[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[project]
name = "llm-ingestion-okf"
version = "0.5.0a2"
description = "Shared OKF (Open Knowledge Format) ingestion library: spec-based connectors, bundle inbox, and external-bundle import, with security delegated to llm-ingestion-guard."
readme = "README.md"
license = "MIT"
requires-python = ">=3.10"
authors = [{ name = "Kjell Tore Guttormsen" }]
classifiers = [
    "Development Status :: 2 - Pre-Alpha",
    "Intended Audience :: Developers",
    "Operating System :: OS Independent",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.10",
]
# Exactly one runtime dependency, ever: the security boundary. Everything
# else is stdlib. The version range is the real pin — it resolves normally
# against a package index, and is satisfied today by the git+https tag
# install documented in the README (a direct reference is an install-time
# channel, not a dependency declaration).
dependencies = ["llm-ingestion-guard>=0.3,<0.4"]

[project.optional-dependencies]
# Binary file-type extraction parsers. OPT-IN ONLY: this extra pulls binary
# wheels (pillow, pypdfium2) and a transitive tree that core must never have —
# the "exactly one runtime dependency" rule above covers the default install,
# and this extra is outside it by construction.
#
# `pdf` only. `docx`/`xlsx` remain fail-fast: the extra names the parsers it
# actually ships, so a consumer installing it gets what the error message
# promised and nothing else.
#
# WHY pdfplumber, and why the floor is not free (measured 2026-08-21,
# docs/2026-08-21-g2-pdf-extraction-measurement.md): on a real Vegnormalene
# requirement table pdfplumber keeps 4 of 4 rows with label and value on the
# same line; pypdf, pdfminer.six and pymupdf each keep 0 of 4, emitting all
# labels then all values, which a downstream reader can only re-pair by
# guessing. In a `krav` document that is a wrong answer that looks right.
# pymupdf is additionally out on LICENSE (AGPL-3.0 or commercial) — this
# package is MIT and an extra must not hand a consumer copyleft they did not
# choose.
#
# PARSER VERSION IS PART OF THE OUTPUT CONTRACT. pdfplumber pins
# `pdfminer.six==20260107` exactly, and pdfminer.six ships date-stamped
# releases with no stability contract. Extraction is deterministic WITHIN a
# parser version (measured, 5 configurations) and NOT guaranteed across one.
# `tests/test_extract.py` holds that promise against a committed fixture, so
# widening this range makes a test go red instead of letting extracted text
# drift silently. See tests/fixtures/README.md.
extract = ["pdfplumber>=0.11.10,<0.12"]

[dependency-groups]
dev = ["pytest>=8", "mypy>=1.14", "ruff>=0.9"]

[tool.hatch.build.targets.wheel]
packages = ["src/llm_ingestion_okf"]

[tool.ruff]
line-length = 100
target-version = "py310"

[tool.mypy]
strict = true
python_version = "3.10"

# llm-ingestion-guard ships no py.typed marker, so its symbols arrive as Any.
# The adapter coerces every value it carries across the seam to a concrete
# type, which is what keeps --strict meaningful on this side of it.
[[tool.mypy.overrides]]
module = ["llm_ingestion_guard", "llm_ingestion_guard.*"]
ignore_missing_imports = true

# Install CHANNEL for the guard, which is not on a package index yet. It is
# uv-specific, and it reaches further than a dev-only setting: measured
# 2026-07-25, a consumer installing this package from git WITH UV picks the
# guard up from this tag automatically, because uv reads this file when it
# builds from the source tree. pip does not read it — it resolves
# [project.dependencies] alone and fails with "No matching distribution found
# for llm-ingestion-guard" until the guard is installed from its own tag first
# (README). Either way the range above stays the pin: the built wheel carries
# `Requires-Dist: llm-ingestion-guard<0.3,>=0.2`, verified against the wheel.
[tool.uv.sources]
llm-ingestion-guard = { git = "https://git.fromaitochitta.com/open/llm-ingestion-pipeline-security.git", tag = "v0.3.4" }