includes/utils/AvroValidator.php

   1 <?php
   2 /**
   3  * This program is free software; you can redistribute it and/or modify
   4  * it under the terms of the GNU General Public License as published by
   5  * the Free Software Foundation; either version 2 of the License, or
   6  * (at your option) any later version.
   7  *
   8  * This program is distributed in the hope that it will be useful,
   9  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  10  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  11  * GNU General Public License for more details.
  12  *
  13  * You should have received a copy of the GNU General Public License along
  14  * with this program; if not, write to the Free Software Foundation, Inc.,
  15  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  16  * http://www.gnu.org/copyleft/gpl.html
  17  *
  18  * @file
  19  */
  20
  21 /**
  22  * Generate error strings for data that doesn't match the specified
  23  * Avro schema. This is very similar to AvroSchema::is_valid_datum(),
  24  * but returns error messages instead of a boolean.
  25  *
  26  * @since 1.26
  27  * @author Erik Bernhardson <ebernhardson@wikimedia.org>
  28  * @copyright © 2015 Erik Bernhardson and Wikimedia Foundation.
  29  */
  30 class AvroValidator {
  31         /**
  32          * @param AvroSchema $schema The rules to conform to.
  33          * @param mixed $datum The value to validate against $schema.
  34          * @return string|string[] An error or list of errors in the
  35          *  provided $datum. When no errors exist the empty array is
  36          *  returned.
  37          */
  38         public static function getErrors( AvroSchema $schema, $datum ) {
  39                 switch ( $schema->type ) {
  40                 case AvroSchema::NULL_TYPE:
  41                         if ( !is_null( $datum ) ) {
  42                                 return self::wrongType( 'null', $datum );
  43                         }
  44                         return [];
  45                 case AvroSchema::BOOLEAN_TYPE:
  46                         if ( !is_bool( $datum ) ) {
  47                                 return self::wrongType( 'boolean', $datum );
  48                         }
  49                         return [];
  50                 case AvroSchema::STRING_TYPE:
  51                 case AvroSchema::BYTES_TYPE:
  52                         if ( !is_string( $datum ) ) {
  53                                 return self::wrongType( 'string', $datum );
  54                         }
  55                         return [];
  56                 case AvroSchema::INT_TYPE:
  57                         if ( !is_int( $datum ) ) {
  58                                 return self::wrongType( 'integer', $datum );
  59                         }
  60                         if ( AvroSchema::INT_MIN_VALUE > $datum
  61                                 || $datum > AvroSchema::INT_MAX_VALUE
  62                         ) {
  63                                 return self::outOfRange(
  64                                         AvroSchema::INT_MIN_VALUE,
  65                                         AvroSchema::INT_MAX_VALUE,
  66                                         $datum
  67                                 );
  68                         }
  69                         return [];
  70                 case AvroSchema::LONG_TYPE:
  71                         if ( !is_int( $datum ) ) {
  72                                 return self::wrongType( 'integer', $datum );
  73                         }
  74                         if ( AvroSchema::LONG_MIN_VALUE > $datum
  75                                 || $datum > AvroSchema::LONG_MAX_VALUE
  76                         ) {
  77                                 return self::outOfRange(
  78                                         AvroSchema::LONG_MIN_VALUE,
  79                                         AvroSchema::LONG_MAX_VALUE,
  80                                         $datum
  81                                 );
  82                         }
  83                         return [];
  84                 case AvroSchema::FLOAT_TYPE:
  85                 case AvroSchema::DOUBLE_TYPE:
  86                         if ( !is_float( $datum ) && !is_int( $datum ) ) {
  87                                 return self::wrongType( 'float or integer', $datum );
  88                         }
  89                         return [];
  90                 case AvroSchema::ARRAY_SCHEMA:
  91                         if ( !is_array( $datum ) ) {
  92                                 return self::wrongType( 'array', $datum );
  93                         }
  94                         $errors = [];
  95                         foreach ( $datum as $d ) {
  96                                 $result = self::getErrors( $schema->items(), $d );
  97                                 if ( $result ) {
  98                                         $errors[] = $result;
  99                                 }
 100                         }
 101                         return $errors;
 102                 case AvroSchema::MAP_SCHEMA:
 103                         if ( !is_array( $datum ) ) {
 104                                 return self::wrongType( 'array', $datum );
 105                         }
 106                         $errors = [];
 107                         foreach ( $datum as $k => $v ) {
 108                                 if ( !is_string( $k ) ) {
 109                                         $errors[] = self::wrongType( 'string key', $k );
 110                                 }
 111                                 $result = self::getErrors( $schema->values(), $v );
 112                                 if ( $result ) {
 113                                         $errors[$k] = $result;
 114                                 }
 115                         }
 116                         return $errors;
 117                 case AvroSchema::UNION_SCHEMA:
 118                         $errors = [];
 119                         foreach ( $schema->schemas() as $schema ) {
 120                                 $result = self::getErrors( $schema, $datum );
 121                                 if ( !$result ) {
 122                                         return [];
 123                                 }
 124                                 $errors[] = $result;
 125                         }
 126                         if ( $errors ) {
 127                                 return [ "Expected any one of these to be true", $errors ];
 128                         }
 129                         return "No schemas provided to union";
 130                 case AvroSchema::ENUM_SCHEMA:
 131                         if ( !in_array( $datum, $schema->symbols() ) ) {
 132                                 $symbols = implode( ', ', $schema->symbols );
 133                                 return "Expected one of $symbols but recieved $datum";
 134                         }
 135                         return [];
 136                 case AvroSchema::FIXED_SCHEMA:
 137                         if ( !is_string( $datum ) ) {
 138                                 return self::wrongType( 'string', $datum );
 139                         }
 140                         $len = strlen( $datum );
 141                         if ( $len !== $schema->size() ) {
 142                                 return "Expected string of length {$schema->size()}, "
 143                                         . "but recieved one of length $len";
 144                         }
 145                         return [];
 146                 case AvroSchema::RECORD_SCHEMA:
 147                 case AvroSchema::ERROR_SCHEMA:
 148                 case AvroSchema::REQUEST_SCHEMA:
 149                         if ( !is_array( $datum ) ) {
 150                                 return self::wrongType( 'array', $datum );
 151                         }
 152                         $errors = [];
 153                         foreach ( $schema->fields() as $field ) {
 154                                 $name = $field->name();
 155                                 if ( !array_key_exists( $name, $datum ) ) {
 156                                         $errors[$name] = 'Missing expected field';
 157                                         continue;
 158                                 }
 159                                 $result = self::getErrors( $field->type(), $datum[$name] );
 160                                 if ( $result ) {
 161                                         $errors[$name] = $result;
 162                                 }
 163                         }
 164                         return $errors;
 165                 default:
 166                         return "Unknown avro schema type: {$schema->type}";
 167                 }
 168         }
 169
 170         public static function typeOf( $datum ) {
 171                 return is_object( $datum ) ? get_class( $datum ) : gettype( $datum );
 172         }
 173
 174         public static function wrongType( $expected, $datum ) {
 175                 return "Expected $expected, but recieved " . self::typeOf( $datum );
 176         }
 177
 178         public static function outOfRange( $min, $max, $datum ) {
 179                 return "Expected value between $min and $max, but recieved $datum";
 180         }
 181 }