ext/soap: Improve SOAP scalar decoding error messages

NEWS

@@ -80,6 +80,8 @@ PHP                                                                        NEWS
     do_request() parameters). (David Carlier)
   . Fixed xsd:hexBinary decoding to reject odd-length values instead of
     silently truncating the last nibble. (Weilin Du)
+  . Made SOAP scalar decoding errors report the affected type instead of the
+    generic "Violation of encoding rules" message. (Weilin Du)
 
 - Standard:
   . Fixed sleep() and usleep() to reject values that overflow the underlying

UPGRADING

@@ -147,6 +147,10 @@ PHP 8.6 UPGRADE NOTES
   . WSDL/XML Schema parsing now rejects out-of-range integer values for
     occurrence constraints and integer restriction facets. Negative minOccurs
     and maxOccurs values are rejected as well.
+  . Scalar decoding errors now report the affected type and specific
+    validation failure in SoapFault::faultstring instead of the generic
+    "Encoding: Violation of encoding rules" message. Code that compares the
+    exact fault string may need to be updated.
 
 - Sodium:
   . The password-hashing functions sodium_crypto_pwhash(),

ext/soap/php_encoding.c

@@ -82,6 +82,26 @@ static xmlNodePtr to_xml_any(encodeTypePtr type, zval *data, int style, xmlNodeP
 static zval *guess_zval_convert(zval *ret, encodeTypePtr type, xmlNodePtr data);
 static xmlNodePtr guess_xml_convert(encodeTypePtr type, zval *data, int style, xmlNodePtr parent);
 
+static zend_always_inline const char *soap_type_name(encodeTypePtr type)
+{
+	return (type && type->type_str) ? type->type_str : "unknown";
+}
+
+static zend_always_inline void soap_encoding_error_invalid_node(encodeTypePtr type)
+{
+	soap_error1(E_ERROR, "Encoding: Type '%s' value must contain a single text or CDATA node", soap_type_name(type));
+}
+
+static zend_always_inline void soap_encoding_error_invalid_value(encodeTypePtr type)
+{
+	soap_error1(E_ERROR, "Encoding: Invalid value for type '%s'", soap_type_name(type));
+}
+
+static zend_always_inline void soap_encoding_error_invalid_hex_length(encodeTypePtr type)
+{
+	soap_error1(E_ERROR, "Encoding: Type '%s' value must contain an even number of hexadecimal digits", soap_type_name(type));
+}
+
 static encodePtr get_array_type(xmlNodePtr node, zval *array, smart_str *out_type);
 
