Ban notes name the reputation sources that listed the client (closes #109)

A ban's notes, in bans.json and in its alert, gain `reputation`: each
blocklist, DNSBL zone or AbuseIPDB that listed the client when the ban
was made, as its `source`, named and ordered as in the request log's
`reputation`, with AbuseIPDB's `score`. It is left out when none did.
README.md shows it in a bans.json example.

Notes now hold a list, so bans can no longer be compared with ==: the
tests compare them with reflect.DeepEqual.

Judgement call: the score is a pointer, so a score of 0, a hit while
SWWAF_ABUSEIPDB_MIN_SCORE is 0, is still written.

Model: opus-5-5

internal/alerts/alerts.go

@@ -44,11 +44,14 @@ const (
 	// EventAnomaly is a count of requests or bytes over an anomaly
 	// threshold.
 	EventAnomaly = "anomaly"
-	// EventWAFBlock and EventReputationHit come with the Core Rule Set and
+	// EventWAFBlock comes with the Core Rule Set; nothing raises it yet.
-	// the reputation sources; nothing raises them yet.
+	EventWAFBlock = "waf_block"
-	EventWAFBlock      = "waf_block"
+	// EventReputationHit is a request whose client a blocklist or a DNSBL
+	// zone lists, or whose AbuseIPDB score is a hit.
 	EventReputationHit = "reputation_hit"
-	// EventSourceFailure is GeoJS failing or refusing smallwebwaf.
+	// EventSourceFailure is GeoJS failing or refusing smallwebwaf, a fetch
+	// of a list failing, a query to a DNSBL zone or a check with AbuseIPDB
+	// failing or refused, or the day's AbuseIPDB checks used up.
 	EventSourceFailure = "source_failure"
 	// EventFileError is a rule file or state file edited while smallwebwaf
 	// runs that does not parse, a replacement of the lookup database that

internal/anomaly/anomaly.go

@@ -27,7 +27,8 @@ const maxCounters = 20000
 // The scopes, what a counter counts, as the settings, alerts.json and the
 // alerts name them.
 const (
-	// ScopeClient is one client: an IPv4 address, or an IPv6 /64.
+	// ScopeClient is one client: an IPv4 address, or an IPv6 netblock of
+	// SWWAF_IPV6_GROUP_PREFIX.
 	ScopeClient = "client"
 	// ScopeNet is the netblock around a client, SWWAF_ANOMALY_NET_V4_PREFIX
 	// or SWWAF_ANOMALY_NET_V6_PREFIX long.
@@ -103,7 +104,8 @@ type Counter struct {
 // Request is a request that has ended, as the counters count it.
 type Request struct {
 	// Client is the client's address, and ClientGroup the client it is
-	// counted as: its IPv4 address, or its IPv6 /64.
+	// counted as: its IPv4 address, or the IPv6 netblock of
+	// SWWAF_IPV6_GROUP_PREFIX its address is in.
 	Client      netip.Addr
 	ClientGroup netip.Prefix
 	// ASN, ASName and Country are the client's as looked up, each "" when

internal/bans/admin_test.go

@@ -2,6 +2,7 @@ package bans_test
 
 import (
 	"net/netip"
+	"reflect"
 	"testing"
 	"time"
 
@@ -117,7 +118,7 @@ func TestLiftedBanForALimitRefusesNothingAndMakesNoBanLonger(t *testing.T) {
 	}
 
 	held := ledger.Bans(netblock)
-	if len(held) != 2 || held[0] != lifted {
+	if len(held) != 2 || !reflect.DeepEqual(held[0], lifted) {
 		t.Errorf("the ledger holds %+v, want the lifted ban and the new one", held)
 	}
 }
@@ -212,7 +213,7 @@ func TestAdminsBanIsMadeWhileAnotherLasts(t *testing.T) {
 
 	got := ledger.BanForAdmin(netip.MustParsePrefix("203.0.113.9/24"), now, time.Time{},
 		"probes for logins")
-	if got != want {
+	if !reflect.DeepEqual(got, want) {
 		t.Errorf("the admin's ban is\n%+v\nwant\n%+v", got, want)
 	}
 
@@ -224,7 +225,7 @@ func TestAdminsBanIsMadeWhileAnotherLasts(t *testing.T) {
 
 	// It refuses once the ban for the limit has ended.
 	ban, banned, _ := ledger.Find(netblock.Addr(), midnight().Add(2*time.Hour))
-	if !banned || ban != want {
+	if !banned || !reflect.DeepEqual(ban, want) {
 		t.Errorf("after the limit's ban the netblock is under %+v (%t), want %+v",
 			ban, banned, want)
 	}

internal/bans/bans.go

@@ -118,6 +118,10 @@ type Notes struct {
 	// of the rule file rule that matched, and its target.
 	RuleID string `json:"rule_id,omitempty"`
 	Target string `json:"target,omitempty"`
+	// Reputation is the reputation sources that listed the client when
+	// the request that caused the ban was made, in the order the request
+	// log's reputation names them. It is left out when none did.
+	Reputation []ReputationHit `json:"reputation,omitempty"`
 	// Request is the request that broke the limit, or whose bytes broke
 	// it, or that was the clear sign of attack.
 	Request Request `json:"request"`
@@ -131,6 +135,15 @@ type Notes struct {
 	EarlierBans EarlierBans `json:"earlier_bans"`
 }
 
+// ReputationHit is a reputation source that listed a client, as a
+// reputation_hit alert's detail gives it: Source is the blocklist's URL,
+// the DNSBL zone with its key masked, or "abuseipdb", and Score, for
+// AbuseIPDB alone, its score of the client.
+type ReputationHit struct {
+	Source string `json:"source"`
+	Score  *int64 `json:"score,omitempty"`
+}
+
 // EarlierBans counts a netblock's bans before a ban, by cause.
 type EarlierBans struct {
 	Limit  int `json:"limit"`

internal/bans/bans_test.go

@@ -2,6 +2,7 @@ package bans_test
 
 import (
 	"net/netip"
+	"reflect"
 	"strings"
 	"testing"
 	"time"
@@ -130,13 +131,13 @@ func TestBrokenLimitDuringABanMakesNoOther(t *testing.T) {
 
 	again, made := ledger.BanForLimit(netblock, midnight().Add(time.Minute), bans.Notes{})
 
-	if made || again != first || len(ledger.Bans(netblock)) != 1 {
+	if made || !reflect.DeepEqual(again, first) || len(ledger.Bans(netblock)) != 1 {
 		t.Errorf("a limit broken during a ban gave %+v, made %t, and %d bans, "+
 			"want %+v, not made, and 1", again, made, len(ledger.Bans(netblock)), first)
 	}
 
 	again, made = ledger.BanForAttack(netblock, midnight().Add(time.Minute), bans.Notes{})
-	if made || again != first {
+	if made || !reflect.DeepEqual(again, first) {
 		t.Errorf("an attack during a ban gave %+v, made %t, want %+v, not made",
 			again, made, first)
 	}
@@ -182,7 +183,7 @@ func TestFindCountsNothing(t *testing.T) {
 	ban, _ := ledger.BanForLimit(netblock, midnight(), bans.Notes{Requests: 5})
 
 	got, banned, _ := ledger.Find(netblock.Addr(), ban.Expires.Add(-time.Nanosecond))
-	if !banned || got != ban {
+	if !banned || !reflect.DeepEqual(got, ban) {
 		t.Errorf("find during the ban gives %+v and %t, want %+v", got, banned, ban)
 	}
 
@@ -191,7 +192,7 @@ func TestFindCountsNothing(t *testing.T) {
 		t.Error("the ban did not end")
 	}
 
-	if notes := ledger.Bans(netblock)[0].Notes; notes != ban.Notes {
+	if notes := ledger.Bans(netblock)[0].Notes; !reflect.DeepEqual(notes, ban.Notes) {
 		t.Errorf("the notes are %+v, want them unchanged, %+v", notes, ban.Notes)
 	}
 }
@@ -247,7 +248,7 @@ func TestFullLedgerDropsTheEarlierBanOfTheNetblockBannedAgain(t *testing.T) {
 	second, _ := ledger.BanForLimit(netblock, first.Expires, bans.Notes{})
 
 	held := ledger.Bans(netblock)
-	if len(held) != 1 || held[0] != second ||
+	if len(held) != 1 || !reflect.DeepEqual(held[0], second) ||
 		held[0].Notes.EarlierBans != (bans.EarlierBans{Limit: 1}) {
 		t.Errorf("the ledger holds %+v, want only the second ban, "+
 			"with 1 earlier ban for a limit", held)
@@ -342,7 +343,7 @@ func TestWouldBanGivesTheBanWithoutMakingIt(t *testing.T) {
 
 	// While the first ban lasts, none would be made.
 	during, would := ledger.WouldBanForAttack(netblock, midnight(), bans.Notes{})
-	if would || during != first {
+	if would || !reflect.DeepEqual(during, first) {
 		t.Errorf("during the first ban, would ban %t with %+v, want false with %+v",
 			would, during, first)
 	}
@@ -371,7 +372,7 @@ func TestWouldBanGivesTheBanWithoutMakingIt(t *testing.T) {
 
 	// The ban made is the one that would have been.
 	made, _ := ledger.BanForLimit(netblock, first.Expires, limitNotes)
-	if made != limit {
+	if !reflect.DeepEqual(made, limit) {
 		t.Errorf("the ban made is %+v, want %+v", made, limit)
 	}
 }

internal/bans/snapshot_test.go

@@ -2,6 +2,7 @@ package bans_test
 
 import (
 	"net/netip"
+	"reflect"
 	"slices"
 	"strings"
 	"testing"
@@ -224,7 +225,7 @@ func TestLoadKeepsAtMostMaxBansDroppingTheEarliest(t *testing.T) {
 	ledger.Load([]bans.Ban{later, earlier})
 
 	held := ledger.Snapshot()
-	if len(held) != 1 || held[0] != later {
+	if len(held) != 1 || !reflect.DeepEqual(held[0], later) {
 		t.Errorf("the ledger holds %+v, want only the ban that began later", held)
 	}
 }
@@ -267,7 +268,7 @@ func TestLoadReplacesTheBansHeld(t *testing.T) {
 		bans.Notes{})
 
 	want := []bans.Ban{first, second, kept}
-	if got := ledger.Snapshot(); !slices.Equal(got, want) {
+	if got := ledger.Snapshot(); !reflect.DeepEqual(got, want) {
 		t.Errorf("the ledger holds %+v, want %+v", got, want)
 	}
 }

internal/config/config.go

@@ -48,6 +48,12 @@ type Config struct {
 	// TrustedProxies are the netblocks whose X-Forwarded-For is
 	// believed (SWWAF_TRUSTED_PROXIES).
 	TrustedProxies []netip.Prefix
+	// IPv6GroupPrefix is the length of the IPv6 netblock that is one client
+	// (SWWAF_IPV6_GROUP_PREFIX), from 32 to 128.
+	IPv6GroupPrefix int
+	// MaxTrackedClients is the most clients the table of clients holds, in
+	// memory and in clients.json (SWWAF_MAX_TRACKED_CLIENTS).
+	MaxTrackedClients int
 	// ClientRequestTimeout bounds reading the whole request from the
 	// client (SWWAF_CLIENT_REQUEST_TIMEOUT).
 	ClientRequestTimeout time.Duration
@@ -131,12 +137,50 @@ type Config struct {
 	// percentages from 0 to 100, by AS number, written as AS64496, or by
 	// country, a two-letter code in capitals, as the lookup gives them.
 	// UnknownLimitPercent is the percentage of every limit a client without
-	// a country gets (SWWAF_UNKNOWN_LIMIT_PERCENT).
+	// a country gets (SWWAF_UNKNOWN_LIMIT_PERCENT). ASNLimitPercentURL is
+	// where a file of AS:percent lines is fetched from, whose percentages
+	// count as those of ASNLimitPercent do (SWWAF_ASN_LIMIT_PERCENT_URL), ""
+	// while it is unset.
 	ASNLimitPercent     map[string]int64
 	CountryLimitPercent map[string]int64
 	ASNBytesPercent     map[string]int64
 	CountryBytesPercent map[string]int64
 	UnknownLimitPercent int64
+	ASNLimitPercentURL  string
+	// BlocklistURLs are where the blocklists are fetched from
+	// (SWWAF_BLOCKLIST_URLS). Each list, and ASNLimitPercentURL's, is
+	// fetched again BlocklistRefresh after it was last fetched or tried
+	// (SWWAF_BLOCKLIST_REFRESH), which is never less than an hour.
+	// BlocklistAction is what is done with a client a blocklist lists
+	// (SWWAF_BLOCKLIST_ACTION): deny, limit or log; for limit,
+	// BlocklistLimitPercent is the percentage of every limit it gets.
+	BlocklistURLs         []string
+	BlocklistRefresh      time.Duration
+	BlocklistAction       string
+	BlocklistLimitPercent int64
+	// DNSBLZones are the DNSBL zones clients are asked about
+	// (SWWAF_DNSBL_ZONES), through DNSBLResolver (SWWAF_DNSBL_RESOLVER), or
+	// the host's resolver while that is the zero AddrPort.
+	// AbuseIPDBKey is the key of the AbuseIPDB account clients are checked
+	// with (SWWAF_ABUSEIPDB_KEY), "" while it is unset and none is. A score
+	// of AbuseIPDBMinScore or more is a hit (SWWAF_ABUSEIPDB_MIN_SCORE), and
+	// at most AbuseIPDBDailyBudget checks are made a day
+	// (SWWAF_ABUSEIPDB_DAILY_BUDGET).
+	// ReputationAction is what is done with a client a zone's verdict lists,
+	// or whose score is a hit (SWWAF_REPUTATION_ACTION): deny, limit or log;
+	// for limit, ReputationLimitPercent is the percentage of every limit it
+	// gets. A verdict or a score is used for ReputationCacheTTL after it was
+	// fetched (SWWAF_REPUTATION_CACHE_TTL), and a query or a check may take
+	// ReputationTimeout (SWWAF_REPUTATION_TIMEOUT). Neither can be off.
+	DNSBLZones             []string
+	DNSBLResolver          netip.AddrPort
+	AbuseIPDBKey           string
+	AbuseIPDBMinScore      int64
+	AbuseIPDBDailyBudget   int
+	ReputationAction       string
+	ReputationLimitPercent int64
+	ReputationCacheTTL     time.Duration
+	ReputationTimeout      time.Duration
 	// BanResponse is the status a refused client is answered with, 403
 	// or 429, or 0 to close the connection without an answer
 	// (SWWAF_BAN_RESPONSE). It answers a banned client, a request that
@@ -171,6 +215,9 @@ type Config struct {
 	// LogRequestHeaders are the request headers whose values the request
 	// log gives, in lower case (SWWAF_LOG_REQUEST_HEADERS).
 	LogRequestHeaders []string
+	// LogLevel is the least severe of the process's own messages that are
+	// written (SWWAF_LOG_LEVEL). It holds back no request log line.
+	LogLevel slog.Level
 	// AdminToken is the bearer token an admin sends for the ban endpoints
 	// and /_smallwebwaf/clients/<ip> (SWWAF_ADMIN_TOKEN), "" while it is
 	// unset and they are off.
@@ -259,6 +306,10 @@ const (
 	gibibyte = 1 << 30
 	ipv4Bits = 32
 	ipv6Bits = 128
+	// minIPv6GroupPrefix is the shortest SWWAF_IPV6_GROUP_PREFIX, the
+	// netblock a provider is usually given: a shorter one would make one
+	// client of the customers of several providers.
+	minIPv6GroupPrefix = 32
 	// minTokenLength is the fewest characters a token may have.
 	minTokenLength = 32
 	// masked is what the log shows for a token that is set, and in place of
@@ -308,6 +359,9 @@ var (
 		"is not the length of an IPv4 netblock, from 0 to 32, such as 24")
 	errNotV6Prefix = errors.New(
 		"is not the length of an IPv6 netblock, from 0 to 128, such as 48")
+	errNotIPv6GroupPrefix = errors.New(
+		"is not the length of an IPv6 netblock, from 32 to 128, such as 64")
+	errNotLogLevel      = errors.New("is not debug, info, warn or error")
 	errNotNamedNetblock = errors.New(
 		"is not a name, = and a netblock, such as office=203.0.113.0/24")
 	errNotAbsolutePath = errors.New(
@@ -344,6 +398,18 @@ var (
 		"is not a code, : and a percentage, such as AS64496:50 or cn:25")
 	errNotPercent  = errors.New("is not a percentage, a whole number from 0 to 100")
 	errListedTwice = errors.New("is listed twice")
+	errNotListURL  = errors.New(
+		"is not an http or https URL without a user or a fragment, " +
+			"such as https://www.spamhaus.org/drop/drop.txt")
+	errInBlocklistURLs = errors.New("is in SWWAF_BLOCKLIST_URLS too")
+	errNotAnHourOrMore = errors.New("is not a duration of 1h or more, such as 24h")
+	errNotAction       = errors.New(
+		"is not deny, limit:<percent> such as limit:25, or log")
+	errNotZone     = errors.New("is not a DNS zone such as dnsbl.dronebl.org")
+	errZoneTooLong = errors.New("is longer than 189 characters, too long for the " +
+		"names IPv6 clients are asked about by")
+	errNotResolver = errors.New("is not an IP address with an optional port, " +
+		"such as 192.0.2.53 or [2001:db8::53]:5353")
 )
 
 // FromEnvironment reads the settings with lookupEnv, normally
@@ -361,6 +427,8 @@ func FromEnvironment(lookupEnv func(string) (string, bool)) (*Config, error) {
 		InstanceName:         env.instanceName(),
 		Observe:              env.observe("SWWAF_MODE", "enforce"),
 		TrustedProxies:       env.netblocks("SWWAF_TRUSTED_PROXIES", privateRanges),
+		IPv6GroupPrefix:      env.ipv6GroupPrefix("SWWAF_IPV6_GROUP_PREFIX", "64"),
+		MaxTrackedClients:    env.numberNotOff("SWWAF_MAX_TRACKED_CLIENTS", "20000"),
 		ClientRequestTimeout: env.duration("SWWAF_CLIENT_REQUEST_TIMEOUT", "60s"),
 		ClientRequestHeaderMaxBytes: env.headerSize(
 			"SWWAF_CLIENT_REQUEST_HEADER_MAX_BYTES", "32K"),
@@ -388,11 +456,21 @@ func FromEnvironment(lookupEnv func(string) (string, bool)) (*Config, error) {
 		DeniedCountries:         env.countries("SWWAF_DENIED_COUNTRIES", ""),
 		ExclusivelyAllowedCountries: env.countries(
 			"SWWAF_EXCLUSIVELY_ALLOWED_COUNTRIES", ""),
-		ASNLimitPercent:      env.percents("SWWAF_ASN_LIMIT_PERCENT", parseASN),
+		ASNLimitPercent:      env.percents("SWWAF_ASN_LIMIT_PERCENT", ParseASN),
 		CountryLimitPercent:  env.percents("SWWAF_COUNTRY_LIMIT_PERCENT", parseCountry),
-		ASNBytesPercent:      env.percents("SWWAF_ASN_BYTES_PERCENT", parseASN),
+		ASNBytesPercent:      env.percents("SWWAF_ASN_BYTES_PERCENT", ParseASN),
 		CountryBytesPercent:  env.percents("SWWAF_COUNTRY_BYTES_PERCENT", parseCountry),
 		UnknownLimitPercent:  env.percent("SWWAF_UNKNOWN_LIMIT_PERCENT", "100"),
+		ASNLimitPercentURL:   env.listURL("SWWAF_ASN_LIMIT_PERCENT_URL"),
+		BlocklistURLs:        env.listURLs("SWWAF_BLOCKLIST_URLS"),
+		BlocklistRefresh:     env.refresh("SWWAF_BLOCKLIST_REFRESH", "24h"),
+		DNSBLZones:           env.zones("SWWAF_DNSBL_ZONES"),
+		DNSBLResolver:        env.resolver("SWWAF_DNSBL_RESOLVER"),
+		AbuseIPDBKey:         env.secret("SWWAF_ABUSEIPDB_KEY"),
+		AbuseIPDBMinScore:    env.percent("SWWAF_ABUSEIPDB_MIN_SCORE", "75"),
+		AbuseIPDBDailyBudget: env.numberNotOff("SWWAF_ABUSEIPDB_DAILY_BUDGET", "900"),
+		ReputationCacheTTL:   env.durationNotOff("SWWAF_REPUTATION_CACHE_TTL", "24h"),
+		ReputationTimeout:    env.durationNotOff("SWWAF_REPUTATION_TIMEOUT", "2s"),
 		BanResponse:          env.banResponse("SWWAF_BAN_RESPONSE", "403"),
 		LimitBanDuration:     env.durationNotOff("SWWAF_LIMIT_BAN_DURATION", "1h"),
 		LimitBanRepeatWindow: env.durationNotOff("SWWAF_LIMIT_BAN_REPEAT_WINDOW", "24h"),
@@ -405,6 +483,7 @@ func FromEnvironment(lookupEnv func(string) (string, bool)) (*Config, error) {
 		StateCounterInterval: env.durationNotOff("SWWAF_STATE_COUNTER_INTERVAL", "15m"),
 		LogRequestHeaders: env.headerNames("SWWAF_LOG_REQUEST_HEADERS",
 			"accept,accept-language,accept-encoding,content-type,origin,range"),
+		LogLevel:             env.logLevel("SWWAF_LOG_LEVEL", "info"),
 		AdminToken:           env.token("SWWAF_ADMIN_TOKEN"),
 		MetricsToken:         env.token("SWWAF_METRICS_TOKEN"),
 		MetricsTopN:          env.numberNotOff("SWWAF_METRICS_TOP_N", "50"),
@@ -435,10 +514,15 @@ func FromEnvironment(lookupEnv func(string) (string, bool)) (*Config, error) {
 
 	cfg.LogRemoteAppName = env.appName("SWWAF_LOG_REMOTE_APP_NAME",
 		cfg.InstanceName, cfg.LogRemoteURL != nil)
+	cfg.BlocklistAction, cfg.BlocklistLimitPercent = env.action(
+		"SWWAF_BLOCKLIST_ACTION", "deny")
+	cfg.ReputationAction, cfg.ReputationLimitPercent = env.action(
+		"SWWAF_REPUTATION_ACTION", "limit:25")
 
 	env.checkInstanceNameForNtfy(cfg.InstanceName, cfg.AlertNtfyURL != nil)
 	env.checkLookupDBPath(cfg)
 	env.checkCountriesAndLookups(cfg)
+	env.checkASNLimitPercentURL(cfg)
 
 	if env.err != nil {
 		return nil, env.err
@@ -664,12 +748,93 @@ func (e *environment) percents(
 
 // percent reads a setting that is a percentage, from 0 to 100.
 func (e *environment) percent(name, defaultValue string) int64 {
-	percent, err := parsePercent(e.value(name, defaultValue))
+	percent, err := ParsePercent(e.value(name, defaultValue))
 	e.check(name, err)
 
 	return percent
 }
 
+// listURL reads a setting that is the URL a list is fetched from, "" while
+// it is unset or empty.
+func (e *environment) listURL(name string) string {
+	value := e.value(name, "")
+	if value != "" && !isListURL(value) {
+		e.check(name, fmt.Errorf("%q %w", value, errNotListURL))
+	}
+
+	return value
+}
+
+// listURLs reads a setting that is a list of the URLs lists are fetched
+// from. It is empty by default.
+func (e *environment) listURLs(name string) []string {
+	urls, err := parseListURLs(e.value(name, ""))
+	e.check(name, err)
+
+	return urls
+}
+
+// refresh reads the setting that is how long after a list was last
+// fetched or tried it is fetched again: a duration of an hour or more,
+// since the Spamhaus lists may be fetched no more often, which cannot be
+// off.
+func (e *environment) refresh(name, defaultValue string) time.Duration {
+	value := e.value(name, defaultValue)
+
+	duration, err := parseDuration(value)
+	if err != nil || duration < time.Hour {
+		e.check(name, fmt.Errorf("%q %w", value, errNotAnHourOrMore))
+	}
+
+	return duration
+}
+
+// action reads a setting that is what is done with a client a blocklist
+// or a DNSBL zone lists: deny, log, or limit:<percent>, which it returns
+// as limit and the percentage.
+func (e *environment) action(name, defaultValue string) (string, int64) {
+	value := e.value(name, defaultValue)
+	if value == "deny" || value == "log" {
+		return value, 0
+	}
+
+	percentText, isLimit := strings.CutPrefix(value, "limit:")
+
+	percent, err := ParsePercent(percentText)
+	if !isLimit || err != nil {
+		e.check(name, fmt.Errorf("%q %w", value, errNotAction))
+	}
+
+	return "limit", percent
+}
+
+// zones reads the setting that is the list of DNSBL zones. It is empty by
+// default. The log shows each zone with its key masked, as MaskZoneKey
+// masks it.
+func (e *environment) zones(name string) []string {
+	value, _ := e.lookup(name)
+	zones, err := parseZones(value)
+	e.check(name, err)
+
+	logged := make([]string, len(zones))
+	for i, zone := range zones {
+		logged[i] = MaskZoneKey(zone)
+	}
+
+	e.settings = append(e.settings, slog.String(name, strings.Join(logged, ",")))
+
+	return zones
+}
+
+// resolver reads the setting that is the resolver the DNSBL zones are
+// asked through, the zero AddrPort while it is unset or empty.
+func (e *environment) resolver(name string) netip.AddrPort {
+	resolver, err := parseResolver(e.value(name, ""))
+	e.check(name, err)
+
+	return resolver
+}
+
 // lookupSource reads the setting that is where clients are looked up:
 // geojs, file, or off.
 func (e *environment) lookupSource(name, defaultValue string) string {
@@ -698,8 +863,9 @@ func (e *environment) checkLookupDBPath(cfg *Config) {
 // checkCountriesAndLookups refuses a country on both country lists, and,
 // while SWWAF_LOOKUP_SOURCE is off, each setting that needs clients looked
 // up: the country lists, SWWAF_ADD_LOOKUP_HEADERS, the biased thresholds,
-// of which SWWAF_UNKNOWN_LIMIT_PERCENT needs them only below 100, where it
+// SWWAF_ASN_LIMIT_PERCENT_URL among them, of which
-// lowers a limit, and the anomaly thresholds per AS number.
+// SWWAF_UNKNOWN_LIMIT_PERCENT needs them only below 100, where it lowers a
+// limit, and the anomaly thresholds per AS number.
 func (e *environment) checkCountriesAndLookups(cfg *Config) {
 	for _, country := range cfg.ExclusivelyAllowedCountries {
 		if slices.Contains(cfg.DeniedCountries, country) {
@@ -724,6 +890,7 @@ func (e *environment) checkCountriesAndLookups(cfg *Config) {
 		{"SWWAF_ASN_BYTES_PERCENT", len(cfg.ASNBytesPercent) > 0},
 		{"SWWAF_COUNTRY_BYTES_PERCENT", len(cfg.CountryBytesPercent) > 0},
 		{"SWWAF_UNKNOWN_LIMIT_PERCENT", cfg.UnknownLimitPercent < 100},
+		{"SWWAF_ASN_LIMIT_PERCENT_URL", cfg.ASNLimitPercentURL != ""},
 		{"SWWAF_ANOMALY_ASN_REQUESTS_PER_MINUTE", cfg.AnomalyASN.RequestsPerMinute > 0},
 		{"SWWAF_ANOMALY_ASN_REQUESTS_PER_HOUR", cfg.AnomalyASN.RequestsPerHour > 0},
 		{"SWWAF_ANOMALY_ASN_BYTES_PER_MINUTE", cfg.AnomalyASN.BytesPerMinute > 0},
@@ -736,6 +903,15 @@ func (e *environment) checkCountriesAndLookups(cfg *Config) {
 	}
 }
 
+// checkASNLimitPercentURL refuses SWWAF_ASN_LIMIT_PERCENT_URL naming a
+// blocklist too: the file at a URL is fetched as one list or the other.
+func (e *environment) checkASNLimitPercentURL(cfg *Config) {
+	if slices.Contains(cfg.BlocklistURLs, cfg.ASNLimitPercentURL) {
+		e.check("SWWAF_ASN_LIMIT_PERCENT_URL",
+			fmt.Errorf("%q %w", cfg.ASNLimitPercentURL, errInBlocklistURLs))
+	}
+}
+
 // headerNames reads a setting that is a list of header names, and
 // returns them in lower case.
 func (e *environment) headerNames(name, defaultValue string) []string {
@@ -787,6 +963,37 @@ func (e *environment) v6Prefix(name, defaultValue string) int {
 	return length
 }
 
+// ipv6GroupPrefix reads the setting that is the length of the IPv6
+// netblock that is one client, from minIPv6GroupPrefix to 128.
+func (e *environment) ipv6GroupPrefix(name, defaultValue string) int {
+	value := e.value(name, defaultValue)
+
+	length, err := strconv.Atoi(value)
+	if err != nil || length < minIPv6GroupPrefix || length > ipv6Bits {
+		e.check(name, fmt.Errorf("%q %w", value, errNotIPv6GroupPrefix))
+	}
+
+	return length
+}
+
+// logLevel reads the setting that is the least severe of the process's
+// own messages that are written: debug, info, warn or error.
+func (e *environment) logLevel(name, defaultValue string) slog.Level {
+	value := e.value(name, defaultValue)
+
+	level, known := map[string]slog.Level{
+		"debug": slog.LevelDebug,
+		"info":  slog.LevelInfo,
+		"warn":  slog.LevelWarn,
+		"error": slog.LevelError,
+	}[value]
+	if !known {
+		e.check(name, fmt.Errorf("%q %w", value, errNotLogLevel))
+	}
+
+	return level
+}
+
 // thresholds reads the four anomaly thresholds whose settings' names
 // start with prefix: requests and bytes per minute and per hour. Each is
 // off by default.
@@ -964,10 +1171,10 @@ func (e *environment) webhookHeaders(name string) http.Header {
 }
 
 // secret reads a setting that is a secret another service gave, such as
-// an ntfy token, "" while it is unset. It is sent in a header, which
+// an ntfy token or an AbuseIPDB key, "" while it is unset. It is sent in
-// cannot hold a control character, so one in it is an error. The log
+// a header, which cannot hold a control character, so one in it is an
-// shows ******** in place of a value that is not empty, and an error
+// error. The log shows ******** in place of a value that is not empty, and
-// shows none of it.
+// an error shows none of it.
 func (e *environment) secret(name string) string {
 	value, _ := e.lookup(name)
 
@@ -1187,7 +1394,7 @@ func parseNetblocks(value string) ([]netip.Prefix, error) {
 	netblocks := make([]netip.Prefix, 0, len(items))
 
 	for _, item := range items {
-		netblock, err := parseNetblock(item)
+		netblock, err := ParseNetblock(item)
 		if err != nil {
 			return nil, err
 		}
@@ -1198,9 +1405,10 @@ func parseNetblocks(value string) ([]netip.Prefix, error) {
 	return netblocks, nil
 }
 
-// parseNetblock reads a netblock in CIDR form, such as 10.0.0.0/8. A bare
+// ParseNetblock reads a netblock in CIDR form, such as 10.0.0.0/8. A bare
-// address is a netblock of that address alone, a /32 or a /128.
+// address is a netblock of that address alone, a /32 or a /128. A
-func parseNetblock(value string) (netip.Prefix, error) {
+// blocklist's lines are read with it too.
+func ParseNetblock(value string) (netip.Prefix, error) {
 	if strings.Contains(value, "/") {
 		netblock, err := netip.ParsePrefix(value)
 		if err != nil {
@@ -1237,7 +1445,7 @@ func parseNamedNetblocks(value string) ([]anomaly.NamedNetblock, error) {
 			return nil, fmt.Errorf("%q %w", item, errNotNamedNetblock)
 		}
 
-		netblock, err := parseNetblock(strings.TrimSpace(netblockText))
+		netblock, err := ParseNetblock(strings.TrimSpace(netblockText))
 		if err != nil {
 			return nil, err
 		}
@@ -1337,10 +1545,11 @@ func parseCountry(value string) (string, error) {
 	return country, nil
 }
 
-// parseASN reads an AS number such as AS64496, in either case, and
+// ParseASN reads an AS number such as AS64496, in either case, and
 // returns it as the lookup gives it: AS and the number, in capitals and
-// without leading zeros.
+// without leading zeros. The file SWWAF_ASN_LIMIT_PERCENT_URL names is
-func parseASN(value string) (string, error) {
+// read with it too.
+func ParseASN(value string) (string, error) {
 	digits, hasAS := strings.CutPrefix(strings.ToUpper(value), "AS")
 
 	number, err := strconv.ParseUint(digits, 10, 32)
@@ -1376,7 +1585,7 @@ func parsePercents(
 			return nil, err
 		}
 
-		percent, err := parsePercent(percentText)
+		percent, err := ParsePercent(percentText)
 		if err != nil {
 			return nil, err
 		}
@@ -1391,8 +1600,9 @@ func parsePercents(
 	return percents, nil
 }
 
-// parsePercent reads a percentage, a whole number from 0 to 100.
+// ParsePercent reads a percentage, a whole number from 0 to 100. The file
-func parsePercent(value string) (int64, error) {
+// SWWAF_ASN_LIMIT_PERCENT_URL names is read with it too.
+func ParsePercent(value string) (int64, error) {
 	percent, err := strconv.ParseInt(value, 10, 64)
 	if err != nil || percent < 0 || percent > 100 {
 		return 0, fmt.Errorf("%q %w", value, errNotPercent)
@@ -1548,16 +1758,7 @@ func parseWebhookURL(value string) (*url.URL, string, error) {
 	}
 
 	webhook, err := url.Parse(value)
-	if err != nil {
+	if err != nil || !isHTTPURL(webhook) {
-		return nil, "", errNotWebhookURL
-	}
-
-	port, err := strconv.ParseUint(webhook.Port(), 10, 16)
-
-	valid := (webhook.Scheme == "http" || webhook.Scheme == "https") &&
-		webhook.Hostname() != "" && (webhook.Port() == "" || (err == nil && port != 0)) &&
-		webhook.User == nil && webhook.Opaque == "" && webhook.Fragment == ""
-	if !valid {
 		return nil, "", errNotWebhookURL
 	}
 
@@ -1569,6 +1770,154 @@ func parseWebhookURL(value string) (*url.URL, string, error) {
 	return webhook, logged, nil
 }
 
