Cache regex

src/worker-script/browser/getCore.js

@@ -3,6 +3,8 @@
 const { simd } = require('wasm-feature-detect');
 const coreVersion = require('../../../package.json').dependencies['tesseract.js-core'];
 
+const trailingSlashRegex = /\/$/;
+
 module.exports = async (lstmOnly, corePath, res) => {
   if (typeof global.TesseractCore === 'undefined') {
     const statusText = 'loading tesseract core';
@@ -24,14 +26,14 @@ module.exports = async (lstmOnly, corePath, res) => {
       const simdSupport = await simd();
       if (simdSupport) {
         if (lstmOnly) {
-          corePathImportFile = `${corePathImport.replace(/\/$/, '')}/tesseract-core-simd-lstm.wasm.js`;
+          corePathImportFile = `${corePathImport.replace(trailingSlashRegex, '')}/tesseract-core-simd-lstm.wasm.js`;
         } else {
-          corePathImportFile = `${corePathImport.replace(/\/$/, '')}/tesseract-core-simd.wasm.js`;
+          corePathImportFile = `${corePathImport.replace(trailingSlashRegex, '')}/tesseract-core-simd.wasm.js`;
         }
       } else if (lstmOnly) {
-        corePathImportFile = `${corePathImport.replace(/\/$/, '')}/tesseract-core-lstm.wasm.js`;
+        corePathImportFile = `${corePathImport.replace(trailingSlashRegex, '')}/tesseract-core-lstm.wasm.js`;
       } else {
-        corePathImportFile = `${corePathImport.replace(/\/$/, '')}/tesseract-core.wasm.js`;
+        corePathImportFile = `${corePathImport.replace(trailingSlashRegex, '')}/tesseract-core.wasm.js`;
       }
     }
 

src/worker-script/index.js

@@ -18,6 +18,9 @@ const defaultOutput = require('./constants/defaultOutput');
 const { log, setLogging } = require('../utils/log');
 const PSM = require('../constants/PSM');
 
+const componentRegex = /components are not present/;
+const trailingSlashRegex = /\/$/;
+
 /*
  * Tesseract Module returned by TesseractCore.
  */
@@ -133,7 +136,7 @@ res) => {
         // The is-url package is used to tell the difference
         // For the browser version, langPath is assumed to be a URL
         if (env !== 'node' || isURL(langPathDownload) || langPathDownload.startsWith('moz-extension://') || langPathDownload.startsWith('chrome-extension://') || langPathDownload.startsWith('file://')) { /** When langPathDownload is an URL */
-          path = langPathDownload.replace(/\/$/, '');
+          path = langPathDownload.replace(trailingSlashRegex, '');
         }
 
         // langPathDownload is a URL, fetch from server
@@ -286,7 +289,7 @@ const initialize = async ({
         // The .wasm build of Tesseract saves this message in a separate file
         // (in addition to the normal debug file location).
         const debugStr = TessModule.FS.readFile('/debugDev.txt', { encoding: 'utf8', flags: 'a+' });
-        if (dataFromCache && /components are not present/.test(debugStr)) {
+        if (dataFromCache && componentRegex.test(debugStr)) {
           log('Data from cache missing requested OEM model. Attempting to refresh cache with new language data.');
           // In this case, language data is re-loaded
           await loadLanguage({ workerId, payload: { langs: loadLanguageLangsWorker, options: loadLanguageOptionsWorker } }); // eslint-disable-line max-len

src/worker-script/utils/setImage.js

@@ -2,6 +2,8 @@
 
 const bmp = require('bmp-js');
 
+const exifRegex = /1 18 0 3 0 0 0 1 0 (\d)/;
+
 /**
  * setImage
  *
@@ -13,7 +15,7 @@ module.exports = (TessModule, api, image, angle = 0) => {
   // Check for bmp magic numbers (42 and 4D in hex)
   const isBmp = (image[0] === 66 && image[1] === 77) || (image[1] === 66 && image[0] === 77);
 
-  const exif = parseInt(image.slice(0, 500).join(' ').match(/1 18 0 3 0 0 0 1 0 (\d)/)?.[1], 10) || 1;
+  const exif = parseInt(image.slice(0, 500).join(' ').match(exifRegex)?.[1], 10) || 1;
 
   // /*
   //  * Leptonica supports some but not all bmp files

src/worker/browser/loadImage.js

@@ -20,6 +20,8 @@ const readFromBlobOrFile = (blob) => (
   })
 );
 
+const imageRegex = /data:image\/([a-zA-Z]*);base64,([^"]*)/;
+
 /**
  * loadImage
  *
@@ -35,7 +37,7 @@ const loadImage = async (image) => {
 
   if (typeof image === 'string') {
     // Base64 Image
-    if (/data:image\/([a-zA-Z]*);base64,([^"]*)/.test(image)) {
+    if (imageRegex.test(image)) {
       data = atob(image.split(',')[1])
         .split('')
         .map((c) => c.charCodeAt(0));

src/worker/node/loadImage.js

@@ -7,6 +7,7 @@ const fetch = global.fetch || require('node-fetch');
 const isURL = require('is-url');
 
 const readFile = util.promisify(fs.readFile);
+const imageRegex = /data:image\/([a-zA-Z]*);base64,([^"]*)/;
 
 /**
  * loadImage
@@ -25,7 +26,7 @@ module.exports = async (image) => {
     if (isURL(image) || image.startsWith('moz-extension://') || image.startsWith('chrome-extension://') || image.startsWith('file://')) {
       const resp = await fetch(image);
       data = await resp.arrayBuffer();
-    } else if (/data:image\/([a-zA-Z]*);base64,([^"]*)/.test(image)) {
+    } else if (imageRegex.test(image)) {
       data = Buffer.from(image.split(',')[1], 'base64');
     } else {
       data = await readFile(image);