 static xmlNodePtr check_and_resolve_href(xmlNodePtr data);
@@ -660,7 +680,7 @@ static zval *to_zval_string(zval *ret, encodeTypePtr type, xmlNodePtr data)
 		} else if (data->children->type == XML_CDATA_SECTION_NODE && data->children->next == NULL) {
 			ZVAL_STRING(ret, (char*)data->children->content);
 		} else {
-			soap_error0(E_ERROR, "Encoding: Violation of encoding rules");
+			soap_encoding_error_invalid_node(type);
 		}
 	} else {
 		ZVAL_EMPTY_STRING(ret);
@@ -693,7 +713,7 @@ static zval *to_zval_stringr(zval *ret, encodeTypePtr type, xmlNodePtr data)
 		} else if (data->children->type == XML_CDATA_SECTION_NODE && data->children->next == NULL) {
 			ZVAL_STRING(ret, (char*)data->children->content);
 		} else {
-			soap_error0(E_ERROR, "Encoding: Violation of encoding rules");
+			soap_encoding_error_invalid_node(type);
 		}
 	} else {
 		ZVAL_EMPTY_STRING(ret);
@@ -726,7 +746,7 @@ static zval *to_zval_stringc(zval *ret, encodeTypePtr type, xmlNodePtr data)
 		} else if (data->children->type == XML_CDATA_SECTION_NODE && data->children->next == NULL) {
 			ZVAL_STRING(ret, (char*)data->children->content);
 		} else {
-			soap_error0(E_ERROR, "Encoding: Violation of encoding rules");
+			soap_encoding_error_invalid_node(type);
 		}
 	} else {
 		ZVAL_EMPTY_STRING(ret);
@@ -755,7 +775,7 @@ static zval *to_zval_base64(zval *ret, encodeTypePtr type, xmlNodePtr data)
 			}
 			ZVAL_STR(ret, str);
 		} else {
-			soap_error0(E_ERROR, "Encoding: Violation of encoding rules");
+			soap_encoding_error_invalid_node(type);
 		}
 	} else {
 		ZVAL_EMPTY_STRING(ret);
@@ -776,12 +796,12 @@ static zval *to_zval_hexbin(zval *ret, encodeTypePtr type, xmlNodePtr data)
 		if (data->children->type == XML_TEXT_NODE && data->children->next == NULL) {
 			whiteSpace_collapse(data->children->content);
 		} else if (data->children->type != XML_CDATA_SECTION_NODE || data->children->next != NULL) {
-			soap_error0(E_ERROR, "Encoding: Violation of encoding rules");
+			soap_encoding_error_invalid_node(type);
 			return ret;
 		}
 		content_len = strlen((char*) data->children->content);
 		if (content_len % 2 != 0) {
-			soap_error0(E_ERROR, "Encoding: Violation of encoding rules");
+			soap_encoding_error_invalid_hex_length(type);
 			return ret;
 		}
 		str = zend_string_alloc(content_len / 2, 0);
@@ -794,7 +814,7 @@ static zval *to_zval_hexbin(zval *ret, encodeTypePtr type, xmlNodePtr data)
 			} else if (c >= 'A' && c <= 'F') {
 				ZSTR_VAL(str)[i] = (c - 'A' + 10) << 4;
 			} else {
-				soap_error0(E_ERROR, "Encoding: Violation of encoding rules");
+				soap_encoding_error_invalid_value(type);
 			}
 			c = data->children->content[j++];
 			if (c >= '0' && c <= '9') {
@@ -804,7 +824,7 @@ static zval *to_zval_hexbin(zval *ret, encodeTypePtr type, xmlNodePtr data)
 			} else if (c >= 'A' && c <= 'F') {
 				ZSTR_VAL(str)[i] |= c - 'A' + 10;
 			} else {
-				soap_error0(E_ERROR, "Encoding: Violation of encoding rules");
+				soap_encoding_error_invalid_value(type);
 			}
 		}
 		ZSTR_VAL(str)[ZSTR_LEN(str)] = '\0';
@@ -1025,11 +1045,11 @@ static zval *to_zval_double(zval *ret, encodeTypePtr type, xmlNodePtr data)
 					} else if (strncasecmp((char*)data->children->content, "-INF", sizeof("-INF")-1) == 0) {
 						ZVAL_DOUBLE(ret, -php_get_inf());
 					} else {
-						soap_error0(E_ERROR, "Encoding: Violation of encoding rules");
+						soap_encoding_error_invalid_value(type);
 					}
 			}
 		} else {
-			soap_error0(E_ERROR, "Encoding: Violation of encoding rules");
+			soap_encoding_error_invalid_node(type);
 		}
 	} else {
 		ZVAL_NULL(ret);
@@ -1058,10 +1078,10 @@ static zval *to_zval_long(zval *ret, encodeTypePtr type, xmlNodePtr data)
 					ZVAL_DOUBLE(ret, dval);
 					break;
 				default:
-					soap_error0(E_ERROR, "Encoding: Violation of encoding rules");
+					soap_encoding_error_invalid_value(type);
 			}
 		} else {
-			soap_error0(E_ERROR, "Encoding: Violation of encoding rules");
+			soap_encoding_error_invalid_node(type);
 		}
 	} else {
 		ZVAL_NULL(ret);
@@ -1127,7 +1147,7 @@ static zval *to_zval_bool(zval *ret, encodeTypePtr type, xmlNodePtr data)
 	}
 	if (data->children->type != XML_TEXT_NODE || data->children->next != NULL) {
 		// TODO Convert to exception?
-		soap_error0(E_ERROR, "Encoding: Violation of encoding rules");
+		soap_encoding_error_invalid_node(type);
 	}
 
 	whiteSpace_collapse(data->children->content);

ext/soap/tests/bugs/bug39832.phpt

@@ -26,4 +26,4 @@ $x->handle($HTTP_RAW_POST_DATA);
 ?>
 --EXPECT--
 <?xml version="1.0" encoding="UTF-8"?>
-<SOAP-ENV:Envelope xmlns:SOAP-ENV="http://schemas.xmlsoap.org/soap/envelope/"><SOAP-ENV:Body><SOAP-ENV:Fault><faultcode>SOAP-ENV:Server</faultcode><faultstring>SOAP-ERROR: Encoding: Violation of encoding rules</faultstring></SOAP-ENV:Fault></SOAP-ENV:Body></SOAP-ENV:Envelope>
+<SOAP-ENV:Envelope xmlns:SOAP-ENV="http://schemas.xmlsoap.org/soap/envelope/"><SOAP-ENV:Body><SOAP-ENV:Fault><faultcode>SOAP-ENV:Server</faultcode><faultstring>SOAP-ERROR: Encoding: Invalid value for type 'integer'</faultstring></SOAP-ENV:Fault></SOAP-ENV:Body></SOAP-ENV:Envelope>

