d795301025
common.js needs to be loaded in all tests so that there is checking for variable leaks and possibly other things. However, it does not need to be assigned to a variable if nothing in common.js is referred to elsewhere in the test. The main tradeoff for this bit of code churn is that it gets the code base most of the way to being able to enable the no-unused-vars rule in eslint. (The non-tooling benefit is that it lessens cognitive load when reading tests as it is an immediate indication that none of the functions or properties in common.js will be used by the test.) PR-URL: https://github.com/nodejs/node/pull/4563 Reviewed-By: James M Snell <jasnell@gmail.com> Reviewed-By: Ben Noordhuis <info@bnoordhuis.nl>
99 lines
3 KiB
JavaScript
99 lines
3 KiB
JavaScript
'use strict';
|
|
require('../common');
|
|
var assert = require('assert');
|
|
var StringDecoder = require('string_decoder').StringDecoder;
|
|
|
|
process.stdout.write('scanning ');
|
|
|
|
// UTF-8
|
|
test('utf-8', new Buffer('$', 'utf-8'), '$');
|
|
test('utf-8', new Buffer('¢', 'utf-8'), '¢');
|
|
test('utf-8', new Buffer('€', 'utf-8'), '€');
|
|
test('utf-8', new Buffer('𤭢', 'utf-8'), '𤭢');
|
|
// A mixed ascii and non-ascii string
|
|
// Test stolen from deps/v8/test/cctest/test-strings.cc
|
|
// U+02E4 -> CB A4
|
|
// U+0064 -> 64
|
|
// U+12E4 -> E1 8B A4
|
|
// U+0030 -> 30
|
|
// U+3045 -> E3 81 85
|
|
test(
|
|
'utf-8',
|
|
new Buffer([0xCB, 0xA4, 0x64, 0xE1, 0x8B, 0xA4, 0x30, 0xE3, 0x81, 0x85]),
|
|
'\u02e4\u0064\u12e4\u0030\u3045'
|
|
);
|
|
|
|
// UCS-2
|
|
test('ucs2', new Buffer('ababc', 'ucs2'), 'ababc');
|
|
|
|
// UTF-16LE
|
|
test('ucs2', new Buffer('3DD84DDC', 'hex'), '\ud83d\udc4d'); // thumbs up
|
|
|
|
console.log(' crayon!');
|
|
|
|
// test verifies that StringDecoder will correctly decode the given input
|
|
// buffer with the given encoding to the expected output. It will attempt all
|
|
// possible ways to write() the input buffer, see writeSequences(). The
|
|
// singleSequence allows for easy debugging of a specific sequence which is
|
|
// useful in case of test failures.
|
|
function test(encoding, input, expected, singleSequence) {
|
|
var sequences;
|
|
if (!singleSequence) {
|
|
sequences = writeSequences(input.length);
|
|
} else {
|
|
sequences = [singleSequence];
|
|
}
|
|
sequences.forEach(function(sequence) {
|
|
var decoder = new StringDecoder(encoding);
|
|
var output = '';
|
|
sequence.forEach(function(write) {
|
|
output += decoder.write(input.slice(write[0], write[1]));
|
|
});
|
|
process.stdout.write('.');
|
|
if (output !== expected) {
|
|
var message =
|
|
'Expected "' + unicodeEscape(expected) + '", ' +
|
|
'but got "' + unicodeEscape(output) + '"\n' +
|
|
'Write sequence: ' + JSON.stringify(sequence) + '\n' +
|
|
'Decoder charBuffer: 0x' + decoder.charBuffer.toString('hex') + '\n' +
|
|
'Full Decoder State: ' + JSON.stringify(decoder, null, 2);
|
|
assert.fail(output, expected, message);
|
|
}
|
|
});
|
|
}
|
|
|
|
// unicodeEscape prints the str contents as unicode escape codes.
|
|
function unicodeEscape(str) {
|
|
var r = '';
|
|
for (var i = 0; i < str.length; i++) {
|
|
r += '\\u' + str.charCodeAt(i).toString(16);
|
|
}
|
|
return r;
|
|
}
|
|
|
|
// writeSequences returns an array of arrays that describes all possible ways a
|
|
// buffer of the given length could be split up and passed to sequential write
|
|
// calls.
|
|
//
|
|
// e.G. writeSequences(3) will return: [
|
|
// [ [ 0, 3 ] ],
|
|
// [ [ 0, 2 ], [ 2, 3 ] ],
|
|
// [ [ 0, 1 ], [ 1, 3 ] ],
|
|
// [ [ 0, 1 ], [ 1, 2 ], [ 2, 3 ] ]
|
|
// ]
|
|
function writeSequences(length, start, sequence) {
|
|
if (start === undefined) {
|
|
start = 0;
|
|
sequence = [];
|
|
} else if (start === length) {
|
|
return [sequence];
|
|
}
|
|
var sequences = [];
|
|
for (var end = length; end > start; end--) {
|
|
var subSequence = sequence.concat([[start, end]]);
|
|
var subSequences = writeSequences(length, end, subSequence, sequences);
|
|
sequences = sequences.concat(subSequences);
|
|
}
|
|
return sequences;
|
|
}
|
|
|