Merge branch 'jh/object-filtering'

In preparation for implementing narrow/partial clone, the object
walking machinery has been taught a way to tell it to "filter" some
objects from enumeration.

* jh/object-filtering:
  rev-list: support --no-filter argument
  list-objects-filter-options: support --no-filter
  list-objects-filter-options: fix 'keword' typo in comment
  pack-objects: add list-objects filtering
  rev-list: add list-objects filtering support
  list-objects: filter objects in traverse_commit_list
  oidset: add iterator methods to oidset
  oidmap: add oidmap iterator methods
  dir: allow exclusions from blob in addition to file

Author: gitster

Documentation/git-pack-objects.txt

@@ -12,7 +12,8 @@ SYNOPSIS
 'git pack-objects' [-q | --progress | --all-progress] [--all-progress-implied]
 	[--no-reuse-delta] [--delta-base-offset] [--non-empty]
 	[--local] [--incremental] [--window=<n>] [--depth=<n>]
-	[--revs [--unpacked | --all]] [--stdout | base-name]
+	[--revs [--unpacked | --all]]
+	[--stdout [--filter=<filter-spec>] | base-name]
 	[--shallow] [--keep-true-parents] < object-list
 
 
@@ -236,6 +237,25 @@ So does `git bundle` (see linkgit:git-bundle[1]) when it creates a bundle.
 	With this option, parents that are hidden by grafts are packed
 	nevertheless.
 
+--filter=<filter-spec>::
+	Requires `--stdout`.  Omits certain objects (usually blobs) from
+	the resulting packfile.  See linkgit:git-rev-list[1] for valid
+	`<filter-spec>` forms.
+
+--no-filter::
+	Turns off any previous `--filter=` argument.
+
+--missing=<missing-action>::
+	A debug option to help with future "partial clone" development.
+	This option specifies how missing objects are handled.
++
+The form '--missing=error' requests that pack-objects stop with an error if
+a missing object is encountered.  This is the default action.
++
+The form '--missing=allow-any' will allow object traversal to continue
+if a missing object is encountered.  Missing objects will silently be
+omitted from the results.
+
 SEE ALSO
 --------
 linkgit:git-rev-list[1]

Documentation/git-rev-list.txt

@@ -47,7 +47,9 @@ SYNOPSIS
 	     [ --fixed-strings | -F ]
 	     [ --date=<format>]
 	     [ [ --objects | --objects-edge | --objects-edge-aggressive ]
-	       [ --unpacked ] ]
+	       [ --unpacked ]
+	       [ --filter=<filter-spec> [ --filter-print-omitted ] ] ]
+	     [ --missing=<missing-action> ]
 	     [ --pretty | --header ]
 	     [ --bisect ]
 	     [ --bisect-vars ]

Documentation/rev-list-options.txt

@@ -706,6 +706,47 @@ 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.  n may be zero.  The suffixes k, m, and g can be used to name
+units in KiB, MiB, or GiB.  For example, 'blob:limit=1k' is the same
+as 'blob:limit=1024'.
++
+The form '--filter=sparse:oid=<blob-ish>' uses a sparse-checkout
+specification contained in the blob (or blob-expression) '<blob-ish>'
+to omit blobs that would not be not required for a sparse checkout on
+the requested refs.
++
+The form '--filter=sparse:path=<path>' similarly uses a sparse-checkout
+specification contained in <path>.
+
+--no-filter::
+	Turn off any previous `--filter=` argument.
+
+--filter-print-omitted::
+	Only useful with `--filter=`; prints a list of the objects omitted
+	by the filter.	Object IDs are prefixed with a ``~'' character.
+
+--missing=<missing-action>::
+	A debug option to help with future "partial clone" development.
+	This option specifies how missing objects are handled.
++
+The form '--missing=error' requests that rev-list stop with an error if
+a missing object is encountered.  This is the default action.
++
+The form '--missing=allow-any' will allow object traversal to continue
+if a missing object is encountered.  Missing objects will silently be
+omitted from the results.
++
+The form '--missing=print' is like 'allow-any', but will also print a
+list of the missing objects.  Object IDs are prefixed with a ``?'' character.
 endif::git-rev-list[]
 
