From 8824fa7bc42c89abb17cbed47c976cc3fbfb5a35 Mon Sep 17 00:00:00 2001
From: Jason Crain <jason@inspiresomeone.us>
Date: Sun, 16 Jul 2017 12:07:54 -0500
Subject: [PATCH] pdftohtml: skip control characters

W3C disallows them and they cause a warning in PHP.

https://bugs.freedesktop.org/show_bug.cgi?id=101770
---
 utils/HtmlFonts.cc | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/utils/HtmlFonts.cc b/utils/HtmlFonts.cc
index 49376d65..c9590e18 100644
--- a/utils/HtmlFonts.cc
+++ b/utils/HtmlFonts.cc
@@ -252,6 +252,11 @@ GooString* HtmlFont::HtmlFilter(Unicode* u, int uLen) {
   }
 
   for (int i = 0; i < uLen; ++i) {
+    // skip control characters.  W3C disallows them and they cause a warning
+    // with PHP.
+    if (u[i] <= 31)
+      continue;
+
     switch (u[i])
       { 
 	case '"': tmp->append("&#34;");  break;
-- 
2.13.2