From b73068c82d54db6ff54ad448729e805b3bb94c3a Mon Sep 17 00:00:00 2001
From: Kevin Dew <kevindew@me.com>
Date: Wed, 3 Apr 2019 20:17:20 +0100
Subject: [PATCH] Consistently handle inline elements with spaces

This resolves some odd situations that can occur when there are inline
elements that contain spaces in sentences.

The first situation is when there is an element that includes a space
between words, for example 'Test<span> </span>content'. This would
previously have produced a two space result: 'Test  content' because
this element would have matched both leading and trailing whitespace
tests.

The second situation is when there is an element that includes a space
outside the tests, which is the case of a non-breaking space character
(unicode U+00A0), then the space is removed. An example of this is
'Test<span>&nbsp;</span>content' which would result in 'Testcontent' as
this wouldn't match the tests for leading/trailing whitespace.

This resolves these problems by changing the whitespace tests to use \s
rather than a subset of space characters (which is consistent with the
blank test [1]) and only allows a leading space if the test for both
leading and trailing whitespace passes on a blank element.

[1]: https://github.com/domchristie/turndown/blob/80297cebeae4b35c8d299b1741b383c74eddc7c1/src/node.js#L14
---
 src/node.js     |  8 +++++---
 test/index.html | 14 ++++++++++++++
 2 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/src/node.js b/src/node.js
index 8ca8fca3..675e9799 100644
--- a/src/node.js
+++ b/src/node.js
@@ -22,13 +22,15 @@ function flankingWhitespace (node) {
   var trailing = ''
 
   if (!node.isBlock) {
-    var hasLeading = /^[ \r\n\t]/.test(node.textContent)
-    var hasTrailing = /[ \r\n\t]$/.test(node.textContent)
+    var hasLeading = /^\s/.test(node.textContent)
+    var hasTrailing = /\s$/.test(node.textContent)
+    var blankWithSpaces = node.isBlank && hasLeading && hasTrailing
 
     if (hasLeading && !isFlankedByWhitespace('left', node)) {
       leading = ' '
     }
-    if (hasTrailing && !isFlankedByWhitespace('right', node)) {
+
+    if (!blankWithSpaces && hasTrailing && !isFlankedByWhitespace('right', node)) {
       trailing = ' '
     }
   }
diff --git a/test/index.html b/test/index.html
index b52c5928..b4d6215e 100644
--- a/test/index.html
+++ b/test/index.html
@@ -888,6 +888,20 @@ <h2>This is a header.</h2>
   <pre class="expected">![](http://example.com/logo.png)</pre>
 </div>
 
+<div class="case" data-name="text separated by a space in an element">
+  <div class="input">
+    <p>Foo<span> </span>Bar</p>
+  </div>
+  <pre class="expected">Foo Bar</pre>
+</div>
+
+<div class="case" data-name="text separated by a non-breaking space in an element">
+  <div class="input">
+    <p>Foo<span>&nbsp;</span>Bar</p>
+  </div>
+  <pre class="expected">Foo Bar</pre>
+</div>
+
 <!-- /TEST CASES -->
 
 <script src="turndown-test.browser.js"></script>