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 ( $schema === null ) {
  89                         trigger_error( "The schema for channel '{$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                 if ( $revId !== null ) {
 101                         return chr( self::MAGIC ) . $this->encode_long( $revId ) . $this->io->string();
 102                 }
 103                 // @todo: remove backward compat code and do not send messages without rev id.
 104                 return $this->io->string();
 105         }
 106
 107         /**
 108          * Format a set of records into a list of binary strings
 109          * conforming to the configured schema.
 110          *
 111          * @param array $records
 112          * @return string[]
 113          */
 114         public function formatBatch( array $records ) {
 115                 $result = array();
 116                 foreach ( $records as $record ) {
 117                         $message = $this->format( $record );
 118                         if ( $message !== null ) {
 119                                 $result[] = $message;
 120                         }
 121                 }
 122                 return $result;
 123         }
 124
 125         /**
 126          * Get the writer for the named channel
 127          *
 128          * @var string $channel Name of the schema to fetch
 129          * @return \AvroSchema|null
 130          */
 131         protected function getSchema( $channel ) {
 132                 if ( !isset( $this->schemas[$channel] ) ) {
 133                         return null;
 134                 }
 135                 $schemaDetails = &$this->schemas[$channel];
 136                 $schema = null;
 137                 if ( isset( $schemaDetails['revision'] ) && isset( $schemaDetails['schema'] ) ) {
 138                         $schema = &$schemaDetails['schema'];
 139                 } else {
 140                         // @todo: Remove backward compat code
 141                         $schema = &$schemaDetails;
 142                 }
 143
 144                 if ( !$schema instanceof AvroSchema ) {
 145                         if ( is_string( $schema ) ) {
 146                                 $schema = AvroSchema::parse( $schema );
 147                         } else {
 148                                 $schema = AvroSchema::real_parse(
 149                                         $this->schemas[$channel],
 150                                         null,
 151                                         new AvroNamedSchemata()
 152                                 );
 153                         }
 154                 }
 155                 return $schema;
 156         }
 157
 158         /**
 159          * Get the writer for the named channel
 160          *
 161          * @var string $channel Name of the schema
 162          * @return int|null
 163          */
 164         public function getSchemaRevisionId( $channel ) {
 165                 // @todo: remove backward compat code
 166                 if ( isset( $this->schemas[$channel] )
 167                                 && is_array( $this->schemas[$channel] )
 168                                 && isset( $this->schemas[$channel]['revision'] ) ) {
 169                         return (int) $this->schemas[$channel]['revision'];
 170                 }
 171                 return null;
 172         }
 173
 174         /**
 175          * convert an integer to a 64bits big endian long (Java compatible)
 176          * NOTE: certainly only compatible with PHP 64bits
 177          * @param int $id
 178          * @return string the binary representation of $id
 179          */
 180         private function encode_long( $id ) {
 181                 $high   = ( $id & 0xffffffff00000000 ) >> 32;
 182                 $low    = $id & 0x00000000ffffffff;
 183                 return pack( 'NN', $high, $low );
 184         }
 185 }