FEATURE: import phpBB avatars

This code adds all three avatar types to the import. Uploaded avatars and default gallery avatars are converted, hotlinked are pulled from the remote web site and stored as local. Beware, though: this is currently done during the importer run and can consume loong periods of time if many downloads fail with timeouts.

A minor fix concerns attachments to posts with white space in the real_name, this is handled properly now.

script/import_scripts/phpbb3.rb

@@ -1,5 +1,7 @@
 require File.expand_path(File.dirname(__FILE__) + "/../../config/environment")
 require File.expand_path(File.dirname(__FILE__) + "/base.rb")
+require_dependency 'url_helper'
+require_dependency 'file_helper'
 
 require "mysql2"
 
@@ -14,11 +16,23 @@ class ImportScripts::PhpBB3 < ImportScripts::Base
   ORIGINAL_SITE_PREFIX = "oldsite.example.com/forums" # without http(s)://
   NEW_SITE_PREFIX      = "http://discourse.example.com"  # with http:// or https://
 
-  # Set ATTACHMENTS_BASE_DIR to the base directory where attachment files are found.
+  # Set PHPBB_BASE_DIR to the base directory of your phpBB installation.
-  # If nil, [attachment] tags won't be processed.
+  # When importing, you should place the subdirectories "files" (containing all
+  # attachments) and "images" (containing avatars) in PHPBB_BASE_DIR.
+  # If nil, [attachment] tags and avatars won't be processed.
   # Edit AUTHORIZED_EXTENSIONS as needed.
-  ATTACHMENTS_BASE_DIR = nil
+  # If you used ATTACHMENTS_BASE_DIR before, e.g. ATTACHMENTS_BASE_DIR = '/var/www/phpbb/files/'
-  AUTHORIZED_EXTENSIONS = ['jpg', 'jpeg', 'png', 'gif', 'zip', 'rar']
+  # would become                                  PHPBB_BASE_DIR       = '/var/www/phpbb'
+  # now.
+  PHPBB_BASE_DIR        = '/var/www/phpbb'
+  AUTHORIZED_EXTENSIONS = ['jpg', 'jpeg', 'png', 'gif', 'zip', 'rar', 'pdf']
+
+  # Avatar types to import.:
+  #  1 = uploaded avatars (you should probably leave this here)
+  #  2 = hotlinked avatars - WARNING: this will considerably slow down your import
+  #                          if there are many hotlinked avatars and some of them unavailable!
+  #  3 = galery avatars   (the predefined avatars phpBB offers. They will be converted to uploaded avatars)
+  IMPORT_AVATARS       = [1, 3]
 
   def initialize
     super
@@ -29,6 +43,7 @@ class ImportScripts::PhpBB3 < ImportScripts::Base
       #password: "password",
       database: PHPBB_DB
     )
+    phpbb_read_config
   end
 
   def execute
@@ -36,7 +51,7 @@ class ImportScripts::PhpBB3 < ImportScripts::Base
     import_categories
     import_posts
     import_private_messages
-    import_attachments unless ATTACHMENTS_BASE_DIR.nil?
+    import_attachments unless PHPBB_BASE_DIR.nil?
     suspend_users
   end
 
@@ -51,7 +66,7 @@ class ImportScripts::PhpBB3 < ImportScripts::Base
 
     batches(BATCH_SIZE) do |offset|
       results = mysql_query(
-        "SELECT user_id id, user_email email, username, user_regdate, group_name
+        "SELECT user_id id, user_email email, username, user_regdate, group_name, user_avatar_type, user_avatar
            FROM phpbb_users u
            JOIN phpbb_groups g ON g.group_id = u.group_id
           WHERE g.group_name != 'BOTS'
@@ -68,7 +83,26 @@ class ImportScripts::PhpBB3 < ImportScripts::Base
           username: user['username'],
           created_at: Time.zone.at(user['user_regdate']),
           moderator: user['group_name'] == 'GLOBAL_MODERATORS',
-          admin: user['group_name'] == 'ADMINISTRATORS' }
+          admin: user['group_name'] == 'ADMINISTRATORS',
+          post_create_action: proc do |newmember|
+            if not PHPBB_BASE_DIR.nil? and IMPORT_AVATARS.include?(user['user_avatar_type']) and newmember.uploaded_avatar_id.blank?
+              path = phpbb_avatar_fullpath(user['user_avatar_type'], user['user_avatar']) and begin
+                upload = create_upload(newmember.id, path, user['user_avatar'])
+                  if upload.persisted?
+                    newmember.import_mode = false
+                    newmember.create_user_avatar
+                    newmember.import_mode = true
+                    newmember.user_avatar.update(custom_upload_id: upload.id)
+                    newmember.update(uploaded_avatar_id: upload.id)
+                  else
+                    puts "Error: Upload did not persist!"
+                  end
+                rescue SystemCallError => err
+                  puts "Could not import avatar: #{err.message}"
+              end
+            end
+          end 
+        }
       end
     end
   end
@@ -304,7 +338,7 @@ class ImportScripts::PhpBB3 < ImportScripts::Base
     setting = AUTHORIZED_EXTENSIONS.join('|')
     SiteSetting.authorized_extensions = setting if setting != SiteSetting.authorized_extensions
 
