4 files changed, 98 insertions, 19 deletions
diff --git a/scripts/arin-to-csv.py b/scripts/arin-to-csv.py
index 63368723..dcb508ff 100644
--- a/scripts/arin-to-csv.py
+++ b/scripts/arin-to-csv.py
@@ -56,18 +56,18 @@ def do_asn(node):
                             find(node, tag_endAsNumber))))
 
 erx_table = {
-  "AF" : "AFRINIC",
-  "AP" : "APNIC",
-  "AR" : "ARIN",
-  "AV" : "ARIN",
-  "FX" : "AFRINIC",
-  "LN" : "LACNIC",
-  "LX" : "LACNIC",
-  "PV" : "APNIC",
-  "PX" : "APNIC",
-  "RN" : "RIPE",
-  "RV" : "RIPE",
-  "RX" : "RIPE" }
+  "AF" : "afrinic",
+  "AP" : "apnic",
+  "AR" : "arin",
+  "AV" : "arin",
+  "FX" : "afrinic",
+  "LN" : "lacnic",
+  "LX" : "lacnic",
+  "PV" : "apnic",
+  "PX" : "apnic",
+  "RN" : "ripe",
+  "RV" : "ripe",
+  "RX" : "ripe" }
 
 def do_net(node):
   handle = find(node, tag_orgHandle)
diff --git a/scripts/convert-from-entitydb-to-sql.py b/scripts/convert-from-entitydb-to-sql.py
index ba073730..e1030ba9 100644
--- a/scripts/convert-from-entitydb-to-sql.py
+++ b/scripts/convert-from-entitydb-to-sql.py
@@ -95,7 +95,7 @@ tag_parent           = xmlns + "parent"
 tag_repository       = xmlns + "repository"
 
 def read_element_tree(filename, tag):
-  print "Reading file %s, tag %s\n" % (filename, tag)
+  print "Reading file %s, tag %s" % (filename, tag)
   e = ElementTree(file = filename).getroot()
   rpki.relaxng.myrpki.assertValid(e)
   assert e.tag == tag
diff --git a/scripts/iana-to-csv.py b/scripts/iana-to-csv.py
new file mode 100644
index 00000000..ee8c53d1
--- /dev/null
+++ b/scripts/iana-to-csv.py
@@ -0,0 +1,85 @@
+"""
+Parse IANA XML data.
+
+$Id$
+
+Copyright (C) 2010-2012  Internet Systems Consortium ("ISC")
+
+Permission to use, copy, modify, and distribute this software for any
+purpose with or without fee is hereby granted, provided that the above
+copyright notice and this permission notice appear in all copies.
+
+THE SOFTWARE IS PROVIDED "AS IS" AND ISC DISCLAIMS ALL WARRANTIES WITH
+REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY
+AND FITNESS.  IN NO EVENT SHALL ISC BE LIABLE FOR ANY SPECIAL, DIRECT,
+INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM
+LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE
+OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
+PERFORMANCE OF THIS SOFTWARE.
+"""
+
+import sys
+import lxml.etree
+from rpki.csv_utils import csv_reader, csv_writer
+from rpki.resource_set import resource_bag
+
+def iterate_xml(filename, tag):
+  return lxml.etree.parse(filename).getroot().getiterator(tag)
+
+def ns(tag):
+  return "{http://www.iana.org/assignments}" + tag
+
+tag_description = ns("description")
+tag_designation = ns("designation")
+tag_record      = ns("record")
+tag_number      = ns("number")
+tag_prefix      = ns("prefix")
+tag_status      = ns("status")
+
+handles = {}
+rirs = { "legacy" : resource_bag() }
+
+for rir in ("AfriNIC", "APNIC", "ARIN", "LACNIC", "RIPE NCC"):
+  handle = rir.split()[0].lower()
+  handles[rir] = handles["Assigned by %s" % rir] = handles["Administered by %s" % rir] = handle
+  rirs[handle] = resource_bag()
+
+asns     = csv_writer("asns.csv")
+prefixes = csv_writer("prefixes.csv")
+
+for record in iterate_xml("as-numbers.xml", tag_record):
+  description = record.findtext(tag_description)
+  if description in handles:
+    asns.writerow((handles[description], record.findtext(tag_number)))
+    
+for record in iterate_xml("ipv4-address-space.xml", tag_record):
+  designation = record.findtext(tag_designation)
+  if record.findtext(tag_status) != "RESERVED":
+    prefix, prefixlen = [int(i) for i in record.findtext(tag_prefix).split("/")]
+    if prefixlen != 8:
+      raise ValueError("%s violated /8 assumption" % record.findtext(tag_prefix))
+    rirs[handles.get(designation, "legacy")] |= resource_bag.from_str("%d.0.0.0/8" % prefix)
+
+for record in iterate_xml("ipv6-unicast-address-assignments.xml", tag_record):
+  description = record.findtext(tag_description)
+  if record.findtext(tag_description) in handles:
+    rirs[handles[description]] |= resource_bag.from_str(record.findtext(tag_prefix))
+
+erx = list(csv_reader("erx.csv"))
+assert all(r in rirs for r, p in erx)
+
+erx_overrides = resource_bag.from_str(",".join(p for r, p in erx), allow_overlap = True)
+
+for rir in rirs:
+  if rir != "legacy":
+    rirs[rir] -= erx_overrides
+    rirs[rir] |= resource_bag.from_str(",".join(p for r, p in erx if r == rir), allow_overlap = True)
+
+for rir, bag in rirs.iteritems():
+  for p in bag.v4:
+    prefixes.writerow((rir, p))
+  for p in bag.v6:
+    prefixes.writerow((rir, p))
+
+asns.close()
+prefixes.close()
diff --git a/scripts/ripe-prefixes-to-csv.awk b/scripts/ripe-prefixes-to-csv.awk
index 582d5ce7..37327484 100644
--- a/scripts/ripe-prefixes-to-csv.awk
+++ b/scripts/ripe-prefixes-to-csv.awk
@@ -3,13 +3,7 @@
 
 # ftp -pa ftp://ftp.ripe.net/pub/stats/ripencc/membership/alloclist.txt
 
-BEGIN {
-    translation["ie.google"] = "GoogleIreland";
-}
-
 function done() {
-    if (handle in translation)
-	handle = translation[handle];
     for (i = 1; i <= n_allocs; i++)
 	print handle "\t" alloc[i];
     n_allocs = 0;