
+	if (list->type == OBJ_BLOB &&
+	    ctx->revs->prune_data.nr &&
+	    !match_pathspec(ctx->repo->index, &ctx->revs->prune_data,
+			   path, strlen(path), 0,
+			   NULL, 0))
+		return 0;
+
 	/* Evaluate function pointer on this data, if requested. */
 	if ((list->type == OBJ_TREE && ctx->info->trees) ||
 	    (list->type == OBJ_BLOB && ctx->info->blobs) ||
@@ -481,6 +533,15 @@ int walk_objects_by_path(struct path_walk_info *info)
 	if (info->tags)
 		info->revs->tag_objects = 1;
 
+	if (ctx.revs->prune_data.nr) {
+		struct pathspec *pd = &ctx.revs->prune_data;
+
+		if (!pd->has_wildcard && !pd->magic)
+			ctx.exact_pathspecs = 1;
+		else
+			ctx.revs->prune = 0;
+	}
+
 	/* Insert a single list for the root tree into the paths. */
 	CALLOC_ARRAY(root_tree_list, 1);
 	root_tree_list->type = OBJ_TREE;

revision.h

@@ -4,6 +4,7 @@
 #include "commit.h"
 #include "grep.h"
 #include "notes.h"
+#include "object-name.h"
 #include "oidset.h"
 #include "pretty.h"
 #include "diff.h"