From 01a4a91c0fddab08d06046155d2a4f02457c52c3 Mon Sep 17 00:00:00 2001
From: Adam Lynch <contact@adamlynch.com>
Date: Wed, 7 Apr 2021 09:50:33 +0100
Subject: [PATCH] Add `stripTextFragment` option (#130)

---
 index.d.ts      | 24 ++++++++++++++++++++++++
 index.js        |  3 +++
 index.test-d.ts |  3 +++
 readme.md       | 23 +++++++++++++++++++++++
 test.js         | 24 ++++++++++++++++++++++++
 5 files changed, 77 insertions(+)

diff --git a/index.d.ts b/index.d.ts
index 74f3403..848b899 100644
--- a/index.d.ts
+++ b/index.d.ts
@@ -103,6 +103,30 @@ declare namespace normalizeUrl {
 		*/
 		readonly stripProtocol?: boolean;
 
+		/**
+		Strip the [text fragment](https://web.dev/text-fragments/) part of the URL
+
+		__Note:__ The text fragment will always be removed if the `stripHash` option is set to `true`, as the hash contains the text fragment.
+
+		@default true
+
+		@example
+		```
+		normalizeUrl('http://sindresorhus.com/about.html#:~:text=hello');
+		//=> 'http://sindresorhus.com/about.html#'
+
+		normalizeUrl('http://sindresorhus.com/about.html#section:~:text=hello');
+		//=> 'http://sindresorhus.com/about.html#section'
+
+		normalizeUrl('http://sindresorhus.com/about.html#:~:text=hello', {stripTextFragment: false});
+		//=> 'http://sindresorhus.com/about.html#:~:text=hello'
+
+		normalizeUrl('http://sindresorhus.com/about.html#section:~:text=hello', {stripTextFragment: false});
+		//=> 'http://sindresorhus.com/about.html#section:~:text=hello'
+		```
+		*/
+		readonly stripTextFragment?: boolean;
+
 		/**
 		Removes `www.` from the URL.
 
diff --git a/index.js b/index.js
index a746086..b66a897 100644
--- a/index.js
+++ b/index.js
@@ -67,6 +67,7 @@ const normalizeUrl = (urlString, options) => {
 		forceHttps: false,
 		stripAuthentication: true,
 		stripHash: false,
+		stripTextFragment: true,
 		stripWWW: true,
 		removeQueryParameters: [/^utm_\w+/i],
 		removeTrailingSlash: true,
@@ -118,6 +119,8 @@ const normalizeUrl = (urlString, options) => {
 	// Remove hash
 	if (options.stripHash) {
 		urlObj.hash = '';
+	} else if (options.stripTextFragment) {
+		urlObj.hash = urlObj.hash.replace(/#?:~:text.*?$/i, '');
 	}
 
