Re: [GSoC PATCH v9 2/5] repo: add the field references.format
- From
- Phillip Wood <phillip.wood123@gmail.com>
- Date
- Aug 11, 2025, 14:41 UTC
- Message-ID
- <f97b712f-95a4-480b-8ed0-174e4f45ff81@gmail.com>
- In-Reply-To
- <20250807150239.6987-3-lucasseikioshiro@gmail.com>
Hi Lucas
On 07/08/2025 16:02, Lucas Seiki Oshiro wrote:
> ++ > +The returned data is lexicographically sorted by the keys.
What's the reason for this? If I query three keys from a script then it is much easier to parse the output if I know the keys are going to appear in the same order that they were on the command line. If the command re-orders them my script now has to check the value of each key which results in a bunch of unnecessary string comparisons because it cannot determine the key from the position in the output. While we were producing json output there was a need to de-duplicate the keys when that output format was selected. However, we no-longer produce json and in any case de-duplication could have been achieved without sorting the input keys by using a hash table, or, as there is a small fixed number of keys, an array that records the keys we've already seen.
Thanks
Phillip
Show 204 quoted lines
> ++
> +The output format consists of key-value pairs one per line using the `=`
> +character as the delimiter between the key and the value. Values containing
> +"unusual" characters are quoted as explained for the configuration variable
> +`core.quotePath` (see linkgit:git-config[1]). This is the default.
> +
> +INFO KEYS
> +---------
> +
> +In order to obtain a set of values from `git repo info`, you should provide
> +the keys that identify them. Here's a list of the available keys and the
> +values that they return:
> +
> +`references.format`::
> +The reference storage format. The valid values are:
> ++
> +include::ref-storage-format.adoc[]
>
> SEE ALSO
> --------
> diff --git a/builtin/repo.c b/builtin/repo.c
> index fd2a9b4216..2b7ab5875e 100644
> --- a/builtin/repo.c
> +++ b/builtin/repo.c
> @@ -1,17 +1,102 @@
> #include "builtin.h"
> #include "parse-options.h"
> +#include "quote.h"
> +#include "refs.h"
> +#include "strbuf.h"
>
> static const char *const repo_usage[] = {
> "git repo info [<key>...]",
> NULL
> };
>
> -static int repo_info(int argc UNUSED, const char **argv UNUSED,
> - const char *prefix UNUSED, struct repository *repo UNUSED)
> +typedef int get_value_fn(struct repository *repo, struct strbuf *buf);
> +
> +struct field {
> + const char *key;
> + get_value_fn *get_value;
> +};
> +
> +static int get_references_format(struct repository *repo, struct strbuf *buf)
> {
> + strbuf_addstr(buf,
> + ref_storage_format_to_name(repo->ref_storage_format));
> return 0;
> }
>
> +/* repo_info_fields keys should be in lexicographical order */
> +static const struct field repo_info_fields[] = {
> + { "references.format", get_references_format },
> +};
> +
> +static int repo_info_fields_cmp(const void *va, const void *vb)
> +{
> + const struct field *a = va;
> + const struct field *b = vb;
> +
> + return strcmp(a->key, b->key);
> +}
> +
> +static get_value_fn *get_value_fn_for_key(const char *key)
> +{
> + const struct field search_key = { key, NULL };
> + const struct field *found = bsearch(&search_key, repo_info_fields,
> + ARRAY_SIZE(repo_info_fields),
> + sizeof(*found),
> + repo_info_fields_cmp);
> + return found ? found->get_value : NULL;
> +}
> +
> +static int qsort_strcmp(const void *va, const void *vb)
> +{
> + const char *a = *(const char **)va;
> + const char *b = *(const char **)vb;
> +
> + return strcmp(a, b);
> +}
