linkcheck: add argparse

checks/linkcheck/main.py

@@ -2,8 +2,8 @@ import json
 import csv
 import re
 import sys
+import argparse
 import xml.etree.ElementTree as ET
-from typing import NoReturn
 
 
 def get_revision_timestamp(revision: ET.Element, ns: dict[str, str]) -> str:
@@ -24,8 +24,8 @@ def get_revision_timestamp(revision: ET.Element, ns: dict[str, str]) -> str:
 
 
 # filter out unimportant pages like Talk:, User:, and old revisions of posts
-def process_dump(dump_file: str, out_file: str) -> None:
-    tree = ET.parse(dump_file)
+def process_dump( args: argparse.Namespace) -> None:
+    tree = ET.parse(args.dump_file)
     root = tree.getroot()
 
     ns = {"mw": "http://www.mediawiki.org/xml/export-0.11/"}
@@ -60,22 +60,23 @@ def process_dump(dump_file: str, out_file: str) -> None:
                 if revision != latest_revision:
                     page.remove(revision)
 
-    tree.write(out_file, encoding="utf-8", xml_declaration=False)
+    tree.write(args.out_file, encoding="utf-8", xml_declaration=False)
 
 
-def badlinks_print(known_file: str, outfile: str) -> None:
-    with open(known_file, "r") as infile, open(outfile, "w") as of:
+def badlinks_print(args: argparse.Namespace) -> None:
+    # known_file: str, outfile: str) -> None:
+    with open(args.known_file, "r") as infile, open(args.outfile, "w") as of:
         for line in infile:
             stripped_line = line.strip()
             if stripped_line and not stripped_line.startswith("#"):
                 of.write(f"--exclude {stripped_line} ")
 
 
-def dump_link_map(jsonfile: str, dumpfile: str) -> None:
-    with open(jsonfile, "r") as json_file:
+def dump_link_map(args: argparse.Namespace) -> None:
+    with open(args.jsonfile, "r") as json_file:
         fail_data = json.load(json_file)
 
-    with open(dumpfile, mode="w", newline="", encoding="utf-8") as csv_file:
+    with open(args.dumpfile, mode="w", newline="", encoding="utf-8") as csv_file:
         csv_writer = csv.writer(csv_file, delimiter="\t", quotechar='"')
         csv_writer.writerow(["STATUS", "URL", "WIKIURL"])
 
@@ -106,44 +107,31 @@ def dump_link_map(jsonfile: str, dumpfile: str) -> None:
                         )
 
 
-def print_usage(status: int = 0) -> NoReturn:
-    print(
-        """
-Usage: python main.py [action] <inputfile> <outfile>
-  [action]     <inputfile>     <outfile>        what?
-  ——————————————————————————————————————————————————————————
-  filter       dumpxmlfile     outxmlfile       filter out unncesscary pages from dump
-  badlinks     badlinksfile    outfile          parse and print known allowed.links
-  dumplinkmap  jsonfile        outfilelinkmap   dumps a map of url and nixos article where it is present
-  help                                          prints this help message and exits
-"""
-    )
-    sys.exit(status)
-
-
 def main() -> None:
-    if len(sys.argv) < 2:
-        print_usage(1)
-    action = sys.argv[1]
-    if action in "filter|badlinks|dumplinkmap":
-        if len(sys.argv) != 4:
-            print_usage(1)
-    if action == "filter":
-        dump_file = sys.argv[2]
-        out_file = sys.argv[3]
-        process_dump(dump_file, out_file)
-    elif action == "badlinks":
-        known_file = sys.argv[2]
-        out_file = sys.argv[3]
-        badlinks_print(known_file, out_file)
-    elif action == "dumplinkmap":
-        jsonfile = sys.argv[2]
-        dumpfile = sys.argv[3]
-        dump_link_map(jsonfile, dumpfile)
-    elif action in "--help":
-        print_usage(0)
-    else:
-        print_usage(1)
+    parser = argparse.ArgumentParser(description="Process wiki dump files")
+    subparsers = parser.add_subparsers()
+    parser_filter = subparsers.add_parser("filter", help="Filter out unimportant pages")
+
+    parser_filter.add_argument("dump_file", type=str)
+    parser_filter.add_argument("out_file", type=str)
+    parser_filter.set_defaults(func=process_dump)
+
+    parser_badlinks = subparsers.add_parser(
+        "badlinks", help="Parse and print known allowed links"
+    )
+    parser_badlinks.add_argument("known_file", type=str)
+    parser_badlinks.add_argument("out_file", type=str)
+    parser_badlinks.set_defaults(func=badlinks_print)
+
+    parser_dumplinkmap = subparsers.add_parser(
+        "dumplinkmap", help="Dump a map of url and nixos article where it is present"
+    )
+    parser_dumplinkmap.add_argument("jsonfile", type=str)
+    parser_dumplinkmap.add_argument("dumpfile", type=str)
+    parser_dumplinkmap.set_defaults(func=dump_link_map)
+
+    args = parser.parse_args()
+    args.func(args)
 
 
 if __name__ == "__main__":