SWW_APPS: an app's Core Rule Set fixes apply only to the hostnames that serve it (closes #220)

Each app's fixes are one .conf file and one entry in apps. They apply
only while Inspect has set the app's transaction variable, such as
tx.app_gitea. SWW_APPS names each hostname's apps. A hostname gets only
its apps' fixes; while SWW_APPS is unset, every hostname gets every
app's fixes.

A hostname in SWW_APPS that is not a DNS name, such as *.example.com,
stops the start. Unset, SWW_APPS is logged at start as null; set
empty, as "".

Model: opus-5-5

internal/config/config.go

@@ -29,6 +29,7 @@ import (
 
 	"sneak.berlin/go/smallwebwaf/internal/alerts"
 	"sneak.berlin/go/smallwebwaf/internal/anomaly"
+	"sneak.berlin/go/smallwebwaf/internal/coreruleset"
 	"sneak.berlin/go/smallwebwaf/internal/remotelog"
 )
 
@@ -235,6 +236,11 @@ type Config struct {
 	WAFExemptPaths            []string
 	WAFBodyLimit              int64
 	CoreRuleSetExclusionsFile string
+	// Apps are the names of the apps each hostname serves, by hostname in
+	// lowercase (SWW_APPS): a request gets only its hostname's apps' fixes
+	// to the Core Rule Set. Apps is nil while SWW_APPS is unset, and every
+	// request gets every app's fixes.
+	Apps map[string][]string
 	// TrapPaths are the paths a request for which is a clear sign of
 	// attack (SWW_TRAP_PATHS), each starting with / and without a ?.
 	TrapPaths []string
@@ -404,6 +410,11 @@ var (
 	errNotTrapPath = errors.New(
 		"is not a path starting with / and without a ?, such as /wp-login.php",
 	)
+	errNotAppsEntry = errors.New(
+		"is not a hostname, : and a list of apps, such as git.example.com:gitea",
+	)
+	errNotHostname      = errors.New("is not a DNS name such as git.example.com")
+	errNotApp           = errors.New("is not an app sww has fixes for; the apps are")
 	errNotWAFMode       = errors.New("is not off, detect or block")
 	errNotParanoiaLevel = errors.New("is not a paranoia level, from 1 to 4")
 	errNotRuleID        = errors.New(
@@ -577,6 +588,7 @@ func FromEnvironment(
 		WAFBodyLimit:   env.wafBodyLimit("SWW_WAF_BODY_LIMIT", off),
 		CoreRuleSetExclusionsFile: env.filePath(
 			"SWW_CORE_RULE_SET_EXCLUSIONS_FILE"),
+		Apps:                 env.apps("SWW_APPS"),
 		TrapPaths:            env.trapPaths("SWW_TRAP_PATHS"),
 		ErrorBurstThreshold:  env.count("SWW_ERROR_BURST_THRESHOLD", "30"),
 		LogRemoteURL:         env.logRemoteURL("SWW_LOG_REMOTE_URL"),
@@ -832,6 +844,25 @@ func (e *environment) pathPrefixes(name, defaultValue string) []string {
 	return prefixes
 }
 
+// apps reads the setting that is the apps each hostname serves. It is nil
+// while the setting is unset, and logged as null, unlike a setting set
+// empty.
+func (e *environment) apps(name string) map[string][]string {
+	value, set := e.lookup(name)
+	if !set {
+		e.settings = append(e.settings, slog.Any(name, nil))
+
+		return nil
+	}
+
+	e.settings = append(e.settings, slog.String(name, value))
+
+	apps, err := parseApps(value)
+	e.check(name, err)
+
+	return apps
+}
+
 // trapPaths reads the setting that is the list of trap paths. It is empty
 // by default.
 func (e *environment) trapPaths(name string) []string {
@@ -1849,6 +1880,65 @@ func parseTrapPaths(value string) ([]string, error) {
 	return paths, nil
 }
 
+// parseApps reads the apps each hostname serves: entries separated by
+// semicolons, each a hostname, a colon, and a comma-separated list of the
+// names coreruleset.AppNames returns, such as
+// git.example.com:gitea;cloud.example.com:nextcloud,wordpress. Each
+// hostname is a DNS name, without a wildcard. It returns them by hostname
+// in lowercase, since a hostname is matched without regard to case. An
+// empty value lists no hostname.
+func parseApps(value string) (map[string][]string, error) {
+	apps := map[string][]string{}
+
+	if strings.TrimSpace(value) == "" {
+		return apps, nil
+	}
+
+	for entry := range strings.SplitSeq(value, ";") {
+		hostname, list, found := strings.Cut(entry, ":")
+		if !found {
+			return nil, fmt.Errorf("%q %w", entry, errNotAppsEntry)
+		}
+
+		hostname = strings.ToLower(strings.TrimSpace(hostname))
+		if hostname == "" {
+			return nil, fmt.Errorf("%q %w", entry, errNotAppsEntry)
+		}
+
+		if !isZone(hostname) {
+			return nil, fmt.Errorf("%q %w", hostname, errNotHostname)
+		}
+
+		if _, listed := apps[hostname]; listed {
+			return nil, fmt.Errorf("%q %w", hostname, errListedTwice)
+		}
+
+		names, err := parseList(list)
+		if err != nil {
+			return nil, err
+		}
+
+		if len(names) == 0 {
+			return nil, fmt.Errorf("%q %w", entry, errNotAppsEntry)
+		}
+
+		for i, name := range names {
+			if !slices.Contains(coreruleset.AppNames(), name) {
+				return nil, fmt.Errorf("%q %w %s", name, errNotApp,
+					strings.Join(coreruleset.AppNames(), ", "))
+			}
+
+			if slices.Contains(names[:i], name) {
+				return nil, fmt.Errorf("%q %w", name, errListedTwice)
+			}
+		}
+
+		apps[hostname] = names
+	}
+
+	return apps, nil
+}
+
 // parseRuleIDs reads a comma-separated list of the ids of Core Rule Set
 // rules, each a whole number above zero and outside firstSetupRuleID to
 // lastSetupRuleID.
@@ -2455,7 +2545,8 @@ func MaskZoneKey(zone string) string {
 	return masked + "." + rest
 }
 
-// isZone reports whether each label of zone is as parseZones takes it.
+// isZone reports whether each label of zone is as parseZones takes it. It
+// also checks the hostnames of SWW_APPS, which are DNS names too.
 func isZone(zone string) bool {
 	for label := range strings.SplitSeq(zone, ".") {
 		badChar := strings.ContainsFunc(label, func(char rune) bool {

internal/config/config_test.go

@@ -89,6 +89,7 @@ const (
 	wafExemptPaths       = "SWW_WAF_EXEMPT_PATHS"
 	wafBodyLimit         = "SWW_WAF_BODY_LIMIT"
 	exclusionsFile       = "SWW_CORE_RULE_SET_EXCLUSIONS_FILE"
+	apps                 = "SWW_APPS"
 	trapPaths            = "SWW_TRAP_PATHS"
 	errorBurstThreshold  = "SWW_ERROR_BURST_THRESHOLD"
 	logRemoteURL         = "SWW_LOG_REMOTE_URL"
@@ -582,6 +583,100 @@ func TestCoreRuleSetSettings(t *testing.T) {
 	}
 }
 
+// gitea is gitea's name in SWW_APPS.
+const gitea = "gitea"
+
+func TestApps(t *testing.T) {
+	t.Parallel()
+
+	for _, tc := range []struct {
+		env  environment
+		want map[string][]string
+	}{
+		{environment{}, nil},
+		{environment{apps: ""}, map[string][]string{}},
+		{
+			environment{apps: "Git.Example.com:gitea; cloud.example.com : gitea "},
+			map[string][]string{
+				"git.example.com": {gitea}, "cloud.example.com": {gitea},
+			},
+		},
+		{
+			environment{apps: "cloud.example.com:gitea,wordpress"},
+			map[string][]string{"cloud.example.com": {gitea, "wordpress"}},
+		},
+	} {
+		cfg := fromEnvironment(t, tc.env)
+		if !reflect.DeepEqual(cfg.Apps, tc.want) {
+			t.Errorf("%v gave %#v, want %#v", tc.env, cfg.Apps, tc.want)
+		}
+	}
+}
+
+// Unset and set empty, SWW_APPS has opposite effects, so it logs differently.
+func TestUnsetAndEmptyAppsAreLoggedDifferently(t *testing.T) {
+	t.Parallel()
+
+	for _, tc := range []struct {
+		env  environment
+		want string
+	}{
+		{environment{}, `"` + apps + `":null`},
+		{environment{apps: ""}, `"` + apps + `":""`},
+	} {
+		var out bytes.Buffer
+
+		slog.New(slog.NewJSONHandler(&out, nil)).
+			Info("starting", "settings", fromEnvironment(t, tc.env))
+
+		if !strings.Contains(out.String(), tc.want) {
+			t.Errorf("%v logged %s, want %s in it", tc.env, out.String(), tc.want)
+		}
+	}
+}
+
+func TestInvalidAppsStopsTheStart(t *testing.T) {
+	t.Parallel()
+
+	const (
+		notEntry = " is not a hostname, : and a list of apps, " +
+			"such as git.example.com:gitea"
+		notHostname = " is not a DNS name such as git.example.com"
+	)
+
+	for _, tc := range []struct{ value, want string }{
+		{"git.example.com:gitea;blog.example.com", `"blog.example.com"` + notEntry},
+		{"git.example.com:gitea;", `""` + notEntry},
+		{":gitea", `":gitea"` + notEntry},
+		{"git.example.com:", `"git.example.com:"` + notEntry},
+		{"*.example.com:gitea", `"*.example.com"` + notHostname},
+		{"git.example.com/:gitea", `"git.example.com/"` + notHostname},
+		{"git example.com:gitea", `"git example.com"` + notHostname},
+		{
+			"git.example.com:gitea,nextcloud",
+			`"nextcloud" is not an app sww has fixes for; ` +
+				`the apps are drupal, gitea, mediawiki, wordpress`,
+		},
+		{
+			"git.example.com:gitea;GIT.example.com:gitea",
+			`"git.example.com" is listed twice`,
+		},
+		{"git.example.com:gitea,gitea", `"gitea" is listed twice`},
+		{"git.example.com:gitea,", `"gitea," has an empty item in its list`},
+	} {
+		t.Run(tc.value, func(t *testing.T) {
+			t.Parallel()
+
+			_, err := config.FromEnvironment(environment{apps: tc.value}.lookupEnv)
+
+			want := apps + ": " + tc.want
+			if err == nil || err.Error() != want {
+				t.Errorf("error %v, want %s", err, want)
+			}
+		})
+	}
+}
+
 func TestWAFBodyLimitOf64K(t *testing.T) {
 	t.Parallel()
 
@@ -2589,6 +2684,7 @@ func TestLogsEachSettingWithItsValue(t *testing.T) {
 		wafExemptPaths:       "",
 		wafBodyLimit:         off,
 		exclusionsFile:       "",
+		apps:                 "", // logged as null, which decodes as ""
 		trapPaths:            "",
 		errorBurstThreshold:  "30",
 		logRemoteURL:         "",