Learn about our RFC process, Open RFC meetings & more.Join in the discussion! »

utf8-binary-cutter

0.9.2 • Public • Published

utf8-binary-cutter

a cutter

A small node.js lib to truncate UTF-8 strings to a given binary size. Useful when dealing with old systems handling UTF-8 as ascii/latin-1, for ex. MySQL or Oracle database.

Interesting reads :

Usage

  • Works on UTF-8 strings (javascript strings are UTF-8 unless you're doing fancy things)
var Cutter = require('utf8-binary-cutter');
  • getBinarySize() : returns the binary size of the given string
var utf8String = 'abc☃☃☃'; // abc then 3 times the UTF-8 « snowman » char which takes 3 bytes
 
console.log( Cutter.getBinarySize( utf8String ) );  // 12 = 1 + 1 + 1 + 3 + 3 + 3
  • truncateToBinarySize() truncate so that final binary size is lower or equal than the given limit :
var utf8String = 'abc☃☃☃'; // abc then 3 times the UTF-8 « snowman » char which takes 3 bytes
 
console.log( Cutter.truncateToBinarySize( utf8String, 20 ) ); // 'abc☃☃☃'  -> no change
console.log( Cutter.truncateToBinarySize( utf8String, 12 ) ); // 'abc☃☃☃'  -> no change
console.log( Cutter.truncateToBinarySize( utf8String, 11 ) ); // 'abc☃...' -> to avoid cutting utf8 chars,
  // the two last snowmen had to be removed. Final size = 9 bytes
console.log( Cutter.truncateToBinarySize( utf8String, 10 ) ); // 'abc☃...' -> idem
console.log( Cutter.truncateToBinarySize( utf8String,  9 ) ); // 'abc☃...' -> idem
console.log( Cutter.truncateToBinarySize( utf8String,  8 ) ); // 'abc...'
  • truncateFieldsToBinarySize() multiple truncations at the same time :
    • NOTE : returns a new object.
    • NOTE : iterates only on own properties
    • NOTE : only truncated strings are copied, other members are shared with original object.
var maxBinarySizes = {
  title: 40,
  content: 200
};
 
console.log( Cutter.truncateFieldsToBinarySize({
    title: '☃☃☃ A véry véry long title with UTF-8 ☃☃☃',
    content: 'I ❤ utf8-binary-cutter !',
    foo: 42
  },
  maxBinarySizes
));
 
--> {
  title: '☃☃☃ A véry véry long title wi...',
  content: 'I ❤ utf8-binary-cutter !',
  foo: 42
}
  • truncateToCharLength() normal truncate is also provided for convenience : truncate so that final char length is lower or equal than the given limit :
var utf8String = 'abc☃☃☃'; // 6 chars
 
console.log( Cutter.truncateToCharLength( utf8String, 10 ) ); // 'abc☃☃☃'  -> no change
console.log( Cutter.truncateToBinarySize( utf8String,  6 ) ); // 'abc☃☃☃'  -> no change
console.log( Cutter.truncateToBinarySize( utf8String,  5 ) ); // 'ab...'   -> 5 chars, ok
  • optional callback when truncating (useful for logging) :
truncateToBinarySize(foo, 42, function(maxBinarySize, originalString, truncatedString) {
  logger.warn(...
});

truncateToCharLength(foo, 42, function(maxCharLength, originalString, truncatedString) {
  logger.warn(...
});

Cutter.truncateFieldsToBinarySize({
    title: '☃☃☃ A véry véry long title with UTF-8 ☃☃☃',
    content: 'I ❤ utf8-binary-cutter !',
    foo: 42
  },
  // maxBinarySizes
  {
    title: 40,
    content: 200
  },
  // callback
  // will be called for each member truncated.
  // 4th param : the key of the member being truncated.
  function(maxCharLength, originalString, truncatedString, key) {
    logger.warn(...
  }
);

Contributing

  • clone repo
  • ensure your editor is decent and pick up the .editorconfig and .jshintrc files
  • npm install
  • npm test
  • add tests, add features, send a PR

Thanks !

Install

npm i utf8-binary-cutter

DownloadsWeekly Downloads

2,582

Version

0.9.2

License

public domain

Unpacked Size

39.9 kB

Total Files

11

Last publish

Collaborators

  • avatar
  • avatar
  • avatar
  • avatar
  • avatar
  • avatar
  • avatar
  • avatar