@@ -9,7 +9,7 @@ git-backfill - Download missing objects in a partial clone
SYNOPSIS
--------
[verse]
-'git backfill' [--batch-size=<n>]
+'git backfill' [--batch-size=<n>] [--[no-]sparse]
DESCRIPTION
-----------
@@ -54,6 +54,10 @@ OPTIONS
blobs seen at a given path. The default minimum batch size is
50,000.
+--[no-]sparse::
+ Only download objects if they appear at a path that matches the
+ current sparse-checkout.
+
SEE ALSO
--------
linkgit:git-clone[1].
@@ -56,6 +56,14 @@ better off using the revision walk API instead.
the revision walk so that the walk emits commits marked with the
`UNINTERESTING` flag.
+`pl`::
+ This pattern list pointer allows focusing the path-walk search to
+ a set of patterns, only emitting paths that match the given
+ patterns. See linkgit:gitignore[5] or
+ linkgit:git-sparse-checkout[1] for details about pattern lists.
+ When the pattern list uses cone-mode patterns, then the path-walk
+ API can prune the set of paths it walks to improve performance.
+
Examples
--------
@@ -4,6 +4,7 @@
#include "parse-options.h"
#include "repository.h"
#include "commit.h"
+#include "dir.h"
#include "hex.h"
#include "tree.h"
#include "tree-walk.h"
@@ -21,7 +22,7 @@
#include "path-walk.h"
static const char * const builtin_backfill_usage[] = {
- N_("git backfill [--batch-size=<n>]"),
+ N_("git backfill [--batch-size=<n>] [--[no-]sparse]"),
NULL
};
@@ -29,6 +30,7 @@ struct backfill_context {
struct repository *repo;
struct oid_array current_batch;
size_t min_batch_size;
+ int sparse;
};
static void backfill_context_clear(struct backfill_context *ctx)
@@ -84,6 +86,14 @@ static int do_backfill(struct backfill_context *ctx)
struct path_walk_info info = PATH_WALK_INFO_INIT;
int ret;
+ if (ctx->sparse) {
+ CALLOC_ARRAY(info.pl, 1);
+ if (get_sparse_checkout_patterns(info.pl)) {
+ path_walk_info_clear(&info);
+ return error(_("problem loading sparse-checkout"));
+ }
+ }
+
repo_init_revisions(ctx->repo, &revs, "");
handle_revision_arg("HEAD", &revs, 0, 0);
@@ -112,10 +122,13 @@ int cmd_backfill(int argc, const char **argv, const char *prefix, struct reposit
.repo = repo,
.current_batch = OID_ARRAY_INIT,
.min_batch_size = 50000,
+ .sparse = 0,
};
struct option options[] = {
OPT_INTEGER(0, "min-batch-size", &ctx.min_batch_size,
N_("Minimum number of objects to request at a time")),
+ OPT_BOOL(0, "sparse", &ctx.sparse,
+ N_("Restrict the missing objects to the current sparse-checkout")),
OPT_END(),
};
@@ -1088,10 +1088,6 @@ static void invalidate_directory(struct untracked_cache *uc,
dir->dirs[i]->recurse = 0;
}
-static int add_patterns_from_buffer(char *buf, size_t size,
- const char *base, int baselen,
- struct pattern_list *pl);
-
/* Flags for add_patterns() */
#define PATTERN_NOFOLLOW (1<<0)
@@ -1181,9 +1177,9 @@ static int add_patterns(const char *fname, const char *base, int baselen,
return 0;
}
-static int add_patterns_from_buffer(char *buf, size_t size,
- const char *base, int baselen,
- struct pattern_list *pl)
+int add_patterns_from_buffer(char *buf, size_t size,
+ const char *base, int baselen,
+ struct pattern_list *pl)
{
char *orig = buf;
int i, lineno = 1;
@@ -467,6 +467,9 @@ void add_patterns_from_file(struct dir_struct *, const char *fname);
int add_patterns_from_blob_to_list(struct object_id *oid,
const char *base, int baselen,
struct pattern_list *pl);
+int add_patterns_from_buffer(char *buf, size_t size,
+ const char *base, int baselen,
+ struct pattern_list *pl);
void parse_path_pattern(const char **string, int *patternlen, unsigned *flags, int *nowildcardlen);
void add_pattern(const char *string, const char *base,
int baselen, struct pattern_list *pl, int srcpos);
@@ -12,6 +12,7 @@
#include "object.h"
#include "oid-array.h"
#include "prio-queue.h"
+#include "repository.h"
