1
0
Fork 0
mirror of https://we.phorge.it/source/phorge.git synced 2024-11-28 17:52:43 +01:00
phorge-phorge/src/applications/files/engine/PhabricatorChunkedFileStorageEngine.php
epriestley 32d8d67535 Support resuming JS uploads of chunked files
Summary: Ref T7149. We can't compute hashes of large files efficiently, but we can resume uploads by the same author, with the same name and file size, which are only partially completed. This seems like a reasonable heuristic that is unlikely to ever misfire, even if it's a little magical.

Test Plan:
  - Forced chunking on.
  - Started uploading a chunked file.
  - Closed the browser window.
  - Dropped it into a new window.
  - Upload resumed //(!!!)//
  - Did this again.
  - Downloaded the final file, which successfully reconstructed the original file.

Reviewers: btrahan

Reviewed By: btrahan

Subscribers: joshuaspence, chad, epriestley

Maniphest Tasks: T7149

Differential Revision: https://secure.phabricator.com/D12070
2015-03-14 08:28:46 -07:00

180 lines
4.7 KiB
PHP

<?php
final class PhabricatorChunkedFileStorageEngine
extends PhabricatorFileStorageEngine {
public function getEngineIdentifier() {
return 'chunks';
}
public function getEnginePriority() {
return 60000;
}
/**
* We can write chunks if we have at least one valid storage engine
* underneath us.
*
* This engine must not also be a chunk engine.
*/
public function canWriteFiles() {
return (bool)$this->getWritableEngine();
}
public function hasFilesizeLimit() {
return false;
}
public function isChunkEngine() {
return true;
}
public function isTestEngine() {
// TODO: For now, prevent this from actually being selected.
return true;
}
public function writeFile($data, array $params) {
// The chunk engine does not support direct writes.
throw new PhutilMethodNotImplementedException();
}
public function readFile($handle) {
// This is inefficient, but makes the API work as expected.
$chunks = $this->loadAllChunks($handle, true);
$buffer = '';
foreach ($chunks as $chunk) {
$data_file = $chunk->getDataFile();
if (!$data_file) {
throw new Exception(pht('This file data is incomplete!'));
}
$buffer .= $chunk->getDataFile()->loadFileData();
}
return $buffer;
}
public function deleteFile($handle) {
$engine = new PhabricatorDestructionEngine();
$chunks = $this->loadAllChunks($handle);
foreach ($chunks as $chunk) {
$engine->destroyObject($chunk);
}
}
private function loadAllChunks($handle, $need_files) {
$chunks = id(new PhabricatorFileChunkQuery())
->setViewer(PhabricatorUser::getOmnipotentUser())
->withChunkHandles(array($handle))
->needDataFiles($need_files)
->execute();
$chunks = msort($chunks, 'getByteStart');
return $chunks;
}
/**
* Compute a chunked file hash for the viewer.
*
* We can not currently compute a real hash for chunked file uploads (because
* no process sees all of the file data).
*
* We also can not trust the hash that the user claims to have computed. If
* we trust the user, they can upload some `evil.exe` and claim it has the
* same file hash as `good.exe`. When another user later uploads the real
* `good.exe`, we'll just create a reference to the existing `evil.exe`. Users
* who download `good.exe` will then receive `evil.exe`.
*
* Instead, we rehash the user's claimed hash with account secrets. This
* allows users to resume file uploads, but not collide with other users.
*
* Ideally, we'd like to be able to verify hashes, but this is complicated
* and time consuming and gives us a fairly small benefit.
*
* @param PhabricatorUser Viewing user.
* @param string Claimed file hash.
* @return string Rehashed file hash.
*/
public static function getChunkedHash(PhabricatorUser $viewer, $hash) {
if (!$viewer->getPHID()) {
throw new Exception(
pht('Unable to compute chunked hash without real viewer!'));
}
$input = $viewer->getAccountSecret().':'.$hash.':'.$viewer->getPHID();
return self::getChunkedHashForInput($input);
}
public static function getChunkedHashForInput($input) {
$rehash = PhabricatorHash::digest($input);
// Add a suffix to identify this as a chunk hash.
$rehash = substr($rehash, 0, -2).'-C';
return $rehash;
}
public function allocateChunks($length, array $properties) {
$file = PhabricatorFile::newChunkedFile($this, $length, $properties);
$chunk_size = $this->getChunkSize();
$handle = $file->getStorageHandle();
$chunks = array();
for ($ii = 0; $ii < $length; $ii += $chunk_size) {
$chunks[] = PhabricatorFileChunk::initializeNewChunk(
$handle,
$ii,
min($ii + $chunk_size, $length));
}
$file->openTransaction();
foreach ($chunks as $chunk) {
$chunk->save();
}
$file->save();
$file->saveTransaction();
return $file;
}
private function getWritableEngine() {
// NOTE: We can't just load writable engines or we'll loop forever.
$engines = PhabricatorFileStorageEngine::loadAllEngines();
foreach ($engines as $engine) {
if ($engine->isChunkEngine()) {
continue;
}
if ($engine->isTestEngine()) {
continue;
}
if (!$engine->canWriteFiles()) {
continue;
}
if ($engine->hasFilesizeLimit()) {
if ($engine->getFilesizeLimit() < $this->getChunkSize()) {
continue;
}
}
return true;
}
return false;
}
public function getChunkSize() {
// TODO: This is an artificially small size to make it easier to
// test chunking.
return 32;
}
}