+// isHTTPURL reports whether u is http or https, with a host, and an
+// optional port from 1 to 65535, path and query, without a user or a
+// fragment.
+func isHTTPURL(u *url.URL) bool {
+	port, err := strconv.ParseUint(u.Port(), 10, 16)
+
+	return (u.Scheme == "http" || u.Scheme == "https") && u.Hostname() != "" &&
+		(u.Port() == "" || (err == nil && port != 0)) &&
+		u.User == nil && u.Opaque == "" && u.Fragment == ""
+}
+
+// isListURL reports whether value is a URL a list can be fetched from, as
+// isHTTPURL says.
+func isListURL(value string) bool {
+	u, err := url.Parse(value)
+
+	return err == nil && isHTTPURL(u)
+}
+
+// parseListURLs reads a comma-separated list of the URLs lists are fetched
+// from. A URL listed twice is an error: it would be fetched twice as
+// often.
+func parseListURLs(value string) ([]string, error) {
+	urls, err := parseList(value)
+	if err != nil {
+		return nil, err
+	}
+
+	for i, listURL := range urls {
+		if !isListURL(listURL) {
+			return nil, fmt.Errorf("%q %w", listURL, errNotListURL)
+		}
+
+		if slices.Contains(urls[:i], listURL) {
+			return nil, fmt.Errorf("%q %w", listURL, errListedTwice)
+		}
+	}
+
+	return urls, nil
+}
+
+const (
+	// maxZoneLength is the most characters a DNSBL zone may have: 253, the
+	// most a DNS name may have, less the 64 that come before the zone in
+	// the name an IPv6 client is asked about by, its 32 hex digits each
+	// followed by a dot.
+	maxZoneLength = 189
+	// maxLabelLength is the most characters a label of a DNS name may have.
+	maxLabelLength = 63
+	// labelChars are the characters a label of a DNS zone may hold.
+	labelChars = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-"
+	// dnsPort is the port a resolver is asked on when SWWAF_DNSBL_RESOLVER
+	// gives none.
+	dnsPort = 53
+)
+
+// parseZones reads a comma-separated list of DNSBL zones, each a DNS name
+// such as dnsbl.dronebl.org: labels separated by dots, each of 1 to 63
+// letters, digits and hyphens, neither starting nor ending with a hyphen,
+// and at most maxZoneLength characters in all. Go's resolver takes any
+// other name for one that does not exist, so that the zone would list no
+// client. A zone listed twice is an error, whatever the case of its
+// letters, which DNS names ignore, and whatever its key, since
+// MaskZoneKey shows two keys of one zone alike. An error shows a zone as
+// MaskZoneKey does.
+func parseZones(value string) ([]string, error) {
+	zones, err := parseList(value)
+	if err != nil {
+		// parseList's error, for an empty item, shows the whole value, keys
+		// included.
+		return nil, errEmptyItem
+	}
+
+	for i, zone := range zones {
+		shown := MaskZoneKey(zone)
+		listedBefore := slices.ContainsFunc(zones[:i], func(earlier string) bool {
+			return strings.EqualFold(MaskZoneKey(earlier), shown)
+		})
+
+		switch {
+		case len(zone) > maxZoneLength:
+			return nil, fmt.Errorf("%q %w", shown, errZoneTooLong)
+		case !isZone(zone):
+			return nil, fmt.Errorf("%q %w", shown, errNotZone)
+		case listedBefore:
+			return nil, fmt.Errorf("%q %w", shown, errListedTwice)
+		}
+	}
+
+	return zones, nil
+}
+
+// MaskZoneKey returns zone with ******** in place of its key, if it is a
+// zone of Spamhaus's keyed query service, a name under dq.spamhaus.net,
+// such as <key>.xbl.dq.spamhaus.net, whose first label is the key. Any
+// other zone it returns as it is. A zone is shown so wherever it leaves
+// the process: in the log, the alerts and the metrics.
+func MaskZoneKey(zone string) string {
+	// DNS names ignore case, and a name may be written with a dot at its
+	// end.
+	name := strings.TrimSuffix(strings.ToLower(zone), ".")
+	if !strings.HasSuffix(name, ".dq.spamhaus.net") {
+		return zone
+	}
+
+	_, rest, _ := strings.Cut(zone, ".")
+
+	return masked + "." + rest
+}
+
+// isZone reports whether each label of zone is as parseZones takes it.
+func isZone(zone string) bool {
+	for label := range strings.SplitSeq(zone, ".") {
+		badChar := strings.ContainsFunc(label, func(char rune) bool {
+			return !strings.ContainsRune(labelChars, char)
+		})
+
+		if label == "" || len(label) > maxLabelLength || badChar ||
+			strings.HasPrefix(label, "-") || strings.HasSuffix(label, "-") {
+			return false
+		}
+	}
+
+	return true
+}
+
+// parseResolver reads the resolver the DNSBL zones are asked through: an
+// IP address with a port from 1 to 65535, such as 192.0.2.53:5353 or
+// [2001:db8::53]:5353, or without one, such as 192.0.2.53 or 2001:db8::53,
+// for port 53. An empty value is none, the zero AddrPort.
+func parseResolver(value string) (netip.AddrPort, error) {
+	if value == "" {
+		return netip.AddrPort{}, nil
+	}
+
+	resolver, err := netip.ParseAddrPort(value)
+	if err == nil && resolver.Port() != 0 {
+		return resolver, nil
+	}
+
+	addr, err := netip.ParseAddr(value)
+	if err != nil {
+		return netip.AddrPort{}, fmt.Errorf("%q %w", value, errNotResolver)
+	}
+
+	return netip.AddrPortFrom(addr, dnsPort), nil
+}
+
 // parseWebhookHeaders reads a comma-separated list of headers, each its
 // name, :, and its value, and returns them, and how the log shows them,
 // with each value as ********. An error names the item by its place in

internal/config/config_test.go

@@ -27,6 +27,8 @@ const (
 	upstreamURL             = "SWWAF_UPSTREAM_URL"
 	mode                    = "SWWAF_MODE"
 	trustedProxies          = "SWWAF_TRUSTED_PROXIES"
+	ipv6GroupPrefix         = "SWWAF_IPV6_GROUP_PREFIX"
+	maxTrackedClients       = "SWWAF_MAX_TRACKED_CLIENTS"
 	clientRequestTimeout    = "SWWAF_CLIENT_REQUEST_TIMEOUT"
 	clientHeaderMaxBytes    = "SWWAF_CLIENT_REQUEST_HEADER_MAX_BYTES"
 	clientIdleTimeout       = "SWWAF_CLIENT_IDLE_TIMEOUT"
@@ -57,6 +59,18 @@ const (
 	asnBytesPercent         = "SWWAF_ASN_BYTES_PERCENT"
 	countryBytesPercent     = "SWWAF_COUNTRY_BYTES_PERCENT"
 	unknownLimitPercent     = "SWWAF_UNKNOWN_LIMIT_PERCENT"
+	asnLimitPercentURL      = "SWWAF_ASN_LIMIT_PERCENT_URL"
+	blocklistURLs           = "SWWAF_BLOCKLIST_URLS"
+	blocklistRefresh        = "SWWAF_BLOCKLIST_REFRESH"
+	blocklistAction         = "SWWAF_BLOCKLIST_ACTION"
+	dnsblZones              = "SWWAF_DNSBL_ZONES"
+	dnsblResolver           = "SWWAF_DNSBL_RESOLVER"
+	abuseIPDBKey            = "SWWAF_ABUSEIPDB_KEY"
+	abuseIPDBMinScore       = "SWWAF_ABUSEIPDB_MIN_SCORE"
+	abuseIPDBDailyBudget    = "SWWAF_ABUSEIPDB_DAILY_BUDGET"
+	reputationAction        = "SWWAF_REPUTATION_ACTION"
+	reputationCacheTTL      = "SWWAF_REPUTATION_CACHE_TTL"
+	reputationTimeout       = "SWWAF_REPUTATION_TIMEOUT"
 	banResponse             = "SWWAF_BAN_RESPONSE"
 	limitBanDuration        = "SWWAF_LIMIT_BAN_DURATION"
 	limitBanRepeatWindow    = "SWWAF_LIMIT_BAN_REPEAT_WINDOW"
@@ -72,6 +86,7 @@ const (
 	metricsTopN             = "SWWAF_METRICS_TOP_N"
 	instanceName            = "SWWAF_INSTANCE_NAME"
 	logRequestHeaders       = "SWWAF_LOG_REQUEST_HEADERS"
+	logLevel                = "SWWAF_LOG_LEVEL"
 	rulesDir                = "SWWAF_RULES_DIR"
 	rulesEnabled            = "SWWAF_RULES_ENABLED"
 	logRemoteURL            = "SWWAF_LOG_REMOTE_URL"
@@ -148,6 +163,9 @@ const (
 	defaultAlertCooldown = "15m"
 )
 
+// defaultReputationCacheTTL is the default of SWWAF_REPUTATION_CACHE_TTL.
+const defaultReputationCacheTTL = "24h"
+
 // defaultLogRequestHeaders is the default of SWWAF_LOG_REQUEST_HEADERS.
 const defaultLogRequestHeaders = "accept,accept-language,accept-encoding," +
 	"content-type,origin,range"
@@ -384,6 +402,57 @@ func TestValuesAsSet(t *testing.T) {
 	wantCountries(t, allowedCountries, cfg.ExclusivelyAllowedCountries, "DE")
 }
 
+func TestIPv6GroupPrefixMaxTrackedClientsAndLogLevel(t *testing.T) {
+	t.Parallel()
+
+	for _, tc := range []struct {
+		env             environment
+		prefix, clients int
+		level           slog.Level
+	}{
+		{environment{}, 64, 20000, slog.LevelInfo},
+		{
+			environment{ipv6GroupPrefix: "48", maxTrackedClients: "500", logLevel: "warn"},
+			48, 500, slog.LevelWarn,
+		},
+	} {
+		cfg := fromEnvironment(t, tc.env)
+		if cfg.IPv6GroupPrefix != tc.prefix || cfg.MaxTrackedClients != tc.clients ||
+			cfg.LogLevel != tc.level {
+			t.Errorf("%v gave %d, %d and %v, want %d, %d and %v", tc.env,
+				cfg.IPv6GroupPrefix, cfg.MaxTrackedClients, cfg.LogLevel,
+				tc.prefix, tc.clients, tc.level)
+		}
+	}
+}
+
+func TestIPv6GroupPrefixFrom32To128(t *testing.T) {
+	t.Parallel()
+
+	for _, length := range []int{32, 128} {
+		cfg := fromEnvironment(t, environment{ipv6GroupPrefix: strconv.Itoa(length)})
+		if cfg.IPv6GroupPrefix != length {
+			t.Errorf("%s=%d gave %d", ipv6GroupPrefix, length, cfg.IPv6GroupPrefix)
+		}
+	}
+}
+
+func TestEachLogLevel(t *testing.T) {
+	t.Parallel()
+
+	for value, want := range map[string]slog.Level{
+		"debug": slog.LevelDebug,
+		"info":  slog.LevelInfo,
+		"warn":  slog.LevelWarn,
+		"error": slog.LevelError,
+	} {
+		cfg := fromEnvironment(t, environment{logLevel: value})
+		if cfg.LogLevel != want {
+			t.Errorf("%s=%s gave %v, want %v", logLevel, value, cfg.LogLevel, want)
+		}
+	}
+}
+
 func TestByteLimitSettingsAsSet(t *testing.T) {
 	t.Parallel()
 
@@ -953,6 +1022,7 @@ func TestSettingNeedingLookupsStopsTheStartWhileTheyAreOff(t *testing.T) {
 		deniedCountries:                "kp",
 		allowedCountries:               "de",
 		addLookupHeaders:               enabled,
+		asnLimitPercentURL:             asnURL,
 		asnLimitPercent:                "AS64496:50",
 		countryLimitPercent:            "cn:25",
 		asnBytesPercent:                "AS64496:50",
@@ -978,11 +1048,13 @@ func TestSettingNeedingLookupsStopsTheStartWhileTheyAreOff(t *testing.T) {
 
 	// Set empty, the lists need nothing looked up, and nor does
 	// SWWAF_UNKNOWN_LIMIT_PERCENT at 100, which lowers no limit, an anomaly
-	// threshold per AS number that is off, or any other anomaly threshold.
+	// threshold per AS number that is off, any other anomaly threshold, or
+	// a blocklist.
 	env := environment{
 		lookupSource: off, deniedCountries: "", allowedCountries: "",
 		asnLimitPercent: "", countryLimitPercent: "", asnBytesPercent: "",
-		countryBytesPercent: "", unknownLimitPercent: "100",
+		countryBytesPercent: "", unknownLimitPercent: "100", asnLimitPercentURL: "",
+		blocklistURLs: dropURL,
 	}
 	for _, name := range anomalyThresholds() {
 		env[name] = "1000"
@@ -1205,6 +1277,382 @@ func TestInvalidBiasedThresholdStopsTheStartSayingWhatIsWrong(t *testing.T) {
 	}
 }
 
+// dropURL and torURL are blocklists, and asnURL a file of AS:percent
+// lines.
+const (
+	dropURL = "https://www.spamhaus.org/drop/drop.txt"
+	torURL  = "https://lists.example/tor-exits.txt"
+	asnURL  = "https://lists.example/asn.txt"
+)
+
+// The actions of SWWAF_BLOCKLIST_ACTION, as Config gives them.
+const (
+	actionDeny  = "deny"
+	actionLimit = "limit"
+	actionLog   = "log"
+)
+
+func TestReputationSettingsAsSet(t *testing.T) {
+	t.Parallel()
+
+	cfg := fromEnvironment(t, environment{})
+	if len(cfg.BlocklistURLs) != 0 || cfg.BlocklistRefresh != 24*time.Hour ||
+		cfg.BlocklistAction != actionDeny || cfg.ASNLimitPercentURL != "" {
+		t.Errorf("%s, %s, %s and %s gave %v, %s, %s and %q by default, "+
+			"want none, 24h, deny and none", blocklistURLs, blocklistRefresh,
+			blocklistAction, asnLimitPercentURL, cfg.BlocklistURLs, cfg.BlocklistRefresh,
+			cfg.BlocklistAction, cfg.ASNLimitPercentURL)
+	}
+
+	for _, tc := range []struct {
+		value, action string
+		percent       int64
+	}{
+		{actionDeny, actionDeny, 0},
+		{actionLog, actionLog, 0},
+		{"limit:25", actionLimit, 25},
+		{"limit:0", actionLimit, 0},
+	} {
+		// An hour, the shortest refresh allowed.
+		cfg := fromEnvironment(t, environment{
+			blocklistURLs: dropURL + ", " + torURL, blocklistRefresh: "1h",
+			blocklistAction: tc.value, asnLimitPercentURL: asnURL,
+		})
+
+		if !slices.Equal(cfg.BlocklistURLs, []string{dropURL, torURL}) ||
+			cfg.BlocklistRefresh != time.Hour || cfg.BlocklistAction != tc.action ||
+			cfg.BlocklistLimitPercent != tc.percent || cfg.ASNLimitPercentURL != asnURL {
+			t.Errorf("%s=%s gave %v, %s, %s, %d and %s", blocklistAction, tc.value,
+				cfg.BlocklistURLs, cfg.BlocklistRefresh, cfg.BlocklistAction,
+				cfg.BlocklistLimitPercent, cfg.ASNLimitPercentURL)
+		}
+	}
+}
+
+func TestInvalidReputationSettingStopsTheStartSayingWhatIsWrong(t *testing.T) {
+	t.Parallel()
+
+	const (
+		notURL = " is not an http or https URL without a user or a fragment, " +
+			"such as https://www.spamhaus.org/drop/drop.txt"
+		notAnHour = " is not a duration of 1h or more, such as 24h"
+		notAction = " is not deny, limit:<percent> such as limit:25, or log"
+	)
+
+	for _, tc := range []struct{ name, value, want string }{
+		{
+			blocklistURLs, "ftp://lists.example/drop.txt",
+			`"ftp://lists.example/drop.txt"` + notURL,
+		},
+		{blocklistURLs, "lists.example/drop.txt", `"lists.example/drop.txt"` + notURL},
+		{
+			blocklistURLs, "https://me:secret@lists.example/drop.txt",
+			`"https://me:secret@lists.example/drop.txt"` + notURL,
+		},
+		{
+			blocklistURLs, dropURL + "," + torURL + "," + dropURL,
+			`"` + dropURL + `" is listed twice`,
+		},
+		{asnLimitPercentURL, asnURL + "#top", `"` + asnURL + `#top"` + notURL},
+		{blocklistRefresh, "59m", `"59m"` + notAnHour},
+		{blocklistRefresh, off, `"off"` + notAnHour},
+		{blocklistRefresh, "a day", `"a day"` + notAnHour},
+		{blocklistAction, "block", `"block"` + notAction},
+		{blocklistAction, actionLimit, `"limit"` + notAction},
+		{blocklistAction, "limit:101", `"limit:101"` + notAction},
+	} {
+		t.Run(tc.name+"="+tc.value, func(t *testing.T) {
+			t.Parallel()
+
+			_, err := config.FromEnvironment(environment{tc.name: tc.value}.lookupEnv)
+
+			want := tc.name + ": " + tc.want
+			if err == nil || err.Error() != want {
+				t.Errorf("error %v, want %s", err, want)
+			}
+		})
+	}
+}
+
+func TestASNLimitPercentURLThatIsABlocklistStopsTheStart(t *testing.T) {
+	t.Parallel()
+
+	_, err := config.FromEnvironment(environment{
+		blocklistURLs: dropURL + "," + asnURL, asnLimitPercentURL: asnURL,
+	}.lookupEnv)
+
+	want := asnLimitPercentURL + `: "` + asnURL + `" is in SWWAF_BLOCKLIST_URLS too`
+	if err == nil || err.Error() != want {
+		t.Errorf("error %v, want %s", err, want)
+	}
+}
+
+// dronebl is a DNSBL zone, and spamhaus one of Spamhaus's, a name
+// containing spamhausKey, the key of its keyed query service, which the
+// log shows as spamhausMasked.
+const (
+	dronebl        = "dnsbl.dronebl.org"
+	spamhausKey    = "abcdefghijklmnopqrstuvwxyz"
+	spamhaus       = spamhausKey + ".xbl.dq.spamhaus.net"
+	spamhausMasked = "********.xbl.dq.spamhaus.net"
+)
+
+func TestDNSBLSettingsAsSet(t *testing.T) {
+	t.Parallel()
+
+	cfg := fromEnvironment(t, environment{})
+	if len(cfg.DNSBLZones) != 0 || cfg.DNSBLResolver.IsValid() ||
+		cfg.ReputationAction != actionLimit || cfg.ReputationLimitPercent != 25 ||
+		cfg.ReputationCacheTTL != 24*time.Hour || cfg.ReputationTimeout != 2*time.Second {
+		t.Errorf("by default, the zones %v, the resolver %s, the action %s:%d, the TTL %s "+
+			"and the timeout %s, want no zone, no resolver, limit:25, 24h and 2s",
+			cfg.DNSBLZones,
+			cfg.DNSBLResolver, cfg.ReputationAction, cfg.ReputationLimitPercent,
+			cfg.ReputationCacheTTL, cfg.ReputationTimeout)
+	}
+
+	// The longest zone allowed, of 189 characters, with labels of 63, the
+	// longest allowed.
+	longest := strings.Repeat("a", 63) + "." + strings.Repeat("b", 63) + "." +
+		strings.Repeat("c", 61)
+
+	for _, tc := range []struct {
+		zones, resolver, action string
+		// want are the zones, resolver, action and percent Config gives.
+		want         []string
+		wantResolver string
+		wantAction   string
+		wantPercent  int64
+	}{
+		{
+			dronebl + ", " + spamhaus, "192.0.2.53", actionDeny,
+			[]string{dronebl, spamhaus}, "192.0.2.53:53", actionDeny, 0,
+		},
+		{
+			longest, "192.0.2.53:5353", actionLog,
+			[]string{longest}, "192.0.2.53:5353", actionLog, 0,
+		},
+		{
+			"Dnsbl-1.Example", "2001:db8::53", "limit:10",
+			[]string{"Dnsbl-1.Example"}, "[2001:db8::53]:53", actionLimit, 10,
+		},
+		{
+			dronebl, "[2001:db8::53]:5353", "limit:0",
+			[]string{dronebl}, "[2001:db8::53]:5353", actionLimit, 0,
+		},
+	} {
+		cfg := fromEnvironment(t, environment{
+			dnsblZones: tc.zones, dnsblResolver: tc.resolver, reputationAction: tc.action,
+			reputationCacheTTL: "12h", reputationTimeout: "3s",
+		})
+
+		if !slices.Equal(cfg.DNSBLZones, tc.want) ||
+			cfg.DNSBLResolver.String() != tc.wantResolver ||
+			cfg.ReputationAction != tc.wantAction ||
+			cfg.ReputationLimitPercent != tc.wantPercent ||
+			cfg.ReputationCacheTTL != 12*time.Hour ||
+			cfg.ReputationTimeout != 3*time.Second {
+			t.Errorf("%s=%s, %s=%s and %s=%s gave %v, %s, %s:%d, %s and %s", dnsblZones,
+				tc.zones, dnsblResolver, tc.resolver, reputationAction, tc.action,
+				cfg.DNSBLZones, cfg.DNSBLResolver, cfg.ReputationAction,
+				cfg.ReputationLimitPercent, cfg.ReputationCacheTTL, cfg.ReputationTimeout)
+		}
+	}
+}
+
+func TestInvalidDNSBLSettingStopsTheStartSayingWhatIsWrong(t *testing.T) {
+	t.Parallel()
+
+	const (
+		notZone     = " is not a DNS zone such as dnsbl.dronebl.org"
+		notResolver = " is not an IP address with an optional port, such as 192.0.2.53 " +
+			"or [2001:db8::53]:5353"
+		notAboveZero = " is not a duration above zero, such as 1h or 7d"
+	)
+
+	label64 := strings.Repeat("a", 64) + ".example"
+	tooLong := strings.Repeat("a", 63) + "." + strings.Repeat("b", 63) + "." +
+		strings.Repeat("c", 62)
+
+	for _, tc := range []struct{ name, value, want string }{
+		{dnsblZones, "dnsbl..example", `"dnsbl..example"` + notZone},
+		{dnsblZones, "dnsbl.example.", `"dnsbl.example."` + notZone},
+		{dnsblZones, "-dnsbl.example", `"-dnsbl.example"` + notZone},
+		{dnsblZones, "dnsbl-.example", `"dnsbl-.example"` + notZone},
+		{dnsblZones, "dns_bl.example", `"dns_bl.example"` + notZone},
+		{dnsblZones, label64, `"` + label64 + `"` + notZone},
+		{
+			dnsblZones, tooLong,
+			`"` + tooLong + `" is longer than 189 characters, too long for the names ` +
+				`IPv6 clients are asked about by`,
+		},
+		{
+			dnsblZones, dronebl + "," + spamhaus + "," + dronebl,
+			`"` + dronebl + `" is listed twice`,
+		},
+		// DNS names ignore case.
+		{dnsblZones, "dnsbl.example,DNSBL.example", `"DNSBL.example" is listed twice`},
+		{dnsblResolver, "resolver.example", `"resolver.example"` + notResolver},
+		{dnsblResolver, "192.0.2.53:0", `"192.0.2.53:0"` + notResolver},
+		{dnsblResolver, "192.0.2.53:65536", `"192.0.2.53:65536"` + notResolver},
+		{dnsblResolver, "[2001:db8::53]", `"[2001:db8::53]"` + notResolver},
+		{
+			reputationAction, "ban",
+			`"ban" is not deny, limit:<percent> such as limit:25, or log`,
+		},
+		{reputationCacheTTL, off, `"off"` + notAboveZero},
+		{reputationTimeout, "0s", `"0s"` + notAboveZero},
+	} {
+		t.Run(tc.name+"="+tc.value, func(t *testing.T) {
+			t.Parallel()
+
+			_, err := config.FromEnvironment(environment{tc.name: tc.value}.lookupEnv)
+
+			want := tc.name + ": " + tc.want
+			if err == nil || err.Error() != want {
+				t.Errorf("error %v, want %s", err, want)
+			}
+		})
+	}
+}
+
+func TestMaskZoneKeyMasksTheFirstLabelOfAZoneUnderDqSpamhausNet(t *testing.T) {
+	t.Parallel()
+
+	for zone, want := range map[string]string{
+		spamhaus:                  spamhausMasked,
+		spamhaus + ".":            spamhausMasked + ".",
+		"KEY.ZEN.DQ.SPAMHAUS.NET": "********.ZEN.DQ.SPAMHAUS.NET",
+		dronebl:                   dronebl,
+		"dq.spamhaus.net":         "dq.spamhaus.net",
+		spamhaus + ".example":     spamhaus + ".example",
+	} {
+		if got := config.MaskZoneKey(zone); got != want {
+			t.Errorf("MaskZoneKey(%q) is %q, want %q", zone, got, want)
+		}
+	}
+}
+
+func TestDNSBLZoneKeyIsLoggedMaskedAndNeverShown(t *testing.T) {
+	t.Parallel()
+
+	cfg := fromEnvironment(t, environment{dnsblZones: dronebl + ", " + spamhaus})
+
+	var out bytes.Buffer
+
+	slog.New(slog.NewJSONHandler(&out, nil)).Info("starting", "settings", cfg)
+
+	logged := out.String()
+	if strings.Contains(logged, spamhausKey) ||
+		!strings.Contains(logged, `"`+dnsblZones+`":"`+dronebl+","+spamhausMasked+`"`) {
+		t.Errorf("the zones are not logged with the key masked: %s", logged)
+	}
+
+	// Nor does an error that stops the start show a key, in any case.
+	const (
+		notZone   = " is not a DNS zone such as dnsbl.dronebl.org"
+		otherKey  = "zyxwvutsrqponmlkjihgfedcba"
+		otherZone = otherKey + ".xbl.dq.spamhaus.net"
+	)
+
+	// 205 characters, 187 with the key masked.
+	labels := strings.Repeat("a", 63) + "." + strings.Repeat("b", 63) + "." +
+		strings.Repeat("c", 30) + ".xbl.dq.spamhaus.net"
+
+	for _, tc := range []struct{ value, want string }{
+		{spamhaus + ".", `"` + spamhausMasked + `."` + notZone},
+		{spamhausKey + "_.xbl.dq.spamhaus.net", `"` + spamhausMasked + `"` + notZone},
+		{
+			spamhausKey + "." + labels,
+			`"********.` + labels + `" is longer than 189 characters, too long ` +
+				`for the names IPv6 clients are asked about by`,
+		},
+		{
+			spamhaus + "," + strings.ToUpper(spamhaus),
+			`"********.XBL.DQ.SPAMHAUS.NET" is listed twice`,
+		},
+		{spamhaus + "," + otherZone, `"` + spamhausMasked + `" is listed twice`},
+		{spamhaus + ",,", "has an empty item in its list"},
+	} {
+		_, err := config.FromEnvironment(environment{dnsblZones: tc.value}.lookupEnv)
+
+		want := dnsblZones + ": " + tc.want
+		if err == nil || err.Error() != want {
+			t.Errorf("%s=%s gave the error %v, want %s", dnsblZones, tc.value, err, want)
+		}
+	}
+}
+
+func TestAbuseIPDBSettingsAsSet(t *testing.T) {
+	t.Parallel()
+
+	cfg := fromEnvironment(t, environment{})
+	if cfg.AbuseIPDBKey != "" || cfg.AbuseIPDBMinScore != 75 ||
+		cfg.AbuseIPDBDailyBudget != 900 {
+		t.Errorf("by default, the key %q, the minimum score %d and the daily budget %d, "+
+			"want none, 75 and 900", cfg.AbuseIPDBKey, cfg.AbuseIPDBMinScore,
+			cfg.AbuseIPDBDailyBudget)
+	}
+
+	cfg = fromEnvironment(t, environment{
+		abuseIPDBKey: token, abuseIPDBMinScore: "0", abuseIPDBDailyBudget: "1",
+	})
+	if cfg.AbuseIPDBKey != token || cfg.AbuseIPDBMinScore != 0 ||
+		cfg.AbuseIPDBDailyBudget != 1 {
+		t.Errorf("set, the key %q, the minimum score %d and the daily budget %d, "+
+			"want %s, 0 and 1", cfg.AbuseIPDBKey, cfg.AbuseIPDBMinScore,
+			cfg.AbuseIPDBDailyBudget, token)
+	}
+}
+
+func TestInvalidAbuseIPDBSettingStopsTheStartSayingWhatIsWrong(t *testing.T) {
+	t.Parallel()
+
+	const (
+		notScore  = " is not a percentage, a whole number from 0 to 100"
+		notBudget = " is not a whole number above zero, such as 5000"
+	)
+
+	for _, tc := range []struct{ name, value, want string }{
+		{abuseIPDBMinScore, "101", `"101"` + notScore},
+		{abuseIPDBMinScore, off, `"off"` + notScore},
+		{abuseIPDBDailyBudget, "0", `"0"` + notBudget},
+		{abuseIPDBDailyBudget, off, `"off"` + notBudget},
+		// The key itself is never shown.
+		{
+			abuseIPDBKey, token + "\r",
+			"holds a control character, such as the carriage return of a Windows line end",
+		},
+	} {
+		t.Run(tc.name+"="+tc.value, func(t *testing.T) {
+			t.Parallel()
+
+			_, err := config.FromEnvironment(environment{tc.name: tc.value}.lookupEnv)
+
+			want := tc.name + ": " + tc.want
+			if err == nil || err.Error() != want {
+				t.Errorf("error %v, want %s", err, want)
+			}
+		})
+	}
+}
+
+func TestAbuseIPDBKeyIsLoggedMasked(t *testing.T) {
+	t.Parallel()
+
+	cfg := fromEnvironment(t, environment{abuseIPDBKey: token})
+
+	var out bytes.Buffer
+
+	slog.New(slog.NewJSONHandler(&out, nil)).Info("starting", "settings", cfg)
+
+	logged := out.String()
+	if strings.Contains(logged, token) ||
+		!strings.Contains(logged, `"`+abuseIPDBKey+`":"********"`) {
+		t.Errorf("the key is not logged masked: %s", logged)
+	}
+}
+
 func TestSizesAndOff(t *testing.T) {
 	t.Parallel()
 
@@ -1304,6 +1752,10 @@ func TestInvalidValueStopsTheStart(t *testing.T) {
 		{trustedProxies, "traefik"},
 		{trustedProxies, "10.0.0.0/8,,192.168.0.0/16"},
 		{trustedProxies, "fe80::1%eth0"},
+		{ipv6GroupPrefix, "31"}, {ipv6GroupPrefix, "129"}, {ipv6GroupPrefix, "/64"},
+		{ipv6GroupPrefix, off}, {ipv6GroupPrefix, ""},
+		{maxTrackedClients, "0"}, {maxTrackedClients, "-1"}, {maxTrackedClients, off},
+		{maxTrackedClients, "20K"},
 		{allowNets, "192.0.2.0/24,monitoring"},
 		{rateLimitExemptNets, "2001:db8::/129"},
 		{denyNets, "198.51.100.0/24,"},
@@ -1357,6 +1809,7 @@ func TestInvalidValueStopsTheStart(t *testing.T) {
 		{logRequestHeaders, "accept language"}, {logRequestHeaders, "x-foo:"},
 		{logRequestHeaders, "host"}, {logRequestHeaders, "accept,Host"},
 		{logRequestHeaders, "transfer-encoding"}, {logRequestHeaders, "TRANSFER-ENCODING"},
+		{logLevel, "INFO"}, {logLevel, "warning"}, {logLevel, "trace"}, {logLevel, ""},
 		{rulesEnabled, "yes"}, {rulesEnabled, "True"},
 	})
 }
@@ -1587,6 +2040,7 @@ func writeFile(t *testing.T, contents string) string {
 	return path
 }
 
+//nolint:funlen // one line for each setting, a list that grows with them
 func TestLogsEachSettingWithItsValue(t *testing.T) {
 	t.Parallel()
 
@@ -1598,6 +2052,8 @@ func TestLogsEachSettingWithItsValue(t *testing.T) {
 		upstreamURL:             "http://127.0.0.1:8081",
 		mode:                    "enforce",
 		trustedProxies:          "10.0.0.0/8,172.16.0.0/12,192.168.0.0/16",
+		ipv6GroupPrefix:         "64",
+		maxTrackedClients:       "20000",
 		clientRequestTimeout:    "45s",
 		clientHeaderMaxBytes:    "32K",
 		clientIdleTimeout:       "120s",
@@ -1628,6 +2084,18 @@ func TestLogsEachSettingWithItsValue(t *testing.T) {
 		asnBytesPercent:         "",
 		countryBytesPercent:     "",
 		unknownLimitPercent:     "100",
+		asnLimitPercentURL:      "",
+		blocklistURLs:           "",
+		blocklistRefresh:        "24h",
+		blocklistAction:         actionDeny,
+		dnsblZones:              "",
+		dnsblResolver:           "",
+		abuseIPDBKey:            "",
+		abuseIPDBMinScore:       "75",
+		abuseIPDBDailyBudget:    "900",
+		reputationAction:        "limit:25",
+		reputationCacheTTL:      defaultReputationCacheTTL,
+		reputationTimeout:       "2s",
 		banResponse:             "403",
 		limitBanDuration:        "1h",
 		limitBanRepeatWindow:    "24h",
@@ -1643,6 +2111,7 @@ func TestLogsEachSettingWithItsValue(t *testing.T) {
 		metricsTopN:             "50",
 		instanceName:            hostname,
 		logRequestHeaders:       defaultLogRequestHeaders,
+		logLevel:                "info",
 		rulesDir:                "/etc/smallwebwaf/rules.d",
 		rulesEnabled:            "true",
 		logRemoteURL:            "",

internal/lookup/lookup.go

@@ -176,7 +176,8 @@ func New(params Params) *GeoJS {
 // when it ends.
 //
 // GeoJS is asked about the client's first address, which is the client's
-// own address for IPv4, and an address in the same place for an IPv6 /64.
+// own address for IPv4, and an address in the same place for an IPv6
+// netblock.
 func (g *GeoJS) LookUp(ctx context.Context, client netip.Prefix) Answer {
 	answer, asked := g.answerOrWait(ctx, client)
 	if asked == nil {

internal/metrics/metrics.go

@@ -14,8 +14,10 @@ import (
 	"github.com/prometheus/client_golang/prometheus/promhttp"
 	"sneak.berlin/go/smallwebwaf/internal/alerts"
 	"sneak.berlin/go/smallwebwaf/internal/bans"
+	"sneak.berlin/go/smallwebwaf/internal/config"
 	"sneak.berlin/go/smallwebwaf/internal/ratelimit"
 	"sneak.berlin/go/smallwebwaf/internal/remotelog"
+	"sneak.berlin/go/smallwebwaf/internal/reputation"
 	"sneak.berlin/go/smallwebwaf/internal/requestlog"
 	"sneak.berlin/go/smallwebwaf/internal/rules"
 )
@@ -35,10 +37,12 @@ type Metrics struct {
 	rateLimitHits        *prometheus.CounterVec
 	sizeAndTimeLimitHits *prometheus.CounterVec
 	offences             *prometheus.CounterVec
-	// ruleMatches are made by AddRules.
+	// ruleMatches are made by AddRules, and reputationHits by
-	ruleMatches *prometheus.CounterVec
+	// AddReputation.
-	countries   *busiest
+	ruleMatches    *prometheus.CounterVec
-	asns        *busiest
+	reputationHits *prometheus.CounterVec
+	countries      *busiest
+	asns           *busiest
 
 	// GeoJSRequests are the requests to GeoJS, and GeoJSFailures those
 	// that failed. GeoJSUnanswered are the requests that needed their
@@ -253,6 +257,80 @@ func (m *Metrics) AddLookupFile(lastRead func() time.Time, readFailures func() i
 	)
 }
 
+// sourceLabel is the label of the reputation metrics: a list's URL, a
+// DNSBL zone, its key masked, or abuseipdb.
+const sourceLabel = "source"
+
+// AddReputation adds the metrics of the lists fetched from URLs and of the
+// DNSBL zones, by source, each list's URL or each zone, its key masked as
+// config.MaskZoneKey masks it: the requests whose client a blocklist, a
+// zone's verdict or AbuseIPDB's score lists, which ReputationHit counts,
+// and, read from lists and dnsbl as the metrics are asked for, for a list,
+// the fetches that failed and when the copy in use was fetched, and for a
+// zone, the queries made and those that failed. It is called once, before
+// ReputationHit.
+func (m *Metrics) AddReputation(lists *reputation.Lists, dnsbl *reputation.DNSBL) {
+	m.reputationHits = counterVec("smallwebwaf_reputation_hits_total",
+		"Requests whose client a blocklist, a DNSBL zone or AbuseIPDB lists, by "+
+			"the blocklist's URL, the zone, or abuseipdb.",
+		[]string{sourceLabel})
+	m.registry.MustRegister(m.reputationHits)
+
+	for _, zone := range dnsbl.Zones() {
+		source := prometheus.Labels{sourceLabel: config.MaskZoneKey(zone)}
+
+		m.addReputationQueries(source, func() int { return dnsbl.Queries(zone) })
+		m.addReputationFailures(source, func() int { return dnsbl.Failures(zone) })
+	}
+
+	for _, listURL := range lists.URLs() {
+		source := prometheus.Labels{sourceLabel: listURL}
+
+		m.addReputationFailures(source, func() int { return lists.Failures(listURL) })
+		m.registry.MustRegister(
+			prometheus.NewGaugeFunc(prometheus.GaugeOpts{
+				Name: "smallwebwaf_reputation_last_fetch_timestamp_seconds",
+				Help: "When the copy of the list in use was fetched, in seconds since " +
+					"1970, or 0 while there is none.",
+				ConstLabels: source,
+			}, func() float64 {
+				fetched := lists.Fetched(listURL)
+				if fetched.IsZero() {
+					return 0
+				}
+
+				return float64(fetched.Unix())
+			}),
+		)
+	}
+}
+
+// AddAbuseIPDB adds the metrics of AbuseIPDB, with the source abuseipdb,
+// read from abuseIPDB as the metrics are asked for: the checks made, those
+// that failed, and how many checks the day's budget has left. It is
+// called once, after AddReputation, while SWWAF_ABUSEIPDB_KEY is set.
+func (m *Metrics) AddAbuseIPDB(abuseIPDB *reputation.AbuseIPDB) {
+	source := prometheus.Labels{sourceLabel: reputation.AbuseIPDBSource}
+
+	m.addReputationQueries(source, abuseIPDB.Checked)
+	m.addReputationFailures(source, abuseIPDB.Failures)
+	m.registry.MustRegister(
+		prometheus.NewGaugeFunc(prometheus.GaugeOpts{
+			Name:        "smallwebwaf_reputation_daily_budget_remaining",
+			Help:        "Checks of the day's SWWAF_ABUSEIPDB_DAILY_BUDGET not yet spent.",
+			ConstLabels: source,
+		}, func() float64 {
+			return float64(abuseIPDB.BudgetLeft())
+		}),
+	)
+}
+
+// ReputationHit counts a request whose client source lists: a blocklist,
+// by its URL, a DNSBL zone, its key masked, or AbuseIPDB, abuseipdb.
+func (m *Metrics) ReputationHit(source string) {
+	m.reputationHits.WithLabelValues(source).Inc()
+}
+
 // AddAlerts adds the metrics of the alerts sent to each destination set,
 // read from queue as the metrics are asked for, by destination: the
 // alerts sent, the requests to the destination that failed, the alerts
@@ -392,6 +470,32 @@ func (m *Metrics) StateFileEditSetAside(name string) {
 	m.stateFileEditsSetAside.WithLabelValues(name).Inc()
 }
 
+// addReputationQueries adds the counter of the queries to source, a DNSBL
+// zone, or of the checks of clients with AbuseIPDB, which count tells.
+func (m *Metrics) addReputationQueries(source prometheus.Labels, count func() int) {
+	m.registry.MustRegister(prometheus.NewCounterFunc(prometheus.CounterOpts{
+		Name:        "smallwebwaf_reputation_queries_total",
+		Help:        "Queries to the DNSBL zone, or checks of clients with AbuseIPDB.",
+		ConstLabels: source,
+	}, func() float64 {
+		return float64(count())
+	}))
+}
+
+// addReputationFailures adds the counter of the fetches of source, a
+// list, the queries to it, a DNSBL zone, or the checks with it, AbuseIPDB,
+// that failed, which count tells.
+func (m *Metrics) addReputationFailures(source prometheus.Labels, count func() int) {
+	m.registry.MustRegister(prometheus.NewCounterFunc(prometheus.CounterOpts{
+		Name: "smallwebwaf_reputation_failures_total",
+		Help: "Fetches of the list, queries to the DNSBL zone, or checks with " +
+			"AbuseIPDB, that failed.",
+		ConstLabels: source,
+	}, func() float64 {
+		return float64(count())
+	}))
+}
+
 // statusClass returns the class of status, such as 2xx, or none when no
 // status was sent.
 func statusClass(status int) string {

internal/proxy/admin.go

@@ -282,7 +282,7 @@ func (rq *request) showClient() {
 
 	answer := clientAnswer{Bans: state.BanEntries(rq.h.ledger.Covering(addr))}
 
-	client, seen := rq.h.limiter.Client(clientGroup(addr))
+	client, seen := rq.h.limiter.Client(rq.h.clientGroup(addr))
 	if seen {
 		answer.Client = &client
 	}

internal/proxy/admin_test.go

@@ -4,7 +4,7 @@ import (
 	"encoding/json"
 	"net/http"
 	"net/netip"
-	"slices"
+	"reflect"
 	"strconv"
 	"strings"
 	"testing"
@@ -48,7 +48,7 @@ func TestAdminEndpointsAreOffWhileTheTokenIsUnset(t *testing.T) {
 		}
 	}
 
-	if after := server.Ledger.Snapshot(); !slices.Equal(after, before) {
+	if after := server.Ledger.Snapshot(); !reflect.DeepEqual(after, before) {
 		t.Errorf("the bans are now\n%+v\nwant them unchanged\n%+v", after, before)
 	}
 }
@@ -79,7 +79,7 @@ func TestAdminEndpointsNeedTheAdminToken(t *testing.T) {
 			}
 		}
 
-		if after := server.Ledger.Snapshot(); !slices.Equal(after, before) {
+		if after := server.Ledger.Snapshot(); !reflect.DeepEqual(after, before) {
 			t.Errorf("%s %s without the token changed the bans to\n%+v\nfrom\n%+v",
 				e.method, e.path, after, before)
 		}

internal/proxy/alerts_test.go

@@ -118,7 +118,8 @@ func TestObserveModeRaisesTheBanAlertsItWouldHave(t *testing.T) {
 	line := s.get(ipv6Client, http.StatusOK, requestlog.ActionForward)
 
 	// No ban is made, and none made permanent.
-	if held := server.Ledger.Snapshot(); len(held) != 1 || held[0] != attackBan ||
+	held := server.Ledger.Snapshot()
+	if len(held) != 1 || !reflect.DeepEqual(held[0], attackBan) ||
 		line.BanExpires != requestlog.FormatTime(attackBan.Expires) {
 		t.Errorf("the ledger holds %+v, and the log line gives %s, want the ban "+
 			"for the attack alone, as it was", held, line.BanExpires)

internal/proxy/bans.go

@@ -45,7 +45,7 @@ func (rq *request) banned(now time.Time) bool {
 // the client over a rate limit, as its limit percentage lowers it, which
 // breaks it.
 func (rq *request) limitBroken(now time.Time) bool {
-	counts, hit, over := rq.h.limiter.Count(clientGroup(rq.client), now,
+	counts, hit, over := rq.h.limiter.Count(rq.h.clientGroup(rq.client), now,
 		rq.limitPercent.percent)
 	rq.line.Counts = counts
 
@@ -71,7 +71,7 @@ func (rq *request) countBytes() {
 
 	now := rq.h.now()
 
-	counts, hit, over := rq.h.limiter.CountBytes(clientGroup(rq.client), now,
+	counts, hit, over := rq.h.limiter.CountBytes(rq.h.clientGroup(rq.client), now,
 		rq.countedBytes(), rq.bytesPercent.percent)
 	rq.line.Counts.MinuteBytes = counts.MinuteBytes
 	rq.line.Counts.HourBytes = counts.HourBytes
@@ -127,15 +127,16 @@ func (rq *request) banForLimit(now time.Time, hit ratelimit.Hit, status int) {
 	}
 
 	notes := bans.Notes{
-		ASN:      rq.line.ASN,
+		ASN:        rq.line.ASN,
-		ASName:   rq.line.ASName,
+		ASName:     rq.line.ASName,
-		Country:  rq.line.Country,
+		Country:    rq.line.Country,
-		Kind:     hit.Kind,
+		Kind:       hit.Kind,
-		Limit:    hit.Limit,
+		Limit:      hit.Limit,
-		Window:   hit.Window,
+		Window:     hit.Window,
-		Count:    hit.Count,
+		Count:      hit.Count,
-		Request:  rq.noted(now, status),
+		Reputation: rq.reputation,
-		Requests: rq.netblockRequests(netblock),
+		Request:    rq.noted(now, status),
+		Requests:   rq.netblockRequests(netblock),
 	}
 
 	percent := rq.limitPercent
@@ -155,7 +156,7 @@ func (rq *request) banForLimit(now time.Time, hit ratelimit.Hit, status int) {
 	}
 
 	ban, made := rq.h.ledger.BanForLimit(netblock, now, notes)
-	rq.h.limiter.Reset(clientGroup(rq.client))
+	rq.h.limiter.Reset(rq.h.clientGroup(rq.client))
 	rq.line.BanExpires = banExpires(ban)
 
 	if made {
@@ -174,13 +175,14 @@ func (rq *request) banForAttack(now time.Time, rule rules.Rule) {
 	}
 
 	notes := bans.Notes{
-		ASN:      rq.line.ASN,
+		ASN:        rq.line.ASN,
-		ASName:   rq.line.ASName,
+		ASName:     rq.line.ASName,
-		Country:  rq.line.Country,
+		Country:    rq.line.Country,
-		RuleID:   rule.ID,
+		RuleID:     rule.ID,
-		Target:   rule.Target,
+		Target:     rule.Target,
-		Request:  rq.noted(now, rq.h.config.BanResponse),
+		Reputation: rq.reputation,
-		Requests: rq.netblockRequests(netblock),
+		Request:    rq.noted(now, rq.h.config.BanResponse),
+		Requests:   rq.netblockRequests(netblock),
 	}
 
 	if rq.h.config.Observe {
@@ -276,7 +278,7 @@ func (h *handler) netblock(client netip.Addr) netip.Prefix {
 		return netip.PrefixFrom(addr, h.config.BanScopeV4Prefix).Masked()
 	}
 
-	return clientGroup(addr)
+	return h.clientGroup(addr)
 }
 
 // banExpires is when ban ends, as the log line gives it: a time, or

internal/proxy/bans_test.go

@@ -7,6 +7,7 @@ import (
 	"maps"
 	"net/http"
 	"net/netip"
+	"reflect"
 	"slices"
 	"sync"
 	"testing"
@@ -165,9 +166,14 @@ func TestBanCoversTheClientsNetblock(t *testing.T) {
 			[]string{otherClient, exempt}, []string{"203.0.112.9", allowed},
 		},
 		{
-			"an IPv6 /64", nil, "2001:db8:5::1",
+			"an IPv6 /64, by default", nil, "2001:db8:5::1",
 			[]string{"2001:db8:5::ffff:1"}, []string{"2001:db8:5:1::1"},
 		},
+		{
+			"the IPv6 netblock SWWAF_IPV6_GROUP_PREFIX sets",
+			map[string]string{ipv6GroupPrefix: "48"}, "2001:db8:7::1",
+			[]string{"2001:db8:7:ffff::1"}, []string{"2001:db8:8::1"},
+		},
 	} {
 		t.Run(tc.name, func(t *testing.T) {
 			t.Parallel()
@@ -307,7 +313,7 @@ func TestBanNotes(t *testing.T) {
 	ledger := server.Ledger
 
 	got := ledger.Bans(netblock)
-	if len(got) != 1 || got[0] != want {
+	if len(got) != 1 || !reflect.DeepEqual(got[0], want) {
 		t.Fatalf("bans\n%+v\nwant\n%+v", got, want)
 	}
 

internal/proxy/biased.go

@@ -17,33 +17,56 @@ type percentage struct {
 }
 
 // biasedThresholdsSet reports whether a biased threshold can lower a
-// client's limits: one of its lists is not empty, or
+// client's limits: one of its lists is not empty,
-// SWWAF_UNKNOWN_LIMIT_PERCENT is below 100. The client's lookup is then
+// SWWAF_UNKNOWN_LIMIT_PERCENT is below 100, or SWWAF_ASN_LIMIT_PERCENT_URL
-// needed before its request goes on.
+// is set. The client's lookup is then needed before its request goes on.
 func biasedThresholdsSet(cfg *config.Config) bool {
 	return len(cfg.ASNLimitPercent) > 0 || len(cfg.CountryLimitPercent) > 0 ||
 		len(cfg.ASNBytesPercent) > 0 || len(cfg.CountryBytesPercent) > 0 ||
-		cfg.UnknownLimitPercent < whole
+		cfg.UnknownLimitPercent < whole || cfg.ASNLimitPercentURL != ""
 }
 
-// limitPercentages returns a client's limit percentages, for the rate
+// limitPercentages returns the client's limit percentages, for the rate
 // limits and for the byte limits, by its AS number and country as looked
-// up, each "" when unknown. Each is the lowest of those the settings give
+// up, each "" when unknown, and the blocklists, DNSBL zones and AbuseIPDB
-// it, the first of them in the order below when several are lowest: the
+// that list it. Each is the lowest of those the settings give it, the
-// percentage SWWAF_ASN_LIMIT_PERCENT gives its AS number, the one
+// first of them in the order below when several are lowest: the
-// SWWAF_COUNTRY_LIMIT_PERCENT gives its country, and, for a client
+// percentage SWWAF_ASN_LIMIT_PERCENT gives its AS number, the one the file
-// without a country, SWWAF_UNKNOWN_LIMIT_PERCENT. For the byte limits,
+// SWWAF_ASN_LIMIT_PERCENT_URL names gives it, the one
-// SWWAF_ASN_BYTES_PERCENT and SWWAF_COUNTRY_BYTES_PERCENT take the place
+// SWWAF_COUNTRY_LIMIT_PERCENT gives its country, for a client without a
-// of the first two for an AS number or a country they list.
+// country, SWWAF_UNKNOWN_LIMIT_PERCENT, for a client a blocklist lists,
-func limitPercentages(
+// the percentage of SWWAF_BLOCKLIST_ACTION while it is limit, and for a
-	cfg *config.Config, asn, country string,
+// client a DNSBL zone's verdict lists, or whose AbuseIPDB score is a hit,
-) (percentage, percentage) {
+// the percentage of SWWAF_REPUTATION_ACTION while it is limit. For the
+// byte limits, SWWAF_ASN_BYTES_PERCENT and SWWAF_COUNTRY_BYTES_PERCENT
+// take the place of the first three for an AS number or a country they
+// list.
+func (rq *request) limitPercentages() (percentage, percentage) {
+	cfg := rq.h.config
+	asn, country := rq.line.ASN, rq.line.Country
+
 	unknown := percentage{percent: whole}
 	if country == "" {
 		unknown = percentage{cfg.UnknownLimitPercent, "SWWAF_UNKNOWN_LIMIT_PERCENT"}
 	}
 
-	asnRequests := given(cfg.ASNLimitPercent, asn, "SWWAF_ASN_LIMIT_PERCENT")
+	fetched := percentage{percent: whole}
+	if percent, listed := rq.h.lists.ASNLimitPercent(asn); listed {
+		fetched = percentage{percent, "SWWAF_ASN_LIMIT_PERCENT_URL"}
+	}
+
+	blocklisted := percentage{percent: whole}
+	if rq.blocklisted && cfg.BlocklistAction == "limit" {
+		blocklisted = percentage{cfg.BlocklistLimitPercent, "SWWAF_BLOCKLIST_ACTION"}
+	}
+
+	reputationListed := percentage{percent: whole}
+	if (rq.dnsblListed || rq.abuseIPDBHit) && cfg.ReputationAction == "limit" {
+		reputationListed = percentage{cfg.ReputationLimitPercent, "SWWAF_REPUTATION_ACTION"}
+	}
+
+	asnRequests := lowest(given(cfg.ASNLimitPercent, asn, "SWWAF_ASN_LIMIT_PERCENT"),
+		fetched)
 	countryRequests := given(cfg.CountryLimitPercent, country,
 		"SWWAF_COUNTRY_LIMIT_PERCENT")
 
@@ -56,8 +79,8 @@ func limitPercentages(
 		countryBytes = given(cfg.CountryBytesPercent, country, "SWWAF_COUNTRY_BYTES_PERCENT")
 	}
 
-	return lowest(asnRequests, countryRequests, unknown),
+	return lowest(asnRequests, countryRequests, unknown, blocklisted, reputationListed),
-		lowest(asnBytes, countryBytes, unknown)
+		lowest(asnBytes, countryBytes, unknown, blocklisted, reputationListed)
 }
 
 // given returns the percentage percents, the setting named setting, gives

internal/proxy/biased_test.go

@@ -310,6 +310,7 @@ func TestRequestWaitsForItsLookupWhileABiasedThresholdIsSet(t *testing.T) {
 		{asnBytesPercent, asnDEHalf, true},
 		{countryBytesPercent, countryDEHalf, true},
 		{unknownLimitPercent, "99", true},
+		{asnLimitPercentURL, asnURL, true},
 		// At 100, its default, it lowers no limit.
 		{unknownLimitPercent, "100", false},
 	} {

internal/proxy/bytelimits_test.go

@@ -6,6 +6,7 @@ import (
 	"net"
 	"net/http"
 	"net/netip"
+	"reflect"
 	"strconv"
 	"strings"
 	"testing"
@@ -337,7 +338,7 @@ func TestBanForABrokenByteLimitHasItsNotesAndItsAlert(t *testing.T) {
 	}
 
 	got := server.Ledger.Bans(netblock)
-	if len(got) != 1 || got[0] != want {
+	if len(got) != 1 || !reflect.DeepEqual(got[0], want) {
 		t.Fatalf("bans\n%+v\nwant\n%+v", got, want)
 	}
 

internal/proxy/client.go

@@ -76,16 +76,14 @@ func scheme(r *http.Request, peerTrusted bool) string {
 	return proto
 }
 
-// ipv6GroupPrefix is the length of the IPv6 netblock that is one client.
-const ipv6GroupPrefix = 64
-
 // clientGroup is the client a request is counted toward: its IPv4
-// address, or the /64 its IPv6 address is in, since one abuser usually
+// address, or its IPv6 group, the netblock its IPv6 address is in of the
-// holds a whole /64. An IPv4 address in IPv6 form counts as IPv4.
+// length SWWAF_IPV6_GROUP_PREFIX sets, a /64 by default, since one abuser
-func clientGroup(addr netip.Addr) netip.Prefix {
+// usually holds a whole /64. An IPv4 address in IPv6 form counts as IPv4.
+func (h *handler) clientGroup(addr netip.Addr) netip.Prefix {
 	addr = addr.Unmap()
 	if addr.Is6() {
-		return netip.PrefixFrom(addr, ipv6GroupPrefix).Masked()
+		return netip.PrefixFrom(addr, h.config.IPv6GroupPrefix).Masked()
 	}
 
 	return netip.PrefixFrom(addr, addr.BitLen())

internal/proxy/history_test.go

@@ -56,6 +56,24 @@ func TestHistoryKeepsEachRequestOfTheClient(t *testing.T) {
 	}
 }
 
+func TestTableOfClientsHoldsAtMostMaxTrackedClients(t *testing.T) {
+	t.Parallel()
+
+	s, _, server := startWithClock(t, "", map[string]string{maxTrackedClients: "2"})
+
+	// The third client drops the least recently seen, the first, with its
+	// history.
+	for _, from := range []string{"192.0.2.1", "192.0.2.2", "192.0.2.3"} {
+		s.get(from, http.StatusOK, requestlog.ActionForward)
+	}
+
+	_, held := server.Limiter.Client(netip.MustParsePrefix("192.0.2.1/32"))
+	if server.Limiter.Len() != 2 || held {
+		t.Errorf("the table holds %d clients, the first among them: %t; want 2, "+
+			"without it", server.Limiter.Len(), held)
+	}
+}
+
 func TestHistoryCountsTheBodiesEachWay(t *testing.T) {
 	t.Parallel()
 

internal/proxy/lookup.go

@@ -31,9 +31,9 @@ func (rq *request) lookUp(ctx context.Context) {
 	}
 
 	if rq.h.config.LookupSource == "file" {
-		rq.lookupAnswer = rq.h.lookupFile.LookUp(clientGroup(rq.client))
+		rq.lookupAnswer = rq.h.lookupFile.LookUp(rq.h.clientGroup(rq.client))
 	} else {
-		rq.lookupAnswer = rq.h.geojs.LookUp(ctx, clientGroup(rq.client))
+		rq.lookupAnswer = rq.h.geojs.LookUp(ctx, rq.h.clientGroup(rq.client))
 	}
 
 	rq.lookedUp = true

internal/proxy/lookup_test.go

@@ -349,6 +349,7 @@ const unansweredGeoJSURL = "unanswered://geojs/v1/ip/geo.json"
 func TestMain(m *testing.M) {
 	transport, _ := http.DefaultTransport.(*http.Transport)
 	transport.RegisterProtocol("unanswered", unansweredGeoJS{})
+	transport.RegisterProtocol("abuseipdb", abuseIPDBStandIn{})
 
 	m.Run()
 }

internal/proxy/observe_test.go

@@ -5,6 +5,7 @@ import (
 	"io"
 	"net/http"
 	"net/netip"
+	"reflect"
 	"sync/atomic"
 	"testing"
 	"time"
@@ -126,7 +127,7 @@ func TestObserveModeMakesNoBanAndKeepsTheBansItHas(t *testing.T) {
 	}
 
 	got := server.Ledger.Snapshot()
-	if len(got) != 1 || got[0] != kept {
+	if len(got) != 1 || !reflect.DeepEqual(got[0], kept) {
 		t.Errorf("bans\n%+v\nwant only\n%+v", got, kept)
 	}
 }

internal/proxy/passthrough_test.go

@@ -320,7 +320,7 @@ func TestServerHasTheDefaultLimits(t *testing.T) {
 	server := proxy.New(proxy.Params{
 		Config:     cfg,
 		RequestLog: io.Discard,
-		ProcessLog: requestlog.NewProcessLogger(io.Discard, cfg.InstanceName),
+		ProcessLog: requestlog.NewProcessLogger(io.Discard, cfg.InstanceName, cfg.LogLevel),
 	})
 
 	if server.Addr != ":8080" || server.MaxHeaderBytes != 28<<10 ||
@@ -399,6 +399,25 @@ func TestAnswers502WhenTheAppCannotBeReached(t *testing.T) {
 	}
 }
 
+func TestLogLevelHoldsBackNoRequestLine(t *testing.T) {
+	t.Parallel()
+
+	// At error the warning that the request to the app failed is held back,
+	// and is written before the answer is.
+	addr, out := startProxy(t, "http://"+localhost+":1", map[string]string{
+		"SWWAF_LOG_LEVEL": "error",
+	})
+
+	wantStatus(t, get(t, addr, "/"), http.StatusBadGateway)
+	wantLine(t, out.requestLine(t), http.StatusBadGateway, requestlog.ActionUpstreamError)
+
+	for _, line := range out.lines(t) {
+		if line["type"] == "process" {
+			t.Errorf("process line %v, want none at error", line)
+		}
+	}
+}
+
 func TestLogsAnAnswerThatBrokeOff(t *testing.T) {
 	t.Parallel()
 

internal/proxy/proxy.go

@@ -18,6 +18,7 @@ import (
 	"sneak.berlin/go/smallwebwaf/internal/lookup"
 	"sneak.berlin/go/smallwebwaf/internal/metrics"
 	"sneak.berlin/go/smallwebwaf/internal/ratelimit"
+	"sneak.berlin/go/smallwebwaf/internal/reputation"
 	"sneak.berlin/go/smallwebwaf/internal/requestlog"
 	"sneak.berlin/go/smallwebwaf/internal/rules"
 )
@@ -58,6 +59,9 @@ type Params struct {
 	// GeoJSURL is where clients' AS numbers and countries are looked up
 	// while SWWAF_LOOKUP_SOURCE is geojs, normally lookup.URL.
 	GeoJSURL string
+	// AbuseIPDBURL is where clients are checked with AbuseIPDB while
+	// SWWAF_ABUSEIPDB_KEY is set, normally reputation.AbuseIPDBURL.
+	AbuseIPDBURL string
 	// LookupFile is the lookup database they are looked up in while
 	// SWWAF_LOOKUP_SOURCE is file, and nil otherwise.
 	LookupFile *lookup.File
@@ -69,14 +73,18 @@ type Params struct {
 	// against.
 	Rules *rules.Files
 	// Alerts receive the alert for each ban the proxy makes or makes
-	// permanent, for each count over an anomaly threshold, and for GeoJS
+	// permanent, for each count over an anomaly threshold, for each request
-	// failing.
+	// whose client a blocklist, a DNSBL zone or AbuseIPDB lists, and for
+	// GeoJS failing, a fetch of a list failing, a query to a DNSBL zone or
+	// a check with AbuseIPDB failing, or the day's AbuseIPDB checks used up.
 	Alerts *alerts.Queue
 }
 
 // Server is the server smallwebwaf runs, with the parts of the proxy
 // whose state the state files keep, the lookup database, nil unless
-// SWWAF_LOOKUP_SOURCE is file, and the metrics.
+// SWWAF_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.
 type Server struct {
 	*http.Server
 
@@ -85,6 +93,9 @@ type Server struct {
 	GeoJS      *lookup.GeoJS
 	Anomalies  *anomaly.Counters
 	LookupFile *lookup.File
+	Lists      *reputation.Lists
+	DNSBL      *reputation.DNSBL
+	AbuseIPDB  *reputation.AbuseIPDB
 	Metrics    *metrics.Metrics
 }
 
@@ -97,6 +108,7 @@ type Server struct {
 func New(params Params) *Server {
 	errorLog := slog.NewLogLogger(params.ProcessLog.Handler(), slog.LevelWarn)
 	m := metrics.New(params.Config.MetricsTopN, params.Config.InstanceName)
+	lists, dnsbl, abuseIPDB := newReputation(params, m)
 	h := &handler{
 		config:     params.Config,
 		requestLog: params.RequestLog,
@@ -112,7 +124,7 @@ func New(params Params) *Server {
 			BytesPerMinute: params.Config.BytesLimitPerMinute,
 			BytesPerHour:   params.Config.BytesLimitPerHour,
 			BytesPerDay:    params.Config.BytesLimitPerDay,
-		}),
+		}, params.Config.MaxTrackedClients),
 		ledger: bans.New(bans.Rules{
 			LimitBanDuration:     params.Config.LimitBanDuration,
 			LimitBanRepeatWindow: params.Config.LimitBanRepeatWindow,
@@ -132,6 +144,9 @@ func New(params Params) *Server {
 			Alerts:         params.Alerts,
 		}),
 		lookupFile: params.LookupFile,
+		lists:      lists,
+		dnsbl:      dnsbl,
+		abuseIPDB:  abuseIPDB,
 		rules:      params.Rules,
 		alerts:     params.Alerts,
 	}
@@ -170,10 +185,47 @@ func New(params Params) *Server {
 		GeoJS:      h.geojs,
 		Anomalies:  h.anomalies,
 		LookupFile: h.lookupFile,
+		Lists:      h.lists,
+		DNSBL:      h.dnsbl,
+		AbuseIPDB:  h.abuseIPDB,
 		Metrics:    m,
 	}
 }
 
+// newReputation returns the lists fetched from URLs, the DNSBL zones'
+// verdicts and AbuseIPDB's scores, as the settings in params name them,
+// with none fetched, asked for or checked yet, and adds their metrics to
+// m, AbuseIPDB's while SWWAF_ABUSEIPDB_KEY is set.
+func newReputation(
+	params Params, m *metrics.Metrics,
+) (*reputation.Lists, *reputation.DNSBL, *reputation.AbuseIPDB) {
+	cfg := params.Config
+	lists := reputation.New(reputation.Params{
+		BlocklistURLs: cfg.BlocklistURLs, Refresh: cfg.BlocklistRefresh,
+		ASNLimitPercentURL: cfg.ASNLimitPercentURL, Now: params.Now,
+		ProcessLog: params.ProcessLog, Alerts: params.Alerts,
+	})
+	dnsbl := reputation.NewDNSBL(reputation.DNSBLParams{
+		Zones: cfg.DNSBLZones, Resolver: cfg.DNSBLResolver, CacheTTL: cfg.ReputationCacheTTL,
+		Timeout: cfg.ReputationTimeout, Now: params.Now, ProcessLog: params.ProcessLog,
+		Alerts: params.Alerts,
+	})
+	abuseIPDB := reputation.NewAbuseIPDB(reputation.AbuseIPDBParams{
+		URL: params.AbuseIPDBURL, Key: cfg.AbuseIPDBKey, MinScore: cfg.AbuseIPDBMinScore,
+		DailyBudget: cfg.AbuseIPDBDailyBudget, CacheTTL: cfg.ReputationCacheTTL,
+		Timeout: cfg.ReputationTimeout, Now: params.Now, ProcessLog: params.ProcessLog,
+		Alerts: params.Alerts,
+	})
+
+	m.AddReputation(lists, dnsbl)
+
+	if cfg.AbuseIPDBKey != "" {
+		m.AddAbuseIPDB(abuseIPDB)
+	}
+
+	return lists, dnsbl, abuseIPDB
+}
+
 // handler is the proxy. It holds what every request shares; what belongs
 // to one request is in a request.
 type handler struct {
@@ -189,6 +241,9 @@ type handler struct {
 	geojs      *lookup.GeoJS
 	anomalies  *anomaly.Counters
 	lookupFile *lookup.File
+	lists      *reputation.Lists
+	dnsbl      *reputation.DNSBL
+	abuseIPDB  *reputation.AbuseIPDB
 	rules      *rules.Files
 	alerts     *alerts.Queue
 }

internal/proxy/proxy_test.go

@@ -61,6 +61,8 @@ const (
 	requestMaxBytes         = "SWWAF_REQUEST_MAX_BYTES"
 	responseMaxBytes        = "SWWAF_RESPONSE_MAX_BYTES"
 	trustedProxies          = "SWWAF_TRUSTED_PROXIES"
+	ipv6GroupPrefix         = "SWWAF_IPV6_GROUP_PREFIX"
+	maxTrackedClients       = "SWWAF_MAX_TRACKED_CLIENTS"
 	allowNets               = "SWWAF_ALLOW_NETS"
 	rateLimitExemptNets     = "SWWAF_RATE_LIMIT_EXEMPT_NETS"
 	denyNets                = "SWWAF_DENY_NETS"
@@ -268,7 +270,8 @@ func startProxyWithAlerts(
 // queue: they wait in it, for the test to look at. With no geojsURL, there
 // is no stand-in for GeoJS to look clients up at, and SWWAF_LOOKUP_SOURCE
 // is off unless env sets it. While it is file, the lookup database
-// SWWAF_LOOKUP_DB_PATH names is read.
+// SWWAF_LOOKUP_DB_PATH names is read. Clients are checked with AbuseIPDB
+// at abuseIPDBURL while env sets SWWAF_ABUSEIPDB_KEY.
 func newProxy(
 	t *testing.T, appURL, geojsURL string, now func() time.Time,
 	env map[string]string,
@@ -294,7 +297,7 @@ func newProxy(
 	}
 
 	out := &output{}
-	processLog := requestlog.NewProcessLogger(out, cfg.InstanceName)
+	processLog := requestlog.NewProcessLogger(out, cfg.InstanceName, cfg.LogLevel)
 
 	ruleFiles, err := rules.Load(rules.Params{
 		Dir: cfg.RulesDir, Enabled: cfg.RulesEnabled, ProcessLog: processLog,
@@ -325,14 +328,15 @@ func newProxy(
 	}
 
 	server := proxy.New(proxy.Params{
-		Config:     cfg,
+		Config:       cfg,
-		RequestLog: out,
+		RequestLog:   out,
-		ProcessLog: processLog,
+		ProcessLog:   processLog,
-		GeoJSURL:   geojsURL,
+		GeoJSURL:     geojsURL,
-		LookupFile: lookupFile,
+		AbuseIPDBURL: abuseIPDBURL,
-		Now:        now,
+		LookupFile:   lookupFile,
-		Rules:      ruleFiles,
+		Now:          now,
-		Alerts:     alertQueue,
+		Rules:        ruleFiles,
+		Alerts:       alertQueue,
 	})
 
 	return server, out, alertQueue

internal/proxy/ratelimits_test.go

@@ -72,6 +72,49 @@ func TestRateLimitRefusesBeforeTheApp(t *testing.T) {
 	}
 }
 
+func TestIPv6GroupPrefixSetsTheClientTheLimitsCount(t *testing.T) {
+	t.Parallel()
+
+	// With SWWAF_IPV6_GROUP_PREFIX at 48, the first two addresses, in two
+	// /64s of one /48, are one client, and the second's request breaks the
+	// limit; the third, in the next /48, is another client.
+	const (
+		first  = "2001:db8:9::1"
+		second = "2001:db8:9:1::1"
+		other  = "2001:db8:a::1"
+	)
+
+	for _, tc := range []struct {
+		setting, value string
+		// status and action are those of the request that breaks the
+		// limit: a rate limit refuses it, a byte limit passes it on.
+		status int
+		action string
+	}{
+		{rateLimitPerMinute, "1", http.StatusForbidden, requestlog.ActionRateLimited},
+		{bytesLimitPerMinute, byteLimit, http.StatusOK, requestlog.ActionForward},
+	} {
+		t.Run(tc.setting, func(t *testing.T) {
+			t.Parallel()
+
+			s, _ := startWithAnswers(t, map[string]string{
+				ipv6GroupPrefix: "48", tc.setting: tc.value,
+			})
+
+			s.get(first, http.StatusOK, requestlog.ActionForward)
+
+			line := s.get(second, tc.status, tc.action)
+			if line.ClientGroup != "2001:db8:9::/48" ||
+				line.Offence != requestlog.OffenceLimit {
+				t.Errorf("log line has client_group %q and offence %q, "+
+					"want 2001:db8:9::/48 and limit", line.ClientGroup, line.Offence)
+			}
+
+			s.get(other, http.StatusOK, requestlog.ActionForward)
+		})
+	}
+}
+
 func TestRateLimitExemptPathsAreNeitherCountedNorRefused(t *testing.T) {
 	t.Parallel()
 

internal/proxy/reputation.go

@@ -0,0 +1,104 @@
+package proxy
+
+import (
+	"context"
+
+	"sneak.berlin/go/smallwebwaf/internal/alerts"
+	"sneak.berlin/go/smallwebwaf/internal/bans"
+	"sneak.berlin/go/smallwebwaf/internal/ratelimit"
+	"sneak.berlin/go/smallwebwaf/internal/reputation"
+)
+
+// deny is the SWWAF_BLOCKLIST_ACTION and the SWWAF_REPUTATION_ACTION that
+// refuses the requests of a client a source lists.
+const deny = "deny"
+
+// blocklistDenied notes the blocklists that list the client, as
+// noteListed does, and reports whether SWWAF_BLOCKLIST_ACTION, being deny,
+// refuses the request. Being limit, it lowers the client's limits instead
+// (see limitPercentages), and being log, it does nothing more.
+func (rq *request) blocklistDenied() bool {
+	listedBy := rq.h.lists.ListedBy(rq.client)
+	rq.blocklisted = len(listedBy) > 0
+	rq.noteListed(listedBy, "listed by a blocklist")
+
+	return rq.blocklisted && rq.h.config.BlocklistAction == deny
+}
+
+// dnsblDenied notes the DNSBL zones whose verdict lists the client, as
+// noteListed does, and reports whether SWWAF_REPUTATION_ACTION, being
+// deny, refuses the request. Being limit, it lowers the client's limits
+// instead (see limitPercentages), and being log, it does nothing more. A
+// zone without a verdict on the client is asked about it in the
+// background, and the request does not wait for the answer. ctx is the
+// request's own context.
+func (rq *request) dnsblDenied(ctx context.Context) bool {
+	listedBy := rq.h.dnsbl.ListedBy(ctx, rq.client)
+	rq.dnsblListed = len(listedBy) > 0
+	rq.noteListed(listedBy, "listed by a DNSBL zone")
+
+	return rq.dnsblListed && rq.h.config.ReputationAction == deny
+}
+
+// abuseIPDBDenied notes AbuseIPDB, as noteHit does, with the score, when
+// its score of the client is a hit, and reports whether
+// SWWAF_REPUTATION_ACTION, being deny, refuses the request, as dnsblDenied
+// does for a zone. While SWWAF_ABUSEIPDB_KEY is unset it does nothing. A
+// client without a score is checked in the background, by the request's
+// address, if its history counts an offence, and the request does not
+// wait for the answer. The score is then used for each address of the
+// client. ctx is the request's own context.
+func (rq *request) abuseIPDBDenied(ctx context.Context) bool {
+	if rq.h.config.AbuseIPDBKey == "" {
+		return false
+	}
+
+	client := rq.h.clientGroup(rq.client)
+	held, _ := rq.h.limiter.Client(client)
+	offender := held.History.Offences != ratelimit.Offences{}
+
+	score, hit := rq.h.abuseIPDB.Hit(ctx, client, rq.client, offender)
+	if !hit {
+		return false
+	}
+
+	rq.abuseIPDBHit = true
+	rq.noteHit(bans.ReputationHit{Source: reputation.AbuseIPDBSource, Score: &score},
+		"scored by AbuseIPDB at or over SWWAF_ABUSEIPDB_MIN_SCORE")
+
+	return rq.h.config.ReputationAction == deny
+}
+
+// noteListed notes each of sources, the URLs of the blocklists or the
+// DNSBL zones, their keys masked, that list the client, as noteHit does,
+// with reason.
+func (rq *request) noteListed(sources []string, reason string) {
+	for _, source := range sources {
+		rq.noteHit(bans.ReputationHit{Source: source}, reason)
+	}
+}
+
+// noteHit adds hit's source, which lists the client, to the log line's
+// reputation, and hit to the notes of a ban the request makes, counts the
+// source in the metrics, and raises a reputation_hit alert with reason,
+// whose detail gives hit's source and score.
+func (rq *request) noteHit(hit bans.ReputationHit, reason string) {
+	detail := map[string]any{"source": hit.Source}
+	if hit.Score != nil {
+		detail["score"] = *hit.Score
+	}
+
+	rq.line.Reputation = append(rq.line.Reputation, hit.Source)
+	rq.reputation = append(rq.reputation, hit)
+	rq.h.metrics.ReputationHit(hit.Source)
+	rq.h.alerts.Raise(alerts.Alert{
+		Event:    alerts.EventReputationHit,
+		Client:   rq.client,
+		Netblock: rq.h.clientGroup(rq.client),
+		ASN:      rq.line.ASN,
+		ASName:   rq.line.ASName,
+		Country:  rq.line.Country,
+		Reason:   reason,
+		Detail:   detail,
+	})
+}

internal/proxy/request.go

@@ -17,6 +17,7 @@ import (
 	"time"
 
 	"sneak.berlin/go/smallwebwaf/internal/anomaly"
+	"sneak.berlin/go/smallwebwaf/internal/bans"
 	"sneak.berlin/go/smallwebwaf/internal/config"
 	"sneak.berlin/go/smallwebwaf/internal/lookup"
 	"sneak.berlin/go/smallwebwaf/internal/ratelimit"
@@ -63,7 +64,18 @@ type request struct {
 	// limits and for the byte limits.
 	counted                    bool
 	limitPercent, bytesPercent percentage
-	start                      time.Time
+	// attack is true for a request that matched a ban rule, and
+	// ruleBlocked for one a block rule refused, each an offence its
+	// client's history counts.
+	attack, ruleBlocked bool
+	// blocklisted is true once a blocklist is found to list the client,
+	// dnsblListed once a DNSBL zone's verdict is, and abuseIPDBHit once
+	// AbuseIPDB's score of it is a hit.
+	blocklisted, dnsblListed, abuseIPDBHit bool
+	// reputation is the reputation sources that list the client, for the
+	// notes of a ban the request makes.
+	reputation []bans.ReputationHit
+	start      time.Time
 	// checked is when the checks were done, and upstreamStart when the
 	// request was handed to the app.
 	checked       time.Time
@@ -132,7 +144,7 @@ func (h *handler) newRequest(w http.ResponseWriter, r *http.Request) *request {
 			RequestID:        requestID(r, peerTrusted),
 			PeerIP:           peer.String(),
 			ForwardedFor:     strings.Join(forwardedFor, ", "),
-			ClientGroup:      clientGroup(client).String(),
+			ClientGroup:      h.clientGroup(client).String(),
 			ContentType:      r.Header.Get("Content-Type"),
 			RequestHeaders:   requestHeaders(r, h.config.LogRequestHeaders),
 			HasAuthorization: len(r.Header.Values("Authorization")) > 0,
@@ -213,9 +225,10 @@ func (rq *request) check(ctx context.Context) *refusal {
 // client in SWWAF_ALLOW_NETS skips them, and is not looked up. For any
 // other client, SWWAF_DENY_NETS comes first, then a ban on its netblock,
 // so that a client either refuses is not looked up, then the lookup of
-// its AS number and country, and then the country lists; a request any of
+// its AS number and country, then the country lists, then the blocklists,
-// them refuses is not counted for the rate limits. Then come the rate
+// then the DNSBL zones' verdicts, and then AbuseIPDB's score; a request
-// limits, unless the client is in SWWAF_RATE_LIMIT_EXEMPT_NETS or the
+// any of them refuses is not counted for the rate limits. Then come the
+// rate limits, unless the client is in SWWAF_RATE_LIMIT_EXEMPT_NETS or the
 // request's path is exempt under SWWAF_RATE_LIMIT_EXEMPT_PATHS, so that
 // every other request is counted, each of them by the client's limit
 // percentages, and last the rule files. A request exempt from the rate
@@ -243,10 +256,18 @@ func (rq *request) checkClient(ctx context.Context) string {
 		return requestlog.ActionCountryDenied
 	}
 
+	if rq.blocklistDenied() {
+		return requestlog.ActionDenied
+	}
+
+	if rq.dnsblDenied(ctx) || rq.abuseIPDBDenied(ctx) {
+		return requestlog.ActionDenied
+	}
+
 	rq.counted = !isInside(rq.client, cfg.RateLimitExemptNets) &&
 		!pathExempt(rq.in.URL, cfg.RateLimitExemptPaths)
 	if rq.counted {
-		rq.limitPercent, rq.bytesPercent = limitPercentages(cfg, rq.line.ASN, rq.line.Country)
+		rq.limitPercent, rq.bytesPercent = rq.limitPercentages()
 		rq.line.LimitPercent, rq.line.LimitPercentSetting = rq.limitPercent.logged()
 		rq.line.BytesPercent, rq.line.BytesPercentSetting = rq.bytesPercent.logged()
 	}
@@ -522,13 +543,15 @@ func timing(start, end time.Time) *float64 {
 func (rq *request) addToHistory() {
 	forwarded := !rq.upstreamStart.IsZero()
 
-	rq.h.limiter.AddToHistory(clientGroup(rq.client), rq.h.now(), ratelimit.Request{
+	rq.h.limiter.AddToHistory(rq.h.clientGroup(rq.client), rq.h.now(), ratelimit.Request{
 		Forwarded:     forwarded,
 		Refused:       !forwarded && rq.refused.Load() != nil,
 		Status:        rq.out.status,
 		RequestBytes:  rq.requestBytes(),
 		ResponseBytes: rq.out.bytes,
 		BrokeLimit:    rq.line.Offence == requestlog.OffenceLimit,
+		Attack:        rq.attack,
+		RuleBlocked:   rq.ruleBlocked,
 	})
 
 	answer, found := rq.answerAtTheEnd()
@@ -553,7 +576,7 @@ func (rq *request) countAnomalies() {
 
 	rq.h.anomalies.Count(rq.h.now(), anomaly.Request{
 		Client:      rq.client,
-		ClientGroup: clientGroup(rq.client),
+		ClientGroup: rq.h.clientGroup(rq.client),
 		ASN:         answer.ASN,
 		ASName:      answer.ASName,
 		Country:     answer.Country,
@@ -582,7 +605,7 @@ func (rq *request) answerAtTheEnd() (lookup.Answer, bool) {
 		return rq.lookupAnswer, true
 	}
 
-	return rq.h.geojs.Kept(clientGroup(rq.client))
+	return rq.h.geojs.Kept(rq.h.clientGroup(rq.client))
 }
 
 // requestBytes is how many bytes of the request's body have been read.

internal/proxy/rulefiles_test.go

@@ -5,6 +5,7 @@ import (
 	"net/netip"
 	"os"
 	"path/filepath"
+	"reflect"
 	"slices"
 	"testing"
 	"time"
@@ -73,7 +74,7 @@ func TestEachRuleAction(t *testing.T) {
 	}
 
 	got := server.Ledger.Bans(netblock)
-	if len(got) != 1 || got[0] != want {
+	if len(got) != 1 || !reflect.DeepEqual(got[0], want) {
 		t.Fatalf("bans\n%+v\nwant\n%+v", got, want)
 	}
 

internal/proxy/rules.go

@@ -12,7 +12,8 @@ import (
 // action of the rule that refuses it, ActionRuleBlocked for a block rule
 // and ActionBanned for a ban rule, or "" when none does. A ban rule bans
 // the client's netblock for a clear sign of attack, or in observe mode
-// raises the alert for the ban it would have made.
+// raises the alert for the ban it would have made. Either rule's match
+// is noted as an offence, for the client's history.
 func (rq *request) checkRules(now time.Time) string {
 	matched := rq.h.rules.Match(rq.in)
 
@@ -28,8 +29,11 @@ func (rq *request) checkRules(now time.Time) string {
 	// Only the last rule matched can refuse the request.
 	switch last := matched[len(matched)-1]; last.Action {
 	case rules.ActionBlock:
+		rq.ruleBlocked = true
+
 		return requestlog.ActionRuleBlocked
 	case rules.ActionBan:
+		rq.attack = true
 		rq.banForAttack(now, last)
 
 		return requestlog.ActionBanned

internal/ratelimit/history_test.go

@@ -11,7 +11,7 @@ import (
 func TestHistoryKeepsEveryRequest(t *testing.T) {
 	t.Parallel()
 
-	limiter := ratelimit.New(ratelimit.Limits{})
+	limiter := ratelimit.New(ratelimit.Limits{}, tableSize)
 	client := netip.MustParsePrefix("203.0.113.9/32")
 	start := midnight()
 
@@ -53,7 +53,7 @@ func TestHistoryKeepsEveryRequest(t *testing.T) {
 func TestLookupReachesTheHistoryOfAClientInTheTable(t *testing.T) {
 	t.Parallel()
 
-	limiter := ratelimit.New(ratelimit.Limits{})
+	limiter := ratelimit.New(ratelimit.Limits{}, tableSize)
 	client := netip.MustParsePrefix("203.0.113.9/32")
 	other := netip.MustParsePrefix("198.51.100.7/32")
 	start := midnight()
@@ -90,7 +90,7 @@ func TestLookupReachesTheHistoryOfAClientInTheTable(t *testing.T) {
 func TestResetKeepsTheHistory(t *testing.T) {
 	t.Parallel()
 
-	limiter := ratelimit.New(ratelimit.Limits{PerMinute: limit})
+	limiter := ratelimit.New(ratelimit.Limits{PerMinute: limit}, tableSize)
 	client := netip.MustParsePrefix("203.0.113.9/32")
 	start := midnight()
 
@@ -109,7 +109,7 @@ func TestResetKeepsTheHistory(t *testing.T) {
 func TestRequestsAddsUpTheClientsInsideTheNetblock(t *testing.T) {
 	t.Parallel()
 
-	limiter := ratelimit.New(ratelimit.Limits{})
+	limiter := ratelimit.New(ratelimit.Limits{}, tableSize)
 
 	for client, requests := range map[string]int{
 		"198.51.100.9/32":  2,

internal/ratelimit/ratelimit.go

@@ -2,8 +2,9 @@
 // and bytes counted over a minute, an hour and a day, as the "Counting
 // method" section of SPEC.md describes, which tell when a request takes
 // the client over a rate limit or a byte limit, and each client's history
-// since it was first seen. At most 20,000 clients are kept, in memory, and
+// since it was first seen. At most SWWAF_MAX_TRACKED_CLIENTS clients are
-// written to clients.json and read from it by the state package.
+// kept, in memory, and written to clients.json and read from it by the
+// state package.
 package ratelimit
 
 import (
@@ -16,11 +17,6 @@ import (
 	"github.com/hashicorp/golang-lru/v2/simplelru"
 )
 
-// maxClients is how many clients are kept. Past it, the least recently
-// seen client is dropped, with its history, and starts afresh if it comes
-// back.
-const maxClients = 20000
-
 const day = 24 * time.Hour
 
 // The kinds of limits, as the metrics name them.
@@ -117,9 +113,15 @@ type Responses struct {
 }
 
 // Offences are a client's offences, by kind.
+//
+//nolint:tagliatelle // the state files use snake_case, as the request log does
 type Offences struct {
-	// Limit is its requests that broke a rate limit or a byte limit.
+	// Limit is its requests that broke a rate limit or a byte limit,
-	Limit int64 `json:"limit"`
+	// Attack those that matched a ban rule, a clear sign of attack, and
+	// RuleBlocked those a block rule refused.
+	Limit       int64 `json:"limit"`
+	Attack      int64 `json:"attack"`
+	RuleBlocked int64 `json:"rule_blocked"`
 }
 
 // Request is what a client's history keeps of one of its requests.
@@ -137,12 +139,18 @@ type Request struct {
 	RequestBytes  int64
 	ResponseBytes int64
 	// BrokeLimit is true for a request that broke a rate limit or a byte
-	// limit.
+	// limit, Attack for one that matched a ban rule, and RuleBlocked for
-	BrokeLimit bool
+	// one a block rule refused.
+	BrokeLimit  bool
+	Attack      bool
+	RuleBlocked bool
 }
 
-// New returns a Limiter for limits, with no client counted yet.
+// New returns a Limiter for limits, with no client counted yet, whose
-func New(limits Limits) *Limiter {
+// table holds at most maxClients clients (SWWAF_MAX_TRACKED_CLIENTS). Past
+// it, the least recently seen client is dropped, with its history, and
+// starts afresh if it comes back.
+func New(limits Limits, maxClients int) *Limiter {
 	clients, err := simplelru.NewLRU[netip.Prefix, *Client](maxClients, nil)
 	if err != nil {
 		panic(err) // NewLRU fails only for a size below one
@@ -258,6 +266,14 @@ func (l *Limiter) AddToHistory(client netip.Prefix, now time.Time, r Request) {
 	if r.BrokeLimit {
 		h.Offences.Limit++
 	}
+
+	if r.Attack {
+		h.Offences.Attack++
+	}
+
+	if r.RuleBlocked {
+		h.Offences.RuleBlocked++
+	}
 }
 
 // AddLookup gives client's history its AS number, AS name and country, as

internal/ratelimit/ratelimit_test.go

@@ -12,6 +12,10 @@ import (
 // limit is the limit the tests set.
 const limit = 3
 
+// tableSize is the most clients the tests' tables hold, the default of
+// SWWAF_MAX_TRACKED_CLIENTS.
+const tableSize = 20000
+
 // whole is the percentage of each limit a client gets when nothing lowers
 // its limits.
 const whole = 100
@@ -37,7 +41,7 @@ func TestEachWindowRefusesAtItsLimitAndLetsTheClientBack(t *testing.T) {
 		t.Run(tc.window, func(t *testing.T) {
 			t.Parallel()
 
-			limiter := ratelimit.New(tc.limits)
+			limiter := ratelimit.New(tc.limits, tableSize)
 			client := netip.MustParsePrefix("203.0.113.9/32")
 			start := midnight()
 			quarter := tc.length / 4
@@ -62,7 +66,7 @@ func TestEachWindowRefusesAtItsLimitAndLetsTheClientBack(t *testing.T) {
 func TestHitGivesTheLimitAndTheRequestsCounted(t *testing.T) {
 	t.Parallel()
 
-	limiter := ratelimit.New(ratelimit.Limits{PerMinute: limit, PerHour: limit})
+	limiter := ratelimit.New(ratelimit.Limits{PerMinute: limit, PerHour: limit}, tableSize)
 	client := netip.MustParsePrefix("203.0.113.9/32")
 	start := midnight()
 
@@ -88,7 +92,8 @@ func TestHitGivesTheLimitAndTheRequestsCounted(t *testing.T) {
 func TestClientGetsItsPercentageOfEachLimitRoundedDown(t *testing.T) {
 	t.Parallel()
 
-	limiter := ratelimit.New(ratelimit.Limits{PerMinute: 5, BytesPerDay: math.MaxInt64})
+	limiter := ratelimit.New(ratelimit.Limits{PerMinute: 5, BytesPerDay: math.MaxInt64},
+		tableSize)
 	client := netip.MustParsePrefix("203.0.113.9/32")
 	start := midnight()
 
@@ -119,7 +124,8 @@ func TestZeroPercentIsAZeroAllowanceAndALimitOffStaysOff(t *testing.T) {
 	t.Parallel()
 
 	// Only the hour has limits: the minute's and the day's are off.
-	limiter := ratelimit.New(ratelimit.Limits{PerHour: limit, BytesPerHour: 1000})
+	limiter := ratelimit.New(ratelimit.Limits{PerHour: limit, BytesPerHour: 1000},
+		tableSize)
 	client := netip.MustParsePrefix("203.0.113.9/32")
 	start := midnight()
 
@@ -156,7 +162,7 @@ func TestEachByteLimitIsBrokenByTheBytesCounted(t *testing.T) {
 		t.Run(tc.window, func(t *testing.T) {
 			t.Parallel()
 
-			limiter := ratelimit.New(tc.limits)
+			limiter := ratelimit.New(tc.limits, tableSize)
 			client := netip.MustParsePrefix("203.0.113.9/32")
 
 			// 600 bytes are within the limit, 600 more over it.
@@ -180,7 +186,8 @@ func TestEachByteLimitIsBrokenByTheBytesCounted(t *testing.T) {
 func TestALimitIsBrokenOnlyByWhatIsAddedToIt(t *testing.T) {
 	t.Parallel()
 
-	limiter := ratelimit.New(ratelimit.Limits{PerMinute: 2, BytesPerMinute: 1000})
+	limiter := ratelimit.New(ratelimit.Limits{PerMinute: 2, BytesPerMinute: 1000},
+		tableSize)
 	client := netip.MustParsePrefix("203.0.113.9/32")
 	other := netip.MustParsePrefix("203.0.113.10/32")
 	start := midnight()
@@ -204,7 +211,7 @@ func TestALimitIsBrokenOnlyByWhatIsAddedToIt(t *testing.T) {
 func TestCountGivesTheBytesInEachWindow(t *testing.T) {
 	t.Parallel()
 
-	limiter := ratelimit.New(ratelimit.Limits{})
+	limiter := ratelimit.New(ratelimit.Limits{}, tableSize)
 	client := netip.MustParsePrefix("203.0.113.9/32")
 	start := midnight()
 
@@ -230,7 +237,7 @@ func TestCountGivesTheBytesInEachWindow(t *testing.T) {
 func TestResetSetsTheBytesBackToZero(t *testing.T) {
 	t.Parallel()
 
-	limiter := ratelimit.New(ratelimit.Limits{BytesPerDay: 1000})
+	limiter := ratelimit.New(ratelimit.Limits{BytesPerDay: 1000}, tableSize)
 	client := netip.MustParsePrefix("203.0.113.9/32")
 	start := midnight()
 
@@ -244,7 +251,7 @@ func TestResetSetsTheBytesBackToZero(t *testing.T) {
 func TestCountGivesTheRequestsInEachWindow(t *testing.T) {
 	t.Parallel()
 
-	limiter := ratelimit.New(ratelimit.Limits{})
+	limiter := ratelimit.New(ratelimit.Limits{}, tableSize)
 	client := netip.MustParsePrefix("203.0.113.9/32")
 	start := midnight()
 
@@ -267,7 +274,7 @@ func TestCountGivesTheRequestsInEachWindow(t *testing.T) {
 func TestResetSetsTheCountsBackToZero(t *testing.T) {
 	t.Parallel()
 
-	limiter := ratelimit.New(ratelimit.Limits{PerMinute: limit, PerDay: limit})
+	limiter := ratelimit.New(ratelimit.Limits{PerMinute: limit, PerDay: limit}, tableSize)
 	client := netip.MustParsePrefix("203.0.113.9/32")
 	start := midnight()
 
@@ -289,7 +296,7 @@ func TestResetSetsTheCountsBackToZero(t *testing.T) {
 func TestClientBackAfterAWholeBucketIsWithinTheLimitAtOnce(t *testing.T) {
 	t.Parallel()
 
-	limiter := ratelimit.New(ratelimit.Limits{PerHour: limit})
+	limiter := ratelimit.New(ratelimit.Limits{PerHour: limit}, tableSize)
 	client := netip.MustParsePrefix("203.0.113.9/32")
 	start := midnight()
 
@@ -308,7 +315,8 @@ func TestClientBackAfterAWholeBucketIsWithinTheLimitAtOnce(t *testing.T) {
 func TestRefusedRequestsCount(t *testing.T) {
 	t.Parallel()
 
-	limiter := ratelimit.New(ratelimit.Limits{PerMinute: limit, PerHour: 2 * limit})
+	limiter := ratelimit.New(ratelimit.Limits{PerMinute: limit, PerHour: 2 * limit},
+		tableSize)
 	refused := netip.MustParsePrefix("203.0.113.9/32")
 	within := netip.MustParsePrefix("203.0.113.10/32")
 	start := midnight()
@@ -341,7 +349,7 @@ func TestRefusedRequestsCount(t *testing.T) {
 func TestRequestCountedLateGoesInTheBucketUnderWay(t *testing.T) {
 	t.Parallel()
 
-	limiter := ratelimit.New(ratelimit.Limits{PerMinute: limit})
+	limiter := ratelimit.New(ratelimit.Limits{PerMinute: limit}, tableSize)
 	client := netip.MustParsePrefix("203.0.113.9/32")
 	start := midnight()
 
@@ -357,7 +365,7 @@ func TestRequestCountedLateGoesInTheBucketUnderWay(t *testing.T) {
 func TestClockSetBackStartsTheBucketsAfresh(t *testing.T) {
 	t.Parallel()
 
-	limiter := ratelimit.New(ratelimit.Limits{PerHour: limit})
+	limiter := ratelimit.New(ratelimit.Limits{PerHour: limit}, tableSize)
 	client := netip.MustParsePrefix("203.0.113.9/32")
 	start := midnight()
 
@@ -380,12 +388,12 @@ func TestClockSetBackStartsTheBucketsAfresh(t *testing.T) {
 	wantCount(t, limiter, client, setBack, hour)
 }
 
-func TestKeepsAtMost20000ClientsDroppingTheLeastRecentlySeen(t *testing.T) {
+func TestKeepsAtMostMaxClientsDroppingTheLeastRecentlySeen(t *testing.T) {
 	t.Parallel()
 
-	const maxClients = 20000
+	const maxClients = 3
 
-	limiter := ratelimit.New(ratelimit.Limits{PerMinute: 1})
+	limiter := ratelimit.New(ratelimit.Limits{PerMinute: 1}, maxClients)
 	now := midnight()
 
 	clients := make([]netip.Prefix, maxClients+1)
@@ -407,6 +415,11 @@ func TestKeepsAtMost20000ClientsDroppingTheLeastRecentlySeen(t *testing.T) {
 	// One client more drops the least recently seen, the second, which
 	// starts afresh, while the first is kept.
 	wantCount(t, limiter, clients[maxClients], now, "")
+
+	if limiter.Len() != maxClients {
+		t.Errorf("the table holds %d clients, want %d", limiter.Len(), maxClients)
+	}
+
 	wantCount(t, limiter, clients[1], now, "")
 	wantCount(t, limiter, clients[0], now, minute)
 }

internal/ratelimit/snapshot_test.go

@@ -14,7 +14,7 @@ func TestSnapshotListsTheClientsByAddress(t *testing.T) {
 
 	want := []string{"192.0.2.1/32", "203.0.113.9/32", "203.0.113.10/32", "2001:db8::/64"}
 
-	limiter := ratelimit.New(ratelimit.Limits{})
+	limiter := ratelimit.New(ratelimit.Limits{}, tableSize)
 	for _, i := range []int{2, 3, 0, 1} {
 		limiter.Count(netip.MustParsePrefix(want[i]), midnight(), whole)
 	}
@@ -43,7 +43,7 @@ func TestLoadedCountsCarryOn(t *testing.T) {
 	client := netip.MustParsePrefix("203.0.113.9/32")
 	start := midnight()
 
-	before := ratelimit.New(ratelimit.Limits{PerHour: limit})
+	before := ratelimit.New(ratelimit.Limits{PerHour: limit}, tableSize)
 	for range limit {
 		wantCount(t, before, client, start, "")
 	}
@@ -51,7 +51,7 @@ func TestLoadedCountsCarryOn(t *testing.T) {
 	// Loaded into a new limiter, as across a restart, the client has no
 	// fresh allowance.
 	later := start.Add(time.Minute)
-	after := ratelimit.New(ratelimit.Limits{PerHour: limit})
+	after := ratelimit.New(ratelimit.Limits{PerHour: limit}, tableSize)
 	after.Load(before.Snapshot(), later)
 	wantCount(t, after, client, later, hour)
 }
@@ -62,7 +62,7 @@ func TestLoadEmptiesBucketsWhoseTimeHasPassed(t *testing.T) {
 	client := netip.MustParsePrefix("203.0.113.9/32")
 	start := midnight()
 
-	limiter := ratelimit.New(ratelimit.Limits{})
+	limiter := ratelimit.New(ratelimit.Limits{}, tableSize)
 	limiter.Count(client, start, whole)
 	limiter.CountBytes(client, start, 5, whole)
 	limiter.AddToHistory(client, start, ratelimit.Request{Forwarded: true})
@@ -70,7 +70,7 @@ func TestLoadEmptiesBucketsWhoseTimeHasPassed(t *testing.T) {
 	loaded := func(now time.Time) ratelimit.Client {
 		t.Helper()
 
-		after := ratelimit.New(ratelimit.Limits{})
+		after := ratelimit.New(ratelimit.Limits{}, tableSize)
 		after.Load(limiter.Snapshot(), now)
 
 		return after.Snapshot()[0]
@@ -102,7 +102,7 @@ func TestLoadEmptiesBucketsWhoseTimeHasPassed(t *testing.T) {
 func TestLoadDropsTheLeastRecentlySeenFirst(t *testing.T) {
 	t.Parallel()
 
-	const maxClients = 20000
+	const maxClients = 3
 
 	// clients.json lists the clients by address. Here each was last seen
 	// a second before the one listed before it, so the last listed is the
@@ -116,7 +116,7 @@ func TestLoadDropsTheLeastRecentlySeenFirst(t *testing.T) {
 		addr = addr.Next()
 	}
 
-	limiter := ratelimit.New(ratelimit.Limits{})
+	limiter := ratelimit.New(ratelimit.Limits{}, maxClients)
 	limiter.Load(clients, midnight())
 
 	got := limiter.Snapshot()

internal/reputation/abuseipdb.go

@@ -0,0 +1,328 @@
+package reputation
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"log/slog"
+	"net/http"
+	"net/netip"
+	"net/url"
+	"slices"
+	"sync"
+	"time"
+
+	"github.com/hashicorp/golang-lru/v2/simplelru"
+	"sneak.berlin/go/smallwebwaf/internal/alerts"
+)
+
+const (
+	// AbuseIPDBURL is where clients are checked: the check endpoint of
+	// AbuseIPDB's API.
+	AbuseIPDBURL = "https://api.abuseipdb.com/api/v2/check"
+	// AbuseIPDBSource is how the request log, the alerts and the metrics
+	// name AbuseIPDB.
+	AbuseIPDBSource = "abuseipdb"
+	// maxAnswerBytes is the most of an answer of AbuseIPDB that is read.
+	maxAnswerBytes = 64 << 10
+	// day is the length of the day the checks are counted in, in UTC.
+	day = 24 * time.Hour
+)
+
+var (
+	errNoScore      = errors.New("the answer gives no abuseConfidenceScore")
+	errBudgetUsedUp = errors.New(
+		"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.
+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    time.Time `json:"day,omitzero"`
+	Spent  int       `json:"spent"`
+	Scores []Score   `json:"scores"`
+}
+
+// AbuseIPDBParams are what NewAbuseIPDB needs.
+type AbuseIPDBParams struct {
+	// URL is where clients are checked, normally AbuseIPDBURL, with Key,
+	// the account's key (SWWAF_ABUSEIPDB_KEY).
+	URL string
+	Key string
+	// MinScore is the least score that is a hit (SWWAF_ABUSEIPDB_MIN_SCORE),
+	// and DailyBudget the most checks made in a day, in UTC
+	// (SWWAF_ABUSEIPDB_DAILY_BUDGET).
+	MinScore    int64
+	DailyBudget int
+	// CacheTTL is how long a score is used after it was fetched
+	// (SWWAF_REPUTATION_CACHE_TTL), and Timeout how long a check may take
+	// (SWWAF_REPUTATION_TIMEOUT).
+	CacheTTL time.Duration
+	Timeout  time.Duration
+	// Now tells the time, normally time.Now in UTC.
+	Now func() time.Time
+	// ProcessLog receives each check that fails, and why, and the day's
+	// budget used up.
+	ProcessLog *slog.Logger
+	// Alerts receive a source_failure alert for each.
+	Alerts *alerts.Queue
+}
+
+// AbuseIPDB checks clients with AbuseIPDB, in the background, and keeps
+// their scores. It is safe for concurrent use.
+type AbuseIPDB struct {
+	params     AbuseIPDBParams
+	httpClient *http.Client
+
+	mu sync.Mutex
+	// scores are by client. Each is added as it is fetched and never moved
+	// up, so that the one fetched longest ago is the first dropped.
+	scores *simplelru.LRU[netip.Prefix, Score]
+	// checking are the clients whose check is under way.
+	checking map[netip.Prefix]bool
+	// day is the day, in UTC, of the checks spent counts.
+	day   time.Time
+	spent int
+	// checks and failures count the checks made and those that failed,
+	// and retryAt is when a client may be checked again after the last
+	// check failed.
+	checks   int
+	failures int
+	retryAt  time.Time
+}
+
+// NewAbuseIPDB returns an AbuseIPDB with no score yet, and no check spent.
+func NewAbuseIPDB(params AbuseIPDBParams) *AbuseIPDB {
+	scores, err := simplelru.NewLRU[netip.Prefix, Score](maxVerdicts, nil)
+	if err != nil {
+		panic(err) // NewLRU fails only for a size below one
+	}
+
+	return &AbuseIPDB{
+		params:     params,
+		httpClient: &http.Client{},
+		scores:     scores,
+		checking:   map[netip.Prefix]bool{},
+	}
+}
+
+// Hit returns AbuseIPDB's score of client, an IPv4 address or an IPv6
+// group, and whether it is a hit: MinScore or more. A score is used until
+// CacheTTL has passed since it was fetched, whichever of the client's
+// addresses its request comes from. A client without one is checked in
+// the background, by addr, the address its request came from, if
+// offender, if it has committed an offence, unless its check is under
+// way, a check failed less than failureDelay ago, or the day's checks
+// have used up DailyBudget; Hit never waits for a check. The check that
+// uses the budget up is logged and raised as a source_failure alert. ctx
+// is the context of the client's request, and a check goes on after the
+// request ends.
+func (a *AbuseIPDB) Hit(
+	ctx context.Context, client netip.Prefix, addr netip.Addr, offender bool,
+) (int64, bool) {
+	a.mu.Lock()
+
+	now := a.params.Now()
+
+	kept, found := a.scores.Peek(client)
+	if found && now.Sub(kept.Fetched) < a.params.CacheTTL {
+		a.mu.Unlock()
+
+		return kept.Score, kept.Score >= a.params.MinScore
+	}
+
+	if today := now.Truncate(day); !a.day.Equal(today) {
+		a.day, a.spent = today, 0
+	}
+
+	check := offender && !a.checking[client] && !now.Before(a.retryAt) &&
+		a.spent < a.params.DailyBudget
+	if check {
+		a.checking[client] = true
+		a.checks++
+		a.spent++
+
+		go a.check(context.WithoutCancel(ctx), client, addr)
+	}
+
+	usedUp := check && a.spent == a.params.DailyBudget
+
+	a.mu.Unlock()
+
+	if usedUp {
+		a.alert("the daily budget of AbuseIPDB checks is used up",
+			fmt.Errorf("%d %w", a.params.DailyBudget, errBudgetUsedUp))
+	}
+
+	return 0, false
+}
+
+// Checked returns how many checks were made.
+func (a *AbuseIPDB) Checked() int {
+	a.mu.Lock()
+	defer a.mu.Unlock()
+
+	return a.checks
+}
+
+// Failures returns how many checks failed.
+func (a *AbuseIPDB) Failures() int {
+	a.mu.Lock()
+	defer a.mu.Unlock()
+
+	return a.failures
+}
+
+// BudgetLeft returns how many checks the day's budget has left.
+func (a *AbuseIPDB) BudgetLeft() int {
+	a.mu.Lock()
+	defer a.mu.Unlock()
+
+	if !a.day.Equal(a.params.Now().Truncate(day)) {
+		return a.params.DailyBudget
+	}
+
+	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 {
+	a.mu.Lock()
+
+	now := a.params.Now()
+	checks := Checks{Day: a.day, Spent: a.spent, 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)
+		}
+	}
+
+	a.mu.Unlock()
+
+	slices.SortFunc(checks.Scores, func(x, y Score) int {
+		return x.Client.Compare(y.Client)
+	})
+
+	return checks
+}
+
+// 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)
+	slices.SortStableFunc(scores, func(x, y Score) int {
+		return x.Fetched.Compare(y.Fetched)
+	})
+
+	a.mu.Lock()
+	defer a.mu.Unlock()
+
+	a.day, a.spent = checks.Day, checks.Spent
+	a.scores.Purge()
+
+	for _, kept := range scores {
+		a.scores.Add(kept.Client, kept)
+	}
+}
+
+// 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
+// source_failure alert, and no client is checked for failureDelay.
+func (a *AbuseIPDB) check(ctx context.Context, client netip.Prefix, addr netip.Addr) {
+	score, err := a.ask(ctx, addr)
+	now := a.params.Now()
+
+	a.mu.Lock()
+
+	delete(a.checking, client)
+
+	if err == nil {
+		a.scores.Add(client, Score{Client: client, Score: score, Fetched: now})
+	} else {
+		a.failures++
+		a.retryAt = now.Add(failureDelay)
+	}
+
+	a.mu.Unlock()
+
+	if err != nil {
+		a.alert("checking a client with AbuseIPDB failed", err)
+	}
+}
+
+// ask asks AbuseIPDB for addr's abuse confidence score, sending the key
+// in the header Key. An answer other than 200, one that gives no score,
+// and none within Timeout, fail.
+func (a *AbuseIPDB) ask(ctx context.Context, addr netip.Addr) (int64, error) {
+	ctx, cancel := context.WithTimeout(ctx, a.params.Timeout)
+	defer cancel()
+
+	query := url.Values{"ipAddress": {addr.String()}}
+
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet,
+		a.params.URL+"?"+query.Encode(), http.NoBody)
+	if err != nil {
+		return 0, fmt.Errorf("make the request: %w", err)
+	}
+
+	req.Header.Set("Key", a.params.Key)
+	req.Header.Set("Accept", "application/json")
+
+	res, err := a.httpClient.Do(req)
+	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 0, fmt.Errorf("check the client: %w", errors.Unwrap(err))
+	}
+
+	defer func() {
+		_ = res.Body.Close()
+	}()
+
+	if res.StatusCode != http.StatusOK {
+		return 0, fmt.Errorf("%w %s", errStatus, res.Status)
+	}
+
+	var answer struct {
+		Data struct {
+			AbuseConfidenceScore *int64 `json:"abuseConfidenceScore"`
+		} `json:"data"`
+	}
+
+	err = json.NewDecoder(io.LimitReader(res.Body, maxAnswerBytes)).Decode(&answer)
+	if err != nil {
+		return 0, fmt.Errorf("read the answer: %w", err)
+	}
+
+	if answer.Data.AbuseConfidenceScore == nil {
+		return 0, errNoScore
+	}
+
+	return *answer.Data.AbuseConfidenceScore, nil
+}
+
+// alert raises a source_failure alert from AbuseIPDB with reason and err,
+// and logs them.
+func (a *AbuseIPDB) alert(reason string, err error) {
+	// Raised before it is logged, so that the alert is there once the log
+	// line is.
+	raiseFailure(a.params.Alerts, reason, AbuseIPDBSource, err)
+	a.params.ProcessLog.Warn(reason, "source", AbuseIPDBSource, "error", err.Error())
+}

internal/reputation/abuseipdb_test.go

@@ -0,0 +1,663 @@
+package reputation_test
+
+import (
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"io"
+	"log/slog"
+	"net/http"
+	"net/http/httptest"
+	"net/netip"
+	"reflect"
+	"slices"
+	"strings"
+	"sync"
+	"testing"
+	"testing/synctest"
+	"time"
+
+	"sneak.berlin/go/smallwebwaf/internal/alerts"
+	"sneak.berlin/go/smallwebwaf/internal/metrics"
+	"sneak.berlin/go/smallwebwaf/internal/reputation"
+)
+
+// The tests of AbuseIPDB run in synctest bubbles, as those of the lists
+// do, and AbuseIPDB is a stand-in reached without the network, for the
+// same reason. A bubble's clock starts at midnight UTC, as a day the
+// checks are counted in starts.
+
+const (
+	// key is the account's key the tests give, the only one the stand-in
+	// takes.
+	key = "abuseipdb-key-0123456789abcdef"
+	// suspect and other are clients that have committed an offence.
+	suspect = "203.0.113.9"
+	other   = "2001:db8::9"
+)
+
+func TestOnlyAnOffenderWithoutAScoreIsChecked(t *testing.T) {
+	t.Parallel()
+
+	synctest.Test(t, func(t *testing.T) {
+		abuseIPDB := &abuseIPDBStandIn{scores: map[string]int64{suspect: 100}}
+		checker := newAbuseIPDB(abuseIPDB, abuseIPDBParams())
+
+		// A client that has committed no offence is not checked.
+		wantScore(t, checker, suspect, false, 0, false)
+		synctest.Wait()
+		wantChecked(t, abuseIPDB)
+
+		// An offender is, and from then on its score is used, whether or not
+		// it is an offender.
+		wantScore(t, checker, suspect, true, 0, false)
+		synctest.Wait()
+		wantScore(t, checker, suspect, true, 100, true)
+		wantScore(t, checker, suspect, false, 100, true)
+		synctest.Wait()
+		wantChecked(t, abuseIPDB, suspect)
+	})
+}
+
+func TestIPv6ClientIsCheckedOnceAndItsScoreUsedForEachOfItsAddresses(t *testing.T) {
+	t.Parallel()
+
+	synctest.Test(t, func(t *testing.T) {
+		// 15 addresses of 2001:db8:1:2::/64, one client, each in a part of
+		// it of its own.
+		var addresses []string
+		for i := 1; i < 16; i++ {
+			addresses = append(addresses, fmt.Sprintf("2001:db8:1:2:%x::9", i<<12))
+		}
+
+		abuseIPDB := &abuseIPDBStandIn{scores: map[string]int64{addresses[0]: 100}}
+		checker := newAbuseIPDB(abuseIPDB, abuseIPDBParams())
+
+		// A request from each has the client checked once, by the first.
+		for _, address := range addresses {
+			hitFrom(t, checker, address, true)
+		}
+
+		synctest.Wait()
+		wantChecked(t, abuseIPDB, addresses[0])
+
+		// Its score is the whole client's.
+		for _, address := range addresses {
+			wantScore(t, checker, address, true, 100, true)
+		}
+
+		synctest.Wait()
+		wantChecked(t, abuseIPDB, addresses[0])
+	})
+}
+
+func TestScoreAtOrOverTheMinimumIsAHit(t *testing.T) {
+	t.Parallel()
+
+	synctest.Test(t, func(t *testing.T) {
+		scores := map[string]int64{"192.0.2.74": 74, "192.0.2.75": 75, "192.0.2.100": 100}
+		p := abuseIPDBParams()
+		p.MinScore = 75
+		checker := newAbuseIPDB(&abuseIPDBStandIn{scores: scores}, p)
+
+		for client := range scores {
+			hitFrom(t, checker, client, true)
+		}
+
+		synctest.Wait()
+
+		for client, score := range scores {
+			wantScore(t, checker, client, true, score, score >= 75)
+		}
+	})
+}
+
+func TestScoreUsedUntilTheCacheTTLHasPassedSinceItWasFetched(t *testing.T) {
+	t.Parallel()
+
+	synctest.Test(t, func(t *testing.T) {
+		abuseIPDB := &abuseIPDBStandIn{scores: map[string]int64{suspect: 100}}
+		checker := newAbuseIPDB(abuseIPDB, abuseIPDBParams())
+
+		hitFrom(t, checker, suspect, true)
+		synctest.Wait()
+
+		// AbuseIPDB gives another score from now on, but the one kept is
+		// used, and the client is not checked again, until the TTL has
+		// passed.
+		abuseIPDB.setScore(suspect, 80)
+		time.Sleep(cacheTTL - time.Nanosecond)
+		wantScore(t, checker, suspect, true, 100, true)
+		synctest.Wait()
+		wantChecked(t, abuseIPDB, suspect)
+
+		// Then it is not used, and the client is checked again.
+		time.Sleep(time.Nanosecond)
+		wantScore(t, checker, suspect, true, 0, false)
+		synctest.Wait()
+		wantScore(t, checker, suspect, true, 80, true)
+		wantChecked(t, abuseIPDB, suspect, suspect)
+	})
+}
+
+func TestDailyBudgetKeptAcrossARestartAndWholeAgainAsTheDayEnds(t *testing.T) {
+	t.Parallel()
+
+	synctest.Test(t, func(t *testing.T) {
+		var log bytes.Buffer
+
+		queue := newQueue()
+		p := abuseIPDBParams()
+		p.DailyBudget = 3
+		p.Alerts = queue
+		p.ProcessLog = slog.New(slog.NewJSONHandler(&log, nil))
+		abuseIPDB := &abuseIPDBStandIn{scores: map[string]int64{suspect: 100}}
+		checker := newAbuseIPDB(abuseIPDB, p)
+
+		// At noon, the first three offenders spend the budget, and the
+		// fourth, unchecked, is not.
+		time.Sleep(12 * time.Hour)
+
+		const unchecked = "192.0.2.4"
+
+		clients := []string{suspect, "192.0.2.2", "192.0.2.3", unchecked}
+		for _, client := range clients {
+			hitFrom(t, checker, client, true)
+		}
+
+		synctest.Wait()
+		wantChecked(t, abuseIPDB, clients[:3]...)
+		wantBudgetLeft(t, checker, 0)
+
+		// The check that used the budget up raised the alert, and logged it.
+		const usedUp = "the daily budget of AbuseIPDB checks is used up"
+
+		wantFailureAlert(t, queue, time.Now(), usedUp,
+			"3 checks spent; none is made until the day ends at 00:00 UTC", 0)
+
+		if !strings.Contains(log.String(), `"msg":"`+usedUp+`"`) {
+			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 := &abuseIPDBStandIn{}
+		again := newAbuseIPDB(restarted, p)
+		again.Load(checker.Snapshot())
+
+		wantScore(t, again, suspect, true, 100, true)
+		wantBudgetLeft(t, again, 0)
+		time.Sleep(12*time.Hour - time.Nanosecond)
+		wantScore(t, again, unchecked, true, 0, false)
+		synctest.Wait()
+		wantChecked(t, restarted)
+
+		// At midnight the budget is whole again.
+		time.Sleep(time.Nanosecond)
+		wantBudgetLeft(t, again, 3)
+		wantScore(t, again, unchecked, true, 0, false)
+		synctest.Wait()
+		wantChecked(t, restarted, unchecked)
+		wantBudgetLeft(t, again, 2)
+	})
+}
+
+func TestFailedCheckGivesNoScoreAndNoClientIsCheckedForAMinute(t *testing.T) {
+	t.Parallel()
+
+	for _, tc := range []struct {
+		name string
+		// key is the key sent, status and body what AbuseIPDB answers with,
+		// and error the failure.
+		key, body string
+		status    int
+		error     string
+	}{
+		{
+			"a refusal, past AbuseIPDB's own limit", key,
+			`{"errors":[{"detail":"Daily rate limit of 1000 requests exceeded"}]}`,
+			http.StatusTooManyRequests, "the server answered 429 Too Many Requests",
+		},
+		{
+			"a refusal of a wrong key", "wrong-key-0123456789abcdef", "", 0,
+			"the server answered 401 Unauthorized",
+		},
+		{
+			"a server failure", key, "", http.StatusInternalServerError,
+			"the server answered 500 Internal Server Error",
+		},
+		{
+			"an answer without a score", key, `{"data":{"ipAddress":"` + suspect + `"}}`,
+			http.StatusOK, "the answer gives no abuseConfidenceScore",
+		},
+		{
+			"an answer that is not JSON", key, "<html>", http.StatusOK,
+			"read the answer: invalid character '<' looking for beginning of value",
+		},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			synctest.Test(t, func(t *testing.T) {
+				var log bytes.Buffer
+
+				queue := newQueue()
+				p := abuseIPDBParams()
+				p.Key = tc.key
+				p.Alerts = queue
+				p.ProcessLog = slog.New(slog.NewJSONHandler(&log, nil))
+				abuseIPDB := &abuseIPDBStandIn{status: tc.status, body: tc.body}
+				checker := newAbuseIPDB(abuseIPDB, p)
+
+				// The failure gives no score, and no client is checked within a
+				// minute of it.
+				wantScore(t, checker, suspect, true, 0, false)
+				synctest.Wait()
+				time.Sleep(time.Minute - time.Nanosecond)
+				wantScore(t, checker, other, true, 0, false)
+				synctest.Wait()
+				wantChecked(t, abuseIPDB, suspect)
+				wantFailures(t, checker, 1)
+
+				time.Sleep(time.Nanosecond)
+				wantScore(t, checker, other, true, 0, false)
+				synctest.Wait()
+				wantChecked(t, abuseIPDB, suspect, other)
+				wantFailures(t, checker, 2)
+
+				if scores := checker.Snapshot().Scores; len(scores) != 0 {
+					t.Errorf("scores %+v, want none", scores)
+				}
+
+				// One alert for the first failure; the cooldown holds back the
+				// second.
+				wantFailureAlert(t, queue, time.Now().Add(-time.Minute),
+					"checking a client with AbuseIPDB failed", tc.error, 1)
+
+				if !strings.Contains(log.String(), `"msg":"checking a client with `+
+					`AbuseIPDB failed","source":"abuseipdb","error":"`+tc.error) {
+					t.Errorf("logged\n%s\nwant the failures", log.String())
+				}
+			})
+		})
+	}
+}
+
+func TestCheckNotAnsweredWithinTheTimeoutFailsAndHitNeverWaits(t *testing.T) {
+	t.Parallel()
+
+	synctest.Test(t, func(t *testing.T) {
+		queue := newQueue()
+		p := abuseIPDBParams()
+		p.Alerts = queue
+		abuseIPDB := &abuseIPDBStandIn{hanging: true}
+		checker := newAbuseIPDB(abuseIPDB, p)
+		began := time.Now()
+
+		// The second, while the first's check is under way, starts none.
+		wantScore(t, checker, suspect, true, 0, false)
+		wantScore(t, checker, suspect, true, 0, false)
+
+		if waited := time.Since(began); waited != 0 {
+			t.Errorf("waited %s for the check, want no wait", waited)
+		}
+
+		time.Sleep(timeout - time.Nanosecond)
+		synctest.Wait()
+		wantChecked(t, abuseIPDB, suspect)
+		wantFailures(t, checker, 0)
+
+		time.Sleep(time.Nanosecond)
+		synctest.Wait()
+		wantFailures(t, checker, 1)
+		wantFailureAlert(t, queue, time.Now(), "checking a client with AbuseIPDB failed",
+			"check the client: context deadline exceeded", 0)
+	})
+}
+
+func TestKeyIsSentInTheKeyHeaderAndNeverShown(t *testing.T) {
+	t.Parallel()
+
+	synctest.Test(t, func(t *testing.T) {
+		var log bytes.Buffer
+
+		queue := newQueue()
+		p := abuseIPDBParams()
+		p.Alerts = queue
+		p.ProcessLog = slog.New(slog.NewJSONHandler(&log, nil))
+		abuseIPDB := &abuseIPDBStandIn{scores: map[string]int64{suspect: 100}}
+		checker := newAbuseIPDB(abuseIPDB, p)
+		m := metrics.New(1, "app")
+		m.AddReputation(reputation.New(params()), reputation.NewDNSBL(dnsblParams()))
+		m.AddAbuseIPDB(checker)
+
+		// One check that AbuseIPDB answers, and one it refuses with an answer
+		// that names the key.
+		wantScore(t, checker, suspect, true, 0, false)
+		synctest.Wait()
+		wantScore(t, checker, suspect, true, 100, true)
+
+		abuseIPDB.answerWith(http.StatusUnauthorized, `{"errors":[{"detail":"`+key+`"}]}`)
+		wantScore(t, checker, other, true, 0, false)
+		synctest.Wait()
+		wantFailures(t, checker, 1)
+
+		abuseIPDB.mu.Lock()
+		sent := slices.Clone(abuseIPDB.keys)
+		abuseIPDB.mu.Unlock()
+
+		if !slices.Equal(sent, []string{key, key}) {
+			t.Errorf("checks sent the keys %v, want %s twice", sent, key)
+		}
+
+		alerted, err := json.Marshal(waiting(queue))
+		if err != nil {
+			t.Fatalf("encode the alerts: %v", err)
+		}
+
+		kept, err := json.Marshal(checker.Snapshot())
+		if err != nil {
+			t.Fatalf("encode the checks: %v", err)
+		}
+
+		for name, shown := range map[string]string{
+			"the log": log.String(), "the alerts": string(alerted),
+			"the metrics": scrapeMetrics(t, m), "reputation.json": string(kept),
+		} {
+			if strings.Contains(shown, key) {
+				t.Errorf("%s shows the key:\n%s", name, shown)
+			}
+		}
+	})
+}
+
+func TestMetricsCountTheChecksTheFailuresAndTheBudgetLeft(t *testing.T) {
+	t.Parallel()
+
+	synctest.Test(t, func(t *testing.T) {
+		abuseIPDB := &abuseIPDBStandIn{}
+		p := abuseIPDBParams()
+		p.DailyBudget = 5
+		checker := newAbuseIPDB(abuseIPDB, p)
+		m := metrics.New(1, "app")
+		m.AddReputation(reputation.New(params()), reputation.NewDNSBL(dnsblParams()))
+		m.AddAbuseIPDB(checker)
+
+		// One check that AbuseIPDB answers, and one that fails.
+		hitFrom(t, checker, suspect, true)
+		synctest.Wait()
+		abuseIPDB.answerWith(http.StatusInternalServerError, "")
+		hitFrom(t, checker, other, true)
+		synctest.Wait()
+
+		scraped := scrapeMetrics(t, m)
+
+		for series, want := range map[string]string{
+			"queries_total":          "2",
+			"failures_total":         "1",
+			"daily_budget_remaining": "3",
+		} {
+			line := "\nsmallwebwaf_reputation_" + series +
+				`{instance="app",source="abuseipdb"} ` + want + "\n"
+			if !strings.Contains(scraped, line) {
+				t.Errorf("metrics\n%s\nwant%s", scraped, line)
+			}
+		}
+	})
+}
+
+func TestScoreFetchedATTLAgoIsNeitherUsedNorKept(t *testing.T) {
+	t.Parallel()
+
+	now := time.Date(2026, 10, 7, 0, 0, 0, 0, time.UTC)
+	p := abuseIPDBParams()
+	p.Now = func() time.Time { return now }
+	checker := reputation.NewAbuseIPDB(p)
+
+	// The last score still in use, and one, of other's /64, fetched a TTL
+	// ago.
+	inUse := reputation.Score{
+		Client: netip.MustParsePrefix(suspect + "/32"), Score: 100,
+		Fetched: now.Add(-cacheTTL + time.Nanosecond),
+	}
+	stale := reputation.Score{
+		Client: netip.MustParsePrefix("2001:db8::/64"), Score: 100,
+		Fetched: now.Add(-cacheTTL),
+	}
+
+	checker.Load(reputation.Checks{Scores: []reputation.Score{stale, inUse}})
+
+	wantScore(t, checker, suspect, false, 100, true)
+	wantScore(t, checker, other, false, 0, false)
+
+	got := checker.Snapshot().Scores
+	if !reflect.DeepEqual(got, []reputation.Score{inUse}) {
+		t.Errorf("scores %+v, want only %+v", got, inUse)
+	}
+}
+
+func TestAtMost100000ScoresKeptTheOneFetchedLongestAgoDroppedFirst(t *testing.T) {
+	t.Parallel()
+
+	now := time.Date(2026, 10, 7, 0, 0, 0, 0, time.UTC)
+	p := abuseIPDBParams()
+	p.Now = func() time.Time { return now }
+	checker := reputation.NewAbuseIPDB(p)
+
+	// 100,001 scores, listed by client, as reputation.json lists them, each
+	// fetched a millisecond before the one before it: the last is one too
+	// many.
+	const count = 100001
+
+	scores := make([]reputation.Score, 0, count)
+
+	addr := netip.MustParseAddr("198.18.0.0")
+	for i := range count {
+		scores = append(scores, reputation.Score{
+			Client:  netip.PrefixFrom(addr, 32),
+			Fetched: now.Add(-time.Duration(i) * time.Millisecond),
+		})
+		addr = addr.Next()
+	}
+
+	checker.Load(reputation.Checks{Scores: scores})
+
+	got := checker.Snapshot().Scores
+	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))
+	}
+}
+
+// abuseIPDBStandIn is a stand-in for AbuseIPDB. It answers a check sent
+// with key by the client's score, as scores gives it, 0 for a client it
+// does not give; a check sent with another key with 401; and, while
+// status is not 0, every check with status and body; and while hanging,
+// none at all. It notes each client checked, and the key sent.
+type abuseIPDBStandIn struct {
+	mu      sync.Mutex
+	scores  map[string]int64
+	status  int
+	body    string
+	hanging bool
+	checked []string
+	keys    []string
+}
+
+// RoundTrip has the stand-in answer req, in place of the network. A check
+// abandoned before the stand-in answers fails, as over the network.
+func (s *abuseIPDBStandIn) RoundTrip(req *http.Request) (*http.Response, error) {
+	client := req.URL.Query().Get("ipAddress")
+	sent := req.Header.Get("Key")
+
+	s.mu.Lock()
+	s.checked = append(s.checked, client)
+	s.keys = append(s.keys, sent)
+	score := s.scores[client]
+	status, body, hanging := s.status, s.body, s.hanging
+	s.mu.Unlock()
+
+	switch {
+	case hanging:
+		<-req.Context().Done()
+
+		return nil, req.Context().Err()
+	case sent != key:
+		status = http.StatusUnauthorized
+	case status == 0:
+		status = http.StatusOK
+		body = fmt.Sprintf(`{"data":{"ipAddress":%q,"abuseConfidenceScore":%d}}`, client,
+			score)
+	}
+
+	return &http.Response{
+		StatusCode: status,
+		Status:     fmt.Sprintf("%d %s", status, http.StatusText(status)),
+		Header:     http.Header{},
+		Body:       io.NopCloser(strings.NewReader(body)),
+		Request:    req,
+	}, nil
+}
+
+// setScore has the stand-in give client score.
+func (s *abuseIPDBStandIn) setScore(client string, score int64) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	s.scores[client] = score
+}
+
+// answerWith has the stand-in answer every check with status and body.
+func (s *abuseIPDBStandIn) answerWith(status int, body string) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	s.status, s.body = status, body
+}
+
+// abuseIPDBParams returns the AbuseIPDBParams of the tests: key, a minimum
+// score of 75, a daily budget of 900, and the cache TTL and timeout of the
+// DNSBL tests, by the bubble's clock, with alerts to a queue that sends
+// none.
+func abuseIPDBParams() reputation.AbuseIPDBParams {
+	return reputation.AbuseIPDBParams{
+		URL:         "https://abuseipdb.example/api/v2/check",
+		Key:         key,
+		MinScore:    75,
+		DailyBudget: 900,
+		CacheTTL:    cacheTTL,
+		Timeout:     timeout,
+		Now:         time.Now,
+		ProcessLog:  slog.New(slog.DiscardHandler),
+		Alerts:      newQueue(),
+	}
+}
+
+// newAbuseIPDB returns the AbuseIPDB of p, checking clients with
+// abuseIPDB.
+func newAbuseIPDB(
+	abuseIPDB *abuseIPDBStandIn, p reputation.AbuseIPDBParams,
+) *reputation.AbuseIPDB {
+	checker := reputation.NewAbuseIPDB(p)
+	checker.SetTransport(abuseIPDB)
+
+	return checker
+}
+
+// wantScore checks the score checker gives client, and whether it is a
+// hit, as a request from client finds them, offender or not.
+func wantScore(
+	t *testing.T, checker *reputation.AbuseIPDB, client string, offender bool,
+	score int64, hit bool,
+) {
+	t.Helper()
+
+	gotScore, gotHit := hitFrom(t, checker, client, offender)
+	if gotScore != score || gotHit != hit {
+		t.Errorf("%s has the score %d, a hit %t, want %d, %t", client, gotScore, gotHit,
+			score, hit)
+	}
+}
+
+// hitFrom is checker's Hit for a request from address, offender or not.
+// Its client is address for an IPv4 address, and its /64 for an IPv6 one,
+// as smallwebwaf counts clients.
+func hitFrom(
+	t *testing.T, checker *reputation.AbuseIPDB, address string, offender bool,
+) (int64, bool) {
+	t.Helper()
+
+	addr := netip.MustParseAddr(address)
+
+	client := netip.PrefixFrom(addr, addr.BitLen())
+	if addr.Is6() {
+		client = netip.PrefixFrom(addr, 64).Masked()
+	}
+
+	return checker.Hit(t.Context(), client, addr, offender)
+}
+
+// wantChecked checks the clients the stand-in was asked about, in any
+// order.
+func wantChecked(t *testing.T, abuseIPDB *abuseIPDBStandIn, want ...string) {
+	t.Helper()
+
+	abuseIPDB.mu.Lock()
+	got := slices.Sorted(slices.Values(abuseIPDB.checked))
+	abuseIPDB.mu.Unlock()
+
+	want = slices.Sorted(slices.Values(want))
+
+	if !slices.Equal(got, want) {
+		t.Errorf("checked %v, want %v", got, want)
+	}
+}
+
+// wantFailures checks how many checks failed.
+func wantFailures(t *testing.T, checker *reputation.AbuseIPDB, want int) {
+	t.Helper()
+
+	if got := checker.Failures(); got != want {
+		t.Errorf("%d checks failed, want %d", got, want)
+	}
+}
+
+// wantFailureAlert checks that the one alert waiting in queue is a
+// source_failure alert from AbuseIPDB, raised at raised, with reason and
+// the error failure, and that the cooldown has held back held repeats of
+// it.
+func wantFailureAlert(
+	t *testing.T, queue *alerts.Queue, raised time.Time, reason, failure string,
+	held int64,
+) {
+	t.Helper()
+
+	got := waiting(queue)
+	if len(got) != 1 || !got[0].Time.Equal(raised) ||
+		got[0].Event != alerts.EventSourceFailure || got[0].Reason != reason ||
+		got[0].Detail["source"] != reputation.AbuseIPDBSource ||
+		got[0].Detail["error"] != failure || queue.Suppressed() != held {
+		t.Errorf("alerts waiting %+v, %d held back, want only AbuseIPDB's %q with %q, "+
+			"and %d", got, queue.Suppressed(), reason, failure, held)
+	}
+}
+
+// wantBudgetLeft checks how many checks the day's budget has left.
+func wantBudgetLeft(t *testing.T, checker *reputation.AbuseIPDB, want int) {
+	t.Helper()
+
+	if got := checker.BudgetLeft(); got != want {
+		t.Errorf("%d checks left, want %d", got, want)
+	}
+}
+
+// scrapeMetrics returns the metrics m serves.
+func scrapeMetrics(t *testing.T, m *metrics.Metrics) string {
+	t.Helper()
+
+	scraped := httptest.NewRecorder()
+	m.ServeHTTP(scraped, httptest.NewRequestWithContext(t.Context(), http.MethodGet, "/",
+		http.NoBody))
+
+	return scraped.Body.String()
+}

internal/reputation/dnsbl.go

@@ -0,0 +1,332 @@
+package reputation
+
+import (
+	"cmp"
+	"context"
+	"encoding/hex"
+	"errors"
+	"fmt"
+	"log/slog"
+	"net"
+	"net/netip"
+	"slices"
+	"strings"
+	"sync"
+	"time"
+
+	"github.com/hashicorp/golang-lru/v2/simplelru"
+	"sneak.berlin/go/smallwebwaf/internal/alerts"
+	"sneak.berlin/go/smallwebwaf/internal/config"
+)
+
+const (
+	// maxVerdicts is how many verdicts of the DNSBL zones are kept, and how
+	// many scores of AbuseIPDB. Past it, the one fetched longest ago is
+	// dropped.
+	maxVerdicts = 100000
+	// maxQueries is how many queries may be under way at once. Past it, a
+	// zone is not asked about a client until the client's next request, so
+	// that a swarm of new addresses cannot fill the memory.
+	maxQueries = 1000
+	// failureDelay is how long a zone is not asked again after a query to
+	// it fails, and no client is checked with AbuseIPDB after a check
+	// fails, so that a source refusing them is not asked on every request.
+	failureDelay = time.Minute
+)
+
+var (
+	errAsk        = errors.New("ask the zone")
+	errRefused    = errors.New("the zone refused the query")
+	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
+// it: the zone, the client's address, whether the zone lists it, and when
+// the zone answered.
+type Verdict struct {
+	Zone    string     `json:"zone"`
+	Client  netip.Addr `json:"client"`
+	Listed  bool       `json:"listed"`
+	Fetched time.Time  `json:"fetched"`
+}
+
+// DNSBLParams are what NewDNSBL needs.
+type DNSBLParams struct {
+	// Zones are the DNSBL zones clients are asked about in
+	// (SWWAF_DNSBL_ZONES).
+	Zones []string
+	// Resolver is the resolver they are asked through
+	// (SWWAF_DNSBL_RESOLVER), or, while it is the zero AddrPort, the
+	// host's, as /etc/resolv.conf names it.
+	Resolver netip.AddrPort
+	// CacheTTL is how long a verdict is used after it was fetched
+	// (SWWAF_REPUTATION_CACHE_TTL), and Timeout how long a query may take
+	// (SWWAF_REPUTATION_TIMEOUT).
+	CacheTTL time.Duration
+	Timeout  time.Duration
+	// Now tells the time, normally time.Now in UTC.
+	Now func() time.Time
+	// ProcessLog receives each query that fails, and why.
+	ProcessLog *slog.Logger
+	// Alerts receive a source_failure alert for each query that fails.
+	Alerts *alerts.Queue
+}
+
+// DNSBL asks the DNSBL zones about clients, in the background, and keeps
+// their verdicts. It is safe for concurrent use.
+type DNSBL struct {
+	params   DNSBLParams
+	resolver *net.Resolver
+
+	mu sync.Mutex
+	// verdicts are by query. Each is added as it is fetched and never moved
+	// up, so that the one fetched longest ago is the first dropped.
+	verdicts *simplelru.LRU[query, Verdict]
+	// asking are the queries under way.
+	asking map[query]bool
+	// queries and failures count, by zone, the queries made and those that
+	// failed, and retryAt is when a zone whose last query failed may be
+	// asked again.
+	queries  map[string]int
+	failures map[string]int
+	retryAt  map[string]time.Time
+}
+
+// query is a client's address, to ask a zone about.
+type query struct {
+	zone   string
+	client netip.Addr
+}
+
+// NewDNSBL returns a DNSBL with no verdict yet.
+func NewDNSBL(params DNSBLParams) *DNSBL {
+	verdicts, err := simplelru.NewLRU[query, Verdict](maxVerdicts, nil)
+	if err != nil {
+		panic(err) // NewLRU fails only for a size below one
+	}
+
+	resolver := &net.Resolver{}
+	if params.Resolver.IsValid() {
+		// Dial is used by Go's own resolver alone.
+		resolver.PreferGo = true
+		resolver.Dial = func(ctx context.Context, network, _ string) (net.Conn, error) {
+			var dialer net.Dialer
+
+			return dialer.DialContext(ctx, network, params.Resolver.String())
+		}
+	}
+
+	return &DNSBL{
+		params:   params,
+		resolver: resolver,
+		verdicts: verdicts,
+		asking:   map[query]bool{},
+		queries:  map[string]int{},
+		failures: map[string]int{},
+		retryAt:  map[string]time.Time{},
+	}
+}
+
+// Zones returns the zones, in the order SWWAF_DNSBL_ZONES names them.
+func (d *DNSBL) Zones() []string {
+	return slices.Clone(d.params.Zones)
+}
+
+// ListedBy returns the zones whose verdict on addr, a client's address,
+// lists it, in the order SWWAF_DNSBL_ZONES names them, each with its key
+// masked, as config.MaskZoneKey masks it, since they go to the request
+// log, the alerts and the metrics. A verdict is used until CacheTTL has
+// passed since it was fetched. Each zone without one is asked about addr
+// in the background, unless a query about addr to it is under way, the
+// zone is left alone after a failure, or maxQueries are under way;
+// ListedBy never waits for a query. ctx is the context of the client's
+// request, and a query goes on after the request ends.
+func (d *DNSBL) ListedBy(ctx context.Context, addr netip.Addr) []string {
+	d.mu.Lock()
+	defer d.mu.Unlock()
+
+	now := d.params.Now()
+
+	var listedBy []string
+
+	for _, zone := range d.params.Zones {
+		q := query{zone: zone, client: addr}
+
+		kept, found := d.verdicts.Peek(q)
+
+		switch {
+		case found && now.Sub(kept.Fetched) < d.params.CacheTTL:
+			if kept.Listed {
+				listedBy = append(listedBy, config.MaskZoneKey(zone))
+			}
+		case !d.asking[q] && !now.Before(d.retryAt[zone]) && len(d.asking) < maxQueries:
+			d.asking[q] = true
+			d.queries[zone]++
+
+			go d.ask(context.WithoutCancel(ctx), q)
+		}
+	}
+
+	return listedBy
+}
+
+// Queries returns how many queries were made to zone.
+func (d *DNSBL) Queries(zone string) int {
+	d.mu.Lock()
+	defer d.mu.Unlock()
+
+	return d.queries[zone]
+}
+
+// Failures returns how many queries to zone failed.
+func (d *DNSBL) Failures(zone string) int {
+	d.mu.Lock()
+	defer d.mu.Unlock()
+
+	return d.failures[zone]
+}
+
+// Snapshot returns every verdict still in use, sorted by client, then by
+// zone, as reputation.json lists them.
+func (d *DNSBL) Snapshot() []Verdict {
+	d.mu.Lock()
+
+	now := d.params.Now()
+	verdicts := make([]Verdict, 0, d.verdicts.Len())
+
+	for _, kept := range d.verdicts.Values() {
+		if now.Sub(kept.Fetched) < d.params.CacheTTL {
+			verdicts = append(verdicts, kept)
+		}
+	}
+
+	d.mu.Unlock()
+
+	slices.SortFunc(verdicts, func(a, b Verdict) int {
+		return cmp.Or(a.Client.Compare(b.Client), strings.Compare(a.Zone, b.Zone))
+	})
+
+	return verdicts
+}
+
+// Load keeps verdicts, read from reputation.json, in place of those it
+// keeps, but for those of a zone SWWAF_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.
+func (d *DNSBL) Load(verdicts []Verdict) {
+	verdicts = slices.Clone(verdicts)
+	slices.SortStableFunc(verdicts, func(a, b Verdict) int {
+		return a.Fetched.Compare(b.Fetched)
+	})
+
+	d.mu.Lock()
+	defer d.mu.Unlock()
+
+	d.verdicts.Purge()
+
+	for _, kept := range verdicts {
+		if slices.Contains(d.params.Zones, kept.Zone) {
+			d.verdicts.Add(query{zone: kept.Zone, client: kept.Client}, kept)
+		}
+	}
+}
+
+// ask asks q's zone about q's client, keeps the verdict, and notes the
+// query as no longer under way. A query that fails gives no verdict: it
+// is counted, logged and raised as a source_failure alert, which show the
+// zone with its key masked, and the zone is not asked again for
+// failureDelay.
+func (d *DNSBL) ask(ctx context.Context, q query) {
+	listed, err := d.lookUp(ctx, q)
+	now := d.params.Now()
+
+	d.mu.Lock()
+
+	delete(d.asking, q)
+
+	if err == nil {
+		d.verdicts.Add(q, Verdict{
+			Zone: q.zone, Client: q.client, Listed: listed, Fetched: now,
+		})
+	} else {
+		d.failures[q.zone]++
+		d.retryAt[q.zone] = now.Add(failureDelay)
+	}
+
+	d.mu.Unlock()
+
+	if err != nil {
+		const failed = "asking a DNSBL zone failed"
+
+		shown := config.MaskZoneKey(q.zone)
+
+		// Raised before it is logged, so that the alert is there once the
+		// log line is.
+		raiseFailure(d.params.Alerts, failed, shown, err)
+		d.params.ProcessLog.Warn(failed, "zone", shown, "error", err.Error())
+	}
+}
+
+// lookUp asks q's zone about q's client through the resolver, and returns
+// whether the zone lists it, as readAnswer reads the answer. No such name
+// is a client the zone does not list. A query not answered within Timeout
+// fails.
+func (d *DNSBL) lookUp(ctx context.Context, q query) (bool, error) {
+	ctx, cancel := context.WithTimeout(ctx, d.params.Timeout)
+	defer cancel()
+
+	answer, err := d.resolver.LookupNetIP(ctx, "ip4", queryName(q.zone, q.client))
+
+	var dnsErr *net.DNSError
+
+	switch {
+	case err == nil:
+		return readAnswer(answer)
+	case errors.As(err, &dnsErr) && dnsErr.IsNotFound:
+		return false, nil
+	case errors.As(err, &dnsErr):
+		// The error names the name asked about, which holds the client's
+		// address, which is not to be logged: only what went wrong is kept.
+		return false, fmt.Errorf("%w: %s", errAsk, dnsErr.Err)
+	default:
+		return false, fmt.Errorf("%w: %w", errAsk, err)
+	}
+}
+
+// queryName returns the name a zone is asked about addr by, as RFC 5782
+// builds it: the four numbers of an IPv4 address, or the 32 hex digits of
+// an IPv6 address, in reverse order, each followed by a dot, then the zone
+// and a dot, which makes it a full name, to which the resolver adds no
+// search domain of /etc/resolv.conf.
+func queryName(zone string, addr netip.Addr) string {
+	parts := strings.Split(addr.String(), ".")
+	if addr.Is6() {
+		parts = strings.Split(hex.EncodeToString(addr.AsSlice()), "")
+	}
+
+	slices.Reverse(parts)
+
+	return strings.Join(parts, ".") + "." + zone + "."
+}
+
+// readAnswer reads the addresses a zone answered with. An address in
+// 127.0.0.0/8 lists the client, as RFC 5782 has zones answer, but one in
+// 127.255.255.0/24 is how Spamhaus refuses a query, such as one sent
+// through a public resolver or one past its limit, and is a failure. So is
+// an address outside 127.0.0.0/8, such as a resolver gives that answers
+// even for names that do not exist.
+func readAnswer(answer []netip.Addr) (bool, error) {
+	listing := netip.MustParsePrefix("127.0.0.0/8")
+	refusal := netip.MustParsePrefix("127.255.255.0/24")
+
+	for _, addr := range answer {
+		switch {
+		case refusal.Contains(addr):
+			return false, fmt.Errorf("%w: %s", errRefused, addr)
+		case !listing.Contains(addr):
+			return false, fmt.Errorf("%w: %s", errNotListing, addr)
+		}
+	}
+
+	return len(answer) > 0, nil
+}