#include "revision.h"
#include "string-list.h"
#include "strmap.h"
@@ -173,6 +174,23 @@ static int add_tree_entries(struct path_walk_context *ctx,
if (type == OBJ_TREE)
strbuf_addch(&path, '/');
+ if (ctx->info->pl) {
+ int dtype;
+ enum pattern_match_result match;
+ match = path_matches_pattern_list(path.buf, path.len,
+ path.buf + base_len, &dtype,
+ ctx->info->pl,
+ ctx->repo->index);
+
+ if (ctx->info->pl->use_cone_patterns &&
+ match == NOT_MATCHED)
+ continue;
+ else if (!ctx->info->pl->use_cone_patterns &&
+ type == OBJ_BLOB &&
+ match != MATCHED)
+ continue;
+ }
+
if (!(list = strmap_get(&ctx->paths_to_lists, path.buf))) {
CALLOC_ARRAY(list, 1);
list->type = type;
@@ -583,10 +601,10 @@ void path_walk_info_init(struct path_walk_info *info)
memcpy(info, &empty, sizeof(empty));
}
-void path_walk_info_clear(struct path_walk_info *info UNUSED)
+void path_walk_info_clear(struct path_walk_info *info)
{
- /*
- * This destructor is empty for now, as info->revs
- * is not owned by 'struct path_walk_info'.
- */
+ if (info->pl) {
+ clear_pattern_list(info->pl);
+ free(info->pl);
+ }
}
@@ -6,6 +6,7 @@
struct rev_info;
struct oid_array;
+struct pattern_list;
/**
* The type of a function pointer for the method that is called on a list of
@@ -48,6 +49,16 @@ struct path_walk_info {
* walk the children of such trees.
*/
int prune_all_uninteresting;
+
+ /**
+ * Specify a sparse-checkout definition to match our paths to. Do not
+ * walk outside of this sparse definition. If the patterns are in
+ * cone mode, then the search may prune directories that are outside
+ * of the cone. If not in cone mode, then all tree paths will be
+ * explored but the path_fn will only be called when the path matches
+ * the sparse-checkout patterns.
+ */
+ struct pattern_list *pl;
};
#define PATH_WALK_INFO_INIT { \
@@ -1,6 +1,7 @@
#define USE_THE_REPOSITORY_VARIABLE
#include "test-tool.h"
+#include "dir.h"
#include "environment.h"
#include "hex.h"
#include "object-name.h"
@@ -9,6 +10,7 @@
#include "revision.h"
#include "setup.h"
#include "parse-options.h"
+#include "strbuf.h"
#include "path-walk.h"
#include "oid-array.h"
@@ -65,7 +67,7 @@ static int emit_block(const char *path, struct oid_array *oids,
int cmd__path_walk(int argc, const char **argv)
{
- int res;
+ int res, stdin_pl = 0;
struct rev_info revs = REV_INFO_INIT;
struct path_walk_info info = PATH_WALK_INFO_INIT;
struct path_walk_test_data data = { 0 };
@@ -80,6 +82,8 @@ int cmd__path_walk(int argc, const char **argv)
N_("toggle inclusion of tree objects")),
OPT_BOOL(0, "prune", &info.prune_all_uninteresting,
N_("toggle pruning of uninteresting paths")),
+ OPT_BOOL(0, "stdin-pl", &stdin_pl,
+ N_("read a pattern list over stdin")),
OPT_END(),
};
@@ -99,6 +103,17 @@ int cmd__path_walk(int argc, const char **argv)
info.path_fn = emit_block;
info.path_fn_data = &data;
+ if (stdin_pl) {
+ struct strbuf in = STRBUF_INIT;
+ CALLOC_ARRAY(info.pl, 1);
+
+ info.pl->use_cone_patterns = 1;
+
+ strbuf_fread(&in, 2048, stdin);
+ add_patterns_from_buffer(in.buf, in.len, "", 0, info.pl);
+ strbuf_release(&in);
+ }
+
res = walk_objects_by_path(&info);
printf("commits:%" PRIuMAX "\n"
@@ -107,6 +122,11 @@ int cmd__path_walk(int argc, const char **argv)
"tags:%" PRIuMAX "\n",
data.commit_nr, data.tree_nr, data.blob_nr, data.tag_nr);
+ if (info.pl) {
+ clear_pattern_list(info.pl);
+ free(info.pl);
+ }
+
release_revisions(&revs);
return res;
}
@@ -77,6 +77,61 @@ test_expect_success 'do partial clone 2, backfill min batch size' '
test_line_count = 0 revs2
'
+test_expect_success 'backfill --sparse' '
+ git clone --sparse --filter=blob:none \
+ --single-branch --branch=main \
+ "file://$(pwd)/srv.bare" backfill3 &&
+
+ # Initial checkout includes four files at root.
