@langchain/community/dist/document_loaders/fs/pptx.cjs.map

Third-party integrations for LangChain.js

{"version":3,"file":"pptx.cjs","names":["BufferLoader","Document"],"sources":["../../../src/document_loaders/fs/pptx.ts"],"sourcesContent":["import { parseOffice } from \"officeparser\";\nimport { Document } from \"@langchain/core/documents\";\nimport { BufferLoader } from \"@langchain/classic/document_loaders/fs/buffer\";\n\n/**\n * A class that extends the `BufferLoader` class. It represents a document\n * loader that loads documents from PPTX files.\n */\nexport class PPTXLoader extends BufferLoader {\n  constructor(filePathOrBlob: string | Blob) {\n    super(filePathOrBlob);\n  }\n\n  /**\n   * A method that takes a `raw` buffer and `metadata` as parameters and\n   * returns a promise that resolves to an array of `Document` instances. It\n   * uses the `parseOffice` function from the `officeparser` module to extract\n   * the raw text content from the buffer. If the extracted powerpoint content is\n   * empty, it returns an empty array. Otherwise, it creates a new\n   * `Document` instance with the extracted powerpoint content and the provided\n   * metadata, and returns it as an array.\n   * @param raw The buffer to be parsed.\n   * @param metadata The metadata of the document.\n   * @returns A promise that resolves to an array of `Document` instances.\n   */\n  public async parse(\n    raw: Buffer,\n    metadata: Document[\"metadata\"]\n  ): Promise<Document[]> {\n    const ast = await parseOffice(raw, { outputErrorToConsole: true });\n    const pptx = ast.toText();\n\n    if (!pptx) return [];\n\n    return [\n      new Document({\n        pageContent: pptx,\n        metadata,\n      }),\n    ];\n  }\n}\n"],"mappings":";;;;;;;;;;;AAQA,IAAa,aAAb,cAAgCA,8CAAAA,aAAa;CAC3C,YAAY,gBAA+B;AACzC,QAAM,eAAe;;;;;;;;;;;;;;CAevB,MAAa,MACX,KACA,UACqB;EAErB,MAAM,QADM,OAAA,GAAA,aAAA,aAAkB,KAAK,EAAE,sBAAsB,MAAM,CAAC,EACjD,QAAQ;AAEzB,MAAI,CAAC,KAAM,QAAO,EAAE;AAEpB,SAAO,CACL,IAAIC,0BAAAA,SAAS;GACX,aAAa;GACb;GACD,CAAC,CACH"}