Code Coverage |
||||||||||
Classes and Traits |
Functions and Methods |
Lines |
||||||||
| Total | |
0.00% |
0 / 1 |
|
0.00% |
0 / 7 |
CRAP | |
0.00% |
0 / 88 |
| DedupReadSingleFile | |
0.00% |
0 / 1 |
|
0.00% |
0 / 7 |
462 | |
0.00% |
0 / 88 |
| __construct | |
0.00% |
0 / 1 |
2 | |
0.00% |
0 / 5 |
|||
| handle | |
0.00% |
0 / 1 |
12 | |
0.00% |
0 / 21 |
|||
| deletePrevious | |
0.00% |
0 / 1 |
6 | |
0.00% |
0 / 11 |
|||
| updatePonderation | |
0.00% |
0 / 1 |
6 | |
0.00% |
0 / 10 |
|||
| insertFile | |
0.00% |
0 / 1 |
72 | |
0.00% |
0 / 27 |
|||
| addToChunk | |
0.00% |
0 / 1 |
20 | |
0.00% |
0 / 9 |
|||
| insert | |
0.00% |
0 / 1 |
2 | |
0.00% |
0 / 5 |
|||
| 1 | <?php |
| 2 | |
| 3 | namespace Qmp\Laravel\Deduplication\Console\Commands; |
| 4 | |
| 5 | use Closure; |
| 6 | use DateTime; |
| 7 | use Illuminate\Console\Command; |
| 8 | use Illuminate\Support\Collection; |
| 9 | use Illuminate\Support\Facades\Storage; |
| 10 | use Qmp\Laravel\Deduplication\Models\{Session, SessionData}; |
| 11 | use Qmp\Laravel\ToolsLaravel\Traits\Timer; |
| 12 | use Qmp\Laravel\ToolsLaravel\FileReader\FileReader; |
| 13 | use MongoDB\BSON\UTCDateTime; |
| 14 | use MongoDB\Driver\WriteConcern; |
| 15 | |
| 16 | class DedupReadSingleFile extends Command |
| 17 | { |
| 18 | |
| 19 | use Timer; |
| 20 | |
| 21 | /** |
| 22 | * |
| 23 | */ |
| 24 | const CHUNK_SIZE = 10000; |
| 25 | |
| 26 | |
| 27 | /** |
| 28 | * The name and signature of the console command. |
| 29 | * |
| 30 | * @var string |
| 31 | */ |
| 32 | protected $signature = 'dedup:read-single-file {sessionId} |
| 33 | {--user-id= : The user id} |
| 34 | {--site-id= : The site id} |
| 35 | {--check-ponderation= : Wether to delete entries or just update ponderation} |
| 36 | {--type= : The type only for blacklists}'; |
| 37 | |
| 38 | /** |
| 39 | * The console command description. |
| 40 | * |
| 41 | * @var string |
| 42 | */ |
| 43 | protected $description = 'Read one file and instert into db'; |
| 44 | |
| 45 | /** |
| 46 | * Undocumented variable |
| 47 | * |
| 48 | * @var \Illuminate\Support\Collection |
| 49 | */ |
| 50 | protected $chunk; |
| 51 | |
| 52 | /** |
| 53 | * Undocumented variable |
| 54 | * |
| 55 | * @var \Illuminate\Contract\Filesystem\Filesystem |
| 56 | */ |
| 57 | protected $disk; |
| 58 | |
| 59 | /** The addToChunk closure |
| 60 | * |
| 61 | * @var Closure |
| 62 | */ |
| 63 | protected $addToChunk; |
| 64 | |
| 65 | /** |
| 66 | * Hash Type |
| 67 | * |
| 68 | * @var string |
| 69 | */ |
| 70 | protected $hashType; |
| 71 | |
| 72 | /** |
| 73 | * Undocumented variable |
| 74 | * |
| 75 | * @var integer |
| 76 | */ |
| 77 | protected $count = 0; |
| 78 | |
| 79 | /** |
| 80 | * Undocumented variable |
| 81 | * |
| 82 | * @var integer |
| 83 | */ |
| 84 | protected $totalCount = 0; |
| 85 | |
| 86 | /** |
| 87 | * Undocumented variable |
| 88 | * |
| 89 | * @var [type] |
| 90 | */ |
| 91 | protected $sessionConfig; |
| 92 | |
| 93 | /** |
| 94 | * The mongo hash structure |
| 95 | * |
| 96 | * @var array |
| 97 | */ |
| 98 | protected $structure = [ |
| 99 | 'hash' => null, |
| 100 | 'session_id' => null, |
| 101 | 'user_id' => 0, |
| 102 | 'site_id' => 0, |
| 103 | 'ponderation' => 0, |
| 104 | 'active' => true, |
| 105 | 'description_dedup_false' => '', |
| 106 | 'filename' => null, |
| 107 | 'updated_at' => null, |
| 108 | ]; |
| 109 | |
| 110 | /** |
| 111 | * Create a new command instance. |
| 112 | * |
| 113 | * @return void |
| 114 | */ |
| 115 | public function __construct() |
| 116 | { |
| 117 | parent::__construct(); |
| 118 | $this->disk = Storage::disk('deduplication'); |
| 119 | $this->addToChunk = Closure::fromCallable([$this, 'addToChunk']); |
| 120 | $this->chunk = collect(); |
| 121 | } |
| 122 | |
| 123 | /** |
| 124 | * Execute the console command. |
| 125 | * |
| 126 | * @return void |
| 127 | */ |
| 128 | public function handle(): void |
| 129 | { |
| 130 | $this->totalCount = 0; |
| 131 | $this->counr = 0; |
| 132 | $this->sessionConfig = Session::findOrFail($this->argument('sessionId')); |
| 133 | |
| 134 | $sessionConfig = collect($this->sessionConfig)->recursive(); |
| 135 | |
| 136 | $this->hashType = $sessionConfig->get('hashType'); |
| 137 | $this->structure['session_id'] = $this->argument('sessionId'); |
| 138 | |
| 139 | if ($type = $this->option('type')) { |
| 140 | $listInfo = $sessionConfig->get('blackLists') |
| 141 | ->where('type', $type) |
| 142 | ->first(); |
| 143 | $this->deletePrevious($listInfo); |
| 144 | $this->insertFile($listInfo, true); |
| 145 | } else { |
| 146 | $listInfo = $sessionConfig->get('sites') |
| 147 | ->where('user_id', $this->option('user-id')) |
| 148 | ->where('id', $this->option('site-id')) |
| 149 | ->first(); |
| 150 | if ($this->option('check-ponderation') === 'true') { |
| 151 | $this->updatePonderation($listInfo->get('ponderation')); |
| 152 | } else { |
| 153 | $this->deletePrevious($listInfo); |
| 154 | } |
| 155 | $this->insertFile($listInfo); |
| 156 | } |
| 157 | } |
| 158 | |
| 159 | |
| 160 | /** |
| 161 | * Undocumented function |
| 162 | * |
| 163 | * @param Collection $site |
| 164 | * @return void |
| 165 | */ |
| 166 | protected function deletePrevious(Collection $site) |
| 167 | { |
| 168 | $this->info('Check previous entries...'); |
| 169 | |
| 170 | $old = SessionData::where('session_id', $this->argument('sessionId')) |
| 171 | ->where('user_id', (int) $this->option('user-id')) |
| 172 | ->where('site_id', (int) $this->option('site-id')); |
| 173 | |
| 174 | if ($old->first()) { |
| 175 | $this->startTimer('delete'); |
| 176 | $this->info('Suppression des anciennes lignes du site ' . $site->get('name')); |
| 177 | $old->delete([ |
| 178 | "writeConcern" => new WriteConcern(0) |
| 179 | ]); |
| 180 | $this->info('Remove duration : ' . $this->getTimer('delete')); |
| 181 | } |
| 182 | } |
| 183 | |
| 184 | /** |
| 185 | * Undocumented function |
| 186 | * |
| 187 | * @param [type] $newPonderation |
| 188 | * @return void |
| 189 | */ |
| 190 | protected function updatePonderation($newPonderation) |
| 191 | { |
| 192 | $this->info('Check if ponderation has change ..'); |
| 193 | |
| 194 | $query = SessionData::where('session_id', $this->argument('sessionId')) |
| 195 | ->where('user_id', (int) $this->option('user-id')) |
| 196 | ->where('site_id', (int) $this->option('site-id')); |
| 197 | |
| 198 | $currentPonderation = $query->first()->ponderation; |
| 199 | |
| 200 | if ($currentPonderation !== $newPonderation) { |
| 201 | $this->info("Update ponderation from $currentPonderation to $newPonderation..."); |
| 202 | $query->update(['ponderation' => $newPonderation]); |
| 203 | } else { |
| 204 | $this->info('Nothing change !'); |
| 205 | } |
