From d7a07d1d9904b84059b61d781c79c1978a9d6fdc Mon Sep 17 00:00:00 2001 From: JustAnotherArchivist Date: Mon, 24 Feb 2020 01:18:18 +0000 Subject: [PATCH] Normalise domain name to lower-case before further processing --- url-normalise | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/url-normalise b/url-normalise index fff05a7..97b5569 100755 --- a/url-normalise +++ b/url-normalise @@ -55,6 +55,14 @@ do suffix="" fi + # Normalise domain + if [[ "${url}" =~ ^https?://.*/ ]] + then + domain="${url#*://}" + domain="${domain%%/*}" + url="${url%%://*}://${domain,,}/${url#*://*/}" + fi + if [[ "${url}" =~ ^https?://((www|m|[a-z][a-z]-[a-z][a-z]).)?facebook.com/login/.*[?\&]next=https?%3A%2F%2F((www|m|[a-z][a-z]-[a-z][a-z]).)?facebook.com%2F && "${url}" != *'%0A'* && "${url}" != *'%00'* ]] then url="${url##*\?next=}"