Improve error reporting

Author: frederic-tingaud-sonarsource

Diff for: rspec-tools/rspec_tools/checklinks.py

@@ -3,7 +3,9 @@
 import json
 import pathlib
 import random
+import re
 import socket
+from collections import defaultdict
 from urllib.parse import urlparse
 
 import requests
@@ -31,9 +33,24 @@
   "https://www.baeldung.com/",
 ]
 
-def show_files(filenames):
-  for filename in filenames:
-    print(filename)
+RULE_LANG_IN_PATH = re.compile(r'.*[\/\\](S\d{3,})[\/\\]([^\/]*)[\/\\]rule.html')
+
+def report_files(filenames):
+  lang_by_rule = defaultdict(list)
+  for file in filenames:
+    m = re.fullmatch(RULE_LANG_IN_PATH, file)
+    if m is not None:
+      lang_by_rule[m[1]].append(m[2])
+  res = ''
+  for k, v in lang_by_rule.items():
+    langs = ','.join(v)
+    res += f'|  {k} ({langs})'
+  return res
+
+
+def error_message_for_domain(errors, urls):
+  return '|\n'.join(f'| {key} in:\n' + report_files(urls[key]) for key in errors)
+
 
 def load_url_probing_history():
   global link_probes_history
@@ -222,9 +239,7 @@ def report_errors(errors, urls):
   by_domain = dict((k, list(g)) for k, g in itertools.groupby(errors, lambda url: urlparse(url).netloc))
   for k, v in by_domain.items():
     print(f"For domain = {k}")
-    for key in v:
-      print(f"{key} in:")
-      show_files(urls[key])
+    print(error_message_for_domain(v, urls))
     print("")
 
 def check_html_links(dir):