From 75919b8ce7598aafd26867e1a25b3e90f7b3b01f Mon Sep 17 00:00:00 2001 From: ProgramFOX Date: Thu, 2 Apr 2015 09:31:41 +0200 Subject: [PATCH] Detect nested quote blocks --- findspam.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/findspam.py b/findspam.py index 56515ec240..f519163ac7 100644 --- a/findspam.py +++ b/findspam.py @@ -60,6 +60,8 @@ class FindSpam: 'sites': [], 'reason': "Bad keyword in {}", 'title': True, 'body': True, 'username': False, 'stripcodeblocks': False, 'body_summary': True}, {'regex': u"(?i)(>>>>|===>|==>>>)(?s).*http", 'all': True, 'sites': [], 'reason': "Bad keyword in {}", 'title': True, 'body': True, 'username': True, 'stripcodeblocks': True, 'body_summary': False}, + {'regex': u"(>\\s+){2,}", 'all': True, + 'sites': [], 'reason': "Nested quote blocks in {}", 'title': False, 'body': True, 'username': False, 'stripcodeblocks': True, 'body_summary': False}, {'regex': u"(?i)\\b(weight (body ?builder|loo?s[es]|reduction)|muscles?|anti aging|loo?s[es] weight|wrinkles?)\\b", 'all': True, 'sites': ["fitness.stackexchange.com", "biology.stackexchange.com"], 'reason': "Bad keyword in {}", 'title': True, 'body': False, 'username': True, 'stripcodeblocks': False, 'body_summary': False}, {'regex': u"(?i)^(?:(?=.*?\\b(?:online|hd)\\b)(?=.*?(?:free|full|unlimited)).*?movies?\\b|(?=.*?\\b(?:acai|kisn)\\b)(?=.*?care).*products?\\b|(?=.*?packer).*mover)", 'all': True,