 	// Remove duplicate slashes if not preceded by a protocol
diff --git a/index.test-d.ts b/index.test-d.ts
index 7f2e308..a59312e 100644
--- a/index.test-d.ts
+++ b/index.test-d.ts
@@ -23,3 +23,6 @@ normalizeUrl('www.sindresorhus.com/foo/default.php', {
 normalizeUrl('www.sindresorhus.com?b=two&a=one&c=three', {
 	sortQueryParameters: false
 });
+normalizeUrl('www.sindresorhus.com/about#:~:text=hello', {
+	stripTextFragment: false
+});
diff --git a/readme.md b/readme.md
index f851c2b..b3406aa 100644
--- a/readme.md
+++ b/readme.md
@@ -135,6 +135,29 @@ normalizeUrl('https://sindresorhus.com', {stripProtocol: true});
 //=> 'sindresorhus.com'
 ```
 
+##### stripTextFragment
+
+Type: `boolean`\
+Default: `true`
+
+Strip the [text fragment](https://web.dev/text-fragments/) part of the URL.
+
+**Note:** The text fragment will always be removed if the `stripHash` option is set to `true`, as the hash contains the text fragment.
+
+```js
+normalizeUrl('http://sindresorhus.com/about.html#:~:text=hello');
+//=> 'http://sindresorhus.com/about.html#'
+
+normalizeUrl('http://sindresorhus.com/about.html#section:~:text=hello');
+//=> 'http://sindresorhus.com/about.html#section'
+
+normalizeUrl('http://sindresorhus.com/about.html#:~:text=hello', {stripTextFragment: false});
+//=> 'http://sindresorhus.com/about.html#:~:text=hello'
+
+normalizeUrl('http://sindresorhus.com/about.html#section:~:text=hello', {stripTextFragment: false});
+//=> 'http://sindresorhus.com/about.html#section:~:text=hello'
+```
+
 ##### stripWWW
 
 Type: `boolean`\
diff --git a/test.js b/test.js
index 5f2e54b..4cf557e 100644
--- a/test.js
+++ b/test.js
@@ -34,6 +34,7 @@ test('main', t => {
 	t.is(normalizeUrl('//sindresorhus.com:80/', {normalizeProtocol: false}), '//sindresorhus.com');
 	t.is(normalizeUrl('http://sindresorhus.com/foo#bar'), 'http://sindresorhus.com/foo#bar');
 	t.is(normalizeUrl('http://sindresorhus.com/foo#bar', {stripHash: true}), 'http://sindresorhus.com/foo');
+	t.is(normalizeUrl('http://sindresorhus.com/foo#bar:~:text=hello%20world', {stripHash: true}), 'http://sindresorhus.com/foo');
 	t.is(normalizeUrl('http://sindresorhus.com/foo/bar/../baz'), 'http://sindresorhus.com/foo/baz');
 	t.is(normalizeUrl('http://sindresorhus.com/foo/bar/./baz'), 'http://sindresorhus.com/foo/bar/baz');
 	t.is(normalizeUrl('sindre://www.sorhus.com'), 'sindre://sorhus.com');
@@ -69,6 +70,29 @@ test('stripProtocol option', t => {
 	t.is(normalizeUrl('sindre://www.sorhus.com', options), 'sindre://sorhus.com');
 });
 
+test('stripTextFragment option', t => {
+	t.is(normalizeUrl('http://sindresorhus.com'), 'http://sindresorhus.com');
+	t.is(normalizeUrl('http://sindresorhus.com/about#'), 'http://sindresorhus.com/about');
+	t.is(normalizeUrl('http://sindresorhus.com/about#:~:text=hello'), 'http://sindresorhus.com/about');
+	t.is(normalizeUrl('http://sindresorhus.com/about#main'), 'http://sindresorhus.com/about#main');
+	t.is(normalizeUrl('http://sindresorhus.com/about#main:~:text=hello'), 'http://sindresorhus.com/about#main');
+	t.is(normalizeUrl('http://sindresorhus.com/about#main:~:text=hello%20world'), 'http://sindresorhus.com/about#main');
+
+	const options = {stripTextFragment: false};
+	t.is(normalizeUrl('http://sindresorhus.com', options), 'http://sindresorhus.com');
+	t.is(normalizeUrl('http://sindresorhus.com/about#:~:text=hello', options), 'http://sindresorhus.com/about#:~:text=hello');
+	t.is(normalizeUrl('http://sindresorhus.com/about#main', options), 'http://sindresorhus.com/about#main');
+	t.is(normalizeUrl('http://sindresorhus.com/about#main:~:text=hello', options), 'http://sindresorhus.com/about#main:~:text=hello');
+	t.is(normalizeUrl('http://sindresorhus.com/about#main:~:text=hello%20world', options), 'http://sindresorhus.com/about#main:~:text=hello%20world');
+
+	const options2 = {stripHash: true, stripTextFragment: false};
+	t.is(normalizeUrl('http://sindresorhus.com', options2), 'http://sindresorhus.com');
+	t.is(normalizeUrl('http://sindresorhus.com/about#:~:text=hello', options2), 'http://sindresorhus.com/about');
+	t.is(normalizeUrl('http://sindresorhus.com/about#main', options2), 'http://sindresorhus.com/about');
+	t.is(normalizeUrl('http://sindresorhus.com/about#main:~:text=hello', options2), 'http://sindresorhus.com/about');
+	t.is(normalizeUrl('http://sindresorhus.com/about#main:~:text=hello%20world', options2), 'http://sindresorhus.com/about');
+});
+
 test('stripWWW option', t => {
 	const options = {stripWWW: false};
 	t.is(normalizeUrl('http://www.sindresorhus.com', options), 'http://www.sindresorhus.com');