Caches of outside APIs live in /var/cache/sww (closes #314)

The answers of GeoJS, the lists fetched by URL, the DNS blocklists,
AbuseIPDB and routewatch each go in a cache file in SWW_CACHE_DIR
(default /var/cache/sww): lookups.json, lists.json, dnsbl.json,
abuseipdb-scores.json and routewatch.json. reputation.json is gone. The
AbuseIPDB checks spent today are a count, not a cache, and stay in
SWW_STATE_DIR as abuseipdb-checks-spent.json.

A cache file never stops the start: one that does not parse is set
aside as an edit is, one that cannot be read is written over, and its
cache starts empty. An unwritable SWW_CACHE_DIR stops the start, as an
unwritable SWW_STATE_DIR does. Each directory is watched on its own.
The run script makes the cache directory and gives it to sww.

Model: opus-5-5

internal/config/config.go

@@ -191,12 +191,15 @@ type Config struct {
 	BanScopeV4Prefix int
 	// StateDir is the directory of the state files, an absolute path
 	// (SWW_STATE_DIR). bans.json is written StateWriteDelay after a ban
-	// is made (SWW_STATE_WRITE_DELAY), and every state file every
-	// StateCounterInterval (SWW_STATE_COUNTER_INTERVAL). Neither can be
-	// off.
+	// is made (SWW_STATE_WRITE_DELAY), and every state and cache file
+	// every StateCounterInterval (SWW_STATE_COUNTER_INTERVAL). Neither
+	// can be off.
 	StateDir             string
 	StateWriteDelay      time.Duration
 	StateCounterInterval time.Duration
+	// CacheDir is the directory of the cache files, which keep answers
+	// from outside services, an absolute path (SWW_CACHE_DIR).
+	CacheDir string
 	// LogRequestHeaders are the request headers whose values the request
 	// log gives, in lower case (SWW_LOG_REQUEST_HEADERS).
 	LogRequestHeaders []string
@@ -560,6 +563,7 @@ func FromEnvironment(
 		StateDir:             env.absolutePath("SWW_STATE_DIR", "/var/lib/sww"),
 		StateWriteDelay:      env.durationNotOff("SWW_STATE_WRITE_DELAY", "10s"),
 		StateCounterInterval: env.durationNotOff("SWW_STATE_COUNTER_INTERVAL", "15m"),
+		CacheDir:             env.absolutePath("SWW_CACHE_DIR", "/var/cache/sww"),
 		LogRequestHeaders: env.headerNames("SWW_LOG_REQUEST_HEADERS",
 			"accept,accept-language,accept-encoding,content-type,origin,range"),
 		LogLevel:            env.logLevel("SWW_LOG_LEVEL", "info"),

internal/config/config_test.go

@@ -74,6 +74,7 @@ const (
 	stateDir             = "SWW_STATE_DIR"
 	stateWriteDelay      = "SWW_STATE_WRITE_DELAY"
 	stateCounterInterval = "SWW_STATE_COUNTER_INTERVAL"
+	cacheDir             = "SWW_CACHE_DIR"
 	adminToken           = "SWW_ADMIN_TOKEN"   //nolint:gosec // the setting's name
 	metricsToken         = "SWW_METRICS_TOKEN" //nolint:gosec // the setting's name
 	metricsTopN          = "SWW_METRICS_TOP_N"
@@ -262,6 +263,7 @@ func TestDefaults(t *testing.T) {
 		StateDir:             "/var/lib/sww",
 		StateWriteDelay:      10 * time.Second,
 		StateCounterInterval: 15 * time.Minute,
+		CacheDir:             "/var/cache/sww",
 		MetricsToken:         "",
 		MetricsTopN:          50,
 		RulesDir:             "/etc/sww/rules.d",
@@ -346,6 +348,7 @@ func TestValuesAsSet(t *testing.T) {
 		stateDir:             "/srv/waf-state",
 		stateWriteDelay:      "500ms",
 		stateCounterInterval: "1h",
+		cacheDir:             "/srv/waf-cache",
 		metricsToken:         token,
 		metricsTopN:          "10",
 		rulesDir:             "/srv/waf-rules",
@@ -368,6 +371,7 @@ func TestValuesAsSet(t *testing.T) {
 		StateDir:             "/srv/waf-state",
 		StateWriteDelay:      500 * time.Millisecond,
 		StateCounterInterval: time.Hour,
+		CacheDir:             "/srv/waf-cache",
 		MetricsToken:         token,
 		MetricsTopN:          10,
 		RulesDir:             "/srv/waf-rules",
@@ -2302,6 +2306,7 @@ func TestInvalidBanOrStateValueStopsTheStart(t *testing.T) {
 		{stateDir, ""}, {stateDir, "state"}, {stateDir, "./var/lib/sww"},
 		{stateWriteDelay, off}, {stateWriteDelay, "0s"},
 		{stateCounterInterval, off}, {stateCounterInterval, "15"},
+		{cacheDir, ""}, {cacheDir, "cache"}, {cacheDir, "./var/cache/sww"},
 	})
 }
 
@@ -2574,6 +2579,7 @@ func TestLogsEachSettingWithItsValue(t *testing.T) {
 		stateDir:             "/var/lib/sww",
 		stateWriteDelay:      "10s",
 		stateCounterInterval: "15m",
+		cacheDir:             "/var/cache/sww",
 		adminToken:           "",
 		metricsToken:         "",
 		metricsTopN:          "50",
@@ -2674,8 +2680,8 @@ func wantLookupSettings(t *testing.T, got *config.Config, want config.Config) {
 	}
 }
 
-// wantBanSettings checks the settings for bans, the state files, the
-// metrics and the rule files.
+// wantBanSettings checks the settings for bans, the state and cache
+// files, the metrics and the rule files.
 func wantBanSettings(t *testing.T, got *config.Config, want config.Config) {
 	t.Helper()
 
@@ -2694,11 +2700,7 @@ func wantBanSettings(t *testing.T, got *config.Config, want config.Config) {
 			got.RulesDir, got.RulesEnabled, want.RulesDir, want.RulesEnabled)
 	}
 
-	if got.StateDir != want.StateDir ||
-		got.StateWriteDelay != want.StateWriteDelay ||
-		got.StateCounterInterval != want.StateCounterInterval {
-		t.Errorf("state settings\n%+v\nwant\n%+v", got, want)
-	}
+	wantStateSettings(t, got, want)
 
 	if got.MetricsToken != want.MetricsToken || got.MetricsTopN != want.MetricsTopN {
 		t.Errorf("metrics token %q and top %d, want %q and %d",
@@ -2706,6 +2708,18 @@ func wantBanSettings(t *testing.T, got *config.Config, want config.Config) {
 	}
 }
 
+// wantStateSettings checks the settings for the state and cache files.
+func wantStateSettings(t *testing.T, got *config.Config, want config.Config) {
+	t.Helper()
+
+	if got.StateDir != want.StateDir ||
+		got.StateWriteDelay != want.StateWriteDelay ||
+		got.StateCounterInterval != want.StateCounterInterval ||
+		got.CacheDir != want.CacheDir {
+		t.Errorf("state settings\n%+v\nwant\n%+v", got, want)
+	}
+}
+
 // wantNetblocks checks a list of netblocks.
 func wantNetblocks(t *testing.T, got []netip.Prefix, want ...string) {
 	t.Helper()

internal/reputation/abuseipdb.go

@@ -36,22 +36,21 @@ var (
 		"checks spent; none is made until the day ends at 00:00 UTC")
 )
 
-// Score is what AbuseIPDB said about a client, as reputation.json holds
-// it: the client, an IPv4 address or an IPv6 group, its abuse confidence
-// score, from 0 to 100, and when AbuseIPDB answered.
+// Score is what AbuseIPDB said about a client, as abuseipdb-scores.json
+// holds it: the client, an IPv4 address or an IPv6 group, its abuse
+// confidence score, from 0 to 100, and when AbuseIPDB answered.
 type Score struct {
 	Client  netip.Prefix `json:"client"`
 	Score   int64        `json:"score"`
 	Fetched time.Time    `json:"fetched"`
 }
 
-// Checks are what reputation.json keeps of the checks of clients with
-// AbuseIPDB: the day, in UTC, of the checks Spent counts, zero before the
-// first, and the scores still in use.
-type Checks struct {
-	Day    civil.Date `json:"day,omitzero"`
-	Spent  int        `json:"spent"`
-	Scores []Score    `json:"scores"`
+// ChecksSpent is what abuseipdb-checks-spent.json keeps of the checks of
+// clients with AbuseIPDB: the day, in UTC, of the checks Spent counts,
+// zero before the first.
+type ChecksSpent struct {
+	Day   civil.Date
+	Spent int
 }
 
 // AbuseIPDBParams are what NewAbuseIPDB needs.
@@ -196,35 +195,35 @@ func (a *AbuseIPDB) BudgetLeft() int {
 	return max(a.params.DailyBudget-a.spent, 0)
 }
 
-// Snapshot returns the checks spent and every score still in use, sorted
-// by client, as reputation.json keeps them.
-func (a *AbuseIPDB) Snapshot() Checks {
+// Snapshot returns every score still in use, sorted by client, as
+// abuseipdb-scores.json keeps them.
+func (a *AbuseIPDB) Snapshot() []Score {
 	a.mu.Lock()
 
 	now := a.params.Now()
-	checks := Checks{Day: a.day, Spent: a.spent, Scores: make([]Score, 0, a.scores.Len())}
+	scores := make([]Score, 0, a.scores.Len())
 
 	for _, kept := range a.scores.Values() {
 		if now.Sub(kept.Fetched) < a.params.CacheTTL {
-			checks.Scores = append(checks.Scores, kept)
+			scores = append(scores, kept)
 		}
 	}
 
 	a.mu.Unlock()
 
-	slices.SortFunc(checks.Scores, func(x, y Score) int {
+	slices.SortFunc(scores, func(x, y Score) int {
 		return x.Client.Compare(y.Client)
 	})
 
-	return checks
+	return scores
 }
 
-// Load keeps checks, read from reputation.json, in place of those it
-// keeps, but for the scores past maxVerdicts, those fetched longest ago.
-// One fetched CacheTTL ago or more is neither used nor written, as for any
-// score.
-func (a *AbuseIPDB) Load(checks Checks) {
-	scores := slices.Clone(checks.Scores)
+// Load keeps scores, read from abuseipdb-scores.json, in place of those
+// it keeps, but for the scores past maxVerdicts, those fetched longest
+// ago. One fetched CacheTTL ago or more is neither used nor written, as
+// for any score.
+func (a *AbuseIPDB) Load(scores []Score) {
+	scores = slices.Clone(scores)
 	slices.SortStableFunc(scores, func(x, y Score) int {
 		return x.Fetched.Compare(y.Fetched)
 	})
@@ -232,7 +231,6 @@ func (a *AbuseIPDB) Load(checks Checks) {
 	a.mu.Lock()
 	defer a.mu.Unlock()
 
