* fix(rio): reject corrupted short compressed/encrypted blocks instead of panicking DecompressReader::poll_read and DecryptReader::poll_read sliced the block body with a fixed `[0..16]` index to read the length varint. The body length comes from an untrusted 24-bit header field, so a corrupted/truncated block shorter than 16 bytes made the slice panic and crash the request task — a read-path DoS on GET of tiered/corrupted data. Pass the whole (arbitrary-length-safe) slice to uvarint and reject a non-positive or out-of-range length prefix with InvalidData. Adds a repro test for each reader; all existing round-trip tests still pass. Refs rustfs/backlog#812 * fix(utils): close SSRF bypass via IPv4-mapped IPv6 addresses validate_outbound_ip branched on the IpAddr variant, and the V6 branch's is_loopback/is_unicast_link_local/is_unique_local checks never inspect the embedded IPv4 of an IPv4-mapped address (::ffff:a.b.c.d). The metadata guard also only matched the plain V4 169.254.169.254. So ::ffff:127.0.0.1, ::ffff:10.0.0.5 and ::ffff:169.254.169.254 all passed the outbound guard, letting an attacker reach loopback/private/metadata endpoints. Normalize IPv4-mapped IPv6 to its embedded IPv4 (via to_ipv4_mapped, which matches only the true mapped form) before classification. Adds reject tests for mapped loopback/private/metadata and an allow test for public IPv6. Refs rustfs/backlog#813 * fix(ecstore): streaming last-part loss, GCS tier Range/remove, stat_all_dirs alignment Four confirmed data-reliability defects: - put_object_multipart_stream: the CompleteMultipartUpload part-collection loop used exclusive `1..total_parts_count`, dropping the final part (and collecting zero parts for a single-part object) — silently truncating the completed object. Extracted collect_complete_parts (1..=total_parts_count) with unit tests. - GCS warm backend get() ignored the requested byte range, returning the whole object for a Range GET; now applies ReadRange::segment like the other backends. - GCS warm backend remove() was an empty stub, so deleting a tiered object left it on GCS forever; now deletes via StorageControl (added a control-plane client), and in_use() actually lists (prefix-scoped) instead of always returning false. - stat_all_dirs skipped None disk slots and dropped JoinErrors, returning a compressed, misaligned error vector; heal_object_dir then zipped it against the full disks array and could make_volume on the WRONG disk. Now returns one index-aligned entry per slot (None -> DiskNotFound), and heal no longer pre-fills the drive report (which would double it). Added an alignment test. Refs rustfs/backlog#807 * fix(kms): stop Vault backend from destroying/reviving keys on failure Two confirmed key-safety defects in the Vault KV2 backend: - get_key_material() 'self-healed' a decrypt or wrong-length failure by minting a fresh random master key and overwriting the stored value. That destroys the original key material, making every DEK ever wrapped by it permanently undecryptable. Decryption must never mutate the stored key: both branches now return a cryptographic_error instead. (The empty-material bootstrap path, which only fills a never-initialized key, is intentionally left intact.) - cancel_key_deletion() reset key_state to Enabled only in the returned response and never persisted it, so the key stayed PendingDeletion in storage and would still be reaped. It now writes the state back via update_key_metadata_in_storage and fails the request if the write fails. Adds ignored (Vault-requiring) integration tests documenting both behaviours. The third item (VaultTransit key state only in memory -> revived as Enabled after restart) is deferred: a fail-closed guard would break restart availability for all transit keys; the correct fix needs a persistent metadata store + Vault integration testing. Tracked in rustfs/backlog#808. Refs rustfs/backlog#808 * fix(admin): clamp STS AssumeRole duration; persist ImportBucketMetadata to disk Two confirmed admin-API defects: - Standard AssumeRole used the raw client-supplied DurationSeconds with no upper bound, so a caller could mint near-permanent temporary credentials. Clamp it to the AWS/MinIO STS window [900, 43200] (with 0 -> default 3600) via a shared clamp_assume_role_duration helper, and build the exp claim with saturating_add. This matches the existing AssumeRoleWithWebIdentity path. - ImportBucketMetadata only mutated an in-memory map and returned 200, silently dropping every imported config. It now persists each non-empty config via metadata_sys::update (which merges onto existing on-disk metadata) and returns InternalError if a write fails. Mapping extracted to imported_configs_to_persist with unit tests. Refs rustfs/backlog#809 * fix(heal): enqueue displacing request in release builds push_displacing_lower_priority folded the real enqueue call into debug_assert_eq!(self.push(request), Accepted). In release builds (debug_assertions off) the whole macro — including its argument — is compiled out, so after evicting a lower-priority queued item the new high-priority request was silently dropped and never healed. Hoist self.push(request) out of the assertion so the side effect runs in all builds. Adds a --release regression test. Refs rustfs/backlog#811 * fix(iam): propagate real delete_policy backend errors instead of swallowing them delete_policy's is_from_notify path had its error handling inverted: a real backend failure (disk IO / insufficient quorum) evicted the cache and returned Ok(()), reporting a phantom success while policy.json survived on disk (to be reloaded on the next full IAM reload); NoSuchPolicy — which should be idempotent success — returned Err. Propagate real errors and let NoSuchPolicy fall through to the idempotent cache-evict + Ok, matching delete_user / the notification handler in the same file. Adds a backend-error-injection regression test. Refs rustfs/backlog#810 * fix(utils): also normalize IPv4-compatible IPv6 in the SSRF guard The initial fix only unwrapped IPv4-mapped (::ffff:a.b.c.d) addresses; the deprecated IPv4-compatible form (::a.b.c.d, e.g. ::127.0.0.1 / ::169.254.169.254) still bypassed the guard. Reject pure-IPv6 specials (::, ::1, fe80::, fc00::) first, then normalize BOTH embedded-IPv4 forms before the IPv4 rules. Adds tests for compatible-form loopback/metadata and confirms ::1 / :: stay rejected. Found by adversarial review of the initial fix. Refs rustfs/backlog#813 * fix(ecstore): fix the same last-part loss in the parallel streaming path put_object_multipart_stream_parallel had the identical off-by-one (1..total_parts_count) that truncated the last part / produced zero parts for a single-part upload — reachable when concurrent stream parts are enabled. Reuse collect_complete_parts, which now returns an error instead of panicking on a gap in the parts map. Adds a missing-part error test. Found by adversarial review of the initial fix. Refs rustfs/backlog#807 * fix(kms): local backend must preserve key material on status change LocalKmsClient (the default KMS backend) regenerated the master key material on enable_key/disable_key/schedule_key_deletion/cancel_key_deletion — a pure status change. A single disable+enable cycle therefore destroyed the original key, making every DEK ever wrapped by it permanently undecryptable (silent data loss, no network needed). Preserve the existing material via get_key_material and re-save with only the status changed. Adds a hermetic regression test that wraps a DEK, cycles all four status methods, and asserts the DEK still decrypts. Found by adversarial review of the Vault fix. Refs rustfs/backlog#808 * test(rio): cover the length-prefix guard; correct its comment Add a DecompressReader test that feeds an unterminated length varint so uvarint returns 0 and the new guard (not the downstream codec) produces the InvalidData error, and reword the guard comment which overclaimed that the > len bound prevents a reachable panic (it is belt-and-suspenders). No behavior change. Found by adversarial review. Refs rustfs/backlog#812 * test(rio): build test block headers via vec! to satisfy clippy The new corrupted-block tests built the header with Vec::new() + repeated push, tripping clippy::vec_init_then_push (-D warnings in CI). Construct the fixed header bytes with vec![] instead. No behavior change. --------- Co-authored-by: houseme <[email protected]>
640 lines
24 KiB
Rust
640 lines
24 KiB
Rust
// Copyright 2024 RustFS Team
|
|
//
|
|
// Licensed under the Apache License, Version 2.0 (the "License");
|
|
// you may not use this file except in compliance with the License.
|
|
// You may obtain a copy of the License at
|
|
//
|
|
// http://www.apache.org/licenses/LICENSE-2.0
|
|
//
|
|
// Unless required by applicable law or agreed to in writing, software
|
|
// distributed under the License is distributed on an "AS IS" BASIS,
|
|
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
// See the License for the specific language governing permissions and
|
|
// limitations under the License.
|
|
#![allow(unused_imports)]
|
|
#![allow(unused_variables)]
|
|
#![allow(unused_mut)]
|
|
#![allow(unused_assignments)]
|
|
#![allow(unused_must_use)]
|
|
#![allow(clippy::all)]
|
|
|
|
use bytes::Bytes;
|
|
use futures::future::join_all;
|
|
use http::{HeaderMap, HeaderName, HeaderValue, StatusCode};
|
|
use std::io::Error;
|
|
use std::sync::RwLock;
|
|
use std::{collections::HashMap, sync::Arc};
|
|
use time::{OffsetDateTime, format_description};
|
|
use tokio::{select, sync::mpsc};
|
|
use tokio_util::sync::CancellationToken;
|
|
use tracing::warn;
|
|
use uuid::Uuid;
|
|
|
|
use crate::client::checksum::{ChecksumMode, add_auto_checksum_headers, apply_auto_checksum};
|
|
use crate::client::{
|
|
api_error_response::{err_invalid_argument, err_unexpected_eof, http_resp_to_error_response},
|
|
api_put_object::PutObjectOptions,
|
|
api_put_object_common::{is_object, optimal_part_info},
|
|
api_put_object_multipart::UploadPartParams,
|
|
api_s3_datatypes::{CompleteMultipartUpload, CompletePart, ObjectPart},
|
|
constants::ISO8601_DATEFORMAT,
|
|
transition_api::{ReaderImpl, RequestMetadata, TransitionClient, UploadInfo},
|
|
};
|
|
|
|
use crate::client::utils::base64_encode;
|
|
use rustfs_utils::path::trim_etag;
|
|
use s3s::header::{X_AMZ_EXPIRATION, X_AMZ_VERSION_ID};
|
|
|
|
pub struct UploadedPartRes {
|
|
pub error: std::io::Error,
|
|
pub part_num: i64,
|
|
pub size: i64,
|
|
pub part: ObjectPart,
|
|
}
|
|
|
|
pub struct UploadPartReq {
|
|
pub part_num: i64,
|
|
pub part: ObjectPart,
|
|
}
|
|
|
|
impl TransitionClient {
|
|
pub async fn put_object_multipart_stream(
|
|
self: Arc<Self>,
|
|
bucket_name: &str,
|
|
object_name: &str,
|
|
reader: ReaderImpl,
|
|
size: i64,
|
|
opts: &PutObjectOptions,
|
|
) -> Result<UploadInfo, std::io::Error> {
|
|
let info: UploadInfo;
|
|
if opts.concurrent_stream_parts && opts.num_threads > 1 {
|
|
info = self
|
|
.put_object_multipart_stream_parallel(bucket_name, object_name, reader, opts)
|
|
.await?;
|
|
} else if !is_object(&reader) && !opts.send_content_md5 {
|
|
info = self
|
|
.put_object_multipart_stream_from_readat(bucket_name, object_name, reader, size, opts)
|
|
.await?;
|
|
} else {
|
|
info = self
|
|
.put_object_multipart_stream_optional_checksum(bucket_name, object_name, reader, size, opts)
|
|
.await?;
|
|
}
|
|
|
|
Ok(info)
|
|
}
|
|
|
|
pub async fn put_object_multipart_stream_from_readat(
|
|
&self,
|
|
bucket_name: &str,
|
|
object_name: &str,
|
|
reader: ReaderImpl,
|
|
size: i64,
|
|
opts: &PutObjectOptions,
|
|
) -> Result<UploadInfo, std::io::Error> {
|
|
let ret = optimal_part_info(size, opts.part_size)?;
|
|
let (total_parts_count, part_size, lastpart_size) = ret;
|
|
let mut opts = opts.clone();
|
|
if opts.checksum.is_set() {
|
|
opts.auto_checksum = opts.checksum.clone();
|
|
}
|
|
|
|
opts.user_metadata.remove("X-Amz-Checksum-Algorithm");
|
|
|
|
self.put_object_multipart_stream_optional_checksum(bucket_name, object_name, reader, size, &opts)
|
|
.await
|
|
}
|
|
|
|
pub async fn put_object_multipart_stream_optional_checksum(
|
|
&self,
|
|
bucket_name: &str,
|
|
object_name: &str,
|
|
mut reader: ReaderImpl,
|
|
size: i64,
|
|
opts: &PutObjectOptions,
|
|
) -> Result<UploadInfo, std::io::Error> {
|
|
let mut opts = opts.clone();
