Created
February 15, 2012 10:32
-
-
Save ejdyksen/1834933 to your computer and use it in GitHub Desktop.
Fix database encoding
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| require 'mysql2' | |
| SIMULATE = true | |
| DB_HOST = "localhost" | |
| DB_NAME = "database" | |
| DB_USER = "root" | |
| DB_PASS = "password" | |
| @client = Mysql2::Client.new( | |
| :host => DB_HOST, | |
| :username => DB_USER, | |
| :password => DB_PASS, | |
| :database => DB_NAME, | |
| :encoding => "UTF8") | |
| @binary_client = Mysql2::Client.new( | |
| :host => DB_HOST, | |
| :username => DB_USER, | |
| :password => DB_PASS, | |
| :database => DB_NAME, | |
| :encoding => "BINARY") | |
| @inf_schema_client = Mysql2::Client.new( | |
| :host => DB_HOST, | |
| :username => DB_USER, | |
| :password => DB_PASS, | |
| :database => "information_schema") | |
| @row_count = 0 | |
| @column_count = 0 | |
| @table_count = 0 | |
| @failed_queries = [] | |
| def fix_column(table_name, column_name, column_type) | |
| results = @binary_client.query("SELECT id, `#{column_name}` FROM `#{table_name}`") | |
| new_row = {} | |
| results.each do |result| | |
| if result[column_name] != nil | |
| id = result["id"] | |
| unicode_version = result[column_name].force_encoding("UTF-8") | |
| if unicode_version.bytes.count > unicode_version.length | |
| new_row[id] = unicode_version | |
| end | |
| end | |
| end | |
| change_encoding = "ALTER TABLE `#{table_name}` CHANGE `#{column_name}` `#{column_name}` #{column_type} CHARACTER SET utf8 NULL DEFAULT NULL" | |
| puts change_encoding | |
| @client.query(change_encoding) unless SIMULATE | |
| @column_count += 1 | |
| new_row.each do |id, new_value| | |
| begin | |
| sql = "UPDATE `#{table_name}` SET `#{column_name}`='#{@client.escape(new_value)}' WHERE id=#{id}" | |
| puts sql | |
| @client.query(sql) unless SIMULATE | |
| @row_count += 1 | |
| rescue Exception => e | |
| @failed_queries.push sql | |
| end | |
| end | |
| end | |
| def fix_columns | |
| columns = @inf_schema_client.query("SELECT * FROM `COLUMNS` WHERE `TABLE_SCHEMA` = '#{DB_NAME}' AND `character_set_name` = 'latin1'") | |
| columns.each do |column| | |
| fix_column(column["TABLE_NAME"], column["COLUMN_NAME"], column["COLUMN_TYPE"]) unless column["TABLE_NAME"] == "schema_migrations" | |
| end | |
| end | |
| def fix_tables | |
| results = @inf_schema_client.query("SELECT * FROM `TABLES` WHERE `TABLE_SCHEMA` = '#{DB_NAME}'") | |
| results.each do |result| | |
| sql = "ALTER TABLE `#{result["TABLE_NAME"]}` CHARACTER SET = utf8" | |
| puts sql | |
| @client.query(sql) unless SIMULATE | |
| @table_count += 1 | |
| end | |
| end | |
| def fix_db | |
| sql = "ALTER DATABASE CHARACTER SET 'utf8'" | |
| puts sql | |
| @client.query(sql) unless SIMULATE | |
| end | |
| fix_columns | |
| fix_tables | |
| fix_db | |
| puts | |
| puts "Only a simulation, relax" if SIMULATE | |
| puts "Rows changed: " + @row_count.to_s | |
| puts "Columns changed: " + @column_count.to_s | |
| puts "Tables changed: " + @table_count.to_s | |
| puts "Failed queries:" unless SIMULATE | |
| puts @failed_queries |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment