Create the image's app user without the system-user flag (closes #248)

`useradd -r` with UID 1000 made the image build warn, since 1000 is above the system range. The user keeps UID 1000, so the data directory's owner does not change.

Model: opus-5-5

.dockerignore

@@ -93,11 +93,12 @@
 **/*.dylib
 
 # Local databases. The image carries a source archive of the whole build
-# context, so these would otherwise ship inside it. The daemon's database
+# context, so these would otherwise ship inside it. The daemon's databases
-# is db.sqlite, with its -wal and -shm files while it runs.
+# are db.sqlite and cache.db, with their -wal and -shm files while it runs.
 **/*.db
 **/*.db-journal
 **/*.db-wal
+**/*.db-shm
 **/*.sqlite
 **/*.sqlite-wal
 **/*.sqlite-shm

.gitignore

@@ -68,10 +68,12 @@ go.work
 go.work.sum
 
 # Local databases, temporary files and debug output. The daemon's
-# database is db.sqlite, with its -wal and -shm files while it runs.
+# databases are db.sqlite and cache.db, with their -wal and -shm files
+# while it runs.
 *.db
 *.db-journal
 *.db-wal
+*.db-shm
 *.sqlite
 *.sqlite-wal
 *.sqlite-shm

Dockerfile

@@ -105,7 +105,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
 ARG CACHEBUST
 
 # Create non-root user
-RUN useradd -r -u 1000 -m routewatch
+RUN useradd -u 1000 -m routewatch
 
 RUN mkdir -p /var/lib/berlin.sneak.app.routewatch && chown routewatch:routewatch /var/lib/berlin.sneak.app.routewatch
 

README.md

@@ -44,8 +44,7 @@ its abuse contact. RouteWatch keeps them in its database and fetches them again
 once they are 30 days old. An IP lookup answers from the stored details and
 never waits for WHOIS.
 
-An IP lookup also says which public blocklists list the address (see
+An IP lookup also says which public IP lists hold the address (see IP lists).
-Blocklists).
 
 ## Getting started
 
@@ -64,8 +63,8 @@ docker run --memory=5g --memory-swap=5g -p 8080:8080 \
     -v routewatch:/var/lib/berlin.sneak.app.routewatch routewatch
 ```
 
-The memory limit is explained in Memory. The volume holds the database and the
+The memory limit is explained in Memory. The volume holds the database, the
-copies of the blocklists.
+copies of the IP lists and the geolocation files.
 
 To run the binary on the host instead, build it with `make build`. The build
 needs Go and a C compiler, because the SQLite library is written in C:
@@ -282,10 +281,20 @@ answer holds `query`, the text looked up, and `results`, with one entry for each
 address. Every entry has the same fields:
 
 - `ip`: the address
-- `ptr`: the address's PTR names, the host names that DNS gives for it, or an
+- `ptr`: the address's PTR names, the host names that DNS gives for it (see PTR
-  empty list when it has none
+  lookups), or an empty list when it has none
-- `blocklists`: the public blocklists the address is on (see Blocklists), or an
+- `flags`: yes-or-no facts about the address:
-  empty list when it is on none
+    - `is_tor`: true when the address is on the `tor_exits` list
+    - `is_vpn`: true when the address is on any list of VPN servers (see IP
+      lists)
+    - `is_relay`: true when the address is on the `icloud_private_relay` list
+    - `is_bogon`: true when the address is reserved, so that no network should
+      announce it on the internet
+- `vpn_providers`: the names of the lists of VPN servers the address is on, or
+  an empty list when it is on none
+- `ip_lists`: the public IP lists the address is on (see IP lists), or an empty
+  list when it is on none
+- `geo`: where the address is (see Geolocation), or null when no source answers
 
 Every other field is about the prefix in the routing table that holds the
 address. Each is null when no prefix in the routing table holds the address:
@@ -327,11 +336,8 @@ address, such as one that resolves to a private address, is reported as
 - `{ip}` comes to more than 10 addresses once its names are resolved
 - nothing in `{ip}` is an IP address or a host name with a public address
 
-Each PTR lookup gets 2 seconds. An address whose lookup takes longer is answered
-without PTR names.
-
 A successful answer carries `Cache-Control` with a `max-age` of 15 minutes, the
-shortest blocklist interval. The answer for the caller's own address (`/ip/`) is
+shortest IP list interval. The answer for the caller's own address (`/ip/`) is
 `private`, and the others are `public`.
 
 ### Errors
@@ -391,10 +397,10 @@ inline `<style>` and `<script>` blocks. Each answer's policy names a random
 value, a nonce, made for that answer. The browser applies or runs only the
 blocks that carry it.
 
-## Blocklists
+## IP lists
 
-An IP lookup reports which public blocklists list each address. Each entry in
+An IP lookup reports which public IP lists hold each address. Each entry in
-`blocklists` has:
+`ip_lists` has:
 
 - `name`: the list's name, from the lists below
 - `description`: what being on the list means
@@ -417,13 +423,38 @@ The lists:
   last 30 days. From
   [FireHOL](https://iplists.firehol.org/?ipset=firehol_level3), downloaded every
   3 hours.
+- `icloud_private_relay`: the networks where iCloud Private Relay traffic
+  leaves. From [Apple](https://mask-api.icloud.com/egress-ip-ranges.csv),
+  downloaded once a day.
+- `ivpn`: VPN servers run by IVPN. From
+  [IVPN](https://api.ivpn.net/v5/servers.json), downloaded once a day.
+- `mullvad`: VPN servers run by Mullvad. From
+  [Mullvad](https://api.mullvad.net/www/relays/all/), downloaded once a day.
+- `nordvpn`: VPN servers run by NordVPN. From
+  [NordVPN](https://api.nordvpn.com/v1/servers?limit=0&fields[servers.station]&fields[servers.ipv6_station]&fields[servers.hostname]),
+  downloaded once a day.
+- `pia`: VPN servers run by Private Internet Access. From
+  [Private Internet Access](https://serverlist.piaservers.net/vpninfo/servers/v6),
+  downloaded once a day.
+- `protonvpn`: the /24 networks that hold ProtonVPN servers. The whole /24 is
+  listed because the ProtonVPN-IPs README says traffic leaves from unpublished
+  addresses in it. From the public
+  [ProtonVPN-IPs](https://github.com/tn3w/ProtonVPN-IPs) mirror of Proton's
+  server list, downloaded once a day.
+- `protonvpn_entry`: the IPv4 and IPv6 addresses of ProtonVPN servers. From the
+  same [ProtonVPN-IPs](https://github.com/tn3w/ProtonVPN-IPs) mirror, downloaded
+  once a day.
 - `spamhaus_drop` and `spamhaus_dropv6`: IPv4 and IPv6 networks hijacked or
   leased by spammers or cyber criminals, according to Spamhaus. From
   [Spamhaus DROP](https://www.spamhaus.org/blocklists/do-not-route-or-peer/),
   downloaded once a day.
-- `tor_exits`: Tor exit nodes, where traffic from the Tor network leaves. From
+- `tor_exits`: the IPv4 and IPv6 addresses of Tor exit nodes, where traffic from
-  the [Tor Project](https://check.torproject.org/torbulkexitlist), downloaded
+  the Tor network leaves. From the Tor Project's
+  [Onionoo](https://metrics.torproject.org/onionoo.html) service, downloaded
   every hour.
+- `x4bnet` and `x4bnet_v6`: IPv4 and IPv6 networks of VPN services, according to
+  a community list that names no service. From
+  [X4BNet](https://github.com/X4BNet/lists_vpn), downloaded once a day.
 
 No list is downloaded more often than its publisher updates it or allows. Each
 can be downloaded whole without an account or a key.
@@ -431,8 +462,8 @@ can be downloaded whole without an account or a key.
 How RouteWatch keeps the lists:
 
 - It holds each list in memory, so a lookup makes no outside request.
-- It keeps a copy of each list in the `blocklists` directory of the state
+- It keeps a copy of each list in the `iplists` directory of the state directory
-  directory (see Configuration). Each copy is a file named after its list.
+  (see Configuration). Each copy is a file named after its list.
 - Beside each copy, a file ending in `.validators` keeps the `Last-Modified` and
   `ETag` headers the publisher sent with that copy.
 - At startup it loads each list from its copy. It downloads a list at once when
@@ -440,10 +471,115 @@ How RouteWatch keeps the lists:
 - A download sends the copy's `Last-Modified` as `If-Modified-Since` and its
   `ETag` as `If-None-Match`. The publisher then sends the list only when it has
   changed.
-- A download fails when it takes over a minute or its file is over 16 MiB.
+- A download fails when it takes over a minute or its file is over 200 MiB.
 - When a download fails, or its file does not parse, RouteWatch keeps the
   previous copy and logs the failure. It tries again one interval later.
 
+## PTR lookups
+
+An IP lookup finds each address's PTR names over DNS-over-HTTPS. It asks these
+public resolvers in order, until one answers:
+
+- Google: `https://dns.google/dns-query`
+- Cloudflare: `https://cloudflare-dns.com/dns-query`
+- AdGuard: `https://unfiltered.adguard-dns.com/dns-query`
+- Quad9: `https://dns.quad9.net/dns-query`
+
+One address's lookup gets 2 seconds across all four. Each resolver gets an equal
+share of the time left, so one that does not answer leaves time for the next.
+When none answers in time, the address's `ptr` is an empty list.
+
+A reserved address, one whose `is_bogon` flag is true, is not sent to the
+resolvers. Its `ptr` is an empty list.
+
+What goes outside: each resolver asked receives the address being looked up. For
+`/ip/` and the home page, that address is the visitor's own. A lookup answered
+from the cache sends nothing.
+
+How RouteWatch keeps the answers:
+
+- It holds answers in memory. An answer that has not expired is served from
+  there.
+- It writes new answers every 5 seconds to `cache.db` in the state directory
+  (see Configuration), and loads them from there at startup.
+- An answer expires after the TTL of its records, the shortest one when there
+  are several. RouteWatch keeps it for at least 60 seconds and at most 24 hours.
+- When an address has no PTR names, that answer expires after the SOA record's
+  minimum field, or the record's own TTL when that is shorter. RouteWatch keeps
+  it for at most 1 hour.
+- An answer with no PTR names and no SOA record is not kept. Neither is one
+  whose SOA record has a TTL or minimum field of 0.
+- A failed lookup is not kept, so the next lookup of the address asks again.
+- Every 10 minutes it deletes expired answers from memory and from `cache.db`.
+- It keeps answers for at most 250,000 addresses, and keeps no answer for a new
+  address while it holds that many.
+
+## Geolocation
+
+An IP lookup finds where each address is, on a best-effort basis. It uses two
+sources:
+
+- [geojs](https://www.geojs.io/) is asked first. One request carries every
+  address of the lookup, and it has 1 second to answer.
+- [DB-IP City Lite](https://db-ip.com/db/download/ip-to-city-lite) answers when
+  geojs has no answer for the address. It is a database file that RouteWatch
+  reads itself.
+
+geojs has no answer when its request fails or runs out of time. An answer with
+no country, city or coordinates also counts as no answer, and RouteWatch does
+not cache it.
+
+The `geo` object of a result has these fields:
+
+- `country_code`: the two-letter country code
+- `country`: the country's name in English
+- `continent_code`: the two-letter continent code
+- `region`: the region or state
+- `city`: the city
+- `latitude` and `longitude`: the location in degrees
+- `accuracy_radius_km`: how far from that location the address may be, in km
+- `time_zone`: the time zone's name, such as `Europe/Berlin`
+- `source`: the source of the answer, `geojs` or `dbip`
+- `updated`: when the answer was fetched from geojs, or when the database copy
+  was downloaded
+
+A field the source does not know is null. DB-IP has no `accuracy_radius_km` and
+no `time_zone`, so both are null in its answers. `geo` itself is null when
+neither source answers. A reserved address, one whose `is_bogon` flag is true,
+goes to neither source, so its `geo` is null.
+
+What goes outside: geojs receives each address that the cache does not hold. For
+`/ip/` and the home page, that address is the visitor's own. A lookup answered
+from the cache sends nothing. DB-IP receives only the monthly request for its
+file.
+
+How RouteWatch keeps the answers of geojs:
+
+- It holds at most 250,000 addresses in memory, and drops the least recently
+  used first. That takes about 100 MB of the Go heap.
+- It writes new answers every 5 seconds to `cache.db` in the state directory.
+- It loads the newest 250,000 answers from `cache.db` at startup.
+- An address not in memory is read from `cache.db` before geojs is asked.
+- An answer expires 7 days after its fetch. Every 10 minutes RouteWatch deletes
+  expired answers from memory and from `cache.db`.
+
+Answers from the database are not cached, because reading the file is local.
+
+How RouteWatch keeps the database:
+
+- It keeps one copy in the state directory, named `dbip-city-lite.mmdb`.
+- It downloads the current month's file at the first start, and then once a
+  month. Until the first download finishes, only geojs answers.
+- A download fails when it takes over 10 minutes or unpacks to over 200 MiB.
+- A new file replaces the old copy only once it opens. After a failed download
+  RouteWatch keeps the old copy and tries again an hour later.
+- The file is about 130 MB. RouteWatch maps it into memory, outside the Go heap.
+  The kernel loads the parts that are read, and can drop them again when memory
+  is short.
+
+The home page's footer says "IP Geolocation by DB-IP" with a link to
+[db-ip.com](https://db-ip.com).
+
 ## Configuration
 
 RouteWatch reads its settings from environment variables. It takes no
@@ -492,7 +628,15 @@ by the client. For a request from any other address, they use the address the
 request came from, whatever headers it carries. `X-Real-IP` and `True-Client-IP`
 are not read.
 
-The state directory holds the database, `db.sqlite`, and the blocklist copies:
+The state directory holds:
+
+- `db.sqlite`: the database
+- `cache.db`: the answers of PTR lookups and of geojs
+- `dbip-city-lite.mmdb`: the copy of DB-IP's City Lite database (see
+  Geolocation)
+- `iplists`: the IP list copies
+
+It is at:
 
 - macOS: `~/Library/Application Support/berlin.sneak.app.routewatch/`
 - Linux and the BSDs, as root: `/var/lib/berlin.sneak.app.routewatch/`
@@ -514,8 +658,9 @@ a memory limit of 5 GiB and swap disabled:
 docker run --memory=5g --memory-swap=5g ...
 ```
 
-The 5 GiB leaves room above the ceilings for spikes and for the kernel's cache
+The 5 GiB leaves room above the ceilings for spikes, for the kernel's cache of
-of the database file.
+the database file, and for the mapped copy of DB-IP's database (see
+Geolocation).
 
 The ceilings add up to 3.7 GiB:
 
@@ -535,6 +680,13 @@ The ceilings add up to 3.7 GiB:
   limit caps the SQLite library.
 - About 0.2 GiB for everything else in the runtime.
 
+The `icloud_private_relay` list has about 285,000 networks. Neighbouring
+networks merge, which leaves about 6,900 address ranges. Loaded, the list adds
+about 0.3 MiB to the Go heap and under 6 MiB to the process's resident memory.
+Parsing the file allocates about 94 MiB in about 0.2 seconds. The next garbage
+collection frees all of it but the 0.3 MiB above. Parsing happens at startup and
+whenever a download brings a new version.
+
 The SQLite library gets its memory from glibc, the C library. glibc keeps freed
 memory in pools called arenas, and hands it back to the kernel slowly. It
 creates up to eight arenas per processor core. So on a host with many cores the
@@ -647,8 +799,12 @@ The parts:
   wait starts at 15 seconds. It halves after a success, down to 1 second, and
   grows by half after a failure, up to a minute. An IP lookup that finds an AS
   with old or missing details asks the fetcher for it at once, without the wait.
-- The blocklists part downloads the blocklists and answers which lists hold an
+- The IP lists part downloads the IP lists and answers which lists hold an
   address.
+- The PTR cache looks up the PTR names of addresses and keeps the answers (see
+  PTR lookups).
+- The geolocation part finds where addresses are, keeps the answers of geojs and
+  downloads DB-IP's database (see Geolocation).
 - The database maintainer checkpoints the database every 5 seconds: it folds the
   write-ahead log, where SQLite first writes changes, into the database file. It
   reclaims free space every 10 minutes. Every hour it refreshes the statistics
@@ -756,8 +912,10 @@ On `SIGTERM` or `SIGINT` the daemon stops its parts in this order:
 2. the handlers, each of which writes what it holds
 3. the WHOIS fetcher
 4. the database maintainer
-5. the blocklist downloads
+5. the IP list downloads
 6. the HTTP server
+7. the geolocation part, which writes the geojs answers it holds
+8. the PTR cache, which writes what it holds
 
 Last, the daemon checkpoints and closes the database. It gives all this 8
 seconds and then exits with status 0. A stop that is still running after 9
@@ -778,6 +936,10 @@ What a stop can lose:
 - When the 8 seconds run out, the streamer and the handlers log what they could
   not hand over or write. The database is then not closed. When it next opens,
   SQLite rolls back any write the exit cut off.
+- When the 8 seconds run out, the PTR answers not yet in `cache.db` are lost.
+  RouteWatch asks the resolvers for them again the next time they are needed.
+- When the 8 seconds run out, the geojs answers not yet in `cache.db` are lost.
+  RouteWatch asks geojs for them again the next time they are needed.
 
 ### Code layout
 
@@ -790,12 +952,15 @@ routewatch/
 ├── docs/
 │   └── message-examples.json  # Examples of RIS Live messages
 ├── internal/
-│   ├── blocklist/          # Public IP blocklists: downloads and lookups
 │   ├── bogon/              # Reserved prefixes and AS numbers
+│   ├── cachedb/            # cache.db, the caches of outside answers
 │   ├── config/             # Settings from the environment
 │   ├── database/           # SQLite storage
+│   ├── geo/                # Geolocation: geojs, DB-IP City Lite, the cache
+│   ├── iplist/             # Public IP lists: downloads and lookups
 │   ├── logger/             # Structured logging
 │   ├── metrics/            # Feed and route update figures
+│   ├── ptr/                # PTR lookups over DNS-over-HTTPS, and their cache
 │   ├── ristypes/           # The RIS Live message types
 │   ├── routetable/         # The whole routing table in memory
 │   ├── routewatch/         # The daemon: startup, handlers, WHOIS fetcher
@@ -844,6 +1009,18 @@ announcements(id PRIMARY KEY, prefix_id, peer_asn, origin_asn, path,
 
 The indexes are in `internal/database/schema.sql`.
 
+`cache.db` is a separate file, with two tables:
+
+```sql
+-- The answers of PTR lookups. names is empty for an address with no PTR names.
+hostnames(address PRIMARY KEY, names, expires_at)
+
+-- The answers of geojs. A part geojs does not know is NULL.
+geolocations(address PRIMARY KEY, country_code, country, continent_code,
+             region, city, latitude, longitude, accuracy_radius_km, time_zone,
+             fetched_at)
+```
+
 ## Development
 
 The `make` targets:

TODO.md

@@ -41,9 +41,6 @@ https://git.eeqj.de/sneak/routewatch/issues/225, also on `next`, takes the peers
 whose sessions go down together out of the table in one walk. A 24-hour run of
 `9bd0e91` on the live feed is checking whether any handler still drops updates.
 
-One question waits for sneak: which fields the IP lookup answer gains
-(https://git.eeqj.de/sneak/routewatch/issues/203).
-
 The order of the project's remaining work is kept on
 https://git.eeqj.de/sneak/routewatch/issues/86.
 
@@ -56,6 +53,38 @@ problem the run finds.
 
 # Completed Steps
 
+- 2026-11-10: the image creates the `routewatch` user as a regular user with UID
+  1000, so the build no longer warns about the system UID range (closes
+  https://git.eeqj.de/sneak/routewatch/issues/248).
+- 2026-11-10: each result of the IP lookup has `geo`, where the address is. It
+  comes from geojs, with DB-IP's City Lite database as the fallback. The geojs
+  answers stay in memory and in `cache.db` for 7 days (closes
+  https://git.eeqj.de/sneak/routewatch/issues/239).
+- 2026-11-10: the IP lookup checks the `icloud_private_relay` list of Apple's
+  iCloud Private Relay networks, downloaded once a day. Each result has
+  `flags.is_relay` (closes https://git.eeqj.de/sneak/routewatch/issues/237).
+- 2026-11-10: the IP lookup checks the `protonvpn` list of ProtonVPN's /24
+  networks and the `protonvpn_entry` list of its servers' IPv4 and IPv6
+  addresses, from a public mirror of Proton's server list (closes
+  https://git.eeqj.de/sneak/routewatch/issues/236).
+- 2026-11-10: the IP lookup finds PTR names over DNS-over-HTTPS and caches them
+  for the record's TTL, in memory and in `cache.db` (closes
+  https://git.eeqj.de/sneak/routewatch/issues/238).
+- 2026-11-10: the tests no longer fail when a busy host stalls for several
+  seconds. Most such waits are now 15 seconds. The test of the stream's idle
+  timeout runs on a fake clock (closes #240)
+- 2026-11-10: the IP lookup checks the public VPN server lists of Mullvad,
+  NordVPN, Private Internet Access and IVPN, and X4BNet's community list. Each
+  result has `flags.is_vpn` and `vpn_providers` (closes
+  https://git.eeqj.de/sneak/routewatch/issues/235).
+- 2026-11-10: `tor_exits` comes from Onionoo, so it holds IPv6 exits and
+  `is_tor` is true for them (closes
+  https://git.eeqj.de/sneak/routewatch/issues/234).
+- 2026-11-10: each result of the IP lookup has a `flags` object with `is_tor`
+  and `is_bogon`. The public IP lists are named `ip_lists` in the answer,
+  `internal/iplist` in the code and `iplists` in the state directory. A list
+  file may be up to 200 MiB (closes
+  https://git.eeqj.de/sneak/routewatch/issues/233).
 - 2026-11-05: the prefix page lists the prefix's origin changes, newest first.
   The routing table records each change, and the prefix handler writes them to a
   new `origin_changes` table. The database maintainer prunes each prefix to its

cmd/asinfo-gen/main_test.go

@@ -12,7 +12,7 @@ import (
 
 // parseTimeLimit is how long a test waits for parseCSV to return before it
 // fails.
-const parseTimeLimit = 2 * time.Second
+const parseTimeLimit = 15 * time.Second
 
 // TestParseCSVReadsTodaysLayout parses an as.csv with the country code column
 // that the source added after the description. It expects each AS with its

go.mod

@@ -8,11 +8,15 @@ require (
 	github.com/go-chi/chi/v5 v5.2.2
 	github.com/google/btree v1.1.3
 	github.com/google/uuid v1.6.0
+	github.com/hashicorp/golang-lru/v2 v2.0.7
 	github.com/mattn/go-sqlite3 v1.14.29
+	github.com/maxmind/mmdbwriter v1.2.0
+	github.com/miekg/dns v1.1.73
+	github.com/oschwald/maxminddb-golang/v2 v2.9.0
 	github.com/rcrowley/go-metrics v0.0.0-20250401214520-65e299d6c5c9
 	go.uber.org/fx v1.24.0
 	go4.org/netipx v0.0.0-20260823151212-3075585bcbeb
-	golang.org/x/term v0.33.0
+	golang.org/x/term v0.45.0
 	golang.org/x/text v0.43.0
 )
 
@@ -20,5 +24,6 @@ require (
 	go.uber.org/dig v1.19.0 // indirect
 	go.uber.org/multierr v1.10.0 // indirect
 	go.uber.org/zap v1.26.0 // indirect
-	golang.org/x/sys v0.34.0 // indirect
+	golang.org/x/net v0.57.0 // indirect
+	golang.org/x/sys v0.49.0 // indirect
 )

go.sum

@@ -1,7 +1,5 @@
 github.com/bits-and-blooms/bitset v1.26.0 h1:WPvcPZbP1yuKofmjs2SYIFO1EjzIGhCP9ducElLsh5Q=
 github.com/bits-and-blooms/bitset v1.26.0/go.mod h1:7hO7Gc7Pp1vODcmWvKMRA9BNmbv6a/7QIWpPxHddWR8=
-github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
-github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY=
 github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto=
 github.com/go-chi/chi/v5 v5.2.2 h1:CMwsvRVTbXVytCk1Wd72Zy1LAsAh9GxMmSNWLHCG618=
@@ -10,14 +8,20 @@ github.com/google/btree v1.1.3 h1:CVpQJjYgC4VbzxeGVHfvZrv1ctoYCAI8vbl07Fcxlyg=
 github.com/google/btree v1.1.3/go.mod h1:qOPhT0dTNdNzV6Z/lhRX0YXUafgPLFUh+gZMl761Gm4=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
+github.com/hashicorp/golang-lru/v2 v2.0.7 h1:a+bsQ5rvGLjzHuww6tVxozPZFVghXaHOwFs4luLUK2k=
+github.com/hashicorp/golang-lru/v2 v2.0.7/go.mod h1:QeFd9opnmA6QUJc5vARoKUSoFhyfM2/ZepoAG6RGpeM=
 github.com/mattn/go-sqlite3 v1.14.29 h1:1O6nRLJKvsi1H2Sj0Hzdfojwt8GiGKm+LOfLaBFaouQ=
 github.com/mattn/go-sqlite3 v1.14.29/go.mod h1:Uh1q+B4BYcTPb+yiD3kU8Ct7aC0hY9fxUwlHK0RXw+Y=
-github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
+github.com/maxmind/mmdbwriter v1.2.0 h1:hyvDopImmgvle3aR8AaddxXnT0iQH2KWJX3vNfkwzYM=
-github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/maxmind/mmdbwriter v1.2.0/go.mod h1:EQmKHhk2y9DRVvyNxwCLKC5FrkXZLx4snc5OlLY5XLE=
+github.com/miekg/dns v1.1.73 h1:uhT8nJxmTrPJYClxVxTCX+CVn6qnzSiybRk72Z6DgrE=
+github.com/miekg/dns v1.1.73/go.mod h1:RW2Obtfd5NZHvOFe3zYG0W8koWOQtAzyHaLo8vASBuQ=
+github.com/oschwald/maxminddb-golang/v2 v2.9.0 h1:YpIl3WoA9oIuNvqNaO/aD1N/7Ci2wOqoKH5GWo53H5Y=
+github.com/oschwald/maxminddb-golang/v2 v2.9.0/go.mod h1:3TxexMBcR0ss3SbyYvnqfsDzDjN4o1KCg/nTsaMAivU=
 github.com/rcrowley/go-metrics v0.0.0-20250401214520-65e299d6c5c9 h1:bsUq1dX0N8AOIL7EB/X911+m4EHsnWEHeJ0c+3TTBrg=
 github.com/rcrowley/go-metrics v0.0.0-20250401214520-65e299d6c5c9/go.mod h1:bCqnVzQkZxMG4s8nGwiZ5l3QUCyqpo9Y+/ZMZ9VjZe4=
-github.com/stretchr/testify v1.8.1 h1:w7B6lhMri9wdJUVmEZPGGhZzrYTPvgJArz7wNPgYKsk=
+github.com/stretchr/testify v1.12.1 h1:EuwCh5fleGS7H32xRwO3wRGT7DxrDhLAT6FF8MpWDWE=
-github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
+github.com/stretchr/testify v1.12.1/go.mod h1:MDEgiDPPsNp5cuIrHPPCyornHKgEVbtFUmoNlxoYthg=
 go.uber.org/dig v1.19.0 h1:BACLhebsYdpQ7IROQ1AGPjrXcP5dF80U3gKoFzbaq/4=
 go.uber.org/dig v1.19.0/go.mod h1:Us0rSJiThwCv2GteUN0Q7OKvU7n5J4dxZ9JKUXozFdE=
 go.uber.org/fx v1.24.0 h1:wE8mruvpg2kiiL1Vqd0CC+tr0/24XIB10Iwp2lLWzkg=
@@ -28,12 +32,18 @@ go.uber.org/multierr v1.10.0 h1:S0h4aNzvfcFsC3dRF1jLoaov7oRaKqRGC/pUEJ2yvPQ=
 go.uber.org/multierr v1.10.0/go.mod h1:20+QtiLqy0Nd6FdQB9TLXag12DsQkrbs3htMFfDN80Y=
 go.uber.org/zap v1.26.0 h1:sI7k6L95XOKS281NhVKOFCUNIvv9e0w4BF8N3u+tCRo=
 go.uber.org/zap v1.26.0/go.mod h1:dtElttAiwGvoJ/vj4IwHBS/gXsEu/pZ50mUIRWuG0so=
+go.yaml.in/yaml/v3 v3.0.5 h1:N6y/pJk8buWs9NY5ERU2HSMfm+IuD/OtfdAnq6kESPw=
+go.yaml.in/yaml/v3 v3.0.5/go.mod h1:HVTZu1O7/Vkt2N+BFy8Zza+lnLsABggaTM2ZpNIGuKg=
 go4.org/netipx v0.0.0-20260823151212-3075585bcbeb h1:XBM4hvfwGAttkkiTIFfeigdfcL1xIfdKXqFdgiHGtDs=
 go4.org/netipx v0.0.0-20260823151212-3075585bcbeb/go.mod h1:PLyyIXexvUFg3Owu6p/WfdlivPbZJsZdgWZlrGope/Y=
-golang.org/x/sys v0.34.0 h1:H5Y5sJ2L2JRdyv7ROF1he/lPdvFsd0mJHFw2ThKHxLA=
+golang.org/x/net v0.57.0 h1:K5+3DljvIuDG9/Jv9rvyMywYNFCQ9RSUY6OOTTkT+tE=
-golang.org/x/sys v0.34.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
+golang.org/x/net v0.57.0/go.mod h1:KpXc8iv+r3XplLAG/f7Jsf9RPszJzdR0f58q9vGOuEU=
-golang.org/x/term v0.33.0 h1:NuFncQrRcaRvVmgRkvM3j/F00gWIAlcmlB8ACEKmGIg=
+golang.org/x/sync v0.24.0 h1:iqiDrGoDgyuvAKrhLQthUEzU/R378N78gXbBjxed7oA=
-golang.org/x/term v0.33.0/go.mod h1:s18+ql9tYWp1IfpV9DmCtQDDSRBUjKaw9M1eAv5UeF0=
+golang.org/x/sync v0.24.0/go.mod h1:sUUOizhqBxiL6pEWpqNLUiaJn1ShEbZ6BBqskPbjZm0=
+golang.org/x/sys v0.49.0 h1:XbzkgYJHdqh/8m2Uu0W/dQv8nktxx4BFHp1M0gROTXA=
+golang.org/x/sys v0.49.0/go.mod h1:hNLxWAXmnKAxqDtdwIYC4bM9oQPEecfsnNMuSxOs3og=
+golang.org/x/term v0.45.0 h1:NwWyBmoJCbfTHpxrWoZ9C6/VxOf7ic219I8xZZFdrf0=
+golang.org/x/term v0.45.0/go.mod h1:9aqxs0blBcrm/n0L9QW0aRVD+ktan8ssZromtqJC43w=
 golang.org/x/text v0.43.0 h1:1QivrlhwAsnMOcqgOdl9my7s9OyZl8O5/UGUTJVXoWc=
 golang.org/x/text v0.43.0/go.mod h1:hbSIYA/amXcRXTFSZqh8tWHEoqRvvbKPJ2uz/KU+a+s=
 gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=