-	a.day, a.spent = checks.Day, checks.Spent
 	a.scores.Purge()
 
 	for _, kept := range scores {
@@ -240,6 +238,24 @@ func (a *AbuseIPDB) Load(checks Checks) {
 	}
 }
 
+// ChecksSpent returns the checks spent, as abuseipdb-checks-spent.json
+// keeps them.
+func (a *AbuseIPDB) ChecksSpent() ChecksSpent {
+	a.mu.Lock()
+	defer a.mu.Unlock()
+
+	return ChecksSpent{Day: a.day, Spent: a.spent}
+}
+
+// LoadChecksSpent keeps checks, read from abuseipdb-checks-spent.json, in
+// place of the checks spent.
+func (a *AbuseIPDB) LoadChecksSpent(checks ChecksSpent) {
+	a.mu.Lock()
+	defer a.mu.Unlock()
+
+	a.day, a.spent = checks.Day, checks.Spent
+}
+
 // check checks client with AbuseIPDB by addr, one of its addresses, keeps
 // the score as client's, and notes the check as no longer under way. A
 // check that fails gives no score: it is counted, logged and raised as a

internal/reputation/abuseipdb_test.go

@@ -17,6 +17,7 @@ import (
 	"testing/synctest"
 	"time"
 
+	"cloud.google.com/go/civil"
 	"sneak.berlin/go/smallwebwaf/internal/alerts"
 	"sneak.berlin/go/smallwebwaf/internal/metrics"
 	"sneak.berlin/go/smallwebwaf/internal/reputation"
@@ -179,11 +180,13 @@ func TestDailyBudgetKeptAcrossARestartAndWholeAgainAsTheDayEnds(t *testing.T) {
 			t.Errorf("logged\n%s\nwant the budget used up", log.String())
 		}
 
-		// Restarted with what reputation.json keeps, it uses the scores, and
-		// checks no client until the day ends.
+		// Restarted with what abuseipdb-scores.json and
+		// abuseipdb-checks-spent.json keep, it uses the scores, and checks
+		// no client until the day ends.
 		restarted := &abuseIPDBStandIn{}
 		again := newAbuseIPDB(restarted, p)
 		again.Load(checker.Snapshot())
+		again.LoadChecksSpent(checker.ChecksSpent())
 
 		wantScore(t, again, suspect, true, 100, true)
 		wantBudgetLeft(t, again, 0)
@@ -224,13 +227,9 @@ func TestChecksAreCountedInUTCDaysWhateverTheClocksZone(t *testing.T) {
 		time.Sleep(2 * time.Hour)
 		wantBudgetLeft(t, checker, 0)
 
-		encoded, err := json.Marshal(checker.Snapshot())
-		if err != nil {
-			t.Fatalf("encode: %v", err)
-		}
-
-		if !strings.Contains(string(encoded), `"day":"2000-01-01"`) {
-			t.Errorf("reputation.json would hold %s, want the day 2000-01-01", encoded)
+		want := civil.Date{Year: 2000, Month: 1, Day: 1}
+		if day := checker.ChecksSpent().Day; day != want {
+			t.Errorf("checks spent on %s, want on %s", day, want)
 		}
 
 		// At 00:00 UTC the budget is whole again.
@@ -302,7 +301,7 @@ func TestFailedCheckGivesNoScoreAndNoClientIsCheckedForAMinute(t *testing.T) {
 				wantChecked(t, abuseIPDB, suspect, other)
 				wantFailures(t, checker, 2)
 
-				if scores := checker.Snapshot().Scores; len(scores) != 0 {
+				if scores := checker.Snapshot(); len(scores) != 0 {
 					t.Errorf("scores %+v, want none", scores)
 				}
 
@@ -399,7 +398,7 @@ func TestKeyIsSentInTheKeyHeaderAndNeverShown(t *testing.T) {
 
 		for name, shown := range map[string]string{
 			"the log": log.String(), "the alerts": string(alerted),
-			"the metrics": scrapeMetrics(t, m), "reputation.json": string(kept),
+			"the metrics": scrapeMetrics(t, m), "abuseipdb-scores.json": string(kept),
 		} {
 			if strings.Contains(shown, key) {
 				t.Errorf("%s shows the key:\n%s", name, shown)
@@ -462,12 +461,12 @@ func TestScoreFetchedATTLAgoIsNeitherUsedNorKept(t *testing.T) {
 		Fetched: now.Add(-cacheTTL),
 	}
 
-	checker.Load(reputation.Checks{Scores: []reputation.Score{stale, inUse}})
+	checker.Load([]reputation.Score{stale, inUse})
 
 	wantScore(t, checker, suspect, false, 100, true)
 	wantScore(t, checker, other, false, 0, false)
 
-	got := checker.Snapshot().Scores
+	got := checker.Snapshot()
 	if !reflect.DeepEqual(got, []reputation.Score{inUse}) {
 		t.Errorf("scores %+v, want only %+v", got, inUse)
 	}
@@ -481,7 +480,7 @@ func TestAtMost100000ScoresKeptTheOneFetchedLongestAgoDroppedFirst(t *testing.T)
 	p.Now = func() time.Time { return now }
 	checker := reputation.NewAbuseIPDB(p)
 
-	// 100,001 scores, listed by client, as reputation.json lists them, each
+	// 100,001 scores, listed by client, as abuseipdb-scores.json lists them, each
 	// fetched a millisecond before the one before it: the last is one too
 	// many.
 	const count = 100001
@@ -497,9 +496,9 @@ func TestAtMost100000ScoresKeptTheOneFetchedLongestAgoDroppedFirst(t *testing.T)
 		addr = addr.Next()
 	}
 
-	checker.Load(reputation.Checks{Scores: scores})
+	checker.Load(scores)
 
-	got := checker.Snapshot().Scores
+	got := checker.Snapshot()
 	if len(got) != count-1 || !slices.Contains(got, scores[0]) ||
 		slices.Contains(got, scores[count-1]) {
 		t.Errorf("%d scores kept, want all but the one fetched longest ago", len(got))

internal/reputation/crowdsec_test.go

@@ -291,7 +291,7 @@ func crowdSecFailures() []crowdSecFailure {
 // other than its decision list, such as the one a redirect names, and that
 // the key is in none of what the fetches leave behind: log, the process
 // log, the alerts waiting in queue, and the copies of lists, which
-// reputation.json keeps.
+// lists.json keeps.
 func wantKeyNotShown(
 	t *testing.T, e *engine, log string, lists *reputation.Lists, queue *alerts.Queue,
 ) {
@@ -326,7 +326,7 @@ func TestCrowdSecDecisionListKeptAcrossARestartEndsWhenItsDecisionsDo(t *testing
 		lists := start(t, e, crowdSecParams())
 		kept := lists.Snapshot()
 
-		// Restarted half an hour later with what reputation.json keeps, and
+		// Restarted half an hour later with what lists.json keeps, and
 		// the engine down, the decision still bans, until the end it had at
 		// the fetch, half an hour on.
 		time.Sleep(30 * time.Minute)

internal/reputation/dnsbl.go

@@ -40,7 +40,7 @@ var (
 	errNotListing = errors.New("the answer is outside 127.0.0.0/8")
 )
 
-// Verdict is what a zone said about a client, as reputation.json holds
+// Verdict is what a zone said about a client, as dnsbl.json holds
 // it: the zone, the client's address, whether the zone lists it, and when
 // the zone answered.
 type Verdict struct {
@@ -187,7 +187,7 @@ func (d *DNSBL) Failures(zone string) int {
 }
 
 // Snapshot returns every verdict still in use, sorted by client, then by
-// zone, as reputation.json lists them.
+// zone, as dnsbl.json lists them.
 func (d *DNSBL) Snapshot() []Verdict {
 	d.mu.Lock()
 
@@ -209,7 +209,7 @@ func (d *DNSBL) Snapshot() []Verdict {
 	return verdicts
 }
 
-// Load keeps verdicts, read from reputation.json, in place of those it
+// Load keeps verdicts, read from dnsbl.json, in place of those it
 // keeps, but for those of a zone SWW_DNSBL_ZONES does not name, and,
 // past maxVerdicts, those fetched longest ago. One fetched CacheTTL ago or
 // more is neither used nor written, as for any verdict.

internal/reputation/dnsbl_test.go

@@ -389,7 +389,7 @@ func TestVerdictsKeptAcrossARestart(t *testing.T) {
 			t.Errorf("verdicts %+v, want %+v", kept, want)
 		}
 
-		// Restarted an hour later with what reputation.json keeps, it uses
+		// Restarted an hour later with what dnsbl.json keeps, it uses
 		// the verdicts, and asks the zone nothing, until the TTL has passed
 		// since they were fetched.
 		time.Sleep(time.Hour)
@@ -446,7 +446,7 @@ func TestAtMost100000VerdictsKeptTheOneFetchedLongestAgoDroppedFirst(t *testing.
 	p.Now = func() time.Time { return now }
 	dnsbl := reputation.NewDNSBL(p)
 
-	// 100,001 verdicts, listed by client, as reputation.json lists them,
+	// 100,001 verdicts, listed by client, as dnsbl.json lists them,
 	// each fetched a millisecond before the one before it: the last is one
 	// too many.
 	const count = 100001

internal/reputation/reputation.go

@@ -7,8 +7,8 @@
 // and when each was last tried. It also asks the DNSBL zones of
 // SWW_DNSBL_ZONES about clients, and keeps their verdicts, and checks
 // clients with AbuseIPDB, and keeps their scores and the checks spent
-// today. The state package writes all of these to reputation.json and
-// reads them from it, so that a restart keeps them too.
+// today. The state package writes all of these to files and reads them
+// from there, so that a restart keeps them too.
 package reputation
 
 import (
@@ -54,7 +54,7 @@ var (
 		"does not give an address or a netblock and a duration, such as 4h0m0s")
 )
 
-// List is a list as reputation.json holds it: the URL it is fetched from,
+// List is a list as lists.json holds it: the URL it is fetched from,
 // when it was last tried, the fetch failed or not, and its last good copy:
 // when that was fetched, and its lines, as fetched, comment lines
 // included, both left out while no fetch of it has succeeded.
@@ -106,7 +106,7 @@ type Lists struct {
 	lists map[string]*list
 }
 
-// list is one list: what reputation.json keeps of it, its last try, zero
+// list is one list: what lists.json keeps of it, its last try, zero
 // before the first, and its last good copy, what that copy says, and how
 // many fetches of it failed.
 type list struct {
@@ -272,7 +272,7 @@ func (l *Lists) Failures(listURL string) int {
 
 // Run fetches each list once it is due, as due tells, until ctx is done. A
 // list never tried is fetched at once, and so is one that is due by its
-// last try or copy read from reputation.json.
+// last try or copy read from lists.json.
 func (l *Lists) Run(ctx context.Context) {
 	if len(l.lists) == 0 {
 		return
@@ -292,7 +292,7 @@ func (l *Lists) Run(ctx context.Context) {
 }
 
