polyfact/dataloader/index.js

<h1 align="center">PolyFact</h1>

"use strict";
var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
    function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
    return new (P || (P = Promise))(function (resolve, reject) {
        function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
        function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
        function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
        step((generator = generator.apply(thisArg, _arguments || [])).next());
    });
};
var __generator = (this && this.__generator) || function (thisArg, body) {
    var _ = { label: 0, sent: function() { if (t[0] & 1) throw t[1]; return t[1]; }, trys: [], ops: [] }, f, y, t, g;
    return g = { next: verb(0), "throw": verb(1), "return": verb(2) }, typeof Symbol === "function" && (g[Symbol.iterator] = function() { return this; }), g;
    function verb(n) { return function (v) { return step([n, v]); }; }
    function step(op) {
        if (f) throw new TypeError("Generator is already executing.");
        while (g && (g = 0, op[0] && (_ = 0)), _) try {
            if (f = 1, y && (t = op[0] & 2 ? y["return"] : op[0] ? y["throw"] || ((t = y["return"]) && t.call(y), 0) : y.next) && !(t = t.call(y, op[1])).done) return t;
            if (y = 0, t) op = [op[0] & 2, t.value];
            switch (op[0]) {
                case 0: case 1: t = op; break;
                case 4: _.label++; return { value: op[1], done: false };
                case 5: _.label++; y = op[1]; op = [0]; continue;
                case 7: op = _.ops.pop(); _.trys.pop(); continue;
                default:
                    if (!(t = _.trys, t = t.length > 0 && t[t.length - 1]) && (op[0] === 6 || op[0] === 2)) { _ = 0; continue; }
                    if (op[0] === 3 && (!t || (op[1] > t[0] && op[1] < t[3]))) { _.label = op[1]; break; }
                    if (op[0] === 6 && _.label < t[1]) { _.label = t[1]; t = op; break; }
                    if (t && _.label < t[2]) { _.label = t[2]; _.ops.push(op); break; }
                    if (t[2]) _.ops.pop();
                    _.trys.pop(); continue;
            }
            op = body.call(thisArg, _);
        } catch (e) { op = [6, e]; y = 0; } finally { f = t = 0; }
        if (op[0] & 5) throw op[1]; return { value: op[0] ? op[1] : void 0, done: true };
    }
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.loaderToMemory = exports.AudioLoader = exports.StringLoader = exports.TextFileLoader = void 0;
var memory_1 = require("../memory");
var transcribe_1 = require("../transcribe");
var split_1 = require("../split");
var utils_1 = require("../utils");
function batchify(array, size, callback) {
    return __awaiter(this, void 0, void 0, function () {
        return __generator(this, function (_a) {
            switch (_a.label) {
                case 0:
                    if (!(array.length < size)) return [3 /*break*/, 2];
                    return [4 /*yield*/, callback(array)];
                case 1:
                    _a.sent();
                    return [2 /*return*/];
                case 2: return [4 /*yield*/, callback(array.slice(0, size))];
                case 3:
                    _a.sent();
                    return [4 /*yield*/, batchify(array.slice(size), size, callback)];
                case 4:
                    _a.sent();
                    return [2 /*return*/];
            }
        });
    });
}
function TextFileLoader(file, maxTokenPerChunk) {
    if (maxTokenPerChunk === void 0) { maxTokenPerChunk = 100; }
    return function loadPdfIntoMemory(memory, _clientOptions) {
        if (_clientOptions === void 0) { _clientOptions = {}; }
        return __awaiter(this, void 0, void 0, function () {
            function addBatchIntoMemory(batches) {
                return __awaiter(this, void 0, void 0, function () {
                    var _this = this;
                    return __generator(this, function (_a) {
                        switch (_a.label) {
                            case 0: return [4 /*yield*/, Promise.all(batches.map(function (batch) { return __awaiter(_this, void 0, void 0, function () { return __generator(this, function (_a) {
                                    return [2 /*return*/, memory.add(batch)];
                                }); }); }))];
                            case 1:
                                _a.sent();
                                return [2 /*return*/];
                        }
                    });
                });
            }
            var fileBuffer, splittedFile;
            return __generator(this, function (_a) {
                switch (_a.label) {
                    case 0: return [4 /*yield*/, (0, utils_1.fileInputToBuffer)(file)];
                    case 1:
                        fileBuffer = _a.sent();
                        splittedFile = (0, split_1.splitString)(fileBuffer.toString("utf8"), maxTokenPerChunk);
