feat(extractors): add image extractor

.gitignore

@@ -30,3 +30,4 @@ logs
 coverage
 cache
 .zed
+*.traineddata 

fixtures/006.expected

@@ -0,0 +1,6 @@
+Lorem ipsum
+
+Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sapien ante conubia vestibulum
+ultrices quisque nam nascetur consectetur. Viverra amet lacinia massa donec gravida primis
+leo tellus. Montes nulla sit cras odio penatibus cum aenean metus. Per per eros fusce et
+platea et feugiat ullamcorper.

fixtures/007.expected

@@ -0,0 +1,41 @@
+at his touch of a certain icy pang along my blood. “Come, sir,” said I.
+“You forget that I have not yet the pleasure of your acquaintance. Be
+seated, if you please.” And I showed him an example, and sat down
+myself in my customary seat and with as fair an imitation of my or-
+dinary manner to a patient, as the lateness of the hour, the nature of
+my preoccupations, and the horror I had of my visitor, would suffer
+me to muster.
+
+“I beg your pardon, Dr. Lanyon,” he replied civilly enough. “What
+you say is very well founded; and my impatience has shown its heels
+to my politeness. I come here at the instance of your colleague, Dr.
+Henry Jekyll, on a piece of business of some moment; and I under-
+stood...” He paused and put his hand to his throat, and I could see,
+in spite of his collected manner, that he was wrestling against the
+approaches of the hysteria—“T understood, a drawer...”
+
+But here I took pity on my visitor's suspense, and some perhaps
+on my own growing curiosity.
+
+“There it is, sir,” said I, pointing to the drawer, where it lay on the
+floor behind a table and still covered with the sheet.
+
+He sprang to it, and then paused, and laid his hand upon his
+heart: I could hear his teeth grate with the convulsive action of his
+jaws; and his face was so ghastly to see that I grew alarmed both for
+his life and reason.
+
+“Compose yourself,” said I.
+
+He turned a dreadful smile to me, and as if with the decision of
+despair, plucked away the sheet. At sight of the contents, he uttered
+one loud sob of such immense relief that I sat petrified. And the
+next moment, in a voice that was already fairly well under control,
+“Have you a graduated glass?” he asked.
+
+I rose from my place with something of an effort and gave him
+what he asked.
+
+He thanked me with a smiling nod, measured out a few min-
+ims of the red tincture and added one of the powders. The mix-
+ture, which was at first of a reddish hue, began, in proportion as the

fixtures/008.expected

@@ -0,0 +1,6 @@
+Lorem ipsum
+
+Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sapien ante conubia vestibulum
+ultrices quisque nam nascetur consectetur. Viverra amet lacinia massa donec gravida primis
+leo tellus. Montes nulla sit cras odio penatibus cum aenean metus. Per per eros fusce et
+platea et feugiat ullamcorper.

package.json

@@ -46,6 +46,7 @@
     "release": "bumpp --commit --tag --push"
   },
   "dependencies": {
+    "tesseract.js": "^6.0.0",
     "unpdf": "^0.12.1"
   },
   "devDependencies": {

src/extractors.registry.ts

@@ -1,10 +1,12 @@
 import type { ExtractorDefinition } from './extractors.models';
+import { imageExtractorDefinition } from './extractors/img.extractor';
 import { pdfExtractorDefinition } from './extractors/pdf.extractor';
 import { txtExtractorDefinition } from './extractors/txt.extractor';
 
 export const extractorDefinitions: ExtractorDefinition[] = [
   pdfExtractorDefinition,
   txtExtractorDefinition,
+  imageExtractorDefinition,
 ];
 
 export function getExtractor({

src/extractors/img.extractor.ts

@@ -0,0 +1,23 @@
+import { Buffer } from 'node:buffer';
+import { createWorker } from 'tesseract.js';
+import { defineTextExtractor } from '../extractors.models';
+
+export const imageExtractorDefinition = defineTextExtractor({
+  name: 'image',
+  mimeTypes: [
+    'image/png',
+    'image/jpeg',
+    'image/webp',
+    'image/gif',
+  ],
+  extract: async ({ arrayBuffer }) => {
+    const buffer = Buffer.from(arrayBuffer);
+
+    const worker = await createWorker();
+
+    const { data: { text } } = await worker.recognize(buffer);
+    await worker.terminate();
+
+    return { content: text };
+  },
+});