From 219b8b792e2a6e1fb72b9e658b06395a50292e59 Mon Sep 17 00:00:00 2001
From: Philip Sargent <philip.sargent@gmail.com>
Date: Thu, 9 Jan 2025 21:59:27 +0000
Subject: AI comments on regexes

---
 parsers/logbooks.py | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'parsers/logbooks.py')

diff --git a/parsers/logbooks.py b/parsers/logbooks.py
index 2ede83f..3d96b3b 100644
--- a/parsers/logbooks.py
+++ b/parsers/logbooks.py
@@ -139,6 +139,18 @@ def GetTripPersons(trippeople, expedition, logtime_underground, tid=None):
     # print(f'# {tid}')
     # print(f" -  {tid} '{trippeople}'  ")
 
+    """
+    re.split(r",|\+|&amp;|&(?!\w+;)| and ", trippeople)
+
+    ,             : The comma character
+    \+            : The plus sign (+); escaped to treat as a literal character
+    &amp;         : The literal string "&amp;" (HTML-encoded ampersand)
+    &(?!\w+;)     : An ampersand (&) not followed by one or more word characters (\w+) and a semicolon (;)
+                    : Uses negative lookahead assertion (?!...) to ensure it's not part of an HTML entity like "&nbsp;"
+     and          : The literal string " and " (with spaces before and after)
+
+    This will split the 'trippeople' string at any of these delimiters.
+    """
     for tripperson in re.split(r",|\+|&amp;|&(?!\w+;)| and ", trippeople):
         tripperson = tripperson.strip()
         # author_u = re.match(r"(?i)<u>(.*?)</u>$", tripperson)
-- 
cgit v1.2.3