From c30ee7397749c4794ee6de8cf96e12047a67a076 Mon Sep 17 00:00:00 2001
From: Felipe <41008398+StrawberryMaster@users.noreply.github.com>
Date: Sat, 26 Jul 2025 20:58:50 +0000
Subject: [PATCH] Sanitize file_id we were not consistently handling non-UTF-8
 characters here, especially after commit
 e4487baafcab64d2b81a5fd7a6b572ac8fa772e2. This also fixes #25

---
 lib/wayback_machine_downloader.rb | 13 ++-----------
 1 file changed, 2 insertions(+), 11 deletions(-)

diff --git a/lib/wayback_machine_downloader.rb b/lib/wayback_machine_downloader.rb
index eee812d..cf6c2e4 100644
--- a/lib/wayback_machine_downloader.rb
+++ b/lib/wayback_machine_downloader.rb
@@ -115,7 +115,7 @@ class WaybackMachineDownloader
   include ArchiveAPI
   include SubdomainProcessor
 
-  VERSION = "2.3.12"
+  VERSION = "2.3.11"
   DEFAULT_TIMEOUT = 30
   MAX_RETRIES = 3
   RETRY_DELAY = 2
@@ -352,16 +352,6 @@ class WaybackMachineDownloader
     file_versions.values
   end
 
-  # Returns a list of files for the composite snapshot
-  def get_file_list_composite_snapshot(target_timestamp)
-    file_list = get_composite_snapshot_file_list(target_timestamp)
-    file_list = file_list.sort_by { |_,v| v[:timestamp].to_s }.reverse
-    file_list.map do |file_remote_info|
-      file_remote_info[1][:file_id] = file_remote_info[0]
-      file_remote_info[1]
-    end
-  end
-
   def get_file_list_curated
     file_list_curated = Hash.new
     get_all_snapshots_to_consider.each do |file_timestamp, file_url|
@@ -694,6 +684,7 @@ class WaybackMachineDownloader
     file_timestamp = file_remote_info[:timestamp]
     
     # sanitize file_id to ensure it is a valid path component
+    file_id = file_id.tidy_bytes if file_id
     raw_path_elements = file_id.split('/')
 
     sanitized_path_elements = raw_path_elements.map do |element|