From patchwork Sat May 22 12:57:58 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: =?utf-8?q?Peter_M=C3=BCller?= X-Patchwork-Id: 4357 Return-Path: Received: from mail01.ipfire.org (mail01.haj.ipfire.org [172.28.1.202]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (P-384) client-signature ECDSA (P-384)) (Client CN "mail01.haj.ipfire.org", Issuer "R3" (verified OK)) by web04.haj.ipfire.org (Postfix) with ESMTPS id 4FnNn63ky3z3wbl for ; Sat, 22 May 2021 12:58:02 +0000 (UTC) Received: from mail02.haj.ipfire.org (mail02.haj.ipfire.org [172.28.1.201]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (P-384) client-signature ECDSA (P-384)) (Client CN "mail02.haj.ipfire.org", Issuer "R3" (verified OK)) by mail01.ipfire.org (Postfix) with ESMTPS id 4FnNn615jHz98; Sat, 22 May 2021 12:58:02 +0000 (UTC) Received: from mail02.haj.ipfire.org (localhost [127.0.0.1]) by mail02.haj.ipfire.org (Postfix) with ESMTP id 4FnNn60bL7z2xbB; Sat, 22 May 2021 12:58:02 +0000 (UTC) Received: from mail01.ipfire.org (mail01.haj.ipfire.org [172.28.1.202]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (P-384) client-signature ECDSA (P-384)) (Client CN "mail01.haj.ipfire.org", Issuer "R3" (verified OK)) by mail02.haj.ipfire.org (Postfix) with ESMTPS id 4FnNn4343Cz2xb4 for ; Sat, 22 May 2021 12:58:00 +0000 (UTC) Received: from location02.haj.ipfire.org (location02.haj.ipfire.org [172.28.1.170]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (P-384) server-digest SHA384 client-signature ECDSA (P-384) client-digest SHA384) (Client CN "location02.haj.ipfire.org", Issuer "R3" (verified OK)) by mail01.ipfire.org (Postfix) with ESMTPS id 4FnNn370jgz98; Sat, 22 May 2021 12:57:59 +0000 (UTC) Received: by location02.haj.ipfire.org (Postfix, from userid 0) id 4FnNn35vCZzyy0; Sat, 22 May 2021 12:57:59 +0000 (UTC) From: =?utf-8?q?Peter_M=C3=BCller?= To: location@lists.ipfire.org Subject: [PATCH v2] location-importer.in: track original countries as well Date: Sat, 22 May 2021 12:57:58 +0000 Message-Id: <20210522125758.28770-1-peter.mueller@ipfire.org> X-Mailer: git-send-email 2.20.1 MIME-Version: 1.0 X-BeenThere: location@lists.ipfire.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: location-bounces@lists.ipfire.org Sender: "Location" This helps us to determine how many network objects have more than one country set, and what their original country code set looked like. The second version of this patch uses ALTER TABLE to add the column for original countries, preventing existing SQL setups from breaking. Signed-off-by: Peter Müller --- src/python/location-importer.in | 52 ++++++++++++++++++++------------- 1 file changed, 32 insertions(+), 20 deletions(-) diff --git a/src/python/location-importer.in b/src/python/location-importer.in index e5f55af..c3f908a 100644 --- a/src/python/location-importer.in +++ b/src/python/location-importer.in @@ -165,6 +165,7 @@ class CLI(object): -- networks CREATE TABLE IF NOT EXISTS networks(network inet, country text); + ALTER TABLE networks ADD COLUMN IF NOT EXISTS original_countries text[]; CREATE UNIQUE INDEX IF NOT EXISTS networks_network ON networks(network); CREATE INDEX IF NOT EXISTS networks_family ON networks USING BTREE(family(network)); CREATE INDEX IF NOT EXISTS networks_search ON networks USING GIST(network inet_ops); @@ -377,7 +378,7 @@ class CLI(object): ON COMMIT DROP; CREATE UNIQUE INDEX _organizations_handle ON _organizations(handle); - CREATE TEMPORARY TABLE _rirdata(network inet NOT NULL, country text NOT NULL) + CREATE TEMPORARY TABLE _rirdata(network inet NOT NULL, country text NOT NULL, original_countries text[] NOT NULL) ON COMMIT DROP; CREATE INDEX _rirdata_search ON _rirdata USING BTREE(family(network), masklen(network)); CREATE UNIQUE INDEX _rirdata_network ON _rirdata(network); @@ -407,8 +408,8 @@ class CLI(object): for family in (row.family for row in families): smallest = self.db.get("SELECT MIN(masklen(network)) AS prefix FROM _rirdata WHERE family(network) = %s", family) - self.db.execute("INSERT INTO networks(network, country) \ - SELECT network, country FROM _rirdata WHERE masklen(network) = %s AND family(network) = %s", smallest.prefix, family) + self.db.execute("INSERT INTO networks(network, country, original_countries) \ + SELECT network, country, original_countries FROM _rirdata WHERE masklen(network) = %s AND family(network) = %s", smallest.prefix, family) # ... determine any other prefixes for this network family, ... prefixes = self.db.query("SELECT DISTINCT masklen(network) AS prefix FROM _rirdata \ @@ -421,7 +422,8 @@ class CLI(object): WITH candidates AS ( SELECT _rirdata.network, - _rirdata.country + _rirdata.country, + _rirdata.original_countries FROM _rirdata WHERE @@ -434,6 +436,7 @@ class CLI(object): DISTINCT ON (c.network) c.network, c.country, + c.original_countries, masklen(networks.network), networks.country AS parent_country FROM @@ -447,10 +450,11 @@ class CLI(object): masklen(networks.network) DESC NULLS LAST ) INSERT INTO - networks(network, country) + networks(network, country, original_countries) SELECT network, - country + country, + original_countries FROM filtered WHERE @@ -617,28 +621,36 @@ class CLI(object): inetnum[key] = [ipaddress.ip_network(val, strict=False)] elif key == "country": - inetnum[key] = val.upper() + # Catch RIR data objects with more than one country code... + if not key in inetnum.keys(): + inetnum[key] = [] + else: + if val.upper() in inetnum.get("country"): + # ... but keep this list distinct... + continue + + inetnum[key].append(val.upper()) # Skip empty objects if not inetnum or not "country" in inetnum: return + # Prepare skipping objects with unknown country codes... + invalidcountries = [singlecountry for singlecountry in inetnum.get("country") if singlecountry not in validcountries] + # Iterate through all networks enumerated from above, check them for plausibility and insert # them into the database, if _check_parsed_network() succeeded for single_network in inetnum.get("inet6num") or inetnum.get("inetnum"): if self._check_parsed_network(single_network): - - # Skip objects with unknown country codes - to avoid log spam for invalid or too small - # networks, this check is - kinda ugly - done at this point - if validcountries and inetnum.get("country") not in validcountries: - log.warning("Skipping network with bogus country '%s': %s" % \ - (inetnum.get("country"), inetnum.get("inet6num") or inetnum.get("inetnum"))) + # Skip objects with unknown country codes if they are valid to avoid log spam... + if validcountries and invalidcountries: + log.warning("Skipping network with bogus countr(y|ies) %s (original countries: %s): %s" % \ + (invalidcountries, inetnum.get("country"), inetnum.get("inet6num") or inetnum.get("inetnum"))) break - # Everything is fine here, run INSERT statement... - self.db.execute("INSERT INTO _rirdata(network, country) \ - VALUES(%s, %s) ON CONFLICT (network) DO UPDATE SET country = excluded.country", - "%s" % single_network, inetnum.get("country"), + self.db.execute("INSERT INTO _rirdata(network, country, original_countries) \ + VALUES(%s, %s, %s) ON CONFLICT (network) DO UPDATE SET country = excluded.country", + "%s" % single_network, inetnum.get("country")[0], inetnum.get("country"), ) def _parse_org_block(self, block): @@ -729,10 +741,10 @@ class CLI(object): if not self._check_parsed_network(network): return - self.db.execute("INSERT INTO networks(network, country) \ - VALUES(%s, %s) ON CONFLICT (network) DO \ + self.db.execute("INSERT INTO networks(network, country, original_countries) \ + VALUES(%s, %s, %s) ON CONFLICT (network) DO \ UPDATE SET country = excluded.country", - "%s" % network, country, + "%s" % network, country, [country], ) def handle_update_announcements(self, ns):