Resolve PTR names over DNS-over-HTTPS and cache them for the record TTL (closes #238)

`ptr` keeps its field and shape. It now comes from Google, Cloudflare, AdGuard and Quad9 over RFC 8484, tried in turn within 2 seconds, in place of the host's resolver with no cache. Answers stay in memory and in a new `cache.db` for the record's TTL, at most 250,000 addresses. A reserved address is not sent to any resolver and has an empty `ptr`.

Judgement call: each resolver gets an equal share of the time left, so a hung one does not use up the limit.
Judgement call: the negative TTL is the smaller of the SOA minimum and the SOA's own TTL.
Deviation: the cache is SQLite, by sneak's words, not the JSON file the standing rule asks for.

Model: opus-5-5

internal/routewatch/app.go

@@ -9,17 +9,20 @@ package routewatch
 
 import (
 	"context"
+	"database/sql"
 	"errors"
 	"fmt"
 	"path/filepath"
 	"sync"
 	"time"
 
+	"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/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"
@@ -62,6 +65,8 @@ type RouteWatch struct {
 	asnFetcher     *ASNFetcher
 	dbMaintainer   *DBMaintainer
 	ipLists        *iplist.IPLists
+	cacheDB        *sql.DB
+	ptrCache       *ptr.Cache
 }
 
 // ipListsDirName is the directory in the state directory that holds the IP
@@ -150,6 +155,11 @@ func (rw *RouteWatch) Run(ctx context.Context) error {
 	rw.ipLists = ipLists
 	rw.server.SetIPLists(ipLists)
 
+	err = rw.startPTRCache(ctx)
+	if err != nil {
+		return err
+	}
+
 	// Start HTTP server
 	err = rw.server.Start(ctx)
 	if err != nil {
@@ -168,8 +178,8 @@ 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
-// IP list downloads and the HTTP server, and last the database, which it
-// checkpoints and closes. Each stage waits at most until ctx ends, so
+// IP list downloads, the HTTP server and the PTR cache, 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.
@@ -229,6 +239,8 @@ func (rw *RouteWatch) Shutdown(ctx context.Context) {
 			"error", err)
 	}
 
+	rw.stopPTRCache(ctx)
+
 	rw.closeDatabase(ctx)
 
 	// Log final metrics
@@ -242,6 +254,55 @@ 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
+}
+
+// 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"
@@ -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)
+	}
+}