FabledScribe/tests/test_design_rulebook_import.py

"""Rulebook prose → checkable claims (milestone #251 step 2).

This is the piece of the design explorer that most needed to be testable, which
is why it lives in Python at all: the frontend has no test runner, so the fiddly
extraction happens server-side and the browser only does set arithmetic over it.

Rule text below is representative of a real design rulebook rather than copied
from this operator's — rule #115: the product must work for an install that has
none of their data, and a test that only passes against their exact wording would
be testing the instance, not the parser.
"""
from types import SimpleNamespace

from scribe.services.design_rulebook_import import (
    expand_token_shorthand,
    extract_expectations,
    normalize_hex,
)


def _rule(rule_id, title, statement, how_to_apply=None):
    return SimpleNamespace(
        id=rule_id, title=title, statement=statement, how_to_apply=how_to_apply
    )


# --- hex normalisation -------------------------------------------------------

def test_normalize_hex_makes_shorthand_and_case_comparable():
    """LOAD-BEARING. The rulebook writes `#FFFFFF` and components write `#fff`.
    If those don't compare equal, the single largest drift finding — 67 hardcoded
    white text colours (#2275) — reads as zero findings."""
    assert normalize_hex("#fff") == normalize_hex("#FFFFFF") == "#ffffff"
    assert normalize_hex("#E8E4D8") == "#e8e4d8"
    assert normalize_hex("#14171a") == "#14171a"


def test_normalize_hex_keeps_alpha_rather_than_inventing_equality():
    """`#fff` and `#ffff` are different colours. Dropping the alpha to make them
    match would manufacture agreement that isn't there."""
    assert normalize_hex("#ffff") == "#ffffffff"
    assert normalize_hex("#fff") != normalize_hex("#ffff")


def test_normalize_hex_rejects_non_colours():
    for junk in ("", "   ", "not-a-colour", "#", "#gg", "#12345"):
        assert normalize_hex(junk) is None


# --- the slash shorthand -----------------------------------------------------

def test_expand_token_shorthand_handles_every_form_a_rulebook_uses():
    """One rule expands all three shapes: take everything up to and including the
    LAST hyphen of the first segment as the prefix."""
    assert expand_token_shorthand("--fs-radius-sm/md/lg/xl") == [
        "--fs-radius-sm", "--fs-radius-md", "--fs-radius-lg", "--fs-radius-xl",
    ]
    # Prefix is just `--fs-` here, and the same rule finds it.
    assert expand_token_shorthand("--fs-obsidian/iron/slate/pewter") == [
        "--fs-obsidian", "--fs-iron", "--fs-slate", "--fs-pewter",
    ]
    assert expand_token_shorthand("--fs-dur-fast/base/slow") == [
        "--fs-dur-fast", "--fs-dur-base", "--fs-dur-slow",
    ]


def test_expand_token_shorthand_passes_plain_names_through():
    assert expand_token_shorthand("--fs-ease") == ["--fs-ease"]


# --- extraction --------------------------------------------------------------

def test_negation_is_scoped_to_the_sentence_not_the_rule():
    """THE trick that makes prohibition detection usable.

    A single rule routinely states what the palette REQUIRES and what it FORBIDS
    in consecutive sentences. Detecting negation across the whole statement would
    mark the required colours as forbidden too — inverting the finding rather
    than missing it, which is worse.
    """
    rule = _rule(
        52, "Text palette",
        "Text tokens: Parchment #E8E4D8 (primary), Vellum #C2BFB4 (secondary), "
        "Ash #9C9A92 (tertiary). Pure white #FFFFFF is NEVER used as text color.",
    )
    found = extract_expectations([rule])
    required = {e.value for e in found if e.kind == "color"}
    forbidden = {e.value for e in found if e.kind == "prohibited_color"}

    assert required == {"#e8e4d8", "#c2bfb4", "#9c9a92"}
    assert forbidden == {"#ffffff"}
    assert not (required & forbidden)


def test_token_names_are_extracted_and_expanded():
    rule = _rule(
        72, "CSS custom properties",
        "Expose the system as custom properties on :root — surfaces "
        "(--fs-obsidian/iron/slate/pewter), radius (--fs-radius-sm/md/lg/xl), "
        "and motion (--fs-ease).",
    )
    names = {e.value for e in extract_expectations([rule]) if e.kind == "token"}
    assert "--fs-obsidian" in names and "--fs-pewter" in names
    assert "--fs-radius-xl" in names
    assert "--fs-ease" in names
    assert len(names) == 9


def test_how_to_apply_is_read_as_well_as_the_statement():
    """Rulebooks routinely put the concrete values in how_to_apply and keep the
    statement declarative, so ignoring it would miss the checkable half."""
    rule = _rule(
        56, "Per-app accent", "Each app owns exactly one accent.",
        how_to_apply='[data-app="scribe"] #5B4A8A, [data-app="minstrel"] #4A6B5C.',
    )
    colours = {e.value for e in extract_expectations([rule]) if e.kind == "color"}
    assert colours == {"#5b4a8a", "#4a6b5c"}


def test_claims_are_deduped_across_rules_keeping_the_first_source():
    """A colour named by several rules is one expectation, attributed to the rule
    that introduced it — usually the most specific place to send a reader."""
    rules = [
        _rule(51, "Surfaces", "Obsidian #14171A is the page background."),
        _rule(99, "Elsewhere", "Obsidian #14171A again, mentioned in passing."),
    ]
    found = [e for e in extract_expectations(rules) if e.kind == "color"]
    assert len(found) == 1
    assert found[0].rule_id == 51


def test_prose_with_nothing_checkable_yields_nothing():
    """Most rules are judgement, not specification. They must contribute no
    findings rather than a shrug — a panel that reports unparseable rules as
    problems would be unusable."""
    rule = _rule(
        68, "Voice and tone",
        "Voice is understated: plain language for anything functional, flavour "
        "only where the user is waiting or failing. Be brief.",
    )
    assert extract_expectations([rule]) == []


def test_every_expectation_carries_the_sentence_it_came_from():
    """The panel has to show its working — "the rulebook says X" is only
    actionable if you can see where, and in what context.

    Asserts the context is the SENTENCE, not the whole statement: a rule that
    states a requirement and a prohibition in consecutive sentences would
    otherwise attribute both to the same undifferentiated blob of prose.
    """
    rule = _rule(63, "Radius", "Radius: Small 4px. Pure white #FFFFFF is never used.")
    found = extract_expectations([rule])
    assert len(found) == 1

    only = found[0]
    assert only.kind == "prohibited_color"
    assert only.rule_id == 63
    assert only.rule_title == "Radius"
    assert only.context == "Pure white #FFFFFF is never used."
    assert "Radius: Small 4px" not in only.context