internal/blocklist/blocklist_internal_test.go

@@ -1,494 +0,0 @@
-package blocklist
-
-import (
-	"context"
-	"errors"
-	"io"
-	"io/fs"
-	"log/slog"
-	"net/http"
-	"net/http/httptest"
-	"net/netip"
-	"os"
-	"path/filepath"
-	"strings"
-	"sync"
-	"testing"
-	"time"
-)
-
-// The test list's name and description, the address its good version lists,
-// and the address a newer version lists instead.
-const (
-	testListName        = "test_list"
-	testListDescription = "On the test list"
-	listedAddr          = "192.0.2.1"
-	goodListBody        = "# A test list\n" + listedAddr + "\n"
-	newListedAddr       = "192.0.2.2"
-	newListBody         = "# A test list\n" + newListedAddr + "\n"
-)
-
-// testETag is the ETag a publisher sends with a version of the test list.
-const testETag = `"v1"`
-
-// maxWait is how long a test waits for the download goroutine.
-const maxWait = 10 * time.Second
-
-// publisher stands in for a list's publisher. It answers every request with
-// its status and body, and keeps the headers of each request. A 200 answer
-// carries lastModified and etag, when set, as Last-Modified and ETag. As
-// from a real publisher, a request whose If-None-Match or If-Modified-Since
-// matches them is answered "not modified".
-type publisher struct {
-	mu           sync.Mutex
-	status       int
-	body         string
-	lastModified time.Time
-	etag         string
-	headers      []http.Header
-}
-
-// newPublisher starts a publisher that answers 200 with body, and returns it
-// and its URL.
-func newPublisher(t *testing.T, body string) (*publisher, string) {
-	t.Helper()
-
-	p := &publisher{status: http.StatusOK, body: body}
-	srv := httptest.NewServer(p)
-	t.Cleanup(srv.Close)
-
-	return p, srv.URL
-}
-
-func (p *publisher) ServeHTTP(w http.ResponseWriter, r *http.Request) {
-	p.mu.Lock()
-	defer p.mu.Unlock()
-
-	p.headers = append(p.headers, r.Header.Clone())
-
-	if p.status != http.StatusOK {
-		w.WriteHeader(p.status)
-		_, _ = io.WriteString(w, p.body)
-
-		return
-	}
-
-	if p.etag != "" {
-		w.Header().Set(etagHeader, p.etag)
-	}
-
-	// ServeContent sends Last-Modified unless lastModified is zero, and
-	// answers "not modified" when the request's conditions match.
-	http.ServeContent(w, r, testListName, p.lastModified,
-		strings.NewReader(p.body))
-}
-
-// answer makes the publisher answer later requests with status and body.
-func (p *publisher) answer(status int, body string) {
-	p.mu.Lock()
-	defer p.mu.Unlock()
-
-	p.status, p.body = status, body
-}
-
-// publish makes the publisher answer later requests with a version of the
-// list: body, with lastModified and etag. A zero lastModified or an empty
-// etag is not sent.
-func (p *publisher) publish(body string, lastModified time.Time, etag string) {
-	p.mu.Lock()
-	defer p.mu.Unlock()
-
-	p.status, p.body = http.StatusOK, body
-	p.lastModified, p.etag = lastModified, etag
-}
-
-// requests returns the headers of the requests the publisher has had.
-func (p *publisher) requests() []http.Header {
-	p.mu.Lock()
-	defer p.mu.Unlock()
-
-	return append([]http.Header(nil), p.headers...)
-}
-
-// testList returns a list served at url, written in format.
-func testList(url string, format Format) List {
-	return List{
-		Name:        testListName,
-		Description: testListDescription,
-		URL:         url,
-		Interval:    time.Hour,
-		Format:      format,
-	}
-}
-
-func newTestBlocklists(dir string, list List) *Blocklists {
-	return New(Params{
-		Dir:    dir,
-		Lists:  []List{list},
-		Logger: slog.New(slog.DiscardHandler),
-	})
-}
-
-// lookup looks addr up in b.
-func lookup(t *testing.T, b *Blocklists, addr string) []Listing {
-	t.Helper()
-
-	return b.Lookup(netip.MustParseAddr(addr))
-}
-
-// TestLookupFindsListedAddresses downloads a list in each format and looks
-// up addresses on it, inside its networks, and off it, in IPv4 and IPv6.
-// A listed address has one listing that names the list; any other has an
-// empty list of listings.
-func TestLookupFindsListedAddresses(t *testing.T) {
-	t.Parallel()
-
-	tests := []struct {
-		name     string
-		format   Format
-		body     string
-		listed   []string
-		unlisted []string
-	}{
-		{
-			name:     "single addresses",
-			format:   FormatLines,
-			body:     "# comment\n192.0.2.1\n\n2001:db8::1\n",
-			listed:   []string{"192.0.2.1", "::ffff:192.0.2.1", "2001:db8::1"},
-			unlisted: []string{"192.0.2.2", "2001:db8::2"},
-		},
-		{
-			name:     "networks",
-			format:   FormatLines,
-			body:     "# comment\n198.51.100.0/24\n2001:db8:1::/48\n",
-			listed:   []string{"198.51.100.0", "198.51.100.255", "2001:db8:1::5"},
-			unlisted: []string{"198.51.101.0", "2001:db8:2::1"},
-		},
-		{
-			name:   "Spamhaus networks",
-			format: FormatSpamhausJSON,
-			body: `{"cidr":"203.0.113.0/25","sblid":"SBL1","rir":"arin"}` + "\n" +
-				`{"cidr":"2001:db8:3::/48","sblid":"SBL2","rir":"ripencc"}` + "\n" +
-				`{"type":"metadata","timestamp":1793074442,"records":2}` + "\n",
-			listed:   []string{"203.0.113.1", "2001:db8:3::1"},
-			unlisted: []string{"203.0.113.200", "2001:db8:4::1"},
-		},
-		{
-			name:   "DShield networks",
-			format: FormatDShield,
-			body: "#   DShield.org Recommended Block List\n" +
-				"192.0.2.0\t192.0.2.255\t24\t327\tEXAMPLE\tUS\tNone\n",
-			listed:   []string{"192.0.2.0", "192.0.2.77"},
-			unlisted: []string{"192.0.3.1", "2001:db8::1"},
-		},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			t.Parallel()
-
-			_, url := newPublisher(t, tt.body)
-			b := newTestBlocklists(t.TempDir(), testList(url, tt.format))
-
-			err := b.download(t.Context(), b.lists[0])
-			if err != nil {
-				t.Fatalf("download: %v", err)
-			}
-
-			for _, addr := range tt.listed {
-				listings := lookup(t, b, addr)
-				if len(listings) != 1 || listings[0].Name != testListName ||
-					listings[0].Description != testListDescription ||
-					listings[0].Updated.IsZero() {
-					t.Errorf("%s: listings %+v, want one for %s", addr,
-						listings, testListName)
-				}
-			}
-
-			for _, addr := range tt.unlisted {
-				listings := lookup(t, b, addr)
-				if listings == nil || len(listings) != 0 {
-					t.Errorf("%s: listings %#v, want an empty list", addr, listings)
-				}
-			}
-		})
-	}
-}
-
-// TestFailedDownloadKeepsThePreviousCopy downloads a good version of a list,
-// then one that fails. The good copy stays in memory and on disk, and no
-// part of the failed download is left beside it.
-func TestFailedDownloadKeepsThePreviousCopy(t *testing.T) {
-	t.Parallel()
-
-	tests := []struct {
-		name   string
-		status int
-		body   string
-	}{
-		{"server error", http.StatusInternalServerError, "unavailable"},
-		{"not a list", http.StatusOK, "<!DOCTYPE html>\n<html></html>\n"},
-		{
-			"over the size limit", http.StatusOK,
-			strings.Repeat(listedAddr+"\n", maxDownloadSize/len(listedAddr)),
-		},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			t.Parallel()
-
-			dir := t.TempDir()
-			p, url := newPublisher(t, goodListBody)
-			b := newTestBlocklists(dir, testList(url, FormatLines))
-
-			err := b.download(t.Context(), b.lists[0])
-			if err != nil {
-				t.Fatalf("first download: %v", err)
-			}
-
-			before := lookup(t, b, listedAddr)
-
-			p.answer(tt.status, tt.body)
-
-			err = b.download(t.Context(), b.lists[0])
-			if err == nil {
-				t.Fatal("second download returned no error")
-			}
-
-			after := lookup(t, b, listedAddr)
-			if len(after) != 1 || len(before) != 1 ||
-				!after[0].Updated.Equal(before[0].Updated) {
-				t.Errorf("listings %+v after the failure, want %+v", after, before)
-			}
-
-			copies := os.DirFS(dir)
-
-			onDisk, err := fs.ReadFile(copies, testListName)
-			if err != nil || string(onDisk) != goodListBody {
-				t.Errorf("copy on disk %q (%v), want %q", onDisk, err, goodListBody)
-			}
-
-			_, err = fs.Stat(copies, testListName+downloadSuffix)
-			if !errors.Is(err, fs.ErrNotExist) {
-				t.Errorf("the failed download's file is still there (%v)", err)
-			}
-		})
-	}
-}
-
-// TestRestartLoadsCopiesFromDisk downloads a list, then starts a new
-// Blocklists on the same directory, as a restart does. The new one answers
-// from the copy on disk at once, and does not download the list again while
-// the copy is younger than the list's interval.
-func TestRestartLoadsCopiesFromDisk(t *testing.T) {
-	t.Parallel()
-
-	dir := t.TempDir()
-	p, url := newPublisher(t, goodListBody)
-	list := testList(url, FormatLines)
-
-	first := newTestBlocklists(dir, list)
-
-	err := first.download(t.Context(), list)
-	if err != nil {
-		t.Fatalf("download: %v", err)
-	}
-
-	downloaded := lookup(t, first, listedAddr)[0].Updated
-
-	second := newTestBlocklists(dir, list)
-	second.Start(t.Context())
-	second.Stop(t.Context())
-
-	listings := lookup(t, second, listedAddr)
-	if len(listings) != 1 ||
-		listings[0].Updated.Sub(downloaded).Abs() > time.Second {
-		t.Errorf("after the restart, listings %+v, want one updated at %s",
-			listings, downloaded)
-	}
-
-	if got := len(p.requests()); got != 1 {
-		t.Errorf("the publisher had %d requests, want 1", got)
-	}
-}
-
-// TestStartRefreshesAnOldCopy starts on a copy older than its list's
-// interval. The list is downloaded at once, with routewatch's User-Agent and
-// the Last-Modified and ETag the publisher sent with the copy, kept on disk.
-// The publisher answers that the copy is still current, so the copy is kept
-// and marked as updated now.
-func TestStartRefreshesAnOldCopy(t *testing.T) {
-	t.Parallel()
-
-	dir := t.TempDir()
-	p, url := newPublisher(t, goodListBody)
-	list := testList(url, FormatLines)
-
-	lastModified := time.Now().Add(-3 * list.Interval).UTC().Truncate(time.Second)
-	p.publish(goodListBody, lastModified, testETag)
-
-	err := newTestBlocklists(dir, list).download(t.Context(), list)
-	if err != nil {
-		t.Fatalf("download: %v", err)
-	}
-
-	old := time.Now().Add(-2 * list.Interval).UTC().Truncate(time.Second)
-
-	err = os.Chtimes(filepath.Join(dir, testListName), old, old)
-	if err != nil {
-		t.Fatalf("Chtimes: %v", err)
-	}
-
-	b := newTestBlocklists(dir, list)
-	b.Start(t.Context())
-
-	deadline := time.Now().Add(maxWait)
-	for !lookup(t, b, listedAddr)[0].Updated.After(old) {
-		if time.Now().After(deadline) {
-			t.Fatalf("the copy was not marked updated within %s", maxWait)
-		}
-
-		time.Sleep(time.Millisecond)
-	}
-
-	b.Stop(t.Context())
-
-	requests := p.requests()
-	last := requests[len(requests)-1]
-
-	want := lastModified.Format(http.TimeFormat)
-	if got := last.Get(ifModifiedSinceHeader); got != want {
-		t.Errorf("If-Modified-Since %q, want %q", got, want)
-	}
-
-	if got := last.Get(ifNoneMatchHeader); got != testETag {
-		t.Errorf("If-None-Match %q, want %q", got, testETag)
-	}
-
-	if got := last.Get(userAgentHeader); got != userAgent {
-		t.Errorf("User-Agent %q, want %q", got, userAgent)
-	}
-}
-
-// TestNewVersionOlderThanTheLastDownloadReplacesTheCopy downloads a list.
-// The publisher then puts out a new version whose Last-Modified is earlier
-// than that download, as when a cache in front of the publisher passes the
-// version on late. The next download sends the Last-Modified of the copy,
-// not the time of the download, so it gets the new version.
-func TestNewVersionOlderThanTheLastDownloadReplacesTheCopy(t *testing.T) {
-	t.Parallel()
-
-	p, url := newPublisher(t, goodListBody)
-	list := testList(url, FormatLines)
-	b := newTestBlocklists(t.TempDir(), list)
-
-	firstVersion := time.Now().Add(-2 * list.Interval).UTC().Truncate(time.Second)
-	p.publish(goodListBody, firstVersion, "")
-
-	err := b.download(t.Context(), list)
-	if err != nil {
-		t.Fatalf("first download: %v", err)
-	}
-
-	p.publish(newListBody, firstVersion.Add(list.Interval), "")
-
-	err = b.download(t.Context(), list)
-	if err != nil {
-		t.Fatalf("second download: %v", err)
-	}
-
-	if listings := lookup(t, b, newListedAddr); len(listings) != 1 {
-		t.Errorf("%s: listings %+v, want one from the new version",
-			newListedAddr, listings)
-	}
-
-	want := firstVersion.Format(http.TimeFormat)
-	if got := p.requests()[1].Get(ifModifiedSinceHeader); got != want {
-		t.Errorf("If-Modified-Since %q, want %q", got, want)
-	}
-}
-
-// TestDownloadWithoutLastModifiedOrETagSendsNoCondition downloads a list
-// twice from a publisher that sends neither Last-Modified nor ETag. Neither
-// request carries If-Modified-Since or If-None-Match, so the second download
-// gets the whole list again.
-func TestDownloadWithoutLastModifiedOrETagSendsNoCondition(t *testing.T) {
-	t.Parallel()
-
-	p, url := newPublisher(t, goodListBody)
-	list := testList(url, FormatLines)
-	b := newTestBlocklists(t.TempDir(), list)
-
-	err := b.download(t.Context(), list)
-	if err != nil {
-		t.Fatalf("first download: %v", err)
-	}
-
-	err = b.download(t.Context(), list)
-	if err != nil {
-		t.Fatalf("second download: %v", err)
-	}
-
-	for i, request := range p.requests() {
-		if request.Get(ifModifiedSinceHeader) != "" ||
-			request.Get(ifNoneMatchHeader) != "" {
-			t.Errorf("request %d has a condition: %v", i, request)
-		}
-	}
-}
-
-// TestStopCancelsADownloadInProgress stops while the publisher has not
-// answered. Stop cancels the download and returns once the download
-// goroutine has stopped.
-func TestStopCancelsADownloadInProgress(t *testing.T) {
-	t.Parallel()
-
-	arrived := make(chan struct{})
-
-	var once sync.Once
-
-	srv := httptest.NewServer(http.HandlerFunc(
-		func(_ http.ResponseWriter, r *http.Request) {
-			once.Do(func() { close(arrived) })
-			<-r.Context().Done()
-		}))
-	t.Cleanup(srv.Close)
-
-	b := newTestBlocklists(t.TempDir(), testList(srv.URL, FormatLines))
-	b.Start(t.Context())
-
-	select {
-	case <-arrived:
-	case <-time.After(maxWait):
-		t.Fatalf("no download began within %s", maxWait)
-	}
-
-	ctx, cancel := context.WithTimeout(t.Context(), maxWait)
-	defer cancel()
-
-	b.Stop(ctx)
-
-	select {
-	case <-b.done:
-	default:
-		t.Error("Stop returned before the download goroutine stopped")
-	}
-}
-
-// TestPublicListsAreComplete checks that every public list has what a
-// download and a lookup answer need, and a unique name.
-func TestPublicListsAreComplete(t *testing.T) {
-	t.Parallel()
-
-	names := make(map[string]bool)
-
-	for _, list := range Lists() {
-		if list.Name == "" || list.Description == "" || list.URL == "" ||
-			list.Interval <= 0 || names[list.Name] {
-			t.Errorf("list %+v is incomplete or has a name used before", list)
-		}
-
-		names[list.Name] = true
-	}
-}

internal/blocklist/lists.go

@@ -1,93 +0,0 @@
-package blocklist
-
-import "time"
-
-// How often each list is downloaded. No list is downloaded more often than
-// its publisher updates it or allows.
-const (
-	// DShield asks that its feeds be downloaded at most once an hour:
-	// https://isc.sans.edu/feeds_doc.html
-	dshieldInterval = time.Hour
-
-	// abuse.ch makes the list every 5 minutes and recommends a download at
-	// least every 15: https://feodotracker.abuse.ch/blocklist/
-	feodoTrackerInterval = 15 * time.Minute
-
-	// FireHOL's page for each list gives how often the list changes on
-	// average: about every 5 hours for abusers and every 3 hours for level
-	// 3. FireHOL sets no download limit.
-	// https://iplists.firehol.org/?ipset=firehol_abusers_30d
-	// https://iplists.firehol.org/?ipset=firehol_level3
-	fireHOLAbusersInterval = 5 * time.Hour
-	fireHOLLevel3Interval  = 3 * time.Hour
-
-	// Spamhaus asks that DROP be downloaded at most once a day:
-	// https://www.spamhaus.org/blocklists/do-not-route-or-peer/
-	spamhausDROPInterval = 24 * time.Hour
-
-	// Tor publishes a new exit list every hour and sets no download limit:
-	// https://collector.torproject.org/recent/exit-lists/
-	torExitsInterval = time.Hour
-)
-
-// Lists returns the public blocklists routewatch downloads. Each can be
-// downloaded whole without an account or a key. Spamhaus merged its EDROP
-// list into DROP, so DROP covers both.
-func Lists() []List {
-	return []List{
-		{
-			Name: "dshield",
-			Description: "In one of the 20 networks that DShield saw scan " +
-				"the most targets in the last three days",
-			URL:      "https://feeds.dshield.org/block.txt",
-			Interval: dshieldInterval,
-			Format:   FormatDShield,
-		},
-		{
-			Name:        "feodo_tracker",
-			Description: "A botnet command-and-control server",
-			URL:         "https://feodotracker.abuse.ch/downloads/ipblocklist.txt",
-			Interval:    feodoTrackerInterval,
-			Format:      FormatLines,
-		},
-		{
-			Name: "firehol_abusers_30d",
-			Description: "Reported for comment, form or forum spam in the " +
-				"last 30 days",
-			URL:      "https://iplists.firehol.org/files/firehol_abusers_30d.netset",
-			Interval: fireHOLAbusersInterval,
-			Format:   FormatLines,
-		},
-		{
-			Name: "firehol_level3",
-			Description: "Reported for attacks, spyware or viruses in the " +
-				"last 30 days",
-			URL:      "https://iplists.firehol.org/files/firehol_level3.netset",
-			Interval: fireHOLLevel3Interval,
-			Format:   FormatLines,
-		},
-		{
-			Name: "spamhaus_drop",
-			Description: "In an IPv4 network that Spamhaus says spammers " +
-				"or cyber criminals have hijacked or lease",
-			URL:      "https://www.spamhaus.org/drop/drop_v4.json",
-			Interval: spamhausDROPInterval,
-			Format:   FormatSpamhausJSON,
-		},
-		{
-			Name: "spamhaus_dropv6",
-			Description: "In an IPv6 network that Spamhaus says spammers " +
-				"or cyber criminals have hijacked or lease",
-			URL:      "https://www.spamhaus.org/drop/drop_v6.json",
-			Interval: spamhausDROPInterval,
-			Format:   FormatSpamhausJSON,
-		},
-		{
-			Name:        "tor_exits",
-			Description: "A Tor exit node, where traffic from the Tor network leaves",
-			URL:         "https://check.torproject.org/torbulkexitlist",
-			Interval:    torExitsInterval,
-			Format:      FormatLines,
-		},
-	}
-}

internal/blocklist/parse.go

@@ -1,158 +0,0 @@
-package blocklist
-
-import (
-	"bufio"
-	"encoding/json"
-	"errors"
-	"fmt"
-	"io"
-	"net/netip"
-	"strings"
-
-	"go4.org/netipx"
-)
-
-const (
-	// commentPrefix starts a comment line in a list file.
-	commentPrefix = "#"
-
-	// networkSeparator separates the address and the mask length of a
-	// network, as in 192.0.2.0/24.
-	networkSeparator = "/"
-
-	// dshieldFieldSeparator separates the fields of a DShield line.
-	dshieldFieldSeparator = "\t"
-
-	// spamhausMetadataType is the type of the line that ends a Spamhaus
-	// file. That line holds the file's metadata and no network.
-	spamhausMetadataType = "metadata"
-)
-
-var (
-	errUnknownFormat = errors.New("unknown list format")
-	errNoNetwork     = errors.New("no network on the line")
-	errBadRange      = errors.New("first and last address make no range")
-)
-
-// parse reads a list file written in format and returns the addresses it
-// holds. A line it cannot read fails the whole file, so a file that is not
-// the list, such as an error page, never replaces a good copy.
-func parse(r io.Reader, format Format) (*netipx.IPSet, error) {
-	var builder netipx.IPSetBuilder
-
-	scanner := bufio.NewScanner(r)
-
-	for lineNumber := 1; scanner.Scan(); lineNumber++ {
-		line := strings.TrimSpace(scanner.Text())
-		if line == "" || strings.HasPrefix(line, commentPrefix) {
-			continue
-		}
-
-		err := addLine(&builder, line, format)
-		if err != nil {
-			return nil, fmt.Errorf("line %d: %w", lineNumber, err)
-		}
-	}
-
-	err := scanner.Err()
-	if err != nil {
-		return nil, err
-	}
-
-	return builder.IPSet()
-}
-
-// addLine adds the address or network on one line of a list file to builder.
-func addLine(builder *netipx.IPSetBuilder, line string, format Format) error {
-	switch format {
-	case FormatLines:
-		return addAddressOrNetwork(builder, line)
-	case FormatSpamhausJSON:
-		return addSpamhausNetwork(builder, line)
-	case FormatDShield:
-		return addDShieldNetwork(builder, line)
-	default:
-		return errUnknownFormat
-	}
-}
-
-// addAddressOrNetwork adds an address, such as 192.0.2.1, or a network, such
-// as 192.0.2.0/24, to builder.
-func addAddressOrNetwork(builder *netipx.IPSetBuilder, text string) error {
-	if strings.Contains(text, networkSeparator) {
-		network, err := netip.ParsePrefix(text)
-		if err != nil {
-			return err
-		}
-
-		builder.AddPrefix(network)
-
-		return nil
-	}
-
-	addr, err := netip.ParseAddr(text)
-	if err != nil {
-		return err
-	}
-
-	builder.Add(addr)
-
-	return nil
-}
-
-// addSpamhausNetwork adds the network on a line of a Spamhaus file to
-// builder. The metadata line adds nothing.
-func addSpamhausNetwork(builder *netipx.IPSetBuilder, line string) error {
-	var entry struct {
-		CIDR string `json:"cidr"`
-		Type string `json:"type"`
-	}
-
-	err := json.Unmarshal([]byte(line), &entry)
-	if err != nil {
-		return err
-	}
-
-	if entry.Type == spamhausMetadataType {
-		return nil
-	}
-
-	network, err := netip.ParsePrefix(entry.CIDR)
-	if err != nil {
-		return err
-	}
-
-	builder.AddPrefix(network)
-
-	return nil
-}
-
-// addDShieldNetwork adds the network on a line of a DShield file to builder.
-// The line's first two fields are the network's first and last address.
-func addDShieldNetwork(builder *netipx.IPSetBuilder, line string) error {
-	firstField, rest, found := strings.Cut(line, dshieldFieldSeparator)
-	if !found {
-		return errNoNetwork
-	}
-
-	lastField, _, _ := strings.Cut(rest, dshieldFieldSeparator)
-
-	first, err := netip.ParseAddr(firstField)
-	if err != nil {
-		return err
-	}
-
-	last, err := netip.ParseAddr(lastField)
-	if err != nil {
-		return err
-	}
-
-	network := netipx.IPRangeFrom(first, last)
-	if !network.IsValid() {
-		return errBadRange
-	}
-
-	builder.AddRange(network)
-
-	return nil
-}

internal/bogon/bogon.go

@@ -1,5 +1,5 @@
-// Package bogon tells whether a prefix or an AS number is reserved: set aside
+// Package bogon tells whether a prefix, an address or an AS number is reserved:
-// for a special purpose, so that no network should announce it on the
+// set aside for a special purpose, so that no network should announce it on the
 // internet. A route is a bogon announcement when its prefix is reserved or its
 // origin AS is.
 //
@@ -42,6 +42,15 @@ func Prefix(prefix netip.Prefix) (string, bool) {
 	return holder.name + " (" + holder.prefix.String() + ")", true
 }
 
+// Addr returns why addr is reserved, and true, when it lies inside a reserved
+// block, as Prefix decides. An IPv4 address written in IPv6 form counts as the
+// IPv4 address it holds. It returns "" and false when addr is not reserved.
+func Addr(addr netip.Addr) (string, bool) {
+	addr = addr.Unmap()
+
+	return Prefix(netip.PrefixFrom(addr, addr.BitLen()))
+}
+
 // ASN returns why asn is reserved, and true, when it is. It returns "" and
 // false when asn is not reserved.
 func ASN(asn int) (string, bool) {

internal/bogon/bogon_test.go

@@ -8,6 +8,9 @@ import (
 	"git.eeqj.de/sneak/routewatch/internal/bogon"
 )
 
+// privateUseTen is why a prefix or an address inside 10.0.0.0/8 is reserved.
+const privateUseTen = "Private-Use (10.0.0.0/8)"
+
 func TestPrefix(t *testing.T) {
 	t.Parallel()
 
@@ -16,8 +19,8 @@ func TestPrefix(t *testing.T) {
 		// want is why the prefix is reserved, or "" when it is not.
 		want string
 	}{
-		{"10.1.2.0/24", "Private-Use (10.0.0.0/8)"},
+		{"10.1.2.0/24", privateUseTen},
-		{"10.0.0.0/8", "Private-Use (10.0.0.0/8)"},
+		{"10.0.0.0/8", privateUseTen},
 		{"192.0.2.0/24", "Documentation (TEST-NET-1) (192.0.2.0/24)"},
 		{"2001:db8:1::/48", "Documentation (2001:db8::/32)"},
 		{"fd00::/8", "Unique-Local (fc00::/7)"},
@@ -56,6 +59,39 @@ func TestPrefix(t *testing.T) {
 	}
 }
 
+func TestAddr(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		addr string
+		// want is why the address is reserved, or "" when it is not.
+		want string
+	}{
+		{"10.0.0.1", privateUseTen},
+		{"fd00::1", "Unique-Local (fc00::/7)"},
+		// An IPv4 address written in IPv6 form counts as the IPv4 address.
+		{"::ffff:10.0.0.1", privateUseTen},
+		{"::ffff:8.8.8.8", ""},
+		// An address that may be announced, inside a reserved block.
+		{"192.0.0.9", ""},
+		// Addresses anyone may announce.
+		{"8.8.8.8", ""},
+		{"2001:4860:4860::8888", ""},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.addr, func(t *testing.T) {
+			t.Parallel()
+
+			reason, reserved := bogon.Addr(netip.MustParseAddr(tc.addr))
+			if reason != tc.want || reserved != (tc.want != "") {
+				t.Errorf("Addr(%s) = %q, %v; want %q", tc.addr, reason,
+					reserved, tc.want)
+			}
+		})
+	}
+}
+
 func TestASN(t *testing.T) {
 	t.Parallel()
 

internal/cachedb/cachedb.go

@@ -0,0 +1,51 @@
+// Package cachedb opens cache.db, the SQLite file in the state directory that
+// holds RouteWatch's caches of answers from outside services. It is separate
+// from the routes database so that a cache write never queues behind a write
+// to that database.
+package cachedb
+
+import (
+	"context"
+	"database/sql"
+	_ "embed" // for schema.sql
+	"fmt"
+	"path/filepath"
+
+	_ "github.com/mattn/go-sqlite3" // CGO SQLite driver
+)
+
+const (
+	// fileName is the database's file in the state directory.
+	fileName = "cache.db"
+
+	// busyTimeoutMs is how long a write waits for another write to finish.
+	busyTimeoutMs = 5000
+)
+
+//go:embed schema.sql
+var schema string
+
+// Open opens cache.db in stateDir, creating the file and its tables when they
+// do not exist. The caller closes the database.
+func Open(ctx context.Context, stateDir string) (*sql.DB, error) {
+	dsn := fmt.Sprintf(
+		"file:%s?_journal_mode=WAL&_synchronous=NORMAL&_busy_timeout=%d"+
+			"&_txlock=immediate",
+		filepath.Join(stateDir, fileName),
+		busyTimeoutMs,
+	)
+
+	db, err := sql.Open("sqlite3", dsn)
+	if err != nil {
+		return nil, fmt.Errorf("opening the cache database: %w", err)
+	}
+
+	_, err = db.ExecContext(ctx, schema)
+	if err != nil {
+		_ = db.Close()
+
+		return nil, fmt.Errorf("creating the cache database's tables: %w", err)
+	}
+
+	return db, nil
+}

internal/cachedb/cachedb_internal_test.go

@@ -0,0 +1,64 @@
+package cachedb
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+)
+
+// TestOpenCreatesTheFileInWALMode opens a new database, and then opens it
+// again, as a restart does.
+func TestOpenCreatesTheFileInWALMode(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+
+	for range 2 {
+		db, err := Open(t.Context(), dir)
+		if err != nil {
+			t.Fatalf("Open: %v", err)
+		}
+
+		var mode string
+
+		err = db.QueryRowContext(t.Context(), "PRAGMA journal_mode").Scan(&mode)
+		if err != nil {
+			t.Fatalf("reading the journal mode: %v", err)
+		}
+
+		if mode != "wal" {
+			t.Errorf("journal mode %q, want wal", mode)
+		}
+
+		var rows int
+
+		err = db.QueryRowContext(t.Context(),
+			"SELECT COUNT(*) FROM hostnames").Scan(&rows)
+		if err != nil {
+			t.Fatalf("reading the hostnames table: %v", err)
+		}
+
+		err = db.Close()
+		if err != nil {
+			t.Fatalf("Close: %v", err)
+		}
+	}
+
+	_, err := os.Stat(filepath.Join(dir, fileName))
+	if err != nil {
+		t.Errorf("the file is not in the state directory: %v", err)
+	}
+}
+
+// TestOpenFailsWhenTheDirectoryDoesNotExist checks that a state directory that
+// is not there is reported, not ignored.
+func TestOpenFailsWhenTheDirectoryDoesNotExist(t *testing.T) {
+	t.Parallel()
+
+	db, err := Open(t.Context(), filepath.Join(t.TempDir(), "missing"))
+	if err == nil {
+		_ = db.Close()
+
+		t.Fatal("Open succeeded in a directory that does not exist")
+	}
+}

internal/cachedb/schema.sql

@@ -0,0 +1,24 @@
+-- hostnames holds the PTR names of addresses. names has the names separated by
+-- spaces, and is empty for an address with no PTR names. expires_at is in
+-- seconds since 1970.
+CREATE TABLE IF NOT EXISTS hostnames (
+    address TEXT PRIMARY KEY,
+    names TEXT NOT NULL,
+    expires_at INTEGER NOT NULL
+);
+
+-- geolocations holds the answers of geojs. A part geojs does not know is NULL.
+-- fetched_at is in seconds since 1970.
+CREATE TABLE IF NOT EXISTS geolocations (
+    address TEXT PRIMARY KEY,
+    country_code TEXT,
+    country TEXT,
+    continent_code TEXT,
+    region TEXT,
+    city TEXT,
+    latitude REAL,
+    longitude REAL,
+    accuracy_radius_km INTEGER,
+    time_zone TEXT,
+    fetched_at INTEGER NOT NULL
+);

internal/database/database_internal_test.go

@@ -72,17 +72,34 @@ const (
 	// lockTestPrefix is the prefix the batch writes in the checkpoint tests
 	// store.
 	lockTestPrefix = "192.0.2.0/24"
+	// longBusyTimeoutMs is the busy timeout setLongBusyTimeout gives the
+	// writing connection. A checkpoint that waits for an open read takes this
+	// long.
+	longBusyTimeoutMs = 30000
 	// readerCheckpointLimit is how long a checkpoint, and a batch write
-	// waiting for it, may take while a reader is open: well under the busy
+	// waiting for it, may take while a reader is open: well under
-	// timeout, which a checkpoint that waits for the reader takes.
+	// longBusyTimeoutMs, with room for a stall on a busy host.
-	readerCheckpointLimit = time.Second
+	readerCheckpointLimit = 15 * time.Second
 	// truncateCheckpointLimit is how long a checkpoint of a WAL file over
 	// sqliteWALSizeLimitBytes may take to give up while a reader is open: its
-	// wait for the reader plus a second, well under the busy timeout.
+	// wait for the reader plus readerCheckpointLimit.
 	truncateCheckpointLimit = truncateBusyTimeoutMs*time.Millisecond +
-		time.Second
+		readerCheckpointLimit
 )
 
+// setLongBusyTimeout gives the writing connection of db longBusyTimeoutMs, so
+// that a checkpoint that waits for an open read takes far longer than a stall
+// on a busy host.
+func setLongBusyTimeout(ctx context.Context, t *testing.T, db *Database) {
+	t.Helper()
+
+	_, err := db.writer.ExecContext(ctx,
+		fmt.Sprintf("PRAGMA busy_timeout=%d", longBusyTimeoutMs))
+	if err != nil {
+		t.Fatalf("failed to set the busy timeout: %v", err)
+	}
+}
+
 // TestConnectionPoolPragmas holds several pooled connections open at once and
 // checks each one carries the per-connection settings from the DSN, plus the
 // process-wide heap limits, and sees the new file with auto_vacuum
@@ -579,6 +596,8 @@ func TestCheckpointDoesNotWaitForReader(t *testing.T) {
 	ctx := context.Background()
 	ts := time.Now().UTC()
 
+	setLongBusyTimeout(ctx, t, db)
+
 	err = db.UpdatePrefixesBatch(map[string]time.Time{"198.51.100.0/24": ts})
 	if err != nil {
 		t.Fatalf("failed to store the prefix the reader reads: %v", err)
@@ -690,6 +709,7 @@ func TestCheckpointEmptiesWALOnceNoReadIsOpen(t *testing.T) {
 	}
 
 	fillWALPastLimit(ctx, t, db)
+	setLongBusyTimeout(ctx, t, db)
 
 	started := time.Now()
 

internal/geo/cache.go

@@ -0,0 +1,253 @@
+package geo
+
+import (
+	"context"
+	"database/sql"
+	"errors"
+	"fmt"
+	"maps"
+	"time"
+)
+
+const (
+	// entryLifetime is how long a geojs answer is kept after its fetch.
+	entryLifetime = 7 * 24 * time.Hour
+
+	// flushInterval is how often new answers are written to cache.db.
+	flushInterval = 5 * time.Second
+
+	// sweepInterval is how often expired answers are deleted.
+	sweepInterval = 10 * time.Minute
+
+	// rowColumns are the columns of the geolocations table in the order
+	// scanRow reads them.
+	rowColumns = "address, country_code, country, continent_code, region, " +
+		"city, latitude, longitude, accuracy_radius_km, time_zone, fetched_at"
+)
+
+// rowScanner is the Scan method of *sql.Row and *sql.Rows.
+type rowScanner interface {
+	Scan(dest ...any) error
+}
+
+// cached returns the current answer held for address, from memory, then from
+// the answers waiting to be written, then from cache.db. It returns nil when
+// there is none.
+func (l *Locator) cached(ctx context.Context, address string) *Location {
+	found, ok := l.entries.Get(address)
+	if ok {
+		if !l.expired(found) {
+			return found
+		}
+
+		l.entries.Remove(address)
+	}
+
+	l.pendingMu.Lock()
+	waiting := l.pending[address]
+	l.pendingMu.Unlock()
+
+	if waiting != nil && !l.expired(waiting) {
+		l.entries.Add(address, waiting)
+
+		return waiting
+	}
+
+	stored, err := l.readRow(ctx, address)
+	if err != nil {
+		l.logger.Warn("Failed to read a geolocation cache row",
+			"address", address, "error", err)
+
+		return nil
+	}
+
+	if stored != nil {
+		l.entries.Add(address, stored)
+	}
+
+	return stored
+}
+
+// expired says whether the answer is at the end of its lifetime.
+func (l *Locator) expired(answer *Location) bool {
+	return !l.now().Before(answer.Updated.Add(entryLifetime))
+}
+
+// cutoff returns the fetch time at or before which an answer has expired.
+func (l *Locator) cutoff() int64 {
+	return l.now().Add(-entryLifetime).Unix()
+}
+
+// store keeps an answer in memory and queues it for cache.db. While cache.db
+// cannot be written, the queue stops growing at maxEntries answers.
+func (l *Locator) store(address string, answer *Location) {
+	l.entries.Add(address, answer)
+
+	l.pendingMu.Lock()
+	defer l.pendingMu.Unlock()
+
+	if len(l.pending) < l.maxEntries {
+		l.pending[address] = answer
+	}
+}
+
+// keepCache writes new answers and deletes expired ones until ctx ends.
+func (l *Locator) keepCache(ctx context.Context) {
+	flushes := time.NewTicker(flushInterval)
+	defer flushes.Stop()
+
+	sweeps := time.NewTicker(sweepInterval)
+	defer sweeps.Stop()
+
+	for {
+		select {
+		case <-ctx.Done():
+			l.flush(context.WithoutCancel(ctx))
+
+			return
+		case <-flushes.C:
+			l.flush(ctx)
+		case <-sweeps.C:
+			l.sweep(ctx)
+		}
+	}
+}
+
+// load reads the answers that have not expired into memory, at most maxEntries
+// of them, the newest last so that they are the last to be dropped.
+func (l *Locator) load(ctx context.Context) error {
+	rows, err := l.db.QueryContext(ctx,
+		"SELECT "+rowColumns+" FROM (SELECT "+rowColumns+" FROM geolocations "+
+			"WHERE fetched_at > ? ORDER BY fetched_at DESC LIMIT ?) "+
+			"ORDER BY fetched_at",
+		l.cutoff(), l.maxEntries)
+	if err != nil {
+		return fmt.Errorf("reading the geolocation cache: %w", err)
+	}
+
+	defer func() { _ = rows.Close() }()
+
+	for rows.Next() {
+		address, answer, err := scanRow(rows)
+		if err != nil {
+			return fmt.Errorf("reading a geolocation cache row: %w", err)
+		}
+
+		l.entries.Add(address, answer)
+	}
+
+	err = rows.Err()
+	if err != nil {
+		return fmt.Errorf("reading the geolocation cache: %w", err)
+	}
+
+	return nil
+}
+
+// readRow returns the current answer for address in cache.db, or nil when it
+// has none.
+func (l *Locator) readRow(
+	ctx context.Context, address string,
+) (*Location, error) {
+	row := l.db.QueryRowContext(ctx,
+		"SELECT "+rowColumns+" FROM geolocations "+
+			"WHERE address = ? AND fetched_at > ?",
+		address, l.cutoff())
+
+	_, answer, err := scanRow(row)
+	if errors.Is(err, sql.ErrNoRows) {
+		return nil, nil //nolint:nilnil // no row is not a failure
+	}
+
+	return answer, err
+}
+
+// scanRow reads one row of the geolocations table.
+func scanRow(row rowScanner) (string, *Location, error) {
+	var (
+		address string
+		fetched int64
+		answer  Location
+	)
+
+	err := row.Scan(&address, &answer.CountryCode, &answer.Country,
+		&answer.ContinentCode, &answer.Region, &answer.City, &answer.Latitude,
+		&answer.Longitude, &answer.AccuracyRadiusKm, &answer.TimeZone, &fetched)
+	if err != nil {
+		return "", nil, err
+	}
+
+	answer.Source = sourceGeoJS
+	answer.Updated = time.Unix(fetched, 0).UTC()
+
+	return address, &answer, nil
+}
+
+// flush writes the pending answers to cache.db. Those it cannot write stay
+// pending, unless a newer answer for the address has arrived meanwhile.
+func (l *Locator) flush(ctx context.Context) {
+	l.pendingMu.Lock()
+	batch := l.pending
+	l.pending = make(map[string]*Location)
+	l.pendingMu.Unlock()
+
+	if len(batch) == 0 {
+		return
+	}
+
+	err := l.writeRows(ctx, batch)
+	if err == nil {
+		return
+	}
+
+	l.logger.Error("Failed to write the geolocation cache", "error", err)
+
+	l.pendingMu.Lock()
+	defer l.pendingMu.Unlock()
+
+	maps.Insert(batch, maps.All(l.pending))
+	l.pending = batch
+}
+
+// writeRows writes batch to cache.db in one transaction.
+func (l *Locator) writeRows(
+	ctx context.Context, batch map[string]*Location,
+) error {
+	tx, err := l.db.BeginTx(ctx, nil)
+	if err != nil {
+		return err
+	}
+
+	defer func() { _ = tx.Rollback() }()
+
+	for address, answer := range batch {
+		_, err = tx.ExecContext(ctx,
+			"INSERT OR REPLACE INTO geolocations ("+rowColumns+") "+
+				"VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)",
+			address, answer.CountryCode, answer.Country, answer.ContinentCode,
+			answer.Region, answer.City, answer.Latitude, answer.Longitude,
+			answer.AccuracyRadiusKm, answer.TimeZone, answer.Updated.Unix())
+		if err != nil {
+			return err
+		}
+	}
+
+	return tx.Commit()
+}
+
+// sweep deletes the expired answers from memory and cache.db.
+func (l *Locator) sweep(ctx context.Context) {
+	for _, address := range l.entries.Keys() {
+		answer, ok := l.entries.Peek(address)
+		if ok && l.expired(answer) {
+			l.entries.Remove(address)
+		}
+	}
+
+	_, err := l.db.ExecContext(ctx,
+		"DELETE FROM geolocations WHERE fetched_at <= ?", l.cutoff())
+	if err != nil {
+		l.logger.Error("Failed to delete expired geolocation cache rows",
+			"error", err)
+	}
+}

