diff mbox series

[v2,2/3] update-index: add --show-index-version

Message ID 20230818233729.2766281-3-gitster@pobox.com (mailing list archive)
State Superseded
Headers show
Series "update-index --show-index-version" | expand

Commit Message

Junio C Hamano Aug. 18, 2023, 11:37 p.m. UTC
"git update-index --version N" is used to set the index format
version to a specific version, but there was no way to query the
current version used in the on-disk index file.

Teach the command a new "--show-index-version" option, and also
teach the "--index-version N" option to report what the version was
when run with the "--verbose" option.

Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 Documentation/git-update-index.txt |  6 +++++-
 builtin/update-index.c             | 19 +++++++++++++------
 t/t2107-update-index-basic.sh      | 16 ++++++++++++++++
 3 files changed, 34 insertions(+), 7 deletions(-)

Comments

Linus Arver Sept. 12, 2023, 5:54 a.m. UTC | #1
Junio C Hamano <gitster@pobox.com> writes:

> "git update-index --version N" is used to set the index format

s/--version/--index-version

> version to a specific version, but there was no way to query the
> current version used in the on-disk index file.
>
> Teach the command a new "--show-index-version" option, and also
> teach the "--index-version N" option to report what the version was
> when run with the "--verbose" option.
>
> Signed-off-by: Junio C Hamano <gitster@pobox.com>
> ---
>  Documentation/git-update-index.txt |  6 +++++-
>  builtin/update-index.c             | 19 +++++++++++++------
>  t/t2107-update-index-basic.sh      | 16 ++++++++++++++++
>  3 files changed, 34 insertions(+), 7 deletions(-)
>
> diff --git a/Documentation/git-update-index.txt b/Documentation/git-update-index.txt
> index a367f8d65a..3f204891ce 100644
> --- a/Documentation/git-update-index.txt
> +++ b/Documentation/git-update-index.txt
> @@ -162,7 +162,8 @@ you will need to handle the situation manually.
>  	Write the resulting index out in the named on-disk format version.
>  	Supported versions are 2, 3 and 4. The current default version is 2
>  	or 3, depending on whether extra features are used, such as
> -	`git add -N`.
> +	`git add -N`.  With `--verbose` option, also reports the

How about

    `git add -N`.  With `--verbose`, also report the

> +	version the index file uses before and after this command.
>  +
>  Version 4 performs a simple pathname compression that reduces index
>  size by 30%-50% on large repositories, which results in faster load
> @@ -171,6 +172,9 @@ and support for it was added to libgit2 in 2016 and to JGit in 2020.
>  Older editions of this manual page called it "relatively young", but
>  it should be considered mature technology these days.
>
> +--show-index-version::
> +	Report the index format version used by the on-disk index file.
> +	See `--index-version` above.

Looks good.

>  -z::
>  	Only meaningful with `--stdin` or `--index-info`; paths are
> diff --git a/builtin/update-index.c b/builtin/update-index.c
> index 5fab9ad2ec..e713e2a04c 100644
> --- a/builtin/update-index.c
> +++ b/builtin/update-index.c
> @@ -1089,6 +1089,8 @@ int cmd_update_index(int argc, const char **argv, const char *prefix)
>  			resolve_undo_clear_callback),
>  		OPT_INTEGER(0, "index-version", &preferred_index_format,
>  			N_("write index in this format")),
> +		OPT_SET_INT(0, "show-index-version", &preferred_index_format,
> +			    N_("show index format version"), -1),

How about

    "show on-disk index format version"

for the help text? Also "report" may be preferable instead of "show" for
consistency with the manpage.

Also, I think it would be easier to read if we didn't overload
preferred_index_format here and instead used a new variable (perhaps named
"show_index_format").

And I just realized that we are now using not only "show" and "report"
interchangeably in this patch, but also "format" and "version" ---
it would be nice to clean up as #leftoverbits.

