Name the municipality behind a CEP that does not existHEADv0.2.0main

A CEP that fails at the checkout is almost never a random number. It is
a shopper who knows perfectly well which town they live in and got a
digit wrong, most often by reaching for the -000 that 957 municipalities
never received. The API now names the municipality such a number would
have belonged to, in the body of its own 404, so the message can say
"that would be in Areal/RJ, which has CEPs from 25845-001 to 25849-899"
instead of leaving the shopper at a dead end with nothing to act on.

It stays an error. Nothing from it is written into a checkout field, on
either checkout and in either lookup mode: a CEP that does not exist has
no address, and filling one in from the municipality behind it means a
parcel delivered to the wrong town and a chargeback behind that. The one
module that reads the 404 body hands its callers a finished sentence and
never the data itself, so there is no shape in which it could leak into
a field later. The two CEPs quoted are the lowest and the highest that
really exist there, never a list and never a suggestion, because the
range is sparse enough that a number out of the middle of it would most
likely not exist either.

The widget correctly throws its 404 away without reading it, so the body
is fetched once more, on the miss path only and once per CEP. In proxy
mode PHP passes the municipality through with the 404 and caches it with
the miss, which is what keeps the two modes indistinguishable from the
browser. Anything missing or misshapen falls back to the message the
plugin has always shown.

1 files changed, 120 insertions, 15 deletions

diff --git a/includes/class-cepis-woo-lookup.php b/includes/class-cepis-woo-lookup.php
index 47e3f16..da2f25a 100644
--- a/includes/class-cepis-woo-lookup.php
+++ b/includes/class-cepis-woo-lookup.php
@@ -43,6 +43,32 @@ final class Cepis_Woo_Lookup {
 	private const MISS_TTL = DAY_IN_SECONDS;
 
 	/**
+	 * The fields of a 404's `faixa` object that are passed on.
+	 *
+	 * A whitelist rather than the whole object, so that a field the API grows
+	 * later cannot reach the checkout unreviewed. None of these is ever written
+	 * into a checkout field — see {@see Cepis_Woo_Lookup::faixa()}.
+	 */
+	private const FAIXA_FIELDS = array(
+		'localidade',
+		'uf',
+		'estado',
+		'regiao',
+		'ibge',
+		'cep_ini',
+		'cep_fim',
+		'ceps',
+	);
+
+	/**
+	 * The transport the client speaks through, kept so that the body of a 404
+	 * can be read back after the client has turned it into an exception.
+	 *
+	 * @var Cepis_Woo_Transport|null
+	 */
+	private static ?Cepis_Woo_Transport $transport = null;
+
+	/**
 	 * Look a CEP up, from cache when possible.
 	 *
 	 * Never throws: every outcome is described by the returned status and body,
@@ -57,21 +83,32 @@ final class Cepis_Woo_Lookup {
 		$cached = get_transient( self::CACHE_PREFIX . $cep );
 
 		if ( is_array( $cached ) ) {
-			return isset( $cached['miss'] )
-				? self::not_found()
-				: array(
-					'status'      => 200,
-					'body'        => $cached,
-					'retry_after' => null,
-				);
+			if ( isset( $cached['miss'] ) ) {
+				$remembered = isset( $cached['faixa'] ) && is_array( $cached['faixa'] ) ? $cached['faixa'] : null;
+
+				return self::not_found( $remembered );
+			}
+
+			return array(
+				'status'      => 200,
+				'body'        => $cached,
+				'retry_after' => null,
+			);
 		}
 
 		try {
 			$address = self::client()->lookup( $cep );
 		} catch ( Cepis\CepNotFoundException ) {
-			set_transient( self::CACHE_PREFIX . $cep, array( 'miss' => true ), self::MISS_TTL );
+			$faixa = self::faixa( self::transport()->last_body() );
+			$miss  = array( 'miss' => true );
+
+			if ( null !== $faixa ) {
+				$miss['faixa'] = $faixa;
+			}
+
+			set_transient( self::CACHE_PREFIX . $cep, $miss, self::MISS_TTL );
 
-			return self::not_found();
+			return self::not_found( $faixa );
 		} catch ( Cepis\InvalidCepException ) {
 			return array(
 				'status'      => 400,
@@ -144,7 +181,7 @@ final class Cepis_Woo_Lookup {
 				maxAttempts: 2,
 				totalTimeout: 8.0,
 				userAgent: 'cepis-woocommerce/' . CEPIS_WOO_VERSION . ' (+https://cep.is)',
-				transport: new Cepis_Woo_Transport(),
+				transport: self::transport(),
 			);
 		}
 
@@ -152,18 +189,86 @@ final class Cepis_Woo_Lookup {
 	}
 
 	/**
+	 * The transport, built once per request.
+	 */
+	private static function transport(): Cepis_Woo_Transport {
+		if ( null === self::$transport ) {
+			self::$transport = new Cepis_Woo_Transport();
+		}
+
+		return self::$transport;
+	}
+
+	/**
+	 * The municipality a missing CEP would have belonged to, out of the API's
+	 * 404 body.
+	 *
+	 * **This is context, not an address.** A CEP that does not exist has no
+	 * address, and nothing here may ever reach a checkout field: a shipping
+	 * address filled from a CEP the Correios do not have is a parcel delivered
+	 * somewhere else. It exists only so the shopper can be told what they most
+	 * likely mistyped — the classic case being the `-000` that 957
+	 * municipalities never received.
+	 *
+	 * Returns `null` for anything unexpected, so a body that changed shape, or
+	 * is not JSON at all, produces exactly the message this plugin has always
+	 * shown.
+	 *
+	 * @param string $body The response body, as it arrived.
+	 *
+	 * @return array<string, int|string>|null The named fields, or null.
+	 */
+	private static function faixa( string $body ): ?array {
+		if ( '' === $body ) {
+			return null;
+		}
+
+		$data = json_decode( $body, true );
+
+		if ( ! is_array( $data ) || ! isset( $data['faixa'] ) || ! is_array( $data['faixa'] ) ) {
+			return null;
+		}
+
+		$faixa = array();
+
+		foreach ( self::FAIXA_FIELDS as $name ) {
+			if ( ! isset( $data['faixa'][ $name ] ) || ! is_scalar( $data['faixa'][ $name ] ) ) {
+				continue;
+			}
+
+			$value = $data['faixa'][ $name ];
+
+			$faixa[ $name ] = is_int( $value ) ? $value : sanitize_text_field( (string) $value );
+		}
+
+		return array() === $faixa ? null : $faixa;
+	}
+
+	/**
 	 * The API's own 404 body, reproduced so the browser cannot tell the two
 	 * modes apart.
 	 *
+	 * `faixa` is **omitted** when there is none, never sent as null, which is
+	 * what the API does and what the browser is written to expect.
+	 *
+	 * @param array<string, int|string>|null $faixa The municipality the CEP
+	 *     would have belonged to, when the API named one.
+	 *
 	 * @return array{status:int, body:array<string, mixed>, retry_after:?int}
 	 */
-	private static function not_found(): array {
+	private static function not_found( ?array $faixa = null ): array {
+		$body = array(
+			'erro'     => 'cep_nao_encontrado',
+			'mensagem' => 'CEP não existe na base do DNE',
+		);
+
+		if ( null !== $faixa ) {
+			$body['faixa'] = $faixa;
+		}
+
 		return array(
 			'status'      => 404,
-			'body'        => array(
-				'erro'     => 'cep_nao_encontrado',
-				'mensagem' => 'CEP não existe na base do DNE',
-			),
+			'body'        => $body,
 			'retry_after' => null,
 		);
 	}