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

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

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

Model: opus-5-5

SPEC.md

@@ -2353,7 +2353,8 @@ but for these headers:
   claims and are replaced. `X-Forwarded-For` names the peer, `X-Forwarded-Host`
   the host it asked for, and `X-Forwarded-Proto` plain `http`. Every other
   header whose name starts with `X-Forwarded-` is removed, and so are
-  `Forwarded` and `X-Real-IP`.
+  `Forwarded` and `X-Real-IP`. A name spelt with `_` for `-`, such as
+  `X_Forwarded_Ssl`, counts as the same name.
 - `X-Request-ID`, which carries the fresh id.
 - `X-Client-ASN` and `X-Client-Country`, which carry what `waf` answered. A
   header it did not give is left out. Any of the two the visitor sent is

internal/alerts/alerts.go

@@ -56,9 +56,11 @@ const (
 	// 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 sww
-	// runs that does not parse, a replacement of the lookup database that
-	// cannot be read, or a state file that cannot be written.
+	// EventFileError is one of:
+	//   - a rule file or state file edited while sww runs that does not parse;
+	//   - a cache file that does not parse, at start or after an edit;
+	//   - a state file or cache file that cannot be written;
+	//   - a replacement of the lookup database that cannot be read.
 	EventFileError = "file_error"
 	// EventSummary is the summary sent as an hour ends: of the alerts held
 	// back in it past SWW_ALERT_MAX_PER_HOUR, and of the repeats held

internal/metrics/metrics.go

@@ -120,17 +120,19 @@ func New(topN int, instanceName string) *Metrics {
 				"went on without it, because GeoJS had not given it in time.",
 		}),
 		stateFileWrites: counterVec("sww_state_file_writes_total",
-			"Writes of each state file.", byFile),
+			"Writes of each state or cache file.", byFile),
 		stateFileWriteFailures: counterVec("sww_state_file_write_failures_total",
-			"Writes of each state file that failed.", byFile),
+			"Writes of each state or cache file that failed.", byFile),
 		stateFileLastWrite: gaugeVec("sww_state_file_last_write_timestamp_seconds",
-			"When each state file was last written, in seconds since 1970.", byFile),
+			"When each state or cache file was last written, in seconds since 1970.",
+			byFile),
 		stateFileSize: gaugeVec("sww_state_file_size_bytes",
-			"The size of each state file, as it was last written.", byFile),
+			"The size of each state or cache file, as it was last written.", byFile),
 		stateFileEditsTakenIn: counterVec("sww_state_file_edits_taken_in_total",
-			"Edits of each state file taken in while running.", byFile),
+			"Edits of each state or cache file taken in while running.", byFile),
 		stateFileEditsSetAside: counterVec("sww_state_file_edits_set_aside_total",
-			"Edits of each state file renamed to <name>.bad because they did not parse.",
+			"Edits of each state or cache file renamed to <name>.bad because they "+
+				"did not parse.",
 			byFile),
 	}
 
@@ -447,8 +449,8 @@ func (m *Metrics) CoreRuleSetMatched(mode string, id int) {
 	m.coreRuleSetMatches.WithLabelValues(mode, strconv.Itoa(id)).Inc()
 }
 
-// StateFileWritten counts a write of the state file name, of size bytes,
-// that ended with err.
+// StateFileWritten counts a write of the state or cache file name, of size
+// bytes, that ended with err.
 func (m *Metrics) StateFileWritten(name string, size int, err error) {
 	m.stateFileWrites.WithLabelValues(name).Inc()
 
@@ -466,13 +468,13 @@ func (m *Metrics) StateFileWritten(name string, size int, err error) {
 	m.stateFileSize.WithLabelValues(name).Set(float64(size))
 }
 
-// StateFileEditTakenIn counts an admin's edit of the state file name
+// StateFileEditTakenIn counts an admin's edit of the state or cache file name
 // taken in while sww runs.
 func (m *Metrics) StateFileEditTakenIn(name string) {
 	m.stateFileEditsTakenIn.WithLabelValues(name).Inc()
 }
 
-// StateFileEditSetAside counts an admin's edit of the state file name
+// StateFileEditSetAside counts an admin's edit of the state or cache file name
 // renamed to name.bad because it did not parse.
 func (m *Metrics) StateFileEditSetAside(name string) {
 	m.stateFileEditsSetAside.WithLabelValues(name).Inc()

internal/rproxy/client.go

@@ -105,17 +105,16 @@ func setForwardedHeaders(in, out *http.Request, peer netip.Addr, trusted bool) {
 		return
 	}
 
-	// ReverseProxy has removed Forwarded and the three set below. Go's server
-	// gives header names in canonical form, so the prefix matches the name in
-	// any letter case.
+	// An app behind CGI or FastCGI reads X_Forwarded_Ssl as X-Forwarded-Ssl, so
+	// a name is matched with each _ read as - and in any letter case.
 	for name := range out.Header {
-		if strings.HasPrefix(name, "X-Forwarded-") {
+		spelt := strings.ToLower(strings.ReplaceAll(name, "_", "-"))
+		if strings.HasPrefix(spelt, "x-forwarded-") ||
+			spelt == "forwarded" || spelt == "x-real-ip" {
 			delete(out.Header, name)
 		}
 	}
 
