From 2fb68b1f485484e524de0635869e57804d6b1c8a Mon Sep 17 00:00:00 2001
From: Dmitry Shirokov <dshirokov@seek.com.au>
Date: Fri, 25 Sep 2020 10:27:21 +1000
Subject: [PATCH] feat: Support strings as inputs

---
 .gitignore        |  1 +
 README.md         | 16 +++++++++++++---
 package.json      |  8 ++++++--
 src/index.test.ts | 17 ++++++++++++++---
 src/index.ts      |  9 ++++++---
 5 files changed, 40 insertions(+), 11 deletions(-)

diff --git a/.gitignore b/.gitignore
index 0d608f6..05061fb 100644
--- a/.gitignore
+++ b/.gitignore
@@ -4,3 +4,4 @@ node_modules
 coverage
 npm-debug.log
 lib
+TODO.md
diff --git a/README.md b/README.md
index d49d4dd..e8efd01 100644
--- a/README.md
+++ b/README.md
@@ -1,8 +1,14 @@
 # chardet [![Build Status](https://travis-ci.org/runk/node-chardet.png)](https://travis-ci.org/runk/node-chardet)
 
-Chardet is a character detection module for NodeJS written in pure Javascript.
-Module is based on ICU project http://site.icu-project.org/, which uses character
-occurency analysis to determine the most probable encoding.
+*Chardet* is a character detection module written in pure Javascript (Typescript). Module uses occurrence analysis to determine the most probable encoding.
+
+- Packed size is only **22 KB**
+- No dependencies
+- No native code / bindings
+- Works in all environments: Node / Browser / Native
+- Works on all platforms: Linux / Mac / Windows
+- 100% written in Typescript
+- Extensive code coverage
 
 ## Installation
 
@@ -87,3 +93,7 @@ Currently only these encodings are supported.
 ## Typescript?
 
 Yes. Type definitions are included.
+
+### References
+
+- ICU project http://site.icu-project.org/
diff --git a/package.json b/package.json
index de04c47..c7cde62 100644
--- a/package.json
+++ b/package.json
@@ -2,7 +2,7 @@
   "name": "chardet",
   "version": "0.0.0-development",
   "homepage": "https://github.com/runk/node-chardet",
-  "description": "Character detector",
+  "description": "Character encoding detector",
   "license": "MIT",
   "repository": {
     "type": "git",
@@ -50,7 +50,11 @@
     "utf8",
     "detector",
     "chardet",
-    "icu"
+    "icu",
+    "character detection",
+    "character encoding",
+    "iconv",
+    "iconv-light"
   ],
   "author": "Dmitry Shirokov <deadrunk@gmail.com>",
   "contributors": [
diff --git a/src/index.test.ts b/src/index.test.ts
index 6a1f403..d0c1cc0 100644
--- a/src/index.test.ts
+++ b/src/index.test.ts
@@ -5,6 +5,8 @@ import fs from 'fs';
 describe('chardet', () => {
 
   const path = __dirname + '/test/data/encodings/utf8';
+  const getInput = () => fs.readFileSync(path);
+
   const expectedEncodingsFromPath = [
     { 'confidence': 100, 'name': 'UTF-8', 'lang': undefined },
     { 'confidence': 32, 'name': 'windows-1252', 'lang': 'fr' },
@@ -25,8 +27,12 @@ describe('chardet', () => {
   });
 
   describe('#detect', () => {
-    it('should detect encoding', () => {
-      expect(chardet.detect(fs.readFileSync(path))).toBe('UTF-8');
+    it('should detect encoding from a buffer', () => {
+      expect(chardet.detect(getInput())).toBe('UTF-8');
+    });
+
+    it('should detect encoding from a string', () => {
+      expect(chardet.detect(getInput().toString('utf-8'))).toBe('UTF-8');
     });
   });
 
@@ -54,7 +60,12 @@ describe('chardet', () => {
 
   describe('#analyse', () => {
     it('should return a list of encodings, sorted by confidence level in decending order', () => {
-      const matches = chardet.analyse(fs.readFileSync(path));
+      const matches = chardet.analyse(getInput());
+      expect(matches).toEqual(expectedEncodingsFromPath);
+    });
+
+    it('should work for strings as inputs', () => {
+      const matches = chardet.analyse(getInput().toString('utf8'));
       expect(matches).toEqual(expectedEncodingsFromPath);
     });
   });
diff --git a/src/index.ts b/src/index.ts
index e5edcb7..f9ceba0 100644
--- a/src/index.ts
+++ b/src/index.ts
@@ -49,13 +49,16 @@ const recognisers: Recogniser[] = [
 ];
 
 type DetectResult = Match[] | string | null;
+type InputData = Uint8Array | string;
 
-export const detect = (buffer: Uint8Array): string | null => {
-  const matches: Match[] = analyse(buffer);
+export const detect = (input: InputData): string | null => {
+  const matches: Match[] = analyse(input);
   return matches.length > 0 ? matches[0].name : null;
 };
 
-export const analyse = (buffer: Uint8Array): Match[] => {
+export const analyse = (input: InputData): Match[] => {
+  const buffer = typeof input === 'string' ? Buffer.from(input) : input;
+
   // Tally up the byte occurrence statistics.
   const fByteStats = [];
   for (let i = 0; i < 256; i++) fByteStats[i] = 0;