Fixed _set_date() in pipermail.py do do a better job.

2 files changed, 27 insertions, 8 deletions

diff --git a/Mailman/Archiver/pipermail.py b/Mailman/Archiver/pipermail.py
index 9c54bbd9..15decd40 100644
--- a/Mailman/Archiver/pipermail.py
+++ b/Mailman/Archiver/pipermail.py
@@ -16,6 +16,7 @@ __version__ = '0.09 (Mailman edition)'
 VERSION = __version__
 CACHESIZE = 100    # Number of slots in the cache
 
+from Mailman import mm_cfg
 from Mailman import Errors
 from Mailman.Mailbox import ArchiverMailbox
 from Mailman.Logging.Syslog import syslog
@@ -230,21 +231,30 @@ class Article:
         self.body = s.readlines()
 
     def _set_date(self, message):
-        def floatdate(header):
-            missing = []
-            datestr = message.get(header, missing)
-            if datestr is missing:
+        def floatdate(datestr):
+            if not datestr:
                 return None
             date = parsedate_tz(datestr)
             try:
-                return mktime_tz(date)
+                date = mktime_tz(date)
+                if (date < 0 or
+                    date - time.time() >
+                        mm_cfg.ARCHIVER_ALLOWABLE_SANE_DATE_SKEW
+                   ):
+                    return None
+                return date
             except (TypeError, ValueError, OverflowError):
                 return None
-        date = floatdate('date')
+        date = floatdate(message.get('date'))
+        if date is None:
+            date = floatdate(message.get('x-list-received-date'))
+        if date is None:
+            date = floatdate(re.sub(r'^.*;\s*', '',
+                                    message.get('received'), flags=re.S))
         if date is None:
-            date = floatdate('x-list-received-date')
+            date = floatdate(re.sub(r'From \s*\S+\s+', '',
+                                    message.get_unixfrom()))
         if date is None:
-            # What's left to try?
             date = self._last_article_time + 1
         self._last_article_time = date
         self.date = '%011i' % date
diff --git a/NEWS b/NEWS
index 26596c37..f3a3c886 100644
--- a/NEWS
+++ b/NEWS
@@ -14,6 +14,15 @@ Here is a history of user visible changes to Mailman.
 
   Bug fixes and other patches
 
+    - Fixed the pipermail archiver to do a better job of figuring the date of
+      a post when its Date: header is missing, unparseable or has an obviously
+      out of range date.  This should only affect bin/arch as ArchRunner has
+      code to fix dates at least if ARCHIVER_CLOBBER_DATE_POLICY has not been
+      set to 0 in mm_cfg.py.  If posts have been added in the past to a list's
+      archive using bin/arch and an imported mbox, running bin/arch again could
+      result is some of those posts being archived with a different date.
+      (LP: #1555798)
+
     - Fixed an issue with CommandRunner shunting a malformed message with a
       null byte in the body.  (LP: #1553888)