From 1f5adece65506a6976d5fefe61c68cfa74f04ef2 Mon Sep 17 00:00:00 2001
From: Jacob Mischka <jacob@mischka.me>
Date: Mon, 26 Jul 2021 13:07:47 -0500
Subject: [PATCH] Add checks to ensure in-word formatting chars aren't replaced

Basic text formatting sequences (_, *, __, **) are now required to not
be entirely within a word; that is, they must have a non-word character
on either side to be replaced.

This prevents words that include those characters (snake_case words, or
some proper nouns that may include an Embedded*Asterisk__Or**Two for
some reason) from being captured.

Fixes #21
---
 src/index.js  | 2 +-
 test/index.js | 7 +++++++
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/src/index.js b/src/index.js
index 3938c5c..530d0f7 100644
--- a/src/index.js
+++ b/src/index.js
@@ -24,7 +24,7 @@ function encodeAttr(str) {
 
 /** Parse Markdown into an HTML String. */
 export default function parse(md, prevLinks) {
-	let tokenizer = /((?:^|\n+)(?:\n---+|\* \*(?: \*)+)\n)|(?:^``` *(\w*)\n([\s\S]*?)\n```$)|((?:(?:^|\n+)(?:\t|  {2,}).+)+\n*)|((?:(?:^|\n)([>*+-]|\d+\.)\s+.*)+)|(?:!\[([^\]]*?)\]\(([^)]+?)\))|(\[)|(\](?:\(([^)]+?)\))?)|(?:(?:^|\n+)([^\s].*)\n(-{3,}|={3,})(?:\n+|$))|(?:(?:^|\n+)(#{1,6})\s*(.+)(?:\n+|$))|(?:`([^`].*?)`)|(  \n\n*|\n{2,}|__|\*\*|[_*]|~~)/gm,
+	let tokenizer = /((?:^|\n+)(?:\n---+|\* \*(?: \*)+)\n)|(?:^``` *(\w*)\n([\s\S]*?)\n```$)|((?:(?:^|\n+)(?:\t|  {2,}).+)+\n*)|((?:(?:^|\n)([>*+-]|\d+\.)\s+.*)+)|(?:!\[([^\]]*?)\]\(([^)]+?)\))|(\[)|(\](?:\(([^)]+?)\))?)|(?:(?:^|\n+)([^\s].*)\n(-{3,}|={3,})(?:\n+|$))|(?:(?:^|\n+)(#{1,6})\s*(.+)(?:\n+|$))|(?:`([^`].*?)`)|(  \n\n*|\n{2,}|(?<=\W|^|$)(?<![_*])__|__(?=\W|^|$)(?![_*])|(?<=\W|^|$)(?<![_*])\*\*|\*\*(?=\W|^|$)(?![_*])|(?<=\W|^|$)(?<![_*])[_*]|[_*](?=\W|^|$)(?![_*])|~~)/gm,
 		context = [],
 		out = '',
 		links = prevLinks || {},
diff --git a/test/index.js b/test/index.js
index 5262b16..a929ad5 100644
--- a/test/index.js
+++ b/test/index.js
@@ -18,6 +18,13 @@ describe('snarkdown()', () => {
 		it('parses italics with _', () => {
 			expect(snarkdown('I _like_ tiny libraries')).to.equal('I <em>like</em> tiny libraries');
 		});
+
+		it('ignores words with special formatting', () => {
+			expect(snarkdown('I like tiny*libraries')).to.equal('I like tiny*libraries');
+			expect(snarkdown('I like tiny_libraries')).to.equal('I like tiny_libraries');
+			expect(snarkdown('I like tiny**libraries')).to.equal('I like tiny**libraries');
+			expect(snarkdown('I like tiny__libraries')).to.equal('I like tiny__libraries');
+		});
 	});
 
 	describe('titles', () => {