list-objects: filter objects in traverse_commit_list

Create traverse_commit_list_filtered() and add filtering
interface to allow certain objects to be omitted from the
traversal.

Update traverse_commit_list() to be a wrapper for the above
with a null filter to minimize the number of callers that
needed to be changed.

Object filtering will be used in a future commit by rev-list
and pack-objects for partial clone and fetch to omit unwanted
objects from the result.

traverse_bitmap_commit_list() does not work with filtering.
If a packfile bitmap is present, it will not be used.  It
should be possible to extend such support in the future (at
least to simple filters that do not require object pathnames),
but that is beyond the scope of this patch series.

Signed-off-by: Jeff Hostetler <[email protected]>
Reviewed-by: Jonathan Tan <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: jeffhostetler

Makefile

@@ -807,6 +807,8 @@ 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

list-objects-filter-options.c

@@ -0,0 +1,81 @@
+#include "cache.h"
+#include "commit.h"
+#include "config.h"
+#include "revision.h"
+#include "argv-array.h"
+#include "list-objects.h"
+#include "list-objects-filter.h"
+#include "list-objects-filter-options.h"
+
+/*
+ * Parse value of the argument to the "filter" keword.
+ * On the command line this looks like:
+ *       --filter=<arg>
+ * and in the pack protocol as:
+ *       "filter" SP <arg>
+ *
+ * The filter keyword will be used by many commands.
+ * See Documentation/rev-list-options.txt for allowed values for <arg>.
+ *
+ * Capture the given arg as the "filter_spec".  This can be forwarded to
+ * subordinate commands when necessary.  We also "intern" the arg for
+ * the convenience of the current command.
+ */
+int parse_list_objects_filter(struct list_objects_filter_options *filter_options,
+			      const char *arg)
+{
+	const char *v0;
+
+	if (filter_options->choice)
+		die(_("multiple object filter types cannot be combined"));
+
+	filter_options->filter_spec = strdup(arg);
+
+	if (!strcmp(arg, "blob:none")) {
+		filter_options->choice = LOFC_BLOB_NONE;
+		return 0;
+	}
+
+	if (skip_prefix(arg, "blob:limit=", &v0)) {
+		if (!git_parse_ulong(v0, &filter_options->blob_limit_value))
+			die(_("invalid filter-spec expression '%s'"), arg);
+		filter_options->choice = LOFC_BLOB_LIMIT;
+		return 0;
+	}
+
+	if (skip_prefix(arg, "sparse:oid=", &v0)) {
+		struct object_context oc;
+		struct object_id sparse_oid;
+
+		/*
+		 * Try to parse <oid-expression> into an OID for the current
+		 * command, but DO NOT complain if we don't have the blob or
+		 * ref locally.
+		 */
+		if (!get_oid_with_context(v0, GET_OID_BLOB,
+					  &sparse_oid, &oc))
+			filter_options->sparse_oid_value = oiddup(&sparse_oid);
+		filter_options->choice = LOFC_SPARSE_OID;
+		return 0;
+	}
+
+	if (skip_prefix(arg, "sparse:path=", &v0)) {
+		filter_options->choice = LOFC_SPARSE_PATH;
+		filter_options->sparse_path_value = strdup(v0);
+		return 0;
+	}
+
+	die(_("invalid filter-spec expression '%s'"), arg);
+	return 0;
+}
+
+int opt_parse_list_objects_filter(const struct option *opt,
+				  const char *arg, int unset)
+{
+	struct list_objects_filter_options *filter_options = opt->value;
+
+	assert(arg);
+	assert(!unset);
+
+	return parse_list_objects_filter(filter_options, arg);
+}

list-objects-filter-options.h

@@ -0,0 +1,58 @@
+#ifndef LIST_OBJECTS_FILTER_OPTIONS_H
+#define LIST_OBJECTS_FILTER_OPTIONS_H
+
+#include "parse-options.h"
+
+/*
+ * The list of defined filters for list-objects.
+ */
+enum list_objects_filter_choice {
+	LOFC_DISABLED = 0,
+	LOFC_BLOB_NONE,
+	LOFC_BLOB_LIMIT,
+	LOFC_SPARSE_OID,
+	LOFC_SPARSE_PATH,
+	LOFC__COUNT /* must be last */
+};
+
+struct list_objects_filter_options {
+	/*
+	 * 'filter_spec' is the raw argument value given on the command line
+	 * or protocol request.  (The part after the "--keyword=".)  For
+	 * commands that launch filtering sub-processes, this value should be
+	 * passed to them as received by the current process.
+	 */
+	char *filter_spec;
+
+	/*
+	 * 'choice' is determined by parsing the filter-spec.  This indicates
+	 * the filtering algorithm to use.
+	 */
+	enum list_objects_filter_choice choice;
+
+	/*
+	 * Parsed values (fields) from within the filter-spec.  These are
+	 * choice-specific; not all values will be defined for any given
+	 * choice.
+	 */
+	struct object_id *sparse_oid_value;
+	char *sparse_path_value;
+	unsigned long blob_limit_value;
+};
+
+/* Normalized command line arguments */
+#define CL_ARG__FILTER "filter"
+
+int parse_list_objects_filter(
+	struct list_objects_filter_options *filter_options,
+	const char *arg);
+
+int opt_parse_list_objects_filter(const struct option *opt,
+				  const char *arg, int unset);
+
+#define OPT_PARSE_LIST_OBJECTS_FILTER(fo) \
+	{ OPTION_CALLBACK, 0, CL_ARG__FILTER, fo, N_("args"), \
+	  N_("object filtering"), PARSE_OPT_NONEG, \
+	  opt_parse_list_objects_filter }
+
+#endif /* LIST_OBJECTS_FILTER_OPTIONS_H */