From d6615c87857eed1d486c0f90c1a9d909ff262d13 Mon Sep 17 00:00:00 2001
From: Andres Rey <andreskrey@gmail.com>
Date: Sat, 10 Mar 2018 18:43:31 +0000
Subject: Failsafe for weird titles

---
 src/Readability.php | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'src')

diff --git a/src/Readability.php b/src/Readability.php
index 9a29313..c17911c 100644
--- a/src/Readability.php
+++ b/src/Readability.php
@@ -468,6 +468,10 @@ class Readability
                 if (count(preg_split('/\s+/', $curTitle)) < 3) {
                     $curTitle = substr($originalTitle, strpos($originalTitle, ':') + 1);
                     $this->logger->info(sprintf('[Metadata] Title too short, using the first part of the title instead: \'%s\'', $curTitle));
+                } else if (count(preg_split('/\s+/', substr($curTitle, 0, strpos($curTitle, ':')))) > 5) {
+                    // But if we have too many words before the colon there's something weird
+                    // with the titles and the H tags so let's just use the original title instead
+                    $curTitle = $originalTitle;
                 }
             }
         } elseif (mb_strlen($curTitle) > 150 || mb_strlen($curTitle) < 15) {
@@ -1485,7 +1489,7 @@ class Readability
      *
      * Readability.js has a special filter to avoid cleaning the classes that the algorithm adds. We don't add classes
      * here so no need to filter those.
-     * 
+     *
      * @param DOMDocument|DOMNode $node
      *
      * @return void
-- 
cgit v1.2.3