Add date option to RFC Editor index mirroring script so one can

control what the publication cut off date is, also fix crash problem
with some old RFCs not having a page count
 - Legacy-Id: 4907

Author: OleLaursen

ietf/bin/rfc-editor-index-updates

@@ -14,6 +14,18 @@ from django.core import management
 management.setup_environ(settings)
 
 
+from optparse import OptionParser
+
+parser = OptionParser()
+parser.add_option("-d", dest="skip_date",
+                  help="To speed up processing skip RFCs published before this date (default is one year ago)", metavar="YYYY-MM-DD")
+
+options, args = parser.parse_args()
+
+skip_date = datetime.date.today() - datetime.timedelta(days=365)
+if options.skip_date:
+    skip_date = datetime.datetime.strptime(options.skip_date, "%Y-%m-%d").date()
+
 from ietf.sync.rfceditor import *
 
 syslog.syslog("Updating document metadata from RFC index from %s" % QUEUE_URL)
@@ -25,6 +37,6 @@ if len(data) < MIN_INDEX_RESULTS:
     syslog.syslog("Not enough results, only %s" % len(data))
     sys.exit(1)
 
-changed = update_docs_from_rfc_index(data)
+changed = update_docs_from_rfc_index(data, skip_older_than_date=skip_date)
 for c in changed:
     syslog.syslog(c)

ietf/sync/rfceditor.py

@@ -273,7 +273,6 @@ def getDocList(parentNode, tagName):
     return data
 
 
-    #skip_older_than_date = date.today() - timedelta(days=365)
 def update_docs_from_rfc_index(data, skip_older_than_date=None):
     std_level_mapping = {
         "Standard": StdLevelName.objects.get(slug="std"),
@@ -347,7 +346,7 @@ def update_docs_from_rfc_index(data, skip_older_than_date=None):
         if abstract and abstract != doc.abstract:
             changed_attributes["abstract"] = abstract
 
-        if int(pages) != doc.pages:
+        if pages and int(pages) != doc.pages:
             changed_attributes["pages"] = int(pages)
 
         if std_level_mapping[current_status] != doc.std_level: