Em Strong fixes

src/Tokenizer.js

@@ -550,7 +550,8 @@ module.exports = class Tokenizer {
     let match = this.rules.inline.emStrong.lDelim.exec(src);
     if (!match) return;
 
-    if (match[3] && prevChar.match(/[\p{L}\p{N}]/u)) return; // _ can't be between two alphanumerics. \p{L}\p{N} includes non-english alphabet/numbers as well
+    // _ can't be between two alphanumerics. \p{L}\p{N} includes non-english alphabet/numbers as well
+    if (match[3] && prevChar.match(/[\p{L}\p{N}]/u)) return;
 
     const nextChar = match[1] || match[2] || '';
 
@@ -561,12 +562,13 @@ module.exports = class Tokenizer {
       const endReg = match[0][0] === '*' ? this.rules.inline.emStrong.rDelimAst : this.rules.inline.emStrong.rDelimUnd;
       endReg.lastIndex = 0;
 
-      maskedSrc = maskedSrc.slice(-1 * src.length + lLength); // Bump maskedSrc to same section of string as src (move to lexer?)
+      // Clip maskedSrc to same section of string as src (move to lexer?)
+      maskedSrc = maskedSrc.slice(-1 * src.length + lLength);
 
       while ((match = endReg.exec(maskedSrc)) != null) {
         rDelim = match[1] || match[2] || match[3] || match[4] || match[5] || match[6];
 
-        if (!rDelim) continue; // matched the first alternative in rules.js (skip the * in __abc*abc__)
+        if (!rDelim) continue; // skip single * in __abc*abc__
 
         rLength = rDelim.length;
 
@@ -584,25 +586,24 @@ module.exports = class Tokenizer {
 
         if (delimTotal > 0) continue; // Haven't found enough closing delimiters
 
-        // If this is the last rDelimiter, remove extra characters. *a*** -> *a*
-        if (delimTotal + midDelimTotal - rLength <= 0 && !maskedSrc.slice(endReg.lastIndex).match(endReg)) {
-          rLength = Math.min(rLength, rLength + delimTotal + midDelimTotal);
-        }
+        // Remove extra characters. *a*** -> *a*
+        rLength = Math.min(rLength, rLength + delimTotal + midDelimTotal);
 
+        // Create `em` if smallest delimiter has odd char count. *a***
         if (Math.min(lLength, rLength) % 2) {
           return {
             type: 'em',
             raw: src.slice(0, lLength + match.index + rLength + 1),
             text: src.slice(1, lLength + match.index + rLength)
           };
         }
-        if (Math.min(lLength, rLength) % 2 === 0) {
-          return {
-            type: 'strong',
-            raw: src.slice(0, lLength + match.index + rLength + 1),
-            text: src.slice(2, lLength + match.index + rLength - 1)
-          };
-        }
+
+        // Create 'strong' if smallest delimiter has even char count. **a***
+        return {
+          type: 'strong',
+          raw: src.slice(0, lLength + match.index + rLength + 1),
+          text: src.slice(2, lLength + match.index + rLength - 1)
+        };
       }
     }
   }

src/rules.js

@@ -176,9 +176,9 @@ const inline = {
   emStrong: {
     lDelim: /^(?:\*+(?:([punct_])|[^\s*]))|^_+(?:([punct*])|([^\s_]))/,
     //        (1) and (2) can only be a Right Delimiter. (3) and (4) can only be Left.  (5) and (6) can be either Left or Right.
-    //        () Skip other delimiter (1) #***                (2) a***#, a***                   (3) #***a, ***a                 (4) ***#              (5) #***#                 (6) a***a
-    rDelimAst: /\_\_[^_]*?\*[^_]*?\_\_|[punct_](\*+)(?=[\s]|$)|[^punct*_\s](\*+)(?=[punct_\s]|$)|[punct_\s](\*+)(?=[^punct*_\s])|[\s](\*+)(?=[punct_])|[punct_](\*+)(?=[punct_])|[^punct*_\s](\*+)(?=[^punct*_\s])/,
-    rDelimUnd: /\*\*[^*]*?\_[^*]*?\*\*|[punct*](\_+)(?=[\s]|$)|[^punct*_\s](\_+)(?=[punct*\s]|$)|[punct*\s](\_+)(?=[^punct*_\s])|[\s](\_+)(?=[punct*])|[punct*](\_+)(?=[punct*])/ // ^- Not allowed for _
+    //        () Skip other delimiter (1) #***                   (2) a***#, a***                   (3) #***a, ***a                 (4) ***#              (5) #***#                 (6) a***a
+    rDelimAst: /\_\_[^_*]*?\*[^_*]*?\_\_|[punct_](\*+)(?=[\s]|$)|[^punct*_\s](\*+)(?=[punct_\s]|$)|[punct_\s](\*+)(?=[^punct*_\s])|[\s](\*+)(?=[punct_])|[punct_](\*+)(?=[punct_])|[^punct*_\s](\*+)(?=[^punct*_\s])/,
+    rDelimUnd: /\*\*[^_*]*?\_[^_*]*?\*\*|[punct*](\_+)(?=[\s]|$)|[^punct*_\s](\_+)(?=[punct*\s]|$)|[punct*\s](\_+)(?=[^punct*_\s])|[\s](\_+)(?=[punct*])|[punct*](\_+)(?=[punct*])/ // ^- Not allowed for _
   },
   code: /^(`+)([^`]|[^`][\s\S]*?[^`])\1(?!`)/,
   br: /^( {2,}|\\)\n(?!\s*$)/,

test/specs/new/em_strong_complex_nesting.html

@@ -0,0 +1 @@
+<p><strong>E<em>mp</em><em><strong>ha</strong></em><em>si</em>s</strong></p>

test/specs/new/em_strong_complex_nesting.md

@@ -0,0 +1 @@
+**E*mp****ha****si*s**

test/specs/new/em_strong_multiline.html

@@ -0,0 +1,3 @@
+<p><em>italic <strong>bold</strong> italic</em>
+<em>italic <strong>bold</strong> italic</em>
+<em>italic <strong>bold</strong> italic</em></p>

test/specs/new/em_strong_multiline.md

@@ -0,0 +1,3 @@
+_italic **bold** italic_
+_italic **bold** italic_
+_italic **bold** italic_