[PATCH v6 4/7] builtin/repo: introduce structure subcommand

[Justin Tobler <jltobler@gmail.com>]

The structure of a repository's history can have huge impacts on the
performance and health of the repository itself. Currently, Git lacks a
means to surface repository metrics regarding its structure/shape via a
single command. Acquiring this information requires users to be familiar
with the relevant data points and the various Git commands required to
surface them. To fill this gap, supplemental tools such as git-sizer(1)
have been developed.

To allow users to more readily identify repository structure related
information, introduce the "structure" subcommand in git-repo(1). The
goal of this subcommand is to eventually provide similar functionality
to git-sizer(1), but natively in Git.

The initial version of this command only iterates through all references
in the repository and tracks the count of branches, tags, remote refs,
and other reference types. The corresponding information is displayed in
a human-friendly table formatted in a very similar manner to
git-sizer(1). The width of each table column is adjusted automatically
to satisfy the requirements of the widest row contained.

Subsequent commits will surface additional relevant data points to
output and also provide other more machine-friendly output formats.

Based-on-patch-by: Derrick Stolee <stolee@gmail.com>
Signed-off-by: Justin Tobler <jltobler@gmail.com>
---
 Documentation/git-repo.adoc |  10 ++
 builtin/repo.c              | 200 ++++++++++++++++++++++++++++++++++++
 t/meson.build               |   1 +
 t/t1901-repo-structure.sh   |  61 +++++++++++
 4 files changed, 272 insertions(+)
 create mode 100755 t/t1901-repo-structure.sh

diff --git a/Documentation/git-repo.adoc b/Documentation/git-repo.adoc
index 209afd1b61..8193298dd5 100644
--- a/Documentation/git-repo.adoc
+++ b/Documentation/git-repo.adoc
@@ -9,6 +9,7 @@ SYNOPSIS
 --------
 [synopsis]
 git repo info [--format=(keyvalue|nul)] [-z] [<key>...]
+git repo structure
 
 DESCRIPTION
 -----------
@@ -43,6 +44,15 @@ supported:
 +
 `-z` is an alias for `--format=nul`.
 
+`structure`::
+	Retrieve statistics about the current repository structure. The
+	following kinds of information are reported:
++
+* Reference counts categorized by type
+
++
+The table output format may change and is not intended for machine parsing.
+
 INFO KEYS
 ---------
 In order to obtain a set of values from `git repo info`, you should provide
diff --git a/builtin/repo.c b/builtin/repo.c
index eeeab8fbd2..e77e8db563 100644
--- a/builtin/repo.c
+++ b/builtin/repo.c
@@ -4,12 +4,16 @@
 #include "environment.h"
 #include "parse-options.h"
 #include "quote.h"
+#include "ref-filter.h"
 #include "refs.h"
 #include "strbuf.h"
+#include "string-list.h"
 #include "shallow.h"
+#include "utf8.h"
 
 static const char *const repo_usage[] = {
 	"git repo info [--format=(keyvalue|nul)] [-z] [<key>...]",
+	"git repo structure",
 	NULL
 };
 
@@ -156,12 +160,208 @@ static int cmd_repo_info(int argc, const char **argv, const char *prefix,
 	return print_fields(argc, argv, repo, format);
 }
 