 // Snapshot returns each list that has been tried, with its copy, if it
-// has one, sorted by URL, as reputation.json lists them.
+// has one, sorted by URL, as lists.json lists them.
 func (l *Lists) Snapshot() []List {
 	l.mu.Lock()
 
@@ -313,7 +313,7 @@ func (l *Lists) Snapshot() []List {
 	return tried
 }
 
-// Load puts lists, read from reputation.json, in place of the last tries
+// Load puts lists, read from lists.json, in place of the last tries
 // and copies held. A list Params does not name is dropped. A copy with a
 // line that parse refuses is an error, and then nothing changes.
 func (l *Lists) Load(lists []List) error {

internal/reputation/reputation_test.go

@@ -260,7 +260,7 @@ func TestKeptCopyIsFetchedAgainOnceRefreshHasPassedSinceItWasFetched(t *testing.
 		lists.SetTransport(servers)
 
 		// drop.txt was fetched an hour ago, and tor.txt a refresh ago, as
-		// reputation.json says at start.
+		// lists.json says at start.
 		err := lists.Load([]reputation.List{
 			{URL: dropURL, Fetched: time.Now().Add(-time.Hour), Lines: []string{"203.0.113.9"}},
 			{URL: torURL, Fetched: time.Now().Add(-refresh), Lines: []string{"198.51.100.9"}},
@@ -297,7 +297,7 @@ func TestRestartWaitsRefreshAfterTheLastTryEvenOneThatFailed(t *testing.T) {
 		time.Sleep(refresh)
 		wantFetches(t, servers, 2)
 
-		// Restarted with what reputation.json keeps, it waits a refresh
+		// Restarted with what lists.json keeps, it waits a refresh
 		// after the failed try, as it does while it runs.
 		restarted := &standIn{lists: map[string]string{dropURL: "198.51.100.2\n"}}
 		again := reputation.New(params(dropURL))
@@ -353,7 +353,7 @@ func TestFetchCutOffAsItStopsIsNoFailureButARestartWaitsForIt(t *testing.T) {
 				waiting(queue))
 		}
 
-		// Restarted an hour later with what reputation.json keeps, it fetches
+		// Restarted an hour later with what lists.json keeps, it fetches
 		// tor.txt, never tried, at once, and drop.txt a refresh after its
 		// cut-off try.
 		time.Sleep(time.Hour)

internal/routewatch/routewatch.go

@@ -1,6 +1,8 @@
 // Package routewatch asks a routewatch instance about client addresses, in the
-// background, and keeps its answers in memory. A routewatch instance knows, for
-// an address, the netblock it is announced in and the AS that originates it.
+// background, and keeps its answers. A routewatch instance knows, for an
+// address, the netblock it is announced in and the AS that originates it. The
+// answers are kept in memory, for at most 100,000 clients and for an hour each,
+// and are written to routewatch.json and read from it by the state package.
 package routewatch
 
 import (
@@ -13,6 +15,7 @@ import (
 	"net/http"
 	"net/netip"
 	"net/url"
+	"slices"
 	"sync"
 	"time"
 
@@ -65,6 +68,17 @@ type Route struct {
 	ASN      uint32
 }
 
+// Answer is what routewatch answered about a client, as routewatch.json holds
+// it: the netblock the client's address is announced in, none for an address
+// without a live route, the AS that originates it, and when routewatch
+// answered.
+type Answer struct {
+	Client   netip.Prefix `json:"client"`
+	Netblock netip.Prefix `json:"netblock"`
+	ASN      uint32       `json:"asn"`
+	Answered time.Time    `json:"answered"`
+}
+
 // Params are what New needs.
 type Params struct {
 	// URL is where routewatch is (SWW_ROUTEWATCH_URL).
@@ -84,23 +98,16 @@ type Client struct {
 	mu sync.Mutex
 	// answers are by client. Each is added as it comes and never moved up,
 	// so that the one that came longest ago is the first dropped.
-	answers *simplelru.LRU[netip.Prefix, answer]
+	answers *simplelru.LRU[netip.Prefix, Answer]
 	// asking are the clients whose query is under way.
 	asking map[netip.Prefix]bool
 	// retryAt is when routewatch may be asked again after a query failed.
 	retryAt time.Time
 }
 
-// answer is one kept answer: the route, or why there is none, and when it came.
-type answer struct {
-	route   Route
-	missing Missing
-	came    time.Time
-}
-
 // New returns a Client with no answer yet.
 func New(params Params) *Client {
-	answers, err := simplelru.NewLRU[netip.Prefix, answer](maxAnswers, nil)
+	answers, err := simplelru.NewLRU[netip.Prefix, Answer](maxAnswers, nil)
 	if err != nil {
 		panic(err) // NewLRU fails only for a size below one
 	}
@@ -128,8 +135,12 @@ func (c *Client) Route(
 	now := c.params.Now()
 
 	kept, found := c.answers.Peek(client)
-	if found && now.Sub(kept.came) < answerKept {
-		return kept.route, kept.missing
+	if found && now.Sub(kept.Answered) < answerKept {
+		if !kept.Netblock.IsValid() {
+			return Route{}, NoRoute
+		}
+
+		return Route{Netblock: kept.Netblock, ASN: kept.ASN}, ""
 	}
 
 	if now.Before(c.retryAt) {
@@ -145,12 +156,58 @@ func (c *Client) Route(
 	return Route{}, NoAnswerYet
 }
 
+// Snapshot returns every answer still in use, sorted by client, as
+// routewatch.json lists them.
+func (c *Client) Snapshot() []Answer {
+	c.mu.Lock()
+
+	now := c.params.Now()
+	answers := make([]Answer, 0, c.answers.Len())
+
+	for _, kept := range c.answers.Values() {
+		if now.Sub(kept.Answered) < answerKept {
+			answers = append(answers, kept)
+		}
+	}
+
+	c.mu.Unlock()
+
+	slices.SortFunc(answers, func(a, b Answer) int {
+		return a.Client.Compare(b.Client)
+	})
+
+	return answers
+}
+
+// Load keeps answers, read from routewatch.json, in place of those it keeps,
+// but for those that came answerKept ago or more and, past maxAnswers, those
+// that came longest ago.
+func (c *Client) Load(answers []Answer) {
+	answers = slices.Clone(answers)
+	slices.SortStableFunc(answers, func(a, b Answer) int {
+		return a.Answered.Compare(b.Answered)
+	})
+
+	c.mu.Lock()
+	defer c.mu.Unlock()
+
+	c.answers.Purge()
+
+	now := c.params.Now()
+
+	for _, kept := range answers {
+		if now.Sub(kept.Answered) < answerKept {
+			c.answers.Add(kept.Client, kept)
+		}
+	}
+}
+
 // ask asks routewatch about addr, keeps the answer as client's, and notes the
 // query as no longer under way. A query that fails gives no answer, and
 // routewatch is not asked again for failureKept. Only the first failure of
 // those under way is logged.
 func (c *Client) ask(ctx context.Context, client netip.Prefix, addr netip.Addr) {
-	route, missing, err := c.query(ctx, addr)
+	route, err := c.query(ctx, addr)
 	now := c.params.Now()
 
 	c.mu.Lock()
@@ -160,7 +217,9 @@ func (c *Client) ask(ctx context.Context, client netip.Prefix, addr netip.Addr)
 	firstFailure := err != nil && !now.Before(c.retryAt)
 
 	if err == nil {
-		c.answers.Add(client, answer{route: route, missing: missing, came: now})
+		c.answers.Add(client, Answer{
+			Client: client, Netblock: route.Netblock, ASN: route.ASN, Answered: now,
+		})
 	} else {
 		c.retryAt = now.Add(failureKept)
 	}
@@ -174,19 +233,19 @@ func (c *Client) ask(ctx context.Context, client netip.Prefix, addr netip.Addr)
 
 // query asks routewatch's IP info API about addr. An answer other than 200, one
 // that cannot be read, and none within queryTimeout, fail. A result with no
-// netblock is an address without a live route.
-func (c *Client) query(ctx context.Context, addr netip.Addr) (Route, Missing, error) {
+// netblock is an address without a live route, and gives a Route without one.
+func (c *Client) query(ctx context.Context, addr netip.Addr) (Route, error) {
 	ctx, cancel := context.WithTimeout(ctx, queryTimeout)
 	defer cancel()
 
 	endpoint, err := url.JoinPath(c.params.URL, "api/v1/ip", addr.String())
 	if err != nil {
-		return Route{}, "", fmt.Errorf("make the URL: %w", err)
+		return Route{}, fmt.Errorf("make the URL: %w", err)
 	}
 
 	req, err := http.NewRequestWithContext(ctx, http.MethodGet, endpoint, http.NoBody)
 	if err != nil {
-		return Route{}, "", fmt.Errorf("make the request: %w", err)
+		return Route{}, fmt.Errorf("make the request: %w", err)
 	}
 
 	req.Header.Set("Accept", "application/json")
@@ -195,7 +254,7 @@ func (c *Client) query(ctx context.Context, addr netip.Addr) (Route, Missing, er
 	if err != nil {
 		// Do's error names the URL, which holds the client's address, which
 		// is not to be logged: only what went wrong is kept.
-		return Route{}, "", fmt.Errorf("ask routewatch: %w", errors.Unwrap(err))
+		return Route{}, fmt.Errorf("ask routewatch: %w", errors.Unwrap(err))
 	}
 
 	defer func() {
@@ -203,14 +262,14 @@ func (c *Client) query(ctx context.Context, addr netip.Addr) (Route, Missing, er
 	}()
 
 	if res.StatusCode != http.StatusOK {
-		return Route{}, "", fmt.Errorf("%w %s", errStatus, res.Status)
+		return Route{}, fmt.Errorf("%w %s", errStatus, res.Status)
 	}
 
 	return readAnswer(io.LimitReader(res.Body, maxAnswerBytes))
 }
 
 // readAnswer reads routewatch's answer about one address.
-func readAnswer(body io.Reader) (Route, Missing, error) {
+func readAnswer(body io.Reader) (Route, error) {
 	var decoded struct {
 		Data struct {
 			Results []struct {
@@ -222,22 +281,22 @@ func readAnswer(body io.Reader) (Route, Missing, error) {
 
 	err := json.NewDecoder(body).Decode(&decoded)
 	if err != nil {
-		return Route{}, "", fmt.Errorf("read the answer: %w", err)
+		return Route{}, fmt.Errorf("read the answer: %w", err)
 	}
 
 	if len(decoded.Data.Results) == 0 {
-		return Route{}, "", errNoResult
+		return Route{}, errNoResult
 	}
 
 	result := decoded.Data.Results[0]
 	if result.Netblock == "" {
-		return Route{}, NoRoute, nil
+		return Route{}, nil
 	}
 
 	netblock, err := netip.ParsePrefix(result.Netblock)
 	if err != nil {
-		return Route{}, "", fmt.Errorf("%w: %q", errNotNetblock, result.Netblock)
+		return Route{}, fmt.Errorf("%w: %q", errNotNetblock, result.Netblock)
 	}
 
-	return Route{Netblock: netblock.Masked(), ASN: result.ASN}, "", nil
+	return Route{Netblock: netblock.Masked(), ASN: result.ASN}, nil
 }

internal/routewatch/routewatch_test.go

@@ -7,6 +7,7 @@ import (
 	"net/http"
 	"net/http/httptest"
 	"net/netip"
+	"slices"
 	"strings"
 	"sync"
 	"sync/atomic"
@@ -336,3 +337,96 @@ func TestRepeatedRequestsMakeOneQueryAndTheAnswerExpires(t *testing.T) {
 		t.Errorf("%d queries after the answer expired, want 2", got)
 	}
 }
+
+func TestSnapshotHoldsTheAnswerUntilItExpires(t *testing.T) {
+	t.Parallel()
+
+	f := newFixture(t, answering(routedAnswer))
+
+	f.route()
+	f.waitFor("")
+
+	want := []routewatch.Answer{{
+		Client:   netip.MustParsePrefix(clientAddr + "/32"),
+		Netblock: netip.MustParsePrefix("192.0.2.0/24"), ASN: 64496,
+		Answered: f.clk.Now(),
+	}}
+	if got := f.client.Snapshot(); !slices.Equal(got, want) {
+		t.Errorf("snapshot %+v, want %+v", got, want)
+	}
+
+	f.clk.advance(time.Hour)
+
+	if got := f.client.Snapshot(); len(got) != 0 {
+		t.Errorf("snapshot %+v an hour after the answer, want none", got)
+	}
+}
+
+func TestLoadedAnswersAreUsedForAnHourFromWhenTheyCame(t *testing.T) {
+	t.Parallel()
+
+	f := newFixture(t, answering(routedAnswer))
+	now := f.clk.Now()
+	kept := routewatch.Answer{
+		Client:   netip.MustParsePrefix(clientAddr + "/32"),
+		Netblock: netip.MustParsePrefix("198.51.100.0/24"), ASN: 64497,
+		Answered: now.Add(-time.Hour + time.Second),
+	}
+	stale := routewatch.Answer{
+		Client:   netip.MustParsePrefix("192.0.2.2/32"),
+		Netblock: netip.MustParsePrefix("192.0.2.0/24"), ASN: 64496,
+		Answered: now.Add(-time.Hour),
+	}
+
+	f.client.Load([]routewatch.Answer{kept, stale})
+
+	if got := f.client.Snapshot(); !slices.Equal(got, []routewatch.Answer{kept}) {
+		t.Errorf("kept %+v, want only the answer that came less than an hour ago", got)
+	}
+
+	route, missing := f.route()
+
+	want := routewatch.Route{Netblock: kept.Netblock, ASN: kept.ASN}
+	if route != want || missing != "" {
+		t.Errorf("route %+v (%q), want %+v", route, missing, want)
+	}
+
+	if got := f.queries.Load(); got != 0 {
+		t.Errorf("%d queries for a client with an answer loaded, want none", got)
+	}
+}
+
+func TestLoadDropsTheAnswerThatCameLongestAgoFirst(t *testing.T) {
+	t.Parallel()
+
+	const maxAnswers = 100000
+
+	f := newFixture(t, answering(routedAnswer))
+	now := f.clk.Now()
+
+	// routewatch.json lists the answers by client. Here each came a
+	// millisecond before the one listed before it, so the last listed is
+	// the one that came longest ago, and the one dropped.
+	answers := make([]routewatch.Answer, maxAnswers+1)
+	addr := netip.MustParseAddr("10.0.0.0")
+
+	for i := range answers {
+		answers[i] = routewatch.Answer{
+			Client:   netip.PrefixFrom(addr, addr.BitLen()),
+			Answered: now.Add(-time.Duration(i) * time.Millisecond),
+		}
+		addr = addr.Next()
+	}
+
+	f.client.Load(answers)
+
+	got := f.client.Snapshot()
+	if len(got) != maxAnswers {
+		t.Fatalf("%d answers kept, want %d", len(got), maxAnswers)
+	}
+
+	if got[0] != answers[0] || got[maxAnswers-1] != answers[maxAnswers-1] {
+		t.Errorf("answers kept from %s to %s, want from %s to %s", got[0].Client,
+			got[maxAnswers-1].Client, answers[0].Client, answers[maxAnswers-1].Client)
+	}
+}

internal/state/state.go

@@ -1,13 +1,23 @@
-// Package state keeps sww's state in JSON files in
-// SWW_STATE_DIR, as the "Persistent state" section of SPEC.md requires
-// and docs/state-files.md lists them:
-// bans.json holds the bans, clients.json each client's counters and
-// history, lookups.json GeoJS's answers, reputation.json the last try and
-// last good copy of each list fetched from a URL, the DNSBL zones'
-// verdicts, and AbuseIPDB's scores and checks spent, and alerts.json the
-// cooldowns, the hour under way, the alerts waiting for each destination
-// and the anomaly counters. Load
-// reads them at start, Watch takes in an admin's edit of one while
+// Package state keeps sww's state in JSON files, as the "Persistent
+// state" section of SPEC.md requires and docs/state-files.md lists them.
+//
+// The state files are in SWW_STATE_DIR:
+//   - bans.json holds the bans;
+//   - clients.json holds each client's counters and history;
+//   - abuseipdb-checks-spent.json holds the AbuseIPDB checks spent today;
+//   - alerts.json holds the cooldowns, the hour under way, the alerts
+//     waiting for each destination and the anomaly counters.
+//
+// The cache files are in SWW_CACHE_DIR. Each keeps answers from an
+// outside service, which are fetched again when the file is lost:
+//   - lookups.json holds GeoJS's answers;
+//   - lists.json holds the last try and last good copy of each list
+//     fetched from a URL;
+//   - dnsbl.json holds the DNSBL zones' verdicts;
+//   - abuseipdb-scores.json holds AbuseIPDB's scores;
+//   - routewatch.json holds routewatch's answers.
+//
+// Load reads them at start, Watch takes in an admin's edit of one while
 // sww runs, and Run and WriteAll write them. The disk is read and
 // written outside the parts' locks, which are held only to take a
 // snapshot or to put in what a file holds, so that no request waits on
@@ -31,6 +41,7 @@ import (
 	"sync"
 	"time"
 
+	"cloud.google.com/go/civil"
 	"github.com/fsnotify/fsnotify"
 	"sneak.berlin/go/smallwebwaf/internal/alerts"
 	"sneak.berlin/go/smallwebwaf/internal/anomaly"
@@ -39,6 +50,7 @@ import (
 	"sneak.berlin/go/smallwebwaf/internal/metrics"
 	"sneak.berlin/go/smallwebwaf/internal/ratelimit"
 	"sneak.berlin/go/smallwebwaf/internal/reputation"
+	"sneak.berlin/go/smallwebwaf/internal/routewatch"
 )
 
 // version is the version of the files' format, the only one read.
@@ -48,15 +60,42 @@ const version = 1
 // hold visitors' addresses.
 const fileMode = 0o600
 
-// The state files' names.
+// The state files' names, in Dir.
 const (
-	bansJSON       = "bans.json"
-	clientsJSON    = "clients.json"
-	lookupsJSON    = "lookups.json"
-	reputationJSON = "reputation.json"
-	alertsJSON     = "alerts.json"
+	bansJSON                 = "bans.json"
+	clientsJSON              = "clients.json"
+	abuseIPDBChecksSpentJSON = "abuseipdb-checks-spent.json"
+	alertsJSON               = "alerts.json"
 )
 
+// The cache files' names, in CacheDir.
+const (
+	lookupsJSON         = "lookups.json"
+	listsJSON           = "lists.json"
+	dnsblJSON           = "dnsbl.json"
+	abuseIPDBScoresJSON = "abuseipdb-scores.json"
+	routeWatchJSON      = "routewatch.json"
+)
+
+// fileNames returns the names of the state files, then those of the
+// cache files, in the order they are written.
+func fileNames() []string {
+	return []string{
+		bansJSON, clientsJSON, abuseIPDBChecksSpentJSON, alertsJSON,
+		lookupsJSON, listsJSON, dnsblJSON, abuseIPDBScoresJSON, routeWatchJSON,
+	}
+}
+
+// isCacheFile reports whether name is the name of a cache file.
+func isCacheFile(name string) bool {
+	switch name {
+	case lookupsJSON, listsJSON, dnsblJSON, abuseIPDBScoresJSON, routeWatchJSON:
+		return true
+	default:
+		return false
+	}
+}
+
 var (
 	errVersion = errors.New("unknown version")
 	// errMissing is for an entry without a field it needs.
@@ -72,24 +111,29 @@ var (
 
 // Params are what Load needs.
 type Params struct {
-	// Dir is the directory of the state files (SWW_STATE_DIR).
-	Dir string
+	// Dir is the directory of the state files (SWW_STATE_DIR), and
+	// CacheDir that of the cache files (SWW_CACHE_DIR).
+	Dir      string
+	CacheDir string
 	// WriteDelay is how long after a ban is made bans.json is written
 	// (SWW_STATE_WRITE_DELAY), and CounterInterval how often every file
 	// is (SWW_STATE_COUNTER_INTERVAL).
 	WriteDelay      time.Duration
 	CounterInterval time.Duration
-	// Ledger, Limiter, GeoJS, Lists, DNSBL, AbuseIPDB, Alerts and Anomalies
-	// hold the state. Alerts also receive a file_error alert for an edit set
-	// aside, and for a write that fails while sww runs.
-	Ledger    *bans.Ledger
-	Limiter   *ratelimit.Limiter
-	GeoJS     *lookup.GeoJS
-	Lists     *reputation.Lists
-	DNSBL     *reputation.DNSBL
-	AbuseIPDB *reputation.AbuseIPDB
-	Alerts    *alerts.Queue
-	Anomalies *anomaly.Counters
+	// Ledger, Limiter, GeoJS, Lists, DNSBL, AbuseIPDB, RouteWatch, Alerts and
+	// Anomalies hold the state. RouteWatch is nil while SWW_ROUTEWATCH_URL is
+	// unset, and routewatch.json then holds no answers. Alerts also receive a
+	// file_error alert for an edit set aside, and for a write that fails while
+	// sww runs.
+	Ledger     *bans.Ledger
+	Limiter    *ratelimit.Limiter
+	GeoJS      *lookup.GeoJS
+	Lists      *reputation.Lists
+	DNSBL      *reputation.DNSBL
+	AbuseIPDB  *reputation.AbuseIPDB
+	RouteWatch *routewatch.Client
+	Alerts     *alerts.Queue
+	Anomalies  *anomaly.Counters
 	// Now tells the time by which the counters' buckets run out, normally
 	// time.Now in UTC.
 	Now func() time.Time
@@ -101,7 +145,7 @@ type Params struct {
 	Metrics *metrics.Metrics
 }
 
-// Files are the state files of a running sww.
+// Files are the state and cache files of a running sww.
 type Files struct {
 	params Params
 
@@ -147,13 +191,38 @@ type lookupsFile struct {
 	Lookups []lookup.Answer `json:"lookups"`
 }
 
-// reputationFile is reputation.json, indented for an admin to read and
-// edit, so that each line of a list's copy is on a line of its own.
-type reputationFile struct {
-	Version   int                  `json:"version"`
-	Lists     []reputation.List    `json:"lists"`
-	Verdicts  []reputation.Verdict `json:"verdicts"`
-	AbuseIPDB reputation.Checks    `json:"abuseipdb"`
+// abuseIPDBChecksSpentFile is abuseipdb-checks-spent.json, indented for an
+// admin to read and edit.
+type abuseIPDBChecksSpentFile struct {
+	Version int        `json:"version"`
+	Day     civil.Date `json:"day,omitzero"`
+	Spent   int        `json:"spent"`
+}
+
+// listsFile is lists.json, indented for an admin to read and edit, so
+// that each line of a list's copy is on a line of its own.
+type listsFile struct {
+	Version int               `json:"version"`
+	Lists   []reputation.List `json:"lists"`
+}
+
+// dnsblFile is dnsbl.json, with each verdict on a line of its own.
+type dnsblFile struct {
+	Version  int                  `json:"version"`
+	Verdicts []reputation.Verdict `json:"verdicts"`
+}
+
+// abuseIPDBScoresFile is abuseipdb-scores.json, with each score on a line
+// of its own.
+type abuseIPDBScoresFile struct {
+	Version int                `json:"version"`
+	Scores  []reputation.Score `json:"scores"`
+}
+
+// routeWatchFile is routewatch.json, with each answer on a line of its own.
+type routeWatchFile struct {
+	Version int                 `json:"version"`
+	Answers []routewatch.Answer `json:"answers"`
 }
 
 // alertsFile is alerts.json, indented for an admin to read and edit.
@@ -178,34 +247,45 @@ type stateFile interface {
 	toUTC()
 }
 
-// Load checks that files can be written in Dir, and reads the state files
-// in it into the parts of Params that hold the state. A missing file is
-// empty state, as on a first start. A file that does not parse, has an
-// unknown version, or has an entry without a field it needs, is an error
-// that names the file and, where the JSON decoder tells it, the line and
-// column, or else the entry.
+// Load checks that files can be written in Dir and CacheDir, and reads the
+// files in them into the parts of Params that hold the state. A missing
+// file is empty state, as on a first start. A state file that does not
+// parse, has an unknown version, or has an entry without a field it
+// needs, is an error that names the file and, where the JSON decoder
+// tells it, the line and column, or else the entry. A cache file is never
+// an error, as readCache describes.
 func Load(params Params) (*Files, error) {
 	err := checkWritable(params.Dir)
 	if err != nil {
 		return nil, fmt.Errorf("SWW_STATE_DIR cannot be written: %w", err)
 	}
 
+	err = checkWritable(params.CacheDir)
+	if err != nil {
+		return nil, fmt.Errorf("SWW_CACHE_DIR cannot be written: %w", err)
+	}
+
 	f := &Files{params: params, sums: map[string][sha256.Size]byte{}}
 
 	bansRead, bansErr := f.read(bansJSON)
 	clientsRead, clientsErr := f.read(clientsJSON)
-	lookupsRead, lookupsErr := f.read(lookupsJSON)
-	reputationRead, reputationErr := f.read(reputationJSON)
+	_, checksErr := f.read(abuseIPDBChecksSpentJSON)
 	alertsRead, alertsErr := f.read(alertsJSON)
 
-	err = errors.Join(bansErr, clientsErr, lookupsErr, reputationErr, alertsErr)
+	err = errors.Join(bansErr, clientsErr, checksErr, alertsErr)
 	if err != nil {
 		return nil, err
 	}
 
+	lookupsRead := f.readCache(lookupsJSON)
+	listsRead := f.readCache(listsJSON)
+	f.readCache(dnsblJSON)
+	f.readCache(abuseIPDBScoresJSON)
+	f.readCache(routeWatchJSON)
+
 	params.ProcessLog.Info("read the state files", "directory", params.Dir,
-		"bans", bansRead, "clients", clientsRead, "lookups", lookupsRead,
-		"lists", reputationRead, "alerts_waiting", alertsRead)
+		"cache_directory", params.CacheDir, "bans", bansRead, "clients", clientsRead,
+		"lookups", lookupsRead, "lists", listsRead, "alerts_waiting", alertsRead)
 
 	return f, nil
 }
@@ -234,38 +314,35 @@ func (f *Files) Run(ctx context.Context) {
 
 			f.logFailure(bansJSON, f.writeFile(bansJSON))
 		case <-interval.C:
-			for _, name := range []string{
-				bansJSON, clientsJSON, lookupsJSON, reputationJSON, alertsJSON,
-			} {
+			for _, name := range fileNames() {
 				f.logFailure(name, f.writeFile(name))
 			}
 		}
 	}
 }
 
-// WriteAll writes every state file, as sww stops. A file that
+// WriteAll writes every state and cache file, as sww stops. A file that
 // fails does not keep the others from being written.
 func (f *Files) WriteAll() error {
-	return errors.Join(f.writeFile(bansJSON), f.writeFile(clientsJSON),
-		f.writeFile(lookupsJSON), f.writeFile(reputationJSON), f.writeFile(alertsJSON))
-}
+	names := fileNames()
+	errs := make([]error, 0, len(names))
 
-// Watch watches Dir until ctx is done, and takes in an admin's edit of a
-// state file as soon as it is saved: what the file holds replaces what
-// sww held for it. An edit that does not parse is left for the
-// file's next write, which sets it aside, since a file can be read while
-// an editor is still writing it. If Dir cannot be watched, that is
-// logged, and an edit is taken in only before its file is written.
-func (f *Files) Watch(ctx context.Context) {
-	watcher, err := fsnotify.NewWatcher()
-	if err == nil {
-		defer func() {
-			_ = watcher.Close()
-		}()
-
-		err = watcher.Add(f.params.Dir)
+	for _, name := range names {
+		errs = append(errs, f.writeFile(name))
 	}
 
+	return errors.Join(errs...)
+}
+
+// Watch watches Dir and CacheDir until ctx is done, and takes in an
+// admin's edit of a file as soon as it is saved: what the file holds
+// replaces what sww held for it. An edit that does not parse is left for
+// the file's next write, which sets it aside, since a file can be read
+// while an editor is still writing it. A directory that cannot be watched
+// is logged, and the other is still watched. An edit in a directory not
+// watched is taken in only before its file is written.
+func (f *Files) Watch(ctx context.Context) {
+	watcher, err := fsnotify.NewWatcher()
 	if err != nil {
 		f.params.ProcessLog.Error("cannot watch the state files for edits",
 			"error", err.Error())
@@ -273,16 +350,42 @@ func (f *Files) Watch(ctx context.Context) {
 		return
 	}
 
+	defer func() {
+		_ = watcher.Close()
+	}()
+
+	var watched []string
+
+	for _, dir := range []struct{ path, failed string }{
+		{f.params.Dir, "cannot watch the state files for edits"},
+		{f.params.CacheDir, "cannot watch the cache files for edits"},
+	} {
+		err = watcher.Add(dir.path)
+		if err != nil {
+			f.params.ProcessLog.Error(dir.failed, "directory", dir.path,
+				"error", err.Error())
+
+			continue
+		}
+
+		watched = append(watched, dir.path)
+	}
+
+	if len(watched) == 0 {
+		return
+	}
+
 	f.params.ProcessLog.Info("watching the state files for edits",
-		"directory", f.params.Dir)
+		"directories", watched)
 
 	for {
 		select {
 		case <-ctx.Done():
 			return
 		case event := <-watcher.Events:
-			switch name := filepath.Base(event.Name); name {
-			case bansJSON, clientsJSON, lookupsJSON, reputationJSON, alertsJSON:
+			name := filepath.Base(event.Name)
+			if slices.Contains(fileNames(), name) &&
+				filepath.Join(f.dir(name), name) == event.Name {
 				f.fileChanged(name)
 			}
 		case err = <-watcher.Errors:
@@ -292,11 +395,14 @@ func (f *Files) Watch(ctx context.Context) {
 	}
 }
 
-// logFailure logs a write of the state file name that failed, and raises
+// logFailure logs a write of the file name that failed, and raises
 // a file_error alert for it.
 func (f *Files) logFailure(name string, err error) {
 	if err != nil {
-		const failed = "writing the state files failed"
+		failed := "writing the state files failed"
+		if isCacheFile(name) {
+			failed = "writing the cache files failed"
+		}
 
 		// Raised before it is logged, so that the alert is there once the
 		// log line is.
@@ -304,14 +410,14 @@ func (f *Files) logFailure(name string, err error) {
 			Event:  alerts.EventFileError,
 			Reason: failed,
 			Detail: map[string]any{
-				"file": filepath.Join(f.params.Dir, name), "error": err.Error(),
+				"file": filepath.Join(f.dir(name), name), "error": err.Error(),
 			},
 		})
 		f.params.ProcessLog.Error(failed, "error", err.Error())
 	}
 }
 
-// fileChanged takes in what the state file name holds, as Watch sees it
+// fileChanged takes in what the file name holds, as Watch sees it
 // change, if that is an edit made since sww last read or wrote
 // the file. A file that cannot be read or does not parse is left for its
 // next write.
@@ -327,7 +433,7 @@ func (f *Files) fileChanged(name string) {
 	_ = f.takeInEdit(name, data)
 }
 
-// takeInEdit takes in data, an edit of the state file name, as takeIn
+// takeInEdit takes in data, an edit of the file name, as takeIn
 // does, and counts and logs it. Every edit taken in while sww
 // runs, by Watch or by a write, is taken in here. An edit that does not
 // parse is neither counted nor logged, and takeIn's error returned.
@@ -341,13 +447,23 @@ func (f *Files) takeInEdit(name string, data []byte) error {
 	// log line is.
 	f.params.Metrics.StateFileEditTakenIn(name)
 	f.params.ProcessLog.Info("took in an edit of a state file",
-		"file", filepath.Join(f.params.Dir, name))
+		"file", filepath.Join(f.dir(name), name))
 
 	return nil
 }
 
-// read takes in the state file name at start, and returns how many
-// entries it holds. A missing file holds none.
+// dir returns the directory of the file name: CacheDir for a cache file,
+// and Dir for a state file.
+func (f *Files) dir(name string) string {
+	if isCacheFile(name) {
+		return f.params.CacheDir
+	}
+
+	return f.params.Dir
+}
+
+// read takes in the file name at start, and returns how many entries it
+// holds. A missing file holds none.
 func (f *Files) read(name string) (int, error) {
 	data, changed, err := f.readChanged(name)
 	if err != nil || !changed {
@@ -357,14 +473,44 @@ func (f *Files) read(name string) (int, error) {
 	return f.takeIn(name, data, false)
 }
 
-// readChanged returns what the state file name holds, and whether that
-// has changed since sww last read or wrote the file, as it has
-// for a file sww never read or wrote. A missing file has not
-// changed: it is written again at its next write.
-func (f *Files) readChanged(name string) ([]byte, bool, error) {
-	path := filepath.Join(f.params.Dir, name)
+// readCache takes in the cache file name at start, as read does. A cache
+// file that cannot be read, or does not parse, does not stop the start:
+// it is logged, and its cache starts empty and fills again. One that does
+// not parse is set aside as an edit is, and one that cannot be read is
+// written over at its next write.
+func (f *Files) readCache(name string) int {
+	data, changed, err := f.readChanged(name)
+	if err != nil || !changed {
+		f.logUnread(name, err)
 
-	data, err := os.ReadFile(path) //nolint:gosec // a state file, in SWW_STATE_DIR
+		return 0
+	}
+
+	entries, err := f.takeIn(name, data, false)
+	if err != nil {
+		f.logUnread(name, f.setAside(name, err))
+	}
+
+	return entries
+}
+
+// logUnread logs err, the reason the cache file name was not read at
+// start, unless it is nil.
+func (f *Files) logUnread(name string, err error) {
+	if err != nil {
+		f.params.ProcessLog.Warn("cannot read a cache file, so its cache starts empty",
+			"file", filepath.Join(f.dir(name), name), "error", err.Error())
+	}
+}
+
+// readChanged returns what the file name holds, and whether that has
+// changed since sww last read or wrote the file, as it has for a file
+// sww never read or wrote. A missing file has not changed: it is written
+// again at its next write.
+func (f *Files) readChanged(name string) ([]byte, bool, error) {
+	path := filepath.Join(f.dir(name), name)
+
+	data, err := os.ReadFile(path) //nolint:gosec // a file in one of the two directories
 	if errors.Is(err, fs.ErrNotExist) {
 		return nil, false, nil
 	}
@@ -376,15 +522,39 @@ func (f *Files) readChanged(name string) ([]byte, bool, error) {
 	return data, sha256.Sum256(data) != f.sums[name], nil
 }
 
-// takeIn parses data, what the state file name holds, puts it into the
+// takeIn parses data, what the file name holds, puts it into the
 // part that keeps that state, in place of what the part held, and returns
 // how many entries the file holds. edit is whether data is an admin's
 // edit taken in while sww runs, rather than the file read at the
 // start. An error names the file and, where the JSON decoder tells it,
-// the line and column, or else the entry.
+// the line and column, or else the entry. abuseipdb-checks-spent.json
+// holds no entries.
 func (f *Files) takeIn(name string, data []byte, edit bool) (int, error) {
-	path := filepath.Join(f.params.Dir, name)
+	path := filepath.Join(f.dir(name), name)
 
+	var (
+		entries int
+		err     error
+	)
+
+	if isCacheFile(name) {
+		entries, err = f.takeInCache(name, path, data)
+	} else {
+		entries, err = f.takeInState(name, path, data, edit)
+	}
+
+	if err != nil {
+		return 0, err
+	}
+
+	f.sums[name] = sha256.Sum256(data)
+
+	return entries, nil
+}
+
+// takeInState parses data, what the state file name, at path, holds, and
+// puts it in, as takeIn describes.
+func (f *Files) takeInState(name, path string, data []byte, edit bool) (int, error) {
 	var entries int
 
 	switch name {
@@ -418,6 +588,33 @@ func (f *Files) takeIn(name string, data []byte, edit bool) (int, error) {
 
 		f.params.Limiter.Load(file.Clients, f.params.Now())
 		entries = len(file.Clients)
+	case abuseIPDBChecksSpentJSON:
+		var file abuseIPDBChecksSpentFile
+
+		err := parse(path, data, &file)
+		if err != nil {
+			return 0, err
+		}
+
+		f.params.AbuseIPDB.LoadChecksSpent(reputation.ChecksSpent{
+			Day: file.Day, Spent: file.Spent,
+		})
+	case alertsJSON:
+		waiting, err := f.takeInAlerts(path, data)
+		if err != nil {
+			return 0, err
+		}
+
+		entries = waiting
+	}
+
+	return entries, nil
+}
+
+// takeInCache parses data, what the cache file name, at path, holds, and
+// puts it in, as takeIn describes.
+func (f *Files) takeInCache(name, path string, data []byte) (int, error) {
+	switch name {
 	case lookupsJSON:
 		var file lookupsFile
 
@@ -427,9 +624,10 @@ func (f *Files) takeIn(name string, data []byte, edit bool) (int, error) {
 		}
 
 		f.params.GeoJS.Load(file.Lookups)
-		entries = len(file.Lookups)
-	case reputationJSON:
-		var file reputationFile
+
+		return len(file.Lookups), nil
+	case listsJSON:
+		var file listsFile
 
 		err := parse(path, data, &file)
 		if err != nil {
@@ -441,21 +639,43 @@ func (f *Files) takeIn(name string, data []byte, edit bool) (int, error) {
 			return 0, fmt.Errorf("%s: %w", path, err)
 		}
 
-		f.params.DNSBL.Load(file.Verdicts)
-		f.params.AbuseIPDB.Load(file.AbuseIPDB)
-		entries = len(file.Lists)
-	case alertsJSON:
-		waiting, err := f.takeInAlerts(path, data)
+		return len(file.Lists), nil
+	case dnsblJSON:
+		var file dnsblFile
+
+		err := parse(path, data, &file)
 		if err != nil {
 			return 0, err
 		}
 
-		entries = waiting
+		f.params.DNSBL.Load(file.Verdicts)
+
+		return len(file.Verdicts), nil
+	case routeWatchJSON:
+		var file routeWatchFile
+
+		err := parse(path, data, &file)
+		if err != nil {
+			return 0, err
+		}
+
+		if f.params.RouteWatch != nil {
+			f.params.RouteWatch.Load(file.Answers)
+		}
+
+		return len(file.Answers), nil
+	default: // abuseipdb-scores.json
+		var file abuseIPDBScoresFile
+
+		err := parse(path, data, &file)
+		if err != nil {
+			return 0, err
+		}
+
+		f.params.AbuseIPDB.Load(file.Scores)
+
+		return len(file.Scores), nil
 	}
-
-	f.sums[name] = sha256.Sum256(data)
-
-	return entries, nil
 }
 
 // takeInAlerts parses data, what alerts.json, at path, holds, puts it
@@ -493,17 +713,22 @@ func (f *Files) takeInAlerts(path string, data []byte) (int, error) {
 	return entries, nil
 }
 
-// writeFile writes the state file name from what sww holds. An
-// edit made since sww last read or wrote the file is taken in
-// first, so that it is not overwritten, or set aside if it does not
-// parse. A file that cannot be read, or an edit that cannot be set
-// aside, is left as it is, and the write given up. Every write is counted
-// in the metrics, and one that fails or is given up as a failure.
+// writeFile writes the file name from what sww holds. An edit made since
+// sww last read or wrote the file is taken in first, so that it is not
+// overwritten, or set aside if it does not parse. A state file that
+// cannot be read, or an edit that cannot be set aside, is left as it is,
+// and the write given up. A cache file that cannot be read is written
+// over, since what it held is fetched again. Every write is counted in
+// the metrics, and one that fails or is given up as a failure.
 func (f *Files) writeFile(name string) error {
 	f.mu.Lock()
 	defer f.mu.Unlock()
 
 	data, changed, err := f.readChanged(name)
+	if err != nil && isCacheFile(name) {
+		err = nil
+	}
+
 	if err == nil && changed {
 		err = f.takeInEdit(name, data)
 		if err != nil {
@@ -519,7 +744,7 @@ func (f *Files) writeFile(name string) error {
 	}
 
 	if err == nil {
-		err = write(f.params.Dir, name, data)
+		err = write(f.dir(name), name, data)
 	}
 
 	if err == nil {
@@ -527,7 +752,7 @@ func (f *Files) writeFile(name string) error {
 		// fails, so that its next read does not take it for an admin's
 		// edit.
 		f.sums[name] = sha256.Sum256(data)
-		err = syncDirectory(f.params.Dir)
+		err = syncDirectory(f.dir(name))
 	}
 
 	f.params.Metrics.StateFileWritten(name, len(data), err)
@@ -535,20 +760,23 @@ func (f *Files) writeFile(name string) error {
 	return err
 }
 
-// setAside renames the state file name, an edit that does not parse with
+// setAside renames the file name, an edit that does not parse with
 // parseErr, to name.bad, for the admin to mend, and logs it with where in
 // the file the error is, and raises a file_error alert for it. If the
 // rename fails, the edit is left as it is, and the error returned is
 // parseErr joined with the rename's.
 func (f *Files) setAside(name string, parseErr error) error {
-	path := filepath.Join(f.params.Dir, name)
+	path := filepath.Join(f.dir(name), name)
 
 	err := os.Rename(path, path+".bad")
 	if err != nil {
 		return errors.Join(parseErr, err)
 	}
 
-	const setAside = "set aside an edit of a state file that does not parse"
+	setAside := "set aside an edit of a state file that does not parse"
+	if isCacheFile(name) {
+		setAside = "set aside an edit of a cache file that does not parse"
+	}
 
 	// Raised before it is logged, so that the alert is there once the log
 	// line is.
@@ -563,7 +791,7 @@ func (f *Files) setAside(name string, parseErr error) error {
 	return nil
 }
 
-// encode returns the state file name as sww writes it, from a
+// encode returns the file name as sww writes it, from a
 // snapshot of the part that keeps that state.
 func (f *Files) encode(name string) ([]byte, error) {
 	switch name {
@@ -575,10 +803,24 @@ func (f *Files) encode(name string) ([]byte, error) {
 		return encodeOnePerLine("clients", f.params.Limiter.Snapshot())
 	case lookupsJSON:
 		return encodeOnePerLine("lookups", f.params.GeoJS.Snapshot())
-	case reputationJSON:
-		return encodeIndented(reputationFile{
-			Version: version, Lists: f.params.Lists.Snapshot(),
-			Verdicts: f.params.DNSBL.Snapshot(), AbuseIPDB: f.params.AbuseIPDB.Snapshot(),
+	case listsJSON:
+		return encodeIndented(listsFile{Version: version, Lists: f.params.Lists.Snapshot()})
+	case dnsblJSON:
+		return encodeOnePerLine("verdicts", f.params.DNSBL.Snapshot())
+	case abuseIPDBScoresJSON:
+		return encodeOnePerLine("scores", f.params.AbuseIPDB.Snapshot())
+	case routeWatchJSON:
+		var answers []routewatch.Answer
+		if f.params.RouteWatch != nil {
+			answers = f.params.RouteWatch.Snapshot()
+		}
+
+		return encodeOnePerLine("answers", answers)
+	case abuseIPDBChecksSpentJSON:
+		checks := f.params.AbuseIPDB.ChecksSpent()
+
+		return encodeIndented(abuseIPDBChecksSpentFile{
+			Version: version, Day: checks.Day, Spent: checks.Spent,
 		})
 	default: // alerts.json
 		held := f.params.Alerts.Snapshot()
@@ -748,14 +990,8 @@ func (f *lookupsFile) check(data []byte) error {
 // check refuses a list without its URL, which would name no list, or the
 // time it was last tried, which would have it fetched at once, and a copy
 // of it without the time it was fetched, or without its lines, which hold
-// the list. It refuses a verdict without its zone or its client, which
-// would be about no one, whether the zone lists the client, or the time
-// it was fetched, which would drop it, and so an AbuseIPDB score without
-// its client, the score, or the time it was fetched. A verdict's listed is
-// false for a client the zone does not list, and a score can be 0, which
-// the structs cannot tell from a missing one, so each is read again as
-// written.
-func (f *reputationFile) check(data []byte) error {
+// the list.
+func (f *listsFile) check([]byte) error {
 	for i, kept := range f.Lists {
 		switch {
 		case kept.URL == "":
@@ -769,6 +1005,15 @@ func (f *reputationFile) check(data []byte) error {
 		}
 	}
 
