stack/src/lead/review/codes.py

"""The five LEAD strands and the decision vocabulary the gate already uses."""

from __future__ import annotations

import re

PROJECTS = (
    "lead-history",
    "lead-limits",
    "lead-scan",
    "lead-precursors",
    "lead-external",
)
DECISIONS = ("include", "exclude", "uncertain")
STAGES = ("title_abstract", "full_text")
PASSES = (1, 2)

# Same sizes prisma.calibrate.sized enforces. A test pins the two.
GATE = {"title_abstract": 200, "full_text": 50}

_CODE = re.compile(r"`([a-z0-9-]+)`")


def reason_codes(project: str) -> tuple[str, ...]:
    """Exclusion codes from that strand's codebook, in codebook order."""
    from prisma.project import STARTERS

    if project not in PROJECTS:
        raise ValueError(project)
    text = STARTERS[project][2]
    return tuple(dict.fromkeys(_CODE.findall(text)))


def criteria(project: str) -> str:
    """The strand's inclusion criteria, as the anchor note would show them."""
    from prisma.project import STARTERS

    if project not in PROJECTS:
        raise ValueError(project)
    return STARTERS[project][0]


def reasons(project: str) -> str:
    """The strand's exclusion codebook."""
    from prisma.project import STARTERS

    if project not in PROJECTS:
        raise ValueError(project)
    return STARTERS[project][2]