'use strict';
var Transform = require('stream').Transform;
var util = require('util');
var clone = require('clone');
var defaults = require('defaults');
/**
* Applies some basic formating to transcriptions:
* - Capitalize the first word of each sentence
* - Add a period to the end
* - Fix any "cruft" in the transcription
* - etc.
*
* @param {Object} opts
* @param {String} opts.model - some models / languages need special handling
* @param {String} [opts.hesitation='\u2026'] - what to put down for a "hesitation" event, defaults to an ellipsis (...)
* @param {Boolean} [options.objectMode=false] - emit `result` objects instead of string Buffers for the `data` events.
* @constructor
*/
function FormatStream(opts) {
this.options = defaults(opts, {
model: '', // some models should have all spaces removed
hesitation: '\u2026', // ellipsis
decodeStrings: false // false = don't convert strings to buffers before passing to _write
});
Transform.call(this, this.options);
this.isJaCn = ((this.options.model.substring(0,5) === 'ja-JP') || (this.options.model.substring(0,5) === 'zh-CN'));
this._transform = this.options.objectMode ? this.formatResult : this.formatString;
}
util.inherits(FormatStream, Transform);
var reHesitation = /%HESITATION\s/g; // when the service tetects a "hesitation" pause, it literally puts the string "%HESITATION" into the transcription
var reRepeatedCharacter = /(.)\1{2,}/g; // detect the same character repeated three or more times and remove it
var reDUnderscoreWords = /D_[^\s]+/g; // replace D_(anything)
/**
* Formats one or more words, removing special symbols, junk, and spacing for some languages
* @param {String} text
* @param {Boolean} isFinal
* @returns {String}
*/
FormatStream.prototype.clean = function clean(text) {
// clean out "junk"
text = text.trim().replace(reHesitation, this.options.hesitation)
.replace(reRepeatedCharacter, '')
.replace(reDUnderscoreWords,'');
// short-circuit if there's no actual text (avoids getting multiple periods after a pause)
if (!text) {
return text;
}
// remove spaces for Japanese and Chinese
if (this.isJaCn) {
text = text.replace(/ /g,'');
}
return text;
};
/**
* Capitalizes the first word of a sentence
* @param {String} text
* @returns {string}
*/
FormatStream.prototype.capitalize = function capitalize(text) {
// capitalize first word, returns '' in the case of an empty word
return text.charAt(0).toUpperCase() + text.substring(1);
};
/**
* puts a period on the end of a sentence
* @param {String} text
* @returns {string}
*/
FormatStream.prototype.period = function period(text) {
return text + (this.isJaCn ? '。' : '. ');
};
FormatStream.prototype.formatString = function(chunk, encoding, next) {
this.push(this.period(this.capitalize(this.clean(chunk.toString()))));
next();
};
/**
* Creates a new result with all transcriptions formatted
*
* @param {Object} result
* @param {String} encoding
* @param {Function} next
*/
FormatStream.prototype.formatResult = function formatResult(result, encoding, next) {
result = clone(result);
result.alternatives = result.alternatives.map(function(alt) {
alt.transcript = this.capitalize(this.clean(alt.transcript));
if (result.final) {
alt.transcript = this.period(alt.transcript);
}
if (alt.timestamps) {
alt.timestamps = alt.timestamps.map(function(ts, i, arr) {
// timestamps is an array of arrays, each sub-array is in the form ["word", startTime, endTime]'
ts[0] = this.clean(ts[0]);
if (i === 0) {
ts[0] = this.capitalize(ts[0]);
}
if (i === arr.length - 1 && result.final) {
ts[0] = this.period(ts[0]);
}
return ts;
}, this);
// todo: remove any timestamps without a word (due to cleaning out junk words)
}
return alt;
}, this);
this.push(result);
next();
};
FormatStream.prototype.promise = require('./to-promise');
module.exports = FormatStream;