From 6a8fcf6f33ce32a7c869580b1eb9b76ce2fc2e53 Mon Sep 17 00:00:00 2001
From: William Kennedy <william.kennedy@hey.com>
Date: Wed, 3 Nov 2021 04:27:12 +0000
Subject: [PATCH] HTML tag and attribute matcher (#15091)

* HTML tag and attribute matcher

This regex was designed for the following matches. It should ignore
plain text

<tag>
</tag>
<hr/>
<div class="signout_confirm-wrapper">
" target="_blank" rel="noopener me" class="profile-header__meta__item p-1">
class="crayons-layout crayons-layout--limited-l crayons-layout--2-cols crayons-layout--2-cols--1-2 pt-4 m:pt-0"
href="javascript:void(0);"
id="asdf"
class="sas"
data-profile-user-id="asdf">sads</s>
data-tag=""

* added rails sanitizer

* removed swap file

* Update bin/untranslated_erb

Co-authored-by: Michael Kohl <me@citizen428.net>

* revert gitignore

Co-authored-by: Michael Kohl <me@citizen428.net>
---
 bin/untranslated_erb | 28 ++++++++++++++++------------
 1 file changed, 16 insertions(+), 12 deletions(-)

diff --git a/bin/untranslated_erb b/bin/untranslated_erb
index 850586925..d341443f9 100755
--- a/bin/untranslated_erb
+++ b/bin/untranslated_erb
@@ -1,7 +1,9 @@
 #!/usr/bin/env ruby
+require 'rails-html-sanitizer'
+
 class I18nExtractor
   ERB_TAG = /<%(.*?)%>/
-  HTML_TAG = /<(.*?)>/
+  HTML_TAG = /<[^>]*>|<\/[^>]*>|[^>]*\/>|\".+">|">|<\w+(.+|)|.+="(.+)|"/
   SEPERATOR = '_@@@_'
   SKIP_TAGS = [[/<script/i,/<\/script>/i],[/<%/,/%>/],[/<style/i,/\/style>/i]]
 
@@ -12,23 +14,25 @@ class I18nExtractor
   end
 
   def extract
-    File.open(@filename).each_with_index do |line,i|
+    sanitizer = Rails::Html::FullSanitizer.new
+    i = 0
+    File.foreach(@filename) do |line|
+      i += 1
       next if in_script_block?(line)
-      text = line.gsub(ERB_TAG, SEPERATOR).gsub(HTML_TAG,SEPERATOR).strip
-      arr = text.split SEPERATOR
-      arr.each do |e|
-        if e.strip.size > 1
-          unless @files_with_results.include?(@filename)
-            @files_with_results << @filename
-            printf "\n\n\e[4m#{@filename}\e[00m\n\n"
-          end
-          printf("%3s:%s\n",i+1,e.strip)
+      striped_line = sanitizer.sanitize(line).chomp.strip.gsub(HTML_TAG, '')
+      next if striped_line.empty?
+      if striped_line.length > 1
+        unless @files_with_results.include?(@filename)
+          @files_with_results << @filename
+          printf "\n\n\e[4m#{@filename}\e[00m\n"
         end
+        printf("%3s:%s\n",i+1,striped_line)
       end
     end
   end
 
-private
+  private
+
   def in_script_block?(s)
     return true if s.nil? || s.strip.size == 0 
     jump_in_tag = SKIP_TAGS.find{ |start_tag,end_tag| s =~ start_tag}