Re: [gentoo-portage-dev] [PATCH] Improve handling of percent-signs in SRC_URI

[Mike Gilbert]

On Sun, May 31, 2020 at 2:01 PM Zac Medico <zmedico@g.o> wrote:
>
> On 5/31/20 6:17 AM, Mike Gilbert wrote:
> > Unquote the URL basename when fetching from upstream.
> > Quote the filename when fetching from mirrors.
> >
> > Bug: https://bugs.gentoo.org/719810
> > Signed-off-by: Mike Gilbert <floppym@g.o>
> > ---
> >  lib/portage/dbapi/porttree.py       | 7 ++++++-
> >  lib/portage/package/ebuild/fetch.py | 9 +++++++--
> >  2 files changed, 13 insertions(+), 3 deletions(-)
> >
> > diff --git a/lib/portage/dbapi/porttree.py b/lib/portage/dbapi/porttree.py
> > index 08af17bcd..984263039 100644
> > --- a/lib/portage/dbapi/porttree.py
> > +++ b/lib/portage/dbapi/porttree.py
> > @@ -55,6 +55,11 @@ try:
> >  except ImportError:
> >       from urlparse import urlparse
> >
> > +try:
> > +     from urllib.parse import unquote as urlunquote
> > +except ImportError:
> > +     from urllib import unquote as urlunquote
> > +
> >  if sys.hexversion >= 0x3000000:
> >       # pylint: disable=W0622
> >       basestring = str
> > @@ -1547,7 +1552,7 @@ def _parse_uri_map(cpv, metadata, use=None):
> >                       myuris.pop()
> >                       distfile = myuris.pop()
> >               else:
> > -                     distfile = os.path.basename(uri)
> > +                     distfile = urlunquote(os.path.basename(uri))
> >                       if not distfile:
> >                               raise portage.exception.InvalidDependString(
> >                                       ("getFetchMap(): '%s' SRC_URI has no file " + \
> > diff --git a/lib/portage/package/ebuild/fetch.py b/lib/portage/package/ebuild/fetch.py
> > index 28e7caf53..47c3ad28f 100644
> > --- a/lib/portage/package/ebuild/fetch.py
> > +++ b/lib/portage/package/ebuild/fetch.py
> > @@ -26,6 +26,11 @@ try:
> >  except ImportError:
> >       from urlparse import urlparse
> >
> > +try:
> > +     from urllib.parse import quote as urlquote
> > +except ImportError:
> > +     from urllib import quote as urlquote
> > +
> >  import portage
> >  portage.proxy.lazyimport.lazyimport(globals(),
> >       'portage.package.ebuild.config:check_config_instance,config',
> > @@ -351,7 +356,7 @@ _size_suffix_map = {
> >
> >  class FlatLayout(object):
> >       def get_path(self, filename):
> > -             return filename
> > +             return urlquote(filename)
> >
> >       def get_filenames(self, distdir):
> >               for dirpath, dirnames, filenames in os.walk(distdir,
> > @@ -382,7 +387,7 @@ class FilenameHashLayout(object):
> >                       c = c // 4
> >                       ret += fnhash[:c] + '/'
> >                       fnhash = fnhash[c:]
> > -             return ret + filename
> > +             return ret + urlquote(filename)
> >
> >       def get_filenames(self, distdir):
> >               pattern = ''
> >
>
> We've also got these other basename calls in fetch.py:
>
> > diff --git a/lib/portage/package/ebuild/fetch.py b/lib/portage/package/ebuild/fetch.py
> > index 28e7caf53..56b375d58 100644
> > --- a/lib/portage/package/ebuild/fetch.py
> > +++ b/lib/portage/package/ebuild/fetch.py
> > @@ -730,9 +730,9 @@ def fetch(myuris, mysettings, listonly=0, fetchonly=0,
> >         else:
> >                 for myuri in myuris:
> >                         if urlparse(myuri).scheme:
> > -                               file_uri_tuples.append((os.path.basename(myuri), myuri))
> > +                               file_uri_tuples.append((urlunquote(os.path.basename(myuri)), myuri))
> >                         else:
> > -                               file_uri_tuples.append((os.path.basename(myuri), None))
> > +                               file_uri_tuples.append((urlunquote(os.path.basename(myuri)), None))

I'm not sure how to reach this particular code path. In my testing,
the fetch() function gets passed an OrderedDict in myuris, and the
filenames have already been unquoted, so we don't want to do it again.

Any idea how this "else" block would ever be executed?