Add tessedit_char_whitelist test case

docs/api.md

@@ -148,6 +148,7 @@ Worker.setParameters() set parameters for Tesseract API (using SetVariable()), i
 | tessedit\_ocr\_engine\_mode | enum | OEM.LSTM\_ONLY | Check [HERE](https://github.com/tesseract-ocr/tesseract/blob/4.0.0/src/ccstruct/publictypes.h#L268) for definition of each mode | 
 | tessedit\_pageseg\_mode | enum | PSM.SINGLE\_BLOCK | Check [HERE](https://github.com/tesseract-ocr/tesseract/blob/4.0.0/src/ccstruct/publictypes.h#L163) for definition of each mode |
 | tessedit\_char\_whitelist | string | '' | setting white list characters makes the result only contains these characters, useful the content in image is limited |
+| preserve\_interword\_spaces | string | '0' | '0' or '1', keeps the space between words |
 | tessjs\_create\_hocr | string | '1' | only 2 values, '0' or '1', when the value is '1', tesseract.js includes hocr in the result |
 | tessjs\_create\_tsv | string | '1' | only 2 values, '0' or '1', when the value is '1', tesseract.js includes tsv in the result |
 | tessjs\_create\_box | string | '0' | only 2 values, '0' or '1', when the value is '1', tesseract.js includes box in the result |

examples/node/preserve-interword-spaces.js

@@ -1,22 +0,0 @@
-#!/usr/bin/env node
-const path = require('path');
-const fs = require('fs');
-const { createWorker } = require('../../');
-
-const [,, imagePath] = process.argv;
-const image = path.resolve(__dirname, (imagePath || '../../tests/assets/images/bill.png'));
-
-console.log(`Recognizing ${image}`);
-
-(async () => {
-  const worker = createWorker();
-  await worker.load();
-  await worker.loadLanguage('eng');
-  await worker.initialize('eng');
-  await worker.setParameters({
-    preserve_interword_spaces: '1',
-  });
-  const { data: { text } } = await worker.recognize(image);
-  console.log(JSON.stringify({ text }));
-  await worker.terminate();
-})();

src/worker-script/constants/defaultParams.js

@@ -6,7 +6,6 @@ const PSM = require('../../constants/PSM');
 module.exports = {
   tessedit_pageseg_mode: PSM.SINGLE_BLOCK,
   tessedit_char_whiltelist: '',
-  user_defined_dpi: '300',
   tessjs_create_hocr: '1',
   tessjs_create_tsv: '1',
   tessjs_create_box: '0',

tests/recognize.test.js

@@ -90,6 +90,15 @@ describe('recognize()', () => {
       const { data: { text } } = await worker.recognize(`${IMAGE_PATH}/bill.png`);
       expect(text).to.be(BILL_SPACED_TEXT);
     }).timeout(TIMEOUT);
+
+    it('support tessedit_char_whitelist', async () => {
+      await worker.initialize('eng');
+      await worker.setParameters({
+        tessedit_char_whitelist: 'Tess',
+      });
+      const { data: { text } } = await worker.recognize(`${IMAGE_PATH}/simple.png`);
+      expect(text).to.be(SIMPLE_WHITELIST_TEXT);
+    }).timeout(TIMEOUT);
   });
 
   describe('should support all page seg modes', () => {