[U-Boot] [PATCH v4 6/7] env: make "env default" selective, check and apply

[Gerlando Falauto]

On 08/24/2012 11:10 PM, Marek Vasut wrote:
> Dear Gerlando Falauto,
>
>> On 08/24/2012 04:56 PM, Marek Vasut wrote:
>>> Dear Gerlando Falauto,
>>>
>>>> Change the syntax (user API) for "env default":
>>>>     -f: override write-once variables
>>>>     var... : accept individual variable(s)
>>>>     -a: all (resetting the whole env is NOT the default behavior)
>>>>
>>>> Enable variable checking and make changes effective by
>>>> enabling do_apply argument to himport_r().
>>>>
>>>> Signed-off-by: Gerlando Falauto<gerlando.falauto at keymile.com>
>>>> ---
>>>>
>>>>    common/cmd_nvedit.c   |   40 ++++++++++++++++++++++++++++++++++------
>>>>    common/env_common.c   |   28 +++++++++++++++++++++++++++-
>>>>    include/environment.h |    3 +++
>>>>    3 files changed, 64 insertions(+), 7 deletions(-)
>>>>
>>>> diff --git a/common/cmd_nvedit.c b/common/cmd_nvedit.c
>>>> index b0860f3..ac2b985 100644
>>>> --- a/common/cmd_nvedit.c
>>>> +++ b/common/cmd_nvedit.c
>>>> @@ -656,14 +656,41 @@ int envmatch(uchar *s1, int i2)
>>>>
>>>>    	return -1;
>>>>
>>>>    }
>>>>
>>>> -static int do_env_default(cmd_tbl_t *cmdtp, int flag,
>>>> +static int do_env_default(cmd_tbl_t *cmdtp, int __flag,
>>>>
>>>>    			  int argc, char * const argv[])
>>>>
>>>>    {
>>>>
>>>> -	if (argc != 2 || strcmp(argv[1], "-f") != 0)
>>>> -		return CMD_RET_USAGE;
>>>> +	int all = 0, flag = 0;
>>>>
>>>> -	set_default_env("## Resetting to default environment\n");
>>>> -	return 0;
>>>> +	debug("Initial value for argc=%d\n", argc);
>>>> +	while (--argc>   0&&   **++argv == '-') {
>>>
>>> mmmmm ... **++argv, yummy :) This might use some cleanup, to make more
>>> readable.
>>
>> Uhm, this pattern is being used all over the place on that file (that's
>> where I copied it from).
>
> That doesn't mean it's right, it just means the codebase is in a very sad state
> :-C
>
>>> Don't we have some getopt or something too ?
>>
>> Not that I (or "git grep") know of.
>
> Even more :-C
>
You're absolutely right, but this patchset has been around for almost a 
year and we've gotten nowhere with it. I'm afraid that if we keep adding 
new (somewhat unrelated) improvement requests we'll get stuck with it 
for quite some time once again.
Could we keep this getopt topic in mind as an open point for a later, 
overall review of how command line options are parsed?

Thank you,
Gerlando