+struct ref_stats {
+	size_t branches;
+	size_t remotes;
+	size_t tags;
+	size_t others;
+};
+
+struct stats_table {
+	struct string_list rows;
+
+	int name_col_width;
+	int value_col_width;
+};
+
+/*
+ * Holds column data that gets stored for each row.
+ */
+struct stats_table_entry {
+	char *value;
+};
+
+static void stats_table_vaddf(struct stats_table *table,
+			      struct stats_table_entry *entry,
+			      const char *format, va_list ap)
+{
+	struct strbuf buf = STRBUF_INIT;
+	struct string_list_item *item;
+	char *formatted_name;
+	int name_width;
+
+	strbuf_vaddf(&buf, format, ap);
+	formatted_name = strbuf_detach(&buf, NULL);
+	name_width = utf8_strwidth(formatted_name);
+
+	item = string_list_append_nodup(&table->rows, formatted_name);
+	item->util = entry;
+
+	if (name_width > table->name_col_width)
+		table->name_col_width = name_width;
+	if (entry) {
+		int value_width = utf8_strwidth(entry->value);
+		if (value_width > table->value_col_width)
+			table->value_col_width = value_width;
+	}
+}
+
+static void stats_table_addf(struct stats_table *table, const char *format, ...)
+{
+	va_list ap;
+
+	va_start(ap, format);
+	stats_table_vaddf(table, NULL, format, ap);
+	va_end(ap);
+}
+
+static void stats_table_count_addf(struct stats_table *table, size_t value,
+				   const char *format, ...)
+{
+	struct stats_table_entry *entry;
+	va_list ap;
+
+	CALLOC_ARRAY(entry, 1);
+	entry->value = xstrfmt("%" PRIuMAX, (uintmax_t)value);
+
+	va_start(ap, format);
+	stats_table_vaddf(table, entry, format, ap);
+	va_end(ap);
+}
+
+static inline size_t get_total_reference_count(struct ref_stats *stats)
+{
+	return stats->branches + stats->remotes + stats->tags + stats->others;
+}
+
+static void stats_table_setup_structure(struct stats_table *table,
+					struct ref_stats *refs)
+{
+	size_t ref_total;
+
+	ref_total = get_total_reference_count(refs);
+	stats_table_addf(table, "* %s", _("References"));
+	stats_table_count_addf(table, ref_total, "  * %s", _("Count"));
+	stats_table_count_addf(table, refs->branches, "    * %s", _("Branches"));
+	stats_table_count_addf(table, refs->tags, "    * %s", _("Tags"));
+	stats_table_count_addf(table, refs->remotes, "    * %s", _("Remotes"));
+	stats_table_count_addf(table, refs->others, "    * %s", _("Others"));
+}
+
+static void stats_table_print_structure(const struct stats_table *table)
+{
+	const char *name_col_title = _("Repository structure");
+	const char *value_col_title = _("Value");
+	int name_col_width = utf8_strwidth(name_col_title);
+	int value_col_width = utf8_strwidth(value_col_title);
+	struct string_list_item *item;
+
+	if (table->name_col_width > name_col_width)
+		name_col_width = table->name_col_width;
+	if (table->value_col_width > value_col_width)
+		value_col_width = table->value_col_width;
+
+	printf("| %-*s | %-*s |\n", name_col_width, name_col_title,
+	       value_col_width, value_col_title);
+	printf("| ");
+	for (int i = 0; i < name_col_width; i++)
+		putchar('-');
+	printf(" | ");
+	for (int i = 0; i < value_col_width; i++)
+		putchar('-');
+	printf(" |\n");
+
+	for_each_string_list_item(item, &table->rows) {
+		struct stats_table_entry *entry = item->util;
+		const char *value = "";
+
+		if (entry) {
+			struct stats_table_entry *entry = item->util;
+			value = entry->value;
+		}
+
+		printf("| %-*s | %*s |\n", name_col_width, item->string,
+		       value_col_width, value);
+	}
+}
+
+static void stats_table_clear(struct stats_table *table)
+{
+	struct stats_table_entry *entry;
+	struct string_list_item *item;
+
+	for_each_string_list_item(item, &table->rows) {
+		entry = item->util;
+		if (entry)
+			free(entry->value);
+	}
+
+	string_list_clear(&table->rows, 1);
+}
+
+static int count_references(const char *refname,
+			    const char *referent UNUSED,
+			    const struct object_id *oid UNUSED,
+			    int flags UNUSED, void *cb_data)
+{
+	struct ref_stats *stats = cb_data;
+
+	switch (ref_kind_from_refname(refname)) {
+	case FILTER_REFS_BRANCHES:
+		stats->branches++;
+		break;
+	case FILTER_REFS_REMOTES:
+		stats->remotes++;
+		break;
+	case FILTER_REFS_TAGS:
+		stats->tags++;
+		break;
+	case FILTER_REFS_OTHERS:
+		stats->others++;
+		break;
+	default:
+		BUG("unexpected reference type");
+	}
+
+	return 0;
+}
+
+static void structure_count_references(struct ref_stats *stats,
+				       struct repository *repo)
+{
+	refs_for_each_ref(get_main_ref_store(repo), count_references, &stats);
+}
+
+static int cmd_repo_structure(int argc, const char **argv, const char *prefix,
+			      struct repository *repo)
+{
+	struct stats_table table = {
+		.rows = STRING_LIST_INIT_DUP,
+	};
+	struct ref_stats stats = { 0 };
+	struct option options[] = { 0 };
+
+	argc = parse_options(argc, argv, prefix, options, repo_usage, 0);
+	if (argc)
+		usage(_("too many arguments"));
+
+	structure_count_references(&stats, repo);
+
+	stats_table_setup_structure(&table, &stats);
+	stats_table_print_structure(&table);
+
+	stats_table_clear(&table);
+
+	return 0;
+}
+
 int cmd_repo(int argc, const char **argv, const char *prefix,
 	     struct repository *repo)
 {
 	parse_opt_subcommand_fn *fn = NULL;
 	struct option options[] = {
 		OPT_SUBCOMMAND("info", &fn, cmd_repo_info),
+		OPT_SUBCOMMAND("structure", &fn, cmd_repo_structure),
 		OPT_END()
 	};
 
