Files
Mangalord/backend/Cargo.toml
MechaCat02 592747f1e0 fix(crawler): budget image tail against actual sniff-prefix length
The per-image download cap subtracted the constant SNIFF_PREFIX_BYTES (64)
from the budget instead of the bytes actually drained into the prefix.
Because the prefix loop appends whole chunks, a single ~16 KiB first chunk
fills the 64-byte sniff window in one drain, so the tail could then add
another near-full cap — storing up to ~2× max_image_bytes per page.

Capture prefix.len() before the prefix is moved into the stream and budget
the tail as `max_image_bytes - prefix_len` via a small `remaining_after_prefix`
helper (unit-tested for the overshoot and saturation cases).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-03 20:57:29 +02:00

75 lines
2.4 KiB
TOML
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
[package]
name = "mangalord"
version = "0.93.4"
edition = "2021"
default-run = "mangalord"
[lib]
path = "src/lib.rs"
[[bin]]
name = "mangalord"
path = "src/main.rs"
[[bin]]
name = "crawler"
path = "src/bin/crawler.rs"
[dependencies]
axum = { version = "0.7", features = ["macros", "multipart"] }
tokio = { version = "1", features = ["full"] }
sqlx = { version = "0.8", features = ["runtime-tokio", "postgres", "uuid", "chrono", "macros", "migrate"] }
serde = { version = "1", features = ["derive"] }
serde_json = "1"
uuid = { version = "1", features = ["v4", "serde"] }
chrono = { version = "0.4", features = ["serde"] }
chrono-tz = "0.9"
tracing = "0.1"
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
tower = { version = "0.5", features = ["util"] }
tower-http = { version = "0.6", features = ["trace", "cors"] }
thiserror = "1"
anyhow = "1"
async-trait = "0.1"
dotenvy = "0.15"
argon2 = "0.5"
rand = "0.8"
sha2 = "0.10"
subtle = "2"
base64 = "0.22"
# Image decode + downscale for the analysis worker (keep the page image
# under the local vision model's token budget). Only the manga page formats.
image = { version = "0.25", default-features = false, features = ["jpeg", "png", "webp"] }
axum-extra = { version = "0.9", features = ["cookie", "typed-header"] }
time = "0.3"
infer = "0.16"
tokio-util = { version = "0.7", features = ["io"] }
futures-core = "0.3"
futures-util = "0.3"
bytes = "1"
chromiumoxide = { version = "0.7", features = ["tokio-runtime", "_fetcher-rusttls-tokio"], default-features = false }
sysinfo = { version = "0.32", default-features = false, features = ["system", "component"] }
nix = { version = "0.29", features = ["fs"] }
scraper = "0.20"
reqwest = { version = "0.12", default-features = false, features = ["rustls-tls", "socks", "cookies", "stream", "json"] }
ocrs = "0.12"
rten = "0.24"
[dev-dependencies]
tempfile = "3"
tower = { version = "0.5", features = ["util"] }
http-body-util = "0.1"
mime = "0.3"
futures-util = "0.3"
tokio = { version = "1", features = ["test-util"] }
# Trim debug builds: keep line numbers in panics / backtraces but drop the
# full DWARF info (variable-level inspection in gdb/lldb). With a sqlx +
# axum + tokio dep tree the default ("full") leaves backend/target on the
# order of tens of GiB; this typically cuts ~5070% off that.
[profile.dev]
debug = "line-tables-only"
[profile.test]
debug = "line-tables-only"