Skip to content

Instantly share code, notes, and snippets.

@jeremyf
Created July 23, 2012 17:25
Show Gist options
  • Save jeremyf/3164862 to your computer and use it in GitHub Desktop.
Save jeremyf/3164862 to your computer and use it in GitHub Desktop.
Latin1 to UTF8 character encoding correction for mysql
# Copyright (C) 2012 Jeremy Friesen
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
#
# The below script attempts to automate the character encoding challenges
# encountered with mysql, latin1 and UTF8.
#
# Much guidance and inspiration is drawn from
# http://www.bluebox.net/news/2009/07/mysql_encoding/
#
# This is a destructive script, so make sure you take precautions with your
# data. I ended up taking the above advice, stopping the mysql server, `tar`-ing
# the data, updating the config, and starting the process.
#
# Good luck! This won't fix it all, but it can help.
#
DB_CONFIG = YAML.load_file(Rails.root.join('config/database.yml').to_s)[Rails.env]
DB_CONFIG['username'] ||= 'root'
MYSQL_PARAMS = "-u#{DB_CONFIG['username']} #{'-p' << DB_CONFIG['password'] if DB_CONFIG['password']} #{'-h' << DB_CONFIG['host'] if DB_CONFIG['host']} #{DB_CONFIG['database']}".freeze
def attempt_conversion
ActiveRecord::Base.connection.select_all(%(show table status where collation like '%latin1%')).each do |options|
table_name = options['Name']
puts "Started Processing\t#{table_name}"
FileUtils.mkdir_p(Rails.root.join('tmp/db-conversion'))
filename_pre_transform = Rails.root.join("tmp/db-conversion/conductor.#{table_name}.pre.sql").to_s
commands = []
commands << %(mysqldump #{MYSQL_PARAMS} --opt --skip-set-charset --default-character-set=latin1 --skip-extended-insert --tables #{table_name} > #{filename_pre_transform})
commands << %(perl -i -pe 's/DEFAULT CHARSET=latin1/DEFAULT CHARSET=utf8/' #{filename_pre_transform})
filename_to_load = filename_pre_transform
commands << %(mysql #{MYSQL_PARAMS} < #{filename_to_load})
system(commands.join(';'))
puts "Finished Processing\t#{table_name}"
end
end
def verify_character_encoding_at_table_level
schema_query = %(
SELECT TABLE_SCHEMA,
TABLE_NAME,
CCSA.CHARACTER_SET_NAME AS DEFAULT_CHAR_SET,
COLUMN_NAME,
COLUMN_TYPE,
C.CHARACTER_SET_NAME
FROM information_schema.TABLES AS T
JOIN information_schema.COLUMNS AS C USING (TABLE_SCHEMA, TABLE_NAME)
JOIN information_schema.COLLATION_CHARACTER_SET_APPLICABILITY AS CCSA
ON (T.TABLE_COLLATION = CCSA.COLLATION_NAME)
WHERE TABLE_SCHEMA=SCHEMA()
AND C.DATA_TYPE IN ('enum', 'varchar', 'char', 'text', 'mediumtext', 'longtext')
ORDER BY TABLE_SCHEMA,
TABLE_NAME,
COLUMN_NAME
)
ActiveRecord::Base.connection.select_all(schema_query).each do |options|
table_name = options['TABLE_NAME']
column_name = options['COLUMN_NAME']
sub_query = "SELECT count(`#{column_name}`) AS count FROM `#{table_name}` WHERE LENGTH(`#{column_name}`) != CHAR_LENGTH(`#{column_name}`);"
response = ActiveRecord::Base.connection.select_one(sub_query)
if response['count'].to_i > 0
puts "Found `#{table_name}`.`#{column_name}`\t#{response['count']}"
convert_double_encoded(table_name, column_name, options['COLUMN_TYPE'])
end
end
end
def convert_double_encoded(table_name, column_name, column_type)
puts "Processing `#{table_name}`.`#{column_name}`"
# normalized_column_type = column_type.sub(/\([^\)]\)/,'').strip
temp_table_name = "temp_#{table_name}_#{column_name}"
ActiveRecord::Base.connection.execute(
"DROP TABLE IF EXISTS `#{temp_table_name}`"
)
ActiveRecord::Base.connection.execute(
"CREATE TABLE `#{temp_table_name}`
(
SELECT * FROM `#{table_name}`
WHERE LENGTH(`#{column_name}`) != CHAR_LENGTH(`#{column_name}`)
)"
)
ActiveRecord::Base.connection.execute(
"ALTER TABLE `#{temp_table_name}`
MODIFY `#{temp_table_name}`.`#{column_name}` #{column_type} CHARACTER SET latin1"
)
ActiveRecord::Base.connection.execute(
"ALTER TABLE `#{temp_table_name}`
MODIFY `#{temp_table_name}`.`#{column_name}` BLOB"
)
ActiveRecord::Base.connection.execute(
"ALTER TABLE `#{temp_table_name}`
MODIFY `#{temp_table_name}`.`#{column_name}` #{column_type} CHARACTER SET UTF8"
)
ActiveRecord::Base.connection.execute(
"DELETE FROM `#{temp_table_name}`
WHERE LENGTH(`#{column_name}`) = CHAR_LENGTH(`#{column_name}`)"
)
ActiveRecord::Base.connection.execute(
"REPLACE INTO `#{table_name}` (SELECT * FROM `#{temp_table_name}`)"
)
ActiveRecord::Base.connection.execute(
"DROP TABLE IF EXISTS `#{temp_table_name}`"
)
end
attempt_conversion
verify_character_encoding_at_table_level
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment