Take Brazilian AS details from NIC.br's WHOIS server (closes #174)

LACNIC's answer for an AS that NIC.br registers is NIC.br's answer with
each accented letter replaced by U+FFFD, so a name such as AS52751's
cannot be recovered from it. When LACNIC's answer carries NIC.br's
copyright notice, the client now also asks whois.registro.br for the AS
and takes the fields from that answer, which is Latin-1 and decoded as
before. When that query fails, when the answer has no fields, or when
NIC.br says the client is over its query limit, LACNIC's fields are kept
and a warning is logged. After an over-limit answer the client skips
NIC.br for an hour. The tests use recorded answers for AS52751.

Model: opus-5-5

internal/whois/whois.go

@@ -7,9 +7,11 @@ import (
 	"errors"
 	"fmt"
 	"io"
+	"log/slog"
 	"net"
 	"regexp"
 	"strings"
+	"sync"
 	"time"
 	"unicode/utf8"
 
@@ -49,8 +51,32 @@ const (
 	whoisServerAPNIC   = "whois.apnic.net:43"
 	whoisServerLACNIC  = "whois.lacnic.net:43"
 	whoisServerAFRINIC = "whois.afrinic.net:43"
+
+	// NIC.br registers Brazil's ASes under LACNIC.
+	whoisServerNICbr = "whois.registro.br:43"
 )
 
+// nicbrHeader starts the copyright notice at the top of NIC.br's WHOIS
+// answers. LACNIC's answer for an AS that NIC.br registers is NIC.br's, and
+// carries the same notice:
+//
+//	% Copyright (c) Nic.br - Use of this data is governed by the Use and
+//	% Privacy Policy at https://registro.br/upp . Distribution,
+const nicbrHeader = "% Copyright (c) Nic.br"
+
+// nicbrLimitReached is in the line that marks NIC.br's reduced answer to a
+// client over its query limit. NIC.br publishes no limit. Its Use and
+// Privacy Policy, https://registro.br/upp, says only that it restricts
+// queries to stop the data being taken in bulk.
+const nicbrLimitReached = "Query rate limit exceeded"
+
+// NICbrSkipTime is how long the client stops asking NIC.br after NIC.br
+// answers that the client is over its query limit. NIC.br publishes
+// neither the limit nor how long it lasts. An hour outlasts a limit
+// counted per minute or per hour. The ASes looked up meanwhile get
+// NIC.br's fields when they are next refreshed.
+const NICbrSkipTime = time.Hour
+
 // RIR identifiers.
 const (
 	RIRARIN   = "ARIN"
@@ -123,21 +149,42 @@ type Client struct {
 	// host:port. NewClient sets a net.Dialer's; tests replace it to reach
 	// local servers instead.
 	DialContext func(ctx context.Context, network, address string) (net.Conn, error)
+
+	// Now returns the current time. NewClient sets time.Now; tests replace
+	// it to move the clock.
+	Now func() time.Time
+
+	logger *slog.Logger
+
+	// mu guards nicbrSkipUntil.
+	mu sync.Mutex
+
+	// nicbrSkipUntil is when the client next asks NIC.br, after NIC.br
+	// answered that the client is over its query limit.
+	nicbrSkipUntil time.Time
 }
 
-// NewClient creates a new WHOIS client.
-func NewClient() *Client {
+// NewClient creates a new WHOIS client that logs to logger.
+func NewClient(logger *slog.Logger) *Client {
 	dialer := &net.Dialer{Timeout: dialTimeout}
 
-	return &Client{DialContext: dialer.DialContext}
+	return &Client{
+		DialContext: dialer.DialContext,
+		Now:         time.Now,
+		logger:      logger,
+	}
 }
 
 // LookupASN asks IANA which RIR holds the given ASN, asks that RIR, and
-// returns what the RIR's answer says. It returns ErrNoReferral when IANA
-// refers the AS to no RIR, and another error when a query fails, when the
-// RIR refuses it, when IANA's answer has neither a referral nor the AS's
-// block, when IANA refers the AS to a server none of the five RIRs run, or
-// when the RIR's answer carries none of ASNInfo's fields.
+// returns what the RIR's answer says. When LACNIC's answer is NIC.br's, it
+// returns what NIC.br's own server says instead, unless that query fails or
+// is skipped, as askNICbr says.
+//
+// It returns ErrNoReferral when IANA refers the AS to no RIR, and another
+// error when the query to IANA or to the RIR fails, when the RIR refuses
+// it, when IANA's answer has neither a referral nor the AS's block, when
+// IANA refers the AS to a server none of the five RIRs run, or when the
+// answer carries none of ASNInfo's fields.
 func (c *Client) LookupASN(ctx context.Context, asn int) (*ASNInfo, error) {
 	// Query IANA first to find the authoritative RIR
 	query := fmt.Sprintf("AS%d", asn)
@@ -169,18 +216,77 @@ func (c *Client) LookupASN(ctx context.Context, asn int) (*ASNInfo, error) {
 		return nil, fmt.Errorf("RIR query failed: %w", err)
 	}
 
