src/konflux-rpm-lockfile: use coreos-pool URLs only

Until now, we tackled the DNF5 issue [1] by prioritizing the URL
location of the repo 'coreos-pool' when multiple repo were found
for the say locked NEVRA.
But, if that locked NEVRA has only one URL location coming from
the fedora repos i.e: fedora, fedora-updates, then the repoquery
command returns a broken URL location for ppc64le and s390x arches
because of the DNF5 issue. It returns the URL from the first item
defined in baseurl, whereas the resolution worked with the second
item i.e fedora-secondary repo where the RPMs for ppc64le and
s390x are available.

This patch fixes this issue with another approach wich consists
of using coreos-pool URLs only. For each non coreos-pool URL we
extract the NEVRA and arch to construct the URL into the
canonical koji path structure. As soon as the 'bump-lockfile'
commit is merged, the coreos-koji-tagger will tag to 'coreos-pool'.
So it's safe to craft the URL prior its availability.
One downside is a possible race condition between the koji
tag operation and the CI/CD system building hermetically. The other
downside is that the `rpms.lock.yaml` changes cannot be tested
locally as this relies on remote koji tagging operation. But,
as it's consumed for Konflux only now, I'd say it's ok.

[1] rpm-software-management/dnf5#2466

Author: joelcapitao

src/konflux-rpm-lockfile

@@ -6,11 +6,51 @@ import os
 import sys
 import subprocess
 import yaml
+import re
 
 sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
 from cosalib.cmdlib import get_basearch
 
 
+def use_koji_url_only(url_list):
+    """
+    Returns a list of package URLs to point only to our koji coreos-pool.
+    If a URL is not a coreos-pool one, then we extract the arch and NEVRA from
+    it and we construct the new one into the canonical koji path structure.
+    """
+    koji_url_base = "https://kojipkgs.fedoraproject.org/repos-dist/coreos-pool"
+    updated_list = []
+    for url in url_list:
+        if koji_url_base in url:
+            updated_list.append(url)
+            continue
+        nevra = url.split("/")[-1]
+        arch = extract_arch_from_url(url)
+        koji_url_base_with_arch = koji_url_base + f"/latest/{arch}/Packages"
+        new_url = "/".join([koji_url_base_with_arch,
+                            nevra[0].lower(),
+                            nevra])
+        updated_list.append(new_url)
+    return updated_list
+
+
+def extract_arch_from_url(url):
+    """
+    Extracts the arch value from the URL.
+    """
+    arches = ['x86_64', 'aarch64', 'ppc64le', 's390x']
+    # using word boundaries (\b) to ensure we match a full architecture name.
+    # this means the chars immediately surrounding the arch string must be
+    # non-word characters e.g: "/"
+    architecture_pattern = re.compile(
+        r'\b(' + '|'.join(re.escape(a) for a in arches) + r')\b')
+    match = architecture_pattern.search(url)
+    if match:
+        return match.group(1)
+    else:
+        return None
+
+
 def format_packages_with_repoid(pkgs, repos):
     """
     Takes a list of package URLs and repos and returns a list
@@ -118,10 +158,6 @@ def query_packages_location(locks, repoquery_args):
             continue
         name, url = line.split(' ')
         # Prioritize the url from fedora-coreos-pool
-        # there is a bug in dnf here where the url returned is incorrect when the
-        # repofile have more than one baseurl, which causes ppc64le and s390x
-        # urls comming from fedora and fedora-updates to be invalid
-        # See https://github.com/rpm-software-management/dnf5/issues/2466
         existing_url = processed_urls.get(name, None)
         if 'coreos-pool' in url or not existing_url:
             processed_urls[name] = url
@@ -201,6 +237,8 @@ def generate_main(args):
             # we have to specify both --arch and --forcearch to get both result for $arch and $noarch
             arch_args = ['--forcearch', arch, '--arch', arch, '--arch', 'noarch']
         pkg_urls = query_packages_location(locks, repoquery_args + arch_args)
+        # we only want coreos-pool URLs
+        pkg_urls = use_koji_url_only(pkg_urls)
         packages.append({'arch': arch, 'packages': pkg_urls})
 
     lockfile = write_hermeto_lockfile(packages, repos)