internal/reputation/dnsbl_test.go

@@ -0,0 +1,737 @@
+package reputation_test
+
+import (
+	"bytes"
+	"context"
+	"encoding/binary"
+	"errors"
+	"io"
+	"log/slog"
+	"net"
+	"net/http"
+	"net/http/httptest"
+	"net/netip"
+	"reflect"
+	"slices"
+	"strings"
+	"sync"
+	"testing"
+	"testing/synctest"
+	"time"
+
+	"sneak.berlin/go/smallwebwaf/internal/alerts"
+	"sneak.berlin/go/smallwebwaf/internal/metrics"
+	"sneak.berlin/go/smallwebwaf/internal/reputation"
+)
+
+// The tests of the DNSBL zones run in synctest bubbles, as those of the
+// lists do, and the resolver the zones are asked through is a stand-in
+// reached through an in-memory connection, net.Pipe's, for the same
+// reason. They run one at a time, none in parallel with another test of
+// this package: Go's resolver counts the queries under way in one
+// sync.WaitGroup for the whole process, and the process fails when
+// queries from two bubbles, or from a bubble and from outside one, are
+// under way at once. TestMain has the resolver make its configuration,
+// which it makes on its first query, outside every bubble, since the
+// configuration holds a channel, which the bubble it was made in would
+// keep to itself.
+
+const (
+	// zone and otherZone are the DNSBL zones the tests name.
+	zone      = "dnsbl.example"
+	otherZone = "other.example"
+	// cacheTTL is the tests' SWWAF_REPUTATION_CACHE_TTL, and timeout their
+	// SWWAF_REPUTATION_TIMEOUT: a second, the least time /etc/resolv.conf
+	// can have Go's resolver wait for one server, so that it is the
+	// DNSBL's own timeout that ends a query, whatever that file says.
+	cacheTTL = 24 * time.Hour
+	timeout  = time.Second
+	// listed and unlisted are clients zone is asked about by the names
+	// listedName and unlistedName, and most tests have zone list the first
+	// alone, by answering with listing.
+	listed       = "192.0.2.99"
+	unlisted     = "192.0.2.100"
+	listedName   = "99.2.0.192." + zone + "."
+	unlistedName = "100.2.0.192." + zone + "."
+	listing      = "127.0.0.2"
+)
+
+// The DNS response codes the stand-in answers with, besides no error.
+const (
+	serverFailure = 2
+	noSuchName    = 3
+	refused       = 5
+)
+
+var errNoNetwork = errors.New("the test dials nothing")
+
+func TestMain(m *testing.M) {
+	// A query that fails at once, as nothing is dialled for it.
+	resolver := &net.Resolver{
+		PreferGo: true,
+		Dial: func(context.Context, string, string) (net.Conn, error) {
+			return nil, errNoNetwork
+		},
+	}
+	_, _ = resolver.LookupNetIP(context.Background(), "ip4", "warm-up.invalid.")
+
+	m.Run()
+}
+
+//nolint:paralleltest // one at a time, as the comment at the top of this file says
+func TestZonesListOrNotClientsByTheirIPv4AndIPv6Addresses(t *testing.T) {
+	synctest.Test(t, func(t *testing.T) {
+		// The addresses of the examples of RFC 5782, and the names it
+		// gives for them.
+		const (
+			v4 = "192.0.2.99"
+			v6 = "2001:db8:1:2:3:4:567:89ab"
+			// v6Name is the hex digits of v6, in reverse order.
+			v6Name = "b.a.9.8.7.6.5.0.4.0.0.0.3.0.0.0.2.0.0.0.1.0.0.0.8.b.d.0.1.0.0.2."
+		)
+
+		resolver := &resolverStandIn{answers: map[string]answer{
+			"99.2.0.192." + zone + ".":      {addrs: []string{listing}},
+			v6Name + otherZone + ".":        {addrs: []string{"127.0.0.4", "127.0.0.10"}},
+			"99.2.0.192." + otherZone + ".": {},
+		}}
+		dnsbl := newDNSBL(resolver, dnsblParams(zone, otherZone))
+
+		// Neither client has a verdict yet, so neither is listed, and each
+		// zone is asked about each.
+		wantZones(t, dnsbl, v4)
+		wantZones(t, dnsbl, v6)
+		synctest.Wait()
+
+		wantZones(t, dnsbl, v4, zone)
+		wantZones(t, dnsbl, v6, otherZone)
+		wantAsked(t, resolver,
+			"99.2.0.192."+zone+".", "99.2.0.192."+otherZone+".",
+			v6Name+zone+".", v6Name+otherZone+".")
+	})
+}
+
+//nolint:paralleltest // one at a time, as the comment at the top of this file says
+func TestListedByNeverWaitsForAQuery(t *testing.T) {
+	synctest.Test(t, func(t *testing.T) {
+		dnsbl := newDNSBL(&resolverStandIn{hanging: true}, dnsblParams(zone))
+		began := time.Now()
+
+		// The second, while the first's query is under way, starts none.
+		wantZones(t, dnsbl, listed)
+		wantZones(t, dnsbl, listed)
+
+		if waited := time.Since(began); waited != 0 {
+			t.Errorf("waited %s for the query, want no wait", waited)
+		}
+
+		synctest.Wait()
+		wantQueries(t, dnsbl, 1, 0)
+		waitForTheResolver()
+	})
+}
+
+//nolint:paralleltest // one at a time, as the comment at the top of this file says
+func TestVerdictUsedUntilTheCacheTTLHasPassedSinceItWasFetched(t *testing.T) {
+	synctest.Test(t, func(t *testing.T) {
+		resolver := &resolverStandIn{answers: map[string]answer{
+			listedName: {addrs: []string{listing}},
+		}}
+		dnsbl := newDNSBL(resolver, dnsblParams(zone))
+
+		wantZones(t, dnsbl, listed)
+		wantZones(t, dnsbl, unlisted)
+		synctest.Wait()
+
+		// The zone lists the other client from now on, but the verdicts
+		// kept are used, and the zone is not asked again, until the TTL
+		// has passed.
+		resolver.set(listedName, answer{rcode: noSuchName})
+		resolver.set(unlistedName, answer{addrs: []string{listing}})
+		time.Sleep(cacheTTL - time.Nanosecond)
+
+		wantZones(t, dnsbl, listed, zone)
+		wantZones(t, dnsbl, unlisted)
+		synctest.Wait()
+		wantQueries(t, dnsbl, 2, 0)
+
+		// Then neither verdict is used, and both clients are asked about
+		// again.
+		time.Sleep(time.Nanosecond)
+		wantZones(t, dnsbl, listed)
+		wantZones(t, dnsbl, unlisted)
+		synctest.Wait()
+
+		wantQueries(t, dnsbl, 4, 0)
+		wantZones(t, dnsbl, listed)
+		wantZones(t, dnsbl, unlisted, zone)
+	})
+}
+
+//nolint:paralleltest // one at a time, as the comment at the top of this file says
+func TestQueryNotAnsweredWithinTheTimeoutFails(t *testing.T) {
+	synctest.Test(t, func(t *testing.T) {
+		queue := newQueue()
+		p := dnsblParams(zone)
+		p.Alerts = queue
+		dnsbl := newDNSBL(&resolverStandIn{hanging: true}, p)
+
+		wantZones(t, dnsbl, listed)
+		time.Sleep(timeout - time.Nanosecond)
+		synctest.Wait()
+		wantQueries(t, dnsbl, 1, 0)
+
+		time.Sleep(time.Nanosecond)
+		synctest.Wait()
+		wantQueries(t, dnsbl, 1, 1)
+
+		if got := waiting(queue); len(got) != 1 ||
+			got[0].Detail["error"] != "ask the zone: i/o timeout" {
+			t.Errorf("alerts waiting %+v, want the timeout's", got)
+		}
+
+		if verdicts := dnsbl.Snapshot(); len(verdicts) != 0 {
+			t.Errorf("verdicts %+v, want none", verdicts)
+		}
+
+		waitForTheResolver()
+	})
+}
+
+//nolint:paralleltest // one at a time, as the comment at the top of this file says
+func TestZoneThatFailsOrRefusesGivesNoVerdictAndIsLeftAloneForAMinute(t *testing.T) {
+	for _, tc := range []struct {
+		name   string
+		answer answer
+		error  string
+	}{
+		{
+			"a server failure", answer{rcode: serverFailure},
+			"ask the zone: server misbehaving",
+		},
+		{"a refusal", answer{rcode: refused}, "ask the zone: server misbehaving"},
+		{
+			"an answer in 127.255.255.0/24, with which Spamhaus refuses a query",
+			answer{addrs: []string{"127.255.255.254"}},
+			"the zone refused the query: 127.255.255.254",
+		},
+		{
+			"an answer outside 127.0.0.0/8, as for a name that does not exist",
+			answer{addrs: []string{"192.0.2.1"}},
+			"the answer is outside 127.0.0.0/8: 192.0.2.1",
+		},
+	} {
+		//nolint:paralleltest // one at a time, as the comment at the top of this file says
+		t.Run(tc.name, func(t *testing.T) {
+			synctest.Test(t, func(t *testing.T) {
+				var log bytes.Buffer
+
+				queue := newQueue()
+				p := dnsblParams(zone)
+				p.Alerts = queue
+				p.ProcessLog = slog.New(slog.NewJSONHandler(&log, nil))
+				dnsbl := newDNSBL(&resolverStandIn{answers: map[string]answer{
+					listedName: tc.answer,
+				}}, p)
+
+				// The failure gives no verdict, and the zone is not asked
+				// again within a minute of it.
+				wantZones(t, dnsbl, listed)
+				synctest.Wait()
+				time.Sleep(time.Minute - time.Nanosecond)
+				wantZones(t, dnsbl, listed)
+				synctest.Wait()
+				wantQueries(t, dnsbl, 1, 1)
+
+				time.Sleep(time.Nanosecond)
+				wantZones(t, dnsbl, listed)
+				synctest.Wait()
+				wantQueries(t, dnsbl, 2, 2)
+
+				if verdicts := dnsbl.Snapshot(); len(verdicts) != 0 {
+					t.Errorf("verdicts %+v, want none", verdicts)
+				}
+
+				// One alert for the first failure; the cooldown holds back
+				// the second.
+				wantAlert(t, queue, alerts.Alert{
+					Time:   time.Now().Add(-time.Minute),
+					Event:  alerts.EventSourceFailure,
+					Reason: "asking a DNSBL zone failed",
+					Detail: map[string]any{"source": zone, "error": tc.error},
+				})
+
+				if !strings.Contains(log.String(), `"msg":"asking a DNSBL zone failed",`+
+					`"zone":"`+zone+`","error":"`+tc.error) {
+					t.Errorf("logged\n%s\nwant the failures", log.String())
+				}
+			})
+		})
+	}
+}
+
+//nolint:paralleltest // one at a time, as the comment at the top of this file says
+func TestAtMost1000QueriesUnderWay(t *testing.T) {
+	synctest.Test(t, func(t *testing.T) {
+		dnsbl := newDNSBL(&resolverStandIn{hanging: true}, dnsblParams(zone))
+
+		client := netip.MustParseAddr("198.18.0.0")
+		for range 1001 {
+			dnsbl.ListedBy(t.Context(), client)
+			client = client.Next()
+		}
+
+		synctest.Wait()
+		wantQueries(t, dnsbl, 1000, 0)
+		waitForTheResolver()
+	})
+}
+
+//nolint:paralleltest // one at a time, as the comment at the top of this file says
+func TestMetricsCountEachZonesQueriesAndThoseThatFailed(t *testing.T) {
+	synctest.Test(t, func(t *testing.T) {
+		resolver := &resolverStandIn{answers: map[string]answer{
+			listedName:                      {addrs: []string{listing}},
+			"99.2.0.192." + otherZone + ".": {rcode: serverFailure},
+		}}
+		dnsbl := newDNSBL(resolver, dnsblParams(zone, otherZone))
+		m := metrics.New(1, "app")
+		m.AddReputation(reputation.New(params()), dnsbl)
+
+		wantZones(t, dnsbl, listed)
+		synctest.Wait()
+
+		scraped := httptest.NewRecorder()
+		m.ServeHTTP(scraped, httptest.NewRequestWithContext(t.Context(), http.MethodGet,
+			"/", http.NoBody))
+
+		for series, want := range map[string]string{
+			"queries_total" + `{instance="app",source="` + zone + `"}`:       "1",
+			"failures_total" + `{instance="app",source="` + zone + `"}`:      "0",
+			"queries_total" + `{instance="app",source="` + otherZone + `"}`:  "1",
+			"failures_total" + `{instance="app",source="` + otherZone + `"}`: "1",
+		} {
+			line := "\nsmallwebwaf_reputation_" + series + " " + want + "\n"
+			if !strings.Contains(scraped.Body.String(), line) {
+				t.Errorf("metrics\n%s\nwant%s", scraped.Body.String(), line)
+			}
+		}
+	})
+}
+
+//nolint:paralleltest // one at a time, as the comment at the top of this file says
+func TestZoneKeyIsMaskedInTheVerdictsTheFailuresAndTheMetrics(t *testing.T) {
+	const (
+		key    = "abcdefghijklmnopqrstuvwxyz"
+		keyed  = key + ".xbl.dq.spamhaus.net"
+		masked = "********.xbl.dq.spamhaus.net"
+	)
+
+	synctest.Test(t, func(t *testing.T) {
+		var log bytes.Buffer
+
+		queue := newQueue()
+		p := dnsblParams(keyed)
+		p.Alerts = queue
+		p.ProcessLog = slog.New(slog.NewJSONHandler(&log, nil))
+		dnsbl := newDNSBL(&resolverStandIn{answers: map[string]answer{
+			"99.2.0.192." + keyed + ".":  {addrs: []string{listing}},
+			"100.2.0.192." + keyed + ".": {rcode: serverFailure},
+		}}, p)
+		m := metrics.New(1, "app")
+		m.AddReputation(reputation.New(params()), dnsbl)
+
+		// Both clients are asked about before either answer comes, so that
+		// the failure does not keep the zone from the other query.
+		wantZones(t, dnsbl, listed)
+		wantZones(t, dnsbl, unlisted)
+		synctest.Wait()
+		wantZones(t, dnsbl, listed, masked)
+
+		if got := waiting(queue); len(got) != 1 || got[0].Detail["source"] != masked {
+			t.Errorf("alerts waiting %+v, want the failure's, from %s", got, masked)
+		}
+
+		scraped := httptest.NewRecorder()
+		m.ServeHTTP(scraped, httptest.NewRequestWithContext(t.Context(), http.MethodGet,
+			"/", http.NoBody))
+
+		for name, shown := range map[string]string{
+			"the log": log.String(), "the metrics": scraped.Body.String(),
+		} {
+			if strings.Contains(shown, key) || !strings.Contains(shown, masked) {
+				t.Errorf("%s shows the key, or does not name the zone:\n%s", name, shown)
+			}
+		}
+	})
+}
+
+//nolint:paralleltest // one at a time, as the comment at the top of this file says
+func TestVerdictsKeptAcrossARestart(t *testing.T) {
+	synctest.Test(t, func(t *testing.T) {
+		resolver := &resolverStandIn{answers: map[string]answer{
+			listedName: {addrs: []string{listing}},
+		}}
+		dnsbl := newDNSBL(resolver, dnsblParams(zone))
+		fetched := time.Now()
+
+		wantZones(t, dnsbl, unlisted)
+		wantZones(t, dnsbl, listed)
+		synctest.Wait()
+
+		kept := dnsbl.Snapshot()
+
+		want := []reputation.Verdict{
+			{Zone: zone, Client: netip.MustParseAddr(listed), Listed: true, Fetched: fetched},
+			{Zone: zone, Client: netip.MustParseAddr(unlisted), Fetched: fetched},
+		}
+		if !reflect.DeepEqual(kept, want) {
+			t.Errorf("verdicts %+v, want %+v", kept, want)
+		}
+
+		// Restarted an hour later with what reputation.json keeps, it uses
+		// the verdicts, and asks the zone nothing, until the TTL has passed
+		// since they were fetched.
+		time.Sleep(time.Hour)
+
+		restarted := &resolverStandIn{}
+		again := newDNSBL(restarted, dnsblParams(zone))
+		again.Load(kept)
+
+		wantZones(t, again, listed, zone)
+		wantZones(t, again, unlisted)
+		synctest.Wait()
+		wantAsked(t, restarted)
+
+		time.Sleep(cacheTTL - time.Hour)
+		wantZones(t, again, listed)
+		synctest.Wait()
+		wantAsked(t, restarted, listedName)
+	})
+}
+
+func TestNeitherAVerdictOfAZoneNotNamedNorOnePastItsTTLIsKept(t *testing.T) {
+	t.Parallel()
+
+	now := time.Date(2026, 10, 7, 0, 0, 0, 0, time.UTC)
+	p := dnsblParams(zone)
+	p.Now = func() time.Time { return now }
+	dnsbl := reputation.NewDNSBL(p)
+
+	// The last verdict still in use, one fetched a TTL ago, and one of a
+	// zone SWWAF_DNSBL_ZONES does not name.
+	inUse := reputation.Verdict{
+		Zone: zone, Client: netip.MustParseAddr(listed), Listed: true,
+		Fetched: now.Add(-cacheTTL + time.Nanosecond),
+	}
+	stale := reputation.Verdict{
+		Zone: zone, Client: netip.MustParseAddr(unlisted), Fetched: now.Add(-cacheTTL),
+	}
+	notNamed := reputation.Verdict{
+		Zone: otherZone, Client: netip.MustParseAddr(listed), Listed: true, Fetched: now,
+	}
+
+	dnsbl.Load([]reputation.Verdict{notNamed, stale, inUse})
+
+	if got := dnsbl.Snapshot(); !reflect.DeepEqual(got, []reputation.Verdict{inUse}) {
+		t.Errorf("verdicts %+v, want only %+v", got, inUse)
+	}
+}
+
+func TestAtMost100000VerdictsKeptTheOneFetchedLongestAgoDroppedFirst(t *testing.T) {
+	t.Parallel()
+
+	now := time.Date(2026, 10, 7, 0, 0, 0, 0, time.UTC)
+	p := dnsblParams(zone)
+	p.Now = func() time.Time { return now }
+	dnsbl := reputation.NewDNSBL(p)
+
+	// 100,001 verdicts, listed by client, as reputation.json lists them,
+	// each fetched a millisecond before the one before it: the last is one
+	// too many.
+	const count = 100001
+
+	verdicts := make([]reputation.Verdict, 0, count)
+
+	client := netip.MustParseAddr("198.18.0.0")
+	for i := range count {
+		verdicts = append(verdicts, reputation.Verdict{
+			Zone: zone, Client: client, Fetched: now.Add(-time.Duration(i) * time.Millisecond),
+		})
+		client = client.Next()
+	}
+
+	dnsbl.Load(verdicts)
+
+	got := dnsbl.Snapshot()
+	if len(got) != count-1 || !slices.Contains(got, verdicts[0]) ||
+		slices.Contains(got, verdicts[count-1]) {
+		t.Errorf("%d verdicts kept, want all but the one fetched longest ago", len(got))
+	}
+}
+
+//nolint:paralleltest // one at a time, as the comment at the top of this file says
+func TestQueriesGoToTheResolverSWWAFDNSBLResolverNames(t *testing.T) {
+	resolver := &resolverStandIn{answers: map[string]answer{
+		listedName: {addrs: []string{listing}},
+	}}
+
+	conn, err := (&net.ListenConfig{}).ListenPacket(t.Context(), "udp", "127.0.0.1:0")
+	if err != nil {
+		t.Fatalf("listen: %v", err)
+	}
+
+	served := make(chan struct{})
+
+	go func() {
+		resolver.serveUDP(conn)
+		close(served)
+	}()
+
+	t.Cleanup(func() {
+		_ = conn.Close()
+
+		<-served
+	})
+
+	p := dnsblParams(zone)
+	p.Resolver = netip.MustParseAddrPort(conn.LocalAddr().String())
+	// On the real clock: the stand-in answers at once, so only a test
+	// process held up for a whole minute would see the query fail.
+	p.Timeout = time.Minute
+
+	isListed, err := reputation.NewDNSBL(p).LookUp(zone, netip.MustParseAddr(listed))
+	if err != nil || !isListed {
+		t.Errorf("listed %t (%v), want true", isListed, err)
+	}
+
+	wantAsked(t, resolver, listedName)
+}
+
+// resolverStandIn is a stand-in for the resolver the zones are asked
+// through. It answers each query by the name asked about, as answers
+// gives, with no such name for a name answers does not give, and not at
+// all while hanging. It notes each name asked about.
+type resolverStandIn struct {
+	mu      sync.Mutex
+	answers map[string]answer
+	hanging bool
+	names   []string
+}
+
+// answer is how the stand-in answers a name: with an A record of each of
+// addrs, or with the response code rcode, unless it is 0, for no error.
+type answer struct {
+	addrs []string
+	rcode uint16
+}
+
+// What the stand-in reads of a query, and writes in its reply.
+const (
+	// headerLength is the length of a DNS message's header, which the
+	// question follows: its id, its flags, and how many questions,
+	// answers and other records it holds, two bytes each.
+	headerLength = 12
+	// typeAndClass is the length of the type and the class that end a
+	// question, after its name.
+	typeAndClass = 4
+	// replyFlags mark a reply to a query that asked for recursion, which
+	// is available, with no error. The response code goes in their last
+	// four bits.
+	replyFlags = 0x8180
+	// maxMessage is the longest query read over UDP.
+	maxMessage = 1232
+)
+
+// set has the stand-in answer name with given.
+func (s *resolverStandIn) set(name string, given answer) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	s.answers[name] = given
+}
+
+// dial connects Go's resolver to the stand-in through an in-memory
+// connection, on which it sends each query, and reads each reply, after
+// its length, as over TCP.
+func (s *resolverStandIn) dial(context.Context, string, string) (net.Conn, error) {
+	client, server := net.Pipe()
+
+	go s.serve(server)
+
+	return client, nil
+}
+
+// serve answers the queries that come on conn until the resolver closes
+// it.
+func (s *resolverStandIn) serve(conn net.Conn) {
+	defer func() {
+		_ = conn.Close()
+	}()
+
+	for {
+		var length [2]byte
+
+		_, err := io.ReadFull(conn, length[:])
+		if err != nil {
+			return
+		}
+
+		message := make([]byte, binary.BigEndian.Uint16(length[:]))
+
+		_, err = io.ReadFull(conn, message)
+		if err != nil {
+			return
+		}
+
+		reply, answered := s.reply(message)
+		if !answered {
+			continue // the resolver gives up, and closes conn
+		}
+
+		//nolint:gosec // a reply of a few dozen bytes
+		_, err = conn.Write(append(binary.BigEndian.AppendUint16(nil, uint16(len(reply))),
+			reply...))
+		if err != nil {
+			return
+		}
+	}
+}
+
+// serveUDP answers the queries that come on conn, each in a datagram, as
+// a resolver does, until conn is closed.
+func (s *resolverStandIn) serveUDP(conn net.PacketConn) {
+	message := make([]byte, maxMessage)
+
+	for {
+		n, from, err := conn.ReadFrom(message)
+		if err != nil {
+			return
+		}
+
+		reply, answered := s.reply(message[:n])
+		if answered {
+			_, _ = conn.WriteTo(reply, from)
+		}
+	}
+}
+
+// reply returns the stand-in's reply to message, a query, and false for
+// none, while it hangs. It notes the name asked about.
+func (s *resolverStandIn) reply(message []byte) ([]byte, bool) {
+	// The name is labels, each after its length, ended by a length of 0.
+	var labels []string
+
+	end := headerLength
+	for message[end] != 0 {
+		length := int(message[end])
+		labels = append(labels, string(message[end+1:end+1+length]))
+		end += 1 + length
+	}
+
+	end += 1 + typeAndClass
+	name := strings.Join(labels, ".") + "."
+
+	s.mu.Lock()
+	s.names = append(s.names, name)
+	given, found := s.answers[name]
+	hanging := s.hanging
+	s.mu.Unlock()
+
+	if hanging {
+		return nil, false
+	}
+
+	if !found {
+		given = answer{rcode: noSuchName}
+	}
+
+	// The query's id, the flags, one question, the answers, and no other
+	// records, then the question, as asked.
+	reply := slices.Clone(message[:2])
+	reply = binary.BigEndian.AppendUint16(reply, replyFlags|given.rcode)
+	reply = binary.BigEndian.AppendUint16(reply, 1)
+	//nolint:gosec // a handful of answers
+	reply = binary.BigEndian.AppendUint16(reply, uint16(len(given.addrs)))
+	reply = append(reply, 0, 0, 0, 0)
+	reply = append(reply, message[headerLength:end]...)
+
+	// An A record starts with the name asked about, by a pointer to it in
+	// the question, then its type, A, its class, IN, how long it may be
+	// kept, 60 seconds, and the length of its address, 4 bytes.
+	record := []byte{0xc0, headerLength, 0, 1, 0, 1, 0, 0, 0, 60, 0, 4}
+
+	for _, addr := range given.addrs {
+		reply = append(reply, record...)
+		reply = append(reply, netip.MustParseAddr(addr).AsSlice()...)
+	}
+
+	return reply, true
+}
+
+// dnsblParams returns the DNSBLParams of zones, with the tests' cache TTL
+// and timeout, by the bubble's clock, with alerts to a queue that sends
+// none.
+func dnsblParams(zones ...string) reputation.DNSBLParams {
+	return reputation.DNSBLParams{
+		Zones:      zones,
+		CacheTTL:   cacheTTL,
+		Timeout:    timeout,
+		Now:        time.Now,
+		ProcessLog: slog.New(slog.DiscardHandler),
+		Alerts:     newQueue(),
+	}
+}
+
+// waitForTheResolver waits, on the bubble's clock, an hour, until Go's
+// resolver has given up on every stand-in that does not answer: it waits
+// for a server as long as /etc/resolv.conf has it wait, a few seconds,
+// even after the query was given up, and a bubble cannot end before it.
+func waitForTheResolver() {
+	time.Sleep(time.Hour)
+}
+
+// newDNSBL returns the DNSBL of p, asking resolver.
+func newDNSBL(resolver *resolverStandIn, p reputation.DNSBLParams) *reputation.DNSBL {
+	dnsbl := reputation.NewDNSBL(p)
+	dnsbl.SetDial(resolver.dial)
+
+	return dnsbl
+}
+
+// wantZones checks the zones whose verdict dnsbl says lists client, as a
+// request from client finds them.
+func wantZones(t *testing.T, dnsbl *reputation.DNSBL, client string, want ...string) {
+	t.Helper()
+
+	got := dnsbl.ListedBy(t.Context(), netip.MustParseAddr(client))
+	if !slices.Equal(got, want) {
+		t.Errorf("%s is listed by %v, want %v", client, got, want)
+	}
+}
+
+// wantQueries checks how many queries dnsbl made to zone, and how many of
+// them failed.
+func wantQueries(t *testing.T, dnsbl *reputation.DNSBL, queries, failures int) {
+	t.Helper()
+
+	if dnsbl.Queries(zone) != queries || dnsbl.Failures(zone) != failures {
+		t.Errorf("%d queries and %d failures, want %d and %d", dnsbl.Queries(zone),
+			dnsbl.Failures(zone), queries, failures)
+	}
+}
+
+// wantAsked checks the names the stand-in was asked about, in any order.
+func wantAsked(t *testing.T, resolver *resolverStandIn, want ...string) {
+	t.Helper()
+
+	resolver.mu.Lock()
+	got := slices.Sorted(slices.Values(resolver.names))
+	resolver.mu.Unlock()
+
+	slices.Sort(want)
+
+	if !slices.Equal(got, want) {
+		t.Errorf("asked about %v, want %v", got, want)
+	}
+}

internal/reputation/export_test.go

@@ -0,0 +1,33 @@
+package reputation
+
+import (
+	"context"
+	"net"
+	"net/http"
+	"net/netip"
+)
+
+// SetTransport has l's fetches go through transport instead of the
+// network.
+func (l *Lists) SetTransport(transport http.RoundTripper) {
+	l.httpClient.Transport = transport
+}
+
+// SetTransport has a's checks go through transport instead of the
+// network.
+func (a *AbuseIPDB) SetTransport(transport http.RoundTripper) {
+	a.httpClient.Transport = transport
+}
+
+// SetDial has d's queries go through dial instead of the network.
+func (d *DNSBL) SetDial(
+	dial func(ctx context.Context, network, address string) (net.Conn, error),
+) {
+	d.resolver = &net.Resolver{PreferGo: true, Dial: dial}
+}
+
+// LookUp asks zone about addr at once, as a query in the background does,
+// and returns whether zone lists addr.
+func (d *DNSBL) LookUp(zone string, addr netip.Addr) (bool, error) {
+	return d.lookUp(context.Background(), query{zone: zone, client: addr})
+}

internal/reputation/reputation.go

@@ -0,0 +1,509 @@
+// Package reputation fetches the lists the settings name by URL: the
+// blocklists of SWWAF_BLOCKLIST_URLS, and the file of AS:percent lines
+// SWWAF_ASN_LIMIT_PERCENT_URL names. It keeps the last good copy of each,
+// whole, comment lines included, which is used while a fetch fails, and
+// when each was last tried. It also asks the DNSBL zones of
+// SWWAF_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.
+package reputation
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"io"
+	"log/slog"
+	"net/http"
+	"net/netip"
+	"slices"
+	"strings"
+	"sync"
+	"time"
+
+	"sneak.berlin/go/smallwebwaf/internal/alerts"
+	"sneak.berlin/go/smallwebwaf/internal/config"
+)
+
+const (
+	// maxListBytes is the most of a list that is read. A longer one is a
+	// failure, so that a wrong URL cannot fill the memory.
+	maxListBytes = 16 << 20
+	// fetchTimeout bounds one fetch of a list.
+	fetchTimeout = time.Minute
+	// mappedBits is the length of ::ffff:0.0.0.0/96, the netblock of every
+	// IPv4-mapped address.
+	mappedBits = 96
+)
+
+var (
+	errStatus        = errors.New("the server answered")
+	errTooLong       = errors.New("the list is longer than 16 MiB")
+	errNotNetblock   = errors.New("is not an address or a netblock, such as 192.0.2.0/24")
+	errNotASNPercent = errors.New(
+		"is not an AS number, : and a percentage, such as AS64496:50")
+)
+
+// List is a list as reputation.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.
+type List struct {
+	URL     string    `json:"url"`
+	Tried   time.Time `json:"tried"`
+	Fetched time.Time `json:"fetched,omitzero"`
+	Lines   []string  `json:"lines,omitzero"`
+}
+
+// Params are what New needs.
+type Params struct {
+	// BlocklistURLs are the blocklists (SWWAF_BLOCKLIST_URLS), and
+	// ASNLimitPercentURL the file of AS:percent lines
+	// (SWWAF_ASN_LIMIT_PERCENT_URL), "" while it is unset.
+	BlocklistURLs      []string
+	ASNLimitPercentURL string
+	// Refresh is how long after a list was last fetched or tried it is
+	// fetched again (SWWAF_BLOCKLIST_REFRESH).
+	Refresh time.Duration
+	// Now tells the time, normally time.Now in UTC.
+	Now func() time.Time
+	// ProcessLog receives each fetch of a list, and why one failed.
+	ProcessLog *slog.Logger
+	// Alerts receive a source_failure alert for each fetch that fails.
+	Alerts *alerts.Queue
+}
+
+// Lists are the lists Params names, each with its last good copy. They
+// are safe for concurrent use.
+type Lists struct {
+	params     Params
+	httpClient *http.Client
+
+	mu sync.Mutex
+	// lists are by URL, one for each URL Params names.
+	lists map[string]*list
+}
+
+// list is one list: what reputation.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 {
+	kept     List
+	entries  entries
+	failures int
+}
+
+// entries are what the lines of a copy say: for a blocklist, the netblocks
+// it names, with the lengths among them, and for the file of AS:percent
+// lines, the percentage it gives each AS number.
+type entries struct {
+	netblocks map[netip.Prefix]bool
+	lengths   []int
+	percents  map[string]int64
+}
+
+// New returns the lists, without a copy of any yet.
+func New(params Params) *Lists {
+	l := &Lists{params: params, httpClient: &http.Client{}, lists: map[string]*list{}}
+
+	for _, listURL := range l.URLs() {
+		l.lists[listURL] = &list{kept: List{URL: listURL}}
+	}
+
+	return l
+}
+
+// URLs returns the URL of every list: the blocklists' in the order
+// SWWAF_BLOCKLIST_URLS names them, then SWWAF_ASN_LIMIT_PERCENT_URL.
+func (l *Lists) URLs() []string {
+	urls := slices.Clone(l.params.BlocklistURLs)
+	if l.params.ASNLimitPercentURL != "" {
+		urls = append(urls, l.params.ASNLimitPercentURL)
+	}
+
+	return urls
+}
+
+// ListedBy returns the URLs of the blocklists whose copy lists addr, in
+// the order SWWAF_BLOCKLIST_URLS names them.
+func (l *Lists) ListedBy(addr netip.Addr) []string {
+	l.mu.Lock()
+	defer l.mu.Unlock()
+
+	var listedBy []string
+
+	for _, listURL := range l.params.BlocklistURLs {
+		if l.lists[listURL].entries.contain(addr) {
+			listedBy = append(listedBy, listURL)
+		}
+	}
+
+	return listedBy
+}
+
+// ASNLimitPercent returns the percentage the copy of the file of
+// AS:percent lines gives asn, and whether it lists asn.
+func (l *Lists) ASNLimitPercent(asn string) (int64, bool) {
+	if l.params.ASNLimitPercentURL == "" {
+		return 0, false
+	}
+
+	l.mu.Lock()
+	defer l.mu.Unlock()
+
+	percent, listed := l.lists[l.params.ASNLimitPercentURL].entries.percents[asn]
+
+	return percent, listed
+}
+
+// Fetched returns when the copy in use of the list at listURL was
+// fetched, or zero while there is none.
+func (l *Lists) Fetched(listURL string) time.Time {
+	l.mu.Lock()
+	defer l.mu.Unlock()
+
+	return l.lists[listURL].kept.Fetched
+}
+
+// Failures returns how many fetches of the list at listURL failed.
+func (l *Lists) Failures(listURL string) int {
+	l.mu.Lock()
+	defer l.mu.Unlock()
+
+	return l.lists[listURL].failures
+}
+
+// Run fetches each list once Refresh has passed since it was last fetched
+// or tried, the later of the two, until ctx is done. A list never tried is
+// fetched at once, and so is one whose last try or copy, read from
+// reputation.json, is that old.
+func (l *Lists) Run(ctx context.Context) {
+	if len(l.lists) == 0 {
+		return
+	}
+
+	for ctx.Err() == nil {
+		next := l.fetchDue(ctx)
+		timer := time.NewTimer(next.Sub(l.params.Now()))
+
+		select {
+		case <-ctx.Done():
+		case <-timer.C:
+		}
+
+		timer.Stop()
+	}
+}
+
+// Snapshot returns each list that has been tried, with its copy, if it
+// has one, sorted by URL, as reputation.json lists them.
+func (l *Lists) Snapshot() []List {
+	l.mu.Lock()
+
+	tried := make([]List, 0, len(l.lists))
+
+	for _, held := range l.lists {
+		if !held.kept.Tried.IsZero() {
+			tried = append(tried, held.kept)
+		}
+	}
+
+	l.mu.Unlock()
+
+	slices.SortFunc(tried, func(a, b List) int {
+		return strings.Compare(a.URL, b.URL)
+	})
+
+	return tried
+}
+
+// Load puts lists, read from reputation.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 {
+	found := make(map[string]entries, len(lists))
+
+	for _, kept := range lists {
+		if _, named := l.lists[kept.URL]; !named {
+			continue
+		}
+
+		read, err := l.parse(kept.URL, kept.Lines)
+		if err != nil {
+			return fmt.Errorf("the copy of %s: %w", kept.URL, err)
+		}
+
+		found[kept.URL] = read
+	}
+
+	l.mu.Lock()
+	defer l.mu.Unlock()
+
+	for listURL, held := range l.lists {
+		held.kept, held.entries = List{URL: listURL}, entries{}
+	}
+
+	for _, kept := range lists {
+		read, named := found[kept.URL]
+		if named {
+			l.lists[kept.URL].kept, l.lists[kept.URL].entries = kept, read
+		}
+	}
+
+	return nil
+}
+
+// fetchDue fetches each list that is due, one after another, and returns
+// when the next is due. Once ctx has ended, it starts none, since a fetch
+// cut off is noted as a try.
+func (l *Lists) fetchDue(ctx context.Context) time.Time {
+	var next time.Time
+
+	for _, listURL := range l.URLs() {
+		due := l.due(listURL)
+		if ctx.Err() == nil && !l.params.Now().Before(due) {
+			l.fetch(ctx, listURL)
+			due = l.due(listURL)
+		}
+
+		if next.IsZero() || due.Before(next) {
+			next = due
+		}
+	}
+
+	return next
+}
+
+// due returns when the list at listURL is to be fetched: Refresh after it
+// was last fetched or tried, the later of the two.
+func (l *Lists) due(listURL string) time.Time {
+	l.mu.Lock()
+	defer l.mu.Unlock()
+
+	held := l.lists[listURL]
+
+	last := held.kept.Fetched
+	if held.kept.Tried.After(last) {
+		last = held.kept.Tried
+	}
+
+	return last.Add(l.params.Refresh)
+}
+
+// fetch fetches the list at listURL, and notes the try. A good copy takes
+// the place of the one held. A failure leaves that in use, and is counted,
+// logged and raised as a source_failure alert. A fetch cut off as ctx
+// ends, as smallwebwaf stops, is no failure, but is still noted as a try,
+// so that a restart waits for it: the server may have had its request.
+func (l *Lists) fetch(ctx context.Context, listURL string) {
+	lines, err := l.get(ctx, listURL)
+
+	var found entries
+	if err == nil {
+		found, err = l.parse(listURL, lines)
+	}
+
+	cutOff := err != nil && ctx.Err() != nil
+	now := l.params.Now()
+
+	l.mu.Lock()
+
+	held := l.lists[listURL]
+	held.kept.Tried = now
+
+	if err == nil {
+		held.kept.Fetched, held.kept.Lines = now, lines
+		held.entries = found
+	} else if !cutOff {
+		held.failures++
+	}
+
+	l.mu.Unlock()
+
+	if cutOff {
+		return
+	}
+
+	if err != nil {
+		const failed = "fetching a list failed"
+
+		// Raised before it is logged, so that the alert is there once the
+		// log line is.
+		raiseFailure(l.params.Alerts, failed, listURL, err)
+		l.params.ProcessLog.Warn(failed, "url", listURL, "error", err.Error())
+
+		return
+	}
+
+	l.params.ProcessLog.Info("fetched a list", "url", listURL, "lines", len(lines))
+}
+
+// raiseFailure raises a source_failure alert into queue, with reason, and
+// in its detail the source that failed, a list's URL, a zone with its key
+// masked or abuseipdb, and err.
+func raiseFailure(queue *alerts.Queue, reason, source string, err error) {
+	queue.Raise(alerts.Alert{
+		Event:  alerts.EventSourceFailure,
+		Reason: reason,
+		Detail: map[string]any{"source": source, "error": err.Error()},
+	})
+}
+
+// get fetches the list at listURL, and returns its lines. An answer other
+// than 200, or a list longer than maxListBytes, is a failure.
+func (l *Lists) get(ctx context.Context, listURL string) ([]string, error) {
+	ctx, cancel := context.WithTimeout(ctx, fetchTimeout)
+	defer cancel()
+
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, listURL, http.NoBody)
+	if err != nil {
+		return nil, fmt.Errorf("make the request: %w", err)
+	}
+
+	res, err := l.httpClient.Do(req)
+	if err != nil {
+		// Do's error names the URL, which the log line and the alert name
+		// already: only what went wrong is kept.
+		return nil, fmt.Errorf("fetch the list: %w", errors.Unwrap(err))
+	}
+
+	defer func() {
+		_ = res.Body.Close()
+	}()
+
+	if res.StatusCode != http.StatusOK {
+		return nil, fmt.Errorf("%w %s", errStatus, res.Status)
+	}
+
+	body, err := io.ReadAll(io.LimitReader(res.Body, maxListBytes+1))
+	if err != nil {
+		return nil, fmt.Errorf("read the list: %w", err)
+	}
+
+	if len(body) > maxListBytes {
+		return nil, errTooLong
+	}
+
+	lines := []string{}
+	for line := range strings.Lines(string(body)) {
+		lines = append(lines, strings.TrimSuffix(line, "\n"))
+	}
+
+	return lines, nil
+}
+
+// parse reads the lines of the list at listURL: those of a blocklist, or
+// of the file of AS:percent lines. Anything after a ; or a # on a line is
+// left out, and so is a line left blank. Any other line that does not read
+// is an error naming it by its number.
+func (l *Lists) parse(listURL string, lines []string) (entries, error) {
+	if listURL == l.params.ASNLimitPercentURL {
+		return parsePercents(lines)
+	}
+
+	return parseNetblocks(lines)
+}
+
+// parseNetblocks reads a blocklist's lines, each an address or a netblock
+// as the settings take them.
+func parseNetblocks(lines []string) (entries, error) {
+	found := entries{netblocks: map[netip.Prefix]bool{}}
+
+	for i, line := range lines {
+		text := withoutComment(line)
+		if text == "" {
+			continue
+		}
+
+		netblock, ok := parseNetblock(text)
+		if !ok {
+			return entries{}, fmt.Errorf("line %d %w", i+1, errNotNetblock)
+		}
+
+		found.netblocks[netblock] = true
+
+		if !slices.Contains(found.lengths, netblock.Bits()) {
+			found.lengths = append(found.lengths, netblock.Bits())
+		}
+	}
+
+	return found, nil
+}
+
+// parseNetblock reads text, a line of a blocklist, and reports whether it
+// is an address or a netblock as the settings take them. A client's IPv4
+// address is checked as IPv4, never IPv4-mapped, so an IPv4-mapped line,
+// such as ::ffff:192.0.2.0/120, is read as the IPv4 address or netblock it
+// stands for, 192.0.2.0/24, and a mapped netblock shorter than /96, which
+// stands for none, is refused.
+func parseNetblock(text string) (netip.Prefix, bool) {
+	netblock, err := config.ParseNetblock(text)
+	if err != nil {
+		return netip.Prefix{}, false
+	}
+
+	// The address as written: ParseNetblock's has the bits past the
+	// netblock's length cleared, the ::ffff among them below /96.
+	written, _, _ := strings.Cut(text, "/")
+	if addr, _ := netip.ParseAddr(written); !addr.Is4In6() {
+		return netblock, true
+	}
+
+	if netblock.Bits() < mappedBits {
+		return netip.Prefix{}, false
+	}
+
+	return netip.PrefixFrom(netblock.Addr().Unmap(), netblock.Bits()-mappedBits), true
+}
+
+// parsePercents reads the lines of the file of AS:percent lines, each an
+// AS number, : and a percentage, as SWWAF_ASN_LIMIT_PERCENT takes them. An
+// AS number listed more than once gets the lowest of its percentages.
+func parsePercents(lines []string) (entries, error) {
+	found := entries{percents: map[string]int64{}}
+
+	for i, line := range lines {
+		text := withoutComment(line)
+		if text == "" {
+			continue
+		}
+
+		asnText, percentText, _ := strings.Cut(text, ":")
+		asn, asnErr := config.ParseASN(asnText)
+
+		percent, percentErr := config.ParsePercent(percentText)
+		if asnErr != nil || percentErr != nil {
+			return entries{}, fmt.Errorf("line %d %w", i+1, errNotASNPercent)
+		}
+
+		earlier, listed := found.percents[asn]
+		if !listed || percent < earlier {
+			found.percents[asn] = percent
+		}
+	}
+
+	return found, nil
+}
+
+// withoutComment returns line without anything after a ; or a #, and
+// without the spaces around what is left.
+func withoutComment(line string) string {
+	text, _, _ := strings.Cut(line, ";")
+	text, _, _ = strings.Cut(text, "#")
+
+	return strings.TrimSpace(text)
+}
+
+// contain reports whether the netblocks of a blocklist's copy hold addr:
+// whether addr, cut to one of their lengths, is one of them.
+func (e entries) contain(addr netip.Addr) bool {
+	for _, length := range e.lengths {
+		netblock, err := addr.Prefix(length)
+		if err == nil && e.netblocks[netblock] {
+			return true
+		}
+	}
+
+	return false
+}

