Links are masked only once per inline string

calculuschild · calculuschild · commit 4db32dc18020 · 2020-06-30T17:49:11.000-04:00
diff --git a/src/Lexer.js b/src/Lexer.js
@@ -322,6 +322,20 @@ module.exports = class Lexer {
   inlineTokens(src, tokens = [], inLink = false, inRawBlock = false, prevChar = '') {
     let token;
 
+    // String with links masked to avoid interference with em and strong
+    let maskedSrc = src;
+    if (this.tokens.links) {
+      const links = Object.keys(this.tokens.links);
+      if (links.length > 0) {
+        let match;
+        while ((match = this.tokenizer.rules.inline.reflinkSearch.exec(maskedSrc)) != null) {
+          if (links.includes(match[0].slice(match[0].lastIndexOf('[') + 1, -1))) {
+            maskedSrc = maskedSrc.slice(0, match.index) + '[' + 'a'.repeat(match[0].length - 2) + ']' + maskedSrc.slice(this.tokenizer.rules.inline.reflinkSearch.lastIndex);
+          }
+        }
+      }
+    }
+
     while (src) {
       // escape
       if (token = this.tokenizer.escape(src)) {
@@ -360,15 +374,15 @@ module.exports = class Lexer {
       }
 
       // strong
-      if (token = this.tokenizer.strong(src, prevChar, this.tokens.links)) {
+      if (token = this.tokenizer.strong(src, maskedSrc, prevChar)) {
         src = src.substring(token.raw.length);
         token.tokens = this.inlineTokens(token.text, [], inLink, inRawBlock);
         tokens.push(token);
         continue;
       }
 
       // em
-      if (token = this.tokenizer.em(src, prevChar, this.tokens.links)) {
+      if (token = this.tokenizer.em(src, maskedSrc, prevChar)) {
         src = src.substring(token.raw.length);
         token.tokens = this.inlineTokens(token.text, [], inLink, inRawBlock);
         tokens.push(token);
diff --git a/src/Tokenizer.js b/src/Tokenizer.js
@@ -58,21 +58,6 @@ function indentCodeCompensation(raw, text) {
     .join('\n');
 }
 
-function maskReflinks(text, links) {
-  if (links) {
-    links = Object.keys(links).filter(l => l.match(/[*_]/));
-    if (links.length > 0) {
-      let match;
-      while ((match = this.rules.inline.reflinkSearch.exec(text)) != null) {
-        if (links.includes(match[0].slice(match[0].lastIndexOf('[') + 1, -1))) {
-          text = text.slice(0, match.index) + '[' + 'a'.repeat(match[0].length - 2) + ']' + text.slice(this.rules.inline.reflinkSearch.lastIndex);
-        }
-      }
-    }
-  }
-  return text;
-}
-
 /**
  * Tokenizer
  */
@@ -504,13 +489,12 @@ module.exports = class Tokenizer {
     }
   }
 
-  strong(src, prevChar = '', links) {
+  strong(src, maskedSrc, prevChar = '') {
     let cap = this.rules.inline.preStrong.exec(src);
 
     if (cap) {
-      const text = maskReflinks(src, links);
-
-      cap = this.rules.inline.strong.exec(text);
+      maskedSrc = maskedSrc.slice(-1*src.length);
+      cap = this.rules.inline.strong.exec(maskedSrc);
 
       if (cap) {
         if (!cap[1] || (cap[1] && (prevChar === '' || this.rules.inline.punctuation.exec(prevChar)))) {
@@ -524,13 +508,12 @@ module.exports = class Tokenizer {
     }
   }
 
-  em(src, prevChar = '', links) {
+  em(src, maskedSrc, prevChar = '') {
     let cap = this.rules.inline.preEm.exec(src);
 
     if (cap) {
-      const text = maskReflinks(src, links);
-
-      cap = this.rules.inline.em.exec(text);
+      maskedSrc = maskedSrc.slice(-1*src.length);
+      cap = this.rules.inline.em.exec(maskedSrc);
 
       if (cap) {
         if (!cap[1] || (cap[1] && (prevChar === '' || this.rules.inline.punctuation.exec(prevChar)))) {
diff --git a/test/specs/new/em_and_reflinks.html b/test/specs/new/em_and_reflinks.html
@@ -2,3 +2,4 @@
 <p><em>Hello [not</em>reflink] guys*!</p>
 <p><em>Hello [not</em>a<em>reflink] guys</em>!</p>
 <p><em>Hello<a href="theaddress">reflink*bottom</a>guys</em>!</p>
+<p><em>Hello<a href="theaddress">reflinknoem</a>guys</em>!</p>
diff --git a/test/specs/new/em_and_reflinks.md b/test/specs/new/em_and_reflinks.md
@@ -8,4 +8,8 @@
 
 *Hello [reflink*bottom] guys*!
 
+*Hello [reflinknoem] guys*!
+
 [reflink*bottom]: theaddress
+
+[reflinknoem]: theaddress
