servewaf: each decision heuristic is its own module (closes #195)

Each check servewaf runs on a request is a type in its own file behind
one interface, heuristic, and is registered in one of four ordered lists
in heuristics.go. Order and behaviour are unchanged.

Every refusal or ban now logs heuristic, the name of the heuristic that
made it, and heuristic_figures, the figures it acted on. Both are in
docs/request-log.md, and SPEC.md names each heuristic at its step.

Model: opus-5-5

internal/servewaf/heuristics.go

@@ -0,0 +1,104 @@
+package servewaf
+
+import (
+	"context"
+	"time"
+)
+
+// To add a heuristic, write one file with a type that implements heuristic,
+// and add one line for it to one of the lists below. Its settings go in
+// config.Config, and the comment at the top of its file names them.
+
+// heuristic is one of the checks that decide what servewaf does with a request.
+type heuristic interface {
+	// name is the heuristic's name, which the log line gives.
+	name() string
+	// check looks at the request at now, and returns nil to let it through.
+	// ctx is the request's own context.
+	check(ctx context.Context, rq *request, now time.Time) *verdict
+}
+
+// verdict is a heuristic refusing a request, or banning its client: the action
+// the log line names, one of requestlog's Action constants, and the figures the
+// heuristic acted on, by name, such as the count and the limit.
+type verdict struct {
+	action  string
+	figures map[string]any
+}
+
+// The names of the figures that more than one heuristic gives.
+const (
+	figureLimit = "limit"
+	figureScore = "score"
+)
+
+// The lists of heuristics, each in the order its heuristics run. A client in
+// SWWAF_ALLOW_NETS skips them all.
+
+// beforeLookup are the heuristics that run before the client's AS number and
+// country are looked up, so that a client they refuse is not looked up.
+func beforeLookup() []heuristic {
+	return []heuristic{
+		denyNets{},
+		activeBan{},
+	}
+}
+
+// afterLookup are the heuristics that run once the lookup has been made.
+func afterLookup() []heuristic {
+	return []heuristic{
+		countries{},
+		blocklists{},
+		crowdSec{},
+		dnsbl{},
+		abuseIPDB{},
+		rateLimits{},
+		trapPaths{},
+		ruleFiles{},
+		headerLimits{},
+		coreRuleSet{},
+	}
+}
+
+// afterAnswer are the heuristics that run on a request once servewaf has
+// answered it, before its decision line is written. They ban the client, and do
+// not change what the request got: their verdict's action is not used.
+func afterAnswer() []heuristic {
+	return []heuristic{
+		refusalLimit{},
+	}
+}
+
+// onReport are the heuristics that run on an allowed request when rproxy's
+// report of it comes, before its report line is written. Like afterAnswer, they
+// only ban.
+func onReport() []heuristic {
+	return []heuristic{
+		byteLimits{},
+	}
+}
+
+// runAfterAnswer runs the heuristics of afterAnswer on the request, at the time
+// it is called.
+func (rq *request) runAfterAnswer(ctx context.Context) {
+	rq.runHeuristics(ctx, afterAnswer(), rq.h.now())
+}
+
+// runHeuristics runs list on the request at now, in order, and returns the
+// first verdict, or nil when none gives one. The log line names the heuristic
+// that gave it, and its figures. ctx is the request's own context.
+func (rq *request) runHeuristics(
+	ctx context.Context, list []heuristic, now time.Time,
+) *verdict {
+	for _, each := range list {
+		v := each.check(ctx, rq, now)
+		if v != nil {
+			rq.line.Heuristic = each.name()
+			rq.line.HeuristicFigures = v.figures
+
+			return v
+		}
+	}
+
+	return nil
+}