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 array Map from schema name to schema definition
  42          */
  43         protected $schemas;
  44
  45         /**
  46          * @var AvroStringIO
  47          */
  48         protected $io;
  49
  50         /**
  51          * @var AvroIOBinaryEncoder
  52          */
  53         protected $encoder;
  54
  55         /**
  56          * @var AvroIODatumWriter
  57          */
  58         protected $writer;
  59
  60         /**
  61          * @var array $schemas Map from Monolog channel to Avro schema.
  62          *  Each schema can be either the JSON string or decoded into PHP
  63          *  arrays.
  64          */
  65         public function __construct( array $schemas ) {
  66                 $this->schemas = $schemas;
  67                 $this->io = new AvroStringIO( '' );
  68                 $this->encoder = new AvroIOBinaryEncoder( $this->io );
  69                 $this->writer = new AvroIODatumWriter();
  70         }
  71
  72         /**
  73          * Formats the record context into a binary string per the
  74          * schema configured for the records channel.
  75          *
  76          * @param array $record
  77          * @return string|null The serialized record, or null if
  78          *  the record is not valid for the selected schema.
  79          */
  80         public function format( array $record ) {
  81                 $this->io->truncate();
  82                 $schema = $this->getSchema( $record['channel'] );
  83                 if ( $schema === null ) {
  84                         trigger_error( "The schema for channel '{$record['channel']}' is not available" );
  85                         return null;
  86                 }
  87                 try {
  88                         $this->writer->write_data( $schema, $record['context'], $this->encoder );
  89                 } catch ( AvroIOTypeException $e ) {
  90                         $errors = AvroValidator::getErrors( $schema, $record['context'] );
  91                         $json = json_encode( $errors );
  92                         trigger_error( "Avro failed to serialize record for {$record['channel']} : {$json}" );
  93                         return null;
  94                 }
  95                 return $this->io->string();
  96         }
  97
  98         /**
  99          * Format a set of records into a list of binary strings
 100          * conforming to the configured schema.
 101          *
 102          * @param array $records
 103          * @return string[]
 104          */
 105         public function formatBatch( array $records ) {
 106                 $result = array();
 107                 foreach ( $records as $record ) {
 108                         $message = $this->format( $record );
 109                         if ( $message !== null ) {
 110                                 $result[] = $message;
 111                         }
 112                 }
 113                 return $result;
 114         }
 115
 116         /**
 117          * Get the writer for the named channel
 118          *
 119          * @var string $channel Name of the schema to fetch
 120          * @return \\AvroSchema|null
 121          */
 122         protected function getSchema( $channel ) {
 123                 if ( !isset( $this->schemas[$channel] ) ) {
 124                         return null;
 125                 }
 126                 if ( !$this->schemas[$channel] instanceof AvroSchema ) {
 127                         if ( is_string( $this->schemas[$channel] ) ) {
 128                                 $this->schemas[$channel] = AvroSchema::parse( $this->schemas[$channel] );
 129                         } else {
 130                                 $this->schemas[$channel] = AvroSchema::real_parse(
 131                                         $this->schemas[$channel],
 132                                         null,
 133                                         new AvroNamedSchemata()
 134                                 );
 135                         }
 136                 }
 137                 return $this->schemas[$channel];
 138         }
 139 }