Oxicloud/Cargo.toml

[package]
name = "oxicloud"
version = "0.8.2"
edition = "2024"
default-run = "oxicloud"


[dependencies]
mimalloc = { version = "0.1.52", default-features = false }
axum = { version = "0.8.9", features = ["multipart", "http1", "http2", "tokio", "macros"] }
# "process" was previously enabled implicitly through aws-config's feature
# unification; ffmpeg_video_frame_service needs it, so declare it ourselves.
tokio = { version = "1.52.3", features = ["rt-multi-thread", "macros", "io-util", "net", "time", "sync", "fs", "process"] }
tokio-util = { version = "0.7.18", features = ["io", "codec", "compat"] }
tokio-stream = { version = "0.1.18", features = ["fs", "sync"] }
bytes = "1.11.1"
tempfile = "3.27.0"
tower = "0.5.3"
tower-http = { version = "0.6.11", features = ["fs", "compression-gzip", "compression-br", "trace", "cors", "add-extension", "request-id", "set-header", "limit"] }
flate2 = "1.1.9"
tracing = "0.1.44"
tracing-subscriber = { version = "0.3.23", features = ["env-filter"] }
chrono = { version = "0.4.45", features = ["serde"] }
# RFC 5545 iCalendar parser + emitter.
#
# Adopted 2026-07-14 to replace the hand-rolled property-scan in
# `src/domain/entities/calendar_event.rs::extract_ical_property`,
# which used a naive `format!("\n{}:", name)` substring search and
# refused ANY property carrying parameters (`DTSTART;VALUE=DATE:...`,
# `RECURRENCE-ID;VALUE=DATE:...`, `ATTENDEE;CN=…;PARTSTAT=…:mailto:…`).
# That broke all-day events and made the domain unaware of exception
# instances (see AtalayaLabs/OxiCloud#528).
#
# The crate is the widely-used Rust parser (~1500 SLOC, MIT/Apache),
# actively maintained by @Peltoche as `ical-rs` on GitHub. It handles
# line-folding, escaped characters, parameter maps, and every standard
# component. If a spec conformance gap is found, we contribute upstream.
ical = "0.11"
http-body = "1.0.1"
serde = { version = "1.0.228", features = ["derive"] }
serde_json = "1.0.150"
futures = "0.3.32"
async-stream = "0.3.6"
async-trait = "0.1.89"
mime_guess = "2.0.5"
uuid = { version = "1.23.3", features = ["v4", "v7", "serde"] }
thiserror = "2.0.18"