internal/geo/database.go

@@ -0,0 +1,349 @@
+package geo
+
+import (
+	"compress/gzip"
+	"context"
+	"errors"
+	"fmt"
+	"io"
+	"io/fs"
+	"net/http"
+	"net/netip"
+	"os"
+	"path/filepath"
+	"time"
+
+	"github.com/oschwald/maxminddb-golang/v2"
+)
+
+const (
+	// DatabaseDownloadFormat is the URL of DB-IP's City Lite database, with %s
+	// for the year and month.
+	DatabaseDownloadFormat = "https://download.db-ip.com/free/" +
+		"dbip-city-lite-%s.mmdb.gz"
+
+	// databaseMonthFormat is the year and month in the URL.
+	databaseMonthFormat = "2006-01"
+
+	// databaseFileName is the copy of the database in the state directory.
+	databaseFileName = "dbip-city-lite.mmdb"
+
+	// databaseDownloadSuffix ends the name of the file a download is written
+	// to, until it has opened.
+	databaseDownloadSuffix = ".download"
+
+	// maxDatabaseSize is the largest database accepted once unpacked, in
+	// bytes.
+	maxDatabaseSize = 200 << 20
+
+	// databaseDownloadTimeout limits one download.
+	databaseDownloadTimeout = 10 * time.Minute
+
+	// databaseCheckInterval is how often RouteWatch checks whether a new
+	// month's database is due. A new month's file appears some time on the
+	// first of the month, so a failed download is tried again this much later.
+	databaseCheckInterval = time.Hour
+)
+
+var (
+	errDatabaseStatus  = errors.New("unexpected HTTP status from DB-IP")
+	errDatabaseTooLong = errors.New("database is over the size limit")
+)
+
+// dbipName is the part of a database record that holds an English name.
+type dbipName struct {
+	Names struct {
+		English string `maxminddb:"en"`
+	} `maxminddb:"names"`
+}
+
+// dbipRecord is the part of a database record RouteWatch reads.
+type dbipRecord struct {
+	City      dbipName `maxminddb:"city"`
+	Continent struct {
+		Code string `maxminddb:"code"`
+	} `maxminddb:"continent"`
+	Country struct {
+		dbipName
+
+		ISOCode string `maxminddb:"iso_code"`
+	} `maxminddb:"country"`
+	Location struct {
+		Latitude  *float64 `maxminddb:"latitude"`
+		Longitude *float64 `maxminddb:"longitude"`
+	} `maxminddb:"location"`
+	Subdivisions []dbipName `maxminddb:"subdivisions"`
+}
+
+// location returns the record as a Location fetched at the time given. The
+// first subdivision is the region. The database has no accuracy radius and no
+// time zone.
+func (r *dbipRecord) location(fetched time.Time) *Location {
+	found := &Location{
+		CountryCode:   nilIfEmpty(r.Country.ISOCode),
+		Country:       nilIfEmpty(r.Country.Names.English),
+		ContinentCode: nilIfEmpty(r.Continent.Code),
+		City:          nilIfEmpty(r.City.Names.English),
+		Latitude:      r.Location.Latitude,
+		Longitude:     r.Location.Longitude,
+		Source:        sourceDBIP,
+		Updated:       fetched,
+	}
+
+	if len(r.Subdivisions) > 0 {
+		found.Region = nilIfEmpty(r.Subdivisions[0].Names.English)
+	}
+
+	return found
+}
+
+// nilIfEmpty returns a pointer to text, or nil when text is empty.
+func nilIfEmpty(text string) *string {
+	if text == "" {
+		return nil
+	}
+
+	return &text
+}
+
+// fromDatabase returns where the copy of the database places addr. It returns
+// nil when there is no copy yet or the copy has no record for addr. It also
+// returns nil, and logs the error, when reading the copy fails.
+func (l *Locator) fromDatabase(addr netip.Addr) *Location {
+	l.databaseMu.RLock()
+	defer l.databaseMu.RUnlock()
+
+	if l.database == nil {
+		return nil
+	}
+
+	result := l.database.Lookup(addr)
+
+	err := result.Err()
+	if err != nil {
+		l.logger.Error("Failed to look up an address in the database",
+			"address", addr, "error", err)
+
+		return nil
+	}
+
+	if !result.Found() {
+		return nil
+	}
+
+	var record dbipRecord
+
+	err = result.Decode(&record)
+	if err != nil {
+		l.logger.Error("Failed to read a database record",
+			"address", addr, "error", err)
+
+		return nil
+	}
+
+	return record.location(l.databaseFetched)
+}
+
+// keepDatabaseCurrent downloads the database when it is due, at once and then
+// every databaseCheckInterval, until ctx ends.
+func (l *Locator) keepDatabaseCurrent(ctx context.Context) {
+	l.downloadDatabaseIfDue(ctx)
+
+	checks := time.NewTicker(databaseCheckInterval)
+	defer checks.Stop()
+
+	for {
+		select {
+		case <-ctx.Done():
+			return
+		case <-checks.C:
+			l.downloadDatabaseIfDue(ctx)
+		}
+	}
+}
+
+// downloadDatabaseIfDue downloads this month's database, unless the copy in
+// use was downloaded this month. A failure leaves the copy as it is.
+func (l *Locator) downloadDatabaseIfDue(ctx context.Context) {
+	now := l.now().UTC()
+
+	if !l.databaseDue(now) {
+		return
+	}
+
+	err := l.downloadDatabase(ctx, now)
+	if err != nil && ctx.Err() == nil {
+		l.logger.Error("Database download failed; keeping the previous copy",
+			"error", err)
+	}
+}
+
+// databaseDue says whether there is no open copy or it is from an earlier
+// month than now.
+func (l *Locator) databaseDue(now time.Time) bool {
+	l.databaseMu.RLock()
+	defer l.databaseMu.RUnlock()
+
+	return l.database == nil ||
+		l.databaseFetched.Format(databaseMonthFormat) !=
+			now.Format(databaseMonthFormat)
+}
+
+// downloadDatabase fetches the database of now's month. The file replaces the
+// copy, on disk and in use, only once it has opened.
+func (l *Locator) downloadDatabase(ctx context.Context, now time.Time) error {
+	ctx, cancel := context.WithTimeout(ctx, databaseDownloadTimeout)
+	defer cancel()
+
+	url := fmt.Sprintf(l.databaseURLFormat, now.Format(databaseMonthFormat))
+
+	request, err := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)
+	if err != nil {
+		return err
+	}
+
+	request.Header.Set(userAgentHeader, userAgent)
+
+	response, err := l.client.Do(request)
+	if err != nil {
+		return err
+	}
+
+	defer func() { _ = response.Body.Close() }()
+
+	if response.StatusCode != http.StatusOK {
+		return fmt.Errorf("%w: %s", errDatabaseStatus, response.Status)
+	}
+
+	return l.replaceDatabase(response.Body, now)
+}
+
+// replaceDatabase unpacks the gzip stream body beside the copy, then makes the
+// result the copy once it has opened. Whatever fails, the file it wrote is
+// removed and the copy stays.
+func (l *Locator) replaceDatabase(body io.Reader, now time.Time) error {
+	root, err := os.OpenRoot(l.dir)
+	if err != nil {
+		return err
+	}
+
+	defer func() { _ = root.Close() }()
+
+	downloadName := databaseFileName + databaseDownloadSuffix
+
+	err = unpackDatabase(root, downloadName, body, l.maxDatabaseBytes)
+	if err != nil {
+		_ = root.Remove(downloadName)
+
+		return err
+	}
+
+	opened, err := maxminddb.Open(filepath.Join(l.dir, downloadName))
+	if err != nil {
+		_ = root.Remove(downloadName)
+
+		return fmt.Errorf("opening the downloaded database: %w", err)
+	}
+
+	err = root.Rename(downloadName, databaseFileName)
+	if err != nil {
+		_ = opened.Close()
+		_ = root.Remove(downloadName)
+
+		return err
+	}
+
+	l.useDatabase(opened, now.Truncate(time.Second))
+	l.logger.Info("Downloaded a new copy of the database")
+
+	return nil
+}
+
+// unpackDatabase writes the gzip stream body to the file name in root, up to
+// limit bytes once unpacked.
+func unpackDatabase(
+	root *os.Root, name string, body io.Reader, limit int64,
+) error {
+	unpacked, err := gzip.NewReader(body)
+	if err != nil {
+		return fmt.Errorf("unpacking the database: %w", err)
+	}
+
+	f, err := root.Create(name)
+	if err != nil {
+		return err
+	}
+
+	defer func() { _ = f.Close() }()
+
+	written, err := io.Copy(f, io.LimitReader(unpacked, limit+1))
+	if err != nil {
+		return fmt.Errorf("unpacking the database: %w", err)
+	}
+
+	if written > limit {
+		return errDatabaseTooLong
+	}
+
+	return nil
+}
+
+// openDatabaseCopy opens the copy left by an earlier run, if there is one. A
+// copy that does not open is treated as no copy, so it is downloaded again.
+func (l *Locator) openDatabaseCopy() {
+	path := filepath.Join(l.dir, databaseFileName)
+
+	info, err := os.Stat(path)
+	if errors.Is(err, fs.ErrNotExist) {
+		return
+	}
+
+	if err != nil {
+		l.logger.Error("Failed to read the database copy", "error", err)
+
+		return
+	}
+
+	opened, err := maxminddb.Open(path)
+	if err != nil {
+		l.logger.Error("Failed to open the database copy", "error", err)
+
+		return
+	}
+
+	l.useDatabase(opened, info.ModTime().UTC().Truncate(time.Second))
+}
+
+// useDatabase makes opened the copy in use and closes the one it replaces.
+func (l *Locator) useDatabase(opened *maxminddb.Reader, fetched time.Time) {
+	l.databaseMu.Lock()
+	defer l.databaseMu.Unlock()
+
+	if l.database != nil {
+		err := l.database.Close()
+		if err != nil {
+			l.logger.Error("Failed to close the old database copy", "error", err)
+		}
+	}
+
+	l.database = opened
+	l.databaseFetched = fetched
+}
+
+// closeDatabase closes the copy in use, after which no source can answer from
+// it.
+func (l *Locator) closeDatabase() {
+	l.databaseMu.Lock()
+	defer l.databaseMu.Unlock()
+
+	if l.database == nil {
+		return
+	}
+
+	err := l.database.Close()
+	if err != nil {
+		l.logger.Error("Failed to close the database copy", "error", err)
+	}
+
+	l.database = nil
+}

internal/geo/geojs.go

@@ -0,0 +1,151 @@
+package geo
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"math"
+	"net/http"
+	"net/netip"
+	"strconv"
+	"strings"
+	"time"
+)
+
+const (
+	// GeoJSEndpoint is the URL of the geojs geo endpoint.
+	GeoJSEndpoint = "https://get.geojs.io/v1/ip/geo.json"
+
+	// geojsTimeLimit limits one request to geojs.
+	geojsTimeLimit = time.Second
+
+	// geojsAddressSeparator separates the addresses of one request.
+	geojsAddressSeparator = ","
+
+	// geojsUnknown is what geojs sends for a value it does not know.
+	geojsUnknown = "nil"
+
+	// maxGeoJSAnswerBytes is far more than an answer for the most addresses
+	// an IP lookup can ask about.
+	maxGeoJSAnswerBytes = 1 << 20
+)
+
+var errGeoJSStatus = errors.New("unexpected HTTP status from geojs")
+
+// geojsAnswer is one address's entry in an answer from geojs.
+//
+//nolint:tagliatelle // the keys geojs sends
+type geojsAnswer struct {
+	IP            string `json:"ip"`
+	CountryCode   string `json:"country_code"`
+	Country       string `json:"country"`
+	ContinentCode string `json:"continent_code"`
+	Region        string `json:"region"`
+	City          string `json:"city"`
+	Latitude      string `json:"latitude"`
+	Longitude     string `json:"longitude"`
+	Accuracy      *int   `json:"accuracy"`
+	TimeZone      string `json:"timezone"`
+}
+
+// askGeoJS asks geojs about addresses in one request, and returns its answers
+// by address. An address geojs left out, or gave no country, city or
+// coordinates for, has no entry.
+func (l *Locator) askGeoJS(
+	ctx context.Context, addresses []string,
+) (map[string]*Location, error) {
+	ctx, cancel := context.WithTimeout(ctx, l.timeLimit)
+	defer cancel()
+
+	// A comma and a colon are legal in a query, and the escaped forms are
+	// not what geojs documents.
+	url := l.geojsURL + "?ip=" + strings.Join(addresses, geojsAddressSeparator)
+
+	request, err := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)
+	if err != nil {
+		return nil, err
+	}
+
+	request.Header.Set(userAgentHeader, userAgent)
+
+	response, err := l.client.Do(request)
+	if err != nil {
+		return nil, err
+	}
+
+	defer func() { _ = response.Body.Close() }()
+
+	if response.StatusCode != http.StatusOK {
+		return nil, fmt.Errorf("%w: %d", errGeoJSStatus, response.StatusCode)
+	}
+
+	var parsed []geojsAnswer
+
+	err = json.NewDecoder(io.LimitReader(response.Body, maxGeoJSAnswerBytes)).
+		Decode(&parsed)
+	if err != nil {
+		return nil, fmt.Errorf("reading the geojs answer: %w", err)
+	}
+
+	fetched := l.now().UTC().Truncate(time.Second)
+	answers := make(map[string]*Location, len(parsed))
+
+	for _, answer := range parsed {
+		addr, err := netip.ParseAddr(answer.IP)
+		if err != nil {
+			continue
+		}
+
+		location := answer.location(fetched)
+		if hasLocation(location) {
+			answers[plainAddress(addr)] = location
+		}
+	}
+
+	return answers, nil
+}
+
+// hasLocation says whether found has a country, a city or a coordinate.
+func hasLocation(found *Location) bool {
+	return found.CountryCode != nil || found.Country != nil ||
+		found.City != nil || found.Latitude != nil || found.Longitude != nil
+}
+
+// location returns the answer as a Location fetched at the time given.
+func (a geojsAnswer) location(fetched time.Time) *Location {
+	return &Location{
+		CountryCode:      knownText(a.CountryCode),
+		Country:          knownText(a.Country),
+		ContinentCode:    knownText(a.ContinentCode),
+		Region:           knownText(a.Region),
+		City:             knownText(a.City),
+		Latitude:         knownNumber(a.Latitude),
+		Longitude:        knownNumber(a.Longitude),
+		AccuracyRadiusKm: a.Accuracy,
+		TimeZone:         knownText(a.TimeZone),
+		Source:           sourceGeoJS,
+		Updated:          fetched,
+	}
+}
+
+// knownText returns a pointer to text, or nil when geojs does not know it.
+func knownText(text string) *string {
+	if text == "" || text == geojsUnknown {
+		return nil
+	}
+
+	return &text
+}
+
+// knownNumber returns text as a number, or nil when geojs does not know it. NaN
+// and infinity parse, but JSON cannot carry them.
+func knownNumber(text string) *float64 {
+	number, err := strconv.ParseFloat(text, 64)
+	if err != nil || math.IsNaN(number) || math.IsInf(number, 0) {
+		return nil
+	}
+
+	return &number
+}

internal/geo/locator.go

@@ -0,0 +1,232 @@
+// Package geo finds where IP addresses are. It asks geojs.io, and keeps those
+// answers in memory and in cache.db. When geojs.io gives no location for an
+// address, it reads a copy of DB-IP's City Lite database, which it downloads
+// once a month.
+package geo
+
+import (
+	"context"
+	"database/sql"
+	"fmt"
+	"log/slog"
+	"net/http"
+	"net/netip"
+	"sync"
+	"time"
+
+	lru "github.com/hashicorp/golang-lru/v2"
+	"github.com/oschwald/maxminddb-golang/v2"
+)
+
+// The values of Location.Source.
+const (
+	sourceGeoJS = "geojs"
+	sourceDBIP  = "dbip"
+)
+
+const (
+	// maxEntries limits how many geojs answers are held in memory.
+	maxEntries = 250_000
+
+	// userAgentHeader and userAgent name routewatch to geojs and DB-IP.
+	userAgentHeader = "User-Agent"
+	userAgent       = "routewatch (+https://git.eeqj.de/sneak/routewatch)"
+)
+
+// Params is what New needs.
+type Params struct {
+	// DB is the open cache.db.
+	DB *sql.DB
+
+	// Dir is the directory that holds the copy of the database.
+	Dir string
+
+	// GeoJSURL is the URL of the geojs geo endpoint, GeoJSEndpoint in use.
+	GeoJSURL string
+
+	// DatabaseURLFormat is the URL of the database with %s for the year and
+	// month, DatabaseDownloadFormat in use.
+	DatabaseURLFormat string
+
+	Logger *slog.Logger
+}
+
+// Location is where an address is. A part the source does not know is nil.
+//
+//nolint:tagliatelle // snake_case keys, as the Go style guide asks
+type Location struct {
+	CountryCode      *string  `json:"country_code"`
+	Country          *string  `json:"country"`
+	ContinentCode    *string  `json:"continent_code"`
+	Region           *string  `json:"region"`
+	City             *string  `json:"city"`
+	Latitude         *float64 `json:"latitude"`
+	Longitude        *float64 `json:"longitude"`
+	AccuracyRadiusKm *int     `json:"accuracy_radius_km"`
+	TimeZone         *string  `json:"time_zone"`
+
+	// Source is geojs or dbip.
+	Source string `json:"source"`
+
+	// Updated is when the value was fetched: the geojs answer, or the copy of
+	// the database.
+	Updated time.Time `json:"updated"`
+}
+
+// Locator answers where addresses are. Start loads its cache and starts its
+// goroutines.
+type Locator struct {
+	db                *sql.DB
+	dir               string
+	geojsURL          string
+	databaseURLFormat string
+	timeLimit         time.Duration
+	maxEntries        int
+	maxDatabaseBytes  int64
+	logger            *slog.Logger
+	client            *http.Client
+	now               func() time.Time
+
+	// entries holds geojs answers by address, and drops the least recently
+	// used first.
+	entries *lru.Cache[string, *Location]
+
+	// pending holds the answers that cache.db does not have yet.
+	pendingMu sync.Mutex
+	pending   map[string]*Location
+
+	// database is the open copy, nil until one has opened, and databaseFetched
+	// is when that copy was downloaded. A lookup holds the read lock, so that
+	// a new copy never closes the old one under it.
+	databaseMu      sync.RWMutex
+	database        *maxminddb.Reader
+	databaseFetched time.Time
+
+	// stop ends the goroutines Start runs, and done is closed when they have
+	// returned.
+	stop context.CancelFunc
+	done chan struct{}
+}
+
+// New returns a Locator with an empty cache. Start loads it.
+func New(params Params) (*Locator, error) {
+	entries, err := lru.New[string, *Location](maxEntries)
+	if err != nil {
+		return nil, fmt.Errorf("creating the geolocation cache: %w", err)
+	}
+
+	return &Locator{
+		db:                params.DB,
+		dir:               params.Dir,
+		geojsURL:          params.GeoJSURL,
+		databaseURLFormat: params.DatabaseURLFormat,
+		timeLimit:         geojsTimeLimit,
+		maxEntries:        maxEntries,
+		maxDatabaseBytes:  maxDatabaseSize,
+		logger:            params.Logger.With("component", "geo"),
+		client:            &http.Client{},
+		now:               time.Now,
+		entries:           entries,
+		pending:           make(map[string]*Location),
+		done:              make(chan struct{}),
+	}, nil
+}
+
+// Lookup returns where each of addrs is, in the same order. The entry for an
+// address neither source answers for is nil. Addresses with no current cached
+// answer go to geojs in one request. The returned Locations are shared with
+// the cache and must not be changed.
+func (l *Locator) Lookup(ctx context.Context, addrs []netip.Addr) []*Location {
+	locations := make([]*Location, len(addrs))
+
+	var unanswered []string
+
+	for i, addr := range addrs {
+		address := plainAddress(addr)
+
+		locations[i] = l.cached(ctx, address)
+		if locations[i] == nil {
+			unanswered = append(unanswered, address)
+		}
+	}
+
+	if len(unanswered) == 0 {
+		return locations
+	}
+
+	answers, err := l.askGeoJS(ctx, unanswered)
+	if err != nil {
+		l.logger.Warn("geojs lookup failed; using the database", "error", err)
+	}
+
+	for i, addr := range addrs {
+		if locations[i] != nil {
+			continue
+		}
+
+		address := plainAddress(addr)
+
+		answer, ok := answers[address]
+		if ok {
+			l.store(address, answer)
+			locations[i] = answer
+
+			continue
+		}
+
+		locations[i] = l.fromDatabase(addr)
+	}
+
+	return locations
+}
+
+// plainAddress returns addr as the requests to geojs and the cache name it: an
+// IPv4 address mapped into IPv6 as plain IPv4, and with no zone. A client
+// chooses the zone, so it must not reach the request.
+func plainAddress(addr netip.Addr) string {
+	return addr.Unmap().WithZone("").String()
+}
+
+// Start loads the cached answers that have not expired and opens the copy of
+// the database, if there is one. It then starts the goroutines that write new
+// answers, delete expired ones and download the database. They run until Stop:
+// the end of ctx does not stop them.
+func (l *Locator) Start(ctx context.Context) error {
+	err := l.load(ctx)
+	if err != nil {
+		return err
+	}
+
+	l.logger.Info("Geolocation cache loaded", "entries", l.entries.Len())
+
+	l.openDatabaseCopy()
+
+	ctx, l.stop = context.WithCancel(context.WithoutCancel(ctx))
+
+	go func() {
+		defer close(l.done)
+		defer l.closeDatabase()
+
+		var workers sync.WaitGroup
+
+		workers.Go(func() { l.keepCache(ctx) })
+		workers.Go(func() { l.keepDatabaseCurrent(ctx) })
+		workers.Wait()
+	}()
+
+	return nil
+}
+
+// Stop cancels a download in progress, writes the answers cache.db does not
+// have yet, and waits until the goroutines have returned or ctx ends.
+func (l *Locator) Stop(ctx context.Context) {
+	l.stop()
+
+	select {
+	case <-l.done:
+		l.logger.Info("Geolocation stopped")
+	case <-ctx.Done():
+		l.logger.Warn("Stop deadline passed before the geolocation cache " +
+			"was written")
+	}
+}

internal/iplist/download.go

@@ -1,4 +1,4 @@
-package blocklist
+package iplist
 
 import (
 	"context"
@@ -21,8 +21,8 @@ const (
 	downloadTimeout = time.Minute
 
 	// maxDownloadSize is the size of the largest list file accepted, in
-	// bytes. The largest list, FireHOL abusers, is about 2.5 MiB.
+	// bytes. The largest list, iCloud Private Relay, is about 12 MiB.
-	maxDownloadSize = 16 << 20
+	maxDownloadSize = 200 << 20
 )
 
 // The request headers a download sets.
@@ -78,10 +78,10 @@ var (
 // downloads each list once its copy is older than its Interval, and a list
 // with no copy at once. The goroutine runs until Stop: the end of ctx does
 // not stop it.
-func (b *Blocklists) Start(ctx context.Context) {
+func (b *IPLists) Start(ctx context.Context) {
 	err := os.MkdirAll(b.dir, dirPermissions)
 	if err != nil {
-		b.logger.Error("Failed to create the blocklists directory",
+		b.logger.Error("Failed to create the IP lists directory",
 			"dir", b.dir, "error", err)
 	}
 
@@ -90,7 +90,7 @@ func (b *Blocklists) Start(ctx context.Context) {
 	for i, list := range b.lists {
 		loadErr := b.loadCopy(list)
 		if loadErr != nil && !errors.Is(loadErr, fs.ErrNotExist) {
-			b.logger.Error("Failed to load a blocklist copy",
+			b.logger.Error("Failed to load an IP list copy",
 				"list", list.Name, "error", loadErr)
 		}
 
@@ -104,20 +104,20 @@ func (b *Blocklists) Start(ctx context.Context) {
 		b.run(ctx, nextDownload)
 	}()
 
-	b.logger.Info("Blocklist downloads started", "dir", b.dir)
+	b.logger.Info("IP list downloads started", "dir", b.dir)
 }
 
 // Stop stops the downloads, cancelling one in progress, and waits until the
 // goroutine has returned or ctx ends. The copies in memory stay, so Lookup
 // still answers.
-func (b *Blocklists) Stop(ctx context.Context) {
+func (b *IPLists) Stop(ctx context.Context) {
 	b.stop()
 
 	select {
 	case <-b.done:
-		b.logger.Info("Blocklist downloads stopped")
+		b.logger.Info("IP list downloads stopped")
 	case <-ctx.Done():
-		b.logger.Warn("Stop deadline passed before the blocklist downloads " +
+		b.logger.Warn("Stop deadline passed before the IP list downloads " +
 			"stopped")
 	}
 }
@@ -125,7 +125,7 @@ func (b *Blocklists) Stop(ctx context.Context) {
 // run downloads each list when nextDownload says, until ctx ends. After each
 // try, whether it worked or not, the list's next download is an Interval
 // later.
-func (b *Blocklists) run(ctx context.Context, nextDownload []time.Time) {
+func (b *IPLists) run(ctx context.Context, nextDownload []time.Time) {
 	defer close(b.done)
 
 	if len(nextDownload) == 0 {
@@ -155,7 +155,7 @@ func (b *Blocklists) run(ctx context.Context, nextDownload []time.Time) {
 			}
 
 			if err != nil {
-				b.logger.Error("Blocklist download failed; keeping the "+
+				b.logger.Error("IP list download failed; keeping the "+
 					"previous copy", "list", list.Name, "error", err)
 			}
 
@@ -169,7 +169,7 @@ func (b *Blocklists) run(ctx context.Context, nextDownload []time.Time) {
 // on disk and in memory. An answer that the copy is still current marks the
 // copy as updated now. Anything else leaves the copy as it is and returns an
 // error.
-func (b *Blocklists) download(ctx context.Context, list List) error {
+func (b *IPLists) download(ctx context.Context, list List) error {
 	ctx, cancel := context.WithTimeout(ctx, downloadTimeout)
 	defer cancel()
 
@@ -212,7 +212,7 @@ func (b *Blocklists) download(ctx context.Context, list List) error {
 // replaceCopy writes a new version of list, read from body, beside the list's
 // copy. Only when it parses does it replace the copy, on disk and in memory.
 // sent are the validators the publisher sent with the new version.
-func (b *Blocklists) replaceCopy(list List, body io.Reader, sent validators) error {
+func (b *IPLists) replaceCopy(list List, body io.Reader, sent validators) error {
 	root, err := os.OpenRoot(b.dir)
 	if err != nil {
 		return err
@@ -244,13 +244,13 @@ func (b *Blocklists) replaceCopy(list List, body io.Reader, sent validators) err
 	b.setCopy(list.Name, listCopy{
 		addresses: addresses, updated: time.Now().UTC(), validators: sent,
 	})
-	b.logger.Info("Downloaded a new version of a blocklist", "list", list.Name)
+	b.logger.Info("Downloaded a new version of an IP list", "list", list.Name)
 
 	// Without this file, the first download after a restart asks for the
 	// whole list.
 	err = writeValidators(root, list.Name, sent)
 	if err != nil {
-		b.logger.Error("Failed to keep the validators of a blocklist copy",
+		b.logger.Error("Failed to keep the validators of an IP list copy",
 			"list", list.Name, "error", err)
 	}
 
@@ -288,7 +288,7 @@ func writeAndParse(
 
 // markCurrent records that the publisher says the list's copy is still
 // current: the copy, on disk and in memory, is marked as updated now.
-func (b *Blocklists) markCurrent(list List) error {
+func (b *IPLists) markCurrent(list List) error {
 	root, err := os.OpenRoot(b.dir)
 	if err != nil {
 		return err
@@ -304,7 +304,7 @@ func (b *Blocklists) markCurrent(list List) error {
 	}
 
 	b.setUpdated(list.Name, now)
-	b.logger.Debug("Blocklist copy is still current", "list", list.Name)
+	b.logger.Debug("IP list copy is still current", "list", list.Name)
 
 	return nil
 }
@@ -312,7 +312,7 @@ func (b *Blocklists) markCurrent(list List) error {
 // loadCopy makes the list's copy on disk, with the validators kept beside it,
 // its copy in memory. The file's modification time is when the copy was
 // updated.
-func (b *Blocklists) loadCopy(list List) error {
+func (b *IPLists) loadCopy(list List) error {
 	root, err := os.OpenRoot(b.dir)
 	if err != nil {
 		return err

internal/iplist/iplist.go

@@ -1,7 +1,7 @@
-// Package blocklist downloads public IP blocklists on a schedule, keeps the
+// Package iplist downloads public IP lists on a schedule, keeps the last good
-// last good copy of each on disk and in memory, and answers which lists
+// copy of each on disk and in memory, and answers which lists contain an
-// contain an address.
+// address.
-package blocklist
+package iplist
 
 import (
 	"context"
@@ -29,9 +29,41 @@ const (
 	// start with the network's first and last address. Lines that start
 	// with # are comments.
 	FormatDShield
+
+	// FormatOnionooJSON is one Onionoo details document. Its relays have
+	// addresses in two fields: exit_addresses, which has IPv4 only, and
+	// or_addresses, which has IPv4 and IPv6, each with a port.
+	FormatOnionooJSON
+
+	// FormatMullvadJSON is Mullvad's JSON list of relays. A relay's addresses
+	// are in ipv4_addr_in, ipv6_addr_in and ipv4_v2ray.
+	FormatMullvadJSON
+
+	// FormatNordVPNJSON is NordVPN's JSON list of servers. A server's
+	// addresses are in station and ipv6_station.
+	FormatNordVPNJSON
+
+	// FormatPIAJSON is Private Internet Access's JSON server list, then a
+	// blank line and a signature. Each region's servers has lists of servers
+	// by protocol, and each server has its address in ip.
+	FormatPIAJSON
+
+	// FormatIVPNJSON is IVPN's JSON server list. The hosts of its wireguard
+	// and openvpn gateways have their addresses in host and v2ray.
+	FormatIVPNJSON
+
+	// FormatProtonVPN has one address or network per line, with comment lines
+	// that start with #. Unlike FormatLines, a file with no addresses or
+	// networks fails.
+	FormatProtonVPN
+
+	// FormatICloudPrivateRelayCSV is Apple's CSV file of iCloud Private Relay
+	// networks. Each line starts with a network, followed by its country,
+	// region and city.
+	FormatICloudPrivateRelayCSV
 )
 
-// List is one public blocklist.
+// List is one public IP list.
 type List struct {
 	// Name names the list in lookup answers, and names its copy on disk.
 	Name string
@@ -48,6 +80,9 @@ type List struct {
 
 	// Format is how the list's file is written.
 	Format Format
+
+	// VPN says that the list holds servers of VPN services.
+	VPN bool
 }
 
 // Listing says that a list contains an address.
@@ -58,6 +93,10 @@ type Listing struct {
 	// Updated is when routewatch last downloaded the list, or last heard from
 	// its publisher that its copy was still current.
 	Updated time.Time `json:"updated"`
+
+	// VPN says that the list holds servers of VPN services. A lookup answer
+	// reports it through is_vpn and vpn_providers.
+	VPN bool `json:"-"`
 }
 
 // listCopy is a list's last good copy in memory.
@@ -80,9 +119,9 @@ type Params struct {
 	Logger *slog.Logger
 }
 
-// Blocklists keeps a copy of each list and answers which lists contain an
+// IPLists keeps a copy of each list and answers which lists contain an
 // address. Start loads the copies from disk and starts downloading the lists.
-type Blocklists struct {
+type IPLists struct {
 	dir    string
 	lists  []List
 	logger *slog.Logger
@@ -97,12 +136,12 @@ type Blocklists struct {
 	done chan struct{}
 }
 
-// New returns a Blocklists with no copies. Start loads them.
+// New returns an IPLists with no copies. Start loads them.
-func New(params Params) *Blocklists {
+func New(params Params) *IPLists {
-	return &Blocklists{
+	return &IPLists{
 		dir:    params.Dir,
 		lists:  params.Lists,
-		logger: params.Logger.With("component", "blocklists"),
+		logger: params.Logger.With("component", "iplists"),
 		copies: make(map[string]listCopy),
 		done:   make(chan struct{}),
 	}
@@ -111,7 +150,7 @@ func New(params Params) *Blocklists {
 // Lookup returns a Listing for each list whose copy contains addr, in the
 // order of the lists given to New. It makes no outside request. When no list
 // contains addr, it returns an empty list, not nil.
-func (b *Blocklists) Lookup(addr netip.Addr) []Listing {
+func (b *IPLists) Lookup(addr netip.Addr) []Listing {
 	b.mu.RLock()
 	defer b.mu.RUnlock()
 
@@ -124,6 +163,7 @@ func (b *Blocklists) Lookup(addr netip.Addr) []Listing {
 				Name:        list.Name,
 				Description: list.Description,
 				Updated:     c.updated,
+				VPN:         list.VPN,
 			})
 		}
 	}
@@ -133,7 +173,7 @@ func (b *Blocklists) Lookup(addr netip.Addr) []Listing {
 
 // ShortestInterval returns the shortest Interval of the lists. That is the
 // soonest a copy can change, and so how long a lookup answer stays current.
-func (b *Blocklists) ShortestInterval() time.Duration {
+func (b *IPLists) ShortestInterval() time.Duration {
 	var shortest time.Duration
 
 	for i, list := range b.lists {
@@ -147,7 +187,7 @@ func (b *Blocklists) ShortestInterval() time.Duration {
 
 // updated returns when the named list's copy was last downloaded or found
 // current, or the zero time when the list has no copy.
-func (b *Blocklists) updated(name string) time.Time {
+func (b *IPLists) updated(name string) time.Time {
 	b.mu.RLock()
 	defer b.mu.RUnlock()
 
@@ -156,7 +196,7 @@ func (b *Blocklists) updated(name string) time.Time {
 
 // copyValidators returns the validators of the named list's copy. They are
 // empty when the list has no copy.
-func (b *Blocklists) copyValidators(name string) validators {
+func (b *IPLists) copyValidators(name string) validators {
 	b.mu.RLock()
 	defer b.mu.RUnlock()
 
@@ -164,7 +204,7 @@ func (b *Blocklists) copyValidators(name string) validators {
 }
 
 // setCopy makes c the named list's copy.
-func (b *Blocklists) setCopy(name string, c listCopy) {
+func (b *IPLists) setCopy(name string, c listCopy) {
 	b.mu.Lock()
 	defer b.mu.Unlock()
 
