Add -s/--start and -e/--end switches to manually specify the start and

end message numbers (counted from zero) with which to archive.  This
can be useful when re-archiving a huge .mbox file, even though you
have to manually chunk it.

1 files changed, 36 insertions, 5 deletions

diff --git a/bin/arch b/bin/arch
index 5adb9a798..4a603123d 100644
--- a/bin/arch
+++ b/bin/arch
@@ -1,6 +1,6 @@
 #! @PYTHON@
 #
-# Copyright (C) 1998,1999,2000,2001 by the Free Software Foundation, Inc.
+# Copyright (C) 1998,1999,2000,2001,2002 by the Free Software Foundation, Inc.
 #
 # This program is free software; you can redistribute it and/or
 # modify it under the terms of the GNU General Public License
@@ -22,7 +22,23 @@ Use this command to rebuild the archives for a mailing list.  You may want to
 do this if you edit some messages in an archive, or remove some messages from
 an archive.
 
-Usage: %(PROGRAM)s <listname> [<mbox>] [-h]
+Usage: %(PROGRAM)s [options] <listname> [<mbox>] [-h]
+
+Where options are:
+    -h / --help
+        Print this help message and exit.
+
+    -s N
+    --start=N
+        Start indexing at article N, where article 0 is the first in the mbox.
+        Defaults to 0.
+
+    -e M
+    --end=M
+        End indexing at article M.  This script is not very efficient with
+        respect to memory management, and for large archives, it may not be
+        possible to index the mbox entirely.  For that reason, you can specify
+        the start and end article numbers.
 
 Where <mbox> is the path to a list's complete mbox archive.  Usually this will 
 be some path in the archives/private directory.  For example:
@@ -60,13 +76,26 @@ def usage(code, msg=''):
 def main():
     # get command line arguments
     try:
-        opts, args = getopt.getopt(sys.argv[1:], 'h', ['help'])
+        opts, args = getopt.getopt(sys.argv[1:], 'hs:e:',
+                                   ['help', 'start', 'end'])
     except getopt.error, msg:
         usage(1, msg)
 
+    start = None
+    end = None
     for opt, arg in opts:
         if opt in ('-h', '--help'):
             usage(0)
+        elif opt in ('-s', '--start'):
+            try:
+                start = int(arg)
+            except ValueError:
+                usage(1)
+        elif opt in ('-e', '--end'):
+            try:
+                end = int(arg)
+            except ValueError:
+                usage(1)
 
     # grok arguments
     if len(args) < 1:
@@ -115,8 +144,10 @@ def main():
 
         archiver = HyperArchive(mlist)
         archiver.VERBOSE = 1
-        archiver.processUnixMailbox(fp, Article)
-        archiver.close()
+        try:
+            archiver.processUnixMailbox(fp, Article, start, end)
+        finally:
+            archiver.close()
         fp.close()
     finally:
         if lock: