From e38014772b50fc387300b13a31800b92afc7ea6e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?R=C3=A9gis=20Hanol?= <regis@hanol.fr>
Date: Wed, 3 May 2017 19:40:34 +0200
Subject: [PATCH] FIX: skip hidden <img> (no tracking for you)

---
 lib/html_to_markdown.rb                  | 11 +++++++++--
 spec/components/html_to_markdown_spec.rb |  7 +++++++
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/lib/html_to_markdown.rb b/lib/html_to_markdown.rb
index 40997fa5c94..30c394648d6 100644
--- a/lib/html_to_markdown.rb
+++ b/lib/html_to_markdown.rb
@@ -37,7 +37,7 @@ class HtmlToMarkdown
   end
 
   def visit(node)
-    return if node["style"] && node["style"][/display[[:space:]]*:[[:space:]]*none/]
+    return if node["style"] && node["style"][/display\s*:\s*none/]
 
     if node.description&.block? && node.parent&.description&.block? && @stack[-1].markdown.size > 0
       block = @stack[-1].dup
@@ -136,7 +136,7 @@ class HtmlToMarkdown
   end
 
   def visit_img(node)
-    if is_valid_url?(node["src"])
+    if is_valid_url?(node["src"]) && is_visible_img?(node)
       if @opts[:keep_img_tags]
         @stack[-1].markdown << node.to_html
       else
@@ -210,4 +210,11 @@ class HtmlToMarkdown
     url.present? && (url.start_with?("http") || url.start_with?("www."))
   end
 
+  def is_visible_img?(img)
+    return false if img["width"].present? && img["width"].to_i == 0
+    return false if img["height"].present? && img["height"].to_i == 0
+    return false if img["style"].present? && img["style"][/(width|height)\s*:\s*0/]
+    true
+  end
+
 end
diff --git a/spec/components/html_to_markdown_spec.rb b/spec/components/html_to_markdown_spec.rb
index 52c0eb670a1..091bc79ee80 100644
--- a/spec/components/html_to_markdown_spec.rb
+++ b/spec/components/html_to_markdown_spec.rb
@@ -71,6 +71,13 @@ describe HtmlToMarkdown do
     expect(html_to_markdown(%Q{<img src="foo.bar">})).to eq("")
   end
 
+  it "skips hidden <img>" do
+    expect(html_to_markdown(%Q{<img src="https://www.discourse.org/logo.svg" width=0>})).to eq("")
+    expect(html_to_markdown(%Q{<img src="https://www.discourse.org/logo.svg" height="0">})).to eq("")
+    expect(html_to_markdown(%Q{<img src="https://www.discourse.org/logo.svg" style="width: 0">})).to eq("")
+    expect(html_to_markdown(%Q{<img src="https://www.discourse.org/logo.svg" style="height:0px">})).to eq("")
+  end
+
   (1..6).each do |n|
     it "converts <h#{n}>" do
       expect(html_to_markdown("<h#{n}>Header #{n}</h#{n}>")).to eq("#" * n + " Header #{n}")