From 05593a8bbd7dfc23f9bf8632bdac9c5c3efcc114 Mon Sep 17 00:00:00 2001
From: Cristian-J <59663672+Cristian-J@users.noreply.github.com>
Date: Wed, 8 Jan 2020 19:05:27 +0000
Subject: [PATCH] Ignore links that start with a hyphen or a dot

If you use filter blacklists you'll end up with many invalid links that start with a hyphen or a dot in the final blacklist.
---
 .../generate-domains-blacklist.py                    | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/utils/generate-domains-blacklists/generate-domains-blacklist.py b/utils/generate-domains-blacklists/generate-domains-blacklist.py
index 466c5372..43eba48b 100755
--- a/utils/generate-domains-blacklists/generate-domains-blacklist.py
+++ b/utils/generate-domains-blacklists/generate-domains-blacklist.py
@@ -52,14 +52,14 @@ def parse_list(content, trusted=False):
     rx_comment = re.compile(r"^(#|$)")
     rx_inline_comment = re.compile(r"\s*#\s*[a-z0-9-].*$")
     rx_u = re.compile(
-        r"^@*\|\|([a-z0-9.-]+[.][a-z]{2,})\^?(\$(popup|third-party))?$")
-    rx_l = re.compile(r"^([a-z0-9.-]+[.][a-z]{2,})$")
+        r"^@*\|\|([a-z0-9][a-z0-9.-]*[.][a-z]{2,})\^?(\$(popup|third-party))?$")
+    rx_l = re.compile(r"^([a-z0-9][a-z0-9.-]*[.][a-z]{2,})$")
     rx_h = re.compile(
-        r"^[0-9]{1,3}[.][0-9]{1,3}[.][0-9]{1,3}[.][0-9]{1,3}\s+([a-z0-9.-]+[.][a-z]{2,})$"
+        r"^[0-9]{1,3}[.][0-9]{1,3}[.][0-9]{1,3}[.][0-9]{1,3}\s+([a-z0-9][a-z0-9.-]*[.][a-z]{2,})$"
     )
-    rx_mdl = re.compile(r'^"[^"]+","([a-z0-9.-]+[.][a-z]{2,})",')
-    rx_b = re.compile(r"^([a-z0-9.-]+[.][a-z]{2,}),.+,[0-9: /-]+,")
-    rx_dq = re.compile(r"^address=/([a-z0-9.-]+[.][a-z]{2,})/.")
+    rx_mdl = re.compile(r'^"[^"]+","([a-z0-9][a-z0-9.-]*[.][a-z]{2,})",')
+    rx_b = re.compile(r"^([a-z0-9][a-z0-9.-]*[.][a-z]{2,}),.+,[0-9: /-]+,")
+    rx_dq = re.compile(r"^address=/([a-z0-9][a-z0-9.-]*[.][a-z]{2,})/.")
 
     if trusted:
         return parse_trusted_list(content)