[package]
name = "kebab-parse-pdf"
version       = { workspace = true }
edition       = { workspace = true }
rust-version  = { workspace = true }
license       = { workspace = true }
repository    = { workspace = true }
description   = "Text PDF extractor + scanned-page image extract helpers for the kebab pipeline (P7-1 + v0.20.0 sub-item 1)"

[dependencies]
kebab-core   = { path = "../kebab-core" }
anyhow       = { workspace = true }
serde_json   = { workspace = true }
time         = { workspace = true }
tracing      = { workspace = true }
# Per-page text extraction. `lopdf::Document::extract_text(&[page])`
# is the only stable per-page API across the pdf-extract / lopdf
# pair (pdf-extract 0.7 still exposes only whole-document calls).
# pdf-extract is intentionally NOT pulled in here — its ~150 transitive
# crates (pom, postscript, type1-encoding-parser, …) buy us nothing
# at v1 (we don't call its whole-doc API), and the future scanned-PDF
# OCR fallback can re-add it when it actually needs it.
lopdf        = { workspace = true }
# Page rasterization for scanned PDFs (issue #232). `dynamic_bindings`
# only: pdfium ships as a shared library and publishes no static build,
# so linking it would end kebab's single-binary property. The renderer
# binds at run time instead — present and every scanned PDF is covered,
# absent and ingest falls back to the DCTDecode passthrough below.
# Default features are off because they pull the `libloading`-free
# static path we deliberately do not use.
pdfium-render = { version = "0.9", default-features = false, features = [
    "image_025",
    "pdfium_latest",
    "thread_safe",
] }
image        = { version = "0.25", default-features = false, features = ["png"] }

[dev-dependencies]
anyhow            = { workspace = true }
blake3            = { workspace = true }
kebab-parse-image = { path = "../kebab-parse-image" }
strsim            = "0.11"
# `tests/page_render.rs` decodes a render back to check its dimensions.
image             = { version = "0.25", default-features = false, features = ["png"] }

[lints]
workspace = true