9f56f283d4
Collapses the crawler to a single newest-first walker and replaces the N-consecutive-unchanged streak with a per-manga rule: stop on the first manga where metadata is Unchanged AND chapter sync reports zero new chapters. The early stop is gated by a per-source recovery flag stored in `crawler_state` — set to `false` when a run starts, back to `true` only on a clean exit (end-of-walk or intentional stop). A crashed run leaves the flag `false` automatically (no shutdown code runs), so the next tick walks the full catalog instead of bailing at the first caught-up manga. This means a crashed mid-walk run self-heals on the next tick: the flag stays `false`, the next walk visits every page (recovering anything the crash missed past its crash point), and steady state resumes once the recovery sweep reaches end-of-walk. Removed: - DiscoverMode enum, Backfill mode, the boundary re-check + displaced-refs machinery in TargetSourceWalker. - Drop-pass (mark_dropped_mangas) and seed-completion plumbing (mark_seed_completed / seed_completed_at). The recovery flag subsumes the seed-completion signal; drop detection was explicitly opted out. - JobPayload::Discover (no production callers). - CRAWLER_MODE / CRAWLER_INCREMENTAL_STOP_AFTER env vars and the CrawlerModePref config type. `should_mark_clean_exit(walked_to_completion, hit_stop_condition)` encodes the clean-exit truth table in its signature — `hit_limit` is deliberately absent so a future edit cannot accidentally count a caller-imposed cap as a clean exit. Net -501 lines, 261 backend tests passing. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
58 lines
1.6 KiB
TOML
58 lines
1.6 KiB
TOML
[package]
|
|
name = "mangalord"
|
|
version = "0.36.0"
|
|
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"
|
|
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 }
|
|
scraper = "0.20"
|
|
reqwest = { version = "0.12", default-features = false, features = ["rustls-tls", "socks", "cookies", "stream"] }
|
|
|
|
[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"] }
|