@@ -172,7 +212,7 @@ func (b *Blocklists) setCopy(name string, c listCopy) {
 }
 
 // setUpdated records that the named list's copy was found current at t.
-func (b *Blocklists) setUpdated(name string, t time.Time) {
+func (b *IPLists) setUpdated(name string, t time.Time) {
 	b.mu.Lock()
 	defer b.mu.Unlock()
 

internal/iplist/iplist_internal_test.go

@@ -0,0 +1,992 @@
+package iplist
+
+import (
+	"context"
+	"errors"
+	"io"
+	"io/fs"
+	"log/slog"
+	"net/http"
+	"net/http/httptest"
+	"net/netip"
+	"os"
+	"path/filepath"
+	"slices"
+	"strings"
+	"sync"
+	"testing"
+	"time"
+)
+
+// The test list's name and description, the address its good version lists,
+// and the address a newer version lists instead.
+const (
+	testListName        = "test_list"
+	testListDescription = "On the test list"
+	listedAddr          = "192.0.2.1"
+	goodListBody        = "# A test list\n" + listedAddr + "\n"
+	newListedAddr       = "192.0.2.2"
+	newListBody         = "# A test list\n" + newListedAddr + "\n"
+)
+
+// A small Onionoo details document: a relay with an exit address and IPv4 and
+// IPv6 relay addresses, one without exit addresses, and one with a list of
+// ports.
+const (
+	onionooExitAddr     = "192.0.2.10"
+	onionooIPv6ExitAddr = "2001:db8::1"
+	onionooBody         = `{"version":"8.0","relays":[
+		{"exit_addresses":["` + onionooExitAddr + `"],
+		 "or_addresses":["192.0.2.11:443","[` + onionooIPv6ExitAddr + `]:9001"]},
+		{"or_addresses":["192.0.2.20:443"]},
+		{"or_addresses":["192.0.2.30:80,443"]}
+	],"bridges":[]}`
+)
+
+// Small documents in the VPN services' formats. PIA's and IVPN's have no
+// public IPv6 addresses, and IVPN's holds addresses that are not its servers,
+// which must not be read.
+const (
+	mullvadBody = `[
+		{"hostname":"a-wg-001","ipv4_addr_in":"192.0.2.40","ipv6_addr_in":"2001:db8::40"},
+		{"hostname":"a-br-001","ipv4_addr_in":"192.0.2.41","ipv6_addr_in":null,
+		 "ipv4_v2ray":"192.0.2.42"}
+	]`
+	nordVPNBody = `[
+		{"hostname":"a1.example.com","station":"192.0.2.50","ipv6_station":""},
+		{"hostname":"a2.example.com","station":"192.0.2.51","ipv6_station":"2001:db8::51"}
+	]`
+	piaBody = `{"groups":{"wg":[{"name":"wireguard","ports":[1337]}]},"regions":[
+		{"id":"a","servers":{
+			"wg":[{"ip":"192.0.2.60","cn":"a1"}],
+			"ikev2":[{"ip":"192.0.2.61","cn":"a1"}]}},
+		{"id":"b","servers":{"meta":[{"ip":"192.0.2.62","cn":"b1","van":true}]}}
+	]}` + "\n\nc2lnbmF0dXJl\nbGluZSB0d28=\n"
+	ivpnBody = `{"wireguard":[{"gateway":"a.wg.example.com","hosts":[
+		{"hostname":"a1","host":"192.0.2.70","v2ray":"192.0.2.71",
+		 "ipv6":{"local_ip":"2001:db8::70/96"}}]}],
+	"openvpn":[{"gateway":"a.gw.example.com","hosts":[
+		{"hostname":"a1","host":"192.0.2.72"}]}],
+	"config":{"api":{"ips":["192.0.2.73"]}}}`
+)
+
+// protonVPNBody is a small file in the format of the ProtonVPN-IPs list.
+const protonVPNBody = "#\n# protonvpn_ip_ranges.txt\n" +
+	"# https://github.com/tn3w/ProtonVPN-IPs\n#\n" +
+	"# The /24 block of every advertised IPv4.\n#\n" +
+	"192.0.2.0/24\n198.51.100.0/24\n"
+
+// protonVPNEntryBody is a small file in the format of the ProtonVPN-IPs list
+// of server addresses.
+const protonVPNEntryBody = "#\n# protonvpn_entry_ips.txt\n" +
+	"# https://github.com/tn3w/ProtonVPN-IPs\n#\n" +
+	"# Entry IPs clients connect to, resolved from ProtonVPN hostnames.\n#\n" +
+	"192.0.2.80\n2001:db8::80\n"
+
+// iCloudPrivateRelayAddr is an address on iCloudPrivateRelayBody.
+const iCloudPrivateRelayAddr = "2001:db8:1::5"
+
+// iCloudPrivateRelayBody is a small file in the format of Apple's iCloud
+// Private Relay file.
+const iCloudPrivateRelayBody = "192.0.2.0/31,GB,GB-EN,London,\n" +
+	"198.51.100.32/27,US,US-CA,Los Angeles,\n" +
+	"2001:db8:1::/64,US,US-AK,Anchorage,\n"
+
+// emptyFileCase names the case of a wrong document that is an empty file.
+const emptyFileCase = "an empty file"
+
+// errorPage is a file that is no list, as a publisher's error page is.
+const errorPage = "<!DOCTYPE html>\n<html></html>\n"
+
+// testETag is the ETag a publisher sends with a version of the test list.
+const testETag = `"v1"`
+
+// maxWait is how long a test waits for the download goroutine.
+const maxWait = 10 * time.Second
+
+// publisher stands in for a list's publisher. It answers every request with
+// its status and body, and keeps the headers of each request. A 200 answer
+// carries lastModified and etag, when set, as Last-Modified and ETag. As
+// from a real publisher, a request whose If-None-Match or If-Modified-Since
+// matches them is answered "not modified".
+type publisher struct {
+	mu           sync.Mutex
+	status       int
+	body         string
+	lastModified time.Time
+	etag         string
+	headers      []http.Header
+}
+
+// newPublisher starts a publisher that answers 200 with body, and returns it
+// and its URL.
+func newPublisher(t *testing.T, body string) (*publisher, string) {
+	t.Helper()
+
+	p := &publisher{status: http.StatusOK, body: body}
+	srv := httptest.NewServer(p)
+	t.Cleanup(srv.Close)
+
+	return p, srv.URL
+}
+
+func (p *publisher) ServeHTTP(w http.ResponseWriter, r *http.Request) {
+	p.mu.Lock()
+	defer p.mu.Unlock()
+
+	p.headers = append(p.headers, r.Header.Clone())
+
+	if p.status != http.StatusOK {
+		w.WriteHeader(p.status)
+		_, _ = io.WriteString(w, p.body)
+
+		return
+	}
+
+	if p.etag != "" {
+		w.Header().Set(etagHeader, p.etag)
+	}
+
+	// ServeContent sends Last-Modified unless lastModified is zero, and
+	// answers "not modified" when the request's conditions match.
+	http.ServeContent(w, r, testListName, p.lastModified,
+		strings.NewReader(p.body))
+}
+
+// answer makes the publisher answer later requests with status and body.
+func (p *publisher) answer(status int, body string) {
+	p.mu.Lock()
+	defer p.mu.Unlock()
+
+	p.status, p.body = status, body
+}
+
+// publish makes the publisher answer later requests with a version of the
+// list: body, with lastModified and etag. A zero lastModified or an empty
+// etag is not sent.
+func (p *publisher) publish(body string, lastModified time.Time, etag string) {
+	p.mu.Lock()
+	defer p.mu.Unlock()
+
+	p.status, p.body = http.StatusOK, body
+	p.lastModified, p.etag = lastModified, etag
+}
+
+// requests returns the headers of the requests the publisher has had.
+func (p *publisher) requests() []http.Header {
+	p.mu.Lock()
+	defer p.mu.Unlock()
+
+	return append([]http.Header(nil), p.headers...)
+}
+
+// testList returns a list served at url, written in format.
+func testList(url string, format Format) List {
+	return List{
+		Name:        testListName,
+		Description: testListDescription,
+		URL:         url,
+		Interval:    time.Hour,
+		Format:      format,
+	}
+}
+
+func newTestIPLists(dir string, list List) *IPLists {
+	return New(Params{
+		Dir:    dir,
+		Lists:  []List{list},
+		Logger: slog.New(slog.DiscardHandler),
+	})
+}
+
+// lookup looks addr up in b.
+func lookup(t *testing.T, b *IPLists, addr string) []Listing {
+	t.Helper()
+
+	return b.Lookup(netip.MustParseAddr(addr))
+}
+
+// TestLookupFindsListedAddresses downloads a list in each format and looks
+// up addresses on it, inside its networks, and off it, in IPv4 and IPv6.
+// A listed address has one listing that names the list; any other has an
+// empty list of listings.
+func TestLookupFindsListedAddresses(t *testing.T) {
+	t.Parallel()
+
+	runLookupCases(t, []lookupCase{
+		{
+			name:     "single addresses",
+			format:   FormatLines,
+			body:     "# comment\n192.0.2.1\n\n2001:db8::1\n",
+			listed:   []string{"192.0.2.1", "::ffff:192.0.2.1", "2001:db8::1"},
+			unlisted: []string{"192.0.2.2", "2001:db8::2"},
+		},
+		{
+			name:     "networks",
+			format:   FormatLines,
+			body:     "# comment\n198.51.100.0/24\n2001:db8:1::/48\n",
+			listed:   []string{"198.51.100.0", "198.51.100.255", "2001:db8:1::5"},
+			unlisted: []string{"198.51.101.0", "2001:db8:2::1"},
+		},
+		{
+			name:   "Spamhaus networks",
+			format: FormatSpamhausJSON,
+			body: `{"cidr":"203.0.113.0/25","sblid":"SBL1","rir":"arin"}` + "\n" +
+				`{"cidr":"2001:db8:3::/48","sblid":"SBL2","rir":"ripencc"}` + "\n" +
+				`{"type":"metadata","timestamp":1793074442,"records":2}` + "\n",
+			listed:   []string{"203.0.113.1", "2001:db8:3::1"},
+			unlisted: []string{"203.0.113.200", "2001:db8:4::1"},
+		},
+		{
+			name:   "DShield networks",
+			format: FormatDShield,
+			body: "#   DShield.org Recommended Block List\n" +
+				"192.0.2.0\t192.0.2.255\t24\t327\tEXAMPLE\tUS\tNone\n",
+			listed:   []string{"192.0.2.0", "192.0.2.77"},
+			unlisted: []string{"192.0.3.1", "2001:db8::1"},
+		},
+		{
+			name:   "Onionoo relays",
+			format: FormatOnionooJSON,
+			body:   onionooBody,
+			listed: []string{
+				onionooExitAddr, "192.0.2.11", "192.0.2.20", "192.0.2.30",
+				onionooIPv6ExitAddr,
+			},
+			unlisted: []string{"192.0.2.12", "2001:db8::2"},
+		},
+		{
+			name:   "iCloud Private Relay networks",
+			format: FormatICloudPrivateRelayCSV,
+			body:   iCloudPrivateRelayBody,
+			listed: []string{
+				"192.0.2.1", "198.51.100.63", iCloudPrivateRelayAddr,
+			},
+			unlisted: []string{"192.0.2.2", "198.51.100.64", "2001:db8:2::1"},
+		},
+	})
+}
+
+// TestLookupFindsVPNServers downloads a list in each VPN service's format and
+// looks up addresses on it and off it.
+func TestLookupFindsVPNServers(t *testing.T) {
+	t.Parallel()
+
+	runLookupCases(t, []lookupCase{
+		{
+			name:     "Mullvad relays",
+			format:   FormatMullvadJSON,
+			body:     mullvadBody,
+			listed:   []string{"192.0.2.40", "192.0.2.41", "192.0.2.42", "2001:db8::40"},
+			unlisted: []string{"192.0.2.43", "2001:db8::41"},
+		},
+		{
+			name:     "NordVPN servers",
+			format:   FormatNordVPNJSON,
+			body:     nordVPNBody,
+			listed:   []string{"192.0.2.50", "192.0.2.51", "2001:db8::51"},
+			unlisted: []string{"192.0.2.52", "2001:db8::50"},
+		},
+		{
+			name:     "PIA servers, with the signature after the JSON",
+			format:   FormatPIAJSON,
+			body:     piaBody,
+			listed:   []string{"192.0.2.60", "192.0.2.61", "192.0.2.62"},
+			unlisted: []string{"192.0.2.63", "2001:db8::60"},
+		},
+		{
+			name:     "IVPN hosts",
+			format:   FormatIVPNJSON,
+			body:     ivpnBody,
+			listed:   []string{"192.0.2.70", "192.0.2.71", "192.0.2.72"},
+			unlisted: []string{"192.0.2.73", "2001:db8::70"},
+		},
+		{
+			name:     "ProtonVPN networks",
+			format:   FormatProtonVPN,
+			body:     protonVPNBody,
+			listed:   []string{"192.0.2.0", "192.0.2.255", "198.51.100.7"},
+			unlisted: []string{"192.0.3.1", "2001:db8::90"},
+		},
+		{
+			name:     "ProtonVPN server addresses",
+			format:   FormatProtonVPN,
+			body:     protonVPNEntryBody,
+			listed:   []string{"192.0.2.80", "2001:db8::80"},
+			unlisted: []string{"192.0.2.81", "2001:db8::81"},
+		},
+	})
+}
+
+// lookupCase is a list file, the addresses it holds and some it does not.
+type lookupCase struct {
+	name     string
+	format   Format
+	body     string
+	listed   []string
+	unlisted []string
+}
+
+// runLookupCases downloads each case's list file and checks its addresses.
+func runLookupCases(t *testing.T, cases []lookupCase) {
+	t.Helper()
+
+	for _, tt := range cases {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			_, url := newPublisher(t, tt.body)
+			b := newTestIPLists(t.TempDir(), testList(url, tt.format))
+
+			err := b.download(t.Context(), b.lists[0])
+			if err != nil {
+				t.Fatalf("download: %v", err)
+			}
+
+			checkLookups(t, b, tt.listed, tt.unlisted)
+		})
+	}
+}
+
+// checkLookups checks that each of listed has one listing that names the test
+// list, and each of unlisted has an empty list of listings.
+func checkLookups(t *testing.T, b *IPLists, listed, unlisted []string) {
+	t.Helper()
+
+	for _, addr := range listed {
+		listings := lookup(t, b, addr)
+		if len(listings) != 1 || listings[0].Name != testListName ||
+			listings[0].Description != testListDescription ||
+			listings[0].Updated.IsZero() {
+			t.Errorf("%s: listings %+v, want one for %s", addr,
+				listings, testListName)
+		}
+	}
+
+	for _, addr := range unlisted {
+		listings := lookup(t, b, addr)
+		if listings == nil || len(listings) != 0 {
+			t.Errorf("%s: listings %#v, want an empty list", addr, listings)
+		}
+	}
+}
+
+// TestFailedDownloadKeepsThePreviousCopy downloads a good version of a list,
+// then one that fails. The good copy stays in memory and on disk, and no
+// part of the failed download is left beside it.
+func TestFailedDownloadKeepsThePreviousCopy(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name   string
+		status int
+		body   string
+	}{
+		{"server error", http.StatusInternalServerError, "unavailable"},
+		{"not a list", http.StatusOK, errorPage},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			dir := t.TempDir()
+			p, url := newPublisher(t, goodListBody)
+			b := newTestIPLists(dir, testList(url, FormatLines))
+
+			err := b.download(t.Context(), b.lists[0])
+			if err != nil {
+				t.Fatalf("first download: %v", err)
+			}
+
+			before := lookup(t, b, listedAddr)
+
+			p.answer(tt.status, tt.body)
+
+			err = b.download(t.Context(), b.lists[0])
+			if err == nil {
+				t.Fatal("second download returned no error")
+			}
+
+			after := lookup(t, b, listedAddr)
+			if len(after) != 1 || len(before) != 1 ||
+				!after[0].Updated.Equal(before[0].Updated) {
+				t.Errorf("listings %+v after the failure, want %+v", after, before)
+			}
+
+			checkGoodCopyOnDisk(t, dir)
+		})
+	}
+}
+
+// TestFileThatIsNotAnOnionooDocumentKeepsThePreviousCopy downloads a good
+// Onionoo document, then files that are not one. Each fails the parse, and
+// the good copy stays.
+func TestFileThatIsNotAnOnionooDocumentKeepsThePreviousCopy(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name string
+		body string
+	}{
+		{"not JSON", errorPage},
+		{"other JSON", `{"status":"ok","data":{"relays_count":1}}`},
+		{"JSON array", `[{"or_addresses":["192.0.2.1:443"]}]`},
+		{"no relays", `{"relays":[],"bridges":[]}`},
+		{"relays without addresses", `{"relays":[{"nickname":"example"}]}`},
+		{"relay address without a port", `{"relays":[{"or_addresses":["192.0.2.1"]}]}`},
+		{"exit address that is not one", `{"relays":[{"exit_addresses":["example"]}]}`},
+		{"text after the document", `{"relays":[{"or_addresses":["192.0.2.1:1"]}]} x`},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			dir := t.TempDir()
+			p, url := newPublisher(t, onionooBody)
+			b := newTestIPLists(dir, testList(url, FormatOnionooJSON))
+
+			err := b.download(t.Context(), b.lists[0])
+			if err != nil {
+				t.Fatalf("first download: %v", err)
+			}
+
+			p.answer(http.StatusOK, tt.body)
+
+			err = b.download(t.Context(), b.lists[0])
+			if err == nil {
+				t.Fatal("second download returned no error")
+			}
+
+			if len(lookup(t, b, onionooExitAddr)) != 1 {
+				t.Errorf("%s is no longer listed", onionooExitAddr)
+			}
+
+			onDisk, err := fs.ReadFile(os.DirFS(dir), testListName)
+			if err != nil || string(onDisk) != onionooBody {
+				t.Errorf("copy on disk %q (%v), want the good version", onDisk, err)
+			}
+		})
+	}
+}
+
+// TestWrongVPNDocumentFailsToParse parses documents that are not a VPN
+// service's list. Each fails, so none can replace a good copy.
+func TestWrongVPNDocumentFailsToParse(t *testing.T) {
+	t.Parallel()
+
+	formats := []struct {
+		name       string
+		format     Format
+		good       string
+		empty      string
+		badAddress string
+	}{
+		{
+			"Mullvad", FormatMullvadJSON, mullvadBody,
+			`[{"hostname":"a"}]`, `[{"ipv4_addr_in":"example"}]`,
+		},
+		{
+			"NordVPN", FormatNordVPNJSON, nordVPNBody,
+			`[{"hostname":"a","station":"","ipv6_station":""}]`,
+			`[{"station":"example"}]`,
+		},
+		{
+			"PIA", FormatPIAJSON, piaBody,
+			`{"regions":[{"id":"a","servers":{}}]}`,
+			`{"regions":[{"servers":{"wg":[{"ip":"example"}]}}]}`,
+		},
+		{
+			"IVPN", FormatIVPNJSON, ivpnBody,
+			`{"wireguard":[{"hosts":[]}],"openvpn":[]}`,
+			`{"wireguard":[{"hosts":[{"host":"example"}]}]}`,
+		},
+	}
+
+	for _, f := range formats {
+		bodies := map[string]string{
+			"not JSON":     errorPage,
+			"other JSON":   `{"status":"ok","data":{"count":1}}`,
+			"no addresses": f.empty,
+			"bad address":  f.badAddress,
+			"cut off":      f.good[:len(f.good)/2],
+			emptyFileCase:  "",
+		}
+
+		for name, body := range bodies {
+			t.Run(f.name+" "+name, func(t *testing.T) {
+				t.Parallel()
+
+				addresses, err := parse(strings.NewReader(body), f.format)
+				if err == nil {
+					t.Errorf("parse returned %v and no error", addresses.Ranges())
+				}
+			})
+		}
+	}
+}
+
+// TestWrongProtonVPNDocumentFailsToParse parses documents that are not a
+// ProtonVPN-IPs list. Each fails, so none can replace a good copy.
+func TestWrongProtonVPNDocumentFailsToParse(t *testing.T) {
+	t.Parallel()
+
+	bodies := map[string]string{
+		"error page":    errorPage,
+		"JSON":          `{"status":"ok"}`,
+		"comments only": "#\n# protonvpn_ip_ranges.txt\n#\n",
+		"bad network":   "192.0.2.0/24\nexample\n",
+		emptyFileCase:   "",
+	}
+
+	for name, body := range bodies {
+		t.Run(name, func(t *testing.T) {
+			t.Parallel()
+
+			addresses, err := parse(strings.NewReader(body), FormatProtonVPN)
+			if err == nil {
+				t.Errorf("parse returned %v and no error", addresses.Ranges())
+			}
+		})
+	}
+}
+
+// TestWrongICloudPrivateRelayDocumentFailsToParse parses documents that are
+// not Apple's iCloud Private Relay file. Each fails, so none can replace a
+// good copy.
+func TestWrongICloudPrivateRelayDocumentFailsToParse(t *testing.T) {
+	t.Parallel()
+
+	bodies := map[string]string{
+		"error page":     errorPage,
+		"JSON":           `{"status":"ok","count":1}`,
+		"no other field": "192.0.2.0/24\n",
+		"bad network":    "192.0.2.0/24,GB,GB-EN,London,\nexample,GB,GB-EN,London,\n",
+		"an address":     "192.0.2.1,GB,GB-EN,London,\n",
+		emptyFileCase:    "",
+	}
+
+	for name, body := range bodies {
+		t.Run(name, func(t *testing.T) {
+			t.Parallel()
+
+			addresses, err := parse(strings.NewReader(body),
+				FormatICloudPrivateRelayCSV)
+			if err == nil {
+				t.Errorf("parse returned %v and no error", addresses.Ranges())
+			}
+		})
+	}
+}
+
+// TestLookupMarksVPNLists looks up an address on a VPN list and on another
+// list. Only the VPN list's listing says it is one.
+func TestLookupMarksVPNLists(t *testing.T) {
+	t.Parallel()
+
+	_, url := newPublisher(t, goodListBody)
+	vpnList := testList(url, FormatLines)
+	vpnList.Name = "test_vpn_list"
+	vpnList.VPN = true
+	otherList := testList(url, FormatLines)
+
+	b := New(Params{
+		Dir:    t.TempDir(),
+		Lists:  []List{vpnList, otherList},
+		Logger: slog.New(slog.DiscardHandler),
+	})
+
+	for _, list := range b.lists {
+		err := b.download(t.Context(), list)
+		if err != nil {
+			t.Fatalf("download of %s: %v", list.Name, err)
+		}
+	}
+
+	listings := lookup(t, b, listedAddr)
+	if len(listings) != 2 || !listings[0].VPN || listings[1].VPN {
+		t.Errorf("listings %+v, want the first of two marked as a VPN list",
+			listings)
+	}
+}
+
+// TestPublicListsMarkTheVPNLists checks which public lists are VPN lists,
+// since their names are what vpn_providers reports.
+func TestPublicListsMarkTheVPNLists(t *testing.T) {
+	t.Parallel()
+
+	var got []string
+
+	for _, list := range Lists() {
+		if list.VPN {
+			got = append(got, list.Name)
+		}
+	}
+
+	want := []string{
+		"ivpn", "mullvad", "nordvpn", "pia", "protonvpn", "protonvpn_entry",
+		"x4bnet", "x4bnet_v6",
+	}
+	if !slices.Equal(got, want) {
+		t.Errorf("VPN lists %v, want %v", got, want)
+	}
+}
+
+// checkGoodCopyOnDisk checks that dir holds the good version of the test list
+// and no part of a failed download.
+func checkGoodCopyOnDisk(t *testing.T, dir string) {
+	t.Helper()
+
+	copies := os.DirFS(dir)
+
+	onDisk, err := fs.ReadFile(copies, testListName)
+	if err != nil || string(onDisk) != goodListBody {
+		t.Errorf("copy on disk %q (%v), want %q", onDisk, err, goodListBody)
+	}
+
+	_, err = fs.Stat(copies, testListName+downloadSuffix)
+	if !errors.Is(err, fs.ErrNotExist) {
+		t.Errorf("the failed download's file is still there (%v)", err)
+	}
+}
+
+// commentLines is an endless io.Reader of comment lines. It lets a test send
+// a large list file without holding the file in memory.
+type commentLines struct {
+	offset int
+}
+
+func (c *commentLines) Read(p []byte) (int, error) {
+	const line = "# a comment line that pads a large list file\n"
+
+	for filled := 0; filled < len(p); {
+		copied := copy(p[filled:], line[c.offset:])
+		filled += copied
+		c.offset = (c.offset + copied) % len(line)
+	}
+
+	return len(p), nil
+}
+
+// largeListFile returns a reader of a list file of size bytes: comment lines,
+// then newListedAddr on the last line.
+func largeListFile(size int64) io.Reader {
+	lastLine := "\n" + newListedAddr + "\n"
+
+	return io.MultiReader(
+		io.LimitReader(&commentLines{}, size-int64(len(lastLine))),
+		strings.NewReader(lastLine),
+	)
+}
+
+// TestLargeFileUnderTheSizeLimitIsAccepted replaces a list with a 199 MiB
+// file. The address on its last line is listed, so the whole file was read.
+func TestLargeFileUnderTheSizeLimitIsAccepted(t *testing.T) {
+	t.Parallel()
+
+	const size = 199 << 20
+
+	b := newTestIPLists(t.TempDir(), testList("", FormatLines))
+
+	err := b.replaceCopy(b.lists[0], largeListFile(size), validators{})
+	if err != nil {
+		t.Fatalf("replaceCopy: %v", err)
+	}
+
+	if listings := lookup(t, b, newListedAddr); len(listings) != 1 {
+		t.Errorf("listings %+v, want one", listings)
+	}
+}
+
+// TestFileOverTheSizeLimitKeepsThePreviousCopy downloads a good version of a
+// list, then replaces it with a file one byte over the limit. The attempt
+// fails, and the good copy stays in memory and on disk.
+func TestFileOverTheSizeLimitKeepsThePreviousCopy(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	_, url := newPublisher(t, goodListBody)
+	b := newTestIPLists(dir, testList(url, FormatLines))
+
+	err := b.download(t.Context(), b.lists[0])
+	if err != nil {
+		t.Fatalf("download: %v", err)
+	}
+
+	err = b.replaceCopy(b.lists[0], largeListFile(maxDownloadSize+1), validators{})
+	if !errors.Is(err, errTooLarge) {
+		t.Fatalf("replaceCopy: %v, want %v", err, errTooLarge)
+	}
+
+	if listings := lookup(t, b, listedAddr); len(listings) != 1 {
+		t.Errorf("listings of %s %+v, want one", listedAddr, listings)
+	}
+
+	checkGoodCopyOnDisk(t, dir)
+}
+
+// TestRestartLoadsCopiesFromDisk downloads a list, then starts a new
+// IPLists on the same directory, as a restart does. The new one answers
+// from the copy on disk at once, and does not download the list again while
+// the copy is younger than the list's interval.
+func TestRestartLoadsCopiesFromDisk(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	p, url := newPublisher(t, goodListBody)
+	list := testList(url, FormatLines)
+
+	first := newTestIPLists(dir, list)
+
+	err := first.download(t.Context(), list)
+	if err != nil {
+		t.Fatalf("download: %v", err)
+	}
+
+	downloaded := lookup(t, first, listedAddr)[0].Updated
+
+	second := newTestIPLists(dir, list)
+	second.Start(t.Context())
+	second.Stop(t.Context())
+
+	// The download takes its time after writing the file, and the restart
+	// reads the file's time. A busy host can put seconds between the two.
+	const maxUpdatedDifference = 15 * time.Second
+
+	listings := lookup(t, second, listedAddr)
+	if len(listings) != 1 ||
+		listings[0].Updated.Sub(downloaded).Abs() > maxUpdatedDifference {
+		t.Errorf("after the restart, listings %+v, want one updated at %s",
+			listings, downloaded)
+	}
+
+	if got := len(p.requests()); got != 1 {
+		t.Errorf("the publisher had %d requests, want 1", got)
+	}
+}
+
+// TestStartRefreshesAnOldCopy starts on a copy older than its list's
+// interval. The list is downloaded at once, with routewatch's User-Agent and
+// the Last-Modified and ETag the publisher sent with the copy, kept on disk.
+// The publisher answers that the copy is still current, so the copy is kept
+// and marked as updated now.
+func TestStartRefreshesAnOldCopy(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	p, url := newPublisher(t, goodListBody)
+	list := testList(url, FormatLines)
+
+	lastModified := time.Now().Add(-3 * list.Interval).UTC().Truncate(time.Second)
+	p.publish(goodListBody, lastModified, testETag)
+
+	err := newTestIPLists(dir, list).download(t.Context(), list)
+	if err != nil {
+		t.Fatalf("download: %v", err)
+	}
+
+	old := time.Now().Add(-2 * list.Interval).UTC().Truncate(time.Second)
+
+	err = os.Chtimes(filepath.Join(dir, testListName), old, old)
+	if err != nil {
+		t.Fatalf("Chtimes: %v", err)
+	}
+
+	b := newTestIPLists(dir, list)
+	b.Start(t.Context())
+
+	deadline := time.Now().Add(maxWait)
+	for !lookup(t, b, listedAddr)[0].Updated.After(old) {
+		if time.Now().After(deadline) {
+			t.Fatalf("the copy was not marked updated within %s", maxWait)
+		}
+
+		time.Sleep(time.Millisecond)
+	}
+
+	b.Stop(t.Context())
+
+	requests := p.requests()
+	last := requests[len(requests)-1]
+
+	want := lastModified.Format(http.TimeFormat)
+	if got := last.Get(ifModifiedSinceHeader); got != want {
+		t.Errorf("If-Modified-Since %q, want %q", got, want)
+	}
+
+	if got := last.Get(ifNoneMatchHeader); got != testETag {
+		t.Errorf("If-None-Match %q, want %q", got, testETag)
+	}
+
+	if got := last.Get(userAgentHeader); got != userAgent {
+		t.Errorf("User-Agent %q, want %q", got, userAgent)
+	}
+}
+
+// TestNewVersionOlderThanTheLastDownloadReplacesTheCopy downloads a list.
+// The publisher then puts out a new version whose Last-Modified is earlier
+// than that download, as when a cache in front of the publisher passes the
+// version on late. The next download sends the Last-Modified of the copy,
+// not the time of the download, so it gets the new version.
+func TestNewVersionOlderThanTheLastDownloadReplacesTheCopy(t *testing.T) {
+	t.Parallel()
+
+	p, url := newPublisher(t, goodListBody)
+	list := testList(url, FormatLines)
+	b := newTestIPLists(t.TempDir(), list)
+
+	firstVersion := time.Now().Add(-2 * list.Interval).UTC().Truncate(time.Second)
+	p.publish(goodListBody, firstVersion, "")
+
+	err := b.download(t.Context(), list)
+	if err != nil {
+		t.Fatalf("first download: %v", err)
+	}
+
+	p.publish(newListBody, firstVersion.Add(list.Interval), "")
+
+	err = b.download(t.Context(), list)
+	if err != nil {
+		t.Fatalf("second download: %v", err)
+	}
+
+	if listings := lookup(t, b, newListedAddr); len(listings) != 1 {
+		t.Errorf("%s: listings %+v, want one from the new version",
+			newListedAddr, listings)
+	}
+
+	want := firstVersion.Format(http.TimeFormat)
+	if got := p.requests()[1].Get(ifModifiedSinceHeader); got != want {
+		t.Errorf("If-Modified-Since %q, want %q", got, want)
+	}
+}
+
+// TestDownloadWithoutLastModifiedOrETagSendsNoCondition downloads a list
+// twice from a publisher that sends neither Last-Modified nor ETag. Neither
+// request carries If-Modified-Since or If-None-Match, so the second download
+// gets the whole list again.
+func TestDownloadWithoutLastModifiedOrETagSendsNoCondition(t *testing.T) {
+	t.Parallel()
+
+	p, url := newPublisher(t, goodListBody)
+	list := testList(url, FormatLines)
+	b := newTestIPLists(t.TempDir(), list)
+
+	err := b.download(t.Context(), list)
+	if err != nil {
+		t.Fatalf("first download: %v", err)
+	}
+
+	err = b.download(t.Context(), list)
+	if err != nil {
+		t.Fatalf("second download: %v", err)
+	}
+
+	for i, request := range p.requests() {
+		if request.Get(ifModifiedSinceHeader) != "" ||
+			request.Get(ifNoneMatchHeader) != "" {
+			t.Errorf("request %d has a condition: %v", i, request)
+		}
+	}
+}
+
+// TestStopCancelsADownloadInProgress stops while the publisher has not
+// answered. Stop cancels the download and returns once the download
+// goroutine has stopped.
+func TestStopCancelsADownloadInProgress(t *testing.T) {
+	t.Parallel()
+
+	arrived := make(chan struct{})
+
+	var once sync.Once
+
+	srv := httptest.NewServer(http.HandlerFunc(
+		func(_ http.ResponseWriter, r *http.Request) {
+			once.Do(func() { close(arrived) })
+			<-r.Context().Done()
+		}))
+	t.Cleanup(srv.Close)
+
+	b := newTestIPLists(t.TempDir(), testList(srv.URL, FormatLines))
+	b.Start(t.Context())
+
+	select {
+	case <-arrived:
+	case <-time.After(maxWait):
+		t.Fatalf("no download began within %s", maxWait)
+	}
+
+	ctx, cancel := context.WithTimeout(t.Context(), maxWait)
+	defer cancel()
+
+	b.Stop(ctx)
+
+	select {
+	case <-b.done:
+	default:
+		t.Error("Stop returned before the download goroutine stopped")
+	}
+}
+
+// TestTorExitsListHoldsIPv6Exits downloads an Onionoo document as the public
+// Tor exit list, which is what an IPv6 address's is_tor answer comes from.
+func TestTorExitsListHoldsIPv6Exits(t *testing.T) {
+	t.Parallel()
+
+	checkPublicListHolds(t, TorExitsList, onionooBody, onionooIPv6ExitAddr)
+}
+
+// TestICloudPrivateRelayListHoldsItsNetworks downloads a file in Apple's
+// format as the public iCloud Private Relay list, which is what an address's
+// is_relay answer comes from.
+func TestICloudPrivateRelayListHoldsItsNetworks(t *testing.T) {
+	t.Parallel()
+
+	checkPublicListHolds(t, ICloudPrivateRelayList, iCloudPrivateRelayBody,
+		iCloudPrivateRelayAddr)
+}
+
+// checkPublicListHolds downloads body as the public list called name and
+// checks that addr has one listing, which names that list.
+func checkPublicListHolds(t *testing.T, name, body, addr string) {
+	t.Helper()
+
+	index := slices.IndexFunc(Lists(), func(list List) bool {
+		return list.Name == name
+	})
+	if index < 0 {
+		t.Fatalf("no list named %s", name)
+	}
+
+	list := Lists()[index]
+	_, list.URL = newPublisher(t, body)
+	b := newTestIPLists(t.TempDir(), list)
+
+	err := b.download(t.Context(), list)
+	if err != nil {
+		t.Fatalf("download: %v", err)
+	}
+
+	listings := lookup(t, b, addr)
+	if len(listings) != 1 || listings[0].Name != name {
+		t.Errorf("listings %+v, want one for %s", listings, name)
+	}
+}
+
+// TestPublicListsAreComplete checks that every public list has what a
+// download and a lookup answer need, and a unique name.
+func TestPublicListsAreComplete(t *testing.T) {
+	t.Parallel()
+
+	names := make(map[string]bool)
+
+	for _, list := range Lists() {
+		if list.Name == "" || list.Description == "" || list.URL == "" ||
+			list.Interval <= 0 || names[list.Name] {
+			t.Errorf("list %+v is incomplete or has a name used before", list)
+		}
+
+		names[list.Name] = true
+	}
+}

