Merge pull request #64 from crisp-dev/master

feat: allow position offset as option

README.md

@@ -37,7 +37,7 @@ import chardet from 'chardet';
 chardet.analyse(Buffer.from('hello there!'));
 ```
 
-Returned value is an array of objects sorted by confidence value in decending order
+Returned value is an array of objects sorted by confidence value in descending order
 
 ```javascript
 [
@@ -48,15 +48,23 @@ Returned value is an array of objects sorted by confidence value in decending or
 
 ## Working with large data sets
 
-Sometimes, when data set is huge and you want to optimize performace (with a tradeoff of less accuracy),
-you can sample only first N bytes of the buffer:
+Sometimes, when data set is huge and you want to optimize performance (with a tradeoff of less accuracy),
+you can sample only the first N bytes of the buffer:
 
 ```javascript
 chardet
   .detectFile('/path/to/file', { sampleSize: 32 })
   .then(encoding => console.log(encoding));
 ```
 
+You can also specify where to begin reading from in the buffer:
+
+```javascript
+chardet
+  .detectFile('/path/to/file', { sampleSize: 32, offset: 128 })
+  .then(encoding => console.log(encoding));
+```
+
 ## Supported Encodings:
 
 - UTF-8

src/index.test.ts

@@ -40,6 +40,11 @@ describe('chardet', () => {
       const res = await chardet.detectFile(path, { sampleSize: 32 });
       expect(res).toBe('UTF-8');
     });
+
+    it('should detect encoding with smaller sample size and offset', async () => {
+      const res = await chardet.detectFile(path, { sampleSize: 32, offset: 64 });
+      expect(res).toBe('UTF-8');
+    });
   });
 
   describe('#detectFileSync', () => {
@@ -50,6 +55,10 @@ describe('chardet', () => {
     it('should detect encoding with smaller sample size', () => {
       expect(chardet.detectFileSync(path, { sampleSize: 32 })).toBe('UTF-8');
     });
+
+    it('should detect encoding with smaller sample size and offset', () => {
+      expect(chardet.detectFileSync(path, { sampleSize: 32, offset: 64 })).toBe('UTF-8');
+    });
   });
 
   describe('#analyse', () => {

src/index.ts

@@ -10,7 +10,8 @@ import * as sbcs from './encoding/sbcs';
 import * as iso2022 from './encoding/iso2022';
 
 interface FullOptions {
-  sampleSize: number
+  sampleSize: number,
+  offset: number
 }
 
 type Options = Partial<FullOptions>
@@ -107,7 +108,7 @@ export const detectFile = (filepath: string, opts: Options = {}): Promise<Detect
       fd = fs.openSync(filepath, 'r');
       const sample: Buffer = Buffer.allocUnsafe(opts.sampleSize);
 
-      fs.read(fd, sample, 0, opts.sampleSize, null, (err?: Error) => {
+      fs.read(fd, sample, 0, opts.sampleSize, opts.offset, (err?: Error) => {
         handler(err, sample);
       });
       return;
@@ -123,7 +124,7 @@ export const detectFileSync = (filepath: string, opts: Options = {}): DetectResu
     const fd = fs.openSync(filepath, 'r');
     const sample = Buffer.allocUnsafe(opts.sampleSize);
 
-    fs.readSync(fd, sample, 0, opts.sampleSize);
+    fs.readSync(fd, sample, 0, opts.sampleSize, opts.offset);
     fs.closeSync(fd);
     return detect(sample);
   }