langchain/dist/document_loaders/fs/text.cjs

Typescript bindings for langchain

"use strict";
var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
    if (k2 === undefined) k2 = k;
    var desc = Object.getOwnPropertyDescriptor(m, k);
    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
      desc = { enumerable: true, get: function() { return m[k]; } };
    }
    Object.defineProperty(o, k2, desc);
}) : (function(o, m, k, k2) {
    if (k2 === undefined) k2 = k;
    o[k2] = m[k];
}));
var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
    Object.defineProperty(o, "default", { enumerable: true, value: v });
}) : function(o, v) {
    o["default"] = v;
});
var __importStar = (this && this.__importStar) || (function () {
    var ownKeys = function(o) {
        ownKeys = Object.getOwnPropertyNames || function (o) {
            var ar = [];
            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
            return ar;
        };
        return ownKeys(o);
    };
    return function (mod) {
        if (mod && mod.__esModule) return mod;
        var result = {};
        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
        __setModuleDefault(result, mod);
        return result;
    };
})();
Object.defineProperty(exports, "__esModule", { value: true });
exports.TextLoader = void 0;
const documents_1 = require("@langchain/core/documents");
const env_1 = require("@langchain/core/utils/env");
const base_js_1 = require("../base.cjs");
/**
 * A class that extends the `BaseDocumentLoader` class. It represents a
 * document loader that loads documents from a text file. The `load()`
 * method is implemented to read the text from the file or blob, parse it
 * using the `parse()` method, and create a `Document` instance for each
 * parsed page. The metadata includes the source of the text (file path or
 * blob) and, if there are multiple pages, the line number of each page.
 * @example
 * ```typescript
 * const loader = new TextLoader("src/document_loaders/example_data/example.txt");
 * const docs = await loader.load();
 * ```
 */
class TextLoader extends base_js_1.BaseDocumentLoader {
    constructor(filePathOrBlob) {
        super();
        Object.defineProperty(this, "filePathOrBlob", {
            enumerable: true,
            configurable: true,
            writable: true,
            value: filePathOrBlob
        });
    }
    /**
     * A protected method that takes a `raw` string as a parameter and returns
     * a promise that resolves to an array containing the raw text as a single
     * element.
     * @param raw The raw text to be parsed.
     * @returns A promise that resolves to an array containing the raw text as a single element.
     */
    async parse(raw) {
        return [raw];
    }
    /**
     * A method that loads the text file or blob and returns a promise that
     * resolves to an array of `Document` instances. It reads the text from
     * the file or blob using the `readFile` function from the
     * `node:fs/promises` module or the `text()` method of the blob. It then
     * parses the text using the `parse()` method and creates a `Document`
     * instance for each parsed page. The metadata includes the source of the
     * text (file path or blob) and, if there are multiple pages, the line
     * number of each page.
     * @returns A promise that resolves to an array of `Document` instances.
     */
    async load() {
        let text;
        let metadata;
        if (typeof this.filePathOrBlob === "string") {
            const { readFile } = await TextLoader.imports();
            text = await readFile(this.filePathOrBlob, "utf8");
            metadata = { source: this.filePathOrBlob };
        }
        else {
            text = await this.filePathOrBlob.text();
            metadata = { source: "blob", blobType: this.filePathOrBlob.type };
        }
        const parsed = await this.parse(text);
        parsed.forEach((pageContent, i) => {
            if (typeof pageContent !== "string") {
                throw new Error(`Expected string, at position ${i} got ${typeof pageContent}`);
            }
        });
        return parsed.map((pageContent, i) => new documents_1.Document({
            pageContent,
            metadata: parsed.length === 1
                ? metadata
                : {
                    ...metadata,
                    line: i + 1,
                },
        }));
    }
    /**
     * A static method that imports the `readFile` function from the
     * `node:fs/promises` module. It is used to dynamically import the
     * function when needed. If the import fails, it throws an error
     * indicating that the `fs/promises` module is not available in the
     * current environment.
     * @returns A promise that resolves to an object containing the `readFile` function from the `node:fs/promises` module.
     */
    static async imports() {
        try {
            const { readFile } = await Promise.resolve().then(() => __importStar(require("node:fs/promises")));
            return { readFile };
        }
        catch (e) {
            console.error(e);
            throw new Error(`Failed to load fs/promises. TextLoader available only on environment 'node'. It appears you are running environment '${(0, env_1.getEnv)()}'. See https://<link to docs> for alternatives.`);
        }
    }
}
exports.TextLoader = TextLoader;