-    r = /\[attachment=[\d]+\]<\!-- [\w]+ --\>([\S]+)<\!-- [\w]+ --\>\[\/attachment\]/
+    r = /\[attachment=[\d]+\]<\!-- [\w]+ --\>([^<]+)<\!-- [\w]+ --\>\[\/attachment\]/
 
     user = Discourse.system_user
 
@@ -324,6 +358,12 @@ class ImportScripts::PhpBB3 < ImportScripts::Base
         matches = r.match(s)
         real_filename = matches[1]
 
+        # note: currently, we do not import PM attachments.
+        # If this should be desired, this has to be fixed,
+        # otherwise, the SQL state coughs up an error for the
+        # clause "WHERE post_msg_id = pm12345"...
+        next s if post.custom_fields['import_id'].start_with?('pm:')
+
         sql = "SELECT physical_filename,
                       mimetype
                  FROM phpbb_attachments
@@ -347,7 +387,7 @@ class ImportScripts::PhpBB3 < ImportScripts::Base
           next s
         end
 
-        filename = File.join(ATTACHMENTS_BASE_DIR, row['physical_filename'])
+        filename = File.join(PHPBB_BASE_DIR+'/files', row['physical_filename'])
         if !File.exists?(filename)
           puts "Attachment file doesn't exist: #{filename}"
           fail_count += 1
@@ -383,6 +423,64 @@ class ImportScripts::PhpBB3 < ImportScripts::Base
     puts ''
   end
 
+  # Read avatar config from phpBB configuration table.
+  # Stored there: - paths relative to the phpBB install path
+  #               - "salt", i.e. base filename for uploaded avatars
+  #
+  def phpbb_read_config
+    results = mysql_query("SELECT config_name, config_value
+                             FROM phpbb_config;")
+    if results.size<1
+      puts "could not read config... no avatars and attachments will be imported!"
+      return
+    end
+    results.each do |result|
+      if result['config_name']=='avatar_gallery_path'
+        @avatar_gallery_path  = result['config_value']
+      elsif result['config_name']=='avatar_path'
+        @avatar_path          = result['config_value']
+      elsif result['config_name']=='avatar_salt'
+        @avatar_salt          = result['config_value']
+      end
+    end
+  end
+
+  # Create the full path to the phpBB avatar specified by avatar_type and filename.
+  #
+  def phpbb_avatar_fullpath(avatar_type, filename)
+    case avatar_type
+    when 1 # uploaded avatar
+      filename.gsub!(/_[0-9]+\./,'.') # we need 1337.jpg, not 1337_2983745.jpg
+      path=@avatar_path
+      PHPBB_BASE_DIR+'/'+path+'/'+@avatar_salt+'_'+filename
+    when 3 # gallery avatar
+      path=@avatar_gallery_path
+      PHPBB_BASE_DIR+'/'+path+'/'+filename
+    when 2 # hotlinked avatar
+      begin
+        hotlinked = FileHelper.download(filename, SiteSetting.max_image_size_kb.kilobytes, "discourse-hotlinked")
+      rescue StandardError => err
+          puts "Error downloading avatar: #{err.message}. Skipping..."
+	  return nil
+      end
+      if hotlinked
+        if hotlinked.size <= SiteSetting.max_image_size_kb.kilobytes
+          return hotlinked
+        else
+          Rails.logger.error("Failed to pull hotlinked image: #{filename} - Image is bigger than #{@max_size}")
+            nil
+        end
+      else
+        Rails.logger.error("There was an error while downloading '#{filename}' locally.")
+        nil
+      end
+    else
+      puts 'Invalid avatar type #{avatar_type}, skipping'
+      nil
+    end
+  end
+
+
   def mysql_query(sql)
     @client.query(sql, cache_rows: false)
   end