v0.2 - Add debugging

goss-correctencoding.rb

@@ -1,7 +1,7 @@
 # Federated Computer, Inc.
 # David Sainty <saint@federated.computer>  2024 A.D.
 # Gossamer Threads to Discourse -- Correct Encoding
-# v0.1 New script
+# v0.2 Debugging
 
 require 'mysql2'
 require 'active_record'
@@ -31,20 +31,22 @@ class GossamerForumsCorrectEncoding < ImportScripts::Base
 
   # Method to detect and fix text encoding
   def fix_text_encoding(text)
-    # Detect encoding
+    begin
-    detection = CharlockHolmes::Detect.detect(text)
+      # Detect encoding
-    original_encoding = detection[:encoding]
+      detection = CharlockHolmes::Detect.detect(text)
-    puts "Original encoding detected: #{original_encoding}"
+      original_encoding = detection[:encoding]
-
+      puts "Original encoding detected: #{original_encoding}"
-    if original_encoding == 'ISO-8859-1'
+  
-      text.force_encoding('ISO-8859-1').encode('UTF-8')
+      if original_encoding == 'ISO-8859-1'
-    else
+        text.force_encoding('ISO-8859-1').encode('UTF-8')
-      # Try to convert from detected encoding to UTF-8
+      else
-      text.encode('UTF-8', original_encoding, invalid: :replace, undef: :replace, replace: '?')
+        # Try to convert from detected encoding to UTF-8
-    end
+        text.encode('UTF-8', original_encoding, invalid: :replace, undef: :replace, replace: '?')
-  rescue StandardError => e
+      end
-    puts "Error during encoding conversion: #{e.message}"
+    rescue StandardError => e
-    text
+      puts "Error during encoding conversion: #{e.message}"
+      puts e.backtrace.join("\n")  # Print the full stack trace
+      text
   end
 
     # Method to fix encoding issues in post content
@@ -52,25 +54,32 @@ class GossamerForumsCorrectEncoding < ImportScripts::Base
     offset = 0
 
     loop do
-      posts = Post.limit(@batch_size).offset(offset)
+      puts "OFFSET:  #{offset}"
-      break if posts.empty?
+      begin
+        posts = Post.limit(@batch_size).offset(offset)
+        break if posts.empty?
 
-      posts.each do |post|
+        posts.each do |post|
-        raw_content = post.raw
+          raw_content = post.raw
-        fixed_content = fix_text_encoding(raw_content)
+          puts "--> NEXT POST:   post.id:  #{post.id}"
-        if fixed_content != raw_content
+          fixed_content = fix_text_encoding(raw_content)
-          puts "Updating post ##{post.id}"
+          if fixed_content != raw_content
-          puts "------- raw_content:\n#{raw_content}"
+            puts "Updating post #{post.id}"
-          puts "+++++++ fixed_content:\n#{fixed_content}"
+            puts "------- raw_content:\n#{raw_content}"
-          puts "---------------------------------------------------------------------------------------------"
+            puts "+++++++ fixed_content:\n#{fixed_content}"
-          # post.update(raw: fixed_content)
+            puts "---------------------------------------------------------------------------------------------"
-#          post.raw = fixed_content
+            # post.update(raw: fixed_content)
-#          if post.save
+#            post.raw = fixed_content
-#            puts "Post ##{post.id} updated successfully."
+#            if post.save
-#          else
+#              puts "Post ##{post.id} updated successfully."
-#            puts "Failed to update Post ##{post.id}: #{post.errors.full_messages.join(', ')}"
+#            else
-#          end
+#              puts "Failed to update Post ##{post.id}: #{post.errors.full_messages.join(', ')}"
+#            end
+          end
         end
+      rescue
+        puts "Error:  #{e.message}"
+        puts e.backtrace.join("\n")  # Print the full stack trace
       end
 
       offset += @batch_size