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

gitea's fixes (its parameters, its cookies and gitea.conf) now apply
only to a hostname SWW_APPS lists gitea for, or to every hostname while
it is unset. Each app's fixes are one .conf file, whose first rule skips
the rest unless Inspect sets tx.app_<name>, and one entry in apps.

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/remotelog"
+	"sneak.berlin/go/smallwebwaf/internal/waf"
 )
 
 // Config is the settings of `sww discriminator`. A time or size limit of
@@ -230,6 +231,11 @@ 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
@@ -398,6 +404,9 @@ var (
 		"is not a path prefix starting with /, such as /assets/")
 	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")
+	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(
@@ -530,6 +539,7 @@ func FromEnvironment(lookupEnv func(string) (string, bool)) (*Config, error) {
 		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"),
@@ -780,6 +790,22 @@ 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.
+func (e *environment) apps(name string) map[string][]string {
+	value, set := e.lookup(name)
+	e.settings = append(e.settings, slog.String(name, value))
+
+	if !set {
+		return nil
+	}
+
+	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 {
@@ -1646,6 +1672,60 @@ 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 waf.AppNames returns, such as
+// git.example.com:gitea;cloud.example.com:nextcloud,wordpress. 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 _, 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(waf.AppNames(), name) {
+				return nil, fmt.Errorf("%q %w %s", name, errNotApp,
+					strings.Join(waf.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.