                        return [4 /*yield*/, batchify(splittedFile, 10, addBatchIntoMemory)];
                    case 2:
                        _a.sent();
                        return [2 /*return*/];
                }
            });
        });
    };
}
exports.TextFileLoader = TextFileLoader;
function StringLoader(str, maxTokenPerChunk) {
    if (maxTokenPerChunk === void 0) { maxTokenPerChunk = 100; }
    return function loadPdfIntoMemory(memory, _clientOptions) {
        if (_clientOptions === void 0) { _clientOptions = {}; }
        return __awaiter(this, void 0, void 0, function () {
            function addBatchIntoMemory(batches) {
                return __awaiter(this, void 0, void 0, function () {
                    var _this = this;
                    return __generator(this, function (_a) {
                        switch (_a.label) {
                            case 0: return [4 /*yield*/, Promise.all(batches.map(function (batch) { return __awaiter(_this, void 0, void 0, function () { return __generator(this, function (_a) {
                                    return [2 /*return*/, memory.add(batch)];
                                }); }); }))];
                            case 1:
                                _a.sent();
                                return [2 /*return*/];
                        }
                    });
                });
            }
            var splittedStr;
            return __generator(this, function (_a) {
                switch (_a.label) {
                    case 0:
                        splittedStr = (0, split_1.splitString)(str, maxTokenPerChunk);
                        return [4 /*yield*/, batchify(splittedStr, 10, addBatchIntoMemory)];
                    case 1:
                        _a.sent();
                        return [2 /*return*/];
                }
            });
        });
    };
}
exports.StringLoader = StringLoader;
function AudioLoader(file, maxTokenPerChunk) {
    if (maxTokenPerChunk === void 0) { maxTokenPerChunk = 100; }
    return function loadAudioIntoMemory(memory, clientOptions) {
        if (clientOptions === void 0) { clientOptions = {}; }
        return __awaiter(this, void 0, void 0, function () {
            function addBatchIntoMemory(batches) {
                return __awaiter(this, void 0, void 0, function () {
                    var _this = this;
                    return __generator(this, function (_a) {
                        switch (_a.label) {
                            case 0: return [4 /*yield*/, Promise.all(batches.map(function (batch) { return __awaiter(_this, void 0, void 0, function () { return __generator(this, function (_a) {
                                    return [2 /*return*/, memory.add(batch)];
                                }); }); }))];
                            case 1:
                                _a.sent();
                                return [2 /*return*/];
                        }
                    });
                });
            }
            var fileBuffer, transcription, transcriptions;
            return __generator(this, function (_a) {
                switch (_a.label) {
                    case 0: return [4 /*yield*/, (0, utils_1.fileInputToBuffer)(file)];
                    case 1:
                        fileBuffer = _a.sent();
                        return [4 /*yield*/, (0, transcribe_1.transcribe)(fileBuffer, clientOptions)];
                    case 2:
                        transcription = _a.sent();
                        transcriptions = (0, split_1.splitString)(transcription, maxTokenPerChunk);
                        return [4 /*yield*/, batchify(transcriptions, 10, addBatchIntoMemory)];
                    case 3:
                        _a.sent();
                        return [2 /*return*/];
                }
            });
        });
    };
}
exports.AudioLoader = AudioLoader;
function loaderToMemory(loaders, clientOptions) {
    if (clientOptions === void 0) { clientOptions = {}; }
    return __awaiter(this, void 0, void 0, function () {
        var memory;
        return __generator(this, function (_a) {
            switch (_a.label) {
                case 0:
                    memory = new memory_1.Memory(clientOptions);
                    if (!(typeof loaders === "function")) return [3 /*break*/, 2];
                    return [4 /*yield*/, loaders(memory, clientOptions)];
                case 1:
                    _a.sent();
                    return [3 /*break*/, 4];
                case 2: return [4 /*yield*/, Promise.all(loaders.map(function (loader) { return loader(memory, clientOptions); }))];
                case 3:
                    _a.sent();
                    _a.label = 4;
                case 4: return [2 /*return*/, memory];
            }
        });
    });
}
exports.loaderToMemory = loaderToMemory;