Paolo Bonzini <pbonz...@redhat.com> writes:
> Il 18/10/2013 03:11, Wenchao Xia ha scritto:
>> The behavior to set sep brings trouble to modification later,
>> the logic is not changed by add tailing space in fprintf().
>>
>> Signed-off-by: Wenchao Xia <xiaw...@linux.vnet.ibm.com>
>> ---
>> util/qemu-error.c | 5 ++---
>> 1 files changed, 2 insertions(+), 3 deletions(-)
>>
>> diff --git a/util/qemu-error.c b/util/qemu-error.c
>> index 0ccd3e9..d1e858a 100644
>> --- a/util/qemu-error.c
>> +++ b/util/qemu-error.c
>> @@ -161,8 +161,7 @@ static void error_print_loc(void)
>> const char *const *argp;
>>
>> if (!cur_mon && progname) {
>> - fprintf(stderr, "%s:", progname);
>> - sep = " ";
>> + fprintf(stderr, "%s: ", progname);
>> }
>> switch (cur_loc->kind) {
>> case LOC_CMDLINE:
>> @@ -181,7 +180,7 @@ static void error_print_loc(void)
>> error_printf(" ");
>> break;
>> default:
>> - error_printf("%s", sep);
>> + break;
>> }
>> }
>>
>>
>
> This changes behavior for LOC_FILE.
>
> Before:
>
> $ cat xyz.cfg
> [device "abc"]
> driver = def
> $ qemu-system-x86_64 -readconfig xyz.cfg
> qemu-system-x86_64:xyz.cfg:2: parse error
>
> After:
>
> $ qemu-system-x86_64 -readconfig xyz.cfg
> qemu-system-x86_64: xyz.cfg:2: parse error
>
> Could even be an improvement, but you need to note it in the commit message.
No, it is not an improvement. The old format matches exactly how other
report errors with location, e.g. jade. Please leave it that way,