|
|
if opts.checksum.is_set() {
|
|
opts.auto_checksum = opts.checksum.clone();
|
|
opts.send_content_md5 = false;
|
|
}
|
|
|
|
if !opts.send_content_md5 {
|
|
add_auto_checksum_headers(&mut opts);
|
|
}
|
|
|
|
let ret = optimal_part_info(size, opts.part_size)?;
|
|
let (total_parts_count, mut part_size, lastpart_size) = ret;
|
|
let upload_id = self.new_upload_id(bucket_name, object_name, &opts).await?;
|
|
opts.user_metadata.remove("X-Amz-Checksum-Algorithm");
|
|
|
|
let mut custom_header = opts.header().clone();
|
|
|
|
let mut total_uploaded_size: i64 = 0;
|
|
|
|
let mut parts_info = HashMap::<i64, ObjectPart>::new();
|
|
let mut buf = Vec::<u8>::with_capacity(part_size as usize);
|
|
|
|
let mut md5_base64: String = "".to_string();
|
|
for part_number in 1..=total_parts_count {
|
|
if part_number == total_parts_count {
|
|
part_size = lastpart_size;
|
|
}
|
|
|
|
match &mut reader {
|
|
ReaderImpl::Body(content_body) => {
|
|
buf = content_body.to_vec();
|
|
}
|
|
ReaderImpl::ObjectBody(content_body) => {
|
|
buf = content_body.read_all().await?;
|
|
}
|
|
}
|
|
let length = buf.len();
|
|
|
|
if opts.send_content_md5 {
|
|
let mut md5_hasher = self.md5_hasher.lock().unwrap();
|
|
let md5_hash = match md5_hasher.as_mut() {
|
|
Some(hasher) => hasher,
|
|
None => return Err(std::io::Error::other("MD5 hasher not initialized")),
|
|
};
|
|
let hash = md5_hash.hash_encode(&buf[..length]);
|
|
md5_base64 = base64_encode(hash.as_ref());
|
|
} else {
|
|
let mut crc = opts.auto_checksum.hasher()?;
|
|
crc.update(&buf[..length]);
|
|
let csum = crc.finalize();
|
|
|
|
if let Ok(header_name) = HeaderName::from_bytes(opts.auto_checksum.key().as_bytes()) {
|
|
if let Ok(header_value) = base64_encode(csum.as_ref()).parse() {
|
|
custom_header.insert(header_name, header_value);
|
|
} else {
|
|
warn!("Failed to parse checksum value");
|
|
}
|
|
} else {
|
|
warn!("Invalid header name: {}", opts.auto_checksum.key());
|
|
}
|
|
}
|
|
|
|
let hooked = ReaderImpl::Body(Bytes::from(buf)); //newHook(BufferReader::new(buf), opts.progress);
|
|
let mut p = UploadPartParams {
|
|
bucket_name: bucket_name.to_string(),
|
|
object_name: object_name.to_string(),
|
|
upload_id: upload_id.clone(),
|
|
reader: hooked,
|
|
part_number,
|
|
md5_base64: md5_base64.clone(),
|
|
size: part_size,
|
|
//sse: opts.server_side_encryption,
|
|
stream_sha256: !opts.disable_content_sha256,
|
|
custom_header: custom_header.clone(),
|
|
sha256_hex: "".to_string(),
|
|
trailer: HeaderMap::new(),
|
|
};
|
|
let obj_part = self.upload_part(&mut p).await?;
|
|
|
|
parts_info.entry(part_number).or_insert(obj_part);
|
|
|
|
total_uploaded_size += part_size as i64;
|
|
}
|
|
|
|
if size > 0 && total_uploaded_size != size {
|
|
return Err(std::io::Error::other(err_unexpected_eof(
|
|
total_uploaded_size,
|
|
size,
|
|
bucket_name,
|
|
object_name,
|
|
)));
|
|
}
|
|
|
|
let mut compl_multipart_upload = CompleteMultipartUpload::default();
|
|
|
|
// Parts are keyed 1..=total_parts_count during upload; every one — including the last —
|
|
// must be collected. The previous exclusive `1..total_parts_count` bound dropped the final
|
|
// part, silently truncating the completed object (and produced zero parts for a single-part
|
|
// upload).
|
|
let mut all_parts = collect_complete_parts(&parts_info, total_parts_count)?;
|
|
for part in &all_parts {
|
|
compl_multipart_upload.parts.push(CompletePart {
|
|
etag: part.etag.clone(),
|
|
part_num: part.part_num,
|
|
checksum_crc32: part.checksum_crc32.clone(),
|
|
checksum_crc32c: part.checksum_crc32c.clone(),
|
|
checksum_sha1: part.checksum_sha1.clone(),
|
|
checksum_sha256: part.checksum_sha256.clone(),
|
|
checksum_crc64nvme: part.checksum_crc64nvme.clone(),
|
|
});
|
|
}
|
|
|
|
compl_multipart_upload.parts.sort();
|
|
|
|
let mut opts = PutObjectOptions {
|
|
//server_side_encryption: opts.server_side_encryption,
|
|
auto_checksum: opts.auto_checksum,
|
|
..Default::default()
|
|
};
|
|
apply_auto_checksum(&mut opts, &mut all_parts);
|
|
let mut upload_info = self
|
|
.complete_multipart_upload(bucket_name, object_name, &upload_id, compl_multipart_upload, &opts)
|
|
.await?;
|
|
|
|
upload_info.size = total_uploaded_size;
|
|
Ok(upload_info)
|
|
}
|
|
|
|
pub async fn put_object_multipart_stream_parallel(
|
|
self: Arc<Self>,
|
|
bucket_name: &str,
|
|
object_name: &str,
|
|
mut reader: ReaderImpl, /*GetObjectReader*/
|
|
opts: &PutObjectOptions,
|
|
) -> Result<UploadInfo, std::io::Error> {
|
|
let mut opts = opts.clone();
|
|
if opts.checksum.is_set() {
|
|
opts.send_content_md5 = false;
|
|
opts.auto_checksum = opts.checksum.clone();
|
|
}
|
|
if !opts.send_content_md5 {
|
|
add_auto_checksum_headers(&mut opts);
|
|
}
|
|
|
|
let ret = optimal_part_info(-1, opts.part_size)?;
|
|
let (total_parts_count, part_size, _) = ret;
|
|
|
|
let upload_id = self.new_upload_id(bucket_name, object_name, &opts).await?;
|
|
opts.user_metadata.remove("X-Amz-Checksum-Algorithm");
|
|
|
|
let mut total_uploaded_size: i64 = 0;
|
|
let parts_info = Arc::new(RwLock::new(HashMap::<i64, ObjectPart>::new()));
|
|
|
|
let n_buffers = opts.num_threads;
|
|
let (bufs_tx, mut bufs_rx) = mpsc::channel(n_buffers as usize);
|
|
//let all = Vec::<u8>::with_capacity(n_buffers as usize * part_size as usize);
|
|
for i in 0..n_buffers {
|
|
//bufs_tx.send(&all[i * part_size..i * part_size + part_size]);
|
|
bufs_tx.send(Vec::<u8>::with_capacity(part_size as usize));
|
|
}
|
|
|
|
let mut futures = Vec::with_capacity(total_parts_count as usize);
|
|
let (err_tx, mut err_rx) = mpsc::channel(opts.num_threads as usize);
|
|
let cancel_token = CancellationToken::new();
|
|
|
|
//reader = newHook(reader, opts.progress);
|
|
|
|
for part_number in 1..=total_parts_count {
|
|
let mut buf = Vec::<u8>::new();
|
|
select! {
|
|
buf1 = bufs_rx.recv() => {
|
|
if let Some(buf1) = buf1 {
|
|
buf = buf1;
|
|
}
|
|
}
|
|
err = err_rx.recv() => {
|
|
//cancel_token.cancel();
|
|
return Err(err.unwrap_or_else(|| std::io::Error::other("Unknown error received from channel")));
|
|
}
|
|
else => (),
|
|
}
|
|
|
|
if buf.len() != part_size as usize {
|
|
return Err(std::io::Error::other(format!(
|
|
"read buffer < {} than expected partSize: {}",
|
|
buf.len(),
|
|
part_size
|
|
)));
|
|
}
|
|
|
|
match &mut reader {
|
|
ReaderImpl::Body(content_body) => {
|
|
buf = content_body.to_vec();
|
|
}
|
|
ReaderImpl::ObjectBody(content_body) => {
|
|
buf = content_body.read_all().await?;
|
|
}
|
|
}
|
|
let length = buf.len();
|
|
|
|
let mut custom_header = HeaderMap::new();
|
|
if !opts.send_content_md5 {
|
|
let mut crc = opts.auto_checksum.hasher()?;
|
|
crc.update(&buf[..length]);
|
|
let csum = crc.finalize();
|
|
|
|