>  		OPT_BOOL(0, "split-index", &split_index,
>  			N_("enable or disable split index")),
>  		OPT_BOOL(0, "untracked-cache", &untracked_cache,
> @@ -1181,15 +1183,20 @@ int cmd_update_index(int argc, const char **argv, const char *prefix)
>
>  	getline_fn = nul_term_line ? strbuf_getline_nul : strbuf_getline_lf;
>  	if (preferred_index_format) {
> -		if (preferred_index_format < INDEX_FORMAT_LB ||
> -		    INDEX_FORMAT_UB < preferred_index_format)
> +		if (preferred_index_format < 0) {
> +			printf(_("%d\n"), the_index.version);
> +		} else if (preferred_index_format < INDEX_FORMAT_LB ||
> +			   INDEX_FORMAT_UB < preferred_index_format) {
>  			die("index-version %d not in range: %d..%d",
>  			    preferred_index_format,
>  			    INDEX_FORMAT_LB, INDEX_FORMAT_UB);
> -
> -		if (the_index.version != preferred_index_format)
> -			the_index.cache_changed |= SOMETHING_CHANGED;
> -		the_index.version = preferred_index_format;
> +		} else {
> +			if (the_index.version != preferred_index_format)
> +				the_index.cache_changed |= SOMETHING_CHANGED;
> +			report(_("index-version: was %d, set to %d"),
> +			       the_index.version, preferred_index_format);
> +			the_index.version = preferred_index_format;
> +		}
>  	}

Looks good. But if you decide to use a new variable like
"show_index_format" as suggested above, you might want to refactor this
out to a separate function. Then you could obviously do away with the
chained if/else and replace them with early returns, which would be
easier to read.

>  	if (read_from_stdin) {
> diff --git a/t/t2107-update-index-basic.sh b/t/t2107-update-index-basic.sh
> index 89b285fa3a..c78d1e9396 100755
> --- a/t/t2107-update-index-basic.sh
> +++ b/t/t2107-update-index-basic.sh
> @@ -111,4 +111,20 @@ test_expect_success '--chmod=+x and chmod=-x in the same argument list' '
>  	test_cmp expect actual
>  '
>
> +test_expect_success '--index-version' '
> +	git commit --allow-empty -m snap &&
> +	git reset --hard &&

Not sure why this "git reset --hard" is needed here --- is it to clear
out state from previous test cases? If so, perhaps it's better to run
this as the very first command in this test case?

But this also makes me wonder why "git commit --allow-empty -m snap" is
even necessary (if we already have a git repo)?

> +	git update-index --index-version 2 >actual &&
> +	test_must_be_empty actual &&

Before we do "--index-version 2", it may be desirable to run the
"--show-index-version" flag first to see what we have before modifying
it with "2".

> +	git update-index --show-index-version >actual &&
> +	echo 2 >expect &&
> +	test_cmp expect actual &&
> +
> +	git update-index --index-version 4 --verbose >actual &&
> +	echo "index-version: was 2, set to 4" >expect &&
> +	test_cmp expect actual
> +'

How about adding this check below to check what happens if the newly-set
version is the same as the existing version?

        git update-index --index-version 4 --verbose >actual &&
        echo "index-version: was 4, set to 4" >expect &&
        test_cmp expect actual

And also how about a similar check, but for downgrading from a higher
version number to a lower one?

        git update-index --index-version 2 --verbose >actual &&
        echo "index-version: was 4, set to 2" >expect &&
        test_cmp expect actual

> +
>  test_done
> --
> 2.42.0-rc2-7-gf9972720e9
Junio C Hamano Sept. 12, 2023, 7:01 p.m. UTC | #2
Linus Arver <linusa@google.com> writes:

> Junio C Hamano <gitster@pobox.com> writes:
>
>> "git update-index --version N" is used to set the index format
>
> s/--version/--index-version

Good eyes.

>> +	`git add -N`.  With `--verbose` option, also reports the
>
> How about
>
>     `git add -N`.  With `--verbose`, also report the

Yup, that is much better.

