Generate filtered file lists for fedfind to use

This adds `filterlist` files alongside the `fullfilelist` and
`fullfiletimelist` files. These are much, much shorter lists
which skip the entries for packages, ARM device tree boot files
and directories. They are intended for consumption by fedfind,
so it can stop using rync scraping to discover the image files
it looks for. To enable this, we update to a newer version of
`create-filelist` from upstream `quick-fedora-mirror` and make
`update-fullfiletimelist` create the filterlist files as well.

We also delete a couple of old copies of `create-filelist`;
nirik made the two roles that use it share a common copy a few
months back, but missed deleting the copy each role had in its
`files` directory.

1 files changed, 9 insertions, 1 deletions

diff --git a/files/scripts/create-filelist b/files/scripts/create-filelist
index eeba9d089..8fc336736 100755
--- a/files/scripts/create-filelist
+++ b/files/scripts/create-filelist
@@ -57,7 +57,9 @@ def recursedir(path='.', skip=[], alwaysskip=['.~tmp~']):
 def parseopts():
     null = open(os.devnull, 'w')
     p = argparse.ArgumentParser(
-        description='Generate a list of files and times, suitable for consumption by quick-fedora-mirror.')
+        description='Generate a list of files and times, suitable for consumption by quick-fedora-mirror, '
+                    'and a much smaller list with packages, Device Tree boot files, HTML files and '
+                    'directories filtered out, for consumption by fedfind.')
     p.add_argument('-c', '--checksum', action='store_true',
                    help='Include checksums of all repomd.xml files in the file list.')
     p.add_argument('-C', '--checksum-file', action='append', dest='checksum_files',
@@ -73,6 +75,8 @@ def parseopts():
                    help='Filename of the file list with times (default: stdout).')
     p.add_argument('-f', '--filelist', type=argparse.FileType('w'), default=null,
                    help='Filename of the file list without times (default: no plain file list is generated).')
+    p.add_argument('-F', '--filterlist', type=argparse.FileType('w'), default=null,
+                   help='Filename of the filtered file list for fedfind (default: not generated).')
 
     opts = p.parse_args()
 
@@ -107,6 +111,10 @@ def main():
     for entry in recursedir(skip=opts.skip_files):
         # opts.filelist.write(entry.path + '\n')
         print(entry.path, file=opts.filelist)
+        # write to filtered list if appropriate
+        skips = ('.rpm', '.drpm', '.dtb', '.html')
+        if not any(entry.path.endswith(skip) for skip in skips) and not (entry.is_dir()):
+            print(entry.path, file=opts.filterlist)
         if entry.name in opts.checksum_files:
             checksums[entry.path[2:]] = True
         info = entry.stat(follow_symlinks=False)