diff options
-rw-r--r-- | src/Readability.php | 2 | ||||
-rw-r--r-- | test/test-pages/missing-paragraphs/expected-metadata.json | 2 |
2 files changed, 2 insertions, 2 deletions
diff --git a/src/Readability.php b/src/Readability.php index 25b79a2..0d9498e 100644 --- a/src/Readability.php +++ b/src/Readability.php @@ -569,7 +569,7 @@ class Readability } } - $curTitle = trim($curTitle); + $curTitle = preg_replace(NodeUtility::$regexps['normalize'], ' ', trim($curTitle)); /* * If we now have 4 words or fewer as our title, and either no diff --git a/test/test-pages/missing-paragraphs/expected-metadata.json b/test/test-pages/missing-paragraphs/expected-metadata.json index b0ef946..cf0a02b 100644 --- a/test/test-pages/missing-paragraphs/expected-metadata.json +++ b/test/test-pages/missing-paragraphs/expected-metadata.json @@ -3,6 +3,6 @@ "Direction": null, "Excerpt": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy\n eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam\n voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet\n clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit\n amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam\n nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat,\n sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum.\n Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor\n sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed\n diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat,\n sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum.\n Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor\n sit amet.", "Image": null, - "Title": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy\n eirmod tempor invidunt", + "Title": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "SiteName": null } |