-	out.Header.Del("X-Real-IP")
-
 	out.Header.Set("X-Forwarded-For", forwardedFor)
 	out.Header.Set("X-Forwarded-Host", in.Host)
 	out.Header.Set("X-Forwarded-Proto", "http")

internal/rproxy/rproxy_test.go

@@ -561,6 +561,7 @@ func TestAPeerNotTrustedHasItsForwardedHeadersReplaced(t *testing.T) {
 		"X-Forwarded-Tls-Client-Cert-Info", "X-Real-Ip",
 		"X-Forwarded-Scheme", "X-Forwarded-Ssl", "X-Forwarded-Protocol",
 		"X-Forwarded-Path", "X-Forwarded-Client-Cert",
+		"X_Forwarded_Ssl", "X_Forwarded_Proto", "X_Real_IP",
 	}
 
 	standIn := startWAF(t, allow)
@@ -628,6 +629,7 @@ func TestATrustedProxysForwardedHeadersPassOn(t *testing.T) {
 		forwardedProtoHeader: "https",
 		"X-Real-Ip":          "198.51.100.1",
 		"X-Forwarded-Ssl":    "on",
+		"X_Forwarded_Ssl":    "on",
 	}
 
 	req := newRequest(t, http.MethodGet, addr, "/", http.NoBody)

internal/sww/sww.go

@@ -1,9 +1,9 @@
 // Package sww runs the sww process, as the command it is given.
 // `sww waf` reads the settings, the rule files, the lookup database
-// and the state files, answers rproxy's questions until it is told to stop, and
-// then stops in an orderly way, writing the state files. `sww rproxy`
-// reads rproxy's settings alone, and runs the reverse proxy in front of one app
-// that asks waf about each request. `sww healthcheck` is the
+// and the state and cache files, answers rproxy's questions until it is told to
+// stop, and then stops in an orderly way, writing the state and cache files.
+// `sww rproxy` reads rproxy's settings alone, and runs the reverse proxy in
+// front of one app that asks waf about each request. `sww healthcheck` is the
 // container's health check.
 package sww
 
@@ -101,8 +101,8 @@ func printUsage(w io.Writer) int {
 }
 
 // RunWAF is `sww waf`: it reads the settings, the rule files,
-// the lookup database and the state files, then serves requests until ctx is
-// done. It returns the process's exit status, 1 when waf cannot start.
+// the lookup database and the state and cache files, then serves requests until
+// ctx is done. It returns the process's exit status, 1 when waf cannot start.
 func RunWAF(ctx context.Context, params Params) int {
 	// Until the settings are read, the one message is an invalid setting's
 	// error, which every SWW_LOG_LEVEL lets through.
@@ -171,7 +171,7 @@ func RunWAF(ctx context.Context, params Params) int {
 
 	files, err := loadStateFiles(cfg, server, alertQueue, now, processLog)
 	if err != nil {
-		processLog.Error("cannot use the state files", "error", err.Error())
+		processLog.Error("cannot use the state and cache files", "error", err.Error())
 
 		return 1
 	}
@@ -236,8 +236,8 @@ func newServer(
 	return server, nil
 }
 
-// loadStateFiles reads the state files into the parts of server and into
-// alertQueue, as state.Load does.
+// loadStateFiles reads the state and cache files into the parts of server and
+// into alertQueue, as state.Load does.
 func loadStateFiles(
 	cfg *config.Config, server *waf.Server, alertQueue *alerts.Queue,
 	now func() time.Time, processLog *slog.Logger,
@@ -319,13 +319,13 @@ 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
+// serve serves requests on listener, writes the state and cache 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, fetches the
 // 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.
+// shutdownTimeout to finish, and writes every state and cache file,
+// alerts.json with the alerts still waiting.
 func serve(
 	ctx context.Context, server *waf.Server, listener net.Listener,
 	files *state.Files, ruleFiles *rules.Files, alertQueue *alerts.Queue,
@@ -395,7 +395,7 @@ func serve(
 
 	err = files.WriteAll()
 	if err != nil {
-		processLog.Error("writing the state files failed", "error", err.Error())
+		processLog.Error("writing the state and cache files failed", "error", err.Error())
 
 		return 1
 	}

internal/sww/sww_test.go

@@ -1235,7 +1235,7 @@ func TestUnwritableCacheDirStopsTheStart(t *testing.T) {
 		t.Fatalf("exit status %d, want 1", status)
 	}
 
-	line := out.line(t, "msg", "cannot use the state files")
+	line := out.line(t, "msg", "cannot use the state and cache files")
 	if message, _ := line["error"].(string); !strings.HasPrefix(message,
 		"SWW_CACHE_DIR cannot be written: ") {
 		t.Errorf("start refused with %q, want SWW_CACHE_DIR named", message)
@@ -1260,7 +1260,7 @@ func wantStartRefused(t *testing.T, dir, want string) {
 		t.Fatalf("exit status %d, want 1", status)
 	}
 
-	line := out.line(t, "msg", "cannot use the state files")
+	line := out.line(t, "msg", "cannot use the state and cache files")
 	message, _ := line["error"].(string)
 
 	if !strings.HasPrefix(message, want) {