n8n-nodes-docxtotext
Version:
n8n node to convert DOCX files to text using mammoth
130 lines • 5.4 kB
JavaScript
;
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 (mod) {
if (mod && mod.__esModule) return mod;
var result = {};
if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
__setModuleDefault(result, mod);
return result;
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.DocxToText = void 0;
const n8n_workflow_1 = require("n8n-workflow");
const mammoth = __importStar(require("mammoth"));
class DocxToText {
constructor() {
this.description = {
displayName: 'DOCX to Text',
name: 'docxToText',
icon: 'file:docx-to-text.svg',
group: ['input'],
version: 1,
subtitle: '={{$parameter["operation"]}}',
description: 'Convert DOCX files to formatted text',
defaults: {
name: 'DOCX to Text',
},
inputs: ["main"],
outputs: ["main"],
properties: [
{
displayName: 'Binary Property',
name: 'binaryPropertyName',
type: 'string',
default: 'data',
required: true,
description: 'Name of the binary property which contains the DOCX file',
},
{
displayName: 'Options',
name: 'options',
type: 'collection',
placeholder: 'Add Option',
default: {},
options: [
{
displayName: 'Include Filename',
name: 'includeFilename',
type: 'boolean',
default: true,
description: 'Whether to include the filename in the output',
},
],
},
],
};
}
async execute() {
const items = this.getInputData();
const returnData = [];
const length = items.length;
const binaryPropertyName = this.getNodeParameter('binaryPropertyName', 0);
const options = this.getNodeParameter('options', 0, {});
for (let i = 0; i < length; i++) {
try {
const item = items[i];
const binaryData = item.binary;
if (binaryData === undefined) {
throw new n8n_workflow_1.NodeOperationError(this.getNode(), 'No binary data exists on item!', { itemIndex: i });
}
if (!binaryData[binaryPropertyName]) {
throw new n8n_workflow_1.NodeOperationError(this.getNode(), `No binary data property "${binaryPropertyName}" does not exists on item!`, { itemIndex: i });
}
const binaryDataBuffer = await this.helpers.getBinaryDataBuffer(i, binaryPropertyName);
const result = await mammoth.extractRawText({ buffer: binaryDataBuffer });
const text = result.value;
const messages = result.messages;
const newItem = {
json: {
text,
messages,
},
};
if (options.includeFilename && binaryData[binaryPropertyName].fileName) {
const fullFilename = binaryData[binaryPropertyName].fileName;
const lastDotIndex = fullFilename.lastIndexOf('.');
if (lastDotIndex > 0) {
newItem.json.filename = fullFilename.substring(0, lastDotIndex);
newItem.json.fileExtension = fullFilename.substring(lastDotIndex + 1).toLowerCase();
}
else {
newItem.json.filename = fullFilename;
}
}
if (item.json !== undefined) {
newItem.json = { ...item.json, ...newItem.json };
}
returnData.push(newItem);
}
catch (error) {
if (this.continueOnFail()) {
returnData.push({
json: {
error: error.message,
},
});
continue;
}
throw error;
}
}
return this.prepareOutputData(returnData);
}
}
exports.DocxToText = DocxToText;
//# sourceMappingURL=DocxToText.node.js.map