internal/iplist/lists.go

@@ -0,0 +1,209 @@
+package iplist
+
+import (
+	"slices"
+	"time"
+)
+
+// TorExitsList is the name of the list of Tor exit nodes.
+const TorExitsList = "tor_exits"
+
+// ICloudPrivateRelayList is the name of the list of iCloud Private Relay's
+// networks.
+const ICloudPrivateRelayList = "icloud_private_relay"
+
+// protonVPNIPsURL is where the ProtonVPN-IPs mirror publishes its files.
+const protonVPNIPsURL = "https://raw.githubusercontent.com/tn3w/ProtonVPN-IPs/master/"
+
+// How often each list is downloaded. No list is downloaded more often than
+// its publisher updates it or allows.
+const (
+	// DShield asks that its feeds be downloaded at most once an hour:
+	// https://isc.sans.edu/feeds_doc.html
+	dshieldInterval = time.Hour
+
+	// abuse.ch makes the list every 5 minutes and recommends a download at
+	// least every 15: https://feodotracker.abuse.ch/blocklist/
+	feodoTrackerInterval = 15 * time.Minute
+
+	// FireHOL's page for each list gives how often the list changes on
+	// average: about every 5 hours for abusers and every 3 hours for level
+	// 3. FireHOL sets no download limit.
+	// https://iplists.firehol.org/?ipset=firehol_abusers_30d
+	// https://iplists.firehol.org/?ipset=firehol_level3
+	fireHOLAbusersInterval = 5 * time.Hour
+	fireHOLLevel3Interval  = 3 * time.Hour
+
+	// Apple's iCloud Private Relay file is 12 MB, so once a day.
+	iCloudPrivateRelayInterval = 24 * time.Hour
+
+	// Spamhaus asks that DROP be downloaded at most once a day:
+	// https://www.spamhaus.org/blocklists/do-not-route-or-peer/
+	spamhausDROPInterval = 24 * time.Hour
+
+	// Onionoo's relay data follows Tor's hourly network consensus, and
+	// Onionoo sets no download limit:
+	// https://metrics.torproject.org/onionoo.html
+	torExitsInterval = time.Hour
+
+	// A VPN service's servers change slowly, so once a day is enough.
+	vpnListInterval = 24 * time.Hour
+)
+
+// Lists returns the public IP lists routewatch downloads. Each can be
+// downloaded whole without an account or a key. Spamhaus merged its EDROP
+// list into DROP, so DROP covers both.
+func Lists() []List {
+	return slices.Concat(nonVPNLists(), vpnLists())
+}
+
+// nonVPNLists returns the public lists that are not lists of VPN servers.
+func nonVPNLists() []List {
+	return []List{
+		{
+			Name: "dshield",
+			Description: "In one of the 20 networks that DShield saw scan " +
+				"the most targets in the last three days",
+			URL:      "https://feeds.dshield.org/block.txt",
+			Interval: dshieldInterval,
+			Format:   FormatDShield,
+		},
+		{
+			Name:        "feodo_tracker",
+			Description: "A botnet command-and-control server",
+			URL:         "https://feodotracker.abuse.ch/downloads/ipblocklist.txt",
+			Interval:    feodoTrackerInterval,
+			Format:      FormatLines,
+		},
+		{
+			Name: "firehol_abusers_30d",
+			Description: "Reported for comment, form or forum spam in the " +
+				"last 30 days",
+			URL:      "https://iplists.firehol.org/files/firehol_abusers_30d.netset",
+			Interval: fireHOLAbusersInterval,
+			Format:   FormatLines,
+		},
+		{
+			Name: "firehol_level3",
+			Description: "Reported for attacks, spyware or viruses in the " +
+				"last 30 days",
+			URL:      "https://iplists.firehol.org/files/firehol_level3.netset",
+			Interval: fireHOLLevel3Interval,
+			Format:   FormatLines,
+		},
+		{
+			Name:        ICloudPrivateRelayList,
+			Description: "In a network where iCloud Private Relay traffic leaves",
+			URL:         "https://mask-api.icloud.com/egress-ip-ranges.csv",
+			Interval:    iCloudPrivateRelayInterval,
+			Format:      FormatICloudPrivateRelayCSV,
+		},
+		{
+			Name: "spamhaus_drop",
+			Description: "In an IPv4 network that Spamhaus says spammers " +
+				"or cyber criminals have hijacked or lease",
+			URL:      "https://www.spamhaus.org/drop/drop_v4.json",
+			Interval: spamhausDROPInterval,
+			Format:   FormatSpamhausJSON,
+		},
+		{
+			Name: "spamhaus_dropv6",
+			Description: "In an IPv6 network that Spamhaus says spammers " +
+				"or cyber criminals have hijacked or lease",
+			URL:      "https://www.spamhaus.org/drop/drop_v6.json",
+			Interval: spamhausDROPInterval,
+			Format:   FormatSpamhausJSON,
+		},
+		{
+			Name:        TorExitsList,
+			Description: "A Tor exit node, where traffic from the Tor network leaves",
+			URL: "https://onionoo.torproject.org/details?" +
+				"flag=Exit&running=true&fields=exit_addresses,or_addresses",
+			Interval: torExitsInterval,
+			Format:   FormatOnionooJSON,
+		},
+	}
+}
+
+// vpnLists returns the public lists of VPN servers. Their names are what
+// vpn_providers reports.
+func vpnLists() []List {
+	return []List{
+		{
+			Name:        "ivpn",
+			Description: "A server of the IVPN service",
+			URL:         "https://api.ivpn.net/v5/servers.json",
+			Interval:    vpnListInterval,
+			Format:      FormatIVPNJSON,
+			VPN:         true,
+		},
+		{
+			Name:        "mullvad",
+			Description: "A server of the Mullvad VPN service",
+			URL:         "https://api.mullvad.net/www/relays/all/",
+			Interval:    vpnListInterval,
+			Format:      FormatMullvadJSON,
+			VPN:         true,
+		},
+		{
+			Name:        "nordvpn",
+			Description: "A server of the NordVPN service",
+			URL: "https://api.nordvpn.com/v1/servers?limit=0" +
+				"&fields[servers.station]&fields[servers.ipv6_station]" +
+				"&fields[servers.hostname]",
+			Interval: vpnListInterval,
+			Format:   FormatNordVPNJSON,
+			VPN:      true,
+		},
+		{
+			Name:        "pia",
+			Description: "A server of the Private Internet Access VPN service",
+			URL:         "https://serverlist.piaservers.net/vpninfo/servers/v6",
+			Interval:    vpnListInterval,
+			Format:      FormatPIAJSON,
+			VPN:         true,
+		},
+		{
+			// Proton's own server list needs a logged-in session, so this is
+			// the public ProtonVPN-IPs mirror of it. Proton publishes only
+			// the addresses clients connect to. The mirror's README says
+			// traffic leaves from others in the same /24, so this file of
+			// /24 networks is the one it says to use for detecting exits.
+			Name: "protonvpn",
+			Description: "In a /24 network that holds a server of the " +
+				"ProtonVPN service",
+			URL:      protonVPNIPsURL + "protonvpn_ip_ranges.txt",
+			Interval: vpnListInterval,
+			Format:   FormatProtonVPN,
+			VPN:      true,
+		},
+		{
+			Name:        "protonvpn_entry",
+			Description: "A server of the ProtonVPN service",
+			URL:         protonVPNIPsURL + "protonvpn_entry_ips.txt",
+			Interval:    vpnListInterval,
+			Format:      FormatProtonVPN,
+			VPN:         true,
+		},
+		{
+			Name: "x4bnet",
+			Description: "In an IPv4 network of a VPN service, according to " +
+				"X4BNet's community list",
+			URL: "https://raw.githubusercontent.com/X4BNet/lists_vpn/main/" +
+				"output/vpn/ipv4.txt",
+			Interval: vpnListInterval,
+			Format:   FormatLines,
+			VPN:      true,
+		},
+		{
+			Name: "x4bnet_v6",
+			Description: "In an IPv6 network of a VPN service, according to " +
+				"X4BNet's community list",
+			URL: "https://raw.githubusercontent.com/X4BNet/lists_vpn/main/" +
+				"output/vpn/ipv6.txt",
+			Interval: vpnListInterval,
+			Format:   FormatLines,
+			VPN:      true,
+		},
+	}
+}

internal/iplist/parse.go

@@ -0,0 +1,435 @@
+package iplist
+
+import (
+	"bufio"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"net"
+	"net/netip"
+	"slices"
+	"strings"
+
+	"go4.org/netipx"
+)
+
+const (
+	// commentPrefix starts a comment line in a list file.
+	commentPrefix = "#"
+
+	// networkSeparator separates the address and the mask length of a
+	// network, as in 192.0.2.0/24.
+	networkSeparator = "/"
+
+	// dshieldFieldSeparator separates the fields of a DShield line.
+	dshieldFieldSeparator = "\t"
+
+	// iCloudPrivateRelayFieldSeparator separates the fields of a line of
+	// Apple's iCloud Private Relay file.
+	iCloudPrivateRelayFieldSeparator = ","
+
+	// spamhausMetadataType is the type of the line that ends a Spamhaus
+	// file. That line holds the file's metadata and no network.
+	spamhausMetadataType = "metadata"
+)
+
+var (
+	errUnknownFormat = errors.New("unknown list format")
+	errNoNetwork     = errors.New("no network on the line")
+	errBadRange      = errors.New("first and last address make no range")
+	errNoAddresses   = errors.New("no addresses in the document")
+)
+
+// parse reads a list file written in format and returns the addresses it
+// holds. Anything it cannot read fails the whole file, so a file that is not
+// the list, such as an error page, never replaces a good copy.
+func parse(r io.Reader, format Format) (*netipx.IPSet, error) {
+	switch format {
+	case FormatLines:
+		return parseLines(r, addAddressOrNetwork)
+	case FormatSpamhausJSON:
+		return parseLines(r, addSpamhausNetwork)
+	case FormatDShield:
+		return parseLines(r, addDShieldNetwork)
+	case FormatOnionooJSON:
+		return parseOnionoo(r)
+	case FormatMullvadJSON:
+		return parseMullvad(r)
+	case FormatNordVPNJSON:
+		return parseNordVPN(r)
+	case FormatPIAJSON:
+		return parsePIA(r)
+	case FormatIVPNJSON:
+		return parseIVPN(r)
+	case FormatProtonVPN:
+		return parseLinesNotEmpty(r, addAddressOrNetwork)
+	case FormatICloudPrivateRelayCSV:
+		return parseLinesNotEmpty(r, addICloudPrivateRelayNetwork)
+	default:
+		return nil, errUnknownFormat
+	}
+}
+
+// parseLines reads a list file line by line, skipping blank lines and
+// comments, and calls addLine with each other line.
+func parseLines(
+	r io.Reader, addLine func(*netipx.IPSetBuilder, string) error,
+) (*netipx.IPSet, error) {
+	var builder netipx.IPSetBuilder
+
+	scanner := bufio.NewScanner(r)
+
+	for lineNumber := 1; scanner.Scan(); lineNumber++ {
+		line := strings.TrimSpace(scanner.Text())
+		if line == "" || strings.HasPrefix(line, commentPrefix) {
+			continue
+		}
+
+		err := addLine(&builder, line)
+		if err != nil {
+			return nil, fmt.Errorf("line %d: %w", lineNumber, err)
+		}
+	}
+
+	err := scanner.Err()
+	if err != nil {
+		return nil, err
+	}
+
+	return builder.IPSet()
+}
+
+// addAddressOrNetwork adds an address, such as 192.0.2.1, or a network, such
+// as 192.0.2.0/24, to builder.
+func addAddressOrNetwork(builder *netipx.IPSetBuilder, text string) error {
+	if strings.Contains(text, networkSeparator) {
+		network, err := netip.ParsePrefix(text)
+		if err != nil {
+			return err
+		}
+
+		builder.AddPrefix(network)
+
+		return nil
+	}
+
+	addr, err := netip.ParseAddr(text)
+	if err != nil {
+		return err
+	}
+
+	builder.Add(addr)
+
+	return nil
+}
+
+// addSpamhausNetwork adds the network on a line of a Spamhaus file to
+// builder. The metadata line adds nothing.
+func addSpamhausNetwork(builder *netipx.IPSetBuilder, line string) error {
+	var entry struct {
+		CIDR string `json:"cidr"`
+		Type string `json:"type"`
+	}
+
+	err := json.Unmarshal([]byte(line), &entry)
+	if err != nil {
+		return err
+	}
+
+	if entry.Type == spamhausMetadataType {
+		return nil
+	}
+
+	network, err := netip.ParsePrefix(entry.CIDR)
+	if err != nil {
+		return err
+	}
+
+	builder.AddPrefix(network)
+
+	return nil
+}
+
+// addDShieldNetwork adds the network on a line of a DShield file to builder.
+// The line's first two fields are the network's first and last address.
+func addDShieldNetwork(builder *netipx.IPSetBuilder, line string) error {
+	firstField, rest, found := strings.Cut(line, dshieldFieldSeparator)
+	if !found {
+		return errNoNetwork
+	}
+
+	lastField, _, _ := strings.Cut(rest, dshieldFieldSeparator)
+
+	first, err := netip.ParseAddr(firstField)
+	if err != nil {
+		return err
+	}
+
+	last, err := netip.ParseAddr(lastField)
+	if err != nil {
+		return err
+	}
+
+	network := netipx.IPRangeFrom(first, last)
+	if !network.IsValid() {
+		return errBadRange
+	}
+
+	builder.AddRange(network)
+
+	return nil
+}
+
+// parseOnionoo returns every address in the exit_addresses and or_addresses
+// fields of the relays in an Onionoo details document. A document with no
+// addresses fails, because the Tor network always has relays.
+func parseOnionoo(r io.Reader) (*netipx.IPSet, error) {
+	//nolint:tagliatelle // Onionoo's own field names
+	var details struct {
+		Relays []struct {
+			ExitAddresses []string `json:"exit_addresses"`
+			ORAddresses   []string `json:"or_addresses"`
+		} `json:"relays"`
+	}
+
+	err := readJSON(r, &details)
+	if err != nil {
+		return nil, err
+	}
+
+	var builder netipx.IPSetBuilder
+
+	for _, relay := range details.Relays {
+		for _, text := range relay.ExitAddresses {
+			err = addAddress(&builder, text)
+			if err != nil {
+				return nil, err
+			}
+		}
+
+		for _, text := range relay.ORAddresses {
+			err = addAddressWithPort(&builder, text)
+			if err != nil {
+				return nil, err
+			}
+		}
+	}
+
+	addresses, err := builder.IPSet()
+	if err != nil {
+		return nil, err
+	}
+
+	if len(addresses.Ranges()) == 0 {
+		return nil, errNoAddresses
+	}
+
+	return addresses, nil
+}
+
+// parseMullvad returns the addresses of the relays in a Mullvad document. A
+// relay with no IPv6 address has null for it, and only bridges have
+// ipv4_v2ray.
+func parseMullvad(r io.Reader) (*netipx.IPSet, error) {
+	//nolint:tagliatelle // Mullvad's own field names
+	var relays []struct {
+		IPv4      string `json:"ipv4_addr_in"`
+		IPv6      string `json:"ipv6_addr_in"`
+		IPv4V2Ray string `json:"ipv4_v2ray"`
+	}
+
+	err := readJSON(r, &relays)
+	if err != nil {
+		return nil, err
+	}
+
+	var texts []string
+
+	for _, relay := range relays {
+		texts = append(texts, relay.IPv4, relay.IPv6, relay.IPv4V2Ray)
+	}
+
+	return addressSet(texts)
+}
+
+// parseNordVPN returns the addresses of the servers in a NordVPN document. A
+// server with no IPv6 address has an empty ipv6_station.
+func parseNordVPN(r io.Reader) (*netipx.IPSet, error) {
+	//nolint:tagliatelle // NordVPN's own field names
+	var servers []struct {
+		Station     string `json:"station"`
+		IPv6Station string `json:"ipv6_station"`
+	}
+
+	err := readJSON(r, &servers)
+	if err != nil {
+		return nil, err
+	}
+
+	var texts []string
+
+	for _, server := range servers {
+		texts = append(texts, server.Station, server.IPv6Station)
+	}
+
+	return addressSet(texts)
+}
+
+// parsePIA returns the addresses of the servers in a Private Internet Access
+// document. json.Decoder stops at the end of the JSON, so the signature after
+// it is not read.
+func parsePIA(r io.Reader) (*netipx.IPSet, error) {
+	var list struct {
+		Regions []struct {
+			Servers map[string][]struct {
+				IP string `json:"ip"`
+			} `json:"servers"`
+		} `json:"regions"`
+	}
+
+	err := json.NewDecoder(r).Decode(&list)
+	if err != nil {
+		return nil, err
+	}
+
+	var texts []string
+
+	for _, region := range list.Regions {
+		for _, servers := range region.Servers {
+			for _, server := range servers {
+				texts = append(texts, server.IP)
+			}
+		}
+	}
+
+	return addressSet(texts)
+}
+
+// parseIVPN returns the addresses of the hosts in an IVPN document. A host's
+// ipv6 object holds only an address inside the VPN, so it is not read.
+func parseIVPN(r io.Reader) (*netipx.IPSet, error) {
+	type gateway struct {
+		Hosts []struct {
+			Host  string `json:"host"`
+			V2Ray string `json:"v2ray"`
+		} `json:"hosts"`
+	}
+
+	var list struct {
+		WireGuard []gateway `json:"wireguard"`
+		OpenVPN   []gateway `json:"openvpn"`
+	}
+
+	err := readJSON(r, &list)
+	if err != nil {
+		return nil, err
+	}
+
+	var texts []string
+
+	for _, gw := range slices.Concat(list.WireGuard, list.OpenVPN) {
+		for _, host := range gw.Hosts {
+			texts = append(texts, host.Host, host.V2Ray)
+		}
+	}
+
+	return addressSet(texts)
+}
+
+// parseLinesNotEmpty is parseLines for a list that always holds addresses, so
+// a file with none fails.
+func parseLinesNotEmpty(
+	r io.Reader, addLine func(*netipx.IPSetBuilder, string) error,
+) (*netipx.IPSet, error) {
+	addresses, err := parseLines(r, addLine)
+	if err != nil {
+		return nil, err
+	}
+
+	if len(addresses.Ranges()) == 0 {
+		return nil, errNoAddresses
+	}
+
+	return addresses, nil
+}
+
+// addICloudPrivateRelayNetwork adds the network at the start of a line of
+// Apple's iCloud Private Relay file to builder.
+func addICloudPrivateRelayNetwork(builder *netipx.IPSetBuilder, line string) error {
+	field, _, found := strings.Cut(line, iCloudPrivateRelayFieldSeparator)
+	if !found {
+		return errNoNetwork
+	}
+
+	network, err := netip.ParsePrefix(field)
+	if err != nil {
+		return err
+	}
+
+	builder.AddPrefix(network)
+
+	return nil
+}
+
+// readJSON reads r to its end and decodes it, as one JSON document, into v.
+func readJSON(r io.Reader, v any) error {
+	data, err := io.ReadAll(r)
+	if err != nil {
+		return err
+	}
+
+	return json.Unmarshal(data, v)
+}
+
+// addressSet returns the set of the addresses in texts, skipping empty ones.
+// A list with no addresses fails, because every VPN service has servers.
+func addressSet(texts []string) (*netipx.IPSet, error) {
+	var builder netipx.IPSetBuilder
+
+	for _, text := range texts {
+		if text == "" {
+			continue
+		}
+
+		err := addAddress(&builder, text)
+		if err != nil {
+			return nil, err
+		}
+	}
+
+	addresses, err := builder.IPSet()
+	if err != nil {
+		return nil, err
+	}
+
+	if len(addresses.Ranges()) == 0 {
+		return nil, errNoAddresses
+	}
+
+	return addresses, nil
+}
+
+// addAddress adds an address, such as 192.0.2.1, to builder.
+func addAddress(builder *netipx.IPSetBuilder, text string) error {
+	addr, err := netip.ParseAddr(text)
+	if err != nil {
+		return err
+	}
+
+	builder.Add(addr)
+
+	return nil
+}
+
+// addAddressWithPort adds the address of text, such as 192.0.2.1:443 or
+// [2001:db8::1]:443, to builder. Onionoo allows a list of ports after the
+// address, so the part after the address is not read.
+func addAddressWithPort(builder *netipx.IPSetBuilder, text string) error {
+	host, _, err := net.SplitHostPort(text)
+	if err != nil {
+		return err
+	}
+
+	return addAddress(builder, host)
+}

internal/ptr/cache.go

@@ -0,0 +1,324 @@
+// Package ptr looks up the PTR names of addresses over DNS-over-HTTPS. It
+// keeps answers in memory for as long as DNS allows, and in cache.db so that
+// the answers survive a restart.
+package ptr
+
+import (
+	"context"
+	"database/sql"
+	"fmt"
+	"log/slog"
+	"maps"
+	"net/http"
+	"net/netip"
+	"slices"
+	"strings"
+	"sync"
+	"time"
+
+	"git.eeqj.de/sneak/routewatch/internal/bogon"
+	"github.com/miekg/dns"
+)
+
+const (
+	// flushInterval is how often new answers are written to cache.db.
+	flushInterval = 5 * time.Second
+
+	// sweepInterval is how often expired answers are deleted.
+	sweepInterval = 10 * time.Minute
+
+	// nameSeparator separates the names in a row of the hostnames table.
+	nameSeparator = " "
+
+	// maxAddresses limits how many addresses the cache holds, so that a public
+	// lookup cannot grow memory and cache.db without bound.
+	maxAddresses = 250_000
+)
+
+// Params is what New needs.
+type Params struct {
+	// DB is the open cache.db.
+	DB *sql.DB
+
+	// Resolvers are the URLs of the DNS-over-HTTPS resolvers to ask, in order.
+	Resolvers []string
+
+	Logger *slog.Logger
+}
+
+// entry is one address's cached answer.
+type entry struct {
+	// names are the address's PTR names, nil when it has none.
+	names   []string
+	expires time.Time
+}
+
+// Cache answers PTR lookups from memory, and asks the resolvers for an address
+// it holds no current answer for. Start loads it from cache.db.
+type Cache struct {
+	db         *sql.DB
+	resolvers  []string
+	timeLimit  time.Duration
+	maxEntries int
+	logger     *slog.Logger
+	client     *http.Client
+	now        func() time.Time
+
+	// entries holds the kept answers by address, at most maxEntries of them.
+	// pending holds those that cache.db does not have yet.
+	mu      sync.RWMutex
+	entries map[string]entry
+	pending map[string]entry
+
+	// stop ends the goroutine Start runs, and done is closed when it returns.
+	stop context.CancelFunc
+	done chan struct{}
+}
+
+// New returns an empty Cache. Start loads it.
+func New(params Params) *Cache {
+	return &Cache{
+		db:         params.DB,
+		resolvers:  params.Resolvers,
+		timeLimit:  LookupTimeout,
+		maxEntries: maxAddresses,
+		logger:     params.Logger.With("component", "ptr"),
+		client:     &http.Client{},
+		now:        time.Now,
+		entries:    make(map[string]entry),
+		pending:    make(map[string]entry),
+		done:       make(chan struct{}),
+	}
+}
+
+// LookupAddr returns the PTR names of addr, fully qualified, or none when it
+// has none. A reserved address has none, and is not sent to the resolvers. A
+// lookup takes at most LookupTimeout. A cached answer makes no outside request.
+// It returns an error when no resolver answered, and nothing is cached then.
+func (c *Cache) LookupAddr(ctx context.Context, addr string) ([]string, error) {
+	parsed, err := netip.ParseAddr(addr)
+	if err != nil {
+		return nil, fmt.Errorf("parsing the address: %w", err)
+	}
+
+	_, reserved := bogon.Addr(parsed)
+	if reserved {
+		return []string{}, nil
+	}
+
+	address := parsed.Unmap().String()
+
+	cached, ok := c.current(address)
+	if ok {
+		return slices.Clone(cached.names), nil
+	}
+
+	reverseName, err := dns.ReverseAddr(address)
+	if err != nil {
+		return nil, fmt.Errorf("building the reverse name: %w", err)
+	}
+
+	result, err := c.lookup(ctx, reverseName)
+	if err != nil {
+		return nil, err
+	}
+
+	if result.ttl > 0 {
+		c.store(address, entry{names: result.names, expires: c.now().Add(result.ttl)})
+	}
+
+	return slices.Clone(result.names), nil
+}
+
+// Start loads the answers that have not expired from cache.db. It then starts
+// the goroutine that writes new answers there and deletes expired ones. The
+// goroutine runs until Stop: the end of ctx does not stop it.
+func (c *Cache) Start(ctx context.Context) error {
+	err := c.load(ctx)
+	if err != nil {
+		return err
+	}
+
+	c.logger.Info("PTR cache loaded", "entries", len(c.entries))
+
+	ctx, c.stop = context.WithCancel(context.WithoutCancel(ctx))
+
+	go c.run(ctx)
+
+	return nil
+}
+
+// Stop ends the goroutine, which first writes the answers cache.db does not
+// have yet, and waits until it has returned or ctx ends.
+func (c *Cache) Stop(ctx context.Context) {
+	c.stop()
+
+	select {
+	case <-c.done:
+		c.logger.Info("PTR cache stopped")
+	case <-ctx.Done():
+		c.logger.Warn("Stop deadline passed before the PTR cache was written")
+	}
+}
+
+// current returns the answer held for address, unless it has expired.
+func (c *Cache) current(address string) (entry, bool) {
+	c.mu.RLock()
+	defer c.mu.RUnlock()
+
+	found, ok := c.entries[address]
+	if !ok || !c.now().Before(found.expires) {
+		return entry{}, false
+	}
+
+	return found, true
+}
+
+// store keeps an answer in memory and queues it for cache.db. Once entries
+// holds maxEntries addresses it keeps no new address. It still replaces the
+// answer of an address already held.
+func (c *Cache) store(address string, answer entry) {
+	c.mu.Lock()
+	defer c.mu.Unlock()
+
+	_, held := c.entries[address]
+	if !held && len(c.entries) >= c.maxEntries {
+		return
+	}
+
+	c.entries[address] = answer
+	c.pending[address] = answer
+}
+
+// run writes new answers and deletes expired ones until ctx ends.
+func (c *Cache) run(ctx context.Context) {
+	defer close(c.done)
+
+	flushes := time.NewTicker(flushInterval)
+	defer flushes.Stop()
+
+	sweeps := time.NewTicker(sweepInterval)
+	defer sweeps.Stop()
+
+	for {
+		select {
+		case <-ctx.Done():
+			c.flush(context.WithoutCancel(ctx))
+
+			return
+		case <-flushes.C:
+			c.flush(ctx)
+		case <-sweeps.C:
+			c.sweep(ctx)
+		}
+	}
+}
+
+// load reads the rows that have not expired into memory.
+func (c *Cache) load(ctx context.Context) error {
+	rows, err := c.db.QueryContext(ctx,
+		"SELECT address, names, expires_at FROM hostnames WHERE expires_at > ?",
+		c.now().Unix())
+	if err != nil {
+		return fmt.Errorf("reading the PTR cache: %w", err)
+	}
+
+	defer func() { _ = rows.Close() }()
+
+	for rows.Next() {
+		var (
+			address, names string
+			expires        int64
+		)
+
+		err = rows.Scan(&address, &names, &expires)
+		if err != nil {
+			return fmt.Errorf("reading a PTR cache row: %w", err)
+		}
+
+		c.entries[address] = entry{
+			names:   strings.Fields(names),
+			expires: time.Unix(expires, 0).UTC(),
+		}
+	}
+
+	err = rows.Err()
+	if err != nil {
+		return fmt.Errorf("reading the PTR cache: %w", err)
+	}
+
+	return nil
+}
+
+// flush writes the pending answers to cache.db. Those it cannot write stay
+// pending, unless a newer answer for the address has arrived meanwhile.
+func (c *Cache) flush(ctx context.Context) {
+	c.mu.Lock()
+	batch := c.pending
+	c.pending = make(map[string]entry)
+	c.mu.Unlock()
+
+	if len(batch) == 0 {
+		return
+	}
+
+	err := c.writeRows(ctx, batch)
+	if err == nil {
+		return
+	}
+
+	c.logger.Error("Failed to write the PTR cache", "error", err)
+
+	c.mu.Lock()
+	defer c.mu.Unlock()
+
+	for address, answer := range batch {
+		_, newer := c.pending[address]
+		if !newer {
+			c.pending[address] = answer
+		}
+	}
+}
+
+// writeRows writes batch to cache.db in one transaction.
+func (c *Cache) writeRows(ctx context.Context, batch map[string]entry) error {
+	tx, err := c.db.BeginTx(ctx, nil)
+	if err != nil {
+		return err
+	}
+
+	defer func() { _ = tx.Rollback() }()
+
+	for address, answer := range batch {
+		_, err = tx.ExecContext(ctx,
+			"INSERT OR REPLACE INTO hostnames (address, names, expires_at) "+
+				"VALUES (?, ?, ?)",
+			address,
+			strings.Join(answer.names, nameSeparator),
+			answer.expires.Unix())
+		if err != nil {
+			return err
+		}
+	}
+
+	return tx.Commit()
+}
+
+// sweep deletes the expired answers from memory and cache.db.
+func (c *Cache) sweep(ctx context.Context) {
+	now := c.now()
+	expired := func(_ string, answer entry) bool {
+		return !now.Before(answer.expires)
+	}
+
+	c.mu.Lock()
+	maps.DeleteFunc(c.entries, expired)
+	maps.DeleteFunc(c.pending, expired)
+	c.mu.Unlock()
+
+	_, err := c.db.ExecContext(ctx,
+		"DELETE FROM hostnames WHERE expires_at <= ?", now.Unix())
+	if err != nil {
+		c.logger.Error("Failed to delete expired PTR cache rows", "error", err)
+	}
+}