-	// The fields come from the RIR's answer alone: IANA's describes the
-	// block the AS is in.
+	// The fields never come from IANA's answer, which describes the block
+	// the AS is in.
 	info := c.parseResponse(asn, rir, rirResp)
+
+	if rir == RIRLACNIC && strings.Contains(rirResp, nicbrHeader) {
+		info = c.askNICbr(ctx, query, info)
+	}
+
 	if info.isEmpty() {
 		return nil, fmt.Errorf("%s from %s: %w", query, whoisServer, errNoFields)
 	}
 
-	info.RawResponse = ianaResp + "\n" + rirResp
+	info.RawResponse = ianaResp + "\n" + info.RawResponse
 
 	return info, nil
 }
 
+// askNICbr asks NIC.br's server about an AS whose answer from LACNIC is
+// NIC.br's, and returns what NIC.br's answer says. LACNIC replaces each
+// accented letter in such an answer with U+FFFD. NIC.br's own server keeps
+// them, in Latin-1.
+//
+// askNICbr returns lacnicInfo, what LACNIC's answer says, and logs a
+// warning when the query fails, when NIC.br sends the reduced answer for a
+// client over its limit, or when NIC.br's answer carries none of ASNInfo's
+// fields. After the reduced answer, it returns lacnicInfo without asking
+// NIC.br until NICbrSkipTime has passed.
+func (c *Client) askNICbr(
+	ctx context.Context, asQuery string, lacnicInfo *ASNInfo,
+) *ASNInfo {
+	asn := lacnicInfo.ASN
+
+	c.mu.Lock()
+	skipping := c.Now().Before(c.nicbrSkipUntil)
+	c.mu.Unlock()
+
+	if skipping {
+		return lacnicInfo
+	}
+
+	answer, err := c.query(ctx, whoisServerNICbr, asQuery)
+	if err != nil {
+		c.logger.Warn("NIC.br query failed, keeping LACNIC's fields",
+			"asn", asn, "error", err)
+
+		return lacnicInfo
+	}
+
+	if strings.Contains(answer, nicbrLimitReached) {
+		c.mu.Lock()
+		c.nicbrSkipUntil = c.Now().Add(NICbrSkipTime)
+		c.mu.Unlock()
+
+		c.logger.Warn("NIC.br answered that the client is over its query "+
+			"limit, keeping LACNIC's fields and skipping NIC.br",
+			"asn", asn, "skip_for", NICbrSkipTime)
+
+		return lacnicInfo
+	}
+
+	info := c.parseResponse(asn, RIRLACNIC, answer)
+	if info.isEmpty() {
+		c.logger.Warn("NIC.br answered with no WHOIS fields, "+
+			"keeping LACNIC's fields", "asn", asn)
+
+		return lacnicInfo
+	}
+
+	return info
+}
+
 // isEmpty reports whether info holds none of the fields a WHOIS answer
 // fills, as when the answer is only comment and error lines.
 func (info *ASNInfo) isEmpty() bool {
@@ -276,9 +382,9 @@ func (c *Client) query(ctx context.Context, server, query string) (string, error
 }
 
 // toUTF8 returns a WHOIS answer in UTF-8. An answer that is valid UTF-8 is
-// returned as it is. Any other answer is decoded as Latin-1, which RIPE and
-// APNIC send. LACNIC, ARIN and AFRINIC send UTF-8. RIPE's database working
-// group lists the five here:
+// returned as it is. Any other answer is decoded as Latin-1, which RIPE,
+// APNIC and NIC.br send. LACNIC, ARIN and AFRINIC send UTF-8. RIPE's
+// database working group lists the five RIRs here:
 // https://www.ripe.net/ripe/mail/archives/db-wg/2024-May/008075.html
 func toUTF8(answer string) (string, error) {
 	if utf8.ValidString(answer) {