From bf32cdb44aa7319deb2a7fe25573bed2502c403f Mon Sep 17 00:00:00 2001
From: Federico Leva <federicoleva@tiscali.it>
Date: Mon, 30 Apr 2018 13:41:18 +0300
Subject: [PATCH] Use a stricter regex for arXiv identifiers

See https://arxiv.org/help/arxiv_identifier
Does not check the number of digits, but avoids a greedy match of ".pdf".

Fixes https://phabricator.wikimedia.org/T187791

Bug: T187791
---
 src/oabot/arguments.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/oabot/arguments.py b/src/oabot/arguments.py
index 901d23e..09317f1 100644
--- a/src/oabot/arguments.py
+++ b/src/oabot/arguments.py
@@ -100,7 +100,7 @@ def present_and_free(self, template):
         custom_access=True),
     ArgumentMapping(
         'arxiv',
-        r'https?://arxiv\.org/(abs|pdf)/(.*)(.pdf)?',
+        r'https?://arxiv\.org/(abs|pdf)/(\d+\.[\dv]+)(\.pdf)?',
         group_id=2,
         alternate_names=['eprint'],
         always_free=True),