@lobehub/tts
Version:
A high-quality & reliable TTS React Hooks library
61 lines • 3.96 kB
JavaScript
function _createForOfIteratorHelper(o, allowArrayLike) { var it = typeof Symbol !== "undefined" && o[Symbol.iterator] || o["@@iterator"]; if (!it) { if (Array.isArray(o) || (it = _unsupportedIterableToArray(o)) || allowArrayLike && o && typeof o.length === "number") { if (it) o = it; var i = 0; var F = function F() {}; return { s: F, n: function n() { if (i >= o.length) return { done: true }; return { done: false, value: o[i++] }; }, e: function e(_e) { throw _e; }, f: F }; } throw new TypeError("Invalid attempt to iterate non-iterable instance.\nIn order to be iterable, non-array objects must have a [Symbol.iterator]() method."); } var normalCompletion = true, didErr = false, err; return { s: function s() { it = it.call(o); }, n: function n() { var step = it.next(); normalCompletion = step.done; return step; }, e: function e(_e2) { didErr = true; err = _e2; }, f: function f() { try { if (!normalCompletion && it.return != null) it.return(); } finally { if (didErr) throw err; } } }; }
function _unsupportedIterableToArray(o, minLen) { if (!o) return; if (typeof o === "string") return _arrayLikeToArray(o, minLen); var n = Object.prototype.toString.call(o).slice(8, -1); if (n === "Object" && o.constructor) n = o.constructor.name; if (n === "Map" || n === "Set") return Array.from(o); if (n === "Arguments" || /^(?:Ui|I)nt(?:8|16|32)(?:Clamped)?Array$/.test(n)) return _arrayLikeToArray(o, minLen); }
function _arrayLikeToArray(arr, len) { if (len == null || len > arr.length) len = arr.length; for (var i = 0, arr2 = new Array(len); i < len; i++) arr2[i] = arr[i]; return arr2; }
import { markdownToTxt } from 'markdown-to-txt';
var toHalfWidthAndCleanSpace = function toHalfWidthAndCleanSpace(str) {
return markdownToTxt(str).replaceAll(/[\uFF01-\uFF5E]/g, function (ch) {
return String.fromCharCode(ch.charCodeAt(0) - 0xFEE0);
}).replaceAll("\u3000", ' ').replaceAll('。', '.').replaceAll('，', ',').replaceAll('！', '!').replaceAll('？', '?').replaceAll('；', ';').replaceAll('：', ':').replaceAll('（', '(').replaceAll('）', ')').replaceAll('【', '[').replaceAll('】', ']').replaceAll('《', '<').replaceAll('》', '>').replaceAll('“', '"').replaceAll('”', '"').replaceAll('‘', "'").replaceAll('’', "'").replaceAll('\n', '. ').replaceAll(/\s+/g, ' ');
};
export var splitTextIntoSegments = function splitTextIntoSegments(text) {
var chunkSize = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : 100;
text = toHalfWidthAndCleanSpace(text);
var chunks = [];
var paragraphs = text.split('\n');
var currentChunk = '';
function addChunk(chunk) {
if (chunk.trim()) {
chunks.push(chunk.trim());
}
}
var _iterator = _createForOfIteratorHelper(paragraphs),
_step;
try {
for (_iterator.s(); !(_step = _iterator.n()).done;) {
var paragraph = _step.value;
if (currentChunk.length + paragraph.length + 1 > chunkSize && currentChunk.length > 0) {
addChunk(currentChunk);
currentChunk = '';
}
if (paragraph.length > chunkSize) {
var sentences = paragraph.match(/[^!.?]+[!.?]+/g) || [paragraph];
var _iterator2 = _createForOfIteratorHelper(sentences),
_step2;
try {
for (_iterator2.s(); !(_step2 = _iterator2.n()).done;) {
var sentence = _step2.value;
if (currentChunk.length + sentence.length + 1 > chunkSize && currentChunk.length > 0) {
addChunk(currentChunk);
currentChunk = '';
}
currentChunk += (currentChunk ? ' ' : '') + sentence.trim();
}
} catch (err) {
_iterator2.e(err);
} finally {
_iterator2.f();
}
} else {
currentChunk += (currentChunk ? '\n' : '') + paragraph;
}
}
} catch (err) {
_iterator.e(err);
} finally {
_iterator.f();
}
if (currentChunk) {
addChunk(currentChunk);
}
return chunks;
};