From c880af81202382bfe7a256f42c693b22cea47f55 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?R=C3=A9gis=20Hanol?= <regis@hanol.fr>
Date: Wed, 3 May 2017 18:04:31 +0200
Subject: [PATCH] FIX: properly trim whitespaces (including those pesky &nbsp;
 html entities)

---
 lib/html_to_markdown.rb                  |  8 ++++----
 spec/components/html_to_markdown_spec.rb | 14 ++++++++++++++
 2 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/lib/html_to_markdown.rb b/lib/html_to_markdown.rb
index 9e18269c664..60f88d9095f 100644
--- a/lib/html_to_markdown.rb
+++ b/lib/html_to_markdown.rb
@@ -15,10 +15,10 @@ class HtmlToMarkdown
   def remove_whitespaces!
     @doc.traverse do |node|
       if node.is_a? Nokogiri::XML::Text
-        node.content = node.content.lstrip if node.previous_element&.description&.block?
-        node.content = node.content.lstrip if node.previous_element.nil? && node.parent.description&.block?
-        node.content = node.content.rstrip if node.next_element&.description&.block?
-        node.content = node.content.rstrip if node.next_element.nil? && node.parent.description&.block?
+        node.content = node.content.gsub(/\A[[:space:]]+/, "") if node.previous_element&.description&.block?
+        node.content = node.content.gsub(/\A[[:space:]]+/, "") if node.previous_element.nil? && node.parent.description&.block?
+        node.content = node.content.gsub(/[[:space:]]+\z/, "") if node.next_element&.description&.block?
+        node.content = node.content.gsub(/[[:space:]]+\z/, "") if node.next_element.nil? && node.parent.description&.block?
         node.remove if node.content.empty?
       end
     end
diff --git a/spec/components/html_to_markdown_spec.rb b/spec/components/html_to_markdown_spec.rb
index 43651536e31..e5a9c5b8e2c 100644
--- a/spec/components/html_to_markdown_spec.rb
+++ b/spec/components/html_to_markdown_spec.rb
@@ -7,6 +7,20 @@ describe HtmlToMarkdown do
     HtmlToMarkdown.new(html).to_markdown
   end
 
+  it "remove whitespaces" do
+    expect(html_to_markdown(<<-HTML
+      <div dir="auto">Hello,
+        <div dir="auto"><br></div>
+        <div dir="auto">&nbsp; &nbsp; This is the 1st paragraph.&nbsp; &nbsp; </div>
+        <div dir="auto"><br></div>
+        <div dir="auto">
+          &nbsp; &nbsp; &nbsp; &nbsp; This is another paragraph
+        </div>
+      </div>
+    HTML
+    )).to eq("Hello,\n\nThis is the 1st paragraph.\n\nThis is another paragraph")
+  end
+
   it "converts <strong>" do
     expect(html_to_markdown("<strong>Strong</strong>")).to eq("**Strong**")
     expect(html_to_markdown("<strong>Str*ng</strong>")).to eq("__Str*ng__")