n8n-nodes-ocrbro 0.1.0

package/dist/index.js

@@ -0,0 +1,5 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.OcrBro = void 0;
+var OcrBro_node_1 = require("./nodes/OcrBro/OcrBro.node");
+Object.defineProperty(exports, "OcrBro", { enumerable: true, get: function () { return OcrBro_node_1.OcrBro; } });

package/dist/nodes/OcrBro/OcrBro.node.js

@@ -0,0 +1,90 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.OcrBro = void 0;
+const tesseract_js_1 = require("tesseract.js");
+class OcrBro {
+    constructor() {
+        this.description = {
+            displayName: 'OCR Bro',
+            name: 'ocrBro',
+            icon: 'file:ocrbro.png',
+            group: ['transform'],
+            version: 1,
+            description: 'OCR Images using Tesseract.js - extracts text from images',
+            defaults: {
+                name: 'OCR Bro',
+            },
+            inputs: ['main'],
+            outputs: ['main'],
+            properties: [
+                {
+                    displayName: 'Input Binary Field',
+                    name: 'binaryPropertyName',
+                    type: 'string',
+                    default: 'data',
+                    required: true,
+                    description: 'The name of the binary property containing the image file to OCR',
+                },
+                {
+                    displayName: 'Language',
+                    name: 'language',
+                    type: 'string',
+                    default: 'eng',
+                    description: 'Tesseract language code (e.g., eng, deu, spa). Multiple languages can be specified separated by "+".',
+                },
+            ],
+        };
+    }
+    async execute() {
+        var _a;
+        const items = this.getInputData();
+        const returnData = [];
+        const binaryPropertyName = this.getNodeParameter('binaryPropertyName', 0);
+        const language = this.getNodeParameter('language', 0);
+        // @ts-ignore
+        const worker = await (0, tesseract_js_1.createWorker)();
+        // @ts-ignore
+        await worker.loadLanguage(language);
+        // @ts-ignore
+        await worker.initialize(language);
+        for (let i = 0; i < items.length; i++) {
+            try {
+                const item = items[i];
+                // @ts-ignore - n8n types are sometimes weird with binary helpers in dry run
+                const binaryData = await this.helpers.getBinaryDataBuffer(i, binaryPropertyName);
+                const binaryMetadata = item.binary ? item.binary[binaryPropertyName] : undefined;
+                if (!binaryMetadata) {
+                    throw new Error(`Binary property "${binaryPropertyName}" does not exist on item ${i}`);
+                }
+                const mimeType = binaryMetadata.mimeType;
+                if (!mimeType.startsWith('image/')) {
+                    throw new Error(`Unsupported file type: ${mimeType}. OCR Bro only supports image files (PNG, JPG, TIFF, BMP, etc.)`);
+                }
+                // @ts-ignore
+                const { data } = await worker.recognize(binaryData);
+                returnData.push({
+                    json: {
+                        text: data.text,
+                        confidence: data.confidence,
+                        words: ((_a = data.words) === null || _a === void 0 ? void 0 : _a.length) || 0,
+                    },
+                    binary: item.binary,
+                });
+            }
+            catch (error) {
+                if (this.continueOnFail()) {
+                    returnData.push({
+                        json: {
+                            error: error.message,
+                        },
+                    });
+                    continue;
+                }
+                throw error;
+            }
+        }
+        await worker.terminate();
+        return [returnData];
+    }
+}
+exports.OcrBro = OcrBro;

package/dist/test/test.js

@@ -0,0 +1,85 @@
+"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 });
+const OcrBro_node_1 = require("../nodes/OcrBro/OcrBro.node");
+const fs = __importStar(require("fs"));
+const path = __importStar(require("path"));
+// Mock helpers
+const mockHelpers = {
+    getBinaryDataBuffer: (index, propertyName) => {
+        const filePath = path.join(__dirname, 'sample.png');
+        console.log(`Reading file from ${filePath}`);
+        return fs.readFileSync(filePath);
+    },
+    getBinaryMetadata: (index, propertyName) => {
+        return { mimeType: 'image/png' };
+    },
+    returnJsonArray: (items) => items
+};
+// Mock Node
+const node = new OcrBro_node_1.OcrBro();
+// Mock Execution Context
+const mockExecute = async function () {
+    this.helpers = mockHelpers;
+    this.getNodeParameter = (param) => {
+        if (param === 'binaryPropertyName')
+            return 'data';
+        if (param === 'language')
+            return 'eng';
+        return '';
+    };
+    this.getInputData = () => {
+        return [{
+                json: {},
+                binary: {
+                    data: {
+                        mimeType: 'image/png'
+                    }
+                }
+            }];
+    };
+    this.continueOnFail = () => false;
+    console.log("Starting execution...");
+    return await node.execute.call(this);
+};
+// Run
+mockExecute.call({})
+    .then((result) => {
+    console.log("Execution successful!");
+    console.log("Result JSON:", JSON.stringify(result[0][0].json, null, 2));
+})
+    .catch((err) => {
+    console.error("Execution failed:", err);
+});

package/package.json

@@ -0,0 +1,47 @@
+{
+  "name": "n8n-nodes-ocrbro",
+  "version": "0.1.0",
+  "description": "Native n8n node for OCR using Tesseract.js",
+  "keywords": [
+    "n8n-community-node-package"
+  ],
+  "license": "MIT",
+  "homepage": "",
+  "author": {
+    "name": "User",
+    "email": "user@example.com"
+  },
+  "community": {
+    "author": {
+      "name": "User",
+      "email": "user@example.com"
+    }
+  },
+  "main": "dist/index.js",
+  "n8n": {
+    "nodes": [
+      "dist/nodes/OcrBro/OcrBro.node.js"
+    ]
+  },
+  "scripts": {
+    "build": "tsc",
+    "dev": "tsc --watch",
+    "test": "ts-node test/test.ts"
+  },
+  "files": [
+    "dist",
+    "eng.traineddata"
+  ],
+  "peerDependencies": {
+    "n8n-workflow": "*"
+  },
+  "devDependencies": {
+    "@types/node": "^18.0.0",
+    "n8n-workflow": "*",
+    "ts-node": "^10.9.1",
+    "typescript": "^5.0.0"
+  },
+  "dependencies": {
+    "tesseract.js": "^4.0.0"
+  }
+}