From f00a95c6a3d7dbb28dc1baf9ec85cdaa75595074 Mon Sep 17 00:00:00 2001
From: Konstantin Nazarov <mail@knazarov.com>
Date: Sun, 1 Aug 2021 22:40:37 +0100
Subject: [PATCH] Add support for better bold/italic formatting

---
 README.md    |  2 +-
 markdown.awk | 53 +++++++++++++++++++++++++++++-----------------------
 test.sh      | 21 +++++++++++++++++++++
 3 files changed, 52 insertions(+), 24 deletions(-)

diff --git a/README.md b/README.md
index 1bfc53a..2fd68af 100644
--- a/README.md
+++ b/README.md
@@ -21,7 +21,7 @@ Here's a list of supported markdown primitives
 
 - Headers
 - Paragraphs
-- Text formatting: bold
+- Text formatting: bold/italic
 - Code blocks
 - Blockquotes
 - Lists, both bulleted and numbered
diff --git a/markdown.awk b/markdown.awk
index 471006c..99b6517 100644
--- a/markdown.awk
+++ b/markdown.awk
@@ -7,7 +7,7 @@ function parse_header(str,    hnum, content) {
 	if (substr(str, 1, 1) == "#") {
 		gsub(/ *#* *$/, "", str);
 		match(str, /#+/);
-    	hnum = RLENGTH;
+		hnum = RLENGTH;
 
 		gsub(/^#+ */, "", str);
 		content = parse_line(str);
@@ -240,20 +240,34 @@ function escape_text(str) {
 	return str;
 }
 
-function extract_emphasis(str, i,    sstr, arr, num, c) {
-    sstr=substr(str, i, length(str) - i + 1);
-	c = ""
+function extract_emphasis(str, i,    sstr) {
+	sstr=substr(str, i, length(str) - i + 1);
 
-	if (match(sstr, /^\*{1,3}[^\*]/)) {
-		c = "*";
-		num = RLENGTH;
+	if (match(sstr, /^\*[^\*]+\*/) ||
+	    match(sstr, /^\*\*[^\*]+\*\*/) ||
+	    match(sstr, /^\*\*\*[^\*]+\*\*\*/) ||
+	    match(sstr, /^_[^_]+_/) ||
+	    match(sstr, /^__[^_]+__/) ||
+	    match(sstr, /^___[^_]+___/))
+		return substr(str, i, RLENGTH);
+
+	return "";
+}
+
+function parse_emphasis(str, i) {
+	match(str, /^[\*_]{1,3}/);
+	num = RLENGTH;
+
+	if (num == 1) {
+		return "<em>" parse_line(substr(str, 2, length(str) - 2)) "</em>";
 	}
-
-	if (match(sstr, /^_{1,3}[^_]/)) {
-		c = "_";
-		num = RLENGTH;
+	if (num == 2) {
+		return "<strong>" parse_line(substr(str, 3, length(str) - 4)) "</strong>";
 	}
-
+	if (num == 3) {
+		return "<strong><em>" parse_line(substr(str, 4, length(str) - 6)) "</em></strong>";
+	}
+	return "";
 }
 
 function parse_line(str,    result, end, i, c) {
@@ -262,17 +276,10 @@ function parse_line(str,    result, end, i, c) {
 	for (i=1; i<=length(str); i++) {
 		c = substr(str, i, 1);
 
-		if (c == "*" && is_token(str, i, "**")){
-			end = find(str, "**", i+2);
-
-			if (end != 0) {
-				result = result "<strong>" parse_line(substr(str, i+2, end - i - 2)) "</strong>";	
-				i = end+1;
-			}
-			else {
-				result = result "**";
-				i++;
-			}
+		if ((c == "*" || c == "_") && extract_emphasis(str, i) != ""){
+			emphasis = extract_emphasis(str, i);
+			result = result parse_emphasis(emphasis)
+			i = i + length(emphasis) - 1;
 		}
 		else if (c == "`" && is_token(str, i, "```")) {
 			end = find(str, "```", i+3);
diff --git a/test.sh b/test.sh
index 25012bb..9b527f7 100755
--- a/test.sh
+++ b/test.sh
@@ -103,10 +103,31 @@ underlined header 2
 <h2>underlined header 2</h2>
 EOF
 
+check <<-EOF
+*italic*
+
+_italic_
+---
+<p><em>italic</em></p>
+<p><em>italic</em></p>
+EOF
+
 check <<-EOF
 **bold**
+
+__bold__
 ---
 <p><strong>bold</strong></p>
+<p><strong>bold</strong></p>
+EOF
+
+check <<-EOF
+***bold italic***
+
+___bold italic___
+---
+<p><strong><em>bold italic</em></strong></p>
+<p><strong><em>bold italic</em></strong></p>
 EOF
 
 check <<-EOF