feat(extractors): refactor image extraction to use child_process for Tesseract

fixtures/007.expected

@@ -1,20 +1,20 @@
-at his touch of a certain icy pang along my blood. “Come, sir,” said I.
+at his touch ofa 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
+“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...”
+approaches of the hysteria—“I understood, a drawer...”
 
-But here I took pity on my visitor's suspense, and some perhaps
+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
@@ -25,7 +25,7 @@ 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.
+“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

package.json

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

src/extractors/img.extractor.ts

@@ -1,5 +1,6 @@
 import { Buffer } from 'node:buffer';
-import { createWorker } from 'tesseract.js';
+import { exec } from 'node:child_process';
+import { env } from 'node:process';
 import { defineTextExtractor } from '../extractors.models';
 
 export const imageExtractorDefinition = defineTextExtractor({
@@ -11,13 +12,23 @@
     'image/gif',
   ],
   extract: async ({ arrayBuffer }) => {
-    const buffer = Buffer.from(arrayBuffer);
+    const binary = env.LECTURE_TESSERACT_BINARY ?? 'tesseract';
 
-    const worker = await createWorker();
+    const { stdout } = await new Promise<{ stdout: string }>((resolve, reject) => {
+      const child = exec(`${binary} stdin stdout`, (error, stdout) => {
+        if (error) {
+          reject(error);
+        } else {
+          resolve({ stdout });
+        }
+      });
 
-    const { data: { text } } = await worker.recognize(buffer);
-    await worker.terminate();
+      child.stdin.write(Buffer.from(arrayBuffer));
+      child.stdin.end();
+    });
 
-    return { content: text };
+    return {
+      content: stdout,
+    };
   },
 });