From 8c4ede12161bdd3b8e2a2a31e21d4df4db13e7b1 Mon Sep 17 00:00:00 2001
From: Danila Fedorin <danila.fedorin@gmail.com>
Date: Sun, 23 Feb 2025 13:19:35 -0800
Subject: [PATCH] WIP

---
 chatgpt-subset-one-go.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/chatgpt-subset-one-go.py b/chatgpt-subset-one-go.py
index f3ed3c7..cb2af75 100644
--- a/chatgpt-subset-one-go.py
+++ b/chatgpt-subset-one-go.py
@@ -16,6 +16,7 @@ def get_used_characters(files):
     """Collect unique characters from all .html files in the given directory."""
     char_set = set()
     for file in files:
+        print("extracting from", file)
         text = extract_text_from_html(file)
         char_set.update(text)
     return "".join(sorted(char_set))