| 206 | } |
| 207 | |
| 208 | /** |
| 209 | * Insert file into DB |
| 210 | * |
| 211 | * @param Collection $site |
| 212 | * @param boolean $blackList |
| 213 | * @return void |
| 214 | */ |
| 215 | protected function insertFile(Collection $site, bool $blackList = false): void |
| 216 | { |
| 217 | $timerName = $site->get('name') ?? 'tmr_' . rand(0, 1000) . rand(0, 500); |
| 218 | |
| 219 | $this->totalCount = $site->dotGet('input_file.count'); |
| 220 | |
| 221 | $this->startTimer($timerName); |
| 222 | $type = $blackList ? 'blacklist' : 'editors'; |
| 223 | $this->info("Insterting $type hashs ... "); |
| 224 | |
| 225 | if ($site->get('name')) { |
| 226 | $this->info("Name :" . $site->get('user_name') . ' - Site : ' . $site->get('name')); |
| 227 | } |
| 228 | |
| 229 | if (!$blackList) { |
| 230 | $this->structure['ponderation'] = $site->get('ponderation'); |
| 231 | $this->structure['user_id'] = $site->get('user_id'); |
| 232 | $this->structure['site_id'] = $site->get('id'); |
| 233 | } |
| 234 | |
| 235 | $input_file = $site->get('input_file'); |
| 236 | |
| 237 | $this->structure['filename'] = $input_file->get('file'); |
| 238 | $this->structure['updated_at'] = new UTCDateTime(new DateTime()); |
| 239 | $reader = new FileReader($this->disk->path($input_file->get('file'))); |
| 240 | |
| 241 | if ($capping = $site->get('capping')) { |
| 242 | $this->info('Capping file to ' . $capping . " entries"); |
| 243 | $reader->randomCapping($capping, $input_file->get('count')); |
| 244 | } |
| 245 | |
| 246 | $reader->each($this->addToChunk); |
| 247 | |
| 248 | // Final insert of remaining chunks |
| 249 | $this->insert(); |
| 250 | |
| 251 | $path = $blackList ? 'blacklists.$type.input_file' : 'sites.$id.input_file'; |
| 252 | $filter = $blackList ? 'customerHashedList' : $site->get('id'); |
| 253 | |
| 254 | $this->sessionConfig->setKeyFilter($path, 'inserted', true, [$filter]); |
| 255 | |
| 256 | if ($site->get('name')) { |
| 257 | $this->info('Insert done for ' . $site->get('user_name') . ': ' . $site->get('name') . ' - ' . $this->getTimer($timerName)); |
| 258 | } else { |
| 259 | $this->info('Insert done for blacklist: ' . $this->option('type') . ' - ' . $this->getTimer($timerName)); |
| 260 | } |
| 261 | } |
| 262 | |
| 263 | /** |
| 264 | * Add hash to chunk |
| 265 | * |
| 266 | * @param string $hash |
| 267 | * @return void |
| 268 | */ |
| 269 | protected function addToChunk(string $hash): void |
| 270 | { |
| 271 | $hash = trim($hash); |
| 272 | |
| 273 | if ($hash !== "") { |
| 274 | if (filter_var($hash, FILTER_VALIDATE_EMAIL) !== false) { |
| 275 | $hash = hash($this->hashType, $hash); |
| 276 | } |
| 277 | $this->structure['hash'] = strtolower($hash); |
| 278 | |
| 279 | $this->chunk->push($this->structure); |
| 280 | |
| 281 | if ($this->chunk->count() >= self::CHUNK_SIZE) { |
| 282 | |
| 283 | $this->insert(); |
| 284 | } |
| 285 | } |
| 286 | } |
| 287 | |
| 288 | /** |
| 289 | * Insert the given chunk |
| 290 | * |
| 291 | * @return void |
| 292 | */ |
| 293 | protected function insert(): void |
| 294 | { |
| 295 | $this->count += $this->chunk->count(); |
| 296 | |
| 297 | SessionData::insert($this->chunk->toArray(), ["writeConcern" => ["w" => 0]]); |
| 298 | $this->line("Inserted : $this->count / $this->totalCount"); |
| 299 | $this->chunk = collect(); |
| 300 | } |
| 301 | } |