From 5d309ff52cd399a6b71968a6b9a70c8ac0b98981 Mon Sep 17 00:00:00 2001 From: Joel Kronqvist Date: Sat, 5 Mar 2022 19:02:27 +0200 Subject: Added node_modules for the updating to work properly. --- node_modules/html-encoding-sniffer/README.md | 38 ++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 node_modules/html-encoding-sniffer/README.md (limited to 'node_modules/html-encoding-sniffer/README.md') diff --git a/node_modules/html-encoding-sniffer/README.md b/node_modules/html-encoding-sniffer/README.md new file mode 100644 index 0000000..8913991 --- /dev/null +++ b/node_modules/html-encoding-sniffer/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 ``-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. -- cgit v1.2.3