includes/debug/logger/monolog/AvroFormatter.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 namespace MediaWiki\Logger\Monolog;
  22
  23 use AvroIODatumWriter;
  24 use AvroIOBinaryEncoder;
  25 use AvroIOTypeException;
  26 use AvroNamedSchemata;
  27 use AvroSchema;
  28 use AvroStringIO;
  29 use AvroValidator;
  30 use Monolog\Formatter\FormatterInterface;
  31
  32 /**
  33  * Log message formatter that uses the apache Avro format.
  34  *
  35  * @since 1.26
  36  * @author Erik Bernhardson <ebernhardson@wikimedia.org>
  37  * @copyright © 2015 Erik Bernhardson and Wikimedia Foundation.
  38  */
  39 class AvroFormatter implements FormatterInterface {
  40         /**
  41          * @var Magic byte to encode schema revision id.
  42          */
  43         const MAGIC = 0x0;
  44         /**
  45          * @var array Map from schema name to schema definition
  46          */
  47         protected $schemas;
  48
  49         /**
  50          * @var AvroStringIO
  51          */
  52         protected $io;
  53
  54         /**
  55          * @var AvroIOBinaryEncoder
  56          */
  57         protected $encoder;
  58
  59         /**
  60          * @var AvroIODatumWriter
  61          */
  62         protected $writer;
  63
  64         /**
  65          * @var array $schemas Map from Monolog channel to Avro schema.
  66          *  Each schema can be either the JSON string or decoded into PHP
  67          *  arrays.
  68          */
  69         public function __construct( array $schemas ) {
  70                 $this->schemas = $schemas;
  71                 $this->io = new AvroStringIO( '' );
  72                 $this->encoder = new AvroIOBinaryEncoder( $this->io );
  73                 $this->writer = new AvroIODatumWriter();
  74         }
  75
  76         /**
  77          * Formats the record context into a binary string per the
  78          * schema configured for the records channel.
  79          *
  80          * @param array $record
  81          * @return string|null The serialized record, or null if
  82          *  the record is not valid for the selected schema.
  83          */
  84         public function format( array $record ) {
  85                 $this->io->truncate();
  86                 $schema = $this->getSchema( $record['channel'] );
  87                 $revId = $this->getSchemaRevisionId( $record['channel'] );
  88                 if ( $schema === null || $revId === null ) {
  89                         trigger_error( "The schema for channel '{$record['channel']}' is not available" );
  90                         return null;
  91                 }
  92                 try {
  93                         $this->writer->write_data( $schema, $record['context'], $this->encoder );
  94                 } catch ( AvroIOTypeException $e ) {
  95                         $errors = AvroValidator::getErrors( $schema, $record['context'] );
  96                         $json = json_encode( $errors );
  97                         trigger_error( "Avro failed to serialize record for {$record['channel']} : {$json}" );
  98                         return null;
  99                 }
 100                 return chr( self::MAGIC ) . $this->encodeLong( $revId ) . $this->io->string();
 101         }
 102
 103         /**
 104          * Format a set of records into a list of binary strings
 105          * conforming to the configured schema.
 106          *
 107          * @param array $records
 108          * @return string[]
 109          */
 110         public function formatBatch( array $records ) {
 111                 $result = [];
 112                 foreach ( $records as $record ) {
 113                         $message = $this->format( $record );
 114                         if ( $message !== null ) {
 115                                 $result[] = $message;
 116                         }
 117                 }
 118                 return $result;
 119         }
 120
 121         /**
 122          * Get the writer for the named channel
 123          *
 124          * @var string $channel Name of the schema to fetch
 125          * @return \AvroSchema|null
 126          */
 127         protected function getSchema( $channel ) {
 128                 if ( !isset( $this->schemas[$channel] ) ) {
 129                         return null;
 130                 }
 131                 if ( !isset( $this->schemas[$channel]['revision'], $this->schemas[$channel]['schema'] ) ) {
 132                         return null;
 133                 }
 134
 135                 if ( !$this->schemas[$channel]['schema'] instanceof AvroSchema ) {
 136                         $schema = $this->schemas[$channel]['schema'];
 137                         if ( is_string( $schema ) ) {
 138                                 $this->schemas[$channel]['schema'] = AvroSchema::parse( $schema );
 139                         } else {
 140                                 $this->schemas[$channel]['schema'] = AvroSchema::real_parse(
 141                                         $schema,
 142                                         null,
 143                                         new AvroNamedSchemata()
 144                                 );
 145                         }
 146                 }
 147                 return $this->schemas[$channel]['schema'];
 148         }
 149
 150         /**
 151          * Get the writer for the named channel
 152          *
 153          * @var string $channel Name of the schema
 154          * @return int|null
 155          */
 156         public function getSchemaRevisionId( $channel ) {
 157                 if ( isset( $this->schemas[$channel]['revision'] ) ) {
 158                         return (int)$this->schemas[$channel]['revision'];
 159                 }
 160                 return null;
 161         }
 162
 163         /**
 164          * convert an integer to a 64bits big endian long (Java compatible)
 165          * NOTE: certainly only compatible with PHP 64bits
 166          * @param int $id
 167          * @return string the binary representation of $id
 168          */
 169         private function encodeLong( $id ) {
 170                 $high   = ( $id & 0xffffffff00000000 ) >> 32;
 171                 $low    = $id & 0x00000000ffffffff;
 172                 return pack( 'NN', $high, $low );
 173         }
 174 }