if let Ok(header_name) = HeaderName::from_bytes(opts.auto_checksum.key().as_bytes()) {
|
|
if let Ok(header_value) = base64_encode(csum.as_ref()).parse() {
|
|
custom_header.insert(header_name, header_value);
|
|
} else {
|
|
warn!("Failed to parse checksum value");
|
|
}
|
|
} else {
|
|
warn!("Invalid header name: {}", opts.auto_checksum.key());
|
|
}
|
|
}
|
|
|
|
let clone_bufs_tx = bufs_tx.clone();
|
|
let clone_parts_info = parts_info.clone();
|
|
let clone_upload_id = upload_id.clone();
|
|
let clone_self = self.clone();
|
|
let err_tx_clone = err_tx.clone();
|
|
futures.push(async move {
|
|
let mut md5_base64: String = "".to_string();
|
|
|
|
if opts.send_content_md5 {
|
|
let mut md5_hasher = clone_self.md5_hasher.lock().unwrap();
|
|
let md5_hash = match md5_hasher.as_mut() {
|
|
Some(hasher) => hasher,
|
|
None => {
|
|
//let _ = err_tx_clone.send(std::io::Error::other("MD5 hasher not initialized")).await;
|
|
return Ok::<(), Error>(());
|
|
}
|
|
};
|
|
let hash = md5_hash.hash_encode(&buf[..length]);
|
|
md5_base64 = base64_encode(hash.as_ref());
|
|
}
|
|
|
|
//defer wg.Done()
|
|
let mut p = UploadPartParams {
|
|
bucket_name: bucket_name.to_string(),
|
|
object_name: object_name.to_string(),
|
|
upload_id: clone_upload_id,
|
|
reader: ReaderImpl::Body(Bytes::from(buf.clone())),
|
|
part_number,
|
|
md5_base64,
|
|
size: length as i64,
|
|
//sse: opts.server_side_encryption,
|
|
stream_sha256: !opts.disable_content_sha256,
|
|
custom_header,
|
|
sha256_hex: "".to_string(),
|
|
trailer: HeaderMap::new(),
|
|
};
|
|
let obj_part = match clone_self.upload_part(&mut p).await {
|
|
Ok(part) => part,
|
|
Err(err) => {
|
|
let _ = err_tx_clone.send(std::io::Error::other(err.to_string())).await;
|
|
return Err::<(), Error>(err);
|
|
}
|
|
};
|
|
|
|
{
|
|
let mut clone_parts_info = clone_parts_info.write().unwrap();
|
|
clone_parts_info.entry(part_number).or_insert(obj_part);
|
|
}
|
|
|
|
let _ = clone_bufs_tx.send(buf).await;
|
|
Ok::<(), Error>(())
|
|
});
|
|
|
|
total_uploaded_size += length as i64;
|
|
}
|
|
|
|
let results = join_all(futures).await;
|
|
|
|
select! {
|
|
err = err_rx.recv() => {
|
|
return Err(err.unwrap_or_else(|| std::io::Error::other("Unknown error received from channel")));
|
|
}
|
|
else => (),
|
|
}
|
|
|
|
let mut compl_multipart_upload = CompleteMultipartUpload::default();
|
|
|
|
// Same inclusive collection as the serial path: parts are keyed 1..=total_parts_count, so
|
|
// the exclusive `1..total_parts_count` bound dropped the final part (and produced zero
|
|
// parts for a single-part upload), silently truncating the object.
|
|
let parts_snapshot = parts_info.read().unwrap().clone();
|
|
let mut all_parts = collect_complete_parts(&parts_snapshot, total_parts_count)?;
|
|
for part in &all_parts {
|
|
compl_multipart_upload.parts.push(CompletePart {
|
|
etag: part.etag.clone(),
|
|
part_num: part.part_num,
|
|
checksum_crc32: part.checksum_crc32.clone(),
|
|
checksum_crc32c: part.checksum_crc32c.clone(),
|
|
checksum_sha1: part.checksum_sha1.clone(),
|
|
checksum_sha256: part.checksum_sha256.clone(),
|
|
checksum_crc64nvme: part.checksum_crc64nvme.clone(),
|
|
..Default::default()
|
|
});
|
|
}
|
|
|
|
compl_multipart_upload.parts.sort();
|
|
|
|
let mut opts = PutObjectOptions {
|
|
//server_side_encryption: opts.server_side_encryption,
|
|
auto_checksum: opts.auto_checksum,
|
|
..Default::default()
|
|
};
|
|
apply_auto_checksum(&mut opts, &mut all_parts);
