[PATCH v3 04/11] bundle-uri: parse bundle.heuristic=creationToken

From: Derrick Stolee via GitGitGadget <gitgitgadget@gmail.com>
Date: Jan 31, 2023, 13:29 UTC
Message-ID: <49bf10e0fd4468720cd86cc47e425bf446a1a4f7.1675171759.git.gitgitgadget@gmail.com>
In-Reply-To: <pull.1454.v3.git.1675171759.gitgitgadget@gmail.com>

From: Derrick Stolee <derrickstolee@github.com>

The bundle.heuristic value communicates that the bundle list is organized to make use of the bundle.<id>.creationToken values that may be provided in the bundle list. Those values will create a total order on the bundles, allowing the Git client to download them in a specific order and even remember previously-downloaded bundles by storing the maximum creation token value.

Before implementing any logic that parses or uses the bundle.<id>.creationToken values, teach Git to parse the bundle.heuristic value from a bundle list. We can use 'test-tool bundle-uri' to print the heuristic value and verify that the parsing works correctly.

As an extra precaution, create the internal 'heuristics' array to be a list of (enum, string) pairs so we can iterate through the array entries carefully, regardless of the enum values.

Signed-off-by: Derrick Stolee <derrickstolee@github.com>
---
 Documentation/config/bundle.txt |  7 +++++++
 bundle-uri.c                    | 34 +++++++++++++++++++++++++++++++++
 bundle-uri.h                    | 14 ++++++++++++++
 t/t5750-bundle-uri-parse.sh     | 19 ++++++++++++++++++
 4 files changed, 74 insertions(+)

diff --git a/Documentation/config/bundle.txt b/Documentation/config/bundle.txt
index daa21eb674a..3faae386853 100644
--- a/Documentation/config/bundle.txt
+++ b/Documentation/config/bundle.txt
@@ -15,6 +15,13 @@ bundle.mode::
 	complete understanding of the bundled information (`all`) or if any one
 	of the listed bundle URIs is sufficient (`any`).
 
+bundle.heuristic::
+	If this string-valued key exists, then the bundle list is designed to
+	work well with incremental `git fetch` commands. The heuristic signals
+	that there are additional keys available for each bundle that help
+	determine which subset of bundles the client should download. The
+	only value currently understood is `creationToken`.
+
 bundle.<id>.*::
 	The `bundle.<id>.*` keys are used to describe a single item in the
 	bundle list, grouped under `<id>` for identification purposes.
diff --git a/bundle-uri.c b/bundle-uri.c
index 36268dda172..36ec542718d 100644
--- a/bundle-uri.c
+++ b/bundle-uri.c
@@ -9,6 +9,14 @@
 #include "config.h"
 #include "remote.h"
 
+static struct {
+	enum bundle_list_heuristic heuristic;
+	const char *name;
+} heuristics[BUNDLE_HEURISTIC__COUNT] = {
+	{ BUNDLE_HEURISTIC_NONE, ""},
+	{ BUNDLE_HEURISTIC_CREATIONTOKEN, "creationToken" },
+};
+
 static int compare_bundles(const void *hashmap_cmp_fn_data,
 			   const struct hashmap_entry *he1,
 			   const struct hashmap_entry *he2,
@@ -100,6 +108,17 @@ void print_bundle_list(FILE *fp, struct bundle_list *list)
 	fprintf(fp, "\tversion = %d\n", list->version);
 	fprintf(fp, "\tmode = %s\n", mode);
 
+	if (list->heuristic) {
+		int i;
+		for (i = 0; i < BUNDLE_HEURISTIC__COUNT; i++) {
+			if (heuristics[i].heuristic == list->heuristic) {
+				printf("\theuristic = %s\n",
+				       heuristics[list->heuristic].name);
+				break;
+			}
+		}
+	}
+
 	for_all_bundles_in_list(list, summarize_bundle, fp);
 }
 
@@ -142,6 +161,21 @@ static int bundle_list_update(const char *key, const char *value,
 			return 0;
 		}
 
+		if (!strcmp(subkey, "heuristic")) {
+			int i;
+			for (i = 0; i < BUNDLE_HEURISTIC__COUNT; i++) {
+				if (heuristics[i].heuristic &&
+				    heuristics[i].name &&
+				    !strcmp(value, heuristics[i].name)) {
+					list->heuristic = heuristics[i].heuristic;
+					return 0;
+				}
+			}
+
+			/* Ignore unknown heuristics. */
+			return 0;
+		}
+
 		/* Ignore other unknown global keys. */
 		return 0;
 	}
diff --git a/bundle-uri.h b/bundle-uri.h
index d5e89f1671c..2e44a50a90b 100644
--- a/bundle-uri.h
+++ b/bundle-uri.h
@@ -52,6 +52,14 @@ enum bundle_list_mode {
 	BUNDLE_MODE_ANY
 };
 
+enum bundle_list_heuristic {
+	BUNDLE_HEURISTIC_NONE = 0,
+	BUNDLE_HEURISTIC_CREATIONTOKEN,
+
+	/* Must be last. */
+	BUNDLE_HEURISTIC__COUNT
+};
+
 /**
  * A bundle_list contains an unordered set of remote_bundle_info structs,
  * as well as information about the bundle listing, such as version and
@@ -75,6 +83,12 @@ struct bundle_list {
 	 * advertised by the bundle list at that location.
 	 */
 	char *baseURI;
+
+	/**
+	 * A list can have a heuristic, which helps reduce the number of
+	 * downloaded bundles.
+	 */
+	enum bundle_list_heuristic heuristic;
 };
 
 void init_bundle_list(struct bundle_list *list);
diff --git a/t/t5750-bundle-uri-parse.sh b/t/t5750-bundle-uri-parse.sh
index 7b4f930e532..6fc92a9c0d4 100755
--- a/t/t5750-bundle-uri-parse.sh
+++ b/t/t5750-bundle-uri-parse.sh
@@ -250,4 +250,23 @@ test_expect_success 'parse config format edge cases: empty key or value' '
 	test_cmp_config_output expect actual
 '
 
+test_expect_success 'parse config format: creationToken heuristic' '
+	cat >expect <<-\EOF &&
+	[bundle]
+		version = 1
+		mode = all
+		heuristic = creationToken
+	[bundle "one"]
+		uri = http://example.com/bundle.bdl
+	[bundle "two"]
+		uri = https://example.com/bundle.bdl
+	[bundle "three"]
+		uri = file:///usr/share/git/bundle.bdl
+	EOF
+
+	test-tool bundle-uri parse-config expect >actual 2>err &&
+	test_must_be_empty err &&
+	test_cmp_config_output expect actual
+'
+
 test_done

-- 
gitgitgadget