git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH 10/13] rev-list: add list-objects filtering support

From
JHJeff Hostetler <git@jeffhostetler.com>
Date
Oct 24, 2017, 18:53 UTC
Message-ID
<20171024185332.57261-11-git@jeffhostetler.com>
In-Reply-To
<20171024185332.57261-1-git@jeffhostetler.com>
From: Jeff Hostetler <jeffhost@microsoft.com>

Teach rev-list to use the filtering provided by the traverse_commit_list_filtered() interface to omit unwanted objects from the result.

This feature is only enabled when one of the "--objects*" options are used.

Furthermore, when the "--filter-print-omitted" option is used, the omitted objects are printed at the end. These are marked with a "~". This option can be combined with "--quiet" to get a list of just the omitted objects.

Signed-off-by: Jeff Hostetler <jeffhost@microsoft.com>
---
 Documentation/git-rev-list.txt     |  5 ++-
 Documentation/rev-list-options.txt | 30 ++++++++++++++
 builtin/rev-list.c                 | 84 +++++++++++++++++++++++++++++++++++++-
 3 files changed, 116 insertions(+), 3 deletions(-)
diff --git a/Documentation/git-rev-list.txt b/Documentation/git-rev-list.txt
index ef22f17..6d2e60d 100644
--- a/Documentation/git-rev-list.txt
+++ b/Documentation/git-rev-list.txt
@@ -47,7 +47,10 @@ SYNOPSIS
 	     [ --fixed-strings | -F ]
 	     [ --date=<format>]
 	     [ [ --objects | --objects-edge | --objects-edge-aggressive ]
-	       [ --unpacked ] ]
+	       [ --unpacked ]
+	       [ --filter=<filter-spec> ] ]
+	     [ --filter-print-missing ]
+	     [ --filter-print-omitted ]
 	     [ --pretty | --header ]
 	     [ --bisect ]
 	     [ --bisect-vars ]
diff --git a/Documentation/rev-list-options.txt b/Documentation/rev-list-options.txt
index 7d860bf..88f8878 100644
--- a/Documentation/rev-list-options.txt
+++ b/Documentation/rev-list-options.txt
@@ -706,6 +706,36 @@ ifdef::git-rev-list[]
 --unpacked::
 	Only useful with `--objects`; print the object IDs that are not
 	in packs.
+
+--filter=<filter-spec>::
+	Only useful with one of the `--objects*`; omits objects (usually
+	blobs) from the list of printed objects.  The '<filter-spec>'
+	may be one of the following:
++
+The form '--filter=blob:none' omits all blobs.
++
+The form '--filter=blob:limit=<n>[kmg]' omits blobs larger than n bytes
+or units.  The value may be zero.  Special files matching '.git*' are
+alwayse included, regardless of size.
++
+The form '--filter=sparse:oid=<oid-ish>' uses a sparse-checkout
+specification contained in the object (or the object that the expression
+evaluates to) to omit blobs not required by the corresponding sparse
+checkout.
++
+The form '--filter=sparse:path=<path>' similarly uses a sparse-checkout
+specification contained in <path>.
+
+--filter-print-missing::
+	Prints a list of the missing objects for the requested traversal.
+	Object IDs are prefixed with a ``?'' character.  The object type
+	is printed after the ID.  This may be used with or without any of
+	the above filtering options.
+
+--filter-print-omitted::
+	Only useful with one of the above `--filter*`; prints a list
+	of the omitted objects.  Object IDs are prefixed with a ``~''
+	character.
 endif::git-rev-list[]
 
