Skip to content

topce/auto-translate-json-library

Repository files navigation

About project

This project is used in, (and refactored from) excellent vs code extension Auto Translate JSON https://marketplace.visualstudio.com/items?itemName=JeffJorczak.auto-translate-json

It opens possibility to use Auto Translation JSON not just in vs code but as a library and command line interface

You can use Azure,AWS,Google,DeepL,Open AI or local OPEN AI compatible REST API for example ollama because it is compatible with Open AI https://ollama.com/blog/openai-compatibility :

Use as library

npm i auto-translate-json-library
import { translate, Configuration } from 'auto-translate-json-library';

let config: Configuration = {} as Configuration;

// set google api key
config.translationKeyInfo = {
          kind: 'google',
          apiKey: googleApiKey
        };
const pivotTranslation="./en.json";
await translate(pivotTranslation, config) ;
// translation for example fr.json in same folder as pivotTranslation should contain the translations

Use as command line tool

first install it

npm i auto-translate-json-library

do not forget to set translation engine parameters in environment variables or .env file

node node_modules\auto-translate-json-library\index.js --pivotTranslation=./translations/en.json

Contribute

Clone repo you can use the following commands

install ollama run ollama run llama2 rename ollama.env to .env install build project and run it

npm i
npm run build
node .\build\src\index.js --pivotTranslation=./tests/translations/en.json

After some time you should see es.json file with translation

CLI PARAMETERS

mode,
file or folder,
default is file

startDelimiter,
start delimiter,
default is {

endDelimiter,
end delimiter,
default is }

keepExtraTranslations,
keep extra translations (not present in pivot translation),
default is keep,
it could be keep or remove

keepTranslations,
keep existing translations,
default is keep
it could be keep or retranslate

sourceLocale
source locale
it could be en or fr ...
if specified it must match with pivot translation

pivotTranslation
pivot translation file that will be used as source for translations

ignorePrefix 
ignore translation that key starts with ignore prefix

# ENVIRONMENT VARIABLES

google parameters
ATJ_GOOGLE_API_KEY=

aws parameters
ATJ_AWS_ACCESS_KEY_ID=
ATJ_AWS_SECRET_ACCESS_KEY=
ATJ_AWS_REGION=

azure parameters
ATJ_AZURE_SECRET_KEY=
ATJ_AZURE_REGION=

deepl pro parameters
ATJ_DEEPL_PRO_SECRET_KEY=
deepl free parameters
ATJ_DEEPL_FREE_SECRET_KEY=

OpenAI parameters 
ATJ_OPEN_AI_SECRET_KEY=
ATJ_OPEN_AI_BASE_URL= 
default value "https://api.openai.com/v1",
ATJ_OPEN_AI_MODEL 
default value gpt-3.5-turbo
ATJ_OPEN_AI_MAX_TOKENS 
default value 256
ATJ_OPEN_AI_TEMPERATURE 
default value 0
ATJ_OPEN_AI_TOP_P 
default value 1.0
ATJ_OPEN_AI_N 
default value 1
ATJ_OPEN_AI_FREQUENCY_PENALTY 
default value 0
ATJ_OPEN_AI_PRESENCE_PENALTY 
default value 0

If you want to run it locally without using Open AI but compatible API 
you need to modify base URL and model for example 
if you use jan https://jan.ai/ you can modify base url model and maximum number of tokens (you do not pay for tokens anymore), secret key is not important 
ATJ_OPEN_AI_SECRET_KEY=whatever
ATJ_OPEN_AI_BASE_URL=http://localhost:1337/v1
ATJ_OPEN_AI_MODEL=mistral-ins-7b-q4
ATJ_OPEN_AI_MAX_TOKENS=4096


start delimiter
ATJ_START_DELIMITER={{
end delimiter
ATJ_END_DELIMITER=}}

file or folder
ATJ_MODE=file

source locale
ATJ_SOURCE_LOCALE=en

keep or retranslate existing translations
ATJ_KEEP_TRANSLATIONS=keep

keep or remove extra translations
ATJ_KEEP_EXTRA_TRANSLATIONS=keep

ignore prefix translation keys to ignore
ATJ_IGNORE_PREFIX=

You can also use .env file to store environment variables

There is also improved version of CLI (since version 1.3.2) for example:

npm install -g auto-translate-library
atj tests/translations/en.json -e google -m file

You can also use it with npx

npx auto-translate-library tests/translations/en.json -e google -m file

Debug

  1. Create .env file in main folder with the desired key/keys from # ENVIRONMENT VARIABLES
  2. Add also in .env source locale "ATJ_SOURCE_LOCALE=en" to test from en
  3. npm run debug