mockall = { version = "0.14.0", optional = true }
sqlx = { version = "0.8.6", features = ["postgres", "runtime-tokio", "tls-rustls", "chrono", "uuid", "json", "migrate"] }
jsonwebtoken = { version = "10.4.0", features = ["rust_crypto"] }
argon2 = "0.5.3"
rand_core = { version = "0.6", features = ["std", "getrandom"] }
quick-xml = "0.41.0"
dotenvy = "0.15.7"
moka = { version = "0.12.15", features = ["future", "sync"] }
http-range-header = "0.4"
image = { version = "0.25.10", default-features = false, features = ["jpeg", "png", "gif", "webp"] }
# Shrink-on-load JPEG decode (DCT 1/2·1/4·1/8 scaling) for thumbnails — pure
# Rust, no C toolchain. The `image` crate's zune-jpeg backend can't scale during
# decode; this can, cutting decode time/RAM ~order-of-magnitude on large photos.
jpeg-decoder = "0.3"
# SIMD (AVX2/SSE4.1/NEON) image resizing for thumbnails — far faster than the
# `image` crate's scalar resampler, and it speeds every format (incl. PNG/WebP).
fast_image_resize = "5"
# Lossy WebP encoding for thumbnails. The `image` crate's webp feature is
# lossless-only; this binds libwebp (vendored + built via `cc`, no system dep)
# for quality-controlled lossy output (~25-30% smaller than JPEG at equal SSIM).
webp = "0.3"
id3 = "1.17"
mp3-duration = "0.1"
kamadak-exif = "0.6.1"
md-5 = "0.11.0"
sha2 = "0.11.0"
unicode-normalization = "0.1.25"
blake3 = { version = "1.8.5", features = ["rayon", "mmap"] }
hex = "0.4.3"
http-body-util = "0.1.3"
percent-encoding = "2.3.2"
reqwest = { version = "0.12", default-features = false, features = ["json", "rustls-tls-webpki-roots","rustls-tls-native-roots"] }
base64 = "0.22.1"
fs2 = "0.4"
rayon = "1.12.0"
infer = "0.19"
async-compression = { version = "0.4.42", features = ["tokio", "gzip"] }
async_zip = { version = "0.0.18", features = ["tokio", "deflate"] }
dashmap = "6.2.1"
socket2 = { version = "0.6.4", features = ["all"] }
urlencoding = "2.1.3"
utoipa = { version = "5.5.0", features = ["axum_extras", "uuid", "chrono"] }
# NOTE: aws-config and aws-smithy-types were removed as direct deps in the
# round-3 perf pass — S3BlobBackend builds its client purely from
# aws_sdk_s3::config with static credentials; nothing referenced either
# crate, and aws-config alone pulled aws-sdk-sso/ssooidc/sts (~90 crates)
# into every build (benches/ROUND3.md).
aws-sdk-s3 = "1.136.0"
azure_core = { version = "0.21", default-features = false, features = ["enable_reqwest_rustls", "hmac_rust"] }
azure_storage = { version = "0.21", default-features = false, features = ["enable_reqwest_rustls", "hmac_rust"] }
azure_storage_blobs = { version = "0.21", default-features = false, features = ["enable_reqwest_rustls", "hmac_rust"] }
aes-gcm = "0.10.3"
lru = "0.16.4"
fastcdc = { version = "4.0.0", features = ["tokio"] }
lettre = { version = "0.11.18", default-features = false, features = ["smtp-transport", "tokio1-rustls-tls", "rustls-native-certs", "builder"] }
idna = "1.1"
smol_str = { version = "0.3.6", features = ["serde"] }
accept-language = "3.1.0"
askama = "0.16.0"
tantivy = "0.26.1"
zip = { version = "8.6.0", default-features = false, features = ["deflate"] }
pdf-extract = "0.12.0"
nom-exif = "3.6.1"
extism = { version = "1.30.0", optional = true }
toml = { version = "1.1.2", optional = true }
file-rotate = { version = "0.7.6", optional = true }
ort = { version = "2.0.0-rc.12", default-features = false, features = ["load-dynamic", "ndarray", "tracing", "api-24"], optional = true }
ndarray = { version = "0.17.2", optional = true }

[features]
default = []
test_utils = ["mockall"]
integration_tests = []
# WASM plugin runtime (Extism). Opt-in: bundles wasmtime, a large engine most
# deployments won't use. Activation also requires OXICLOUD_ENABLE_PLUGINS=true.
plugins = ["dep:extism", "dep:toml", "dep:file-rotate"]
# Empty marker feature that gates the `load-seed` binary so it isn't built
# by default (and skipped in prod Docker builds). Kept separate from
# test_utils so enabling it doesn't change the oxicloud dependency graph —
# this lets one `cargo build` produce both `oxicloud` and `load-seed`
# without recompiling oxicloud with mockall in scope.
load_seed_bin = []
# Real ONNX-backed face analyzer (detector + embedder) for the People feature.
# Opt-in: pulls `ort` (ONNX Runtime, load-dynamic — dlopen's libonnxruntime at
# runtime) + `ndarray`, a heavy stack most deployments won't use. Activation also
# requires OXICLOUD_ENABLE_FACES=true *and* operator-provided ONNX models; without
# this feature the People pipeline falls back to the inert NoopFaceAnalyzer.
faces-onnx = ["dep:ort", "dep:ndarray"]
# Performance benchmark harness (Phase 0). Exposes `bench_support` + thin public
# wrappers over the private thumbnail render functions so `benches/` and
# `examples/` can measure them. Off by default — adds nothing to prod builds.
# Run with: `cargo bench --features bench` / `cargo run --release --features bench --example bench_thumbnails_mem`.
bench = []

[dev-dependencies]
criterion = "0.5"