internal/ptr/cache_internal_test.go

@@ -0,0 +1,951 @@
+package ptr
+
+import (
+	"context"
+	"database/sql"
+	"errors"
+	"io"
+	"log/slog"
+	"net/http"
+	"net/http/httptest"
+	"slices"
+	"strconv"
+	"sync"
+	"testing"
+	"testing/synctest"
+	"time"
+
+	"git.eeqj.de/sneak/routewatch/internal/cachedb"
+	"github.com/miekg/dns"
+)
+
+// These addresses are public, because a reserved address is not sent to the
+// resolvers. That rules out the documentation ranges.
+const (
+	testAddress   = "8.8.4.4"
+	testReverse   = "4.4.8.8.in-addr.arpa."
+	mappedAddress = "::ffff:" + testAddress
+	otherAddress  = "8.8.8.8"
+	testV6Address = "2606:4700:4700::1111"
+	testV6Reverse = "1.1.1.1.0.0.0.0.0.0.0.0.0.0.0.0." +
+		"0.0.0.0.0.0.7.4.0.0.7.4.6.0.6.2.ip6.arpa."
+)
+
+const (
+	testName  = "host.example.com."
+	otherName = "other.example.com."
+
+	// testTimeLimit replaces LookupTimeout in the tests that use a real
+	// server. A stall on a busy host cannot use it up, and no test waits for
+	// it.
+	testTimeLimit = 2 * time.Minute
+)
+
+// classlessOwner is the name that holds the PTR records of a CNAME chain.
+const classlessOwner = "4.0-25.4.8.8.in-addr.arpa."
+
+// fixedTime returns the time a test's clock starts at.
+func fixedTime() time.Time {
+	return time.Date(2026, time.January, 2, 3, 4, 5, 0, time.UTC)
+}
+
+// fakeResolver is a DNS-over-HTTPS server. It answers each query with reply's
+// result, and counts its requests.
+type fakeResolver struct {
+	server *httptest.Server
+
+	mu       sync.Mutex
+	requests int
+	reply    func(http.ResponseWriter, *http.Request, *dns.Msg)
+}
+
+// newFakeResolver starts a fake resolver that answers with reply.
+func newFakeResolver(
+	t *testing.T,
+	reply func(http.ResponseWriter, *http.Request, *dns.Msg),
+) *fakeResolver {
+	t.Helper()
+
+	resolver := &fakeResolver{reply: reply}
+	resolver.server = httptest.NewServer(http.HandlerFunc(resolver.serve))
+	t.Cleanup(resolver.server.Close)
+
+	return resolver
+}
+
+// serve checks that the request is RFC 8484 wire format and passes the
+// question on to the current reply.
+func (f *fakeResolver) serve(w http.ResponseWriter, r *http.Request) {
+	f.mu.Lock()
+	f.requests++
+	reply := f.reply
+	f.mu.Unlock()
+
+	body, err := io.ReadAll(r.Body)
+	if err != nil {
+		http.Error(w, err.Error(), http.StatusBadRequest)
+
+		return
+	}
+
+	var query dns.Msg
+
+	err = query.Unpack(body)
+	if err != nil || r.Header.Get("Content-Type") != dnsMessageType ||
+		r.Header.Get("Accept") != dnsMessageType || r.Method != http.MethodPost {
+		http.Error(w, "not an RFC 8484 request", http.StatusBadRequest)
+
+		return
+	}
+
+	reply(w, r, &query)
+}
+
+func (f *fakeResolver) setReply(
+	reply func(http.ResponseWriter, *http.Request, *dns.Msg),
+) {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+
+	f.reply = reply
+}
+
+func (f *fakeResolver) requestCount() int {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+
+	return f.requests
+}
+
+// writeReply packs reply and writes it as the answer to query.
+func writeReply(w http.ResponseWriter, query, reply *dns.Msg) {
+	reply.SetReply(query)
+
+	wire, err := reply.Pack()
+	if err != nil {
+		http.Error(w, err.Error(), http.StatusInternalServerError)
+
+		return
+	}
+
+	w.Header().Set("Content-Type", dnsMessageType)
+	_, _ = w.Write(wire)
+}
+
+// ptrReply answers with one PTR record for each name, each with the TTL ttl.
+func ptrReply(
+	ttl uint32, names ...string,
+) func(http.ResponseWriter, *http.Request, *dns.Msg) {
+	return func(w http.ResponseWriter, _ *http.Request, query *dns.Msg) {
+		reply := new(dns.Msg)
+
+		for _, name := range names {
+			reply.Answer = append(reply.Answer, &dns.PTR{
+				Hdr: dns.RR_Header{
+					Name: query.Question[0].Name, Rrtype: dns.TypePTR,
+					Class: dns.ClassINET, Ttl: ttl,
+				},
+				Ptr: name,
+			})
+		}
+
+		writeReply(w, query, reply)
+	}
+}
+
+// rcodeReply answers with the response code and nothing else.
+func rcodeReply(rcode int) func(http.ResponseWriter, *http.Request, *dns.Msg) {
+	return func(w http.ResponseWriter, _ *http.Request, query *dns.Msg) {
+		reply := new(dns.Msg)
+		reply.SetRcode(query, rcode)
+
+		wire, err := reply.Pack()
+		if err != nil {
+			http.Error(w, err.Error(), http.StatusInternalServerError)
+
+			return
+		}
+
+		_, _ = w.Write(wire)
+	}
+}
+
+// soaReply answers with the response code and a SOA record with these TTLs.
+func soaReply(
+	rcode int, soaTTL, minimum uint32,
+) func(http.ResponseWriter, *http.Request, *dns.Msg) {
+	return func(w http.ResponseWriter, _ *http.Request, query *dns.Msg) {
+		reply := new(dns.Msg)
+		reply.SetRcode(query, rcode)
+		reply.Ns = []dns.RR{&dns.SOA{
+			Hdr: dns.RR_Header{
+				Name: "arpa.", Rrtype: dns.TypeSOA, Class: dns.ClassINET, Ttl: soaTTL,
+			},
+			Ns: "ns.example.com.", Mbox: "hostmaster.example.com.", Minttl: minimum,
+		}}
+
+		wire, err := reply.Pack()
+		if err != nil {
+			http.Error(w, err.Error(), http.StatusInternalServerError)
+
+			return
+		}
+
+		_, _ = w.Write(wire)
+	}
+}
+
+// hangingReply never answers: it waits until the client gives up.
+func hangingReply(_ http.ResponseWriter, r *http.Request, _ *dns.Msg) {
+	<-r.Context().Done()
+}
+
+// statusReply answers with an HTTP status.
+func statusReply(status int) func(http.ResponseWriter, *http.Request, *dns.Msg) {
+	return func(w http.ResponseWriter, _ *http.Request, _ *dns.Msg) {
+		w.WriteHeader(status)
+	}
+}
+
+// openTestDB opens a cache.db in dir.
+func openTestDB(t *testing.T, dir string) *sql.DB {
+	t.Helper()
+
+	db, err := cachedb.Open(t.Context(), dir)
+	if err != nil {
+		t.Fatalf("opening the cache database: %v", err)
+	}
+
+	t.Cleanup(func() { _ = db.Close() })
+
+	return db
+}
+
+// testClock is a clock a test moves by hand.
+type testClock struct {
+	mu  sync.Mutex
+	now time.Time
+}
+
+func (c *testClock) time() time.Time {
+	c.mu.Lock()
+	defer c.mu.Unlock()
+
+	return c.now
+}
+
+func (c *testClock) advance(d time.Duration) {
+	c.mu.Lock()
+	defer c.mu.Unlock()
+
+	c.now = c.now.Add(d)
+}
+
+// newTestCache returns a Cache that asks the resolvers in order, reads the
+// time from a clock the test holds, has testTimeLimit, and is not started.
+func newTestCache(
+	t *testing.T, db *sql.DB, resolvers ...*fakeResolver,
+) (*Cache, *testClock) {
+	t.Helper()
+
+	urls := make([]string, 0, len(resolvers))
+	for _, resolver := range resolvers {
+		urls = append(urls, resolver.server.URL)
+	}
+
+	cache := New(Params{DB: db, Resolvers: urls, Logger: slog.Default()})
+	clock := &testClock{now: fixedTime()}
+	cache.now = clock.time
+	cache.timeLimit = testTimeLimit
+
+	return cache, clock
+}
+
+// handlerTransport hands each request to the fake resolver for its host, with
+// no network between them. A test in a synctest bubble needs this: the bubble's
+// clock stands still while one of its goroutines waits on a real connection. As
+// over a network, a request whose time is up is not sent.
+type handlerTransport map[string]*fakeResolver
+
+func (h handlerTransport) RoundTrip(r *http.Request) (*http.Response, error) {
+	recorder := httptest.NewRecorder()
+
+	if r.Context().Err() == nil {
+		h[r.URL.Host].serve(recorder, r)
+	}
+
+	err := r.Context().Err()
+	if err != nil {
+		return nil, err
+	}
+
+	return recorder.Result(), nil
+}
+
+// newBubbleCache returns a Cache with the real time limit, for a test in a
+// synctest bubble. It has one fake resolver for each reply, in order, reached
+// through a handlerTransport.
+func newBubbleCache(
+	replies ...func(http.ResponseWriter, *http.Request, *dns.Msg),
+) (*Cache, []*fakeResolver) {
+	transport := make(handlerTransport, len(replies))
+	resolvers := make([]*fakeResolver, 0, len(replies))
+	urls := make([]string, 0, len(replies))
+
+	for i, reply := range replies {
+		host := "resolver" + strconv.Itoa(i) + ".example.com"
+		resolver := &fakeResolver{reply: reply}
+
+		transport[host] = resolver
+		resolvers = append(resolvers, resolver)
+		urls = append(urls, "https://"+host+"/dns-query")
+	}
+
+	cache := New(Params{Resolvers: urls, Logger: slog.Default()})
+	cache.client = &http.Client{Transport: transport}
+
+	return cache, resolvers
+}
+
+// lookupOK looks up address and fails the test on an error.
+func lookupOK(t *testing.T, cache *Cache, address string) []string {
+	t.Helper()
+
+	names, err := cache.LookupAddr(t.Context(), address)
+	if err != nil {
+		t.Fatalf("LookupAddr(%s): %v", address, err)
+	}
+
+	return names
+}
+
+func countRows(t *testing.T, db *sql.DB) int {
+	t.Helper()
+
+	var rows int
+
+	err := db.QueryRowContext(t.Context(),
+		"SELECT COUNT(*) FROM hostnames").Scan(&rows)
+	if err != nil {
+		t.Fatalf("counting rows: %v", err)
+	}
+
+	return rows
+}
+
+func TestLookupAsksForTheReverseName(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		address string
+		want    string
+	}{
+		{testAddress, testReverse},
+		{mappedAddress, testReverse},
+		{testV6Address, testV6Reverse},
+	}
+
+	for _, tt := range tests {
+		var asked string
+
+		resolver := newFakeResolver(t,
+			func(w http.ResponseWriter, r *http.Request, query *dns.Msg) {
+				asked = query.Question[0].Name
+				if query.Question[0].Qtype != dns.TypePTR {
+					t.Errorf("query type %d, want PTR", query.Question[0].Qtype)
+				}
+
+				ptrReply(300, testName)(w, r, query)
+			})
+		cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
+
+		names := lookupOK(t, cache, tt.address)
+		if !slices.Equal(names, []string{testName}) {
+			t.Errorf("%s: names %v, want %s", tt.address, names, testName)
+		}
+
+		if asked != tt.want {
+			t.Errorf("%s: asked for %s, want %s", tt.address, asked, tt.want)
+		}
+	}
+}
+
+// TestOnlyPublicAddressesAreSentToTheResolvers gives every resolver an answer
+// to send, which a reserved address must not get.
+func TestOnlyPublicAddressesAreSentToTheResolvers(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name     string
+		address  string
+		want     []string
+		requests int
+	}{
+		{"private IPv4", "10.0.0.1", []string{}, 0},
+		{"documentation IPv4", "192.0.2.1", []string{}, 0},
+		{"private IPv4 in IPv6 form", "::ffff:10.0.0.1", []string{}, 0},
+		{"unique-local IPv6", "fd00::1", []string{}, 0},
+		{"documentation IPv6", "2001:db8::1", []string{}, 0},
+		{"public IPv4", testAddress, []string{testName}, 1},
+		{"public IPv4 in IPv6 form", mappedAddress, []string{testName}, 1},
+		{"public IPv6", testV6Address, []string{testName}, 1},
+	}
+
+	for _, tt := range tests {
+		resolver := newFakeResolver(t, ptrReply(300, testName))
+		cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
+
+		names := lookupOK(t, cache, tt.address)
+		if names == nil || !slices.Equal(names, tt.want) {
+			t.Errorf("%s: names %#v, want %#v", tt.name, names, tt.want)
+		}
+
+		if got := resolver.requestCount(); got != tt.requests {
+			t.Errorf("%s: %d requests, want %d", tt.name, got, tt.requests)
+		}
+	}
+}
+
+// TestResolversAreTriedInOrderUntilOneAnswers has the first two resolvers fail,
+// in different ways, and the third answer. The fourth is not asked.
+func TestResolversAreTriedInOrderUntilOneAnswers(t *testing.T) {
+	t.Parallel()
+
+	var (
+		mu    sync.Mutex
+		order []int
+	)
+
+	asked := func(
+		index int, reply func(http.ResponseWriter, *http.Request, *dns.Msg),
+	) func(http.ResponseWriter, *http.Request, *dns.Msg) {
+		return func(w http.ResponseWriter, r *http.Request, query *dns.Msg) {
+			mu.Lock()
+
+			order = append(order, index)
+
+			mu.Unlock()
+
+			reply(w, r, query)
+		}
+	}
+
+	resolvers := []*fakeResolver{
+		newFakeResolver(t, asked(0, statusReply(http.StatusServiceUnavailable))),
+		newFakeResolver(t, asked(1, rcodeReply(dns.RcodeServerFailure))),
+		newFakeResolver(t, asked(2, ptrReply(300, testName))),
+		newFakeResolver(t, asked(3, ptrReply(300, otherName))),
+	}
+	cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), resolvers...)
+
+	names := lookupOK(t, cache, testAddress)
+	if !slices.Equal(names, []string{testName}) {
+		t.Errorf("names %v, want %s", names, testName)
+	}
+
+	if !slices.Equal(order, []int{0, 1, 2}) {
+		t.Errorf("resolvers asked %v, want [0 1 2]", order)
+	}
+}
+
+// TestResolverThatNeverAnswersLeavesTimeForTheNext would fail if the first
+// resolver could take the whole time limit. The first gets half of it, the
+// share of one resolver in two. The test runs in a synctest bubble, whose clock
+// is fake, so a stall on the host uses none of the limit.
+func TestResolverThatNeverAnswersLeavesTimeForTheNext(t *testing.T) {
+	t.Parallel()
+
+	synctest.Test(t, func(t *testing.T) {
+		cache, _ := newBubbleCache(hangingReply, ptrReply(300, testName))
+
+		start := time.Now()
+		names := lookupOK(t, cache, testAddress)
+		elapsed := time.Since(start)
+
+		if !slices.Equal(names, []string{testName}) {
+			t.Errorf("names %v, want %s", names, testName)
+		}
+
+		if elapsed != time.Second {
+			t.Errorf("took %s, want 1s", elapsed)
+		}
+	})
+}
+
+// TestLookupStopsAtTheTimeLimit has no resolver answer. The lookup fails when
+// 2 seconds have passed, having asked every resolver. The test runs in a
+// synctest bubble, whose clock is fake, so a stall on the host uses none of the
+// limit.
+func TestLookupStopsAtTheTimeLimit(t *testing.T) {
+	t.Parallel()
+
+	synctest.Test(t, func(t *testing.T) {
+		cache, resolvers := newBubbleCache(
+			hangingReply, hangingReply, hangingReply, hangingReply)
+
+		start := time.Now()
+		_, err := cache.LookupAddr(t.Context(), testAddress)
+		elapsed := time.Since(start)
+
+		if !errors.Is(err, context.DeadlineExceeded) {
+			t.Errorf("error %v, want %v", err, context.DeadlineExceeded)
+		}
+
+		if elapsed != 2*time.Second {
+			t.Errorf("took %s, want 2s", elapsed)
+		}
+
+		for i, resolver := range resolvers {
+			if resolver.requestCount() != 1 {
+				t.Errorf("resolver %d asked %d times, want once",
+					i, resolver.requestCount())
+			}
+		}
+	})
+}
+
+// TestAnswerIsServedFromMemoryUntilItExpires makes a second lookup within the
+// TTL, which asks nobody, and a third after it, which asks again.
+func TestAnswerIsServedFromMemoryUntilItExpires(t *testing.T) {
+	t.Parallel()
+
+	resolver := newFakeResolver(t, ptrReply(300, testName))
+	cache, clock := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
+
+	lookupOK(t, cache, testAddress)
+
+	names := lookupOK(t, cache, testAddress)
+	if !slices.Equal(names, []string{testName}) {
+		t.Errorf("cached names %v, want %s", names, testName)
+	}
+
+	if got := resolver.requestCount(); got != 1 {
+		t.Errorf("%d requests after the second lookup, want 1", got)
+	}
+
+	clock.advance(300 * time.Second)
+	lookupOK(t, cache, testAddress)
+
+	if got := resolver.requestCount(); got != 2 {
+		t.Errorf("%d requests after the TTL passed, want 2", got)
+	}
+}
+
+// TestAnAddressHasOneCacheEntryHoweverItIsWritten looks up an IPv4 address in
+// its IPv4-mapped IPv6 form, then in its usual form.
+func TestAnAddressHasOneCacheEntryHoweverItIsWritten(t *testing.T) {
+	t.Parallel()
+
+	resolver := newFakeResolver(t, ptrReply(300, testName))
+	cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
+
+	lookupOK(t, cache, mappedAddress)
+	lookupOK(t, cache, testAddress)
+
+	if got := resolver.requestCount(); got != 1 {
+		t.Errorf("%d requests, want 1", got)
+	}
+}
+
+// TestCallerCannotChangeACachedAnswer changes the list each lookup returned, as
+// the server does when it removes the trailing dots. The second lookup is the
+// first answered from the cache. The third shows that the cached list did not
+// change with the list the second returned.
+func TestCallerCannotChangeACachedAnswer(t *testing.T) {
+	t.Parallel()
+
+	resolver := newFakeResolver(t, ptrReply(300, testName))
+	cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
+
+	for range 3 {
+		names := lookupOK(t, cache, testAddress)
+		if !slices.Equal(names, []string{testName}) {
+			t.Errorf("names %v, want %s", names, testName)
+		}
+
+		names[0] = "changed"
+	}
+}
+
+func TestTTLIsClamped(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name string
+		ttl  uint32
+		want time.Duration
+	}{
+		{"below the minimum", 1, time.Minute},
+		{"zero", 0, time.Minute},
+		{"at the minimum", 60, time.Minute},
+		{"in range", 300, 300 * time.Second},
+		{"at the maximum", 86400, 24 * time.Hour},
+		{"above the maximum", 604800, 24 * time.Hour},
+	}
+
+	for _, tt := range tests {
+		resolver := newFakeResolver(t, ptrReply(tt.ttl, testName))
+		cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
+
+		lookupOK(t, cache, testAddress)
+
+		got := cache.entries[testAddress].expires.Sub(fixedTime())
+		if got != tt.want {
+			t.Errorf("%s: kept for %s, want %s", tt.name, got, tt.want)
+		}
+	}
+}
+
+// TestSmallestTTLOfTheChainCounts answers with a CNAME record and two PTR
+// records, whose TTLs all differ.
+func TestSmallestTTLOfTheChainCounts(t *testing.T) {
+	t.Parallel()
+
+	reply := func(w http.ResponseWriter, _ *http.Request, query *dns.Msg) {
+		owner := query.Question[0].Name
+		answer := new(dns.Msg)
+		answer.Answer = []dns.RR{
+			&dns.CNAME{
+				Hdr: dns.RR_Header{
+					Name: owner, Rrtype: dns.TypeCNAME, Class: dns.ClassINET, Ttl: 200,
+				},
+				Target: classlessOwner,
+			},
+			&dns.PTR{
+				Hdr: dns.RR_Header{
+					Name: classlessOwner, Rrtype: dns.TypePTR,
+					Class: dns.ClassINET, Ttl: 900,
+				},
+				Ptr: testName,
+			},
+			&dns.PTR{
+				Hdr: dns.RR_Header{
+					Name: classlessOwner, Rrtype: dns.TypePTR,
+					Class: dns.ClassINET, Ttl: 600,
+				},
+				Ptr: otherName,
+			},
+		}
+
+		writeReply(w, query, answer)
+	}
+
+	cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), newFakeResolver(t, reply))
+
+	names := lookupOK(t, cache, testAddress)
+	if !slices.Equal(names, []string{testName, otherName}) {
+		t.Errorf("names %v, want both PTR names", names)
+	}
+
+	got := cache.entries[testAddress].expires.Sub(fixedTime())
+	if got != 200*time.Second {
+		t.Errorf("kept for %s, want 200s", got)
+	}
+}
+
+func TestNegativeTTL(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name    string
+		rcode   int
+		soaTTL  uint32
+		minimum uint32
+		want    time.Duration
+	}{
+		{"name does not exist", dns.RcodeNameError, 3600, 300, 300 * time.Second},
+		{"no PTR record", dns.RcodeSuccess, 3600, 300, 300 * time.Second},
+		{"limited to an hour", dns.RcodeNameError, 86400, 7200, time.Hour},
+		{"SOA's own TTL is smaller", dns.RcodeNameError, 100, 300, 100 * time.Second},
+	}
+
+	for _, tt := range tests {
+		resolver := newFakeResolver(t, soaReply(tt.rcode, tt.soaTTL, tt.minimum))
+		cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
+
+		names := lookupOK(t, cache, testAddress)
+		if len(names) != 0 {
+			t.Errorf("%s: names %v, want none", tt.name, names)
+		}
+
+		got := cache.entries[testAddress].expires.Sub(fixedTime())
+		if got != tt.want {
+			t.Errorf("%s: kept for %s, want %s", tt.name, got, tt.want)
+		}
+
+		lookupOK(t, cache, testAddress)
+
+		if count := resolver.requestCount(); count != 1 {
+			t.Errorf("%s: %d requests, want 1", tt.name, count)
+		}
+	}
+}
+
+// TestAnswerWithoutNamesOrSOAIsNotCached has nothing to say how long the
+// answer may be kept.
+func TestAnswerWithoutNamesOrSOAIsNotCached(t *testing.T) {
+	t.Parallel()
+
+	resolver := newFakeResolver(t, rcodeReply(dns.RcodeNameError))
+	cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
+
+	lookupOK(t, cache, testAddress)
+	lookupOK(t, cache, testAddress)
+
+	if got := resolver.requestCount(); got != 2 {
+		t.Errorf("%d requests, want 2", got)
+	}
+}
+
+// TestFailedQueryIsNotCached has the only resolver fail, and then recover.
+func TestFailedQueryIsNotCached(t *testing.T) {
+	t.Parallel()
+
+	resolver := newFakeResolver(t, rcodeReply(dns.RcodeServerFailure))
+	cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
+
+	_, err := cache.LookupAddr(t.Context(), testAddress)
+	if !errors.Is(err, errBadResponse) {
+		t.Fatalf("error %v, want %v", err, errBadResponse)
+	}
+
+	if len(cache.entries)+len(cache.pending) != 0 {
+		t.Error("a failed query left an entry in the cache")
+	}
+
+	resolver.setReply(ptrReply(300, testName))
+
+	names := lookupOK(t, cache, testAddress)
+	if !slices.Equal(names, []string{testName}) {
+		t.Errorf("names %v, want %s", names, testName)
+	}
+}
+
+// TestNamesThatAreNotHostNamesAreDropped answers with a name that holds markup
+// beside a good one, as a PTR record can.
+func TestNamesThatAreNotHostNamesAreDropped(t *testing.T) {
+	t.Parallel()
+
+	resolver := newFakeResolver(t,
+		ptrReply(300, "bad<script>.example.com.", testName, "."))
+	cache, _ := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
+
+	names := lookupOK(t, cache, testAddress)
+	if !slices.Equal(names, []string{testName}) {
+		t.Errorf("names %v, want only %s", names, testName)
+	}
+}
+
+// TestCacheSurvivesARestart stops a cache that holds a positive and a negative
+// answer, and starts a new one on the reopened file. It makes no request.
+func TestCacheSurvivesARestart(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	db := openTestDB(t, dir)
+
+	resolver := newFakeResolver(t,
+		func(w http.ResponseWriter, r *http.Request, query *dns.Msg) {
+			if query.Question[0].Name == testReverse {
+				ptrReply(300, testName, otherName)(w, r, query)
+
+				return
+			}
+
+			soaReply(dns.RcodeNameError, 3600, 300)(w, r, query)
+		})
+
+	cache, _ := newTestCache(t, db, resolver)
+
+	err := cache.Start(t.Context())
+	if err != nil {
+		t.Fatalf("Start: %v", err)
+	}
+
+	lookupOK(t, cache, testAddress)
+	lookupOK(t, cache, otherAddress)
+	cache.Stop(t.Context())
+
+	err = db.Close()
+	if err != nil {
+		t.Fatalf("closing the database: %v", err)
+	}
+
+	restarted, _ := newTestCache(t, openTestDB(t, dir), resolver)
+
+	err = restarted.Start(t.Context())
+	if err != nil {
+		t.Fatalf("Start after the restart: %v", err)
+	}
+
+	defer restarted.Stop(t.Context())
+
+	requestsBefore := resolver.requestCount()
+
+	names := lookupOK(t, restarted, testAddress)
+	if !slices.Equal(names, []string{testName, otherName}) {
+		t.Errorf("names after restart %v", names)
+	}
+
+	if names := lookupOK(t, restarted, otherAddress); len(names) != 0 {
+		t.Errorf("names of the address with none after restart: %v", names)
+	}
+
+	if got := resolver.requestCount(); got != requestsBefore {
+		t.Errorf("%d requests after the restart, want none",
+			got-requestsBefore)
+	}
+}
+
+// TestSweepDeletesExpiredRows also checks that a restart does not load a row
+// that has expired since it was written.
+func TestSweepDeletesExpiredRows(t *testing.T) {
+	t.Parallel()
+
+	db := openTestDB(t, t.TempDir())
+	resolver := newFakeResolver(t,
+		func(w http.ResponseWriter, r *http.Request, query *dns.Msg) {
+			ttl := uint32(300)
+			if query.Question[0].Name == testReverse {
+				ttl = 60
+			}
+
+			ptrReply(ttl, testName)(w, r, query)
+		})
+	cache, clock := newTestCache(t, db, resolver)
+
+	lookupOK(t, cache, testAddress)
+	lookupOK(t, cache, otherAddress)
+	cache.flush(t.Context())
+
+	if got := countRows(t, db); got != 2 {
+		t.Fatalf("%d rows before the sweep, want 2", got)
+	}
+
+	clock.advance(90 * time.Second)
+
+	loaded, loadedClock := newTestCache(t, db, resolver)
+	loadedClock.advance(90 * time.Second)
+
+	err := loaded.load(t.Context())
+	if err != nil {
+		t.Fatalf("load: %v", err)
+	}
+
+	if len(loaded.entries) != 1 {
+		t.Errorf("loaded %d entries, want the 1 not expired", len(loaded.entries))
+	}
+
+	cache.sweep(t.Context())
+
+	if got := countRows(t, db); got != 1 {
+		t.Errorf("%d rows after the sweep, want 1", got)
+	}
+
+	if len(cache.entries) != 1 {
+		t.Errorf("%d entries in memory after the sweep, want 1", len(cache.entries))
+	}
+}
+
+// TestFlushKeepsAnswersItCouldNotWrite makes one write fail by hiding the
+// table. The next write, once the table is back, stores the answer.
+func TestFlushKeepsAnswersItCouldNotWrite(t *testing.T) {
+	t.Parallel()
+
+	db := openTestDB(t, t.TempDir())
+	resolver := newFakeResolver(t, ptrReply(300, testName))
+	cache, _ := newTestCache(t, db, resolver)
+
+	lookupOK(t, cache, testAddress)
+
+	_, err := db.ExecContext(t.Context(), "ALTER TABLE hostnames RENAME TO hidden")
+	if err != nil {
+		t.Fatalf("renaming the table: %v", err)
+	}
+
+	cache.flush(t.Context())
+
+	_, err = db.ExecContext(t.Context(), "ALTER TABLE hidden RENAME TO hostnames")
+	if err != nil {
+		t.Fatalf("renaming the table back: %v", err)
+	}
+
+	if got := countRows(t, db); got != 0 {
+		t.Fatalf("%d rows after the failed write, want 0", got)
+	}
+
+	cache.flush(t.Context())
+
+	if got := countRows(t, db); got != 1 {
+		t.Errorf("%d rows after the second write, want 1", got)
+	}
+}
+
+// TestNewAddressIsNotKeptAtTheLimit fills a cache that holds one address. A
+// lookup of a second address still returns its answer, and the cache keeps
+// nothing for it until the sweep has deleted the first address's expired
+// answer.
+func TestNewAddressIsNotKeptAtTheLimit(t *testing.T) {
+	t.Parallel()
+
+	db := openTestDB(t, t.TempDir())
+	resolver := newFakeResolver(t, ptrReply(300, testName))
+	cache, clock := newTestCache(t, db, resolver)
+	cache.maxEntries = 1
+
+	lookupOK(t, cache, testAddress)
+
+	names := lookupOK(t, cache, otherAddress)
+	if !slices.Equal(names, []string{testName}) {
+		t.Errorf("names %v at the limit, want %s", names, testName)
+	}
+
+	_, inEntries := cache.entries[otherAddress]
+	_, inPending := cache.pending[otherAddress]
+
+	if inEntries || inPending {
+		t.Errorf("a new address was kept at the limit: in entries %t, in pending %t",
+			inEntries, inPending)
+	}
+
+	cache.flush(t.Context())
+
+	if got := countRows(t, db); got != 1 {
+		t.Errorf("%d rows at the limit, want 1", got)
+	}
+
+	clock.advance(300 * time.Second)
+	cache.sweep(t.Context())
+	lookupOK(t, cache, otherAddress)
+
+	_, inEntries = cache.entries[otherAddress]
+	if !inEntries {
+		t.Error("a new address was not kept after the sweep made room")
+	}
+}
+
+// TestHeldAddressIsReplacedAtTheLimit lets the answer of the only address a
+// cache holds expire. The new answer replaces it in memory and is queued for
+// cache.db.
+func TestHeldAddressIsReplacedAtTheLimit(t *testing.T) {
+	t.Parallel()
+
+	resolver := newFakeResolver(t, ptrReply(300, testName))
+	cache, clock := newTestCache(t, openTestDB(t, t.TempDir()), resolver)
+	cache.maxEntries = 1
+
+	lookupOK(t, cache, testAddress)
+	clock.advance(300 * time.Second)
+	resolver.setReply(ptrReply(300, otherName))
+	lookupOK(t, cache, testAddress)
+
+	want := []string{otherName}
+
+	if got := cache.entries[testAddress].names; !slices.Equal(got, want) {
+		t.Errorf("entries holds %v, want %v", got, want)
+	}
+
+	if got := cache.pending[testAddress].names; !slices.Equal(got, want) {
+		t.Errorf("pending holds %v, want %v", got, want)
+	}
+}

internal/ptr/doh.go

@@ -0,0 +1,200 @@
+package ptr
+
+import (
+	"bytes"
+	"context"
+	"errors"
+	"fmt"
+	"io"
+	"math"
+	"net/http"
+	"strings"
+	"time"
+
+	"github.com/miekg/dns"
+)
+
+const (
+	// LookupTimeout limits one address's lookup, every resolver included.
+	LookupTimeout = 2 * time.Second
+
+	// minTTL and maxTTL limit how long PTR names are kept.
+	minTTL = time.Minute
+	maxTTL = 24 * time.Hour
+
+	// maxNegativeTTL limits how long an address with no PTR names is
+	// remembered as having none.
+	maxNegativeTTL = time.Hour
+
+	// dnsMessageType is the content type of RFC 8484 requests and answers.
+	dnsMessageType = "application/dns-message"
+
+	// maxMessageBytes is the largest possible DNS message.
+	maxMessageBytes = 65535
+)
+
+var (
+	errBadStatus   = errors.New("unexpected HTTP status")
+	errBadResponse = errors.New("resolver reported an error")
+)
+
+// Resolvers returns the URLs of the public DNS-over-HTTPS resolvers, in the
+// order they are tried.
+func Resolvers() []string {
+	return []string{
+		"https://dns.google/dns-query",
+		"https://cloudflare-dns.com/dns-query",
+		"https://unfiltered.adguard-dns.com/dns-query",
+		"https://dns.quad9.net/dns-query",
+	}
+}
+
+// answer is a resolver's answer for one address.
+type answer struct {
+	// names are the address's PTR names, nil when it has none.
+	names []string
+
+	// ttl is how long the answer may be kept. Zero means it is not kept.
+	ttl time.Duration
+}
+
+// lookup asks the resolvers in turn for the PTR names of the reverse name
+// until one answers. It fails when none has answered within the time limit.
+func (c *Cache) lookup(ctx context.Context, reverseName string) (answer, error) {
+	ctx, cancel := context.WithTimeout(ctx, c.timeLimit)
+	defer cancel()
+
+	query := new(dns.Msg).SetQuestion(reverseName, dns.TypePTR)
+	query.Id = 0 // RFC 8484 asks for 0, so that equal queries can be cached.
+
+	wire, err := query.Pack()
+	if err != nil {
+		return answer{}, fmt.Errorf("packing the query: %w", err)
+	}
+
+	var failures []error
+
+	for i, resolver := range c.resolvers {
+		// Each resolver gets an equal share of the time left, so that one
+		// that never answers leaves time for the next.
+		deadline, _ := ctx.Deadline()
+		share := time.Until(deadline) / time.Duration(len(c.resolvers)-i)
+
+		result, err := c.ask(ctx, resolver, wire, share)
+		if err == nil {
+			return result, nil
+		}
+
+		failures = append(failures, fmt.Errorf("%s: %w", resolver, err))
+	}
+
+	return answer{}, errors.Join(failures...)
+}
+
+// ask sends the query to one resolver and waits at most timeout for its answer.
+func (c *Cache) ask(
+	ctx context.Context, resolver string, query []byte, timeout time.Duration,
+) (answer, error) {
+	ctx, cancel := context.WithTimeout(ctx, timeout)
+	defer cancel()
+
+	request, err := http.NewRequestWithContext(
+		ctx, http.MethodPost, resolver, bytes.NewReader(query))
+	if err != nil {
+		return answer{}, err
+	}
+
+	request.Header.Set("Content-Type", dnsMessageType)
+	request.Header.Set("Accept", dnsMessageType)
+
+	response, err := c.client.Do(request)
+	if err != nil {
+		return answer{}, err
+	}
+
+	defer func() { _ = response.Body.Close() }()
+
+	if response.StatusCode != http.StatusOK {
+		return answer{}, fmt.Errorf("%w: %d", errBadStatus, response.StatusCode)
+	}
+
+	body, err := io.ReadAll(io.LimitReader(response.Body, maxMessageBytes))
+	if err != nil {
+		return answer{}, err
+	}
+
+	var reply dns.Msg
+
+	err = reply.Unpack(body)
+	if err != nil {
+		return answer{}, err
+	}
+
+	return answerFrom(&reply)
+}
+
+// answerFrom reads a resolver's reply. A name that does not exist and a name
+// with no PTR records are answers. Every other response code is a failure.
+func answerFrom(reply *dns.Msg) (answer, error) {
+	if reply.Rcode != dns.RcodeSuccess && reply.Rcode != dns.RcodeNameError {
+		return answer{}, fmt.Errorf("%w: %s",
+			errBadResponse, dns.RcodeToString[reply.Rcode])
+	}
+
+	var names []string
+
+	seconds := uint32(math.MaxUint32)
+
+	for _, record := range reply.Answer {
+		// The chain to a PTR record can hold CNAME records, and the answer
+		// is good only as long as every record in it.
+		seconds = min(seconds, record.Header().Ttl)
+
+		ptr, ok := record.(*dns.PTR)
+		if ok && isHostName(ptr.Ptr) {
+			names = append(names, ptr.Ptr)
+		}
+	}
+
+	if len(names) == 0 {
+		return answer{ttl: negativeTTL(reply.Ns)}, nil
+	}
+
+	ttl := time.Duration(seconds) * time.Second
+
+	return answer{names: names, ttl: min(max(ttl, minTTL), maxTTL)}, nil
+}
+
+// negativeTTL returns how long a reply with no PTR names may be kept: the
+// smaller of the SOA record's own TTL and its minimum field (RFC 2308), at most
+// maxNegativeTTL. Without a SOA record it is zero.
+func negativeTTL(authority []dns.RR) time.Duration {
+	for _, record := range authority {
+		soa, ok := record.(*dns.SOA)
+		if ok {
+			ttl := time.Duration(min(soa.Hdr.Ttl, soa.Minttl)) * time.Second
+
+			return min(ttl, maxNegativeTTL)
+		}
+	}
+
+	return 0
+}
+
+// isHostName reports whether name is a host name. A PTR record can hold any
+// bytes, and the names go into web pages, so anything else is dropped, as
+// net.Resolver.LookupAddr drops it. The root name is not a host name.
+func isHostName(name string) bool {
+	_, ok := dns.IsDomainName(name)
+
+	return ok && name != "." && !strings.ContainsFunc(name, notInHostName)
+}
+
+// notInHostName reports whether r cannot be part of a host name.
+func notInHostName(r rune) bool {
+	return !strings.ContainsRune(hostNameCharacters, r)
+}
+
+// hostNameCharacters are the characters of a host name, in presentation format.
+const hostNameCharacters = "abcdefghijklmnopqrstuvwxyz" +
+	"ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_."

internal/routewatch/app.go

@@ -9,17 +9,21 @@ package routewatch
 
 import (
 	"context"
+	"database/sql"
 	"errors"
 	"fmt"
 	"path/filepath"
 	"sync"
 	"time"
 
-	"git.eeqj.de/sneak/routewatch/internal/blocklist"
+	"git.eeqj.de/sneak/routewatch/internal/cachedb"
 	"git.eeqj.de/sneak/routewatch/internal/config"
 	"git.eeqj.de/sneak/routewatch/internal/database"
+	"git.eeqj.de/sneak/routewatch/internal/geo"
+	"git.eeqj.de/sneak/routewatch/internal/iplist"
 	"git.eeqj.de/sneak/routewatch/internal/logger"
 	"git.eeqj.de/sneak/routewatch/internal/metrics"
+	"git.eeqj.de/sneak/routewatch/internal/ptr"
 	"git.eeqj.de/sneak/routewatch/internal/routetable"
 	"git.eeqj.de/sneak/routewatch/internal/server"
 	"git.eeqj.de/sneak/routewatch/internal/streamer"
@@ -61,12 +65,15 @@ type RouteWatch struct {
 	peeringHandler *PeeringHandler
 	asnFetcher     *ASNFetcher
 	dbMaintainer   *DBMaintainer
-	blocklists     *blocklist.Blocklists
+	ipLists        *iplist.IPLists
+	cacheDB        *sql.DB
+	ptrCache       *ptr.Cache
+	geoLocator     *geo.Locator
 }
 
-// blocklistsDirName is the directory in the state directory that holds the
+// ipListsDirName is the directory in the state directory that holds the IP
-// blocklist copies.
+// list copies.
-const blocklistsDirName = "blocklists"
+const ipListsDirName = "iplists"
 
 // New creates a new RouteWatch instance
 func New(deps Dependencies) *RouteWatch {
@@ -138,17 +145,27 @@ func (rw *RouteWatch) Run(ctx context.Context) error {
 	rw.asnFetcher.Start(ctx)
 	rw.server.SetASNFetcher(rw.asnFetcher)
 
-	// Load the blocklist copies from disk and start downloading the lists.
+	// Load the IP list copies from disk and start downloading the lists.
-	// The HTTP handlers read the server's blocklists without a lock, so they
+	// The HTTP handlers read the server's IP lists without a lock, so they
 	// are set before the handlers run.
-	blocklists := blocklist.New(blocklist.Params{
+	ipLists := iplist.New(iplist.Params{
-		Dir:    filepath.Join(rw.config.StateDir, blocklistsDirName),
+		Dir:    filepath.Join(rw.config.StateDir, ipListsDirName),
-		Lists:  blocklist.Lists(),
+		Lists:  iplist.Lists(),
 		Logger: rw.logger.Logger,
 	})
-	blocklists.Start(ctx)
+	ipLists.Start(ctx)
-	rw.blocklists = blocklists
+	rw.ipLists = ipLists
-	rw.server.SetBlocklists(blocklists)
+	rw.server.SetIPLists(ipLists)
+
+	err = rw.startPTRCache(ctx)
+	if err != nil {
+		return err
+	}
+
+	err = rw.startGeoLocator(ctx)
+	if err != nil {
+		return err
+	}
 
 	// Start HTTP server
 	err = rw.server.Start(ctx)
@@ -168,8 +185,9 @@ func (rw *RouteWatch) Run(ctx context.Context) error {
 
 // Shutdown stops all services in order: the streamer, the handlers, which
 // write what they hold, the WHOIS fetcher, the database maintainer, the
-// blocklist downloads and the HTTP server, and last the database, which it
+// IP list downloads, the HTTP server, the geolocation cache and the PTR cache,
-// checkpoints and closes. Each stage waits at most until ctx ends, so
+// and last the database, which it checkpoints and closes. Each stage waits at
+// most until ctx ends, so
 // Shutdown returns soon after: a handler logs what it could not write by
 // then, and the HTTP server closes the connections of requests still
 // running.
@@ -219,8 +237,8 @@ func (rw *RouteWatch) Shutdown(ctx context.Context) {
 		rw.dbMaintainer.Stop(ctx)
 	}
 
-	if rw.blocklists != nil {
+	if rw.ipLists != nil {
-		rw.blocklists.Stop(ctx)
+		rw.ipLists.Stop(ctx)
 	}
 
 	err := rw.server.Stop(ctx)
@@ -229,6 +247,12 @@ func (rw *RouteWatch) Shutdown(ctx context.Context) {
 			"error", err)
 	}
 
+	if rw.geoLocator != nil {
+		rw.geoLocator.Stop(ctx)
+	}
+
+	rw.stopPTRCache(ctx)
+
 	rw.closeDatabase(ctx)
 
 	// Log final metrics
@@ -242,6 +266,81 @@ func (rw *RouteWatch) Shutdown(ctx context.Context) {
 	)
 }
 
+// startPTRCache opens cache.db, loads the PTR cache from it and gives the
+// server the cache. The HTTP handlers read it without a lock, so it is set
+// before they run.
+func (rw *RouteWatch) startPTRCache(ctx context.Context) error {
+	cacheDB, err := cachedb.Open(ctx, rw.config.StateDir)
+	if err != nil {
+		return err
+	}
+
+	ptrCache := ptr.New(ptr.Params{
+		DB:        cacheDB,
+		Resolvers: ptr.Resolvers(),
+		Logger:    rw.logger.Logger,
+	})
+
+	err = ptrCache.Start(ctx)
+	if err != nil {
+		_ = cacheDB.Close()
+
+		return err
+	}
+
+	rw.cacheDB = cacheDB
+	rw.ptrCache = ptrCache
+	rw.server.SetPTRResolver(ptrCache)
+
+	return nil
+}
+
+// startGeoLocator loads the geolocation cache from cache.db, which
+// startPTRCache has opened, and gives the server the locator. The HTTP handlers
+// read it without a lock, so it is set before they run.
+func (rw *RouteWatch) startGeoLocator(ctx context.Context) error {
+	locator, err := geo.New(geo.Params{
+		DB:                rw.cacheDB,
+		Dir:               rw.config.StateDir,
+		GeoJSURL:          geo.GeoJSEndpoint,
+		DatabaseURLFormat: geo.DatabaseDownloadFormat,
+		Logger:            rw.logger.Logger,
+	})
+	if err != nil {
+		return err
+	}
+
+	err = locator.Start(ctx)
+	if err != nil {
+		return err
+	}
+
+	rw.geoLocator = locator
+	rw.server.SetGeoLocator(locator)
+
+	return nil
+}
+
+// stopPTRCache stops the PTR cache, which writes the answers cache.db does not
+// have yet, and closes cache.db, unless ctx has ended and a write may still be
+// running.
+func (rw *RouteWatch) stopPTRCache(ctx context.Context) {
+	if rw.ptrCache == nil {
+		return
+	}
+
+	rw.ptrCache.Stop(ctx)
+
+	if ctx.Err() != nil {
+		return
+	}
+
+	err := rw.cacheDB.Close()
+	if err != nil {
+		rw.logger.Error("Failed to close the cache database", "error", err)
+	}
+}
+
 // closeDatabase checkpoints and closes the database, unless ctx has ended: a
 // write may then still be running, and both would wait for it. SQLite rolls
 // back a write cut off by the exit when the database next opens.