ext/soap/tests/hexbin_odd_length.phpt

@@ -34,4 +34,4 @@ try {
 }
 ?>
 --EXPECT--
-SOAP-ERROR: Encoding: Violation of encoding rules
+SOAP-ERROR: Encoding: Type 'hexBinary' value must contain an even number of hexadecimal digits

ext/soap/tests/scalar_error_messages.phpt

@@ -0,0 +1,50 @@
+--TEST--
+SOAP reports specific scalar encoding errors
+--EXTENSIONS--
+soap
+--FILE--
+<?php
+class ScalarErrorClient extends SoapClient {
+    public string $response;
+
+    public function __doRequest($request, $location, $action, $version, $one_way = false, ?string $uriParserClass = null): string {
+        return $this->response;
+    }
+}
+
+function soap_response(string $type, string $value): string {
+    return <<<XML
+<?xml version="1.0" encoding="UTF-8"?>
+<SOAP-ENV:Envelope xmlns:SOAP-ENV="http://schemas.xmlsoap.org/soap/envelope/"
+                   xmlns:xsd="http://www.w3.org/2001/XMLSchema"
+                   xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
+  <SOAP-ENV:Body>
+    <ns1:testResponse xmlns:ns1="urn:test">
+      <return xsi:type="$type">$value</return>
+    </ns1:testResponse>
+  </SOAP-ENV:Body>
+</SOAP-ENV:Envelope>
+XML;
+}
+
+function run_case(string $label, string $type, string $value): void {
+    $client = new ScalarErrorClient(null, [
+        'location' => 'test://',
+        'uri' => 'urn:test',
+        'exceptions' => true,
+    ]);
+    $client->response = soap_response($type, $value);
+
+    try {
+        $client->__soapCall('test', []);
+    } catch (SoapFault $e) {
+        echo $label, ': ', $e->faultstring, "\n";
+    }
+}
+
+run_case('double', 'xsd:double', 'abc');
+run_case('long', 'xsd:long', 'abc');
+?>
+--EXPECT--
+double: SOAP-ERROR: Encoding: Invalid value for type 'double'
+long: SOAP-ERROR: Encoding: Invalid value for type 'long'

ext/soap/tests/soap12/T27.phpt

@@ -25,4 +25,4 @@ include "soap12-test.inc";
 ?>
 --EXPECT--
 <?xml version="1.0" encoding="UTF-8"?>
-<env:Envelope xmlns:env="http://www.w3.org/2003/05/soap-envelope"><env:Body><env:Fault><env:Code><env:Value>env:Receiver</env:Value></env:Code><env:Reason><env:Text xml:lang="en">SOAP-ERROR: Encoding: Violation of encoding rules</env:Text></env:Reason></env:Fault></env:Body></env:Envelope>
+<env:Envelope xmlns:env="http://www.w3.org/2003/05/soap-envelope"><env:Body><env:Fault><env:Code><env:Value>env:Receiver</env:Value></env:Code><env:Reason><env:Text xml:lang="en">SOAP-ERROR: Encoding: Type 'string' value must contain a single text or CDATA node</env:Text></env:Reason></env:Fault></env:Body></env:Envelope>

ext/soap/tests/soap12/T58.phpt

@@ -24,4 +24,4 @@ include "soap12-test.inc";
 ?>
 --EXPECT--
 <?xml version="1.0" encoding="UTF-8"?>
-<env:Envelope xmlns:env="http://www.w3.org/2003/05/soap-envelope"><env:Body><env:Fault><env:Code><env:Value>env:Receiver</env:Value></env:Code><env:Reason><env:Text xml:lang="en">SOAP-ERROR: Encoding: Violation of encoding rules</env:Text></env:Reason></env:Fault></env:Body></env:Envelope>
+<env:Envelope xmlns:env="http://www.w3.org/2003/05/soap-envelope"><env:Body><env:Fault><env:Code><env:Value>env:Receiver</env:Value></env:Code><env:Reason><env:Text xml:lang="en">SOAP-ERROR: Encoding: Type 'int' value must contain a single text or CDATA node</env:Text></env:Reason></env:Fault></env:Body></env:Envelope>