anything-llm/collector/processSingleFile/convert/asTxt.js
Timothy Carambat d52f8aafd4
689 links in citation (#715)
* Include links in citations
force ChunkSource key to retain this information
old links will be unsupported

* show special icons depending on source

* remove console log

* reset server documents writeTo
2024-02-13 14:11:57 -08:00

54 lines
1.5 KiB
JavaScript

const { v4 } = require("uuid");
const fs = require("fs");
const { tokenizeString } = require("../../utils/tokenizer");
const {
createdDate,
trashFile,
writeToServerDocuments,
} = require("../../utils/files");
const { default: slugify } = require("slugify");
async function asTxt({ fullFilePath = "", filename = "" }) {
let content = "";
try {
content = fs.readFileSync(fullFilePath, "utf8");
} catch (err) {
console.error("Could not read file!", err);
}
if (!content?.length) {
console.error(`Resulting text content was empty for ${filename}.`);
trashFile(fullFilePath);
return {
success: false,
reason: `No text content found in ${filename}.`,
documents: [],
};
}
console.log(`-- Working ${filename} --`);
const data = {
id: v4(),
url: "file://" + fullFilePath,
title: filename,
docAuthor: "Unknown", // TODO: Find a better author
description: "Unknown", // TODO: Find a better description
docSource: "a text file uploaded by the user.",
chunkSource: "",
published: createdDate(fullFilePath),
wordCount: content.split(" ").length,
pageContent: content,
token_count_estimate: tokenizeString(content).length,
};
const document = writeToServerDocuments(
data,
`${slugify(filename)}-${data.id}`
);
trashFile(fullFilePath);
console.log(`[SUCCESS]: ${filename} converted & ready for embedding.\n`);
return { success: true, reason: null, documents: [document] };
}
module.exports = asTxt;