diff --git a/lib/core/common.py b/lib/core/common.py index b9564207f..0c3e05717 100644 --- a/lib/core/common.py +++ b/lib/core/common.py @@ -1128,7 +1128,9 @@ def preparePageForLineComparison(page): def getFilteredPageContent(page): retVal = page if isinstance(page, basestring): - retVal = re.sub(r"(?s)||<[^>]+>|\t|\n|\r", "", page) + retVal = re.sub(r"(?s)||<[^>]+>|\t|\n|\r", " ", page) + while retVal.find(" ") != -1: + retVal = retVal.replace(" ", " ") return retVal def getPageTextWordsSet(page):