+	return nil
+}
+
+// check refuses a verdict without its zone or its client, which would be
+// about no one, whether the zone lists the client, or the time it was
+// fetched, which would drop it. A verdict's listed is false for a client
+// the zone does not list, which Verdict cannot tell from a missing one,
+// so each listed is read again as written.
+func (f *dnsblFile) check(data []byte) error {
 	var written struct {
 		Verdicts []struct {
 			Listed *bool `json:"listed"`
@@ -783,28 +1028,27 @@ func (f *reputationFile) check(data []byte) error {
 	for i, verdict := range f.Verdicts {
 		switch {
 		case verdict.Zone == "":
-			return fmt.Errorf("verdicts %w", missing(i, "zone"))
+			return missing(i, "zone")
 		case !verdict.Client.IsValid():
-			return fmt.Errorf("verdicts %w", missing(i, "client"))
+			return missing(i, "client")
 		case written.Verdicts[i].Listed == nil:
-			return fmt.Errorf("verdicts %w", missing(i, "listed"))
+			return missing(i, "listed")
 		case verdict.Fetched.IsZero():
-			return fmt.Errorf("verdicts %w", missing(i, "fetched"))
+			return missing(i, "fetched")
 		}
 	}
 
-	return checkScores(f.AbuseIPDB.Scores, data)
+	return nil
 }
 
-// checkScores refuses an AbuseIPDB score, of scores, read from data, as
-// reputationFile's check describes.
-func checkScores(scores []reputation.Score, data []byte) error {
+// check refuses an AbuseIPDB score without its client, the score, or the
+// time it was fetched. A score can be 0, which Score cannot tell from a
+// missing one, so each score is read again as written.
+func (f *abuseIPDBScoresFile) check(data []byte) error {
 	var written struct {
-		AbuseIPDB struct {
-			Scores []struct {
-				Score *int64 `json:"score"`
-			} `json:"scores"`
-		} `json:"abuseipdb"`
+		Scores []struct {
+			Score *int64 `json:"score"`
+		} `json:"scores"`
 	}
 
 	err := json.Unmarshal(data, &written)
@@ -812,20 +1056,57 @@ func checkScores(scores []reputation.Score, data []byte) error {
 		return err
 	}
 
-	for i, kept := range scores {
+	for i, kept := range f.Scores {
 		switch {
 		case !kept.Client.IsValid():
-			return fmt.Errorf("abuseipdb scores %w", missing(i, "client"))
-		case written.AbuseIPDB.Scores[i].Score == nil:
-			return fmt.Errorf("abuseipdb scores %w", missing(i, "score"))
+			return missing(i, "client")
+		case written.Scores[i].Score == nil:
+			return missing(i, "score")
 		case kept.Fetched.IsZero():
-			return fmt.Errorf("abuseipdb scores %w", missing(i, "fetched"))
+			return missing(i, "fetched")
 		}
 	}
 
 	return nil
 }
 
+// check refuses an answer without its client, which would answer for
+// nobody, its netblock, or the time routewatch gave it, which would drop
+// it. "" is the netblock of an address without a live route, which Answer
+// cannot tell from a missing one, so each netblock is read again as
+// written.
+func (f *routeWatchFile) check(data []byte) error {
+	var written struct {
+		Answers []struct {
+			Netblock *string `json:"netblock"`
+		} `json:"answers"`
+	}
+
+	err := json.Unmarshal(data, &written)
+	if err != nil {
+		return err
+	}
+
+	for i, answer := range f.Answers {
+		switch {
+		case !answer.Client.IsValid():
+			return missing(i, "client")
+		case written.Answers[i].Netblock == nil:
+			return missing(i, "netblock")
+		case answer.Answered.IsZero():
+			return missing(i, "answered")
+		}
+	}
+
+	return nil
+}
+
+// check refuses nothing, since a missing day or count means no check
+// spent.
+func (f *abuseIPDBChecksSpentFile) check([]byte) error {
+	return nil
+}
+
 // check refuses a cooldown without its event or when its alert was sent,
 // which would hold back no repeat, alerts waiting for a destination with
 // another name than webhook, slack or ntfy, most likely misspelt, an
@@ -947,22 +1228,37 @@ func (f *lookupsFile) toUTC() {
 	}
 }
 
-// toUTC converts every time of each list, verdict and AbuseIPDB score to
-// UTC.
-func (f *reputationFile) toUTC() {
+// toUTC converts both times of each list to UTC.
+func (f *listsFile) toUTC() {
 	for i := range f.Lists {
 		convertToUTC(&f.Lists[i].Tried, &f.Lists[i].Fetched)
 	}
+}
 
+// toUTC converts the time of each verdict to UTC.
+func (f *dnsblFile) toUTC() {
 	for i := range f.Verdicts {
 		convertToUTC(&f.Verdicts[i].Fetched)
 	}
+}
 
-	for i := range f.AbuseIPDB.Scores {
-		convertToUTC(&f.AbuseIPDB.Scores[i].Fetched)
+// toUTC converts the time of each AbuseIPDB score to UTC.
+func (f *abuseIPDBScoresFile) toUTC() {
+	for i := range f.Scores {
+		convertToUTC(&f.Scores[i].Fetched)
 	}
 }
 
+// toUTC converts the time of each answer to UTC.
+func (f *routeWatchFile) toUTC() {
+	for i := range f.Answers {
+		convertToUTC(&f.Answers[i].Answered)
+	}
+}
+
+// toUTC does nothing: abuseipdb-checks-spent.json holds a day, not a time.
+func (f *abuseIPDBChecksSpentFile) toUTC() {}
+
 // toUTC converts every time of each cooldown, of the hour, of each alert
 // waiting and of each anomaly counter to UTC.
 func (f *alertsFile) toUTC() {
@@ -1114,7 +1410,7 @@ func write(dir, name string, data []byte) error {
 
 // syncDirectory syncs dir to the disk, so that a rename in it lasts.
 func syncDirectory(dir string) error {
-	directory, err := os.Open(dir) //nolint:gosec // SWW_STATE_DIR itself
+	directory, err := os.Open(dir) //nolint:gosec // SWW_STATE_DIR or SWW_CACHE_DIR itself
 	if err != nil {
 		return err
 	}
@@ -1124,7 +1420,7 @@ func syncDirectory(dir string) error {
 
 // writeSynced writes data to the file at path, and syncs it to the disk.
 func writeSynced(path string, data []byte) error {
-	//nolint:gosec // a state file's temporary file, in SWW_STATE_DIR
+	//nolint:gosec // a file's temporary file, in SWW_STATE_DIR or SWW_CACHE_DIR
 	file, err := os.OpenFile(path, os.O_WRONLY|os.O_CREATE|os.O_TRUNC, fileMode)
 	if err != nil {
 		return err

internal/sww/sww.go

@@ -244,6 +244,7 @@ func loadStateFiles(
 ) (*state.Files, error) {
 	return state.Load(state.Params{
 		Dir:             cfg.StateDir,
+		CacheDir:        cfg.CacheDir,
 		WriteDelay:      cfg.StateWriteDelay,
 		CounterInterval: cfg.StateCounterInterval,
 		Ledger:          server.Ledger,
@@ -252,6 +253,7 @@ func loadStateFiles(
 		Lists:           server.Lists,
 		DNSBL:           server.DNSBL,
 		AbuseIPDB:       server.AbuseIPDB,
+		RouteWatch:      server.RouteWatch,
 		Alerts:          alertQueue,
 		Anomalies:       server.Anomalies,
 		Now:             now,

internal/sww/sww_test.go

@@ -38,6 +38,7 @@ const (
 	stateDir             = "SWW_STATE_DIR"
 	stateWriteDelay      = "SWW_STATE_WRITE_DELAY"
 	stateCounterInterval = "SWW_STATE_COUNTER_INTERVAL"
+	cacheDir             = "SWW_CACHE_DIR"
 	rateLimitPerDay      = "SWW_RATE_LIMIT_PER_DAY"
 	rateLimitExemptNets  = "SWW_RATE_LIMIT_EXEMPT_NETS"
 	rulesDir             = "SWW_RULES_DIR"
@@ -160,6 +161,12 @@ func run(ctx context.Context, env map[string]string, out *output) int {
 				return "off", true
 			}
 
+			// The cache files go beside the state files unless the test
+			// says otherwise.
+			if !ok && name == cacheDir {
+				return env[stateDir], env[stateDir] != ""
+			}
+
 			return value, ok
 		},
 		Stdout: out,
@@ -699,7 +706,7 @@ func TestLookupDatabaseReplacedWhileRunningTakesEffect(t *testing.T) {
 	}
 }
 
-func TestBlocklistTriesAndCopiesKeptInReputationJSONAcrossRestarts(t *testing.T) {
+func TestBlocklistTriesAndCopiesKeptInListsJSONAcrossRestarts(t *testing.T) {
 	t.Parallel()
 
 	const (
@@ -732,10 +739,11 @@ func TestBlocklistTriesAndCopiesKeptInReputationJSONAcrossRestarts(t *testing.T)
 	t.Cleanup(server.Close)
 
 	torURL, dropURL := server.URL+torPath, server.URL+dropPath
-	dir := t.TempDir()
+	cache := t.TempDir()
 	env := map[string]string{
 		listenAddr:           localhost + ":0",
-		stateDir:             dir,
+		stateDir:             t.TempDir(),
+		cacheDir:             cache,
 		rulesDir:             t.TempDir(),
 		metricsToken:         token,
 		instanceName:         instance,
@@ -755,7 +763,7 @@ func TestBlocklistTriesAndCopiesKeptInReputationJSONAcrossRestarts(t *testing.T)
 	})
 