internal/reputation/reputation_test.go

@@ -0,0 +1,610 @@
+package reputation_test
+
+import (
+	"bytes"
+	"context"
+	"fmt"
+	"io"
+	"log/slog"
+	"net/http"
+	"net/netip"
+	"net/url"
+	"reflect"
+	"slices"
+	"strings"
+	"sync"
+	"testing"
+	"testing/synctest"
+	"time"
+
+	"sneak.berlin/go/smallwebwaf/internal/alerts"
+	"sneak.berlin/go/smallwebwaf/internal/reputation"
+)
+
+// The tests run in a synctest bubble, where the time package runs on a
+// clock of the test's own: time.Sleep moves it on at once, and
+// synctest.Wait returns once Run waits for the next list to be due, so
+// that every fetch due by then has been made. The stand-in for the
+// servers the lists are fetched from answers without the network, since a
+// fetch waiting on the network would keep that clock from moving on.
+
+const (
+	// dropURL and torURL are the blocklists, and asnURL the file of
+	// AS:percent lines.
+	dropURL = "https://lists.example/drop.txt"
+	torURL  = "https://lists.example/tor.txt"
+	asnURL  = "https://lists.example/asn.txt"
+	// refresh is the tests' SWWAF_BLOCKLIST_REFRESH, and cooldown their
+	// SWWAF_ALERT_COOLDOWN, longer than it.
+	refresh  = 24 * time.Hour
+	cooldown = 48 * time.Hour
+	// drop is a blocklist as the Spamhaus DROP list is written, with an
+	// address and a netblock in each of its comments, which list nothing.
+	drop = "; Spamhaus DROP List 2026/10/07 - (c) 2026 The Spamhaus Project SLL\n" +
+		"; Last-Modified: Wed, 07 Oct 2026 00:00:00 GMT ; 192.0.2.1\n" +
+		"# 198.51.100.0/24\n" +
+		"\n" +
+		"203.0.113.0/24 ; SBL1\n" +
+		"  192.0.2.9  # one address\n" +
+		"2001:db8:1::/48 ; SBL2\n"
+)
+
+func TestListedAddressesAndNetblocksWithTheCommentsLeftOut(t *testing.T) {
+	t.Parallel()
+
+	synctest.Test(t, func(t *testing.T) {
+		servers := &standIn{lists: map[string]string{dropURL: drop}}
+		lists := start(t, servers, params(dropURL))
+
+		for addr, want := range map[string][]string{
+			"203.0.113.0":   {dropURL},
+			"203.0.113.255": {dropURL},
+			"192.0.2.9":     {dropURL},
+			"2001:db8:1::7": {dropURL},
+			"203.0.114.0":   nil,
+			"192.0.2.8":     nil,
+			"192.0.2.1":     nil,
+			"198.51.100.7":  nil,
+			"2001:db8:2::7": nil,
+		} {
+			wantListedBy(t, lists, addr, want...)
+		}
+	})
+}
+
+func TestIPv4MappedLineListsTheIPv4AddressOrNetblockItStandsFor(t *testing.T) {
+	t.Parallel()
+
+	now := time.Now()
+	lists := reputation.New(params(dropURL))
+
+	err := lists.Load([]reputation.List{{
+		URL: dropURL, Tried: now, Fetched: now,
+		Lines: []string{"::ffff:192.0.2.9", "::ffff:203.0.113.0/120"},
+	}})
+	if err != nil {
+		t.Fatalf("load: %v", err)
+	}
+
+	for addr, want := range map[string][]string{
+		"192.0.2.9":     {dropURL},
+		"203.0.113.255": {dropURL},
+		"192.0.2.8":     nil,
+		"203.0.114.0":   nil,
+	} {
+		wantListedBy(t, lists, addr, want...)
+	}
+
+	// A mapped netblock shorter than /96 stands for no IPv4 one.
+	err = lists.Load([]reputation.List{{
+		URL: dropURL, Tried: now, Fetched: now, Lines: []string{"::ffff:198.51.100.0/88"},
+	}})
+
+	const want = "the copy of " + dropURL +
+		": line 1 is not an address or a netblock, such as 192.0.2.0/24"
+	if err == nil || err.Error() != want {
+		t.Errorf("error %v, want %s", err, want)
+	}
+}
+
+func TestClientIsListedByEachBlocklistThatListsIt(t *testing.T) {
+	t.Parallel()
+
+	synctest.Test(t, func(t *testing.T) {
+		servers := &standIn{lists: map[string]string{
+			dropURL: "203.0.113.0/24\n", torURL: "203.0.113.9\n",
+		}}
+		lists := start(t, servers, params(torURL, dropURL))
+
+		// In the order SWWAF_BLOCKLIST_URLS names them.
+		wantListedBy(t, lists, "203.0.113.9", torURL, dropURL)
+		wantListedBy(t, lists, "203.0.113.8", dropURL)
+	})
+}
+
+func TestListFetchedAgainOnceRefreshHasPassed(t *testing.T) {
+	t.Parallel()
+
+	synctest.Test(t, func(t *testing.T) {
+		servers := &standIn{lists: map[string]string{dropURL: "203.0.113.9\n"}}
+		lists := start(t, servers, params(dropURL))
+		began := time.Now()
+
+		wantFetches(t, servers, 1)
+
+		servers.set(dropURL, "203.0.113.10\n")
+		time.Sleep(refresh - time.Nanosecond)
+		wantFetches(t, servers, 1)
+		wantListedBy(t, lists, "203.0.113.9", dropURL)
+
+		time.Sleep(time.Nanosecond)
+		wantFetches(t, servers, 2)
+		wantListedBy(t, lists, "203.0.113.9")
+		wantListedBy(t, lists, "203.0.113.10", dropURL)
+
+		if fetched := lists.Fetched(dropURL); !fetched.Equal(began.Add(refresh)) {
+			t.Errorf("the copy in use was fetched at %s, want %s", fetched,
+				began.Add(refresh))
+		}
+	})
+}
+
+func TestFailedFetchKeepsTheLastGoodCopyAndAlertsOncePerCooldown(t *testing.T) {
+	t.Parallel()
+
+	for _, tc := range []struct {
+		name string
+		// fail has the stand-in answer the fetches after the first so that
+		// they fail with error.
+		fail  func(servers *standIn)
+		error string
+	}{
+		{
+			"an answer other than 200",
+			func(servers *standIn) { servers.set(dropURL, "") },
+			"the server answered 503 Service Unavailable",
+		},
+		{
+			"a line that does not read",
+			func(servers *standIn) { servers.set(dropURL, "203.0.113.10\n<html>\n") },
+			"line 2 is not an address or a netblock, such as 192.0.2.0/24",
+		},
+		{
+			"a list longer than 16 MiB",
+			func(servers *standIn) {
+				servers.set(dropURL, strings.Repeat("#\n", 8<<20+1))
+			},
+			"the list is longer than 16 MiB",
+		},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			synctest.Test(t, func(t *testing.T) {
+				var log bytes.Buffer
+
+				servers := &standIn{lists: map[string]string{dropURL: drop}}
+				queue := newQueue()
+				p := params(dropURL)
+				p.ProcessLog = slog.New(slog.NewJSONHandler(&log, nil))
+				p.Alerts = queue
+				lists := start(t, servers, p)
+				kept := lists.Snapshot()
+
+				tc.fail(servers)
+
+				// Each failure is tried again once refresh has passed since it.
+				for range 2 {
+					time.Sleep(refresh)
+					synctest.Wait()
+				}
+
+				wantFetches(t, servers, 3)
+				wantListedBy(t, lists, "203.0.113.9", dropURL)
+
+				want := kept[0]
+				want.Tried = time.Now()
+
+				if got := lists.Snapshot(); !reflect.DeepEqual(got, []reputation.List{want}) {
+					t.Errorf("lists %+v, want the first copy, last tried now, %+v", got, want)
+				}
+
+				if lists.Failures(dropURL) != 2 {
+					t.Errorf("%d failures, want 2", lists.Failures(dropURL))
+				}
+
+				// One alert for the first failure; the cooldown holds back the
+				// second.
+				wantAlert(t, queue, alerts.Alert{
+					Time:   time.Now().Add(-refresh),
+					Event:  alerts.EventSourceFailure,
+					Reason: "fetching a list failed",
+					Detail: map[string]any{"source": dropURL, "error": tc.error},
+				})
+
+				if !strings.Contains(log.String(), `"msg":"fetching a list failed",`+
+					`"url":"`+dropURL+`","error":"`+tc.error) {
+					t.Errorf("logged\n%s\nwant the failures", log.String())
+				}
+			})
+		})
+	}
+}
+
+func TestFetchNotDoneWithinAMinuteFails(t *testing.T) {
+	t.Parallel()
+
+	synctest.Test(t, func(t *testing.T) {
+		servers := &standIn{lists: map[string]string{}, hanging: true}
+		lists := start(t, servers, params(dropURL))
+
+		time.Sleep(time.Minute - time.Nanosecond)
+		synctest.Wait()
+
+		if lists.Failures(dropURL) != 0 {
+			t.Errorf("%d failures before a minute, want none", lists.Failures(dropURL))
+		}
+
+		time.Sleep(time.Nanosecond)
+		synctest.Wait()
+
+		if lists.Failures(dropURL) != 1 {
+			t.Errorf("%d failures after a minute, want 1", lists.Failures(dropURL))
+		}
+	})
+}
+
+func TestKeptCopyIsFetchedAgainOnceRefreshHasPassedSinceItWasFetched(t *testing.T) {
+	t.Parallel()
+
+	synctest.Test(t, func(t *testing.T) {
+		servers := &standIn{lists: map[string]string{
+			dropURL: "203.0.113.10\n", torURL: "198.51.100.10\n",
+		}}
+		lists := reputation.New(params(dropURL, torURL))
+		lists.SetTransport(servers)
+
+		// drop.txt was fetched an hour ago, and tor.txt a refresh ago, as
+		// reputation.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"}},
+		})
+		if err != nil {
+			t.Fatalf("load: %v", err)
+		}
+
+		run(t, lists)
+
+		wantFetches(t, servers, 1)
+		wantListedBy(t, lists, "203.0.113.9", dropURL)
+		wantListedBy(t, lists, "198.51.100.10", torURL)
+
+		time.Sleep(refresh - time.Hour - time.Nanosecond)
+		wantFetches(t, servers, 1)
+
+		time.Sleep(time.Nanosecond)
+		wantFetches(t, servers, 2)
+		wantListedBy(t, lists, "203.0.113.10", dropURL)
+	})
+}
+
+func TestRestartWaitsRefreshAfterTheLastTryEvenOneThatFailed(t *testing.T) {
+	t.Parallel()
+
+	synctest.Test(t, func(t *testing.T) {
+		// drop.txt is fetched, and a refresh later the fetch downloads it
+		// whole but fails on a line that does not read.
+		servers := &standIn{lists: map[string]string{dropURL: "198.51.100.1\n"}}
+		lists := start(t, servers, params(dropURL))
+
+		servers.set(dropURL, "198.51.100.2\n<html>\n")
+		time.Sleep(refresh)
+		wantFetches(t, servers, 2)
+
+		// Restarted with what reputation.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))
+		again.SetTransport(restarted)
+
+		err := again.Load(lists.Snapshot())
+		if err != nil {
+			t.Fatalf("load: %v", err)
+		}
+
+		run(t, again)
+		wantFetches(t, restarted, 0)
+		wantListedBy(t, again, "198.51.100.1", dropURL)
+
+		time.Sleep(refresh - time.Nanosecond)
+		wantFetches(t, restarted, 0)
+
+		time.Sleep(time.Nanosecond)
+		wantFetches(t, restarted, 1)
+		wantListedBy(t, again, "198.51.100.2", dropURL)
+	})
+}
+
+func TestFetchCutOffAsItStopsIsNoFailureButARestartWaitsForIt(t *testing.T) {
+	t.Parallel()
+
+	synctest.Test(t, func(t *testing.T) {
+		// Stopped 30 seconds into the fetch of drop.txt, before tor.txt's.
+		servers := &standIn{lists: map[string]string{}, hanging: true}
+		queue := newQueue()
+		p := params(dropURL, torURL)
+		p.Alerts = queue
+
+		lists := reputation.New(p)
+		lists.SetTransport(servers)
+
+		ctx, stop := context.WithCancel(t.Context())
+		stopped := make(chan struct{})
+
+		go func() {
+			lists.Run(ctx)
+			close(stopped)
+		}()
+
+		time.Sleep(30 * time.Second)
+		stop()
+		<-stopped
+
+		wantFetches(t, servers, 1)
+
+		if lists.Failures(dropURL) != 0 || len(waiting(queue)) != 0 {
+			t.Errorf("%d failures and alerts %+v, want none", lists.Failures(dropURL),
+				waiting(queue))
+		}
+
+		// Restarted an hour later with what reputation.json keeps, it fetches
+		// tor.txt, never tried, at once, and drop.txt a refresh after its
+		// cut-off try.
+		time.Sleep(time.Hour)
+
+		restarted := &standIn{lists: map[string]string{
+			dropURL: "203.0.113.7\n", torURL: "198.51.100.7\n",
+		}}
+		again := reputation.New(params(dropURL, torURL))
+		again.SetTransport(restarted)
+
+		err := again.Load(lists.Snapshot())
+		if err != nil {
+			t.Fatalf("load: %v", err)
+		}
+
+		run(t, again)
+		wantFetches(t, restarted, 1)
+		wantListedBy(t, again, "198.51.100.7", torURL)
+
+		time.Sleep(refresh - time.Hour - time.Nanosecond)
+		wantFetches(t, restarted, 1)
+
+		time.Sleep(time.Nanosecond)
+		wantFetches(t, restarted, 2)
+		wantListedBy(t, again, "203.0.113.7", dropURL)
+	})
+}
+
+func TestASNLimitPercentFileGivesEachASNumberItsLowestPercentage(t *testing.T) {
+	t.Parallel()
+
+	synctest.Test(t, func(t *testing.T) {
+		servers := &standIn{lists: map[string]string{
+			asnURL: "# hosting networks\nAS14061:50 ; DigitalOcean\nas16276:25\n\n" +
+				"AS14061:10\nAS14061:30\n",
+		}}
+		p := params()
+		p.ASNLimitPercentURL = asnURL
+		lists := start(t, servers, p)
+
+		for asn, want := range map[string]int64{"AS14061": 10, "AS16276": 25} {
+			percent, listed := lists.ASNLimitPercent(asn)
+			if !listed || percent != want {
+				t.Errorf("%s has %d (listed %t), want %d", asn, percent, listed, want)
+			}
+		}
+
+		if _, listed := lists.ASNLimitPercent("AS64496"); listed {
+			t.Error("AS64496 is listed")
+		}
+
+		// A line that does not read fails the fetch.
+		servers.set(asnURL, "AS14061:50\nAS16276\n")
+		time.Sleep(refresh)
+		synctest.Wait()
+
+		if lists.Failures(asnURL) != 1 {
+			t.Errorf("%d failures, want 1", lists.Failures(asnURL))
+		}
+	})
+}
+
+func TestLoadDropsCopiesOfListsNotNamedAndRefusesOnesThatDoNotRead(t *testing.T) {
+	t.Parallel()
+
+	fetched := time.Date(2026, 10, 6, 0, 0, 0, 0, time.UTC)
+	kept := reputation.List{
+		URL: dropURL, Tried: fetched, Fetched: fetched, Lines: []string{"203.0.113.9"},
+	}
+	lists := reputation.New(params(dropURL))
+
+	err := lists.Load([]reputation.List{kept, {
+		URL: torURL, Tried: fetched, Fetched: fetched, Lines: []string{"198.51.100.9"},
+	}})
+	if err != nil {
+		t.Fatalf("load: %v", err)
+	}
+
+	if got := lists.Snapshot(); !reflect.DeepEqual(got, []reputation.List{kept}) {
+		t.Errorf("copies %+v, want only %+v", got, kept)
+	}
+
+	err = lists.Load([]reputation.List{{URL: dropURL, Fetched: fetched, Lines: []string{
+		"; DROP", "203.0.113.300",
+	}}})
+
+	const want = "the copy of " + dropURL +
+		": line 2 is not an address or a netblock, such as 192.0.2.0/24"
+	if err == nil || err.Error() != want {
+		t.Errorf("error %v, want %s", err, want)
+	}
+
+	if got := lists.Snapshot(); !reflect.DeepEqual(got, []reputation.List{kept}) {
+		t.Errorf("copies %+v after the error, want %+v still", got, kept)
+	}
+}
+
+// standIn is a stand-in for the servers the lists are fetched from. It
+// notes the URL of each fetch.
+type standIn struct {
+	mu sync.Mutex
+	// lists are what it answers with, by URL; it answers a URL it has no
+	// list for with 503, and none at all while hanging.
+	lists   map[string]string
+	hanging bool
+	fetches []string
+}
+
+// RoundTrip has the stand-in answer req, in place of the network. A fetch
+// abandoned before the stand-in answers fails, as over the network.
+func (s *standIn) RoundTrip(req *http.Request) (*http.Response, error) {
+	s.mu.Lock()
+	s.fetches = append(s.fetches, req.URL.String())
+	list, found := s.lists[req.URL.String()]
+	hanging := s.hanging
+	s.mu.Unlock()
+
+	if hanging {
+		<-req.Context().Done()
+
+		return nil, req.Context().Err()
+	}
+
+	status := http.StatusOK
+	if !found {
+		status = http.StatusServiceUnavailable
+	}
+
+	return &http.Response{
+		StatusCode: status,
+		Status:     fmt.Sprintf("%d %s", status, http.StatusText(status)),
+		Header:     http.Header{},
+		Body:       io.NopCloser(strings.NewReader(list)),
+		Request:    req,
+	}, nil
+}
+
+// set has the stand-in answer listURL with list, or with 503 for "".
+func (s *standIn) set(listURL, list string) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	if list == "" {
+		delete(s.lists, listURL)
+
+		return
+	}
+
+	s.lists[listURL] = list
+}
+
+// params returns the Params of the blocklists at urls, refreshed every
+// refresh, by the bubble's clock, with alerts to a queue that sends none.
+func params(urls ...string) reputation.Params {
+	return reputation.Params{
+		BlocklistURLs: urls,
+		Refresh:       refresh,
+		Now:           time.Now,
+		ProcessLog:    slog.New(slog.DiscardHandler),
+		Alerts:        newQueue(),
+	}
+}
+
+// newQueue returns a queue of alerts to a webhook that is never sent
+// them, with a cooldown of cooldown.
+func newQueue() *alerts.Queue {
+	return alerts.New(alerts.Params{
+		WebhookURL: &url.URL{Scheme: "https", Host: "alerts.example"},
+		Events:     alerts.Events(),
+		Cooldown:   cooldown,
+		Now:        time.Now,
+	})
+}
+
+// start returns the lists of p, fetched through servers by Run, which runs
+// until the test ends, once Run has fetched those due at start.
+func start(t *testing.T, servers *standIn, p reputation.Params) *reputation.Lists {
+	t.Helper()
+
+	lists := reputation.New(p)
+	lists.SetTransport(servers)
+	run(t, lists)
+
+	return lists
+}
+
+// run runs lists' Run until the test ends, and waits until it has fetched
+// the lists due.
+func run(t *testing.T, lists *reputation.Lists) {
+	t.Helper()
+
+	ctx, stop := context.WithCancel(t.Context())
+	stopped := make(chan struct{})
+
+	go func() {
+		lists.Run(ctx)
+		close(stopped)
+	}()
+
+	t.Cleanup(func() {
+		stop()
+		<-stopped
+	})
+
+	synctest.Wait()
+}
+
+// wantFetches waits until Run has made the fetches due, and checks how
+// many the servers have had.
+func wantFetches(t *testing.T, servers *standIn, want int) {
+	t.Helper()
+
+	synctest.Wait()
+
+	servers.mu.Lock()
+	got := len(servers.fetches)
+	servers.mu.Unlock()
+
+	if got != want {
+		t.Errorf("%d fetches, want %d", got, want)
+	}
+}
+
+// wantListedBy checks the URLs of the blocklists lists says list addr.
+func wantListedBy(t *testing.T, lists *reputation.Lists, addr string, want ...string) {
+	t.Helper()
+
+	got := lists.ListedBy(netip.MustParseAddr(addr))
+	if !slices.Equal(got, want) {
+		t.Errorf("%s is listed by %v, want %v", addr, got, want)
+	}
+}
+
+// waiting returns the alerts waiting in queue.
+func waiting(queue *alerts.Queue) []alerts.Alert {
+	return queue.Snapshot().Waiting[alerts.DestinationWebhook]
+}
+
+// wantAlert checks that want is the one alert waiting in queue, and that
+// the cooldown has held back one repeat of it.
+func wantAlert(t *testing.T, queue *alerts.Queue, want alerts.Alert) {
+	t.Helper()
+
+	got := waiting(queue)
+	if len(got) != 1 || !reflect.DeepEqual(got[0], want) || queue.Suppressed() != 1 {
+		t.Errorf("alerts waiting %+v, %d held back, want only %+v and 1", got,
+			queue.Suppressed(), want)
+	}
+}

internal/requestlog/requestlog.go

@@ -35,7 +35,9 @@ const (
 	// rule.
 	ActionRuleBlocked = "rule_blocked"
 	// ActionDenied is a request refused because its client is in
-	// SWWAF_DENY_NETS.
+	// SWWAF_DENY_NETS, in a blocklist while SWWAF_BLOCKLIST_ACTION is deny,
+	// or listed by a DNSBL zone, or scored a hit by AbuseIPDB, while
+	// SWWAF_REPUTATION_ACTION is deny.
 	ActionDenied = "denied"
 	// ActionCountryDenied is a request refused for its client's country.
 	ActionCountryDenied = "country_denied"
@@ -137,6 +139,10 @@ type Line struct {
 	// Counts names its count: minute, hour or day for a rate limit, and
 	// minute_bytes, hour_bytes or day_bytes for a byte limit.
 	LimitHit string `json:"limit_hit,omitempty"`
+	// Reputation are the URLs of the blocklists that list the client, then
+	// the DNSBL zones whose verdict lists it, their keys masked, then
+	// abuseipdb when its score is a hit.
+	Reputation []string `json:"reputation,omitempty"`
 	// Offence is the offence the request was held as, OffenceLimit.
 	Offence string `json:"offence,omitempty"`
 	// BanExpires is when the ban the request made, or was refused under,
@@ -187,8 +193,11 @@ func Milliseconds(d time.Duration) float64 {
 // NewProcessLogger returns the logger for the process's own messages:
 // JSON lines on w, marked "type":"process", with the time in the same form
 // as a request line's, and instanceName, SWWAF_INSTANCE_NAME, as instance.
-func NewProcessLogger(w io.Writer, instanceName string) *slog.Logger {
+// It writes only the messages at level, SWWAF_LOG_LEVEL, or more severe;
+// the request lines Write writes are never held back.
+func NewProcessLogger(w io.Writer, instanceName string, level slog.Level) *slog.Logger {
 	handler := slog.NewJSONHandler(w, &slog.HandlerOptions{
+		Level: level,
 		ReplaceAttr: func(groups []string, attr slog.Attr) slog.Attr {
 			if attr.Key == slog.TimeKey && len(groups) == 0 {
 				return slog.String(slog.TimeKey, FormatTime(attr.Value.Time()))

internal/requestlog/requestlog_test.go

@@ -3,6 +3,8 @@ package requestlog_test
 import (
 	"bytes"
 	"encoding/json"
+	"log/slog"
+	"slices"
 	"strings"
 	"testing"
 	"time"
@@ -70,7 +72,8 @@ func TestProcessLinesAreMarkedProcessAndGiveTheInstance(t *testing.T) {
 
 	var out bytes.Buffer
 
-	requestlog.NewProcessLogger(&out, "fsn1app1/gitea").Info("starting", "version", "v1")
+	requestlog.NewProcessLogger(&out, "fsn1app1/gitea", slog.LevelInfo).Info("starting",
+		"version", "v1")
 
 	var fields map[string]any
 
@@ -94,3 +97,47 @@ func TestProcessLinesAreMarkedProcessAndGiveTheInstance(t *testing.T) {
 		t.Errorf("process line time %q, want now in UTC with milliseconds", timeText)
 	}
 }
+
+func TestProcessLoggerWritesTheMessagesAtItsLevelOrMoreSevere(t *testing.T) {
+	t.Parallel()
+
+	levels := []slog.Level{
+		slog.LevelDebug, slog.LevelInfo, slog.LevelWarn, slog.LevelError,
+	}
+
+	for i, level := range levels {
+		t.Run(level.String(), func(t *testing.T) {
+			t.Parallel()
+
+			var out bytes.Buffer
+
+			processLog := requestlog.NewProcessLogger(&out, "fsn1app1/gitea", level)
+			for _, at := range levels {
+				processLog.Log(t.Context(), at, "message")
+			}
+
+			var got, want []string
+
+			for line := range strings.Lines(out.String()) {
+				var fields struct {
+					Level string `json:"level"`
+				}
+
+				err := json.Unmarshal([]byte(line), &fields)
+				if err != nil {
+					t.Fatalf("decode %q: %v", line, err)
+				}
+
+				got = append(got, fields.Level)
+			}
+
+			for _, written := range levels[i:] {
+				want = append(want, written.String())
+			}
+
+			if !slices.Equal(got, want) {
+				t.Errorf("lines at %v, want %v", got, want)
+			}
+		})
+	}
+}

internal/smallwebwaf/smallwebwaf.go

@@ -21,6 +21,7 @@ import (
 	"sneak.berlin/go/smallwebwaf/internal/lookup"
 	"sneak.berlin/go/smallwebwaf/internal/proxy"
 	"sneak.berlin/go/smallwebwaf/internal/remotelog"
+	"sneak.berlin/go/smallwebwaf/internal/reputation"
 	"sneak.berlin/go/smallwebwaf/internal/requestlog"
 	"sneak.berlin/go/smallwebwaf/internal/rules"
 	"sneak.berlin/go/smallwebwaf/internal/state"
@@ -69,8 +70,10 @@ func Main(version string) int {
 // state files, then serves requests until ctx is done. It returns the
 // process's exit status, 1 when smallwebwaf cannot start.
 func Run(ctx context.Context, params Params) int {
+	// Until the settings are read, the one message is an invalid setting's
+	// error, which every SWWAF_LOG_LEVEL lets through.
 	processLog := requestlog.NewProcessLogger(params.Stdout,
-		config.InstanceName(params.LookupEnv))
+		config.InstanceName(params.LookupEnv), slog.LevelError)
 
 	cfg, err := config.FromEnvironment(params.LookupEnv)
 	if err != nil {
@@ -88,8 +91,11 @@ func Run(ctx context.Context, params Params) int {
 	if cfg.LogRemoteURL != nil {
 		remote = newRemoteLogSender(cfg)
 		stdout = io.MultiWriter(params.Stdout, remote)
-		processLog = requestlog.NewProcessLogger(stdout, cfg.InstanceName)
+	}
 
+	processLog = requestlog.NewProcessLogger(stdout, cfg.InstanceName, cfg.LogLevel)
+
+	if remote != nil {
 		stopSending := startSending(ctx, remote, processLog)
 		defer stopSending()
 	}
@@ -169,14 +175,15 @@ func newServer(
 	}
 
 	server := proxy.New(proxy.Params{
-		Config:     cfg,
+		Config:       cfg,
-		RequestLog: stdout,
+		RequestLog:   stdout,
-		ProcessLog: processLog,
+		ProcessLog:   processLog,
-		GeoJSURL:   lookup.URL,
+		GeoJSURL:     lookup.URL,
-		LookupFile: lookupFile,
+		AbuseIPDBURL: reputation.AbuseIPDBURL,
-		Now:        now,
+		LookupFile:   lookupFile,
-		Rules:      ruleFiles,
+		Now:          now,
-		Alerts:     alertQueue,
+		Rules:        ruleFiles,
+		Alerts:       alertQueue,
 	})
 	server.Metrics.AddAlerts(alertQueue)
 
@@ -200,6 +207,9 @@ func loadStateFiles(
 		Ledger:          server.Ledger,
 		Limiter:         server.Limiter,
 		GeoJS:           server.GeoJS,
+		Lists:           server.Lists,
+		DNSBL:           server.DNSBL,
+		AbuseIPDB:       server.AbuseIPDB,
 		Alerts:          alertQueue,
 		Anomalies:       server.Anomalies,
 		Now:             now,
@@ -267,8 +277,9 @@ func startSending(
 
 // serve serves requests on listener, writes the state files as they are
 // due, takes in an admin's edits of them, reads the rule files again as
-// they change, and the lookup database when it is replaced, and sends the
+// they change, and the lookup database when it is replaced, fetches the
-// alerts, until ctx is done. Then it gives the requests in progress
+// lists the settings name by URL as they are due, and sends the alerts,
+// until ctx is done. Then it gives the requests in progress
 // shutdownTimeout to finish, and writes every state file, alerts.json with
 // the alerts still waiting.
 func serve(
@@ -293,6 +304,7 @@ func serve(
 			server.LookupFile.Watch(writing)
 		}
 	})
+	listsFetched := inBackground(func() { server.Lists.Run(writing) })
 	alertsSent := inBackground(func() { alertQueue.Run(writing) })
 
 	select {
@@ -336,6 +348,7 @@ func serve(
 	<-watched
 	<-rulesWatched
 	<-lookupFileWatched
+	<-listsFetched
 	<-alertsSent
 
 	err = files.WriteAll()

internal/smallwebwaf/smallwebwaf_test.go

@@ -38,6 +38,7 @@ const (
 	stateWriteDelay      = "SWWAF_STATE_WRITE_DELAY"
 	stateCounterInterval = "SWWAF_STATE_COUNTER_INTERVAL"
 	rateLimitPerDay      = "SWWAF_RATE_LIMIT_PER_DAY"
+	rateLimitExemptNets  = "SWWAF_RATE_LIMIT_EXEMPT_NETS"
 	rulesDir             = "SWWAF_RULES_DIR"
 	lookupSource         = "SWWAF_LOOKUP_SOURCE"
 	lookupDBPath         = "SWWAF_LOOKUP_DB_PATH"
@@ -248,6 +249,54 @@ func TestServesUntilToldToStop(t *testing.T) {
 	out.line(t, "msg", "stopped")
 }
 
+func TestLogLevelHoldsBackTheLessSevereProcessLines(t *testing.T) {
+	t.Parallel()
+
+	// A list that cannot be fetched has a warning written once smallwebwaf
+	// serves, after its starting line.
+	lists := httptest.NewServer(http.HandlerFunc(
+		func(w http.ResponseWriter, _ *http.Request) {
+			w.WriteHeader(http.StatusServiceUnavailable)
+		}))
+	t.Cleanup(lists.Close)
+
+	ctx, stop := context.WithCancel(t.Context())
+	out := &output{}
+	exited := make(chan int, 1)
+
+	go func() {
+		exited <- run(ctx, map[string]string{
+			listenAddr:             localhost + ":0",
+			stateDir:               t.TempDir(),
+			rulesDir:               t.TempDir(),
+			"SWWAF_BLOCKLIST_URLS": lists.URL + "/tor.txt",
+			"SWWAF_LOG_LEVEL":      "warn",
+		}, out)
+	}()
+
+	out.line(t, "msg", "fetching a list failed")
+	stop()
+
+	select {
+	case status := <-exited:
+		if status != 0 {
+			t.Fatalf("exit status %d, want 0; output:\n%s", status, out.text())
+		}
+	case <-time.After(waitLimit):
+		t.Fatal("still running after being told to stop")
+	}
+
+	// Not one of the info lines from the start to the stop.
+	for line := range strings.Lines(out.text()) {
+		var fields map[string]any
+
+		err := json.Unmarshal([]byte(line), &fields)
+		if err != nil || fields["level"] == "INFO" {
+			t.Errorf("line %q (%v), want none at info", line, err)
+		}
+	}
+}
+
 func TestEveryLogLineAndMetricCarriesTheInstanceName(t *testing.T) {
 	t.Parallel()
 
@@ -522,7 +571,7 @@ func TestLookupDatabaseReplacedWhileRunningTakesEffect(t *testing.T) {
 		// The requests sent until a replacement takes effect, and those
 		// for the metrics, must not break a rate limit, whose ban would
 		// refuse them too.
-		"SWWAF_RATE_LIMIT_EXEMPT_NETS": placed + "," + localhost,
+		rateLimitExemptNets: placed + "," + localhost,
 	}
 	began := time.Now()
 	// Each replacement is written beside the file and renamed over it, as
@@ -573,6 +622,111 @@ func TestLookupDatabaseReplacedWhileRunningTakesEffect(t *testing.T) {
 	}
 }
 
+func TestBlocklistTriesAndCopiesKeptInReputationJSONAcrossRestarts(t *testing.T) {
+	t.Parallel()
+
+	const (
+		token    = "0123456789abcdef0123456789abcdef"
+		torPath  = "/tor.txt"
+		dropPath = "/drop.txt"
+		// copyright is the DROP list's date and copyright line.
+		copyright = "; Spamhaus DROP List 2026/10/07 - (c) 2026 The Spamhaus Project SLL"
+	)
+
+	failing, torFetches := new(atomic.Bool), new(atomic.Int32)
+	lists := map[string]string{
+		torPath:  "198.51.100.0/24\n",
+		dropPath: copyright + "\n" + placed + " ; SBL1\n",
+	}
+	server := httptest.NewServer(http.HandlerFunc(
+		func(w http.ResponseWriter, r *http.Request) {
+			if r.URL.Path == torPath {
+				torFetches.Add(1)
+			}
+
+			if failing.Load() {
+				w.WriteHeader(http.StatusServiceUnavailable)
+
+				return
+			}
+
+			_, _ = io.WriteString(w, lists[r.URL.Path])
+		}))
+	t.Cleanup(server.Close)
+
+	torURL, dropURL := server.URL+torPath, server.URL+dropPath
+	dir := t.TempDir()
+	env := map[string]string{
+		listenAddr:             localhost + ":0",
+		upstreamURL:            startApp(t),
+		stateDir:               dir,
+		rulesDir:               t.TempDir(),
+		trustedProxies:         localhost + "/32",
+		metricsToken:           token,
+		instanceName:           instance,
+		"SWWAF_BLOCKLIST_URLS": torURL,
+		// The requests sent until the list takes effect, and those for the
+		// metrics, must not break a rate limit, whose ban would refuse them
+		// too.
+		rateLimitExemptNets: placed + "," + localhost,
+	}
+	failures := `smallwebwaf_reputation_failures_total{instance="fsn1app1/gitea",` +
+		`source="` + torURL + `"} `
+
+	// tor.txt cannot be fetched at first, which is counted.
+	failing.Store(true)
+	runUntilStopped(t, env, func(url string) {
+		metricsWith(t, url+"_smallwebwaf/metrics", token, failures+"1")
+	})
+
+	// Restarted with drop.txt named after it and the server answering, tor.txt
+	// waits SWWAF_BLOCKLIST_REFRESH after its failed try, kept in reputation.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)
+
+	env["SWWAF_BLOCKLIST_URLS"] = torURL + "," + dropURL
+	out := runUntilStopped(t, env, func(url string) {
+		for statusFrom(t, url, placed) != http.StatusForbidden {
+			time.Sleep(pollInterval)
+		}
+	})
+	wantDeniedByList(t, out.line(t, "action", "denied"), dropURL)
+
+	if fetches := torFetches.Load(); fetches != 1 {
+		t.Errorf("tor.txt fetched %d times, want once, before the restart", fetches)
+	}
+
+	// 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.
+	failing.Store(true)
+
+	out = runUntilStopped(t, env, func(url string) {
+		wantStatus(t, url, placed, http.StatusForbidden)
+	})
+	wantDeniedByList(t, out.line(t, "type", "request"), dropURL)
+
+	path := filepath.Join(dir, "reputation.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,
+			err)
+	}
+}
+
+// wantDeniedByList checks that the request log line is of a request the
+// blocklist at listURL refused.
+func wantDeniedByList(t *testing.T, line map[string]any, listURL string) {
+	t.Helper()
+
+	reputation, _ := line["reputation"].([]any)
+	if line["action"] != "denied" || len(reputation) != 1 || reputation[0] != listURL {
+		t.Errorf("request log line %v, want one denied for %s", line, listURL)
+	}
+}
+
 func TestLookupDatabaseThatCannotBeReadStopsTheStart(t *testing.T) {
 	t.Parallel()
 