[lints.rust]
unexpected_cfgs = { level = "warn", check-cfg = ['cfg(integration_tests)'] }

[[bin]]
name = "generate-openapi"
path = "src/bin/generate-openapi.rs"

[[bin]]
name = "migrate-nfc-filenames"
path = "src/bin/migrate-nfc-filenames.rs"

[[bin]]
name = "load-seed"
path = "src/bin/load-seed.rs"
# Test fixture seeder. Gated behind the empty `load_seed_bin` feature so
# `cargo build --release` (and the prod Dockerfile) skip it. tests/load/run.sh
# and load-nightly.yml build it explicitly with --features load_seed_bin.
required-features = ["load_seed_bin"]

# Phase 0 perf harness — Task 0.2 (criterion latency + output-size bench).
[[bench]]
name = "thumbnails"
path = "benches/thumbnails.rs"
harness = false
required-features = ["bench"]

# Phase 0 perf harness — Task 0.3 (peak-RAM + saturated-throughput baseline).
[[example]]
name = "bench_thumbnails_mem"
path = "examples/bench_thumbnails_mem.rs"
required-features = ["bench"]

# ZIP entry-compression benchmark — Deflate-always vs MIME-aware Stored for
# already-compressed media on the folder/batch ZIP download path. No Postgres.
[[example]]
name = "bench_zip_media"
path = "examples/bench_zip_media.rs"
required-features = ["bench"]

# WebDAV dead-properties fetch benchmark — PROPFIND's per-child N+1 (with a
# non-indexable IS NOT DISTINCT FROM predicate) vs batched = ANY($1) per page
# (needs the dev Postgres up).
[[example]]
name = "bench_dead_props"
path = "examples/bench_dead_props.rs"
required-features = ["bench"]

# NC chroot / default-drive resolution benchmark — the middleware's 2 uncached
# queries per request vs the moka caches (needs the dev Postgres up).
[[example]]
name = "bench_chroot_cache"
path = "examples/bench_chroot_cache.rs"
required-features = ["bench"]

# Quota-path benchmark — full auth.users row (incl. 512 KiB avatar) vs the
# narrow 2-column read, on every upload check / quota PROPFIND (needs Postgres).
[[example]]
name = "bench_quota_path"
path = "examples/bench_quota_path.rs"
required-features = ["bench"]

# People-tab benchmark — full faces scan (2 KiB embedding per row) vs grouped
# COUNT + batched cover lookup (needs Postgres).
[[example]]
name = "bench_people_list"
path = "examples/bench_people_list.rs"
required-features = ["bench"]

# PROPFIND folder-paging benchmark — LIMIT/OFFSET full-folder rescan per page
# vs keyset + (folder_id, name) index (needs Postgres).
[[example]]
name = "bench_propfind_paging"
path = "examples/bench_propfind_paging.rs"
required-features = ["bench"]

# Static-asset compression benchmark — per-request Brotli vs precompressed
# sibling read. No Postgres.
[[example]]
name = "bench_static_precompress"
path = "examples/bench_static_precompress.rs"
required-features = ["bench"]

# Round-2 battery: range-from-cache, NC chunk gate, delta prefetch, ingest
# overlap (real store_from_stream; run with OXICLOUD_INGEST_OVERLAP=0/1),
# ZIP streaming TTFB. Sections 1 and 4 need Postgres.
[[example]]
name = "bench_round2"
path = "examples/bench_round2.rs"
required-features = ["bench"]

# Video thumbnail benchmark — Option B (server-side ffmpeg frame → WebP). Needs
# `ffmpeg` on PATH (libx264/libx265/libvpx-vp9 to synthesize the test corpus).
[[example]]
name = "bench_video_thumbnails"
path = "examples/bench_video_thumbnails.rs"
required-features = ["bench"]

# DB connection-pool tail-latency benchmark (needs the dev Postgres up).
[[example]]
name = "bench_db_pool"
path = "examples/bench_db_pool.rs"
required-features = ["bench"]

# Blob-manifest read round-trip benchmark: OLD 2 queries vs NEW 1 (needs dev Postgres).
[[example]]
name = "bench_blob_manifest"
path = "examples/bench_blob_manifest.rs"
required-features = ["bench"]

# Blob download read-ahead benchmark — sweeps the local backend's chunk prefetch
# depth (read_prefetch / buffered(N)) under disk-bound vs network-bound consumers
# and warm vs cold page cache. No Postgres needed.
[[example]]
name = "bench_blob_prefetch"
path = "examples/bench_blob_prefetch.rs"
required-features = ["bench"]

# Tokio runtime tuning benchmark — worker over-subscription (throughput + p99
# under CPU contention) and blocking-pool RSS blast radius, default vs tuned.
# No Postgres needed; run under `taskset -c 0,1` to model a 2-core quota.
[[example]]
name = "bench_tokio_runtime"
path = "examples/bench_tokio_runtime.rs"
required-features = ["bench"]

# CPU pool concurrency benchmark — thumbnail decode throughput + p99 as the
# decode-permit count is swept, showing the effect of sizing the image pools to
# the CFS quota (effective_parallelism) vs the host core count. No Postgres;
# run under `taskset -c 0,1` to model a 2-core quota.
[[example]]
name = "bench_pool_concurrency"
path = "examples/bench_pool_concurrency.rs"
required-features = ["bench"]

# ACL owner-cache benchmark — owner query vs moka hit (needs the dev Postgres up).
[[example]]
name = "bench_owner_cache"
path = "examples/bench_owner_cache.rs"
required-features = ["bench"]

# Round-4 battery ─────────────────────────────────────────────────────────────

# PG row → entity path materialization — the per-listing-row make_file_path
# split→rejoin + NFC copy chain vs the one-pass builders. No Postgres.
[[example]]
name = "bench_row_path"
path = "examples/bench_row_path.rs"
required-features = ["bench"]

# WebDAV drive-selector resolution — the per-request list_readable_by grants
# join vs the per-user readable_cache (needs the dev Postgres up).
[[example]]
name = "bench_drive_selector"
path = "examples/bench_drive_selector.rs"
required-features = ["bench"]

# CalDAV parse path — from_ical's 8×-reparse vs single parse, per-event
# uppercase copies on REPORT/GET, UID clone churn. No Postgres.
[[example]]
name = "bench_caldav_parse"
path = "examples/bench_caldav_parse.rs"
required-features = ["bench"]

# PROPFIND per-row XML emit — partition Vec churn + chrono format-interpreter
# dates vs single-pass + stack-rendered fields. No Postgres.
[[example]]
name = "bench_propfind_xml"
path = "examples/bench_propfind_xml.rs"
required-features = ["bench"]

# Grant-listing hydration N+1 (calendars / address books / playlists) +
# user-flags cold-cache herd (needs the dev Postgres up).
[[example]]
name = "bench_n1_hydration"
path = "examples/bench_n1_hydration.rs"
required-features = ["bench"]

# Face-indexing fan-out — unbounded per-image spawn vs core-count semaphore;
# peak-live-heap + wall on the bench_support photo corpus. No Postgres.
[[example]]
name = "bench_faces_bound"
path = "examples/bench_faces_bound.rs"
required-features = ["bench"]

# Azure download path — whole-blob collect vs streamed pages, TTFB + peak
# live heap against a local Azure-GET stub (endpoint_url hook). No Postgres.
[[example]]
name = "bench_azure_stream"
path = "examples/bench_azure_stream.rs"
required-features = ["bench"]

# Round-5 battery ─────────────────────────────────────────────────────────────

# CalDAV whole-calendar REPORT/GET — buffered double-residency vs uid-keyset
# streaming; TTFB + peak live heap (needs the dev Postgres up).
[[example]]
name = "bench_caldav_stream"
path = "examples/bench_caldav_stream.rs"
required-features = ["bench"]

# Round-5 micro-allocation pack — suggest clones, readable-cache Arc hit,
# SPA-listing interning, NC href prefix, CardDAV REPORT churn. No Postgres.
[[example]]
name = "bench_micro_allocs"
path = "examples/bench_micro_allocs.rs"
required-features = ["bench"]

