40 lines
1.6 KiB
JavaScript
40 lines
1.6 KiB
JavaScript
|
"use strict";
|
||
|
|
Object.defineProperty(exports, "__esModule", { value: true });
|
||
|
|
exports.PPTXLoader = void 0;
|
||
|
|
const officeparser_1 = require("officeparser");
|
||
|
|
const documents_1 = require("@langchain/core/documents");
|
||
|
|
const buffer_1 = require("langchain/document_loaders/fs/buffer");
|
||
|
|
/**
|
||
|
|
* A class that extends the `BufferLoader` class. It represents a document
|
||
|
|
* loader that loads documents from PDF files.
|
||
|
|
*/
|
||
|
|
class PPTXLoader extends buffer_1.BufferLoader {
|
||
|
|
constructor(filePathOrBlob) {
|
||
|
|
super(filePathOrBlob);
|
||
|
|
}
|
||
|
|
/**
|
||
|
|
* A method that takes a `raw` buffer and `metadata` as parameters and
|
||
|
|
* returns a promise that resolves to an array of `Document` instances. It
|
||
|
|
* uses the `parseOfficeAsync` function from the `officeparser` module to extract
|
||
|
|
* the raw text content from the buffer. If the extracted powerpoint content is
|
||
|
|
* empty, it returns an empty array. Otherwise, it creates a new
|
||
|
|
* `Document` instance with the extracted powerpoint content and the provided
|
||
|
|
* metadata, and returns it as an array.
|
||
|
|
* @param raw The buffer to be parsed.
|
||
|
|
* @param metadata The metadata of the document.
|
||
|
|
* @returns A promise that resolves to an array of `Document` instances.
|
||
|
|
*/
|
||
|
|
async parse(raw, metadata) {
|
||
|
|
const pptx = await (0, officeparser_1.parseOfficeAsync)(raw, { outputErrorToConsole: true });
|
||
|
|
if (!pptx)
|
||
|
|
return [];
|
||
|
|
return [
|
||
|
|
new documents_1.Document({
|
||
|
|
pageContent: pptx,
|
||
|
|
metadata,
|
||
|
|
}),
|
||
|
|
];
|
||
|
|
}
|
||
|
|
}
|
||
|
|
exports.PPTXLoader = PPTXLoader;
|