@@ -1014,7 +1168,7 @@ func wantStartingLine(t *testing.T, line map[string]any, appURL, dir string) {
 		"SWWAF_REQUEST_MAX_BYTES":               "100M",
 		"SWWAF_RESPONSE_MAX_BYTES":              "5G",
 		"SWWAF_ALLOW_NETS":                      "",
-		"SWWAF_RATE_LIMIT_EXEMPT_NETS":          "",
+		rateLimitExemptNets:                     "",
 		"SWWAF_DENY_NETS":                       "",
 		"SWWAF_RATE_LIMIT_PER_MINUTE":           "1000",
 		"SWWAF_RATE_LIMIT_PER_HOUR":             "10000",

internal/state/state.go

@@ -1,9 +1,11 @@
 // Package state keeps smallwebwaf's state in JSON files in
 // SWWAF_STATE_DIR, as the "Persistent state" section of SPEC.md describes:
 // bans.json holds the bans, clients.json each client's counters and
-// history, lookups.json GeoJS's answers, and alerts.json the cooldowns,
+// history, lookups.json GeoJS's answers, reputation.json the last try and
-// the hour under way, the alerts waiting for each destination and the
+// last good copy of each list fetched from a URL, the DNSBL zones'
-// anomaly counters. Load
+// 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
 // smallwebwaf runs, and Run and WriteAll write them. The disk is read and
 // written outside the parts' locks, which are held only to take a
@@ -35,6 +37,7 @@ import (
 	"sneak.berlin/go/smallwebwaf/internal/lookup"
 	"sneak.berlin/go/smallwebwaf/internal/metrics"
 	"sneak.berlin/go/smallwebwaf/internal/ratelimit"
+	"sneak.berlin/go/smallwebwaf/internal/reputation"
 )
 
 // version is the version of the files' format, the only one read.
@@ -46,10 +49,11 @@ const fileMode = 0o600
 
 // The state files' names.
 const (
-	bansJSON    = "bans.json"
+	bansJSON       = "bans.json"
-	clientsJSON = "clients.json"
+	clientsJSON    = "clients.json"
-	lookupsJSON = "lookups.json"
+	lookupsJSON    = "lookups.json"
-	alertsJSON  = "alerts.json"
+	reputationJSON = "reputation.json"
+	alertsJSON     = "alerts.json"
 )
 
 var (
@@ -73,12 +77,15 @@ type Params struct {
 	// is (SWWAF_STATE_COUNTER_INTERVAL).
 	WriteDelay      time.Duration
 	CounterInterval time.Duration
-	// Ledger, Limiter, GeoJS, Alerts and Anomalies hold the state. Alerts
+	// Ledger, Limiter, GeoJS, Lists, DNSBL, AbuseIPDB, Alerts and Anomalies
-	// also receive a file_error alert for an edit set aside, and for a
+	// hold the state. Alerts also receive a file_error alert for an edit set
-	// write that fails while smallwebwaf runs.
+	// aside, and for a write that fails while smallwebwaf 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
 	// Now tells the time by which the counters' buckets run out, normally
@@ -138,6 +145,15 @@ 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"`
+}
+
 // alertsFile is alerts.json, indented for an admin to read and edit.
 //
 //nolint:tagliatelle // the state files use snake_case, as the request log does
@@ -159,10 +175,10 @@ type stateFile interface {
 }
 
 // Load checks that files can be written in Dir, and reads the state files
-// in it into the ledger, the limiter and GeoJS. A missing file is empty
+// in it into the parts of Params that hold the state. A missing file is
-// state, as on a first start. A file that does not parse, has an unknown
+// empty state, as on a first start. A file that does not parse, has an
-// version, or has an entry without a field it needs, is an error that
+// unknown version, or has an entry without a field it needs, is an error
-// names the file and, where the JSON decoder tells it, the line and
+// that names the file and, where the JSON decoder tells it, the line and
 // column, or else the entry.
 func Load(params Params) (*Files, error) {
 	err := checkWritable(params.Dir)
@@ -175,16 +191,17 @@ func Load(params Params) (*Files, error) {
 	bansRead, bansErr := f.read(bansJSON)
 	clientsRead, clientsErr := f.read(clientsJSON)
 	lookupsRead, lookupsErr := f.read(lookupsJSON)
+	reputationRead, reputationErr := f.read(reputationJSON)
 	alertsRead, alertsErr := f.read(alertsJSON)
 
-	err = errors.Join(bansErr, clientsErr, lookupsErr, alertsErr)
+	err = errors.Join(bansErr, clientsErr, lookupsErr, reputationErr, alertsErr)
 	if err != nil {
 		return nil, err
 	}
 
 	params.ProcessLog.Info("read the state files", "directory", params.Dir,
 		"bans", bansRead, "clients", clientsRead, "lookups", lookupsRead,
-		"alerts_waiting", alertsRead)
+		"lists", reputationRead, "alerts_waiting", alertsRead)
 
 	return f, nil
 }
@@ -213,7 +230,9 @@ func (f *Files) Run(ctx context.Context) {
 
 			f.logFailure(bansJSON, f.writeFile(bansJSON))
 		case <-interval.C:
-			for _, name := range []string{bansJSON, clientsJSON, lookupsJSON, alertsJSON} {
+			for _, name := range []string{
+				bansJSON, clientsJSON, lookupsJSON, reputationJSON, alertsJSON,
+			} {
 				f.logFailure(name, f.writeFile(name))
 			}
 		}
@@ -224,7 +243,7 @@ func (f *Files) Run(ctx context.Context) {
 // 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(alertsJSON))
+		f.writeFile(lookupsJSON), f.writeFile(reputationJSON), f.writeFile(alertsJSON))
 }
 
 // Watch watches Dir until ctx is done, and takes in an admin's edit of a
@@ -259,7 +278,7 @@ func (f *Files) Watch(ctx context.Context) {
 			return
 		case event := <-watcher.Events:
 			switch name := filepath.Base(event.Name); name {
-			case bansJSON, clientsJSON, lookupsJSON, alertsJSON:
+			case bansJSON, clientsJSON, lookupsJSON, reputationJSON, alertsJSON:
 				f.fileChanged(name)
 			}
 		case err = <-watcher.Errors:
@@ -405,33 +424,29 @@ func (f *Files) takeIn(name string, data []byte, edit bool) (int, error) {
 
 		f.params.GeoJS.Load(file.Lookups)
 		entries = len(file.Lookups)
-	case alertsJSON:
+	case reputationJSON:
-		// waiting was a list, of the alerts waiting for the webhook, before
+		var file reputationFile
-		// alerts went to Slack and ntfy too.
-		var written struct {
-			Waiting json.RawMessage `json:"waiting"`
-		}
-
-		if json.Unmarshal(data, &written) == nil &&
-			bytes.HasPrefix(written.Waiting, []byte("[")) {
-			return 0, fmt.Errorf("%s: %w", path, errWaitingList)
-		}
-
-		var file alertsFile
 
 		err := parse(path, data, &file)
 		if err != nil {
 			return 0, err
 		}
 
-		f.params.Alerts.Load(alerts.State{
+		err = f.params.Lists.Load(file.Lists)
-			Cooldowns: file.Cooldowns, Hour: file.Hour, Waiting: file.Waiting,
+		if err != nil {
-		})
+			return 0, fmt.Errorf("%s: %w", path, err)
-		f.params.Anomalies.Load(file.AnomalyCounters, f.params.Now())
-
-		for _, waiting := range file.Waiting {
-			entries += len(waiting)
 		}
+
+		f.params.DNSBL.Load(file.Verdicts)
+		f.params.AbuseIPDB.Load(file.AbuseIPDB)
+		entries = len(file.Lists)
+	case alertsJSON:
+		waiting, err := f.takeInAlerts(path, data)
+		if err != nil {
+			return 0, err
+		}
+
+		entries = waiting
 	}
 
 	f.sums[name] = sha256.Sum256(data)
@@ -439,6 +454,41 @@ func (f *Files) takeIn(name string, data []byte, edit bool) (int, error) {
 	return entries, nil
 }
 
+// takeInAlerts parses data, what alerts.json, at path, holds, puts it
+// into the alerts and the anomaly counters, in place of what they held,
+// and returns how many alerts wait in it, as takeIn describes.
+func (f *Files) takeInAlerts(path string, data []byte) (int, error) {
+	// waiting was a list, of the alerts waiting for the webhook, before
+	// alerts went to Slack and ntfy too.
+	var written struct {
+		Waiting json.RawMessage `json:"waiting"`
+	}
+
+	if json.Unmarshal(data, &written) == nil &&
+		bytes.HasPrefix(written.Waiting, []byte("[")) {
+		return 0, fmt.Errorf("%s: %w", path, errWaitingList)
+	}
+
+	var file alertsFile
+
+	err := parse(path, data, &file)
+	if err != nil {
+		return 0, err
+	}
+
+	f.params.Alerts.Load(alerts.State{
+		Cooldowns: file.Cooldowns, Hour: file.Hour, Waiting: file.Waiting,
+	})
+	f.params.Anomalies.Load(file.AnomalyCounters, f.params.Now())
+
+	entries := 0
+	for _, waiting := range file.Waiting {
+		entries += len(waiting)
+	}
+
+	return entries, nil
+}
+
 // writeFile writes the state file name from what smallwebwaf holds. An
 // edit made since smallwebwaf last read or wrote the file is taken in
 // first, so that it is not overwritten, or set aside if it does not
@@ -514,34 +564,39 @@ func (f *Files) setAside(name string, parseErr error) error {
 func (f *Files) encode(name string) ([]byte, error) {
 	switch name {
 	case bansJSON:
-		file := bansFile{Version: version, Bans: BanEntries(f.params.Ledger.Snapshot())}
+		return encodeIndented(bansFile{
-
+			Version: version, Bans: BanEntries(f.params.Ledger.Snapshot()),
-		data, err := json.MarshalIndent(file, "", "    ")
+		})
-		if err != nil {
-			return nil, err
-		}
-
-		return append(data, '\n'), nil
 	case clientsJSON:
 		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(),
+		})
 	default: // alerts.json
 		held := f.params.Alerts.Snapshot()
-		file := alertsFile{
+
+		return encodeIndented(alertsFile{
 			Version: version, Cooldowns: held.Cooldowns, Hour: held.Hour,
 			Waiting: held.Waiting, AnomalyCounters: f.params.Anomalies.Snapshot(),
-		}
+		})
-
-		data, err := json.MarshalIndent(file, "", "    ")
-		if err != nil {
-			return nil, err
-		}
-
-		return append(data, '\n'), nil
 	}
 }
 
+// encodeIndented encodes file, a state file's struct, indented for an
+// admin to read and edit.
+func encodeIndented(file any) ([]byte, error) {
+	data, err := json.MarshalIndent(file, "", "    ")
+	if err != nil {
+		return nil, err
+	}
+
+	return append(data, '\n'), nil
+}
+
 // BanEntries returns held as bans.json lists them, an empty list for
 // none.
 func BanEntries(held []bans.Ban) []BanEntry {
@@ -679,6 +734,87 @@ func (f *lookupsFile) check(data []byte) error {
 	return nil
 }
 
+// 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 {
+	for i, kept := range f.Lists {
+		switch {
+		case kept.URL == "":
+			return missing(i, "url")
+		case kept.Tried.IsZero():
+			return missing(i, "tried")
+		case kept.Fetched.IsZero() && kept.Lines != nil:
+			return missing(i, "fetched")
+		case kept.Lines == nil && !kept.Fetched.IsZero():
+			return missing(i, "lines")
+		}
+	}
+
+	var written struct {
+		Verdicts []struct {
+			Listed *bool `json:"listed"`
+		} `json:"verdicts"`
+	}
+
+	err := json.Unmarshal(data, &written)
+	if err != nil {
+		return err
+	}
+
+	for i, verdict := range f.Verdicts {
+		switch {
+		case verdict.Zone == "":
+			return fmt.Errorf("verdicts %w", missing(i, "zone"))
+		case !verdict.Client.IsValid():
+			return fmt.Errorf("verdicts %w", missing(i, "client"))
+		case written.Verdicts[i].Listed == nil:
+			return fmt.Errorf("verdicts %w", missing(i, "listed"))
+		case verdict.Fetched.IsZero():
+			return fmt.Errorf("verdicts %w", missing(i, "fetched"))
+		}
+	}
+
+	return checkScores(f.AbuseIPDB.Scores, data)
+}
+
+// checkScores refuses an AbuseIPDB score, of scores, read from data, as
+// reputationFile's check describes.
+func checkScores(scores []reputation.Score, data []byte) error {
+	var written struct {
+		AbuseIPDB struct {
+			Scores []struct {
+				Score *int64 `json:"score"`
+			} `json:"scores"`
+		} `json:"abuseipdb"`
+	}
+
+	err := json.Unmarshal(data, &written)
+	if err != nil {
+		return err
+	}
+
+	for i, kept := range 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"))
+		case kept.Fetched.IsZero():
+			return fmt.Errorf("abuseipdb scores %w", missing(i, "fetched"))
+		}
+	}
+
+	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

internal/state/state_test.go

@@ -27,15 +27,22 @@ import (
 	"sneak.berlin/go/smallwebwaf/internal/lookup"
 	"sneak.berlin/go/smallwebwaf/internal/metrics"
 	"sneak.berlin/go/smallwebwaf/internal/ratelimit"
+	"sneak.berlin/go/smallwebwaf/internal/reputation"
 	"sneak.berlin/go/smallwebwaf/internal/state"
 )
 
 const (
 	// The state files.
-	bansJSON    = "bans.json"
+	bansJSON       = "bans.json"
-	clientsJSON = "clients.json"
+	clientsJSON    = "clients.json"
-	lookupsJSON = "lookups.json"
+	lookupsJSON    = "lookups.json"
-	alertsJSON  = "alerts.json"
+	reputationJSON = "reputation.json"
+	alertsJSON     = "alerts.json"
+	// blocklistURL and torURL are the blocklists the tests' lists name, and
+	// dnsblZone the DNSBL zone of the tests' verdicts.
+	blocklistURL = "https://lists.example/drop.txt"
+	torURL       = "https://lists.example/tor.txt"
+	dnsblZone    = "dnsbl.example"
 	// The AS number and AS name the tests' clients are looked up in.
 	asn    = "AS64496"
 	asName = "Example Net"
@@ -68,6 +75,15 @@ const permanentBansJSON = `{
                 "limit": 1000,
                 "window": "minute",
                 "count": 1000.5,
+                "reputation": [
+                    {
+                        "source": "https://lists.example/drop.txt"
+                    },
+                    {
+                        "source": "abuseipdb",
+                        "score": 100
+                    }
+                ],
                 "request": {
                     "time": "2026-10-06T00:00:00Z",
                     "method": "GET",
@@ -204,6 +220,61 @@ const filledAlertsJSON = `{
 }
 `
 
+// filledReputationJSON is reputation.json holding the blocklists' last
+// tries and the copy of one, with its comment line, two verdicts of a
+// DNSBL zone, and the AbuseIPDB checks spent today with two scores, as
+// fill puts them in.
+const filledReputationJSON = `{
+    "version": 1,
+    "lists": [
+        {
+            "url": "https://lists.example/drop.txt",
+            "tried": "2026-10-06T00:00:00Z",
+            "fetched": "2026-10-05T23:00:00Z",
+            "lines": [
+                "; Spamhaus DROP List 2026/10/05 - (c) 2026 The Spamhaus Project SLL",
+                "203.0.113.0/24 ; SBL1",
+                "2001:db8::/32 ; SBL2"
+            ]
+        },
+        {
+            "url": "https://lists.example/tor.txt",
+            "tried": "2026-10-06T00:00:00Z"
+        }
+    ],
+    "verdicts": [
+        {
+            "zone": "dnsbl.example",
+            "client": "203.0.113.9",
+            "listed": true,
+            "fetched": "2026-10-05T23:00:00Z"
+        },
+        {
+            "zone": "dnsbl.example",
+            "client": "2001:db8::1",
+            "listed": false,
+            "fetched": "2026-10-05T22:00:00Z"
+        }
+    ],
+    "abuseipdb": {
+        "day": "2026-10-06T00:00:00Z",
+        "spent": 3,
+        "scores": [
+            {
+                "client": "203.0.113.9/32",
+                "score": 100,
+                "fetched": "2026-10-05T23:00:00Z"
+            },
+            {
+                "client": "2001:db8::/64",
+                "score": 0,
+                "fetched": "2026-10-05T22:00:00Z"
+            }
+        ]
+    }
+}
+`
+
 func TestFilesWrittenAndReadBack(t *testing.T) {
 	t.Parallel()
 
@@ -230,6 +301,18 @@ func TestFilesWrittenAndReadBack(t *testing.T) {
 	wantEqual(t, clientsJSON, after.Limiter.Snapshot(), before.Limiter.Snapshot())
 	wantEqual(t, lookupsJSON, after.GeoJS.Snapshot(), before.GeoJS.Snapshot())
 
+	if got, want := after.Lists.Snapshot(), before.Lists.Snapshot(); !reflect.DeepEqual(
+		got, want) {
+		t.Errorf("%s read back\n%+v\nwant\n%+v", reputationJSON, got, want)
+	}
+
+	wantEqual(t, reputationJSON, after.DNSBL.Snapshot(), before.DNSBL.Snapshot())
+
+	checks, wantChecks := after.AbuseIPDB.Snapshot(), before.AbuseIPDB.Snapshot()
+	if !reflect.DeepEqual(checks, wantChecks) {
+		t.Errorf("%s read back\n%+v\nwant\n%+v", reputationJSON, checks, wantChecks)
+	}
+
 	if got, want := after.Alerts.Snapshot(), before.Alerts.Snapshot(); !reflect.DeepEqual(
 		got, want) {
 		t.Errorf("%s read back\n%+v\nwant\n%+v", alertsJSON, got, want)
@@ -238,12 +321,32 @@ func TestFilesWrittenAndReadBack(t *testing.T) {
 	wantEqual(t, alertsJSON, after.Anomalies.Snapshot(), before.Anomalies.Snapshot())
 
 	// Each one-per-line file lists its entries by client, and nothing
-	// but the four files is left in the directory.
+	// but the five files is left in the directory.
 	wantEntries(t, filepath.Join(dir, clientsJSON), "clients",
 		"192.0.2.1/32", "203.0.113.9/32", "2001:db8::/64")
 	wantEntries(t, filepath.Join(dir, lookupsJSON), "lookups",
 		"192.0.2.1/32", "203.0.113.9/32")
-	wantFiles(t, dir, alertsJSON, bansJSON, clientsJSON, lookupsJSON)
+	wantFiles(t, dir, alertsJSON, bansJSON, clientsJSON, lookupsJSON, reputationJSON)
+}
+
+func TestReputationJSONKeepsEachCopyWholeOneLineToALine(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	params := newParams(dir)
+	fill(params)
+
+	files := load(t, params)
+
+	err := files.WriteAll()
+	if err != nil {
+		t.Fatalf("write: %v", err)
+	}
+
+	got := readFile(t, filepath.Join(dir, reputationJSON))
+	if got != filledReputationJSON {
+		t.Errorf("reputation.json\n%s\nwant\n%s", got, filledReputationJSON)
+	}
 }
 
 func TestAlertsJSONIsIndentedWithTheCooldownsTheHourAndTheAlertsWaiting(t *testing.T) {
@@ -367,9 +470,13 @@ func TestMissingFilesAreEmptyState(t *testing.T) {
 	load(t, params)
 
 	held := params.Alerts.Snapshot()
+	checks := params.AbuseIPDB.Snapshot()
+
 	if len(params.Ledger.Snapshot()) != 0 || len(params.Limiter.Snapshot()) != 0 ||
-		len(params.GeoJS.Snapshot()) != 0 || len(held.Cooldowns) != 0 ||
+		len(params.GeoJS.Snapshot()) != 0 || len(params.Lists.Snapshot()) != 0 ||
-		len(held.Waiting[alerts.DestinationWebhook]) != 0 || held.Hour.Sent != 0 {
+		len(params.DNSBL.Snapshot()) != 0 || len(checks.Scores) != 0 || checks.Spent != 0 ||
+		len(held.Cooldowns) != 0 || len(held.Waiting[alerts.DestinationWebhook]) != 0 ||
+		held.Hour.Sent != 0 {
 		t.Error("state from no files")
 	}
 }
@@ -428,6 +535,14 @@ func TestFileThatDoesNotParseStopsTheStart(t *testing.T) {
 			`: anomaly_counters entry 2's scope "nett" is not client, net, asn, total ` +
 				`or watch`,
 		},
+		{
+			"a copy of a list with a line that does not read", reputationJSON,
+			`{"version": 1, "lists": [{"url": "` + blocklistURL + `", ` +
+				`"tried": "2026-10-06T00:00:00Z", "fetched": "2026-10-06T00:00:00Z", ` +
+				`"lines": ["; DROP", "203.0.113.300"]}]}`,
+			`: the copy of ` + blocklistURL + `: line 2 is not an address or a netblock, ` +
+				`such as 192.0.2.0/24`,
+		},
 	} {
 		t.Run(tc.name, func(t *testing.T) {
 			t.Parallel()
@@ -523,6 +638,121 @@ func TestEntryWithoutAFieldItNeedsStopsTheStart(t *testing.T) {
 	}
 }
 
+func TestReputationJSONEntryWithoutAFieldItNeedsStopsTheStart(t *testing.T) {
+	t.Parallel()
+
+	const (
+		drop    = `"url": "` + blocklistURL + `", `
+		tried   = `"tried": "2026-10-06T00:00:00Z", `
+		fetched = `"fetched": "2026-10-06T00:00:00Z"`
+		// verdictZone, verdictClient and listed start a verdict, which
+		// fetched ends.
+		verdictZone   = `"zone": "` + dnsblZone + `", `
+		verdictClient = `"client": "198.51.100.7", `
+		listed        = `"listed": false, `
+	)
+
+	for _, tc := range []struct {
+		name, content string
+		// want is what the error says after the file's path.
+		want string
+	}{
+		{
+			"a list without its URL",
+			`{"version": 1, "lists": [{` + tried + fetched + `, "lines": []}]}`,
+			`: entry 1 has no "url"`,
+		},
+		{
+			"a list without the time it was last tried",
+			`{"version": 1, "lists": [{` + drop + fetched + `, "lines": []}]}`,
+			`: entry 1 has no "tried"`,
+		},
+		{
+			"a copy of a list without the time it was fetched",
+			`{"version": 1, "lists": [{` + drop + tried + `"lines": []}]}`,
+			`: entry 1 has no "fetched"`,
+		},
+		{
+			// An empty list has no lines, which is not having none.
+			"a copy of a list without its lines",
+			`{"version": 1, "lists": [{` + drop + tried + fetched + `, "lines": []}, ` +
+				`{"url": "` + torURL + `", ` + tried + fetched + `}]}`,
+			`: entry 2 has no "lines"`,
+		},
+		{
+			"a verdict without its zone",
+			`{"version": 1, "verdicts": [{` + verdictClient + listed + fetched + `}]}`,
+			`: verdicts entry 1 has no "zone"`,
+		},
+		{
+			"a verdict without its client",
+			`{"version": 1, "verdicts": [{` + verdictZone + listed + fetched + `}]}`,
+			`: verdicts entry 1 has no "client"`,
+		},
+		{
+			// A client the zone does not list has a listed of false, which is
+			// not having none.
+			"a verdict without whether the zone lists the client",
+			`{"version": 1, "verdicts": [{` + verdictZone + verdictClient + listed +
+				fetched + `}, {` + verdictZone + verdictClient + fetched + `}]}`,
+			`: verdicts entry 2 has no "listed"`,
+		},
+		{
+			"a verdict without the time it was fetched",
+			`{"version": 1, "verdicts": [{` + verdictZone + verdictClient +
+				`"listed": true}]}`,
+			`: verdicts entry 1 has no "fetched"`,
+		},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			wantRefused(t, reputationJSON, tc.content, tc.want)
+		})
+	}
+}
+
+func TestReputationJSONScoreWithoutAFieldItNeedsStopsTheStart(t *testing.T) {
+	t.Parallel()
+
+	// scores opens the list of AbuseIPDB scores, and ends closes it; client,
+	// score and fetched make a score.
+	const (
+		scores  = `{"version": 1, "abuseipdb": {"scores": [`
+		client  = `"client": "198.51.100.7/32", `
+		score   = `"score": 0, `
+		fetched = `"fetched": "2026-10-06T00:00:00Z"`
+		ends    = `}]}}`
+	)
+
+	for _, tc := range []struct {
+		name, content string
+		// want is what the error says after the file's path.
+		want string
+	}{
+		{
+			"without its client", scores + `{` + score + fetched + ends,
+			`: abuseipdb scores entry 1 has no "client"`,
+		},
+		{
+			// A score of 0 is not having none.
+			"without the score",
+			scores + `{` + client + score + fetched + `}, {` + client + fetched + ends,
+			`: abuseipdb scores entry 2 has no "score"`,
+		},
+		{
+			"without the time it was fetched", scores + `{` + client + `"score": 100` + ends,
+			`: abuseipdb scores entry 1 has no "fetched"`,
+		},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			wantRefused(t, reputationJSON, tc.content, tc.want)
+		})
+	}
+}
+
 func TestAlertsJSONEntryWithoutAFieldItNeedsStopsTheStart(t *testing.T) {
 	t.Parallel()
 
@@ -626,7 +856,9 @@ func TestBanWithAnotherCauseStopsTheStart(t *testing.T) {
 func TestUnknownVersionStopsTheStart(t *testing.T) {
 	t.Parallel()
 
-	for _, file := range []string{bansJSON, clientsJSON, lookupsJSON, alertsJSON} {
+	for _, file := range []string{
+		bansJSON, clientsJSON, lookupsJSON, reputationJSON, alertsJSON,
+	} {
 		for _, content := range []string{`{"version": 2}`, `{}`} {
 			t.Run(file+" "+content, func(t *testing.T) {
 				t.Parallel()
@@ -696,7 +928,7 @@ func TestBansWrittenOnceWriteDelayAfterABan(t *testing.T) {
 		load(t, read)
 
 		want := []bans.Ban{first, second}
-		if got := read.Ledger.Snapshot(); !slices.Equal(got, want) {
+		if got := read.Ledger.Snapshot(); !reflect.DeepEqual(got, want) {
 			t.Errorf("bans.json holds %+v, want %+v", got, want)
 		}
 
@@ -728,8 +960,9 @@ func TestEveryFileWrittenEveryCounterInterval(t *testing.T) {
 
 			time.Sleep(time.Nanosecond)
 			synctest.Wait()
-			wantFiles(t, dir, alertsJSON, bansJSON, clientsJSON, lookupsJSON)
+			wantFiles(t, dir, alertsJSON, bansJSON, clientsJSON, lookupsJSON, reputationJSON)
-			removeFiles(t, dir, alertsJSON, bansJSON, clientsJSON, lookupsJSON)
+			removeFiles(t, dir, alertsJSON, bansJSON, clientsJSON, lookupsJSON,
+				reputationJSON)
 		}
 	})
 }
@@ -948,7 +1181,7 @@ func TestFileThatCannotBeReadIsNotWrittenOver(t *testing.T) {
 		t.Errorf("bans.json is now %v (%v), want the socket", info, err)
 	}
 
-	wantFiles(t, dir, alertsJSON, bansJSON, clientsJSON, lookupsJSON)
+	wantFiles(t, dir, alertsJSON, bansJSON, clientsJSON, lookupsJSON, reputationJSON)
 	wantWriteFailed(t, params, bansJSON)
 }
 
@@ -1021,6 +1254,32 @@ func TestEditOfEachFileTakenIn(t *testing.T) {
 	wantEqual(t, lookupsJSON, params.GeoJS.Snapshot(),
 		[]lookup.Answer{{Client: client, Country: "FR", Answered: midnight()}})
 
+	edit(t, dir, reputationJSON, `{"version": 1, "lists": [{"url": "`+blocklistURL+`", `+
+		`"tried": "2026-10-06T00:00:00Z", "fetched": "2026-10-06T00:00:00Z", `+
+		`"lines": ["198.51.100.7"]}], "verdicts": [{"zone": "`+dnsblZone+`", `+
+		`"client": "198.51.100.7", "listed": true, "fetched": "2026-10-06T00:00:00Z"}], `+
+		`"abuseipdb": {"day": "2026-10-06T00:00:00Z", "spent": 9, "scores": [`+
+		`{"client": "198.51.100.7/32", "score": 80, "fetched": "2026-10-06T00:00:00Z"}]}}`)
+	wantTakenIn(t, lines, dir, reputationJSON)
+
+	listedBy := params.Lists.ListedBy(client.Addr())
+	if !slices.Equal(listedBy, []string{blocklistURL}) {
+		t.Errorf("%s taken in lists %s on %v, want on the blocklist", reputationJSON,
+			client.Addr(), listedBy)
+	}
+
+	wantEqual(t, reputationJSON, params.DNSBL.Snapshot(), []reputation.Verdict{{
+		Zone: dnsblZone, Client: client.Addr(), Listed: true, Fetched: midnight(),
+	}})
+
+	checks := reputation.Checks{
+		Day: midnight(), Spent: 9,
+		Scores: []reputation.Score{{Client: client, Score: 80, Fetched: midnight()}},
+	}
+	if got := params.AbuseIPDB.Snapshot(); !reflect.DeepEqual(got, checks) {
+		t.Errorf("%s taken in as\n%+v\nwant\n%+v", reputationJSON, got, checks)
+	}
+
 	// A netblock with bits past its length is read as the netblock it is
 	// in.
 	edit(t, dir, alertsJSON, `{"version": 1, "cooldowns": [{"event": "ban", `+
@@ -1248,7 +1507,7 @@ func TestBrokenEditSetAsideAtTheNextWrite(t *testing.T) {
 	edit(t, dir, bansJSON, broken)
 	edit(t, dir, clientsJSON, `{"version": 1, "clients": []}`)
 	wantTakenIn(t, lines, dir, clientsJSON)
-	wantFiles(t, dir, alertsJSON, bansJSON, clientsJSON, lookupsJSON)
+	wantFiles(t, dir, alertsJSON, bansJSON, clientsJSON, lookupsJSON, reputationJSON)
 
 	// The next write sets it aside, logged with where the error is, and
 	// writes bans.json again from what smallwebwaf still holds.
@@ -1272,7 +1531,8 @@ func TestBrokenEditSetAsideAtTheNextWrite(t *testing.T) {
 		t.Errorf("alerts waiting %+v, want a file_error alert for %s", waiting, path+".bad")
 	}
 
-	wantFiles(t, dir, alertsJSON, bansJSON, bansJSON+".bad", clientsJSON, lookupsJSON)
+	wantFiles(t, dir, alertsJSON, bansJSON, bansJSON+".bad", clientsJSON, lookupsJSON,
+		reputationJSON)
 
 	if got := readFile(t, path+".bad"); got != broken {
 		t.Errorf("bans.json.bad holds\n%s\nwant the edit", got)
@@ -1401,9 +1661,10 @@ func midnight() time.Time {
 }
 
 // newParams returns Params for the state files in dir, with parts that
-// hold nothing yet. GeoJS is never asked, and the alerts, at most two an
+// hold nothing yet. GeoJS is never asked, the lists, two blocklists, are
-// hour, are never sent. The anomaly counters count the scopes fill
+// never fetched, and the alerts, at most two an hour, are
-// counts, with thresholds fill does not reach.
+// never sent. The anomaly counters count the scopes fill counts, with
+// thresholds fill does not reach.
 func newParams(dir string) state.Params {
 	discard := slog.New(slog.DiscardHandler)
 	m := metrics.New(1, "app")
@@ -1427,10 +1688,22 @@ func newParams(dir string) state.Params {
 			AttackBanDuration:    7 * 24 * time.Hour,
 			MaxBans:              5000,
 		}),
-		Limiter: ratelimit.New(ratelimit.Limits{}),
+		Limiter: ratelimit.New(ratelimit.Limits{}, 20000),
 		GeoJS: lookup.New(lookup.Params{
 			Now: midnight, ProcessLog: discard, Metrics: m,
 		}),
+		Lists: reputation.New(reputation.Params{
+			BlocklistURLs: []string{blocklistURL, torURL}, Refresh: 24 * time.Hour,
+			Now: midnight, ProcessLog: discard, Alerts: queue,
+		}),
+		DNSBL: reputation.NewDNSBL(reputation.DNSBLParams{
+			Zones: []string{dnsblZone}, CacheTTL: 24 * time.Hour, Timeout: time.Second,
+			Now: midnight, ProcessLog: discard, Alerts: queue,
+		}),
+		AbuseIPDB: reputation.NewAbuseIPDB(reputation.AbuseIPDBParams{
+			MinScore: 75, DailyBudget: 900, CacheTTL: 24 * time.Hour, Timeout: time.Second,
+			Now: midnight, ProcessLog: discard, Alerts: queue,
+		}),
 		Alerts: queue,
 		Anomalies: anomaly.New(anomaly.Params{
 			Net:            anomaly.Thresholds{RequestsPerMinute: 1000},
@@ -1455,8 +1728,11 @@ func office() netip.Prefix {
 
 // fill puts a permanent ban an admin made, a ban for a broken limit and
 // one for a clear sign of attack, clients with counts and histories,
-// GeoJS answers, and alerts and anomaly counters, as filledAlertsJSON
+// GeoJS answers, the blocklists' last tries and the copy of one, two
-// holds them, into the parts of params.
+// verdicts of a DNSBL zone, and the AbuseIPDB checks spent today with two
+// scores, as filledReputationJSON holds them, and alerts
+// and anomaly counters, as filledAlertsJSON holds them, into the parts of
+// params.
 func fill(params state.Params) {
 	now := midnight()
 	client := netip.MustParsePrefix("203.0.113.9/32")
@@ -1489,6 +1765,32 @@ func fill(params state.Params) {
 		},
 	})
 
+	// The copy of drop.txt was fetched an hour ago, and the fetches of it
+	// and of tor.txt tried since failed.
+	err := params.Lists.Load([]reputation.List{{
+		URL: blocklistURL, Tried: now, Fetched: now.Add(-time.Hour),
+		Lines: []string{
+			"; Spamhaus DROP List 2026/10/05 - (c) 2026 The Spamhaus Project SLL",
+			"203.0.113.0/24 ; SBL1",
+			"2001:db8::/32 ; SBL2",
+		},
+	}, {URL: torURL, Tried: now}})
+	if err != nil {
+		panic(err) // the copy reads
+	}
+
+	params.DNSBL.Load([]reputation.Verdict{
+		{
+			Zone: dnsblZone, Client: netip.MustParseAddr("2001:db8::1"),
+			Fetched: now.Add(-2 * time.Hour),
+		},
+		{Zone: dnsblZone, Client: client.Addr(), Listed: true, Fetched: now.Add(-time.Hour)},
+	})
+	params.AbuseIPDB.Load(reputation.Checks{Day: now, Spent: 3, Scores: []reputation.Score{
+		{Client: netip.MustParsePrefix("2001:db8::/64"), Fetched: now.Add(-2 * time.Hour)},
+		{Client: client, Score: 100, Fetched: now.Add(-time.Hour)},
+	}})
+
 	// An alert waiting, a repeat of it the cooldown holds back, another
 	// alert waiting, and one past the two an hour, for the hour's summary.
 	ban := alerts.Alert{
@@ -1515,6 +1817,8 @@ func fill(params state.Params) {
 
 // permanentBan is the ban permanentBansJSON holds.
 func permanentBan() bans.Ban {
+	score := int64(100)
+
 	return bans.Ban{
 		Netblock: netip.MustParsePrefix("2001:db8::/64"),
 		Start:    midnight(),
@@ -1527,6 +1831,9 @@ func permanentBan() bans.Ban {
 			Limit:   1000,
 			Window:  "minute",
 			Count:   1000.5,
+			Reputation: []bans.ReputationHit{
+				{Source: blocklistURL}, {Source: reputation.AbuseIPDBSource, Score: &score},
+			},
 			Request: bans.Request{
 				Time:      midnight(),
 				Method:    "GET",
@@ -1702,10 +2009,10 @@ func edit(t *testing.T, dir, name, content string) {
 
 // wantEqual checks that the entries read back from file are those
 // written.
-func wantEqual[E comparable](t *testing.T, file string, got, want []E) {
+func wantEqual[E any](t *testing.T, file string, got, want []E) {
 	t.Helper()
 
-	if !slices.Equal(got, want) {
+	if !reflect.DeepEqual(got, want) {
 		t.Errorf("%s read back\n%+v\nwant\n%+v", file, got, want)
 	}
 }