internal/routewatch/app_integration_internal_test.go

@@ -8,6 +8,8 @@ import (
 	"net/http"
 	"net/http/httptest"
 	"net/netip"
+	"os"
+	"path/filepath"
 	"slices"
 	"strconv"
 	"strings"
@@ -418,7 +420,7 @@ func TestRouteWatchLiveFeed(t *testing.T) {
 	// Create streamer
 	s := streamer.New(logger, metricsTracker)
 
-	// The state directory holds the blocklist copies Run downloads.
+	// The state directory holds the IP list copies Run downloads.
 	cfg := &config.Config{
 		StateDir:                    t.TempDir(),
 		MaxRuntime:                  5 * time.Second,
@@ -783,3 +785,74 @@ func TestShutdownCheckpointsAndClosesTheDatabaseLast(t *testing.T) {
 		t.Errorf("Shutdown made the calls %q, want %q", store.calls, want)
 	}
 }
+
+// TestPTRCacheAnswersTheIPLookup starts the PTR cache and the HTTP server as
+// Run does, and looks up a reserved address, which asks no resolver. Without
+// the PTR cache the server has no PTR resolver, and every IP lookup answers
+// 500.
+func TestPTRCacheAnswersTheIPLookup(t *testing.T) {
+	t.Parallel()
+
+	store := newMockStore()
+	log := logger.New()
+	port := freePort(t)
+	cfg := &config.Config{Port: port, StateDir: t.TempDir()}
+	s := streamer.New(log, metrics.New())
+
+	// A started server reads its routing table in the background, so it
+	// needs one.
+	rw := New(Dependencies{
+		DB:       store,
+		Streamer: s,
+		Server: server.New(store, routetable.New(routetable.Params{}), s, log,
+			cfg),
+		Logger: log,
+		Config: cfg,
+	})
+
+	err := rw.startPTRCache(t.Context())
+	if err != nil {
+		t.Fatalf("failed to start the PTR cache: %v", err)
+	}
+
+	defer rw.stopPTRCache(t.Context())
+
+	err = rw.server.Start(t.Context())
+	if err != nil {
+		t.Fatalf("failed to start the HTTP server: %v", err)
+	}
+
+	defer func() { _ = rw.server.Stop(t.Context()) }()
+
+	req, err := http.NewRequestWithContext(t.Context(), http.MethodGet,
+		"http://"+net.JoinHostPort("127.0.0.1", strconv.Itoa(port))+
+			"/api/v1/ip/10.0.0.1", nil)
+	if err != nil {
+		t.Fatalf("failed to build the request: %v", err)
+	}
+
+	resp, err := http.DefaultClient.Do(req)
+	if err != nil {
+		t.Fatalf("the IP lookup failed: %v", err)
+	}
+
+	defer func() { _ = resp.Body.Close() }()
+
+	body, err := io.ReadAll(resp.Body)
+	if err != nil {
+		t.Fatalf("failed to read the answer: %v", err)
+	}
+
+	if resp.StatusCode != http.StatusOK {
+		t.Fatalf("status %d, want %d; body %s", resp.StatusCode, http.StatusOK, body)
+	}
+
+	if !strings.Contains(string(body), `"ptr":[]`) {
+		t.Errorf("answer %s, want an empty ptr", body)
+	}
+
+	_, err = os.Stat(filepath.Join(cfg.StateDir, "cache.db"))
+	if err != nil {
+		t.Errorf("cache.db is not in the state directory: %v", err)
+	}
+}

internal/server/handlers.go

@@ -15,8 +15,10 @@ import (
 	"strings"
 	"time"
 
-	"git.eeqj.de/sneak/routewatch/internal/blocklist"
+	"git.eeqj.de/sneak/routewatch/internal/bogon"
 	"git.eeqj.de/sneak/routewatch/internal/database"
+	"git.eeqj.de/sneak/routewatch/internal/geo"
+	"git.eeqj.de/sneak/routewatch/internal/iplist"
 	"git.eeqj.de/sneak/routewatch/internal/metrics"
 	"git.eeqj.de/sneak/routewatch/internal/ristypes"
 	"git.eeqj.de/sneak/routewatch/internal/routetable"
@@ -38,12 +40,9 @@ const (
 const (
 	// maxLookupTargets is the most addresses and host names an IP lookup may
 	// list, and the most addresses it may have once the names are resolved:
-	// each address costs two database reads and a PTR lookup.
+	// each address costs two database reads and a PTR lookup. Ten PTR lookups
+	// that run to ptr.LookupTimeout fit in the request's 30-second limit.
 	maxLookupTargets = 10
-
-	// ptrLookupTimeout is each PTR lookup's own time limit, so that ten
-	// addresses whose PTR lookups never answer fit in the 30-second limit.
-	ptrLookupTimeout = 2 * time.Second
 )
 
 // The Cache-Control header of an IP lookup answer, such as
@@ -765,9 +764,12 @@ type IPLookupResponse struct {
 	Errors  []string         `json:"errors,omitempty"`
 }
 
-// IPLookupResult is the answer for one address: its PTR names, its live route
+// IPLookupResult is the answer for one address: its PTR names, its flags, its
-// and that route's AS, and the blocklists that list it. Every result has every
+// live route and that route's AS, the IP lists that contain it, and where it
-// field. The fields of IPInfo are null when the address has no live route.
+// is. Every result has every field. The fields of IPInfo are null when the
+// address has no live route.
+//
+//nolint:tagliatelle // snake_case keys, as the Go style guide asks
 type IPLookupResult struct {
 	IPInfo
 
@@ -775,8 +777,35 @@ type IPLookupResult struct {
 	// PTR is empty, never nil, when the address has no PTR names.
 	PTR []string `json:"ptr"`
 
-	// Blocklists has one entry for each blocklist the address is on.
+	Flags IPLookupFlags `json:"flags"`
-	Blocklists []blocklist.Listing `json:"blocklists"`
+
+	// VPNProviders names the VPN lists the address is on. It is empty, never
+	// nil, when there are none.
+	VPNProviders []string `json:"vpn_providers"`
+
+	// IPLists has one entry for each IP list the address is on.
+	IPLists []iplist.Listing `json:"ip_lists"`
+
+	// Geo is where the address is. It is nil when no source answers.
+	Geo *geo.Location `json:"geo"`
+}
+
+// IPLookupFlags are the yes-or-no facts about an address. Every result has
+// them, whether or not the address has a live route.
+//
+//nolint:tagliatelle // snake_case keys, as the Go style guide asks
+type IPLookupFlags struct {
+	// IsTor says that the address is on the Tor exit list.
+	IsTor bool `json:"is_tor"`
+
+	// IsVPN says that the address is on a list of VPN servers.
+	IsVPN bool `json:"is_vpn"`
+
+	// IsRelay says that the address is on the iCloud Private Relay list.
+	IsRelay bool `json:"is_relay"`
+
+	// IsBogon says that the address is reserved, as package bogon tells.
+	IsBogon bool `json:"is_bogon"`
 }
 
 // handleIPInfo returns a handler that provides comprehensive IP information.
@@ -817,6 +846,8 @@ func (s *Server) handleIPInfo() http.HandlerFunc {
 			return
 		}
 
+		locations := s.geoLocations(ctx, ipsToLookup)
+
 		// Track ASNs that need WHOIS refresh
 		refreshASNs := make(map[int]bool)
 
@@ -852,12 +883,9 @@ func (s *Server) handleIPInfo() http.HandlerFunc {
 				return
 			}
 
-			response.Results = append(response.Results, IPLookupResult{
+			result := s.ipLookupResult(ip, ptrs, ipInfo)
-				IP:         ip,
+			result.Geo = locations[ip]
-				PTR:        ptrs,
+			response.Results = append(response.Results, result)
-				IPInfo:     ipInfo,
-				Blocklists: s.blocklistListings(ip),
-			})
 
 			if ipInfo.NeedsWHOISRefresh {
 				refreshASNs[*ipInfo.ASN] = true
@@ -958,23 +986,120 @@ func ipVersionOf(prefix netip.Prefix) int {
 	return ipVersionV6
 }
 
-// blocklistListings returns the blocklists that list ip. It returns an empty
+// ipLookupResult returns the result for ip, adding its flags and IP lists to
-// list, never nil, so that an answer's blocklists is [] rather than null.
+// its PTR names and route.
-func (s *Server) blocklistListings(ip string) []blocklist.Listing {
+func (s *Server) ipLookupResult(ip string, ptrs []string, info IPInfo) IPLookupResult {
-	addr, err := netip.ParseAddr(ip)
+	listings := s.ipListListings(ip)
-	if s.blocklists == nil || err != nil {
+
-		return []blocklist.Listing{}
+	return IPLookupResult{
+		IP:           ip,
+		PTR:          ptrs,
+		IPInfo:       info,
+		Flags:        ipLookupFlags(ip, listings),
+		VPNProviders: vpnProviders(listings),
+		IPLists:      listings,
+	}
 }
 
-	return s.blocklists.Lookup(addr)
+// vpnProviders returns the names of the VPN lists among listings. It returns
+// an empty list, never nil, so that an answer's vpn_providers is [] rather
+// than null.
+func vpnProviders(listings []iplist.Listing) []string {
+	names := []string{}
+
+	for _, listing := range listings {
+		if listing.VPN {
+			names = append(names, listing.Name)
+		}
+	}
+
+	return names
+}
+
+// ipListListings returns the IP lists that contain ip. It returns an empty
+// list, never nil, so that an answer's ip_lists is [] rather than null.
+func (s *Server) ipListListings(ip string) []iplist.Listing {
+	addr, err := netip.ParseAddr(ip)
+	if s.ipLists == nil || err != nil {
+		return []iplist.Listing{}
+	}
+
+	return s.ipLists.Lookup(addr)
+}
+
+// ipLookupFlags returns the flags of ip, whose IP list entries are listings.
+func ipLookupFlags(ip string, listings []iplist.Listing) IPLookupFlags {
+	return IPLookupFlags{
+		IsTor: slices.ContainsFunc(listings, func(l iplist.Listing) bool {
+			return l.Name == iplist.TorExitsList
+		}),
+		IsVPN: slices.ContainsFunc(listings, func(l iplist.Listing) bool {
+			return l.VPN
+		}),
+		IsRelay: slices.ContainsFunc(listings, func(l iplist.Listing) bool {
+			return l.Name == iplist.ICloudPrivateRelayList
+		}),
+		IsBogon: isBogon(ip),
+	}
+}
+
+// geoLocations returns where ips are, by address. An address that does not
+// parse has no entry. Nor has a reserved one, which is sent to no outside
+// source and has no location.
+func (s *Server) geoLocations(
+	ctx context.Context, ips []string,
+) map[string]*geo.Location {
+	if s.geoLocator == nil {
+		return nil
+	}
+
+	var (
+		kept  []string
+		addrs []netip.Addr
+	)
+
+	for _, ip := range ips {
+		addr, err := netip.ParseAddr(ip)
+		if err != nil || isBogon(ip) {
+			continue
+		}
+
+		kept = append(kept, ip)
+		addrs = append(addrs, addr)
+	}
+
+	if len(addrs) == 0 {
+		return nil
+	}
+
+	answers := s.geoLocator.Lookup(ctx, addrs)
+	locations := make(map[string]*geo.Location, len(kept))
+
+	for i, ip := range kept {
+		locations[ip] = answers[i]
+	}
+
+	return locations
+}
+
+// isBogon says whether the address ip is reserved, as package bogon tells.
+func isBogon(ip string) bool {
+	addr, err := netip.ParseAddr(ip)
+	if err != nil {
+		return false
+	}
+
+	_, reserved := bogon.Addr(addr)
+
+	return reserved
 }
 
 // setIPLookupCacheControl lets caches keep an IP lookup answer for the
-// shortest blocklist interval, the soonest a blocklist copy can change. The
+// shortest IP list interval, the soonest an IP list copy can change. The
 // answer about the caller's own address is private, so that a shared cache
-// does not give it to another caller. Without blocklists it sets nothing.
+// does not give it to another caller. Without IP lists it sets nothing.
 func (s *Server) setIPLookupCacheControl(w http.ResponseWriter, ownAddress bool) {
-	if s.blocklists == nil {
+	if s.ipLists == nil {
 		return
 	}
 
@@ -983,7 +1108,7 @@ func (s *Server) setIPLookupCacheControl(w http.ResponseWriter, ownAddress bool)
 		visibility = cacheControlPrivate
 	}
 
-	maxAgeSeconds := int(s.blocklists.ShortestInterval().Seconds())
+	maxAgeSeconds := int(s.ipLists.ShortestInterval().Seconds())
 	w.Header().Set(cacheControlHeader,
 		visibility+cacheControlMaxAge+strconv.Itoa(maxAgeSeconds))
 }
@@ -1143,15 +1268,17 @@ func publicAddresses(addrs []string) []string {
 }
 
 // lookupPTRNames returns the PTR records of ip without their trailing dots. It
-// returns an empty list, never nil, when there are none, when the lookup fails
+// returns an empty list, never nil, when there are none and when the lookup
-// and when it runs past ptrLookupTimeout, so that an answer's ptr is [] rather
+// fails, so that an answer's ptr is [] rather than null.
-// than null.
 func (s *Server) lookupPTRNames(ctx context.Context, ip string) []string {
-	ctx, cancel := context.WithTimeout(ctx, ptrLookupTimeout)
+	ptrs, err := s.ptrResolver.LookupAddr(ctx, ip)
-	defer cancel()
+	if err != nil {
+		s.logger.Warn("PTR lookup failed", "ip", ip, "error", err)
 
-	ptrs, err := s.resolver.LookupAddr(ctx, ip)
+		return []string{}
-	if err != nil || ptrs == nil {
+	}
+
+	if ptrs == nil {
 		return []string{}
 	}
 

internal/server/handlers_internal_test.go

@@ -15,15 +15,19 @@ import (
 	"slices"
 	"strconv"
 	"strings"
+	"sync"
 	"sync/atomic"
 	"testing"
+	"testing/synctest"
 	"time"
 
-	"git.eeqj.de/sneak/routewatch/internal/blocklist"
 	"git.eeqj.de/sneak/routewatch/internal/config"
 	"git.eeqj.de/sneak/routewatch/internal/database"
+	"git.eeqj.de/sneak/routewatch/internal/geo"
+	"git.eeqj.de/sneak/routewatch/internal/iplist"
 	"git.eeqj.de/sneak/routewatch/internal/logger"
 	"git.eeqj.de/sneak/routewatch/internal/metrics"
+	"git.eeqj.de/sneak/routewatch/internal/ptr"
 	"git.eeqj.de/sneak/routewatch/internal/ristypes"
 	"git.eeqj.de/sneak/routewatch/internal/routetable"
 	"git.eeqj.de/sneak/routewatch/internal/streamer"
@@ -173,6 +177,9 @@ type tableStats struct {
 // carried 203.0.113.0/24, the two with kept routes withdrew it, so its origin
 // keeps no route. The oldest and newest routes are those of the other two
 // prefixes.
+//
+// The requests run in a synctest bubble, whose clock is fake, so a stall on
+// the host does not use up the handlers' 4-second limit.
 func TestStatsHandlersAnswerFromMemory(t *testing.T) {
 	t.Parallel()
 
@@ -218,7 +225,11 @@ func TestStatsHandlersAnswerFromMemory(t *testing.T) {
 
 	for name, handler := range handlers {
 		rec := httptest.NewRecorder()
-		handler(rec, httptest.NewRequestWithContext(t.Context(), http.MethodGet, "/", nil))
+
+		synctest.Test(t, func(t *testing.T) {
+			handler(rec,
+				httptest.NewRequestWithContext(t.Context(), http.MethodGet, "/", nil))
+		})
 
 		if rec.Code != http.StatusOK {
 			t.Errorf("%s: status %d, want %d; body %s",
@@ -253,15 +264,20 @@ func TestStatsHandlersAnswerFromMemory(t *testing.T) {
 // TestStatsAnswerCarriesChurnPerMinute checks that the stream object of the
 // /api/v1/stats answer holds route_churn_per_min as a whole number, and no
 // longer route_churn_per_sec, the moving average it replaces
-// (https://git.eeqj.de/sneak/routewatch/issues/160).
+// (https://git.eeqj.de/sneak/routewatch/issues/160). The request runs in a
+// synctest bubble, whose clock is fake, so a stall on the host does not use up
+// the handler's 4-second limit.
 func TestStatsAnswerCarriesChurnPerMinute(t *testing.T) {
 	t.Parallel()
 
 	s := newServerWithTestRoutes(t)
 
 	rec := httptest.NewRecorder()
+
+	synctest.Test(t, func(t *testing.T) {
 		s.handleStats()(rec,
 			httptest.NewRequestWithContext(t.Context(), http.MethodGet, statsPath, nil))
+	})
 
 	if rec.Code != http.StatusOK {
 		t.Fatalf("status %d, want %d; body %s", rec.Code, http.StatusOK, rec.Body)
@@ -309,18 +325,26 @@ func (heldBackHandler) HeldBackCount() int                 { return heldBackMess
 
 // TestStatsAnswerGivesHowManyMessagesAHandlerHoldsBack registers a handler
 // that holds back messages. Its figures in /api/v1/stats, which the status
-// page shows, must give how many.
+// page shows, must give how many. The request runs in a synctest bubble, whose
+// clock is fake, so a stall on the host does not use up the handler's 4-second
+// limit.
 func TestStatsAnswerGivesHowManyMessagesAHandlerHoldsBack(t *testing.T) {
 	t.Parallel()
 
 	s := newServerWithTestRoutes(t)
 	s.streamer.RegisterHandler(heldBackHandler{})
 
+	var answer []byte
+
+	synctest.Test(t, func(t *testing.T) {
+		answer = get(t, s, statsPath).Body.Bytes()
+	})
+
 	var body struct {
 		Data StatsResponse `json:"data"`
 	}
 
-	err := json.Unmarshal(get(t, s, statsPath).Body.Bytes(), &body)
+	err := json.Unmarshal(answer, &body)
 	if err != nil {
 		t.Fatalf("decoding the answer: %v", err)
 	}
@@ -364,7 +388,9 @@ type unitStats struct {
 // names. They used to be strings with the unit in them, such as "1h18m34s" or
 // "1.1 GB" (https://git.eeqj.de/sneak/routewatch/issues/199). The stream has
 // never connected, so the uptime is 0. The memory use in /api/v1/stats is the
-// same number of bytes as its gc.heap_alloc_bytes.
+// same number of bytes as its gc.heap_alloc_bytes. The requests run in a
+// synctest bubble, whose clock is fake, so a stall on the host does not use up
+// the handlers' 4-second limit.
 func TestStatsAnswersGiveUnitsInFieldNames(t *testing.T) {
 	t.Parallel()
 
@@ -374,7 +400,11 @@ func TestStatsAnswersGiveUnitsInFieldNames(t *testing.T) {
 	s.SetASNFetcher(fixedIntervalASNFetcher{interval: fetchInterval})
 
 	for _, path := range []string{statusJSONPath, statsPath} {
-		answer := get(t, s, path).Body.Bytes()
+		var answer []byte
+
+		synctest.Test(t, func(t *testing.T) {
+			answer = get(t, s, path).Body.Bytes()
+		})
 
 		var body struct {
 			Data unitStats `json:"data"`
@@ -415,12 +445,15 @@ func TestStatsAnswersGiveUnitsInFieldNames(t *testing.T) {
 // connection_duration_seconds of /api/v1/stats is null while the stream is not
 // connected, and a whole number of seconds once it is. It used to be the
 // string "disconnected", or a Go duration such as "1h18m34s"
-// (https://git.eeqj.de/sneak/routewatch/issues/199).
+// (https://git.eeqj.de/sneak/routewatch/issues/199). The test runs in a
+// synctest bubble, whose clock is fake, so a stall on the host does not use up
+// the handler's 4-second limit.
 func TestStatsAnswerGivesConnectionDurationInSeconds(t *testing.T) {
 	t.Parallel()
 
 	s := newServerWithTestRoutes(t)
 
+	synctest.Test(t, func(t *testing.T) {
 		connectionDuration := func() json.RawMessage {
 			answer := get(t, s, statsPath).Body.Bytes()
 
@@ -458,15 +491,18 @@ func TestStatsAnswerGivesConnectionDurationInSeconds(t *testing.T) {
 			t.Errorf("just connected: connection_duration_seconds = %s, want 0",
 				connected)
 		}
+	})
 }
 
 // TestStreamDurationsCountSeconds checks that the uptime and the connection
 // duration of a stream that connected 90 seconds ago are both 90. A stream
 // that has never connected has an uptime of 0, and one that is not connected
-// has no connection duration.
+// has no connection duration. The test runs in a synctest bubble, whose clock
+// is fake, so a stall on the host does not add to the 90 seconds.
 func TestStreamDurationsCountSeconds(t *testing.T) {
 	t.Parallel()
 
+	synctest.Test(t, func(t *testing.T) {
 		const connectedFor = 90 * time.Second
 
 		connectedSince := time.Now().Add(-connectedFor)
@@ -491,6 +527,7 @@ func TestStreamDurationsCountSeconds(t *testing.T) {
 			t.Errorf("connectionDurationSeconds while not connected = %d, want nil",
 				*got)
 		}
+	})
 }
 
 // newTestTable returns a routing table that holds a route for testPrefixV4,
@@ -523,8 +560,11 @@ func newServerWithTable(t *testing.T, table *routetable.Table) *Server {
 
 	t.Cleanup(func() { _ = db.Close() })
 
-	return New(db, table, streamer.New(logger.New(), metrics.New()), logger.New(),
+	s := New(db, table, streamer.New(logger.New(), metrics.New()), logger.New(),
 		&config.Config{})
+	useFakeResolver(s, &fakeResolver{})
+
+	return s
 }
 
 // TestPrefixDetailHandlersParsePrefix checks that both prefix pages find a
@@ -1134,7 +1174,9 @@ func (failingDB) GetPrefixFirstSeen(
 // with the driver's error text. It also sends a prefix that does not parse.
 // No answer may carry the driver's or the prefix parser's text. Before the fix
 // the answers sent it to the client
-// (https://git.eeqj.de/sneak/routewatch/issues/108).
+// (https://git.eeqj.de/sneak/routewatch/issues/108). The requests run in a
+// synctest bubble, whose clock is fake, so a stall on the host does not use up
+// the stats handlers' 4-second limit.
 func TestJSONRoutesDoNotSendErrorDetails(t *testing.T) {
 	t.Parallel()
 
@@ -1155,8 +1197,11 @@ func TestJSONRoutesDoNotSendErrorDetails(t *testing.T) {
 
 	for _, tt := range tests {
 		rec := httptest.NewRecorder()
+
+		synctest.Test(t, func(t *testing.T) {
 			s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
 				t.Context(), http.MethodGet, tt.path, nil))
+		})
 
 		if rec.Code != tt.wantCode {
 			t.Errorf("%s: status %d, want %d; body %s",
@@ -1213,7 +1258,7 @@ func TestIPLookupAnswers500WhenDatabaseReadFails(t *testing.T) {
 
 	s := New(failingIPLookupDB{}, newTestTable(),
 		streamer.New(logger.New(), metrics.New()), logger.New(), &config.Config{})
-	s.resolver = &fakeResolver{}
+	useFakeResolver(s, &fakeResolver{})
 
 	tests := []struct {
 		path     string
@@ -1249,16 +1294,19 @@ func TestIPLookupAnswers500WhenDatabaseReadFails(t *testing.T) {
 	}
 }
 
-// errNoSuchHost is what fakeResolver answers a lookup it has no answer for
+// errNoSuchHost is what fakeResolver answers a host name lookup it has no
-// with.
+// addresses for with.
 var errNoSuchHost = errors.New("no such host")
 
 // fakeResolver answers a host name lookup with the addresses hosts lists for
-// the name, and a PTR lookup with no names or, when ptrNeverAnswers is set,
+// the name. It answers a PTR lookup with the names ptrs lists for the address,
-// not at all: it waits until the lookup's context ends. hostLookups counts the
+// and with no names and no error, as the real one does, when ptrs lists none.
-// host name lookups.
+// When ptrNeverAnswers is set, a PTR lookup fails after ptr.LookupTimeout, as
+// the real one does when no resolver answers. hostLookups counts the host name
+// lookups.
 type fakeResolver struct {
 	hosts           map[string][]string
+	ptrs            map[string][]string
 	ptrNeverAnswers bool
 
 	hostLookups atomic.Int64
@@ -1275,14 +1323,23 @@ func (r *fakeResolver) LookupHost(_ context.Context, host string) ([]string, err
 	return addrs, nil
 }
 
-func (r *fakeResolver) LookupAddr(ctx context.Context, _ string) ([]string, error) {
+func (r *fakeResolver) LookupAddr(ctx context.Context, addr string) ([]string, error) {
 	if r.ptrNeverAnswers {
+		ctx, cancel := context.WithTimeout(ctx, ptr.LookupTimeout)
+		defer cancel()
+
 		<-ctx.Done()
 
 		return nil, ctx.Err()
 	}
 
-	return nil, errNoSuchHost
+	return r.ptrs[addr], nil
+}
+
+// useFakeResolver makes r answer the server's host name and PTR lookups.
+func useFakeResolver(s *Server, r *fakeResolver) {
+	s.resolver = r
+	s.ptrResolver = r
 }
 
 // countingIPLookupDB embeds database.Store (left nil) and answers the IP
@@ -1353,7 +1410,7 @@ func TestIPLookupRefusesTooManyAddresses(t *testing.T) {
 		s := New(db, newTestTable(), streamer.New(logger.New(), metrics.New()),
 			logger.New(), &config.Config{})
 		resolver := &fakeResolver{hosts: hosts}
-		s.resolver = resolver
+		useFakeResolver(s, resolver)
 
 		rec := httptest.NewRecorder()
 		s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
@@ -1388,17 +1445,21 @@ const addrInTestPrefixV4 = "192.0.2.1"
 
 // TestIPLookupKeepsRouteWhenPTRLookupDoesNotAnswer looks up a routed address
 // with a resolver that never answers its PTR lookup. Once the PTR lookup's own
-// limit passes, the lookup answers 200 with the route. Before the fix the PTR
+// limit passes, the lookup answers 200 with the route and an empty ptr. Before
-// lookup ran until the request's time limit, and the lookup answered 504
+// the fix the PTR lookup ran until the request's time limit, and the lookup
-// without the route (https://git.eeqj.de/sneak/routewatch/issues/110).
+// answered 504 without the route
+// (https://git.eeqj.de/sneak/routewatch/issues/110).
 func TestIPLookupKeepsRouteWhenPTRLookupDoesNotAnswer(t *testing.T) {
 	t.Parallel()
 
 	s := newServerWithTestRoutes(t)
-	s.resolver = &fakeResolver{ptrNeverAnswers: true}
+	useFakeResolver(s, &fakeResolver{ptrNeverAnswers: true})
 
-	// The request's time limit passes after the PTR lookup's.
+	// The request's time limit passes well after the PTR lookup's, so that a
-	ctx, cancel := context.WithTimeout(t.Context(), 2*ptrLookupTimeout)
+	// stall on a busy host does not use up the difference.
+	const requestTimeLimit = ptr.LookupTimeout + 15*time.Second
+
+	ctx, cancel := context.WithTimeout(t.Context(), requestTimeLimit)
 	defer cancel()
 
 	rec := httptest.NewRecorder()
@@ -1422,56 +1483,339 @@ func TestIPLookupKeepsRouteWhenPTRLookupDoesNotAnswer(t *testing.T) {
 		*body.Data.Results[0].Netblock != testPrefixV4 {
 		t.Errorf("answer %s, want one result in %s", rec.Body, testPrefixV4)
 	}
+
+	if !strings.Contains(rec.Body.String(), `"ptr":[]`) {
+		t.Errorf("answer %s, want an empty ptr list", rec.Body)
+	}
 }
 
 // addrInTestPrefixV6 is an address in testPrefixV6, which
 // newServerWithTestRoutes stores a route for.
 const addrInTestPrefixV6 = "2001:db8::1"
 
-// testBlocklistInterval is fakeBlocklists' shortest interval.
+// testIPListInterval is fakeIPLists' shortest interval.
-const testBlocklistInterval = 15 * time.Minute
+const testIPListInterval = 15 * time.Minute
 
 // ownAddressPath is the IP lookup of the caller's own address.
 const ownAddressPath = "/ip/"
 
-// listedUnroutedAddr is an address that fakeBlocklists lists, outside the
+// listedUnroutedAddr is an address that fakeIPLists lists, outside the routes
-// routes newServerWithTestRoutes stores.
+// newServerWithTestRoutes stores.
 const listedUnroutedAddr = "203.0.113.1"
 
-// fakeBlocklists has one list, which lists addrInTestPrefixV4 and
+// torExitAddr is the address that fakeIPLists lists on the Tor exit list.
-// listedUnroutedAddr and no other address.
+const torExitAddr = "203.0.113.2"
-type fakeBlocklists struct{}
 
-func testListing() blocklist.Listing {
+// relayAddr is the address that fakeIPLists lists on the iCloud Private Relay
-	return blocklist.Listing{
+// list.
+const relayAddr = "203.0.113.5"
+
+// The addresses that fakeIPLists lists on one and on two VPN lists, and the
+// names of those lists.
+const (
+	oneVPNListAddr  = "203.0.113.3"
+	twoVPNListsAddr = "203.0.113.4"
+	testVPNList     = "test_vpn"
+	otherTestVPN    = "other_test_vpn"
+)
+
+// fakeIPLists has five lists. The test list holds addrInTestPrefixV4,
+// listedUnroutedAddr and twoVPNListsAddr. The Tor exit list holds torExitAddr.
+// The iCloud Private Relay list holds relayAddr. The test VPN list holds
+// oneVPNListAddr and twoVPNListsAddr, and the other test VPN list holds
+// twoVPNListsAddr.
+type fakeIPLists struct{}
+
+func testListing() iplist.Listing {
+	return iplist.Listing{
 		Name:        "test_list",
 		Description: "On the test list",
 		Updated:     time.Date(2026, 10, 27, 4, 0, 0, 0, time.UTC),
 	}
 }
 
-func (fakeBlocklists) Lookup(addr netip.Addr) []blocklist.Listing {
+func (fakeIPLists) Lookup(addr netip.Addr) []iplist.Listing {
 	if addr == netip.MustParseAddr(addrInTestPrefixV4) ||
 		addr == netip.MustParseAddr(listedUnroutedAddr) {
-		return []blocklist.Listing{testListing()}
+		return []iplist.Listing{testListing()}
 	}
 
-	return []blocklist.Listing{}
+	if addr == netip.MustParseAddr(torExitAddr) {
+		return []iplist.Listing{{Name: iplist.TorExitsList}}
 	}
 
-func (fakeBlocklists) ShortestInterval() time.Duration {
+	if addr == netip.MustParseAddr(relayAddr) {
-	return testBlocklistInterval
+		return []iplist.Listing{{Name: iplist.ICloudPrivateRelayList}}
 	}
 