+ git -C backfill3 rev-list --quiet --objects --missing=print HEAD >missing &&
+ test_line_count = 44 missing &&
+
+ # Initial sparse-checkout is just the files at root, so we get the
+ # older versions of the four files at tip.
+ GIT_TRACE2_EVENT="$(pwd)/sparse-trace1" git \
+ -C backfill3 backfill --sparse &&
+ test_trace2_data promisor fetch_count 4 <sparse-trace1 &&
+ test_trace2_data path-walk paths 5 <sparse-trace1 &&
+ git -C backfill3 rev-list --quiet --objects --missing=print HEAD >missing &&
+ test_line_count = 40 missing &&
+
+ # Expand the sparse-checkout to include 'd' recursively. This
+ # engages the algorithm to skip the trees for 'a'. Note that
+ # the "sparse-checkout set" command downloads the objects at tip
+ # to satisfy the current checkout.
+ git -C backfill3 sparse-checkout set d &&
+ GIT_TRACE2_EVENT="$(pwd)/sparse-trace2" git \
+ -C backfill3 backfill --sparse &&
+ test_trace2_data promisor fetch_count 8 <sparse-trace2 &&
+ test_trace2_data path-walk paths 15 <sparse-trace2 &&
+ git -C backfill3 rev-list --quiet --objects --missing=print HEAD >missing &&
+ test_line_count = 24 missing
+'
+
+test_expect_success 'backfill --sparse without cone mode' '
+ git clone --no-checkout --filter=blob:none \
+ --single-branch --branch=main \
+ "file://$(pwd)/srv.bare" backfill4 &&
+
+ # No blobs yet
+ git -C backfill4 rev-list --quiet --objects --missing=print HEAD >missing &&
+ test_line_count = 48 missing &&
+
+ # Define sparse-checkout by filename regardless of parent directory.
+ # This downloads 6 blobs to satisfy the checkout.
+ git -C backfill4 sparse-checkout set --no-cone "**/file.1.txt" &&
+ git -C backfill4 checkout main &&
+
+ GIT_TRACE2_EVENT="$(pwd)/no-cone-trace1" git \
+ -C backfill4 backfill --sparse &&
+ test_trace2_data promisor fetch_count 6 <no-cone-trace1 &&
+
+ # This walk needed to visit all directories to search for these paths.
+ test_trace2_data path-walk paths 12 <no-cone-trace1 &&
+ git -C backfill4 rev-list --quiet --objects --missing=print HEAD >missing &&
+ test_line_count = 36 missing
+'
+
. "$TEST_DIRECTORY"/lib-httpd.sh
start_httpd
@@ -176,6 +176,38 @@ test_expect_success 'branches and indexed objects mix well' '
test_cmp_sorted expect out
'
+test_expect_success 'base & topic, sparse' '
+ cat >patterns <<-EOF &&
+ /*
+ !/*/
+ /left/
+ EOF
+
+ test-tool path-walk --stdin-pl -- base topic <patterns >out &&
+
+ cat >expect <<-EOF &&
+ 0:commit::$(git rev-parse topic)
+ 0:commit::$(git rev-parse base)
+ 0:commit::$(git rev-parse base~1)
+ 0:commit::$(git rev-parse base~2)
+ 1:tree::$(git rev-parse topic^{tree})
+ 1:tree::$(git rev-parse base^{tree})
+ 1:tree::$(git rev-parse base~1^{tree})
+ 1:tree::$(git rev-parse base~2^{tree})
+ 2:blob:a:$(git rev-parse base~2:a)
+ 3:tree:left/:$(git rev-parse base:left)
+ 3:tree:left/:$(git rev-parse base~2:left)
+ 4:blob:left/b:$(git rev-parse base~2:left/b)
+ 4:blob:left/b:$(git rev-parse base:left/b)
+ blobs:3
+ commits:4
+ tags:0
+ trees:6
+ EOF
+
+ test_cmp_sorted expect out
+'
+
test_expect_success 'topic only' '
test-tool path-walk -- topic >out &&