Created
February 5, 2018 15:06
-
-
Save dacer/004fdd95ed9be76b743f1f11cff62129 to your computer and use it in GitHub Desktop.
translate JMDict
This file contains 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 "sqlite3" | |
require 'rest-client' | |
require 'json' | |
require 'open-uri' | |
# RestClient.proxy = "http://127.0.0.1:6152" | |
DB = SQLite3::Database.new "./JMDict(cn+en).sqlite3" | |
TARGET_LANG = "zh-CN" | |
def getTranslation(source, currentId) | |
begin | |
url = "https://translate.googleapis.com/translate_a/single?client=gtx&sl=en&tl=#{TARGET_LANG}&dt=t&q=#{URI::encode(source)}" | |
result = JSON.parse(RestClient.get(url))[0][0][0] | |
puts "#{source} => #{result}" | |
result | |
rescue Exception => e | |
puts "error, retry... #{e.message}" | |
sleep 10 | |
start(currentId) | |
end | |
end | |
def start(startId = 2828358) | |
DB.execute( "select * from entry WHERE id>=#{startId}" ) do |row| | |
puts row[0] | |
DB.execute "UPDATE entry SET gloss_cn=? WHERE id=#{row[0]}", getTranslation(row[1], row[0]) | |
end | |
end | |
def deleteDuplicateTranslation() | |
DB.execute( "select * from entry" ) do |row| | |
puts row[0] | |
newRow = row[3].split(",").uniq | |
# newRow = row[3].split(", ").uniq | |
puts "#{row[3]} => #{newRow}" | |
DB.execute "UPDATE entry SET gloss_cn=? WHERE id=#{row[0]}", newRow.join(", ") | |
end | |
end | |
# start() | |
# deleteDuplicateTranslation() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment