From 59c2660584734af92eca2eae31af3fbf5557f853 Mon Sep 17 00:00:00 2001
From: Jan Jansky <jjansky@redhat.com>
Date: Mon, 10 Jul 2023 13:10:22 +0200
Subject: [PATCH] [clean] Properly obfuscate MAC addresses

Some of mac addresses was not properly obfuscated because
some collected data contains mac addresses in format
01:<mac> and parser was not ready for that.

Also added mapper which will obfuscate mac address in case
it is in format with _ instead of : as for example

00_50_56_87_5d_01

instead of

00:50:56:87:5d:01

Format with _ is used for example by vmware plugin.

Resolves: #3302

Signed-off-by: Jan Jansky <jjansky@redhat.com>
---
 sos/cleaner/mappings/mac_map.py   | 2 +-
 sos/cleaner/parsers/mac_parser.py | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/sos/cleaner/mappings/mac_map.py b/sos/cleaner/mappings/mac_map.py
index 334a6681..4ccba25a 100644
--- a/sos/cleaner/mappings/mac_map.py
+++ b/sos/cleaner/mappings/mac_map.py
@@ -75,5 +75,5 @@ class SoSMacMap(SoSMap):
         if re.match('(([0-9a-fA-F]{4}:){3}([0-9a-fA-F]){4})', item):
             return self.mac6_quad_template % hextets
         # match 48-bit IPv4 MAC addresses
-        if re.match('([0-9a-fA-F]:?){12}', item):
+        if re.match('([0-9a-fA-F][:_]?){12}', item):
             return self.mac_template % hextets
diff --git a/sos/cleaner/parsers/mac_parser.py b/sos/cleaner/parsers/mac_parser.py
index 88b0ac2e..4e790018 100644
--- a/sos/cleaner/parsers/mac_parser.py
+++ b/sos/cleaner/parsers/mac_parser.py
@@ -25,8 +25,8 @@ IPV6_REG_4HEX = (
 )
 # aa:bb:cc:dd:ee:ff avoiding ipv6 substring matches
 IPV4_REG = (
-    r'((?<!([0-9a-fA-F\'\"]:)|::)(([^:\-])?([0-9a-fA-F]{2}([:-])){5}'
-    r'([0-9a-fA-F]){2}(\'|\")?(\/|\,|\-|\.|\s|$)))'
+    r'((?<!([0-9a-fA-F\'\"]:)|::)'
+    r'(([^:\-])?(([0-9a-fA-F]{2}([:\-\_])){5,6}([0-9a-fA-F]{2}))))'
 )
 
 
-- 
2.31.1