|
|
|
|
let mut upload_info = self
|
|
.complete_multipart_upload(bucket_name, object_name, &upload_id, compl_multipart_upload, &opts)
|
|
.await?;
|
|
|
|
upload_info.size = total_uploaded_size;
|
|
Ok(upload_info)
|
|
}
|
|
|
|
pub async fn put_object_gcs(
|
|
&self,
|
|
bucket_name: &str,
|
|
object_name: &str,
|
|
reader: ReaderImpl,
|
|
size: i64,
|
|
opts: &PutObjectOptions,
|
|
) -> Result<UploadInfo, std::io::Error> {
|
|
let mut opts = opts.clone();
|
|
if opts.checksum.is_set() {
|
|
opts.send_content_md5 = false;
|
|
}
|
|
|
|
let md5_base64: String = "".to_string();
|
|
let progress_reader = reader; //newHook(reader, opts.progress);
|
|
|
|
self.put_object_do(bucket_name, object_name, progress_reader, &md5_base64, "", size, &opts)
|
|
.await
|
|
}
|
|
|
|
pub async fn put_object_do(
|
|
&self,
|
|
bucket_name: &str,
|
|
object_name: &str,
|
|
reader: ReaderImpl,
|
|
md5_base64: &str,
|
|
sha256_hex: &str,
|
|
size: i64,
|
|
opts: &PutObjectOptions,
|
|
) -> Result<UploadInfo, std::io::Error> {
|
|
let custom_header = opts.header();
|
|
|
|
let mut req_metadata = RequestMetadata {
|
|
bucket_name: bucket_name.to_string(),
|
|
object_name: object_name.to_string(),
|
|
custom_header,
|
|
content_body: reader,
|
|
content_length: size,
|
|
content_md5_base64: md5_base64.to_string(),
|
|
content_sha256_hex: sha256_hex.to_string(),
|
|
stream_sha256: !opts.disable_content_sha256,
|
|
add_crc: Default::default(),
|
|
bucket_location: Default::default(),
|
|
pre_sign_url: Default::default(),
|
|
query_values: Default::default(),
|
|
extra_pre_sign_header: Default::default(),
|
|
expires: Default::default(),
|
|
trailer: Default::default(),
|
|
};
|
|
let mut add_crc = false; //self.trailing_header_support && md5_base64 == "" && !s3utils.IsGoogleEndpoint(self.endpoint_url) && (opts.disable_content_sha256 || self.secure);
|
|
let mut opts = opts.clone();
|
|
if opts.checksum.is_set() {
|
|
req_metadata.add_crc = opts.checksum;
|
|
} else if add_crc {
|
|
for (k, _) in opts.user_metadata {
|
|
if k.to_lowercase().starts_with("x-amz-checksum-") {
|
|
add_crc = false;
|
|
}
|
|
}
|
|
if add_crc {
|
|
opts.auto_checksum.set_default(ChecksumMode::ChecksumCRC32C);
|
|
req_metadata.add_crc = opts.auto_checksum;
|
|
}
|
|
}
|
|
|
|
if opts.internal.source_version_id != "" {
|
|
if !opts.internal.source_version_id.is_empty() {
|
|
if let Err(err) = Uuid::parse_str(&opts.internal.source_version_id) {
|
|
return Err(std::io::Error::other(err_invalid_argument(&err.to_string())));
|
|
}
|
|
}
|
|
let mut url_values = HashMap::new();
|
|
url_values.insert("versionId".to_string(), opts.internal.source_version_id);
|
|
req_metadata.query_values = url_values;
|
|
}
|
|
|
|
let resp = self.execute_method(http::Method::PUT, &mut req_metadata).await?;
|
|
|
|
let resp_status = resp.status();
|
|
let h = resp.headers().clone();
|
|
|
|
if resp.status() != StatusCode::OK {
|
|
return Err(std::io::Error::other(http_resp_to_error_response(
|
|
resp_status,
|
|
&h,
|
|
vec![],
|
|
bucket_name,
|
|
object_name,
|
|
)));
|
|
}
|
|
|
|
let exp_time = resp
|
|
.headers()
|
|
.get(X_AMZ_EXPIRATION)
|
|
.and_then(|v| v.to_str().ok())
|
|
.and_then(|s| OffsetDateTime::parse(s, ISO8601_DATEFORMAT).ok())
|
|
.unwrap_or_else(OffsetDateTime::now_utc);
|
|
let rule_id = "".to_string();
|
|
let h = resp.headers();
|
|
Ok(UploadInfo {
|
|
bucket: bucket_name.to_string(),
|
|
key: object_name.to_string(),
|
|
