Files
Mangalord/backend/Cargo.toml
MechaCat02 25aba3ac58 feat(analysis): position-aware OCR seam dedup for sliced pages
Boundary text duplicated across slices (often with slightly different,
cropped transcriptions) survived the text-only merge. The OCR pass now
asks for a per-piece vertical position and the merge uses it:

- OcrResult gains optional `y` (fraction 0..1 of the slice); the Pass-A
  OCR schema/prompt request it (combined path leaves it None). Not
  persisted.
- merge_ocr takes each slice's working-image y-band and maps `y` to a
  page-global position. A seam pair is a duplicate when position-close
  (same kind) OR text-similar, so a mis-OCR'd boundary line is caught even
  when the text differs. The kept copy is the one more central in its slice
  (less cropped); falls back to keep-longer when positions are missing.
- Self-calibrates the model's y values (pixels vs. fraction) and ignores
  degenerate columns, so a bad localizer can't over-merge.

Tests: position pairs differing texts and keeps the less-cropped copy;
text-only fallback (dedup/keep-longer/non-adjacent/order) still holds.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-13 23:17:55 +02:00

73 lines
2.3 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 = "0.79.0"
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"
# 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"] }
nix = { version = "0.29", features = ["fs"] }
scraper = "0.20"
reqwest = { version = "0.12", default-features = false, features = ["rustls-tls", "socks", "cookies", "stream", "json"] }
[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"