> +
> +static int print_fields(int argc, const char **argv, struct repository *repo)
> +{
> + int ret = 0;
> + const char *last = "";
> + struct strbuf valbuf = STRBUF_INIT;
> + struct strbuf quotbuf = STRBUF_INIT;
> +
> + QSORT(argv, argc, qsort_strcmp);
> +
> + for (int i = 0; i < argc; i++) {
> + get_value_fn *get_value;
> + const char *key = argv[i];
> +
> + strbuf_reset(&valbuf);
> + strbuf_reset("buf);
> +
> + if (!strcmp(key, last))
> + continue;
> +
> + last = key;
> + get_value = get_value_fn_for_key(key);
> +
> + if (!get_value) {
> + ret = error(_("key '%s' not found"), key);
> + continue;
> + }
> +
> + get_value(repo, &valbuf);
> + quote_c_style(valbuf.buf, "buf, NULL, 0);
> + printf("%s=%s\n", key, quotbuf.buf);
> + }
> +
> + strbuf_release(&valbuf);
> + strbuf_release("buf);
> + return ret;
> +}
> +
> +static int repo_info(int argc, const char **argv, const char *prefix UNUSED,
> + struct repository *repo)
> +{
> + return print_fields(argc - 1, argv + 1, repo);
> +}
> +
> int cmd_repo(int argc, const char **argv, const char *prefix,
> struct repository *repo)
> {
> diff --git a/t/meson.build b/t/meson.build
> index bbeba1a8d5..252dbbc031 100644
> --- a/t/meson.build
> +++ b/t/meson.build
> @@ -230,6 +230,7 @@ integration_tests = [
> 't1700-split-index.sh',
> 't1701-racy-split-index.sh',
> 't1800-hook.sh',
> + 't1900-repo.sh',
> 't2000-conflict-when-checking-files-out.sh',
> 't2002-checkout-cache-u.sh',
> 't2003-checkout-cache-mkdir.sh',
> diff --git a/t/t1900-repo.sh b/t/t1900-repo.sh
> new file mode 100755
> index 0000000000..2b2516dbae
> --- /dev/null
> +++ b/t/t1900-repo.sh
> @@ -0,0 +1,57 @@
> +#!/bin/sh
> +
> +test_description='test git repo-info'
> +
> +. ./test-lib.sh
> +
> +# Test whether a key-value pair is correctly returned
> +#
> +# Usage: test_repo_info <label> <init command> <key> <expected value>
> +#
> +# Arguments:
> +# label: the label of the test
> +# init_command: a command which creates a repository
> +# repo_name: the name of the repository that will be created in init_command
> +# key: the key of the field that is being tested
> +# expected_value: the value that the field should contain
> +test_repo_info () {
> + label=$1
> + init_command=$2
> + repo_name=$3
> + key=$4
> + expected_value=$5
> +
> + test_expect_success "$label" '
> + eval "$init_command $repo_name" &&
> + echo "$key=$expected_value" >expected &&
> + git -C $repo_name repo info "$key" >actual &&
> + test_cmp expected actual
> + '
> +}
> +
> +test_repo_info 'ref format files is retrieved correctly' '
> + git init --ref-format=files' 'format-files' 'references.format' 'files'
> +
> +test_repo_info 'ref format reftable is retrieved correctly' '
> + git init --ref-format=reftable' 'format-reftable' 'references.format' 'reftable'
> +
> +test_expect_success 'git-repo-info fails if an invalid key is requested' '
> + echo "error: key ${SQ}foo${SQ} not found" >expected_err &&
> + test_must_fail git repo info foo 2>actual_err &&
> + test_cmp expected_err actual_err
> +'
> +
> +test_expect_success 'git-repo-info outputs data even if there is an invalid field' '
> + echo "references.format=$(test_detect_ref_format)" >expected &&
> + test_must_fail git repo info foo references.format bar >actual &&
> + test_cmp expected actual
> +'
> +
> +test_expect_success 'only one value is returned if the same key is requested twice' '
> + val=$(git rev-parse --show-ref-format) &&
> + echo "references.format=$val" >expect &&
> + git repo info references.format references.format >actual &&
> + test_cmp expect actual
> +'
> +
> +test_done