etag: trim_etag(h.get("ETag").and_then(|v| v.to_str().ok()).unwrap_or("")),
|
|
|
|
version_id: if let Some(h_x_amz_version_id) = h.get(X_AMZ_VERSION_ID) {
|
|
h_x_amz_version_id.to_str().unwrap_or("").to_string()
|
|
} else {
|
|
"".to_string()
|
|
},
|
|
size,
|
|
expiration: exp_time,
|
|
expiration_rule_id: rule_id,
|
|
checksum_crc32: if let Some(h_checksum_crc32) = h.get(ChecksumMode::ChecksumCRC32.key()) {
|
|
h_checksum_crc32.to_str().unwrap_or("").to_string()
|
|
} else {
|
|
"".to_string()
|
|
},
|
|
checksum_crc32c: if let Some(h_checksum_crc32c) = h.get(ChecksumMode::ChecksumCRC32C.key()) {
|
|
h_checksum_crc32c.to_str().unwrap_or("").to_string()
|
|
} else {
|
|
"".to_string()
|
|
},
|
|
checksum_sha1: if let Some(h_checksum_sha1) = h.get(ChecksumMode::ChecksumSHA1.key()) {
|
|
h_checksum_sha1.to_str().unwrap_or("").to_string()
|
|
} else {
|
|
"".to_string()
|
|
},
|
|
checksum_sha256: if let Some(h_checksum_sha256) = h.get(ChecksumMode::ChecksumSHA256.key()) {
|
|
h_checksum_sha256.to_str().unwrap_or("").to_string()
|
|
} else {
|
|
"".to_string()
|
|
},
|
|
checksum_crc64nvme: if let Some(h_checksum_crc64nvme) = h.get(ChecksumMode::ChecksumCRC64NVME.key()) {
|
|
h_checksum_crc64nvme.to_str().unwrap_or("").to_string()
|
|
} else {
|
|
"".to_string()
|
|
},
|
|
..Default::default()
|
|
})
|
|
}
|
|
}
|
|
|
|
/// Collect the uploaded parts for CompleteMultipartUpload in ascending part order.
|
|
///
|
|
/// Parts are keyed `1..=total_parts_count` during upload (see the upload loop that inserts each
|
|
/// part), so every one — including the final part — must be collected. The previous exclusive
|
|
/// `1..total_parts_count` bound dropped the last part, silently truncating the completed object,
|
|
/// and collected zero parts for a single-part upload.
|
|
fn collect_complete_parts(parts_info: &HashMap<i64, ObjectPart>, total_parts_count: i64) -> Result<Vec<ObjectPart>, Error> {
|
|
let mut all_parts = Vec::with_capacity(parts_info.len());
|
|
for i in 1..=total_parts_count {
|
|
let part = parts_info
|
|
.get(&i)
|
|
.ok_or_else(|| Error::other(format!("missing uploaded part {i} of {total_parts_count}")))?;
|
|
all_parts.push(part.clone());
|
|
}
|
|
Ok(all_parts)
|
|
}
|
|
|
|
#[cfg(test)]
|
|
mod tests {
|
|
use super::{ObjectPart, collect_complete_parts};
|
|
use std::collections::HashMap;
|
|
|
|
fn parts_map(n: i64) -> HashMap<i64, ObjectPart> {
|
|
let mut m = HashMap::new();
|
|
for i in 1..=n {
|
|
m.insert(
|
|
i,
|
|
ObjectPart {
|
|
part_num: i,
|
|
..Default::default()
|
|
},
|
|
);
|
|
}
|
|
m
|
|
}
|
|
|
|
#[test]
|
|
fn collects_every_part_including_the_last() {
|
|
let collected: Vec<i64> = collect_complete_parts(&parts_map(3), 3)
|
|
.expect("all parts present")
|
|
.iter()
|
|
.map(|p| p.part_num)
|
|
.collect();
|
|
assert_eq!(collected, vec![1, 2, 3], "CompleteMultipartUpload must include the final part");
|
|
}
|
|
|
|
#[test]
|
|
fn single_part_upload_submits_one_part() {
|
|
let collected = collect_complete_parts(&parts_map(1), 1).expect("single part present");
|
|
assert_eq!(collected.len(), 1, "a single-part object must submit exactly one part, not zero");
|
|
assert_eq!(collected[0].part_num, 1);
|
|
}
|
|
|
|
#[test]
|
|
fn missing_part_is_an_error_not_a_panic() {
|
|
let mut m = parts_map(3);
|
|
m.remove(&2);
|
|
assert!(
|
|
collect_complete_parts(&m, 3).is_err(),
|
|
"a gap in the parts map must be an error, not a panic"
|
|
);
|
|
}
|
|
}
|