src/konflux-rpm-lockfile: update baseurl dynamically

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 until the issue [1] is fixed upstream. It's
designed to work only with the main fedora baseurl FQDN
i.e dl.fedoraproject.org and for ppc64le/s390x arches. It basically
updates the repos to use the fedora-secondary URL as the main one
as we know the RPMs for those arches lives there.

[1] rpm-software-management/dnf5#1673

Author: joelcapitao

src/konflux-rpm-lockfile

@@ -6,11 +6,58 @@ import os
 import sys
 import subprocess
 import yaml
+import shutil
+import tempfile
+import re
+from pathlib import Path
 
 sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
 from cosalib.cmdlib import get_basearch
 
 
+# TODO: remove the use of this function once the DNF5 issue is fixed
+#       c.f https://github.com/rpm-software-management/dnf5/issues/2466
+def copy_repo_files_to_temp_repo(context_dir, arch):
+    """
+    If the architecture is 'ppc64le' or 's390x', then we copy all '.repo' files
+    from contextdir to a new temporary directory. We then edit the baseurls.
+    If not, then we return context_dir without processing anything.
+    """
+    if arch not in ['ppc64le', 's390x']:
+        return context_dir
+    temp_repo_dir = Path(tempfile.mkdtemp())
+    context_path = Path(context_dir)
+    for source_path in context_path.rglob('*.repo'):
+        destination_path = temp_repo_dir / source_path.name
+        shutil.copy2(source_path, destination_path)
+        update_repo_baseurls(str(destination_path))
+    return str(temp_repo_dir)
+
+
+# TODO: remove the use of this function once the DNF5 issue is fixed
+#       c.f https://github.com/rpm-software-management/dnf5/issues/2466
+#       This is fragile as it relies on the repo definitions we are defining in the config dir
+#       but also on the Fedora URL structure that might evolve in the future.
+def update_repo_baseurls(repo_path):
+    """
+    Updates the baseurl in the repo file to use the fedora-secondary repo which
+    provides the RPMs for ppc64le and s390x arches.
+    """
+    old_baseurl_pattern = r"(baseurl=https?://dl\.fedoraproject\.org/)(.*)fedora/linux(.*)"
+    new_baseurl_replacement = r"\1\2fedora-secondary\3"
+    with open(repo_path, 'r', encoding='utf-8') as f:
+        content = f.read()
+    new_content, count = re.subn(
+        old_baseurl_pattern,
+        new_baseurl_replacement,
+        content,
+        flags=re.IGNORECASE | re.MULTILINE
+    )
+    if count > 0:
+        with open(repo_path, 'w', encoding='utf-8') as f:
+            f.write(new_content)
+
+
 def format_packages_with_repoid(pkgs, repos):
     """
     Takes a list of package URLs and repos and returns a list
@@ -117,13 +164,8 @@ def query_packages_location(locks, repoquery_args):
         if not line:
             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:
+        if not existing_url:
             processed_urls[name] = url
 
     pkg_urls = list(processed_urls.values())
@@ -179,7 +221,7 @@ def generate_main(args):
     repos += manifest_data.get('lockfile-repos', [])
 
     # Tell dnf to load repos files from $contextdir
-    repoquery_args = ["--refresh", "--quiet", f"--setopt=reposdir={contextdir}"]
+    repoquery_args = ["--refresh", "--quiet"]
     repoquery_args.extend([f"--repo={','.join(repos)}"])
 
     if releasever is None:
@@ -195,13 +237,16 @@ def generate_main(args):
             sys.exit(1)
         print(f"Resolving packages for {arch}...")
         arch_args = []
+        repos_dir = copy_repo_files_to_temp_repo(contextdir, arch)
         if arch is not get_basearch():
             # append noarch as well because otherwise those packages get excluded from results
             # We use --forcearch here because otherwise dnf still respect the system basearch
             # we have to specify both --arch and --forcearch to get both result for $arch and $noarch
-            arch_args = ['--forcearch', arch, '--arch', arch, '--arch', 'noarch']
+            arch_args = [f"--setopt=reposdir={repos_dir}", '--forcearch', arch, '--arch', arch, '--arch', 'noarch']
         pkg_urls = query_packages_location(locks, repoquery_args + arch_args)
         packages.append({'arch': arch, 'packages': pkg_urls})
+        if repos_dir != contextdir:
+            shutil.rmtree(repos_dir)
 
     lockfile = write_hermeto_lockfile(packages, repos)