 --no-walk[=(sorted|unsorted)]::
diff --git a/builtin/rev-list.c b/builtin/rev-list.c
index c1c74d4..7a0353f 100644
--- a/builtin/rev-list.c
+++ b/builtin/rev-list.c
@@ -12,6 +12,7 @@
 #include "bisect.h"
 #include "progress.h"
 #include "reflog-walk.h"
+#include "partial-clone-utils.h"
 
 static const char rev_list_usage[] =
 "git rev-list [OPTION] <commit-id>... [ -- paths... ]\n"
@@ -54,6 +55,11 @@ static const char rev_list_usage[] =
 
 static struct progress *progress;
 static unsigned progress_counter;
+static struct list_objects_filter_options filter_options;
+static struct oidmap missing_objects;
+static int arg_print_missing;
+static int arg_print_omitted;
+#define DEFAULT_MAP_SIZE (16*1024)
 
 static void finish_commit(struct commit *commit, void *data);
 static void show_commit(struct commit *commit, void *data)
@@ -181,8 +187,26 @@ static void finish_commit(struct commit *commit, void *data)
 static void finish_object(struct object *obj, const char *name, void *cb_data)
 {
 	struct rev_list_info *info = cb_data;
-	if (obj->type == OBJ_BLOB && !has_object_file(&obj->oid))
+	if (obj->type == OBJ_BLOB && !has_object_file(&obj->oid)) {
+		if (arg_print_missing) {
+			list_objects_filter_map_insert(
+				&missing_objects, &obj->oid, name, obj->type);
+			return;
+		}
+
+		/*
+		 * Relax consistency checks when we expect missing
+		 * objects because of partial-clone or a previous
+		 * partial-fetch.
+		 *
+		 * Note that this is independent of any filtering that
+		 * we are doing in this run.
+		 */
+		if (is_partial_clone_registered())
+			return;
+
 		die("missing blob object '%s'", oid_to_hex(&obj->oid));
+	}
 	if (info->revs->verify_objects && !obj->parsed && obj->type != OBJ_COMMIT)
 		parse_object(&obj->oid);
 }
@@ -202,6 +226,22 @@ static void show_edge(struct commit *commit)
 	printf("-%s\n", oid_to_hex(&commit->object.oid));
 }
 
+static void print_omitted_object(int i, int i_limit, struct list_objects_filter_map_entry *e, void *cb_data)
+{
+	/* struct rev_list_info *info = cb_data; */
+	const char *tn = typename(e->type);
+
+	printf("~%s %s\n", oid_to_hex(&e->entry.oid), tn);
+}
+
+static void print_missing_object(int i, int i_limit, struct list_objects_filter_map_entry *e, void *cb_data)
+{
+	/* struct rev_list_info *info = cb_data; */
+	const char *tn = typename(e->type);
+
+	printf("?%s %s\n", oid_to_hex(&e->entry.oid), tn);
+}
+
 static void print_var_str(const char *var, const char *val)
 {
 	printf("%s='%s'\n", var, val);
@@ -335,6 +375,26 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix)
 			show_progress = arg;
 			continue;
 		}
+
+		if (skip_prefix(arg, ("--" CL_ARG__FILTER "="), &arg)) {
+			parse_list_objects_filter(&filter_options, arg);
+			if (filter_options.choice && !revs.blob_objects)
+				die(_("object filtering requires --objects"));
+			if (filter_options.choice == LOFC_SPARSE_OID &&
+			    !filter_options.sparse_oid_value)
+				die(_("invalid sparse value '%s'"),
+				    filter_options.raw_value);
+			continue;
+		}
+		if (!strcmp(arg, "--filter-print-missing")) {
+			arg_print_missing = 1;
+			continue;
+		}
+		if (!strcmp(arg, "--filter-print-omitted")) {
+			arg_print_omitted = 1;
+			continue;
+		}
+		
 		usage(rev_list_usage);
 
 	}
@@ -360,6 +420,9 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix)
 	if (revs.show_notes)
 		die(_("rev-list does not support display of notes"));
 
+	if (filter_options.choice && use_bitmap_index)
+		die(_("cannot combine --use-bitmap-index with object filtering"));
+
 	save_commit_buffer = (revs.verbose_header ||
 			      revs.grep_filter.pattern_list ||
 			      revs.grep_filter.header_list);
@@ -404,7 +467,24 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix)
 			return show_bisect_vars(&info, reaches, all);
 	}
 