# Round-6 battery ─────────────────────────────────────────────────────────────

# CardDAV whole-book REPORT/PROPFIND — buffered double-residency vs cursor
# streaming; TTFB + peak live heap (needs the dev Postgres up).
[[example]]
name = "bench_carddav_stream"
path = "examples/bench_carddav_stream.rs"
required-features = ["bench"]

# Batch-favorites authz pre-check — serial require loop vs try_join_all
# against the real PgAclEngine (needs the dev Postgres up).
[[example]]
name = "bench_favorites_authz"
path = "examples/bench_favorites_authz.rs"
required-features = ["bench"]

# Digest-hex rendering + NC id-batch marshalling micro-allocs (pure CPU).
[[example]]
name = "bench_hex_ids"
path = "examples/bench_hex_ids.rs"
required-features = ["bench"]

# `id::text` server cast vs binary UUID decode + app-side formatting A/B
# (needs the dev Postgres up).
[[example]]
name = "bench_uuid_text_cast"
path = "examples/bench_uuid_text_cast.rs"
required-features = ["bench"]

# Round-3 battery ─────────────────────────────────────────────────────────────

# Web-UI folder listing — whole-folder rescan + top-N sort per page vs keyset
# pushdown into the UNION-ALL branches + (folder_id, LOWER(name), id) indexes
# (needs the dev Postgres up).
[[example]]
name = "bench_listing_keyset"
path = "examples/bench_listing_keyset.rs"
required-features = ["bench"]

# Photos timeline — full-library scan + top-N above the grants join vs
# per-drive LATERAL top-N on the media-timeline index (needs Postgres).
[[example]]
name = "bench_photos_timeline"
path = "examples/bench_photos_timeline.rs"
required-features = ["bench"]

# PROPFIND subfolder paging — LIMIT/OFFSET + COUNT(*) OVER() per page vs
# keyset batch, mirroring the files-side PROPFIND-PAGING fix (needs Postgres).
[[example]]
name = "bench_folder_keyset"
path = "examples/bench_folder_keyset.rs"
required-features = ["bench"]

# Basic-auth thundering herd — K concurrent cache misses each paying Argon2id
# vs single-flight try_get_with (needs Postgres).
[[example]]
name = "bench_auth_herd"
path = "examples/bench_auth_herd.rs"
required-features = ["bench"]

# CachedBlobBackend — miss stampede (N duplicate remote fetches racing on one
# .tmp) vs per-hash single-flight; warm-hit index throughput. No Postgres.
[[example]]
name = "bench_blob_cache"
path = "examples/bench_blob_cache.rs"
required-features = ["bench"]

# Upload spool/assembly I/O — ReaderStream capacity sweep on part-file reads
# and BufWriter vs bare-File frame writes on the chunk spool path. No Postgres.
[[example]]
name = "bench_upload_spool"
path = "examples/bench_upload_spool.rs"
required-features = ["bench"]

# S3 chunk PUT — HEAD-before-PUT vs unconditional PUT against a local axum
# stub with injected latency; Azure Bytes-vs-to_vec copy micro. No Postgres.
[[example]]
name = "bench_s3_put"
path = "examples/bench_s3_put.rs"
required-features = ["bench"]

# File/Folder -> DTO mapping allocations — Arc<str> interning of closed-set
# display fields, 1-alloc etag/size formatting. No Postgres.
[[example]]
name = "bench_dto_map"
path = "examples/bench_dto_map.rs"
required-features = ["bench"]

# CardDAV REPORT — dead per-contact vCard pre-generation + O(N^2) uid scan vs
# single on-demand generation. No Postgres.
[[example]]
name = "bench_carddav_report"
path = "examples/bench_carddav_report.rs"
required-features = ["bench"]

# Search-results cache RSS — entry-count capacity vs byte weigher. No Postgres.
[[example]]
name = "bench_search_cache_mem"
path = "examples/bench_search_cache_mem.rs"
required-features = ["bench"]

[profile.release]
lto = "thin"
codegen-units = 1
opt-level = 3
strip = true

[profile.dev]
opt-level = 1
debug = true

[profile.bench]
lto = "fat"
codegen-units = 1
opt-level = 3