Fallbacks: accept relays that are a fuzzy match to the whitelist

If a relay matches at least one fingerprint, IPv4 address, or IPv6
address in the fallback whitelist, it can become a fallback. This
reduces the work required to keep the list up to date.

Closes ticket 28768.

2 files changed, 42 insertions, 14 deletions

diff --git a/scripts/maint/fallback.whitelist b/scripts/maint/fallback.whitelist
index 97291d73be..eb7fd92d4b 100644
--- a/scripts/maint/fallback.whitelist
+++ b/scripts/maint/fallback.whitelist
@@ -1,16 +1,18 @@
 # updateFallbackDirs.py directory mirror whitelist
-
-# All attributes must match for the directory mirror to be included.
-# If the fallback has an ipv6 key, the whitelist line must also have
-# it, and vice versa, otherwise they don't match.
-
-# To replace this list with the hard-coded fallback list (for testing), use
-# "updateFallbackDirs.py check_existing", or a command similar to:
-#   cat src/app/config/fallback_dirs.inc | grep \" | grep -v weight | \
-#   tr -d '\n' | \
-#   sed 's/"" / /g' | sed 's/""/"/g' | tr \" '\n' | grep -v '^$' \
-#   > scripts/maint/fallback.whitelist
-
+#
+# At least one of these keys must match for a directory mirror to be included
+# in the fallback list:
+#   id
+#   ipv4
+#   ipv6
+# The ports and nickname are ignored. Missing or extra ipv6 addresses
+# are ignored.
+#
+# The latest relay details from Onionoo are included in the generated list.
+#
+# To check the hard-coded fallback list (for testing), use:
+# $ updateFallbackDirs.py check_existing
+#
 # If a relay operator wants their relay to be a FallbackDir,
 # enter the following information here:
 # <IPv4>:<DirPort> orport=<ORPort> id=<ID> ( ipv6=[<IPv6>]:<IPv6 ORPort> )?
diff --git a/scripts/maint/updateFallbackDirs.py b/scripts/maint/updateFallbackDirs.py
index b334352152..14372d0e83 100755
--- a/scripts/maint/updateFallbackDirs.py
+++ b/scripts/maint/updateFallbackDirs.py
@@ -1061,14 +1061,40 @@ class Candidate(object):
       return False
     return True
 
+  def entry_matches_fuzzy(self, entry):
+    """ Is entry a fuzzy match for this fallback?
+        A fallback is a fuzzy match for entry if at least one of these keys
+        in entry matches:
+          id
+          ipv4
+          ipv6 (if present in both the fallback and whitelist)
+        The ports and nickname are ignored. Missing or extra ipv6 addresses
+        are ignored.
+
+        Doesn't log any warning messages. """
+    if self.id_matches(entry['id'], exact=False):
+      return True
+    if self.ipv4_addr_matches(entry['ipv4'], exact=False):
+      return True
+    if entry.has_key('ipv6') and self.has_ipv6():
+      # if both entry and fallback have an ipv6 address, compare them
+      if self.ipv6_addr_matches(entry['ipv6_addr'], exact=False):
+        return True
+    return False
+
   def is_in_whitelist(self, relaylist, exact=False):
     """ If exact is True (existing fallback list), check if this fallback is
         an exact match for any whitelist entry, using entry_matches_exact().
-    """
+
+        If exact is False (new fallback whitelist), check if this fallback is
+        a fuzzy match for any whitelist entry, using entry_matches_fuzzy(). """
     for entry in relaylist:
       if exact:
         if self.entry_matches_exact(entry):
           return True
+      else:
+        if self.entry_matches_fuzzy(entry):
+          return True
     return False
 
   def cw_to_bw_factor(self):
@@ -2193,7 +2219,7 @@ def process_default():
   logging.getLogger('stem').setLevel(logging.WARNING)
   whitelist = {'data': read_from_file(WHITELIST_FILE_NAME, MAX_LIST_FILE_SIZE),
                'name': WHITELIST_FILE_NAME}
-  list_fallbacks(whitelist, exact=True)
+  list_fallbacks(whitelist, exact=False)
 
 ## Main Function
 def main():