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