-// TestIPLookupReportsBlocklists looks up two routed addresses, one of them on
+	if addr == netip.MustParseAddr(oneVPNListAddr) {
-// a blocklist. The listed address's result names the list, says what it means
+		return []iplist.Listing{{Name: testVPNList, VPN: true}}
-// and when it was updated. The other's result has an empty list.
+	}
-func TestIPLookupReportsBlocklists(t *testing.T) {
+
+	if addr == netip.MustParseAddr(twoVPNListsAddr) {
+		return []iplist.Listing{
+			{Name: otherTestVPN, VPN: true},
+			testListing(),
+			{Name: testVPNList, VPN: true},
+		}
+	}
+
+	return []iplist.Listing{}
+}
+
+func (fakeIPLists) ShortestInterval() time.Duration {
+	return testIPListInterval
+}
+
+// TestIPLookupFlags looks up addresses with and without a route. Every result
+// has every flag, under the JSON keys the API documents.
+func TestIPLookupFlags(t *testing.T) {
+	t.Parallel()
+
+	s := newServerWithTestRoutes(t)
+	useFakeResolver(s, &fakeResolver{})
+	s.SetIPLists(fakeIPLists{})
+
+	tests := []struct {
+		name  string
+		addr  string
+		tor   bool
+		relay bool
+		bogon bool
+	}{
+		{"on the Tor exit list", torExitAddr, true, false, true},
+		{"on the iCloud Private Relay list", relayAddr, false, true, true},
+		{"on another list", listedUnroutedAddr, false, false, true},
+		{"routed IPv4", addrInTestPrefixV4, false, false, true},
+		{"routed IPv6", addrInTestPrefixV6, false, false, true},
+		{"private IPv4", "10.0.0.1", false, false, true},
+		{"loopback IPv4", "127.0.0.1", false, false, true},
+		{"public IPv4", "1.1.1.1", false, false, false},
+		{"private IPv6", "fd00::1", false, false, true},
+		{"loopback IPv6", "::1", false, false, true},
+		{"public IPv6", "2606:4700:4700::1111", false, false, false},
+		{"public IPv4 in IPv6 form", "::ffff:1.1.1.1", false, false, false},
+		{"private IPv4 in IPv6 form", "::ffff:10.0.0.1", false, false, true},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			path := "/api/v1/ip/" + tt.addr
+
+			results := resultFields(t, get(t, s, path).Body.Bytes())
+			if len(results) != 1 {
+				t.Fatalf("%s: %d results, want 1", path, len(results))
+			}
+
+			var got map[string]bool
+
+			err := json.Unmarshal(results[0]["flags"], &got)
+			if err != nil {
+				t.Fatalf("%s: decoding flags %s: %v", path, results[0]["flags"], err)
+			}
+
+			want := map[string]bool{
+				"is_tor": tt.tor, "is_vpn": false, "is_relay": tt.relay,
+				"is_bogon": tt.bogon,
+			}
+			if !maps.Equal(got, want) {
+				t.Errorf("%s: flags %v, want %v", path, got, want)
+			}
+		})
+	}
+}
+
+// fakeGeoLocator answers every address with location, and keeps the addresses
+// of each call. It is safe for the concurrent subtests that share it.
+type fakeGeoLocator struct {
+	location *geo.Location
+
+	mu    sync.Mutex
+	calls [][]netip.Addr
+}
+
+func (f *fakeGeoLocator) Lookup(
+	_ context.Context, addrs []netip.Addr,
+) []*geo.Location {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+
+	f.calls = append(f.calls, addrs)
+
+	answers := make([]*geo.Location, len(addrs))
+	for i := range addrs {
+		answers[i] = f.location
+	}
+
+	return answers
+}
+
+// TestIPLookupGivesTheGeoObject looks up two public addresses. They go to the
+// locator in one call, and each result has the geo object under the keys the
+// API documents. These addresses are public, because a reserved one is not
+// looked up.
+func TestIPLookupGivesTheGeoObject(t *testing.T) {
+	t.Parallel()
+
+	s := newServerWithTestRoutes(t)
+	useFakeResolver(s, &fakeResolver{})
+
+	locator := &fakeGeoLocator{location: &geo.Location{
+		CountryCode: new("DE"),
+		City:        new("Berlin"),
+		Latitude:    new(52.5),
+		Source:      "geojs",
+		Updated:     testRouteTime(0),
+	}}
+	s.SetGeoLocator(locator)
+
+	path := "/api/v1/ip/1.1.1.1,8.8.8.8"
+
+	results := resultFields(t, get(t, s, path).Body.Bytes())
+	if len(results) != 2 {
+		t.Fatalf("%s: %d results, want 2", path, len(results))
+	}
+
+	if len(locator.calls) != 1 || len(locator.calls[0]) != 2 {
+		t.Errorf("locator calls %v, want one with both addresses", locator.calls)
+	}
+
+	var got map[string]json.RawMessage
+
+	err := json.Unmarshal(results[0]["geo"], &got)
+	if err != nil {
+		t.Fatalf("decoding geo %s: %v", results[0]["geo"], err)
+	}
+
+	wantKeys := []string{
+		"accuracy_radius_km", "city", "continent_code", "country",
+		"country_code", "latitude", "longitude", "region", "source",
+		"time_zone", "updated",
+	}
+	if keys := slices.Sorted(maps.Keys(got)); !slices.Equal(keys, wantKeys) {
+		t.Errorf("geo keys %v, want %v", keys, wantKeys)
+	}
+
+	if string(got["city"]) != `"Berlin"` || string(got["latitude"]) != "52.5" ||
+		string(got["region"]) != jsonNull {
+		t.Errorf("wrong geo %s", results[0]["geo"])
+	}
+}
+
+// TestIPLookupOfAReservedAddressHasNoGeo looks up a reserved address alone and
+// beside a public one. The reserved one never reaches the locator, and its geo
+// is null.
+func TestIPLookupOfAReservedAddressHasNoGeo(t *testing.T) {
+	t.Parallel()
+
+	s := newServerWithTestRoutes(t)
+	useFakeResolver(s, &fakeResolver{})
+
+	locator := &fakeGeoLocator{location: &geo.Location{Source: "geojs"}}
+	s.SetGeoLocator(locator)
+
+	results := resultFields(t, get(t, s, "/api/v1/ip/"+addrInTestPrefixV4).Body.Bytes())
+	if len(results) != 1 || string(results[0]["geo"]) != jsonNull {
+		t.Fatalf("results %v, want one with geo null", results)
+	}
+
+	if len(locator.calls) != 0 {
+		t.Errorf("locator calls %v, want none", locator.calls)
+	}
+
+	results = resultFields(t,
+		get(t, s, "/api/v1/ip/"+addrInTestPrefixV4+",1.1.1.1").Body.Bytes())
+	if len(results) != 2 || string(results[0]["geo"]) != jsonNull ||
+		string(results[1]["geo"]) == jsonNull {
+		t.Errorf("results %v, want geo only for the public address", results)
+	}
+
+	if len(locator.calls) != 1 || len(locator.calls[0]) != 1 {
+		t.Errorf("locator calls %v, want one with one address", locator.calls)
+	}
+}
+
+// TestIPLookupGeoIsNullWhenNoSourceAnswers checks an address the locator has
+// no answer for.
+func TestIPLookupGeoIsNullWhenNoSourceAnswers(t *testing.T) {
+	t.Parallel()
+
+	s := newServerWithTestRoutes(t)
+	useFakeResolver(s, &fakeResolver{})
+	s.SetGeoLocator(&fakeGeoLocator{})
+
+	results := resultFields(t, get(t, s, "/api/v1/ip/1.1.1.1").Body.Bytes())
+	if len(results) != 1 || string(results[0]["geo"]) != jsonNull {
+		t.Errorf("results %v, want one with geo null", results)
+	}
+}
+
+// TestIPLookupReportsVPNProviders looks up addresses on no list, on a list
+// that is not a VPN list, on one VPN list and on two. is_vpn says whether any
+// VPN list holds the address, and vpn_providers names only those lists. An
+// address on none has [], not null.
+func TestIPLookupReportsVPNProviders(t *testing.T) {
 	t.Parallel()
 
 	s := newServerWithTestRoutes(t)
 	s.resolver = &fakeResolver{}
-	s.SetBlocklists(fakeBlocklists{})
+	s.SetIPLists(fakeIPLists{})
+
+	tests := []struct {
+		name      string
+		addr      string
+		isVPN     string
+		providers string
+	}{
+		{"on no list", "1.1.1.1", "false", `[]`},
+		{"on a list that is not a VPN list", listedUnroutedAddr, "false", `[]`},
+		{"on one VPN list", oneVPNListAddr, "true", `["` + testVPNList + `"]`},
+		{
+			"on two VPN lists", twoVPNListsAddr, "true",
+			`["` + otherTestVPN + `","` + testVPNList + `"]`,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			path := "/api/v1/ip/" + tt.addr
+
+			results := resultFields(t, get(t, s, path).Body.Bytes())
+			if len(results) != 1 {
+				t.Fatalf("%s: %d results, want 1", path, len(results))
+			}
+
+			var flags map[string]json.RawMessage
+
+			err := json.Unmarshal(results[0]["flags"], &flags)
+			if err != nil {
+				t.Fatalf("%s: decoding flags %s: %v", path, results[0]["flags"], err)
+			}
+
+			if got := string(flags["is_vpn"]); got != tt.isVPN {
+				t.Errorf("%s: is_vpn %s, want %s", path, got, tt.isVPN)
+			}
+
+			if got := string(results[0]["vpn_providers"]); got != tt.providers {
+				t.Errorf("%s: vpn_providers %s, want %s", path, got, tt.providers)
+			}
+		})
+	}
+}
+
+// TestIPLookupReportsIPLists looks up two routed addresses, one of them on an
+// IP list. The listed address's result names the list, says what it means and
+// when it was updated. The other's result has an empty list.
+func TestIPLookupReportsIPLists(t *testing.T) {
+	t.Parallel()
+
+	s := newServerWithTestRoutes(t)
+	useFakeResolver(s, &fakeResolver{})
+	s.SetIPLists(fakeIPLists{})
 
 	rec := httptest.NewRecorder()
 	s.router.ServeHTTP(rec, httptest.NewRequestWithContext(t.Context(),
@@ -1498,15 +1842,15 @@ func TestIPLookupReportsBlocklists(t *testing.T) {
 
 	want := testListing()
 
-	listed := results[0].Blocklists
+	listed := results[0].IPLists
 	if len(listed) != 1 || listed[0].Name != want.Name ||
 		listed[0].Description != want.Description ||
 		!listed[0].Updated.Equal(want.Updated) {
-		t.Errorf("%s: blocklists %+v, want [%+v]", results[0].IP, listed, want)
+		t.Errorf("%s: ip_lists %+v, want [%+v]", results[0].IP, listed, want)
 	}
 
-	if !strings.Contains(rec.Body.String(), `"blocklists":[]`) {
+	if !strings.Contains(rec.Body.String(), `"ip_lists":[]`) {
-		t.Errorf("answer %s, want an empty blocklists list for %s",
+		t.Errorf("answer %s, want an empty ip_lists list for %s",
 			rec.Body, addrInTestPrefixV6)
 	}
 }
@@ -1536,20 +1880,19 @@ func resultFields(t *testing.T, answer []byte) []map[string]json.RawMessage {
 	return body.Data.Results
 }
 
-// TestIPLookupReportsBlocklistsOfAnAddressWithNoRoute looks up a listed
+// TestIPLookupReportsIPListsOfAnAddressWithNoRoute looks up a listed address
-// address that has no live route, alone and beside a routed address. Each
+// that has no live route, alone and beside a routed address. Each answer is
-// answer is 200 and has a result for the address, with its blocklists and
+// 200 and has a result for the address, with its IP lists and every route
-// every route field set to null. Before the fix the lookup of that address
+// field set to null. Before the fix the lookup of that address alone answered
-// alone answered 404, and beside a routed address it was only named in
+// 404, and beside a routed address it was only named in errors, so its IP
-// errors, so its blocklists were never reported. After that fix the result
+// lists were never reported. After that fix the result still left out the
-// still left out the route fields
+// route fields (https://git.eeqj.de/sneak/routewatch/issues/200).
-// (https://git.eeqj.de/sneak/routewatch/issues/200).
+func TestIPLookupReportsIPListsOfAnAddressWithNoRoute(t *testing.T) {
-func TestIPLookupReportsBlocklistsOfAnAddressWithNoRoute(t *testing.T) {
 	t.Parallel()
 
 	s := newServerWithTestRoutes(t)
-	s.resolver = &fakeResolver{}
+	useFakeResolver(s, &fakeResolver{})
-	s.SetBlocklists(fakeBlocklists{})
+	s.SetIPLists(fakeIPLists{})
 
 	// routeFields are the fields of a result that come from the address's
 	// route and that route's origin AS.
@@ -1605,10 +1948,10 @@ func TestIPLookupReportsBlocklistsOfAnAddressWithNoRoute(t *testing.T) {
 		}
 
 		result := body.Data.Results[i]
-		if len(result.Blocklists) != 1 ||
+		if len(result.IPLists) != 1 ||
-			result.Blocklists[0].Name != testListing().Name {
+			result.IPLists[0].Name != testListing().Name {
-			t.Errorf("%s: blocklists %+v, want [%+v]",
+			t.Errorf("%s: ip_lists %+v, want [%+v]",
-				target, result.Blocklists, testListing())
+				target, result.IPLists, testListing())
 		}
 	}
 }
@@ -1626,10 +1969,10 @@ func TestIPLookupResultsHaveTheSameFields(t *testing.T) {
 	t.Parallel()
 
 	s := newServerWithTestRoutes(t)
-	s.resolver = &fakeResolver{hosts: map[string][]string{
+	useFakeResolver(s, &fakeResolver{hosts: map[string][]string{
 		twoAddressHostName: {addrInTestPrefixV4, listedUnroutedAddr},
-	}}
+	}})
-	s.SetBlocklists(fakeBlocklists{})
+	s.SetIPLists(fakeIPLists{})
 
 	// want is the fields of the first result.
 	var want []string
@@ -1661,7 +2004,7 @@ func TestIPLookupOfAnAddressWithoutPTRNamesOrStoredNetblock(t *testing.T) {
 	t.Parallel()
 
 	s := newServerWithTestRoutes(t)
-	s.resolver = &fakeResolver{}
+	useFakeResolver(s, &fakeResolver{})
 
 	path := "/api/v1/ip/" + addrInTestPrefixV4
 
@@ -1683,16 +2026,42 @@ func TestIPLookupOfAnAddressWithoutPTRNamesOrStoredNetblock(t *testing.T) {
 	}
 }
 
+// TestIPLookupGivesPTRNamesWithoutTrailingDots looks up an address whose PTR
+// name the resolver gives fully qualified. The result's ptr holds the name
+// without its trailing dot.
+func TestIPLookupGivesPTRNamesWithoutTrailingDots(t *testing.T) {
+	t.Parallel()
+
+	s := newServerWithTestRoutes(t)
+	useFakeResolver(s, &fakeResolver{ptrs: map[string][]string{
+		addrInTestPrefixV4: {"host.example.com."},
+	}})
+
+	path := "/api/v1/ip/" + addrInTestPrefixV4
+
+	results := resultFields(t, get(t, s, path).Body.Bytes())
+	if len(results) != 1 {
+		t.Fatalf("%s: %d results, want 1", path, len(results))
+	}
+
+	got := string(results[0]["ptr"])
+
+	want := `["host.example.com"]`
+	if got != want {
+		t.Errorf("%s: ptr is %s, want %s", path, got, want)
+	}
+}
+
 // TestIPLookupAnswersMayBeCached checks the Cache-Control header of the IP
-// lookup answers. Caches may keep them for the blocklists' shortest interval,
+// lookup answers. Caches may keep them for the IP lists' shortest interval,
 // and only the caller's own browser may keep the answer about the caller's
 // own address.
 func TestIPLookupAnswersMayBeCached(t *testing.T) {
 	t.Parallel()
 
 	s := newServerWithTestRoutes(t)
-	s.resolver = &fakeResolver{}
+	useFakeResolver(s, &fakeResolver{})
-	s.SetBlocklists(fakeBlocklists{})
+	s.SetIPLists(fakeIPLists{})
 
 	tests := []struct {
 		path string
@@ -1742,10 +2111,10 @@ func TestIPLookupHidesPrivateAddresses(t *testing.T) {
 	t.Parallel()
 
 	s := newServerWithTestRoutes(t)
-	s.resolver = &fakeResolver{hosts: map[string][]string{
+	useFakeResolver(s, &fakeResolver{hosts: map[string][]string{
 		internalHostName: {internalHostAddr},
 		"mixed.test":     {internalHostAddr, addrInTestPrefixV4},
-	}}
+	}})
 
 	notPublic := internalHostName + ": " + hostNotPublicMessage
 
@@ -2226,9 +2595,13 @@ func settledGoroutineCount() int {
 	return prev
 }
 
-// waitForGoroutines waits until the goroutine count drops to target or below.
+// waitForGoroutines waits up to 15 seconds for the goroutine count to drop to
+// target or below.
 func waitForGoroutines(target int) bool {
-	for range 100 {
+	const maxWait = 15 * time.Second
+
+	deadline := time.Now().Add(maxWait)
+	for time.Now().Before(deadline) {
 		if runtime.NumGoroutine() <= target {
 			return true
 		}

internal/server/handlers_table_internal_test.go

@@ -85,7 +85,7 @@ func TestIPLookupGivesTheOriginMostPeersCarry(t *testing.T) {
 	t.Parallel()
 
 	s := newServerWithTable(t, newTwoOriginTable())
-	s.resolver = &fakeResolver{}
+	useFakeResolver(s, &fakeResolver{})
 
 	firstSeen := testRouteTime(-1)
 

internal/server/home_internal_test.go

@@ -76,7 +76,9 @@ func asLink(asn int) string {
 }
 
 // TestHomePageCardsShowTheTableFigures fills a routing table and the asns
-// table, works out the cards, and checks that each card shows its figure.
+// table, works out the cards, and checks that each card shows its figure. The
+// cards are worked out in a synctest bubble, whose clock is fake, so a stall on
+// the host does not use up the 4-second limit on their database read.
 func TestHomePageCardsShowTheTableFigures(t *testing.T) {
 	t.Parallel()
 
@@ -95,7 +97,9 @@ func TestHomePageCardsShowTheTableFigures(t *testing.T) {
 		t.Fatalf("GetOrCreateASNBatch: %v", err)
 	}
 
+	synctest.Test(t, func(t *testing.T) {
 		s.refreshHomeCards(t.Context())
+	})
 
 	page := get(t, s, "/").Body.String()
 
@@ -279,7 +283,7 @@ func TestKeepHomeCardsFreshWorksThemOutEveryInterval(t *testing.T) {
 
 	const (
 		interval = 10 * time.Millisecond
-		maxWait  = 5 * time.Second
+		maxWait  = 15 * time.Second
 	)
 
 	table := emptyTable()
@@ -321,7 +325,7 @@ func TestKeepHomeCardsFreshWorksThemOutEveryInterval(t *testing.T) {
 func TestStartedServerWorksOutTheCards(t *testing.T) {
 	t.Parallel()
 
-	const maxWait = 5 * time.Second
+	const maxWait = 15 * time.Second
 
 	s := newServerWithTable(t, newCardsTable())
 

internal/server/middleware_internal_test.go

@@ -14,6 +14,7 @@ import (
 	"regexp"
 	"strings"
 	"testing"
+	"testing/synctest"
 	"time"
 
 	"git.eeqj.de/sneak/routewatch/internal/config"
@@ -114,7 +115,7 @@ func TestJSONAnswersPutNoUnitInAString(t *testing.T) {
 		`^([0-9]+(\.[0-9]+)? ?(ns|µs|ms|s|m|h|B|kB|MB|GB|TB))+$`)
 
 	s := newServerWithTestRoutes(t)
-	s.resolver = &fakeResolver{}
+	useFakeResolver(s, &fakeResolver{})
 	s.SetASNFetcher(fixedIntervalASNFetcher{interval: time.Second})
 
 	paths := []string{
@@ -163,6 +164,10 @@ func TestJSONAnswersPutNoUnitInAString(t *testing.T) {
 // router and the middleware write. Before the fix a panic in a handler, and a
 // method /status.json or the health check does not take, answered with an
 // empty body (https://git.eeqj.de/sneak/routewatch/issues/201).
+//
+// The requests run in a synctest bubble, whose clock is fake, so a stall on
+// the host does not use up the 2-second limit of the health check or the
+// 4-second limit of the stats handlers.
 func TestJSONAnswersCarryMeta(t *testing.T) {
 	t.Parallel()
 
@@ -174,13 +179,17 @@ func TestJSONAnswersCarryMeta(t *testing.T) {
 	)
 
 	s := newServerWithTestRoutes(t)
-	s.resolver = &fakeResolver{}
+	useFakeResolver(s, &fakeResolver{})
 	s.streamer.GetMetricsTracker().SetConnected(true)
 	s.router.Get(writesNothingPath, JSONValidationMiddleware(http.HandlerFunc(
 		func(http.ResponseWriter, *http.Request) {})).ServeHTTP)
 	s.router.Get(panicsPath, JSONValidationMiddleware(http.HandlerFunc(
 		func(http.ResponseWriter, *http.Request) { panic(errDiskIO) })).ServeHTTP)
 
+	failing := New(failingDB{}, newTestTable(),
+		streamer.New(logger.New(), metrics.New()), logger.New(), &config.Config{})
+	useFakeResolver(failing, &fakeResolver{})
+
 	tests := []struct {
 		method   string
 		path     string
@@ -216,14 +225,15 @@ func TestJSONAnswersCarryMeta(t *testing.T) {
 		{http.MethodGet, panicsPath, http.StatusInternalServerError},
 	}
 
+	synctest.Test(t, func(t *testing.T) {
 		for _, tt := range tests {
 			checkAnswerCarriesMeta(t, s, httptest.NewRequestWithContext(
 				t.Context(), tt.method, tt.path, nil), tt.wantCode)
 		}
 
-	// A request whose time limit has already passed answers 504. The handlers
+		// A request whose time limit has already passed answers 504. The
-	// write the answers of the first five routes, and the JSON check on the
+		// handlers write the answers of the first five routes, and the JSON
-	// route writes the last.
+		// check on the route writes the last.
 		pastTimeLimit, cancel := context.WithDeadline(t.Context(), time.Now())
 		defer cancel()
 
@@ -235,12 +245,8 @@ func TestJSONAnswersCarryMeta(t *testing.T) {
 				pastTimeLimit, http.MethodGet, path, nil), http.StatusGatewayTimeout)
 		}
 
-	// With a store whose reads fail, the health check answers 503, and the
+		// With a store whose reads fail, the health check answers 503, and
-	// handlers of the other routes 500.
+		// the handlers of the other routes 500.
-	failing := New(failingDB{}, newTestTable(),
-		streamer.New(logger.New(), metrics.New()), logger.New(), &config.Config{})
-	failing.resolver = &fakeResolver{}
-
 		checkAnswerCarriesMeta(t, failing, httptest.NewRequestWithContext(
 			t.Context(), http.MethodGet, healthCheckPath, nil),
 			http.StatusServiceUnavailable)
@@ -252,6 +258,7 @@ func TestJSONAnswersCarryMeta(t *testing.T) {
 			checkAnswerCarriesMeta(t, failing, httptest.NewRequestWithContext(
 				t.Context(), http.MethodGet, path, nil), http.StatusInternalServerError)
 		}
+	})
 }
 
 // checkAnswerCarriesMeta serves req through the server's router, and checks
@@ -514,7 +521,7 @@ func newServerWithConfig(
 
 	s := New(db, newTestTable(), streamer.New(logger.New(), metrics.New()),
 		&logger.Logger{Logger: slog.New(slog.NewJSONHandler(requestLog, nil))}, cfg)
-	s.resolver = &fakeResolver{}
+	useFakeResolver(s, &fakeResolver{})
 
 	return s
 }

internal/server/routes_internal_test.go

@@ -5,6 +5,7 @@ import (
 	"net/http"
 	"net/http/httptest"
 	"testing"
+	"testing/synctest"
 )
 
 // TestRoutesAnswerHEAD sends HEAD for a page and JSON routes through the
@@ -12,15 +13,23 @@ import (
 // lookup of the caller's own address, are in the list because chi's GetHead
 // does not reach them. Before the fix every route answered HEAD with 405
 // (https://git.eeqj.de/sneak/routewatch/issues/111).
+//
+// The requests run in a synctest bubble, whose clock is fake, so a stall on
+// the host does not use up the stats handlers' 4-second limit. The resolver
+// is fake because no time limit would cut off a real DNS lookup in a bubble.
 func TestRoutesAnswerHEAD(t *testing.T) {
 	t.Parallel()
 
 	s := newServerWithTestRoutes(t)
+	s.resolver = &fakeResolver{}
 
 	for _, path := range []string{"/", statusJSONPath, statsPath, "/ip", "/ip/"} {
 		rec := httptest.NewRecorder()
+
+		synctest.Test(t, func(t *testing.T) {
 			s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
 				t.Context(), http.MethodHead, path, nil))
+		})
 
 		if rec.Code != http.StatusOK {
 			t.Errorf("HEAD %s: status %d, want %d; body %s",

internal/server/server.go

@@ -22,9 +22,10 @@ import (
 	"sync/atomic"
 	"time"
 
-	"git.eeqj.de/sneak/routewatch/internal/blocklist"
 	"git.eeqj.de/sneak/routewatch/internal/config"
 	"git.eeqj.de/sneak/routewatch/internal/database"
+	"git.eeqj.de/sneak/routewatch/internal/geo"
+	"git.eeqj.de/sneak/routewatch/internal/iplist"
 	"git.eeqj.de/sneak/routewatch/internal/logger"
 	"git.eeqj.de/sneak/routewatch/internal/routetable"
 	"git.eeqj.de/sneak/routewatch/internal/streamer"
@@ -45,20 +46,30 @@ type ASNFetcher interface {
 	GetStats() ASNFetcherStats
 }
 
-// Blocklists tells which public blocklists list an address, from copies it
+// IPLists tells which public IP lists contain an address, from copies it keeps
-// keeps in memory, as *blocklist.Blocklists does.
+// in memory, as *iplist.IPLists does.
-type Blocklists interface {
+type IPLists interface {
-	Lookup(addr netip.Addr) []blocklist.Listing
+	Lookup(addr netip.Addr) []iplist.Listing
 	ShortestInterval() time.Duration
 }
 
-// dnsResolver looks up the addresses of host names and the names of addresses
+// dnsResolver looks up the addresses of host names in DNS, as *net.Resolver
-// in DNS, as *net.Resolver does.
+// does.
 type dnsResolver interface {
 	LookupHost(ctx context.Context, host string) ([]string, error)
+}
+
+// PTRResolver looks up the PTR names of addresses, as *ptr.Cache does.
+type PTRResolver interface {
 	LookupAddr(ctx context.Context, addr string) ([]string, error)
 }
 
+// GeoLocator finds where addresses are, as *geo.Locator does. It returns one
+// entry for each address, nil when no source answers.
+type GeoLocator interface {
+	Lookup(ctx context.Context, addrs []netip.Addr) []*geo.Location
+}
+
 // Server provides HTTP endpoints for status monitoring
 type Server struct {
 	router     *chi.Mux
@@ -69,16 +80,23 @@ type Server struct {
 	port       int
 	srv        *http.Server
 	asnFetcher ASNFetcher
-	blocklists Blocklists
+	ipLists    IPLists
 
 	// trustedProxies are the reverse proxies whose X-Forwarded-For header
 	// RealIPMiddleware believes
 	trustedProxies []netip.Prefix
 
-	// resolver makes the IP lookup's DNS lookups: net.DefaultResolver, or a
+	// resolver looks up the IP lookup's host names: net.DefaultResolver, or a
 	// fake in tests
 	resolver dnsResolver
 
+	// ptrResolver looks up the IP lookup's PTR names. SetPTRResolver sets it.
+	ptrResolver PTRResolver
+
+	// geoLocator finds where the IP lookup's addresses are. SetGeoLocator
+	// sets it.
+	geoLocator GeoLocator
+
 	// cards is the copy of the home page's cards that the pages serve, nil
 	// until the server first works them out
 	cards atomic.Pointer[homeCards]
@@ -196,14 +214,26 @@ func (s *Server) Stop(ctx context.Context) error {
 	return nil
 }
 
+// SetPTRResolver sets what looks up the IP lookup's PTR names. Call it before
+// Start: the handlers read it without a lock.
+func (s *Server) SetPTRResolver(resolver PTRResolver) {
+	s.ptrResolver = resolver
+}
+
+// SetGeoLocator sets what finds where the IP lookup's addresses are. Call it
+// before Start: the handlers read it without a lock.
+func (s *Server) SetGeoLocator(locator GeoLocator) {
+	s.geoLocator = locator
+}
+
 // SetASNFetcher sets the ASN WHOIS fetcher for on-demand lookups. Call it
 // before Start: the handlers read the fetcher without a lock.
 func (s *Server) SetASNFetcher(fetcher ASNFetcher) {
 	s.asnFetcher = fetcher
 }
 
-// SetBlocklists sets the blocklists the IP lookups report. Call it before
+// SetIPLists sets the IP lists the IP lookups report. Call it before Start:
-// Start: the handlers read the blocklists without a lock.
+// the handlers read the IP lists without a lock.
-func (s *Server) SetBlocklists(blocklists Blocklists) {
+func (s *Server) SetIPLists(ipLists IPLists) {
-	s.blocklists = blocklists
+	s.ipLists = ipLists
 }

internal/server/server_internal_test.go

@@ -22,10 +22,10 @@ func TestStopClosesTheConnectionOfARequestStillRunning(t *testing.T) {
 		stopDeadline = 100 * time.Millisecond
 		// waitTimeout is how long the test waits for the request to reach
 		// the handler, and then for the client to see its connection closed.
-		waitTimeout = 2 * time.Second
+		waitTimeout = 15 * time.Second
 		// readHeaderTimeout bounds the test server's read of the request
 		// header, as every http.Server must.
-		readHeaderTimeout = time.Second
+		readHeaderTimeout = waitTimeout
 	)
 
 	release := make(chan struct{})

internal/streamer/streamer_internal_test.go

@@ -14,6 +14,7 @@ import (
 	"strings"
 	"sync/atomic"
 	"testing"
+	"testing/synctest"
 	"time"
 
 	"git.eeqj.de/sneak/routewatch/internal/logger"
@@ -398,7 +399,7 @@ func TestStopQueuesTheHeldStateMessages(t *testing.T) {
 	const (
 		held    = 2
 		lines   = held + 1
-		maxWait = 5 * time.Second
+		maxWait = 15 * time.Second
 	)
 
 	srv := httptest.NewServer(http.HandlerFunc(
@@ -478,15 +479,15 @@ func TestStopQueuesTheHeldStateMessages(t *testing.T) {
 // TestStopReturnsByItsDeadline stops a streamer whose handler has a full queue
 // and a STATE message held for it, and a worker that stays busy until the test
 // ends, as one does whose handler waits for a database write. Stop must return
-// within its deadline plus a small margin instead of waiting for room on the
+// within its deadline plus a margin instead of waiting for room on the queue
-// queue and for the worker, and log as not handed over the held message and
+// and for the worker, and log as not handed over the held message and every
-// every message on the queue.
+// message on the queue.
 func TestStopReturnsByItsDeadline(t *testing.T) {
 	t.Parallel()
 
 	const (
 		deadline = 100 * time.Millisecond
-		margin   = 2 * time.Second
+		margin   = 15 * time.Second
 	)
 
 	var logs bytes.Buffer
@@ -577,7 +578,7 @@ func TestStopBeforeMessageReachesQueues(t *testing.T) {
 func TestReconnectWhenStreamEnds(t *testing.T) {
 	t.Parallel()
 
-	endResponse := func(http.ResponseWriter, *http.Request) {}
+	endResponse := pipeTransport{write: func(context.Context, io.Writer) {}}
 	checkReconnect(t, endResponse, streamIdleTimeout)
 }
 
@@ -589,9 +590,8 @@ func TestReconnectWhenStreamGoesIdle(t *testing.T) {
 
 	const idleTimeout = 50 * time.Millisecond
 
-	holdResponse := func(w http.ResponseWriter, r *http.Request) {
+	holdResponse := pipeTransport{
-		flush(w)
+		write: func(ctx context.Context, _ io.Writer) { <-ctx.Done() },
-		<-r.Context().Done()
 	}
 	checkReconnect(t, holdResponse, idleTimeout)
 }
@@ -604,16 +604,51 @@ func TestReconnectWhenServerNeverAnswers(t *testing.T) {
 
 	const idleTimeout = 50 * time.Millisecond
 
-	neverAnswer := func(_ http.ResponseWriter, r *http.Request) {
+	neverAnswer := roundTripFunc(
-		<-r.Context().Done()
+		func(req *http.Request) (*http.Response, error) {
-	}
+			<-req.Context().Done()
+
+			return nil, req.Context().Err()
+		},
+	)
 	checkReconnect(t, neverAnswer, idleTimeout)
 }
 
-// TestStreamNotDroppedWhileLinesArrive has the server send lines well within
+// pipeTransport answers every request with a response whose body write fills.
-// the idle timeout for several times the timeout, then end the response. Each
+// The body fails when the request's context ends, as a connection's does.
-// line must start the idle timeout over, so the stream lasts until the server
+// write gets that context, so that it can end when the request does.
-// ends it instead of being dropped as idle.
+type pipeTransport struct {
+	write func(context.Context, io.Writer)
+}
+
+func (p pipeTransport) RoundTrip(req *http.Request) (*http.Response, error) {
+	body, w := io.Pipe()
+
+	context.AfterFunc(req.Context(), func() {
+		_ = w.CloseWithError(req.Context().Err())
+	})
+
+	go func(ctx context.Context) {
+		p.write(ctx, w)
+
+		_ = w.Close()
+	}(req.Context())
+
+	return &http.Response{StatusCode: http.StatusOK, Body: body}, nil
+}
+
+// roundTripFunc makes a function an http.RoundTripper.
+type roundTripFunc func(*http.Request) (*http.Response, error)
+
+func (f roundTripFunc) RoundTrip(req *http.Request) (*http.Response, error) {
+	return f(req)
+}
+
+// TestStreamNotDroppedWhileLinesArrive has a response send lines well within
+// the idle timeout for several times the timeout, then end. Each line must
+// start the idle timeout over, so the stream lasts until the response ends
+// instead of being dropped as idle. It runs in a synctest bubble, whose clock
+// is fake, so a stall on the host does not use up the timeout.
 func TestStreamNotDroppedWhileLinesArrive(t *testing.T) {
 	t.Parallel()
 
@@ -623,26 +658,35 @@ func TestStreamNotDroppedWhileLinesArrive(t *testing.T) {
 		sendFor      = 5 * idleTimeout
 	)
 
-	srv := httptest.NewServer(http.HandlerFunc(
+	// The streamer is made outside the bubble. Its metrics start a goroutine
-		func(w http.ResponseWriter, _ *http.Request) {
+	// that never returns, and a bubble waits for each of its goroutines to
+	// return.
+	s := New(logger.New(), metrics.New())
+	s.idleTimeout = idleTimeout
+	s.client = &http.Client{Transport: pipeTransport{
+		write: func(ctx context.Context, w io.Writer) {
 			deadline := time.Now().Add(sendFor)
 			for time.Now().Before(deadline) {
 				_, _ = io.WriteString(w, updateLine)
 
-				flush(w)
+				// The wait ends with the stream. A bubble's clock stops when
-				time.Sleep(lineInterval)
+				// the test function returns, and a goroutine then still
+				// asleep panics the test binary.
+				select {
+				case <-ctx.Done():
+					return
+				case <-time.After(lineInterval):
 				}
-		}))
+			}
-	defer srv.Close()
+		},
-
+	}}
-	s := New(logger.New(), metrics.New())
-	s.url = srv.URL
-	s.idleTimeout = idleTimeout
 
+	synctest.Test(t, func(t *testing.T) {
 		err := s.stream(context.Background())
 		if !errors.Is(err, errStreamEnded) {
 			t.Fatalf("stream returned %v, want %v", err, errStreamEnded)
 		}
+	})
 }
 
 // TestStreamReadsLongLine has the server send one UPDATE line of about
@@ -706,7 +750,7 @@ func TestHandlerStatsReadWhileMessagesAreDropped(t *testing.T) {
 	const (
 		lines       = 5
 		wantDropped = lines - 2
-		maxWait     = 5 * time.Second
+		maxWait     = 15 * time.Second
 	)
 
 	srv := httptest.NewServer(http.HandlerFunc(
@@ -820,24 +864,38 @@ func streamLines(t *testing.T, s *Streamer, lines string) {
 // line and then stays open. The streamer must come back for a second
 // response, must not be marked connected when it does, and must handle the
 // UPDATE in it.
+//
+// It runs in a synctest bubble, whose clock is fake, so a stall on the host
+// does not use up the idle timeout. The fake server gets the requests in the
+// order the streamer makes them, because no real connection carries them.
 func checkReconnect(
-	t *testing.T, firstResponse http.HandlerFunc, idleTimeout time.Duration,
+	t *testing.T, firstResponse http.RoundTripper, idleTimeout time.Duration,
 ) {
 	t.Helper()
 
-	const maxWait = 5 * time.Second
+	const maxWait = 15 * time.Second
 
+	// The tracker is made outside the bubble. It starts a goroutine that never
+	// returns, and a bubble waits for each of its goroutines to return.
 	tracker := metrics.New()
+
+	synctest.Test(t, func(t *testing.T) {
 		connectedAtReconnect := make(chan bool, 1)
+		laterResponse := pipeTransport{
+			write: func(ctx context.Context, w io.Writer) {
+				_, _ = io.WriteString(w, updateLine)
+
+				<-ctx.Done()
+			},
+		}
 
 		var requests atomic.Int32
 
-	srv := httptest.NewServer(http.HandlerFunc(
+		s := New(logger.New(), tracker)
-		func(w http.ResponseWriter, r *http.Request) {
+		s.client = &http.Client{Transport: roundTripFunc(
+			func(req *http.Request) (*http.Response, error) {
 				if requests.Add(1) == 1 {
-				firstResponse(w, r)
+					return firstResponse.RoundTrip(req)
-
-				return
 				}
 
 				select {
@@ -845,15 +903,9 @@ func checkReconnect(
 				default:
 				}
 
-			_, _ = io.WriteString(w, updateLine)
+				return laterResponse.RoundTrip(req)
-
+			},
-			flush(w)
+		)}
-			<-r.Context().Done()
-		}))
-	defer srv.Close()
-
-	s := New(logger.New(), tracker)
-	s.url = srv.URL
 		s.idleTimeout = idleTimeout
 		s.minBackoff = time.Millisecond
 		handler := updateHandler{handled: make(chan struct{}, 1)}
@@ -875,6 +927,7 @@ func checkReconnect(
 			t.Error("streamer was still marked connected when it came back " +
 				"for a second response")
 		}
+	})
 }
 
 // settledGoroutineCount lets transient goroutines finish, then reports the
@@ -896,9 +949,13 @@ func settledGoroutineCount() int {
 	return prev
 }
 
-// waitForGoroutines waits until the goroutine count drops to target or below.
+// waitForGoroutines waits up to 15 seconds for the goroutine count to drop to
+// target or below.
 func waitForGoroutines(target int) bool {
-	for range 100 {
+	const maxWait = 15 * time.Second
+
+	deadline := time.Now().Add(maxWait)
+	for time.Now().Before(deadline) {
 		if runtime.NumGoroutine() <= target {
 			return true
 		}

internal/templates/index.html

@@ -544,6 +544,8 @@
         <span>{{appLicense}}</span>
         <span class="separator">|</span>
         <span><a href="{{appGitCommitURL}}">{{appGitRevision}}</a></span>
+        <span class="separator">|</span>
+        <span>IP Geolocation by <a href="https://db-ip.com">DB-IP</a></span>
     </footer>
 
     <script nonce="{{.CSPNonce}}">

internal/templates/templates_test.go

@@ -67,6 +67,23 @@ func TestFooterLicense(t *testing.T) {
 	}
 }
 
+// TestHomePageCreditsDBIP expects the home page's footer to carry the credit
+// to DB-IP.
+func TestHomePageCreditsDBIP(t *testing.T) {
+	t.Parallel()
+
+	const attribution = `IP Geolocation by <a href="https://db-ip.com">DB-IP</a>`
+
+	_, footer, found := strings.Cut(renderPage(t, templates.IndexTemplate()), "<footer")
+	if !found {
+		t.Fatal("the page has no footer")
+	}
+
+	if !strings.Contains(footer, attribution) {
+		t.Errorf("footer does not credit DB-IP: %q", footer)
+	}
+}
+
 // TestFreshnessIndicator renders the home and status pages and expects each to
 // have, right after the status element, the element where the page's script
 // shows its spinner or "stale".