diff --git a/t/meson.build b/t/meson.build
index 7974795fe4..9e426f8edc 100644
--- a/t/meson.build
+++ b/t/meson.build
@@ -236,6 +236,7 @@ integration_tests = [
   't1701-racy-split-index.sh',
   't1800-hook.sh',
   't1900-repo.sh',
+  't1901-repo-structure.sh',
   't2000-conflict-when-checking-files-out.sh',
   't2002-checkout-cache-u.sh',
   't2003-checkout-cache-mkdir.sh',
diff --git a/t/t1901-repo-structure.sh b/t/t1901-repo-structure.sh
new file mode 100755
index 0000000000..e592eea0eb
--- /dev/null
+++ b/t/t1901-repo-structure.sh
@@ -0,0 +1,61 @@
+#!/bin/sh
+
+test_description='test git repo structure'
+
+. ./test-lib.sh
+
+test_expect_success 'empty repository' '
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	(
+		cd repo &&
+		cat >expect <<-\EOF &&
+		| Repository structure | Value |
+		| -------------------- | ----- |
+		| * References         |       |
+		|   * Count            |     0 |
+		|     * Branches       |     0 |
+		|     * Tags           |     0 |
+		|     * Remotes        |     0 |
+		|     * Others         |     0 |
+		EOF
+
+		git repo structure >out 2>err &&
+
+		test_cmp expect out &&
+		test_line_count = 0 err
+	)
+'
+
+test_expect_success 'repository with references' '
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	(
+		cd repo &&
+		git commit --allow-empty -m init &&
+		git tag -a foo -m bar &&
+
+		oid="$(git rev-parse HEAD)" &&
+		git update-ref refs/remotes/origin/foo "$oid" &&
+
+		git notes add -m foo &&
+
+		cat >expect <<-\EOF &&
+		| Repository structure | Value |
+		| -------------------- | ----- |
+		| * References         |       |
+		|   * Count            |     4 |
+		|     * Branches       |     1 |
+		|     * Tags           |     1 |
+		|     * Remotes        |     1 |
+		|     * Others         |     1 |
+		EOF
+
+		git repo structure >out 2>err &&
+
+		test_cmp expect out &&
+		test_line_count = 0 err
+	)
+'
+
+test_done
-- 
2.51.0.193.g4975ec3473b