From 656c3e4aba6a00eb3664ff7e829878ed9222c339 Mon Sep 17 00:00:00 2001
From: Tony Brix <tony@brix.ninja>
Date: Thu, 10 Dec 2020 10:27:58 -0600
Subject: [PATCH] fix: fix link with angle brackets around href (#1851)

---
 src/Tokenizer.js                           | 49 +++++++++++++++-------
 src/rules.js                               |  2 +-
 test/specs/commonmark/commonmark.0.29.json | 12 ++----
 test/specs/gfm/commonmark.0.29.json        | 12 ++----
 test/specs/new/link_lt.html                |  4 +-
 test/specs/new/link_lt.md                  |  5 +++
 6 files changed, 52 insertions(+), 32 deletions(-)

diff --git a/src/Tokenizer.js b/src/Tokenizer.js
index 20f122332f..972c5b9ea3 100644
--- a/src/Tokenizer.js
+++ b/src/Tokenizer.js
@@ -457,34 +457,56 @@ module.exports = class Tokenizer {
   link(src) {
     const cap = this.rules.inline.link.exec(src);
     if (cap) {
-      const lastParenIndex = findClosingBracket(cap[2], '()');
-      if (lastParenIndex > -1) {
-        const start = cap[0].indexOf('!') === 0 ? 5 : 4;
-        const linkLen = start + cap[1].length + lastParenIndex;
-        cap[2] = cap[2].substring(0, lastParenIndex);
-        cap[0] = cap[0].substring(0, linkLen).trim();
-        cap[3] = '';
+      const trimmedUrl = cap[2].trim();
+      if (!this.options.pedantic && trimmedUrl.startsWith('<')) {
+        // commonmark requires matching angle brackets
+        if (!trimmedUrl.endsWith('>')) {
+          return;
+        }
+
+        // ending angle bracket cannot be escaped
+        const rtrimSlash = rtrim(trimmedUrl.slice(0, -1), '\\');
+        if ((trimmedUrl.length - rtrimSlash.length) % 2 === 0) {
+          return;
+        }
+      } else {
+        // find closing parenthesis
+        const lastParenIndex = findClosingBracket(cap[2], '()');
+        if (lastParenIndex > -1) {
+          const start = cap[0].indexOf('!') === 0 ? 5 : 4;
+          const linkLen = start + cap[1].length + lastParenIndex;
+          cap[2] = cap[2].substring(0, lastParenIndex);
+          cap[0] = cap[0].substring(0, linkLen).trim();
+          cap[3] = '';
+        }
       }
       let href = cap[2];
       let title = '';
       if (this.options.pedantic) {
+        // split pedantic href and title
         const link = /^([^'"]*[^\s])\s+(['"])(.*)\2/.exec(href);
 
         if (link) {
           href = link[1];
           title = link[3];
-        } else {
-          title = '';
         }
       } else {
         title = cap[3] ? cap[3].slice(1, -1) : '';
       }
-      href = href.trim().replace(/^<([\s\S]*)>$/, '$1');
-      const token = outputLink(cap, {
+
+      href = href.trim();
+      if (href.startsWith('<')) {
+        if (this.options.pedantic && !trimmedUrl.endsWith('>')) {
+          // pedantic allows starting angle bracket without ending angle bracket
+          href = href.slice(1);
+        } else {
+          href = href.slice(1, -1);
+        }
+      }
+      return outputLink(cap, {
         href: href ? href.replace(this.rules.inline._escapes, '$1') : href,
         title: title ? title.replace(this.rules.inline._escapes, '$1') : title
       }, cap[0]);
-      return token;
     }
   }
 
