finished_update_article(): Richard Barrett's fix to reduce Pipermail

archive bloat by deleting the html_body attribute on Article objects.
Closes SF bug #835332.  This is a stub in the base class.

_update_thread_index(): Call finished_update_article() when done.

store_article(): squirrel away the html_body value when pickling the
article.

This only reduces bloat on new articles.  See bin/rb-archfix to clean
up older archives.

1 files changed, 9 insertions, 0 deletions

diff --git a/Mailman/Archiver/pipermail.py b/Mailman/Archiver/pipermail.py
index 210030ed..ec8e46f6 100644
--- a/Mailman/Archiver/pipermail.py
+++ b/Mailman/Archiver/pipermail.py
@@ -126,9 +126,13 @@ class Database(DatabaseInterface):
         """Store article without message body to save space"""
         # TBD this is not thread safe!
         temp = article.body
+        temp2 = article.html_body
         article.body = []
+        del article.html_body
         self.articleIndex[article.msgid] = pickle.dumps(article)
         article.body = temp
+        article.html_body = temp2
+
 
 # The Article class encapsulates a single posting.  The attributes
 # are:
@@ -239,6 +243,9 @@ class Article:
     def __repr__(self):
         return '<Article ID = '+repr(self.msgid)+'>'
 
+    def finished_update_article(self):
+        pass    
+
 # Pipermail formatter class
 
 class T:
@@ -486,6 +493,8 @@ class T:
                             self.update_article(arcdir, a1, L[0], L[2])
                         else:
                             del self.database.changed[key]
+            if L[0]:
+                L[0].finished_update_article()
             L = L[1:]                   # Rotate the list
             if msgid is None:
                 L.append(msgid)