list-objects-filter: implement composite filters

Allow combining filters such that only objects accepted by all filters
are shown. The motivation for this is to allow getting directory
listings without also fetching blobs. This can be done by combining
blob:none with tree:<depth>. There are massive repositories that have
larger-than-expected trees - even if you include only a single commit.

A combined filter supports any number of subfilters, and is written in
the following form:

	combine:<filter 1>+<filter 2>+<filter 3>

Certain non-alphanumeric characters in each filter must be
URL-encoded.

For now, combined filters must be specified in this form. In a
subsequent commit, rev-list will support multiple --filter arguments
which will have the same effect as specifying one filter argument
starting with "combine:". The documentation will be updated in that
commit, as the URL-encoding scheme is in general not meant to be used
directly by the user, and it is better to describe the URL-encoding
feature in terms of the repeated flag.

Helped-by: Emily Shaffer <emilyshaffer@google.com>
Helped-by: Jeff Hostetler <git@jeffhostetler.com>
Helped-by: Johannes Schindelin <Johannes.Schindelin@gmx.de>
Helped-by: Jonathan Tan <jonathantanmy@google.com>
Helped-by: Junio C Hamano <gitster@pobox.com>
Signed-off-by: Matthew DeVore <matvore@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 104 insertions, 2 deletions

diff --git a/list-objects-filter-options.c b/list-objects-filter-options.c
index 7c3e397d29..75d0236ee2 100644
--- a/list-objects-filter-options.c
+++ b/list-objects-filter-options.c
@@ -6,6 +6,12 @@
 #include "list-objects.h"
 #include "list-objects-filter.h"
 #include "list-objects-filter-options.h"
+#include "url.h"
+
+static int parse_combine_filter(
+	struct list_objects_filter_options *filter_options,
+	const char *arg,
+	struct strbuf *errbuf);
 
 /*
  * Parse value of the argument to the "filter" keyword.
@@ -35,8 +41,6 @@ static int gently_parse_list_objects_filter(
 		return 1;
 	}
 
-	filter_options->filter_spec = strdup(arg);
-
 	if (!strcmp(arg, "blob:none")) {
 		filter_options->choice = LOFC_BLOB_NONE;
 		return 0;
@@ -77,6 +81,10 @@ static int gently_parse_list_objects_filter(
 				_("sparse:path filters support has been dropped"));
 		}
 		return 1;
+
+	} else if (skip_prefix(arg, "combine:", &v0)) {
+		return parse_combine_filter(filter_options, v0, errbuf);
+
 	}
 	/*
 	 * Please update _git_fetch() in git-completion.bash when you
@@ -89,10 +97,95 @@ static int gently_parse_list_objects_filter(
 	return 1;
 }
 
+static const char *RESERVED_NON_WS = "~`!@#$^&*()[]{}\\;'\",<>?";
+
+static int has_reserved_character(
+	struct strbuf *sub_spec, struct strbuf *errbuf)
+{
+	const char *c = sub_spec->buf;
+	while (*c) {
+		if (*c <= ' ' || strchr(RESERVED_NON_WS, *c)) {
+			strbuf_addf(
+				errbuf,
+				_("must escape char in sub-filter-spec: '%c'"),
+				*c);
+			return 1;
+		}
+		c++;
+	}
+
+	return 0;
+}
+
+static int parse_combine_subfilter(
+	struct list_objects_filter_options *filter_options,
+	struct strbuf *subspec,
+	struct strbuf *errbuf)
+{
+	size_t new_index = filter_options->sub_nr++;
+	char *decoded;
+	int result;
+
+	ALLOC_GROW(filter_options->sub, filter_options->sub_nr,
+		   filter_options->sub_alloc);
+	memset(&filter_options->sub[new_index], 0,
+	       sizeof(*filter_options->sub));
+
+	decoded = url_percent_decode(subspec->buf);
+
+	result = has_reserved_character(subspec, errbuf) ||
+		gently_parse_list_objects_filter(
+			&filter_options->sub[new_index], decoded, errbuf);
+
+	free(decoded);
+	return result;
+}
+
+static int parse_combine_filter(
+	struct list_objects_filter_options *filter_options,
+	const char *arg,
+	struct strbuf *errbuf)
+{
+	struct strbuf **subspecs = strbuf_split_str(arg, '+', 0);
+	size_t sub;
+	int result = 0;
+
+	if (!subspecs[0]) {
+		strbuf_addstr(errbuf, _("expected something after combine:"));
+		result = 1;
+		goto cleanup;
+	}
+
+	for (sub = 0; subspecs[sub] && !result; sub++) {
+		if (subspecs[sub + 1]) {
+			/*
+			 * This is not the last subspec. Remove trailing "+" so
+			 * we can parse it.
+			 */
+			size_t last = subspecs[sub]->len - 1;
+			assert(subspecs[sub]->buf[last] == '+');
+			strbuf_remove(subspecs[sub], last, 1);
+		}
+		result = parse_combine_subfilter(
+			filter_options, subspecs[sub], errbuf);
+	}
+
+	filter_options->choice = LOFC_COMBINE;
+
+cleanup:
+	strbuf_list_free(subspecs);
+	if (result) {
+		list_objects_filter_release(filter_options);
+		memset(filter_options, 0, sizeof(*filter_options));
+	}
+	return result;
+}
+
 int parse_list_objects_filter(struct list_objects_filter_options *filter_options,
 			      const char *arg)
 {
 	struct strbuf buf = STRBUF_INIT;
+	filter_options->filter_spec = strdup(arg);
 	if (gently_parse_list_objects_filter(filter_options, arg, &buf))
 		die("%s", buf.buf);
 	return 0;
@@ -129,8 +222,15 @@ void expand_list_objects_filter_spec(
 void list_objects_filter_release(
 	struct list_objects_filter_options *filter_options)
 {
+	size_t sub;
+
+	if (!filter_options)
+		return;
 	free(filter_options->filter_spec);
 	free(filter_options->sparse_oid_value);
+	for (sub = 0; sub < filter_options->sub_nr; sub++)
+		list_objects_filter_release(&filter_options->sub[sub]);
+	free(filter_options->sub);
 	memset(filter_options, 0, sizeof(*filter_options));
 }
 
@@ -174,6 +274,8 @@ void partial_clone_get_default_filter_spec(
 	 */
 	if (!core_partial_clone_filter_default)
 		return;
+
+	filter_options->filter_spec = strdup(core_partial_clone_filter_default);
 	gently_parse_list_objects_filter(filter_options,
 					 core_partial_clone_filter_default,
 					 &errbuf);