@@ -502,8 +524,7 @@ module.exports = class Tokenizer {
           text
         };
       }
-      const token = outputLink(cap, link, cap[0]);
-      return token;
+      return outputLink(cap, link, cap[0]);
     }
   }
 
diff --git a/src/rules.js b/src/rules.js
index 13356df367..df14188275 100644
--- a/src/rules.js
+++ b/src/rules.js
@@ -260,7 +260,7 @@ inline.tag = edit(inline.tag)
   .getRegex();
 
 inline._label = /(?:\[(?:\\.|[^\[\]\\])*\]|\\.|`[^`]*`|[^\[\]\\`])*?/;
-inline._href = /<(?:\\[<>]?|[^\s<>\\])*>|[^\s\x00-\x1f]*/;
+inline._href = /<(?:\\.|[^\n<>\\])+>|[^\s\x00-\x1f]*/;
 inline._title = /"(?:\\"?|[^"\\])*"|'(?:\\'?|[^'\\])*'|\((?:\\\)?|[^)\\])*\)/;
 
 inline.link = edit(inline.link)
diff --git a/test/specs/commonmark/commonmark.0.29.json b/test/specs/commonmark/commonmark.0.29.json
index 1440e2f2c1..7d9e16f58a 100644
--- a/test/specs/commonmark/commonmark.0.29.json
+++ b/test/specs/commonmark/commonmark.0.29.json
@@ -3939,8 +3939,7 @@
     "example": 486,
     "start_line": 7543,
     "end_line": 7547,
-    "section": "Links",
-    "shouldFail": true
+    "section": "Links"
   },
   {
     "markdown": "[link](foo\nbar)\n",
@@ -3964,8 +3963,7 @@
     "example": 489,
     "start_line": 7571,
     "end_line": 7575,
-    "section": "Links",
-    "shouldFail": true
+    "section": "Links"
   },
   {
     "markdown": "[link](<foo\\>)\n",
@@ -3973,8 +3971,7 @@
     "example": 490,
     "start_line": 7579,
     "end_line": 7583,
-    "section": "Links",
-    "shouldFail": true
+    "section": "Links"
   },
   {
     "markdown": "[a](<b)c\n[a](<b)c>\n[a](<b>c)\n",
@@ -3982,8 +3979,7 @@
     "example": 491,
     "start_line": 7588,
     "end_line": 7596,
-    "section": "Links",
-    "shouldFail": true
+    "section": "Links"
   },
   {
     "markdown": "[link](\\(foo\\))\n",
diff --git a/test/specs/gfm/commonmark.0.29.json b/test/specs/gfm/commonmark.0.29.json
index 7732f6a9da..0526dbf1d3 100644
--- a/test/specs/gfm/commonmark.0.29.json
+++ b/test/specs/gfm/commonmark.0.29.json
@@ -3939,8 +3939,7 @@
     "example": 486,
     "start_line": 7543,
     "end_line": 7547,
-    "section": "Links",
-    "shouldFail": true
+    "section": "Links"
   },
   {
     "markdown": "[link](foo\nbar)\n",
@@ -3964,8 +3963,7 @@
     "example": 489,
     "start_line": 7571,
     "end_line": 7575,
-    "section": "Links",
-    "shouldFail": true
+    "section": "Links"
   },
   {
     "markdown": "[link](<foo\\>)\n",
@@ -3973,8 +3971,7 @@
     "example": 490,
     "start_line": 7579,
     "end_line": 7583,
-    "section": "Links",
-    "shouldFail": true
+    "section": "Links"
   },
   {
     "markdown": "[a](<b)c\n[a](<b)c>\n[a](<b>c)\n",
@@ -3982,8 +3979,7 @@
     "example": 491,
     "start_line": 7588,
     "end_line": 7596,
-    "section": "Links",
-    "shouldFail": true
+    "section": "Links"
   },
   {
     "markdown": "[link](\\(foo\\))\n",
diff --git a/test/specs/new/link_lt.html b/test/specs/new/link_lt.html
index ea48caa950..bb32e53966 100644
--- a/test/specs/new/link_lt.html
+++ b/test/specs/new/link_lt.html
@@ -1 +1,3 @@
-<p><a href="%3Ctest">URL</a></p>
+<p><a href="test">URL</a></p>
+
+<p><a href="test%5C">URL</a></p>
diff --git a/test/specs/new/link_lt.md b/test/specs/new/link_lt.md
index f4f9adddc9..bfbe71c1b4 100644
--- a/test/specs/new/link_lt.md
+++ b/test/specs/new/link_lt.md
@@ -1 +1,6 @@
+---
+pedantic: true
+---
 [URL](<test)
+
+[URL](<test\>)