Re: [PATCH v2 01/19] qapi: Smarter camel_to_upper() to reduce need for 'prefix'

[Peter Xu]

On Thu, Sep 05, 2024 at 04:52:36PM +0100, Daniel P. Berrangé wrote:
> On Thu, Sep 05, 2024 at 07:59:13AM +0200, Markus Armbruster wrote:
> > Daniel P. Berrangé <berrange@redhat.com> writes:
> > 
> > > On Wed, Sep 04, 2024 at 01:18:18PM +0200, Markus Armbruster wrote:
> > >> camel_to_upper() converts its argument from camel case to upper case
> > >> with '_' between words.  Used for generated enumeration constant
> > >> prefixes.
> > >
> > >
> > >> 
> > >> Signed-off-by: Markus Armbruster <armbru@redhat.com>
> > >> Reviewed-by: Daniel P. Berrang?? <berrange@redhat.com>
> > >
> > > The accent in my name is getting mangled in this series.
> > 
> > Uh-oh!
> > 
> > Checking...  Hmm.  It's correct in git, correct in output of
> > git-format-patch, correct in the copy I got from git-send-email --bcc
> > armbru via localhost MTA, and the copy I got from --to
> > qemu-devel@nongnu.org, correct in lore.kernel.org[*], correct in an mbox
> > downloaded from patchew.
> > 
> > Could the culprit be on your side?
> 
> I compared my received mail vs the mbox archive on nongnu.org for
> qemu-devel.
> 
> In both cases the actual mail body seems to be valid UTF-8 and is
> identical. The message in the nongnu.org archive, however, has
> 
>   Content-Type: text/plain; charset=UTF-8
> 
> while the copy I got in my inbox has merely
> 
>   Content-Type: text/plain
> 
> What I can't determine is whether your original sent message
> had "charset=UTF-8" which then got stripped by redhat's incoming
> mail server, or whether your original lacked 'charset=UTF8' and
> it got added by mailman when saving the message to the mbox archives ?

I didn't read into details of what Markus hit, but I just remembered I hit
similar things before and Dan reported similar issue.  At that time (which
I tried to recall..) was because I used git-publish sending patches, in
which there is an encoding issue. I tried to fix with this branch:

https://github.com/xzpeter/git-publish/commits/fix-print-2/

I also remember I tried to upstream that to Stefan's repo but I totally
forgot what happened later, but the result is I am still using this branch
internally (which I completely forgot which version I'm using... but I
found that until I see this discussion and checked..).

Please ignore everything if git-publish is not used at all.. but just in
case helpful..

-- 
Peter Xu