Resolve PTR names over DNS-over-HTTPS and cache them for the record TTL (closes #238)

`internal/ptr` asks Google, Cloudflare, AdGuard and Quad9 in turn, 2 seconds in all per address. It keeps answers in memory and writes them through to `cache.db`, opened by the new `internal/cachedb`.

Judgement calls:
- Each resolver gets an equal share of the time left, so a hung resolver does not use up the 2 seconds.
- The negative TTL is the smaller of the SOA minimum and the SOA's own TTL (RFC 2308).
- Names that are not host names are dropped, as `net.Resolver.LookupAddr` does.

Model: opus-5-5

internal/ptr/doh.go

@@ -0,0 +1,200 @@
+package ptr
+
+import (
+	"bytes"
+	"context"
+	"errors"
+	"fmt"
+	"io"
+	"math"
+	"net/http"
+	"strings"
+	"time"
+
+	"github.com/miekg/dns"
+)
+
+const (
+	// LookupTimeout limits one address's lookup, every resolver included.
+	LookupTimeout = 2 * time.Second
+
+	// minTTL and maxTTL limit how long PTR names are kept.
+	minTTL = time.Minute
+	maxTTL = 24 * time.Hour
+
+	// maxNegativeTTL limits how long an address with no PTR names is
+	// remembered as having none.
+	maxNegativeTTL = time.Hour
+
+	// dnsMessageType is the content type of RFC 8484 requests and answers.
+	dnsMessageType = "application/dns-message"
+
+	// maxMessageBytes is the largest possible DNS message.
+	maxMessageBytes = 65535
+)
+
+var (
+	errBadStatus   = errors.New("unexpected HTTP status")
+	errBadResponse = errors.New("resolver reported an error")
+)
+
+// Resolvers returns the URLs of the public DNS-over-HTTPS resolvers, in the
+// order they are tried.
+func Resolvers() []string {
+	return []string{
+		"https://dns.google/dns-query",
+		"https://cloudflare-dns.com/dns-query",
+		"https://unfiltered.adguard-dns.com/dns-query",
+		"https://dns.quad9.net/dns-query",
+	}
+}
+
+// answer is a resolver's answer for one address.
+type answer struct {
+	// names are the address's PTR names, nil when it has none.
+	names []string
+
+	// ttl is how long the answer may be kept. Zero means it is not kept.
+	ttl time.Duration
+}
+
+// lookup asks the resolvers in turn for the PTR names of the reverse name
+// until one answers. It fails when none has answered within LookupTimeout.
+func (c *Cache) lookup(ctx context.Context, reverseName string) (answer, error) {
+	ctx, cancel := context.WithTimeout(ctx, LookupTimeout)
+	defer cancel()
+
+	query := new(dns.Msg).SetQuestion(reverseName, dns.TypePTR)
+	query.Id = 0 // RFC 8484 asks for 0, so that equal queries can be cached.
+
+	wire, err := query.Pack()
+	if err != nil {
+		return answer{}, fmt.Errorf("packing the query: %w", err)
+	}
+
+	var failures []error
+
+	for i, resolver := range c.resolvers {
+		// Each resolver gets an equal share of the time left, so that one
+		// that never answers leaves time for the next.
+		deadline, _ := ctx.Deadline()
+		share := time.Until(deadline) / time.Duration(len(c.resolvers)-i)
+
+		result, err := c.ask(ctx, resolver, wire, share)
+		if err == nil {
+			return result, nil
+		}
+
+		failures = append(failures, fmt.Errorf("%s: %w", resolver, err))
+	}
+
+	return answer{}, errors.Join(failures...)
+}
+
+// ask sends the query to one resolver and waits at most timeout for its answer.
+func (c *Cache) ask(
+	ctx context.Context, resolver string, query []byte, timeout time.Duration,
+) (answer, error) {
+	ctx, cancel := context.WithTimeout(ctx, timeout)
+	defer cancel()
+
+	request, err := http.NewRequestWithContext(
+		ctx, http.MethodPost, resolver, bytes.NewReader(query))
+	if err != nil {
+		return answer{}, err
+	}
+
+	request.Header.Set("Content-Type", dnsMessageType)
+	request.Header.Set("Accept", dnsMessageType)
+
+	response, err := c.client.Do(request)
+	if err != nil {
+		return answer{}, err
+	}
+
+	defer func() { _ = response.Body.Close() }()
+
+	if response.StatusCode != http.StatusOK {
+		return answer{}, fmt.Errorf("%w: %d", errBadStatus, response.StatusCode)
+	}
+
+	body, err := io.ReadAll(io.LimitReader(response.Body, maxMessageBytes))
+	if err != nil {
+		return answer{}, err
+	}
+
+	var reply dns.Msg
+
+	err = reply.Unpack(body)
+	if err != nil {
+		return answer{}, err
+	}
+
+	return answerFrom(&reply)
+}
+
+// answerFrom reads a resolver's reply. A name that does not exist and a name
+// with no PTR records are answers. Every other response code is a failure.
+func answerFrom(reply *dns.Msg) (answer, error) {
+	if reply.Rcode != dns.RcodeSuccess && reply.Rcode != dns.RcodeNameError {
+		return answer{}, fmt.Errorf("%w: %s",
+			errBadResponse, dns.RcodeToString[reply.Rcode])
+	}
+
+	var names []string
+
+	seconds := uint32(math.MaxUint32)
+
+	for _, record := range reply.Answer {
+		// The chain to a PTR record can hold CNAME records, and the answer
+		// is good only as long as every record in it.
+		seconds = min(seconds, record.Header().Ttl)
+
+		ptr, ok := record.(*dns.PTR)
+		if ok && isHostName(ptr.Ptr) {
+			names = append(names, ptr.Ptr)
+		}
+	}
+
+	if len(names) == 0 {
+		return answer{ttl: negativeTTL(reply.Ns)}, nil
+	}
+
+	ttl := time.Duration(seconds) * time.Second
+
+	return answer{names: names, ttl: min(max(ttl, minTTL), maxTTL)}, nil
+}
+
+// negativeTTL returns how long a reply with no PTR names may be kept: the
+// smaller of the SOA record's own TTL and its minimum field (RFC 2308), at most
+// maxNegativeTTL. Without a SOA record it is zero.
+func negativeTTL(authority []dns.RR) time.Duration {
+	for _, record := range authority {
+		soa, ok := record.(*dns.SOA)
+		if ok {
+			ttl := time.Duration(min(soa.Hdr.Ttl, soa.Minttl)) * time.Second
+
+			return min(ttl, maxNegativeTTL)
+		}
+	}
+
+	return 0
+}
+
+// isHostName reports whether name is a host name. A PTR record can hold any
+// bytes, and the names go into web pages, so anything else is dropped, as
+// net.Resolver.LookupAddr drops it. The root name is not a host name.
+func isHostName(name string) bool {
+	_, ok := dns.IsDomainName(name)
+
+	return ok && name != "." && !strings.ContainsFunc(name, notInHostName)
+}
+
+// notInHostName reports whether r cannot be part of a host name.
+func notInHostName(r rune) bool {
+	return !strings.ContainsRune(hostNameCharacters, r)
+}
+
+// hostNameCharacters are the characters of a host name, in presentation format.
+const hostNameCharacters = "abcdefghijklmnopqrstuvwxyz" +
+	"ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_."