 --no-walk[=(sorted|unsorted)]::

Makefile

@@ -811,6 +811,8 @@ LIB_OBJS += levenshtein.o
 LIB_OBJS += line-log.o
 LIB_OBJS += line-range.o
 LIB_OBJS += list-objects.o
+LIB_OBJS += list-objects-filter.o
+LIB_OBJS += list-objects-filter-options.o
 LIB_OBJS += ll-merge.o
 LIB_OBJS += lockfile.o
 LIB_OBJS += log-tree.o

builtin/pack-objects.c

@@ -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 +81,15 @@ static unsigned long cache_max_small_delta_size = 1000;
 
 static unsigned long window_memory_limit = 0;
 
+static struct list_objects_filter_options filter_options;
+
+enum missing_action {
+	MA_ERROR = 0,    /* fail if any missing objects are encountered */
+	MA_ALLOW_ANY,    /* silently allow ALL missing objects */
+};
+static enum missing_action arg_missing_action;
+static show_object_fn fn_show_object;
+
 /*
  * stats
  */
@@ -2553,6 +2564,42 @@ static void show_object(struct object *obj, const char *name, void *data)
 	obj->flags |= OBJECT_ADDED;
 }
 
+static void show_object__ma_allow_any(struct object *obj, const char *name, void *data)
+{
+	assert(arg_missing_action == MA_ALLOW_ANY);
+
+	/*
+	 * Quietly ignore ALL missing objects.  This avoids problems with
+	 * staging them now and getting an odd error later.
+	 */
+	if (!has_object_file(&obj->oid))
+		return;
+
+	show_object(obj, name, data);
+}
+
+static int option_parse_missing_action(const struct option *opt,
+				       const char *arg, int unset)
+{
+	assert(arg);
+	assert(!unset);
+
+	if (!strcmp(arg, "error")) {
+		arg_missing_action = MA_ERROR;
+		fn_show_object = show_object;
+		return 0;
+	}
+
+	if (!strcmp(arg, "allow-any")) {
+		arg_missing_action = MA_ALLOW_ANY;
+		fn_show_object = show_object__ma_allow_any;
+		return 0;
+	}
+
+	die(_("invalid value for --missing"));
+	return 0;
+}
+
 static void show_edge(struct commit *commit)
 {
 	add_preferred_base(&commit->object.oid);
@@ -2817,7 +2864,12 @@ 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);
+
+	if (!fn_show_object)
+		fn_show_object = show_object;
+	traverse_commit_list_filtered(&filter_options, &revs,
+				      show_commit, fn_show_object, NULL,
+				      NULL);
 
 	if (unpack_unreachable_expiration) {
 		revs.ignore_missing_links = 1;
@@ -2953,6 +3005,10 @@ 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),
+		{ OPTION_CALLBACK, 0, "missing", NULL, N_("action"),
+		  N_("handling for missing objects"), PARSE_OPT_NONEG,
+		  option_parse_missing_action },
 		OPT_END(),
 	};
 
@@ -3029,6 +3085,12 @@ 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 --filter without --stdout.");
+		use_bitmap_index = 0;
+	}
+
 	/*
 	 * "soft" reasons not to use bitmaps - for on-disk repack by default we want
 	 *

builtin/rev-list.c

@@ -4,6 +4,8 @@
 #include "diff.h"
 #include "revision.h"
 #include "list-objects.h"
+#include "list-objects-filter.h"
+#include "list-objects-filter-options.h"
 #include "pack.h"
 #include "pack-bitmap.h"
 #include "builtin.h"
@@ -12,6 +14,7 @@
 #include "bisect.h"
 #include "progress.h"
 #include "reflog-walk.h"
+#include "oidset.h"
 
 static const char rev_list_usage[] =
 "git rev-list [OPTION] <commit-id>... [ -- paths... ]\n"
@@ -55,6 +58,20 @@ static const char rev_list_usage[] =
 static struct progress *progress;
 static unsigned progress_counter;
 