 	// Restarted with drop.txt named after it and the server answering, tor.txt
-	// waits SWW_BLOCKLIST_REFRESH after its failed try, kept in reputation.json,
+	// waits SWW_BLOCKLIST_REFRESH after its failed try, kept in lists.json,
 	// while drop.txt, never tried, is fetched at once. Lists are fetched in the
 	// order named, so once drop.txt refuses the client, tor.txt has had its turn.
 	failing.Store(false)
@@ -773,8 +781,8 @@ func TestBlocklistTriesAndCopiesKeptInReputationJSONAcrossRestarts(t *testing.T)
 	}
 
 	// After another restart, with the server failing, the copy of drop.txt
-	// kept in reputation.json, its copyright line included, refuses the
-	// client from the first request.
+	// kept in lists.json, its copyright line included, refuses the client
+	// from the first request.
 	failing.Store(true)
 
 	out = runUntilStopped(t, env, func(url string) {
@@ -782,16 +790,16 @@ func TestBlocklistTriesAndCopiesKeptInReputationJSONAcrossRestarts(t *testing.T)
 	})
 	wantDeniedByList(t, out.line(t, "type", "request"), dropURL)
 
-	path := filepath.Join(dir, "reputation.json")
+	path := filepath.Join(cache, "lists.json")
 
 	kept, err := os.ReadFile(path) //nolint:gosec // a file in the test's directory
 	if err != nil || !strings.Contains(string(kept), `"`+copyright+`"`) {
-		t.Errorf("reputation.json holds\n%s\nwant the copy with %q (%v)", kept, copyright,
+		t.Errorf("lists.json holds\n%s\nwant the copy with %q (%v)", kept, copyright,
 			err)
 	}
 }
 
-func TestCrowdSecDecisionListKeptInReputationJSONAcrossARestart(t *testing.T) {
+func TestCrowdSecDecisionListKeptInListsJSONAcrossARestart(t *testing.T) {
 	t.Parallel()
 
 	const bouncerKey = "crowdsec-key-0123456789abcdef"
@@ -814,10 +822,11 @@ func TestCrowdSecDecisionListKeptInReputationJSONAcrossARestart(t *testing.T) {
 		}))
 	t.Cleanup(engine.Close)
 
-	dir := t.TempDir()
+	dir, cache := t.TempDir(), t.TempDir()
 	env := map[string]string{
 		listenAddr:              localhost + ":0",
 		stateDir:                dir,
+		cacheDir:                cache,
 		rulesDir:                t.TempDir(),
 		"SWW_CROWDSEC_LAPI_URL": engine.URL,
 		"SWW_CROWDSEC_LAPI_KEY": bouncerKey,
@@ -836,7 +845,7 @@ func TestCrowdSecDecisionListKeptInReputationJSONAcrossARestart(t *testing.T) {
 		t.Errorf("bans.json holds %v, want the ban for crowdsec on %s", ban, placed)
 	}
 
-	// Restarted with the engine down, the copy kept in reputation.json bans
+	// Restarted with the engine down, the copy kept in lists.json bans
 	// another client in the netblock from its first request.
 	down.Store(true)
 
@@ -844,22 +853,25 @@ func TestCrowdSecDecisionListKeptInReputationJSONAcrossARestart(t *testing.T) {
 		wantStatus(t, url, "203.0.113.10", http.StatusForbidden)
 	})
 
-	// The key is in neither run's output, nor in a state file.
-	files := []string{"bans.json", "reputation.json", "clients.json"}
+	// The key is in neither run's output, nor in a state or cache file.
+	files := []string{
+		filepath.Join(dir, "bans.json"), filepath.Join(dir, "clients.json"),
+		filepath.Join(cache, "lists.json"),
+	}
 	shown := make([]string, 0, len(files)+2)
 	shown = append(shown, first.text(), second.text())
 
-	for _, name := range files {
-		data, err := os.ReadFile(filepath.Join(dir, name)) //nolint:gosec // the test's
+	for _, path := range files {
+		data, err := os.ReadFile(path) //nolint:gosec // the test's
 		if err != nil {
-			t.Fatalf("read %s: %v", name, err)
+			t.Fatalf("read %s: %v", path, err)
 		}
 
 		shown = append(shown, string(data))
 	}
 
 	if all := strings.Join(shown, "\n"); strings.Contains(all, bouncerKey) {
-		t.Errorf("the key is shown in the output or the state files:\n%s", all)
+		t.Errorf("the key is shown in the output or the state and cache files:\n%s", all)
 	}
 }
 
@@ -1207,6 +1219,29 @@ func TestUnwritableStateDirStopsTheStart(t *testing.T) {
 		"SWW_STATE_DIR cannot be written: ")
 }
 
+func TestUnwritableCacheDirStopsTheStart(t *testing.T) {
+	t.Parallel()
+
+	ctx, stop := context.WithTimeout(t.Context(), waitLimit)
+	defer stop()
+
+	out := &output{}
+
+	status := run(ctx, map[string]string{
+		listenAddr: localhost + ":0", stateDir: t.TempDir(), rulesDir: t.TempDir(),
+		cacheDir: filepath.Join(t.TempDir(), "missing"),
+	}, out)
+	if status != 1 {
+		t.Fatalf("exit status %d, want 1", status)
+	}
+
+	line := out.line(t, "msg", "cannot use the state files")
+	if message, _ := line["error"].(string); !strings.HasPrefix(message,
+		"SWW_CACHE_DIR cannot be written: ") {
+		t.Errorf("start refused with %q, want SWW_CACHE_DIR named", message)
+	}
+}
+
 // wantStartRefused runs sww with its state files in dir, and
 // checks that it stops at start, with an error that starts with want. If
 // it starts instead, it is stopped after waitLimit.

internal/sww/waf_test.go

@@ -67,6 +67,7 @@ func TestMainRunsWAF(t *testing.T) {
 		commandForMain+"="+wafCommand,
 		listenAddr+"="+localhost+":0",
 		stateDir+"="+dir,
+		cacheDir+"="+dir,
 		rulesDir+"="+t.TempDir(),
 		lookupSource+"=off")
 

internal/waf/crowdsec_test.go

@@ -16,7 +16,7 @@ import (
 
 // The CrowdSec settings, and the tests' engine, which is never asked: each
 // test puts in the copy of its decision list, at decisionsURL, that it
-// needs, as reputation.json would at start.
+// needs, as lists.json would at start.
 const (
 	crowdSecURL  = "SWW_CROWDSEC_LAPI_URL"
 	crowdSecKey  = "SWW_CROWDSEC_LAPI_KEY"
@@ -182,7 +182,7 @@ func TestObserveModeForwardsAClientTheCrowdSecDecisionListListsAndAlertsTheBan(
 
 // loadDecisions puts into server's lists the copy of the decision list at
 // decisionsURL, answer, the engine's answer, fetched at fetched, as
-// reputation.json would at start.
+// lists.json would at start.
 func loadDecisions(
 	t *testing.T, server *waf.Server, fetched time.Time, answer string,
 ) {

internal/waf/proxy.go

@@ -86,8 +86,8 @@ type Params struct {
 // Server is the server waf runs, with the parts whose state the state
 // files keep, the lookup database, nil unless SWW_LOOKUP_SOURCE is file, the
 // lists fetched from URLs, which its Run fetches, the DNSBL zones' verdicts,
-// AbuseIPDB's scores and checks spent, and the metrics. RouteWatch, nil while
-// SWW_ROUTEWATCH_URL is unset, keeps its answers in memory only.
+// AbuseIPDB's scores and checks spent, routewatch's answers, and the metrics.
+// RouteWatch is nil while SWW_ROUTEWATCH_URL is unset.
 type Server struct {
 	*http.Server
 

internal/waf/reputation_test.go

@@ -39,7 +39,7 @@ const (
 )
 
 // The lists these tests name, which are never fetched: each test puts in
-// the copies it needs, as reputation.json would at start.
+// the copies it needs, as lists.json would at start.
 const (
 	dropURL = "https://lists.example/drop.txt"
 	torURL  = "https://lists.example/tor.txt"
@@ -374,7 +374,7 @@ const (
 
 // The DNSBL zones these tests name, which are never asked about the
 // clients the tests send requests from: each test puts in the verdicts it
-// needs, as reputation.json would at start. A query a test does start is
+// needs, as dnsbl.json would at start. A query a test does start is
 // sent to noResolver, where nothing listens, so that none leaves the host.
 const (
 	dnsblZone  = "dnsbl.example"
@@ -759,7 +759,7 @@ func TestOnlyAClientThatHasCommittedAnOffenceIsCheckedWithAbuseIPDB(t *testing.T
 	clk.advance(time.Hour)
 	wantReputation(t, s.get(fromDE, http.StatusOK, forward))
 	wantAbuseIPDBChecks(t, server, 1)
-	waitUntil(func() bool { return len(server.AbuseIPDB.Snapshot().Scores) == 1 })
+	waitUntil(func() bool { return len(server.AbuseIPDB.Snapshot()) == 1 })
 	wantReputation(t, s.get(fromDE, http.StatusOK, forward), abuseipdb)
 
 	s.get(fromKP, http.StatusOK, forward)
@@ -1072,7 +1072,7 @@ func verdictsFetched() time.Time {
 
 // loadVerdicts puts into server's DNSBL, for each client listedBy names,
 // a verdict of each zone SWW_DNSBL_ZONES names, fetched at
-// verdictsFetched, as reputation.json would at start: one that lists the
+// verdictsFetched, as dnsbl.json would at start: one that lists the
 // client from each zone listedBy gives for it, and one that does not from
 // each other zone.
 func loadVerdicts(server *waf.Server, listedBy map[string][]string) {
@@ -1091,8 +1091,8 @@ func loadVerdicts(server *waf.Server, listedBy map[string][]string) {
 }
 
 // loadScores puts into server's AbuseIPDB the score scores gives each
-// client, an IPv4 address, fetched at verdictsFetched, as reputation.json
-// would at start.
+// client, an IPv4 address, fetched at verdictsFetched, as
+// abuseipdb-scores.json would at start.
 func loadScores(server *waf.Server, scores map[string]int64) {
 	kept := make([]reputation.Score, 0, len(scores))
 	for client, score := range scores {
@@ -1102,7 +1102,7 @@ func loadScores(server *waf.Server, scores map[string]int64) {
 		})
 	}
 
-	server.AbuseIPDB.Load(reputation.Checks{Scores: kept})
+	server.AbuseIPDB.Load(kept)
 }
 
 // wantAbuseIPDBChecks checks how many clients server has checked with
@@ -1116,7 +1116,7 @@ func wantAbuseIPDBChecks(t *testing.T, server *waf.Server, want int) {
 }
 
 // loadLists puts copies of lists into server's lists, by URL, each with
-// its lines, fetched at listsFetched, as reputation.json would at start.
+// its lines, fetched at listsFetched, as lists.json would at start.
 func loadLists(t *testing.T, server *waf.Server, copies map[string][]string) {
 	t.Helper()