-	traverse_commit_list(&revs, show_commit, show_object, &info);
+	if (arg_print_missing) {
+		memset(&missing_objects, 0, sizeof(missing_objects));
+		oidmap_init(&missing_objects, DEFAULT_MAP_SIZE);
+	}
+
+	if (filter_options.choice)
+		traverse_commit_list_filtered(&filter_options, &revs,
+			show_commit, show_object,
+			(arg_print_omitted ? print_omitted_object : NULL),
+			&info);
+	else
+		traverse_commit_list(&revs, show_commit, show_object, &info);
+
+	if (arg_print_missing) {
+		list_objects_filter_map_foreach(&missing_objects,
+						print_missing_object, &info);
+		oidmap_free(&missing_objects, 1);
+	}
 
 	stop_progress(&progress);
 

-- 
2.9.3
Previous: Jeff HostetlerNext: Jonathan Tan
Message 14 of 37 in “WIP Partial clone part 1: object filtering”
  1. 00/13 WIP Partial clone part 1: object filteringJeff Hostetler, Oct 24, 2017
  2. 02/13 list-objects-filter-map: extend oidmap to collect omitted objectsJeff Hostetler, Oct 24, 2017
  3. Junio C HamanoOct 25, 2017
  4. Jeff HostetlerOct 25, 2017
  5. Junio C HamanoOct 26, 2017
  6. 06/13 list-objects-filter-sparse: add sparse filterJeff Hostetler, Oct 24, 2017
  7. 08/13 list-objects: add traverse_commit_list_filtered methodJeff Hostetler, Oct 24, 2017
  8. Jonathan TanOct 25, 2017
  9. Jeff HostetlerOct 25, 2017
  10. 11/13 t6112: rev-list object filtering testJeff Hostetler, Oct 24, 2017
  11. 05/13 list-objects-filter-blobs-limit: add large blob filteringJeff Hostetler, Oct 24, 2017
  12. 13/13 t5317: pack-objects object filtering testJeff Hostetler, Oct 24, 2017
  13. 12/13 pack-objects: add list-objects filteringJeff Hostetler, Oct 24, 2017
  14. 10/13 rev-list: add list-objects filtering supportJeff Hostetler, Oct 24, 2017
  15. Jonathan TanOct 25, 2017
  16. Jeff HostetlerOct 25, 2017
  17. 04/13 list-objects-filter-blobs-none: add filter to omit all blobsJeff Hostetler, Oct 24, 2017
  18. 09/13 extension.partialclone: introduce partial clone extensionJeff Hostetler, Oct 24, 2017
  19. 01/13 dir: allow exclusions from blob in addition to fileJeff Hostetler, Oct 24, 2017
  20. Eric SunshineOct 25, 2017
  21. Junio C HamanoOct 25, 2017
  22. Jeff HostetlerOct 25, 2017
  23. Junio C HamanoOct 26, 2017
  24. Jeff HostetlerOct 26, 2017
  25. 07/13 list-objects-filter-options: common argument parsingJeff Hostetler, Oct 24, 2017
  26. Jonathan TanOct 25, 2017
  27. Jeff HostetlerOct 25, 2017
  28. 03/13 list-objects: filter objects in traverse_commit_listJeff Hostetler, Oct 24, 2017
  29. Jonathan TanOct 25, 2017
  30. Jeff HostetlerOct 25, 2017
  31. Jonathan TanOct 25, 2017
  32. Junio C HamanoOct 25, 2017
  33. Jonathan TanOct 25, 2017
  34. Jeff HostetlerOct 25, 2017
  35. Junio C HamanoOct 26, 2017
  36. Junio C HamanoOct 26, 2017
  37. Jonathan NiederOct 30, 2017

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.