chardet - npm Package Compare versions

Comparing version 1.2.2 to 1.3.0

lib/encoding/iso2022.d.ts

 import { Context, Recogniser } from '.';
+import { Match } from '../match';
 declare class ISO_2022 implements Recogniser {
     escapeSequences: number[][];
     name(): string;
-    match(det: Context): any;
+    match(det: Context): Match | null;
 }
@@ -7,0 +8,0 @@ export declare class ISO_2022_JP extends ISO_2022 {

lib/encoding/iso2022.js

 "use strict";
+var __importDefault = (this && this.__importDefault) || function (mod) {
+    return (mod && mod.__esModule) ? mod : { "default": mod };
+};
 Object.defineProperty(exports, "__esModule", { value: true });
-var match = require('../match').default;
+exports.ISO_2022_CN = exports.ISO_2022_KR = exports.ISO_2022_JP = void 0;
+const match_1 = __importDefault(require("../match"));
 class ISO_2022 {
@@ -12,14 +16,14 @@ constructor() {
     match(det) {
-        var i, j;
-        var escN;
-        var hits = 0;
-        var misses = 0;
-        var shifts = 0;
-        var quality;
-        var text = det.fInputBytes;
-        var textLen = det.fInputLen;
+        let i, j;
+        let escN;
+        let hits = 0;
+        let misses = 0;
+        let shifts = 0;
+        let quality;
+        const text = det.fInputBytes;
+        const textLen = det.fInputLen;
         scanInput: for (i = 0; i < textLen; i++) {
             if (text[i] == 0x1b) {
                 checkEscapes: for (escN = 0; escN < this.escapeSequences.length; escN++) {
-                    var seq = this.escapeSequences[escN];
+                    const seq = this.escapeSequences[escN];
                     if (textLen - i < seq.length)
@@ -44,3 +48,3 @@ continue checkEscapes;
             quality -= (5 - (hits + shifts)) * 10;
-        return quality <= 0 ? null : match(det, this, quality);
+        return quality <= 0 ? null : match_1.default(det, this, quality);
     }
@@ -47,0 +51,0 @@ }

lib/encoding/mbcs.d.ts

 import { Context, Recogniser } from '.';
+import { Match } from '../match';
 declare class IteratedChar {
@@ -15,3 +16,3 @@ charValue: number;
     name(): string;
-    match(det: Context): any;
+    match(det: Context): Match | null;
     nextChar(iter: IteratedChar, det: Context): boolean;
@@ -18,0 +19,0 @@ }

lib/encoding/mbcs.js

 "use strict";
+var __importDefault = (this && this.__importDefault) || function (mod) {
+    return (mod && mod.__esModule) ? mod : { "default": mod };
+};
 Object.defineProperty(exports, "__esModule", { value: true });
-var match = require('../match').default;
+exports.gb_18030 = exports.euc_kr = exports.euc_jp = exports.big5 = exports.sjis = void 0;
+const match_1 = __importDefault(require("../match"));
 function binarySearch(arr, searchValue) {
@@ -8,3 +12,3 @@ const find = (arr, searchValue, left, right) => {
             return -1;
-        var mid = Math.floor((left + right) >>> 1);
+        const mid = Math.floor((left + right) >>> 1);
         if (searchValue > arr[mid])
@@ -38,3 +42,3 @@ return find(arr, searchValue, mid + 1, right);
         }
-        var byteValue = det.fRawInput[this.nextIndex++] & 0x00ff;
+        const byteValue = det.fRawInput[this.nextIndex++] & 0x00ff;
         return byteValue;
@@ -51,4 +55,4 @@ }
     match(det) {
-        var singleByteCharCount = 0, doubleByteCharCount = 0, commonCharCount = 0, badCharCount = 0, totalCharCount = 0, confidence = 0;
-        var iter = new IteratedChar();
+        let singleByteCharCount = 0, doubleByteCharCount = 0, commonCharCount = 0, badCharCount = 0, totalCharCount = 0, confidence = 0;
+        const iter = new IteratedChar();
         detectBlock: {
@@ -61,3 +65,3 @@ for (iter.reset(); this.nextChar(iter, det);) {
                 else {
-                    var cv = iter.charValue & 0xffffffff;
+                    const cv = iter.charValue & 0xffffffff;
                     if (cv <= 0xff) {
@@ -99,4 +103,4 @@ singleByteCharCount++;
             else {
-                var maxVal = Math.log(parseFloat(doubleByteCharCount) / 4);
-                var scaleFactor = 90.0 / maxVal;
+                const maxVal = Math.log(doubleByteCharCount / 4);
+                const scaleFactor = 90.0 / maxVal;
                 confidence = Math.floor(Math.log(commonCharCount + 1) * scaleFactor + 10);
@@ -106,3 +110,3 @@ confidence = Math.min(confidence, 100);
         }
-        return confidence == 0 ? null : match(det, this, confidence);
+        return confidence == 0 ? null : match_1.default(det, this, confidence);
     }
@@ -185,4 +189,3 @@ nextChar(iter, det) {
         iter.error = false;
-        var firstByte;
-        firstByte = iter.charValue = iter.nextByte(det);
+        const firstByte = (iter.charValue = iter.nextByte(det));
         if (firstByte < 0)
@@ -192,3 +195,3 @@ return false;
             return true;
-        var secondByte = iter.nextByte(det);
+        const secondByte = iter.nextByte(det);
         if (secondByte < 0)
@@ -316,3 +319,3 @@ return false;
         iter.error = false;
-        var firstByte = (iter.charValue = iter.nextByte(det));
+        const firstByte = (iter.charValue = iter.nextByte(det));
         if (firstByte < 0)
@@ -322,3 +325,3 @@ return false;
             return true;
-        var secondByte = iter.nextByte(det);
+        const secondByte = iter.nextByte(det);
         if (secondByte < 0)
@@ -336,5 +339,5 @@ return false;
     iter.error = false;
-    var firstByte = 0;
-    var secondByte = 0;
-    var thirdByte = 0;
+    let firstByte = 0;
+    let secondByte = 0;
+    let thirdByte = 0;
     buildChar: {
@@ -718,6 +721,6 @@ firstByte = iter.charValue = iter.nextByte(det);
         iter.error = false;
-        var firstByte = 0;
-        var secondByte = 0;
-        var thirdByte = 0;
-        var fourthByte = 0;
+        let firstByte = 0;
+        let secondByte = 0;
+        let thirdByte = 0;
+        let fourthByte = 0;
         buildChar: {
@@ -724,0 +727,0 @@ firstByte = iter.charValue = iter.nextByte(det);

