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.
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.
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
21 namespace MediaWiki\Logger\Monolog
;
23 use AvroIODatumWriter
;
24 use AvroIOBinaryEncoder
;
25 use AvroIOTypeException
;
29 use Monolog\Formatter\FormatterInterface
;
32 * Log message formatter that uses the apache Avro format.
35 * @author Erik Bernhardson <ebernhardson@wikimedia.org>
36 * @copyright © 2015 Erik Bernhardson and Wikimedia Foundation.
38 class AvroFormatter
implements FormatterInterface
{
40 * @var Magic byte to encode schema revision id.
44 * @var array Map from schema name to schema definition
54 * @var AvroIOBinaryEncoder
59 * @var AvroIODatumWriter
64 * @param array $schemas Map from Monolog channel to Avro schema.
65 * Each schema can be either the JSON string or decoded into PHP
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();
76 * Formats the record context into a binary string per the
77 * schema configured for the records channel.
79 * @param array $record
80 * @return string|null The serialized record, or null if
81 * the record is not valid for the selected schema.
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" );
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}" );
99 return chr( self
::MAGIC
) . $this->encodeLong( $revId ) . $this->io
->string();
103 * Format a set of records into a list of binary strings
104 * conforming to the configured schema.
106 * @param array $records
109 public function formatBatch( array $records ) {
111 foreach ( $records as $record ) {
112 $message = $this->format( $record );
113 if ( $message !== null ) {
114 $result[] = $message;
121 * Get the writer for the named channel
123 * @param string $channel Name of the schema to fetch
124 * @return \AvroSchema|null
126 protected function getSchema( $channel ) {
127 if ( !isset( $this->schemas
[$channel] ) ) {
130 if ( !isset( $this->schemas
[$channel]['revision'], $this->schemas
[$channel]['schema'] ) ) {
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 );
139 $this->schemas
[$channel]['schema'] = AvroSchema
::real_parse(
144 return $this->schemas
[$channel]['schema'];
148 * Get the writer for the named channel
150 * @param string $channel Name of the schema
153 public function getSchemaRevisionId( $channel ) {
154 if ( isset( $this->schemas
[$channel]['revision'] ) ) {
155 return (int)$this->schemas
[$channel]['revision'];
161 * convert an integer to a 64bits big endian long (Java compatible)
162 * NOTE: certainly only compatible with PHP 64bits
164 * @return string the binary representation of $id
166 private function encodeLong( $id ) {
167 $high = ( $id & 0xffffffff00000000 ) >> 32;
168 $low = $id & 0x00000000ffffffff;
169 return pack( 'NN', $high, $low );