+static struct list_objects_filter_options filter_options;
+static struct oidset omitted_objects;
+static int arg_print_omitted; /* print objects omitted by filter */
+
+static struct oidset missing_objects;
+enum missing_action {
+	MA_ERROR = 0,    /* fail if any missing objects are encountered */
+	MA_ALLOW_ANY,    /* silently allow ALL missing objects */
+	MA_PRINT,        /* print ALL missing objects in special section */
+};
+static enum missing_action arg_missing_action;
+
+#define DEFAULT_OIDSET_SIZE     (16*1024)
+
 static void finish_commit(struct commit *commit, void *data);
 static void show_commit(struct commit *commit, void *data)
 {
@@ -178,11 +195,31 @@ static void finish_commit(struct commit *commit, void *data)
 	free_commit_buffer(commit);
 }
 
+static inline void finish_object__ma(struct object *obj)
+{
+	switch (arg_missing_action) {
+	case MA_ERROR:
+		die("missing blob object '%s'", oid_to_hex(&obj->oid));
+		return;
+
+	case MA_ALLOW_ANY:
+		return;
+
+	case MA_PRINT:
+		oidset_insert(&missing_objects, &obj->oid);
+		return;
+
+	default:
+		BUG("unhandled missing_action");
+		return;
+	}
+}
+
 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))
-		die("missing blob object '%s'", oid_to_hex(&obj->oid));
+		finish_object__ma(obj);
 	if (info->revs->verify_objects && !obj->parsed && obj->type != OBJ_COMMIT)
 		parse_object(&obj->oid);
 }
@@ -269,6 +306,26 @@ static int show_object_fast(
 	return 1;
 }
 
+static inline int parse_missing_action_value(const char *value)
+{
+	if (!strcmp(value, "error")) {
+		arg_missing_action = MA_ERROR;
+		return 1;
+	}
+
+	if (!strcmp(value, "allow-any")) {
+		arg_missing_action = MA_ALLOW_ANY;
+		return 1;
+	}
+
+	if (!strcmp(value, "print")) {
+		arg_missing_action = MA_PRINT;
+		return 1;
+	}
+
+	return 0;
+}
+
 int cmd_rev_list(int argc, const char **argv, const char *prefix)
 {
 	struct rev_info revs;
@@ -335,6 +392,30 @@ 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.filter_spec);
+			continue;
+		}
+		if (!strcmp(arg, ("--no-" CL_ARG__FILTER))) {
+			list_objects_filter_release(&filter_options);
+			continue;
+		}
+		if (!strcmp(arg, "--filter-print-omitted")) {
+			arg_print_omitted = 1;
+			continue;
+		}
+
+		if (skip_prefix(arg, "--missing=", &arg) &&
+		    parse_missing_action_value(arg))
+			continue;
+
 		usage(rev_list_usage);
 
 	}
@@ -360,6 +441,9 @@ 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);
@@ -403,7 +487,31 @@ 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_omitted)
+		oidset_init(&omitted_objects, DEFAULT_OIDSET_SIZE);
+	if (arg_missing_action == MA_PRINT)
+		oidset_init(&missing_objects, DEFAULT_OIDSET_SIZE);
+
+	traverse_commit_list_filtered(
+		&filter_options, &revs, show_commit, show_object, &info,
+		(arg_print_omitted ? &omitted_objects : NULL));
+
+	if (arg_print_omitted) {
+		struct oidset_iter iter;
+		struct object_id *oid;
+		oidset_iter_init(&omitted_objects, &iter);
+		while ((oid = oidset_iter_next(&iter)))
+			printf("~%s\n", oid_to_hex(oid));
+		oidset_clear(&omitted_objects);
+	}
+	if (arg_missing_action == MA_PRINT) {
+		struct oidset_iter iter;
+		struct object_id *oid;
+		oidset_iter_init(&missing_objects, &iter);
+		while ((oid = oidset_iter_next(&iter)))
+			printf("?%s\n", oid_to_hex(oid));
+		oidset_clear(&missing_objects);
+	}
 
 	stop_progress(&progress);