lib/encoding/sbcs.d.ts

 import { Context, Recogniser } from '../encoding/index';
+import { Match } from '../match';
 declare class NGramsPlusLang {
@@ -12,3 +13,3 @@ fLang: string;
     name(input: Context): string;
-    match(det: Context): any;
+    match(det: Context): Match | null;
 }
@@ -15,0 +16,0 @@ export declare class ISO_8859_1 extends sbcs {

lib/encoding/unicode.d.ts

 import { Context, Recogniser } from '.';
+import { Match } from '../match';
 export declare class UTF_16BE implements Recogniser {
     name(): string;
-    match(det: Context): any;
+    match(det: Context): Match | null;
 }
 export declare class UTF_16LE implements Recogniser {
     name(): string;
-    match(det: Context): any;
+    match(det: Context): Match | null;
 }
@@ -16,3 +17,3 @@ interface WithGetChar {
     getChar(input: Uint8Array, index: number): number;
-    match(det: Context): any;
+    match(det: Context): Match | null;
 }
@@ -19,0 +20,0 @@ export declare class UTF_32BE extends UTF_32 {

lib/encoding/unicode.js

 "use strict";
+var __importDefault = (this && this.__importDefault) || function (mod) {
+    return (mod && mod.__esModule) ? mod : { "default": mod };
+};
 Object.defineProperty(exports, "__esModule", { value: true });
-const match = require('../match').default;
+exports.UTF_32LE = exports.UTF_32BE = exports.UTF_16LE = exports.UTF_16BE = void 0;
+const match_1 = __importDefault(require("../match"));
 class UTF_16BE {
@@ -9,7 +13,7 @@ name() {
     match(det) {
-        var input = det.fRawInput;
+        const input = det.fRawInput;
         if (input.length >= 2 &&
             (input[0] & 0xff) == 0xfe &&
             (input[1] & 0xff) == 0xff) {
-            return match(det, this, 100);
+            return match_1.default(det, this, 100);
         }
@@ -25,3 +29,3 @@ return null;
     match(det) {
-        var input = det.fRawInput;
+        const input = det.fRawInput;
         if (input.length >= 2 &&
@@ -33,3 +37,3 @@ (input[0] & 0xff) == 0xff &&
             }
-            return match(det, this, 100);
+            return match_1.default(det, this, 100);
         }
@@ -48,3 +52,5 @@ return null;
     match(det) {
-        var input = det.fRawInput, limit = (det.fRawLength / 4) * 4, numValid = 0, numInvalid = 0, hasBOM = false, confidence = 0;
+        let numValid = 0, numInvalid = 0, hasBOM = false, confidence = 0;
+        const limit = (det.fRawLength / 4) * 4;
+        const input = det.fRawInput;
         if (limit == 0) {
@@ -56,4 +62,4 @@ return null;
         }
-        for (var i = 0; i < limit; i += 4) {
-            var ch = this.getChar(input, i);
+        for (let i = 0; i < limit; i += 4) {
+            const ch = this.getChar(input, i);
             if (ch < 0 || ch >= 0x10ffff || (ch >= 0xd800 && ch <= 0xdfff)) {
@@ -81,3 +87,3 @@ numInvalid += 1;
         }
-        return confidence == 0 ? null : match(det, this, confidence);
+        return confidence == 0 ? null : match_1.default(det, this, confidence);
     }
@@ -84,0 +90,0 @@ }

lib/encoding/utf8.d.ts

 import { Context, Recogniser } from '.';
+import { Match } from '../match';
 export default class Utf8 implements Recogniser {
     name(): string;
-    match(det: Context): any;
+    match(det: Context): Match | null;
 }

lib/encoding/utf8.js

 "use strict";
+var __importDefault = (this && this.__importDefault) || function (mod) {
+    return (mod && mod.__esModule) ? mod : { "default": mod };
+};
 Object.defineProperty(exports, "__esModule", { value: true });
-var match = require('../match').default;
+const match_1 = __importDefault(require("../match"));
 class Utf8 {
@@ -9,3 +12,4 @@ name() {
     match(det) {
-        var hasBOM = false, numValid = 0, numInvalid = 0, input = det.fRawInput, trailBytes = 0, confidence;
+        let hasBOM = false, numValid = 0, numInvalid = 0, trailBytes = 0, confidence;
+        const input = det.fRawInput;
         if (det.fRawLength >= 3 &&
@@ -17,4 +21,4 @@ (input[0] & 0xff) == 0xef &&
         }
-        for (var i = 0; i < det.fRawLength; i++) {
-            var b = input[i];
+        for (let i = 0; i < det.fRawLength; i++) {
+            const b = input[i];
             if ((b & 0x80) == 0)
@@ -66,3 +70,3 @@ continue;
             return null;
-        return match(det, this, confidence);
+        return match_1.default(det, this, confidence);
     }
@@ -69,0 +73,0 @@ }

lib/index.d.ts

@@ -5,7 +5,8 @@ import { Match } from './match';
 }
+declare type Options = Partial<FullOptions>;
 declare type DetectResult = Match[] | string | null;
 export declare const detect: (buffer: Uint8Array) => string | null;
 export declare const analyse: (buffer: Uint8Array) => Match[];
-export declare const detectFile: (filepath: string, opts?: Partial<FullOptions>) => Promise<DetectResult>;
-export declare const detectFileSync: (filepath: string, opts?: Partial<FullOptions>) => DetectResult;
+export declare const detectFile: (filepath: string, opts?: Options) => Promise<DetectResult>;
+export declare const detectFileSync: (filepath: string, opts?: Options) => DetectResult;
 declare const _default: {
@@ -12,0 +13,0 @@ analyse: (buffer: Uint8Array) => Match[];

lib/index.js

 "use strict";
-var __importDefault = (this && this.__importDefault) || function (mod) {
-    return (mod && mod.__esModule) ? mod : { "default": mod };
-};
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    Object.defineProperty(o, k2, { enumerable: true, get: function() { return m[k]; } });
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
+    Object.defineProperty(o, "default", { enumerable: true, value: v });
+}) : function(o, v) {
+    o["default"] = v;
+});
 var __importStar = (this && this.__importStar) || function (mod) {
     if (mod && mod.__esModule) return mod;
     var result = {};
-    if (mod != null) for (var k in mod) if (Object.hasOwnProperty.call(mod, k)) result[k] = mod[k];
-    result["default"] = mod;
+    if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
+    __setModuleDefault(result, mod);
     return result;
 };
+var __importDefault = (this && this.__importDefault) || function (mod) {
+    return (mod && mod.__esModule) ? mod : { "default": mod };
+};
 Object.defineProperty(exports, "__esModule", { value: true });
+exports.detectFileSync = exports.detectFile = exports.analyse = exports.detect = void 0;
+const node_1 = __importDefault(require("./fs/node"));
 const utf8_1 = __importDefault(require("./encoding/utf8"));
@@ -18,10 +32,2 @@ const unicode = __importStar(require("./encoding/unicode"));
 const iso2022 = __importStar(require("./encoding/iso2022"));
-let fsModule;
-const loadFs = () => {
-    if (typeof module === 'object' && typeof module.exports === 'object') {
-        fsModule = fsModule ? fsModule : require('fs');
-        return fsModule;
-    }
-    throw new Error('File system is not available');
-};
 const recognisers = [
@@ -91,3 +97,3 @@ new utf8_1.default(),
     let fd;
-    const fs = loadFs();
+    const fs = node_1.default();
     const handler = (err, buffer) => {
@@ -115,3 +121,3 @@ if (fd) {
 exports.detectFileSync = (filepath, opts = {}) => {
-    const fs = loadFs();
+    const fs = node_1.default();
     if (opts && opts.sampleSize) {
@@ -118,0 +124,0 @@ const fd = fs.openSync(filepath, 'r');

lib/match.d.ts

@@ -0,7 +1,8 @@
+import { Context, Recogniser } from "./encoding";
 export interface Match {
     confidence: number;
     name: string;
-    lang: string;
+    lang?: string;
 }
-declare const _default: (det: any, rec: any, confidence: any, name: any, lang: any) => Match;
+declare const _default: (det: Context, rec: Recogniser, confidence: number, name?: string | undefined, lang?: string | undefined) => Match;
 export default _default;

package.json

 {
   "name": "chardet",
-  "version": "1.2.2",
+  "version": "1.3.0",
   "homepage": "https://github.com/runk/node-chardet",
-  "description": "Character detector",
+  "description": "Character encoding detector",
   "license": "MIT",
@@ -17,3 +17,3 @@ "repository": {
     "build": "rm -rf lib/* && tsc",
-    "lint": "tslint -p tsconfig.json -c tslint.json",
+    "lint": "eslint . --ext .js,.jsx,.ts,.tsx",
     "lint:types": "tsc --noEmit",
@@ -26,6 +26,6 @@ "format": "prettier --write ./src/**/*.ts",
   },
-  "main": "lib/index.js",
   "files": [
     "lib"
   ],
+  "main": "lib/index.js",
   "typings": "lib/index.d.ts",
@@ -40,10 +40,12 @@ "engine": {
   "devDependencies": {
-    "@types/jest": "^25.1.4",
-    "@types/node": "^13.9.5",
-    "jest": "^25.2.4",
-    "prettier": "^2.0.2",
-    "semantic-release": "^15.14.0",
-    "ts-jest": "^25.2.1",
-    "tslint": "^6.1.0",
-    "typescript": "^3.8.3"
+    "@types/jest": "^26.0.14",
+    "@types/node": "^14.11.2",
+    "@typescript-eslint/eslint-plugin": "^4.2.0",
+    "@typescript-eslint/parser": "^4.2.0",
+    "eslint": "^7.9.0",
+    "jest": "^26.4.2",
+    "prettier": "^2.1.2",
+    "semantic-release": "^17.1.2",
+    "ts-jest": "^26.4.0",
+    "typescript": "^4.0.3"
   },
@@ -56,3 +58,34 @@ "keywords": [
     "chardet",
-    "icu"
+    "icu",
+    "character detection",
+    "character encoding",
+    "language",
+    "iconv",
+    "iconv-light",
+    "UTF-8",
+    "UTF-16",
+    "UTF-32",
+    "ISO-2022-JP",
+    "ISO-2022-KR",
+    "ISO-2022-CN",
+    "Shift_JIS",
+    "Big5",
+    "EUC-JP",
+    "EUC-KR",
+    "GB18030",
+    "ISO-8859-1",
+    "ISO-8859-2",
+    "ISO-8859-5",
+    "ISO-8859-6",
+    "ISO-8859-7",
+    "ISO-8859-8",
+    "ISO-8859-9",
+    "windows-1250",
+    "windows-1251",
+    "windows-1252",
+    "windows-1253",
+    "windows-1254",
+    "windows-1255",
+    "windows-1256",
+    "KOI8-R"
   ],
@@ -66,3 +99,6 @@ "author": "Dmitry Shirokov <[e-mail]>",
     "@zevanty"
-  ]
+  ],
+  "browser": {
+    "./lib/fs/node.js": "./lib/fs/browser.js"
+  }
 }

README.md

 # 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**
+- Works in all environments: Node / Browser / Native
+- Works on all platforms: Linux / Mac / Windows
+- No dependencies
+- No native code / bindings
+- 100% written in Typescript
+- Extensive code coverage
+
 ## Installation
@@ -90,1 +96,5 @@
 Yes. Type definitions are included.
+
+### References
+
+- ICU project http://site.icu-project.org/

No alert changes

Improved metrics

Total package byte prevSize

206901

increased by1.94%

Number of package files

33

increased by22.22%

Lines of code

5752

increased by0.93%

Number of lines in readme file

100

increased by11.11%

Worsened metrics

Dev dependency count

10

increased by25%

No dependency changes