Issue #23266: Much faster implementation of ipaddress.collapse_addresses() when there are many non-consecutive addresses.

1 files changed, 10 insertions, 6 deletions

diff --git a/Lib/ipaddress.py b/Lib/ipaddress.py
index b32a7e1dac..8d369e3986 100644
--- a/Lib/ipaddress.py
+++ b/Lib/ipaddress.py
@@ -170,16 +170,19 @@ def _find_address_range(addresses):
         addresses: a list of IPv#Address objects.
 
     Returns:
-        A tuple containing the first and last IP addresses in the sequence.
+        A tuple containing the first and last IP addresses in the sequence,
+        and the number of distinct IP addresses in the sequence.
 
     """
     first = last = addresses[0]
+    i = 1
     for ip in addresses[1:]:
         if ip._ip == last._ip + 1:
             last = ip
+            i += 1
         else:
             break
-    return (first, last)
+    return (first, last, i)
 
 
 def _count_righthand_zero_bits(number, bits):
@@ -346,12 +349,13 @@ def collapse_addresses(addresses):
                                  ip, nets[-1]))
             nets.append(ip)
 
-    # sort and dedup
-    ips = sorted(set(ips))
+    # sort
+    ips = sorted(ips)
 
+    # find consecutive address ranges in the sorted sequence and summarize them
     while i < len(ips):
-        (first, last) = _find_address_range(ips[i:])
-        i = ips.index(last) + 1
+        (first, last, items) = _find_address_range(ips[i:])
+        i = items + i
         addrs.extend(summarize_address_range(first, last))
 
     return _collapse_addresses_internal(addrs + nets)