>>  		OPT_INTEGER(0, "index-version", &preferred_index_format,
>>  			N_("write index in this format")),
>> +		OPT_SET_INT(0, "show-index-version", &preferred_index_format,
>> +			    N_("show index format version"), -1),
>
> How about
>
>     "show on-disk index format version"

OK.  The entry before that says "write" and it makes it clear enough
that it is talking about the "on-disk" thing, hence "write index" is
sufficient.  The readers, who do not know the "format version"
matters only on-disk and does not matter once the index data gets
slurped into memory, would benefit with "on-disk index" here.  I
will also take your "show" -> "report" suggestion.

>> diff --git a/t/t2107-update-index-basic.sh b/t/t2107-update-index-basic.sh
>> index 89b285fa3a..c78d1e9396 100755
>> --- a/t/t2107-update-index-basic.sh
>> +++ b/t/t2107-update-index-basic.sh
>> @@ -111,4 +111,20 @@ test_expect_success '--chmod=+x and chmod=-x in the same argument list' '
>>  	test_cmp expect actual
>>  '
>>
>> +test_expect_success '--index-version' '
>> +	git commit --allow-empty -m snap &&
>> +	git reset --hard &&
>
> Not sure why this "git reset --hard" is needed here --- is it to clear
> out state from previous test cases? If so, perhaps it's better to run
> this as the very first command in this test case?
>
> But this also makes me wonder why "git commit --allow-empty -m snap" is
> even necessary (if we already have a git repo)?

There is no commit yet in this repository at this point, which means
that "reset --hard [HEAD]" cannot be the first command.  There are
newly added paths in the index, some of which are further modified
in the working tree.  Creating a snapshot commit will record what is
in the index, and a hard reset will make the contents of the working
tree match exactly what was in the index, reverting the modification
made to some paths in the working tree.

Having said that, we may further want to tighten these "clean the
slate" steps for later tests (read on).

>> +	git update-index --index-version 2 >actual &&
>> +	test_must_be_empty actual &&
>
> Before we do "--index-version 2", it may be desirable to run the
> "--show-index-version" flag first to see what we have before modifying
> it with "2".

That was what I specifically wanted to avoid.  I am not interested
in testing what the default version of the day is.  The only thing
this invocation cares about is to (try to) use the version 2; it
will be detected as a failure if the next show-index-version
reported something else ...

>> +	git update-index --show-index-version >actual &&
>> +	echo 2 >expect &&
>> +	test_cmp expect actual &&

... which is checked here.

>> +	git update-index --index-version 4 --verbose >actual &&
>> +	echo "index-version: was 2, set to 4" >expect &&
>> +	test_cmp expect actual

And how a transition is reported with --verbose is tested here.

>> +'
>
> How about adding this check below to check what happens if the newly-set
> version is the same as the existing version?
>
>         git update-index --index-version 4 --verbose >actual &&
>         echo "index-version: was 4, set to 4" >expect &&
>         test_cmp expect actual
>
> And also how about a similar check, but for downgrading from a higher
> version number to a lower one?
>
>         git update-index --index-version 2 --verbose >actual &&
>         echo "index-version: was 4, set to 2" >expect &&
>         test_cmp expect actual

I assumed that the flipping between versions without --verbose had
adequate coverage and the tests this patch adds were solely about
reporting with the "--verbose" option.  It seems there is no such
test coverage, so these may want to be added.  Perhaps we should
flip from 2 to 4 _without_ verbose and make sure we are still silent
as well.

Testing downgrading an index with unspecified [*] contents from 3
(or higher) to 2 would be unwise, as such a conversion may or may
not work depending on the contents.  I will tighten the "clean the
slate" steps and add downgrades to the list, as the initial "try to
set to 2" may not even work with unknown contents in the index.

Thanks.


