Fix issue with .7z archives

Before, only fandom wikis dumps were compressed with .7z.
These archives can have several .xml files in the .7z; not just one.
So we need to have a flag for the fandom-2020 dumps.

This fixes the bug so .7z archives work in either case.

wikiq

@@ -704,17 +704,21 @@ class WikiqParser:
         line = rev_data.to_tsv_row()
         print(line, file=self.output_file)
 
-
-def open_input_file(input_filename):
+def match_archive_suffix(input_filename):
     if re.match(r'.*\.7z$', input_filename):
-        cmd = ["7za", "x", "-so", input_filename, "*.xml"]
+        cmd = ["7za", "x", "-so", input_filename]
     elif re.match(r'.*\.gz$', input_filename):
         cmd = ["zcat", input_filename]
     elif re.match(r'.*\.bz2$', input_filename):
         cmd = ["bzcat", "-dk", input_filename]
     else:
         raise ValueError("Unrecognized file type: %s" % input_filename)
+    return cmd
 
+def open_input_file(input_filename, fandom_2020=False):
+    cmd = match_archive_suffix(input_filename)
+    if fandom_2020:
+        cmd.append("*.xml")
     try:
         return Popen(cmd, stdout=PIPE).stdout
     except NameError:
@@ -787,6 +791,10 @@ def main():
                         action='append',
                         help="The label for the outputted column based on matching the regex in comments.")
 
+    parser.add_argument('--fandom-2020', dest="fandom_2020",
+                        action='store_true',
+                        help="Whether the archive is from the fandom 2020 dumps by Wikiteam. These dumps can have multiple .xml files in their archives.")
+
     args = parser.parse_args()
 
     # set persistence method
@@ -808,7 +816,7 @@ def main():
     if len(args.dumpfiles) > 0:
         output_parquet = False
         for filename in args.dumpfiles:
-            input_file = open_input_file(filename)
+            input_file = open_input_file(filename, args.fandom_2020)
 
             # open directory for output
             if args.output_dir: