From 2fcba49433886ef2e1237f1bd256aadcea494309 Mon Sep 17 00:00:00 2001
From: enwuenwu <108224417+enwuenwu@users.noreply.github.com>
Date: Sun, 28 Jul 2024 20:11:48 +0000
Subject: [PATCH] [Mailman2Bridge] fix message separation and improve "From_
 lines" disambiguation   (#4156)

* [Mailman2Bridge.php] enable PCRE_MULTILINE pattern modifier

Enable PCRE_MULTILINE pattern modifier on mbox content parsing. Without it parsing monthly archives results in only a single message each.

* [Mailman2Bridge.php] extend mbox "From_ lines" pattern

Extend PCRE pattern matching individual "From_ lines" used to split single messages in mbox content.

In addition to the matching line having to start with 'From ' it now also has to end with time and date (hh:mm:ss yyyy).

This makes the pattern slightly more robust against accidental matches when a line within the actual message body starts with 'From ' which Mailman 2 (Pipermail) may not be configured to disambiguate.

* [Mailman2Bridge.php] remove trailing slash from URI constant

---------

Co-authored-by: enwu <108224417+8279279374@users.noreply.github.com>
---
 bridges/Mailman2Bridge.php | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/bridges/Mailman2Bridge.php b/bridges/Mailman2Bridge.php
index ad0d8110..6b620c03 100644
--- a/bridges/Mailman2Bridge.php
+++ b/bridges/Mailman2Bridge.php
@@ -3,7 +3,7 @@
 class Mailman2Bridge extends BridgeAbstract
 {
     const NAME = 'Mailman2Bridge';
-    const URI = 'https://list.org/';
+    const URI = 'https://list.org';
     const MAINTAINER = 'imagoiq';
     const CACHE_TIMEOUT = 60 * 30; // 30m
     const DESCRIPTION = 'Fetch latest messages from Mailman 2 archive (Pipermail)';
@@ -68,7 +68,7 @@ class Mailman2Bridge extends BridgeAbstract
                     throw new \Exception('Failed to gzdecode');
                 }
             }
-            $mboxParts = preg_split('/^From /', $data);
+            $mboxParts = preg_split('/^From\s.+\d{2}:\d{2}:\d{2}\s\d{4}$/m', $data);
             // Drop the first element which is always an empty string
             array_shift($mboxParts);
             $mboxMails = array_reverse($mboxParts);