[Footnote] 

* This is in a very late part of the test script and the state
  previous tests left us will change over time.
diff mbox series

Patch

diff --git a/Documentation/git-update-index.txt b/Documentation/git-update-index.txt
index a367f8d65a..3f204891ce 100644
--- a/Documentation/git-update-index.txt
+++ b/Documentation/git-update-index.txt
@@ -162,7 +162,8 @@  you will need to handle the situation manually.
 	Write the resulting index out in the named on-disk format version.
 	Supported versions are 2, 3 and 4. The current default version is 2
 	or 3, depending on whether extra features are used, such as
-	`git add -N`.
+	`git add -N`.  With `--verbose` option, also reports the
+	version the index file uses before and after this command.
 +
 Version 4 performs a simple pathname compression that reduces index
 size by 30%-50% on large repositories, which results in faster load
@@ -171,6 +172,9 @@  and support for it was added to libgit2 in 2016 and to JGit in 2020.
 Older editions of this manual page called it "relatively young", but
 it should be considered mature technology these days.
 
+--show-index-version::
+	Report the index format version used by the on-disk index file.
+	See `--index-version` above.
 
 -z::
 	Only meaningful with `--stdin` or `--index-info`; paths are
diff --git a/builtin/update-index.c b/builtin/update-index.c
index 5fab9ad2ec..e713e2a04c 100644
--- a/builtin/update-index.c
+++ b/builtin/update-index.c
@@ -1089,6 +1089,8 @@  int cmd_update_index(int argc, const char **argv, const char *prefix)
 			resolve_undo_clear_callback),
 		OPT_INTEGER(0, "index-version", &preferred_index_format,
 			N_("write index in this format")),
+		OPT_SET_INT(0, "show-index-version", &preferred_index_format,
+			    N_("show index format version"), -1),
 		OPT_BOOL(0, "split-index", &split_index,
 			N_("enable or disable split index")),
 		OPT_BOOL(0, "untracked-cache", &untracked_cache,
@@ -1181,15 +1183,20 @@  int cmd_update_index(int argc, const char **argv, const char *prefix)
 
 	getline_fn = nul_term_line ? strbuf_getline_nul : strbuf_getline_lf;
 	if (preferred_index_format) {
-		if (preferred_index_format < INDEX_FORMAT_LB ||
-		    INDEX_FORMAT_UB < preferred_index_format)
+		if (preferred_index_format < 0) {
+			printf(_("%d\n"), the_index.version);
+		} else if (preferred_index_format < INDEX_FORMAT_LB ||
+			   INDEX_FORMAT_UB < preferred_index_format) {
 			die("index-version %d not in range: %d..%d",
 			    preferred_index_format,
 			    INDEX_FORMAT_LB, INDEX_FORMAT_UB);
-
-		if (the_index.version != preferred_index_format)
-			the_index.cache_changed |= SOMETHING_CHANGED;
-		the_index.version = preferred_index_format;
+		} else {
+			if (the_index.version != preferred_index_format)
+				the_index.cache_changed |= SOMETHING_CHANGED;
+			report(_("index-version: was %d, set to %d"),
+			       the_index.version, preferred_index_format);
+			the_index.version = preferred_index_format;
+		}
 	}
 
 	if (read_from_stdin) {
diff --git a/t/t2107-update-index-basic.sh b/t/t2107-update-index-basic.sh
index 89b285fa3a..c78d1e9396 100755
--- a/t/t2107-update-index-basic.sh
+++ b/t/t2107-update-index-basic.sh
@@ -111,4 +111,20 @@  test_expect_success '--chmod=+x and chmod=-x in the same argument list' '
 	test_cmp expect actual
 '
 
+test_expect_success '--index-version' '
+	git commit --allow-empty -m snap &&
+	git reset --hard &&
+
+	git update-index --index-version 2 >actual &&
+	test_must_be_empty actual &&
+
+	git update-index --show-index-version >actual &&
+	echo 2 >expect &&
+	test_cmp expect actual &&
+
+	git update-index --index-version 4 --verbose >actual &&
+	echo "index-version: was 2, set to 4" >expect &&
+	test_cmp expect actual
+'
+
 test_done