From 59d2d46d507db7469d0dc4c8ccd54f3e1da12f04 Mon Sep 17 00:00:00 2001 From: Ivanq Date: Sun, 28 Mar 2021 10:47:55 +0300 Subject: [PATCH] Update find-duplicates.py --- find-duplicates.py | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/find-duplicates.py b/find-duplicates.py index 033d1f0e6..04031bd09 100644 --- a/find-duplicates.py +++ b/find-duplicates.py @@ -2,15 +2,23 @@ import os from collections import defaultdict +file_name_by_name = defaultdict(list) file_name_by_link = defaultdict(list) for file_name in sorted(os.listdir("_data/signed")): with open(f"_data/signed/{file_name}") as f: contents = f.read().replace("\r", "") + name = next(line for line in contents.split("\n") if line.startswith("name:"))[5:].strip() link = next(line for line in contents.split("\n") if line.startswith("link:"))[5:].strip() - if link == "/#": + if name[0] == name[0].lower() or " " in name: # looks like a nickname or a full name + file_name_by_name[name].append(file_name) + if link != "/#": + file_name_by_link[link].append(file_name) + +for name, file_names in file_name_by_name.items(): + if len(file_names) == 1: continue - file_name_by_link[link].append(file_name) + print(name, "duplicates:", file_names) for link, file_names in file_name_by_link.items(): if len(file_names) == 1: