Initial commit

Author: domenic

.editorconfig

@@ -0,0 +1,9 @@
+root = true
+
+[*]
+end_of_line = lf
+insert_final_newline = true
+trim_trailing_whitespace = true
+charset = utf-8
+indent_style = space
+indent_size = 2

.eslintrc.json

@@ -0,0 +1,237 @@
+{
+  "root": true,
+  "env": {
+    "node": true,
+    "es6": true
+  },
+  "parserOptions": {
+    "ecmaVersion": 6
+  },
+  "rules": {
+    // Possible errors
+    "comma-dangle": ["error", "never"],
+    "no-cond-assign": ["error", "except-parens"],
+    "no-console": "error",
+    "no-constant-condition": "off",
+    "no-control-regex": "off",
+    "no-debugger": "error",
+    "no-dupe-args": "error",
+    "no-dupe-keys": "error",
+    "no-duplicate-case": "error",
+    "no-empty": "error",
+    "no-empty-character-class": "error",
+    "no-ex-assign": "error",
+    "no-extra-boolean-cast": "error",
+    "no-extra-parens": ["error", "all", { "conditionalAssign": false, "nestedBinaryExpressions": false, "returnAssign": false }],
+    "no-extra-semi": "error",
+    "no-func-assign": "error",
+    "no-inner-declarations": "off",
+    "no-invalid-regexp": "error",
+    "no-irregular-whitespace": "error",
+    "no-negated-in-lhs": "error",
+    "no-obj-calls": "error",
+    "no-regex-spaces": "error",
+    "no-sparse-arrays": "error",
+    "no-unexpected-multiline": "error",
+    "no-unreachable": "error",
+    "no-unsafe-finally": "off",
+    "use-isnan": "error",
+    "valid-jsdoc": "off",
+    "valid-typeof": "error",
+
+    // Best practices
+    "accessor-pairs": "error",
+    "array-callback-return": "error",
+    "block-scoped-var": "off",
+    "complexity": "off",
+    "consistent-return": "error",
+    "curly": ["error", "all"],
+    "default-case": "off",
+    "dot-location": ["error", "property"],
+    "dot-notation": "error",
+    "eqeqeq": "error",
+    "guard-for-in": "off",
+    "no-alert": "error",
+    "no-caller": "error",
+    "no-case-declarations": "error",
+    "no-div-regex": "off",
+    "no-else-return": "error",
+    "no-empty-function": "error",
+    "no-empty-pattern": "error",
+    "no-eq-null": "error",
+    "no-eval": "error",
+    "no-extend-native": "error",
+    "no-extra-bind": "error",
+    "no-extra-label": "error",
+    "no-fallthrough": "error",
+    "no-floating-decimal": "error",
+    "no-implicit-coercion": "error",
+    "no-implicit-globals": "error",
+    "no-implied-eval": "error",
+    "no-invalid-this": "error",
+    "no-iterator": "error",
+    "no-labels": ["error", { "allowLoop": true }],
+    "no-lone-blocks": "error",
+    "no-loop-func": "off",
+    "no-magic-numbers": "off",
+    "no-multi-spaces": "error",
+    "no-multi-str": "error",
+    "no-native-reassign": "error",
+    "no-new": "error",
+    "no-new-func": "error",
+    "no-new-wrappers": "error",
+    "no-octal": "error",
+    "no-octal-escape": "error",
+    "no-param-reassign": "off",
+    "no-process-env": "error",
+    "no-proto": "error",
+    "no-redeclare": "error",
+    "no-return-assign": ["error", "except-parens"],
+    "no-script-url": "off",
+    "no-self-assign": "error",
+    "no-self-compare": "error",
+    "no-sequences": "error",
+    "no-throw-literal": "error",
+    "no-unmodified-loop-condition": "error",
+    "no-unused-expressions": "error",
+    "no-unused-labels": "error",
+    "no-useless-call": "error",
+    "no-useless-concat": "error",
+    "no-useless-escape": "error",
+    "no-void": "error",
+    "no-warning-comments": "off",
+    "no-with": "error",
+    "radix": ["error", "as-needed"],
+    "vars-on-top": "off",
+    "wrap-iife": ["error", "outside"],
+    "yoda": ["error", "never"],
+
+    // Strict Mode
+    "strict": ["error", "global"],
+
+    // Variables
+    "init-declarations": "off",
+    "no-catch-shadow": "error",
+    "no-delete-var": "error",
+    "no-label-var": "error",
+    "no-restricted-globals": "off",
+    "no-shadow": "error",
+    "no-shadow-restricted-names": "error",
+    "no-undef": "error",
+    "no-undef-init": "error",
+    "no-undefined": "off",
+    "no-unused-vars": "error",
+    "no-use-before-define": ["error", "nofunc"],
+
+    // Node.js and CommonJS
+    "callback-return": "off",
+    "global-require": "error",
+    "handle-callback-err": "error",
+    "no-mixed-requires": ["error", true],
+    "no-new-require": "error",
+    "no-path-concat": "error",
+    "no-process-exit": "error",
+    "no-restricted-imports": "off",
+    "no-restricted-modules": "off",
+    "no-sync": "off",
+
+    // Stylistic Issues
+    "array-bracket-spacing": ["error", "never"],
+    "block-spacing": ["error", "always"],
+    "brace-style": ["error", "1tbs", { "allowSingleLine": false }],
+    "camelcase": ["error", { "properties": "always" }],
+    "comma-spacing": ["error", { "before": false, "after": true }],
+    "comma-style": ["error", "last"],
+    "computed-property-spacing": ["error", "never"],
+    "consistent-this": "off",
+    "eol-last": "error",
+    "func-names": "off",
+    "func-style": ["error", "declaration"],
+    "id-blacklist": "off",
+    "id-length": "off",
+    "id-match": "off",
+    "indent": ["error", 2, { "SwitchCase": 1 }],
+    "jsx-quotes": "off",
+    "key-spacing": ["error", { "beforeColon": false, "afterColon": true, "mode": "strict" }],
+    "keyword-spacing": ["error", { "before": true, "after": true }],
+    "linebreak-style": ["error", "unix"],
+    "lines-around-comment": "off",
+    "max-depth": "off",
+    "max-len": ["error", 120, { "ignoreUrls": true }],
+    "max-nested-callbacks": "off",
+    "max-params": "off",
+    "max-statements": "off",
+    "max-statements-per-line": ["error", { "max": 1 }],
+    "new-cap": ["error", { "capIsNewExceptions": ["USVString"] }],
+    "new-parens": "error",
+    "newline-after-var": "off",
+    "newline-before-return": "off",
+    "newline-per-chained-call": "off",
+    "no-array-constructor": "error",
+    "no-bitwise": "off",
+    "no-continue": "off",
+    "no-inline-comments": "off",
+    "no-lonely-if": "error",
+    "no-mixed-spaces-and-tabs": "error",
+    "no-multiple-empty-lines": "error",
+    "no-negated-condition": "off",
+    "no-nested-ternary": "error",
+    "no-new-object": "error",
+    "no-plusplus": "off",
+    "no-restricted-syntax": "off",
+    "no-spaced-func": "error",
+    "no-ternary": "off",
+    "no-trailing-spaces": "error",
+    "no-underscore-dangle": "off",
+    "no-unneeded-ternary": "error",
+    "no-whitespace-before-property": "error",
+    "object-curly-spacing": ["error", "always"],
+    "object-property-newline": "off",
+    "one-var": ["error", "never"],
+    "one-var-declaration-per-line": ["error", "initializations"],
+    "operator-assignment": ["error", "always"],
+    "operator-linebreak": ["error", "after"],
+    "padded-blocks": ["error", "never"],
+    "quote-props": ["error", "as-needed"],
+    "quotes": ["error", "double", { "avoidEscape": true, "allowTemplateLiterals": true }],
+    "require-jsdoc": "off",
+    "semi": ["error", "always"],
+    "semi-spacing": "error",
+    "sort-imports": "off",
+    "sort-vars": "off",
+    "space-before-blocks": ["error", "always"],
+    "space-before-function-paren": ["error", { "anonymous": "always", "named": "never" }],
+    "space-in-parens": ["error", "never"],
+    "space-infix-ops": "error",
+    "space-unary-ops": ["error", { "words": true, "nonwords": false }],
+    "spaced-comment": ["error", "always", { "markers": ["///"] }],
+    "wrap-regex": "off",
+
+    // ECMAScript 6
+    "arrow-body-style": "off", // meh
+    "arrow-parens": ["error", "as-needed"],
+    "arrow-spacing": "error",
+    "constructor-super": "error",
+    "generator-star-spacing": ["error", "after"],
+    "no-class-assign": "error",
+    "no-confusing-arrow": "off",
+    "no-const-assign": "error",
+    "no-dupe-class-members": "error",
+    "no-duplicate-imports": "error",
+    "no-new-symbol": "error",
+    "no-this-before-super": "error",
+    "no-useless-computed-key": "error",
+    "no-useless-constructor": "error",
+    "no-var": "error",
+    "object-shorthand": "error",
+    "prefer-arrow-callback": "error",
+    "prefer-const": ["error", { "ignoreReadBeforeAssign": true }],
+    "prefer-reflect": "off",
+    "prefer-rest-params": "off",
+    "prefer-spread": "off", // TODO with new Node versions
+    "prefer-template": "off",
+    "require-yield": "error",
+    "template-curly-spacing": ["error", "never"],
+    "yield-star-spacing": ["error", "after"]
+  }
+}

.gitignore

@@ -0,0 +1,4 @@
+/node_modules/
+/npm-debug.log
+
+/lib/labels-to-names.json

.travis.yml

@@ -0,0 +1,5 @@
+language: node_js
+node_js:
+  - stable
+script:
+  npm run lint && npm test

LICENSE.txt

@@ -0,0 +1,19 @@
+Copyright © 2016 Domenic Denicola <[email protected]>
+
+This work is free. You can redistribute it and/or modify it under the
+terms of the Do What The Fuck You Want To Public License, Version 2,
+as published by Sam Hocevar. See below for more details.
+
+        DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE
+                    Version 2, December 2004
+
+ Copyright (C) 2004 Sam Hocevar <[email protected]>
+
+ Everyone is permitted to copy and distribute verbatim or modified
+ copies of this license document, and changing it is allowed as long
+ as the name is changed.
+
+            DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. You just DO WHAT THE FUCK YOU WANT TO.

README.md

@@ -0,0 +1,38 @@
+# Determine the Encoding of a HTML Byte Stream
+
+This package implements the HTML Standard's [encoding sniffing algorithm](https://html.spec.whatwg.org/multipage/syntax.html#encoding-sniffing-algorithm) in all its glory. The most interesting part of this is how it pre-scans the first 1024 bytes in order to search for certain `<meta charset>`-related patterns.
+
+```js
+const htmlEncodingSniffer = require("html-encoding-sniffer");
+const fs = require("fs");
+
+const htmlBuffer = fs.readFileSync("./html-page.html");
+const sniffedEncoding = htmlEncodingSniffer(htmlBuffer);
+```
+
+The returned value will be a canonical [encoding name](https://encoding.spec.whatwg.org/#names-and-labels) (not a label). You might then combine this with the [whatwg-encoding](https://github.com/jsdom/whatwg-encoding) package to decode the result:
+
+```js
+const whatwgEncoding = require("whatwg-encoding");
+const htmlString = whatwgEncoding.decode(htmlBuffer, sniffedEncoding);
+```
+
+## Options
+
+You can pass two potential options to `htmlEncodingSniffer`:
+
+```js
+const sniffedEncoding = htmlEncodingSniffer(htmlBuffer, {
+  transportLayerEncodingLabel,
+  defaultEncoding
+});
+```
+
+These represent two possible inputs into the [encoding sniffing algorithm](https://html.spec.whatwg.org/multipage/syntax.html#encoding-sniffing-algorithm):
+
+- `transportLayerEncodingLabel` is an encoding label that is obtained from the "transport layer" (probably a HTTP `Content-Type` header), which overrides everything but a BOM.
+- `defaultEncoding` is the ultimate fallback encoding used if no valid encoding is supplied by the transport layer, and no encoding is sniffed from the bytes. It defaults to `"windows-1252"`, as recommended by the algorithm's table of suggested defaults for "All other locales" (including the `en` locale).
+
+## Credits
+
+This package was originally based on the excellent work of [@nicolashenry](https://github.com/nicolashenry), [in jsdom](https://github.com/tmpvar/jsdom/blob/16fd85618f2705d181232f6552125872a37164bc/lib/jsdom/living/helpers/encoding.js). It has since been pulled out into this separate package.