FabledGrimoire/src/scribe/services/design_rulebook_import.py

"""Design-system expectations — turning rulebook prose into checkable claims.

Milestone #251 step 2. The drift panel compares what the design rulebook SAYS
against what the stylesheet and components actually DO. This module owns the
first half: reading a rulebook's rules and extracting the claims that can be
mechanically checked.

WHY THIS LIVES SERVER-SIDE. The frontend has no test runner — `vue-tsc --noEmit`
is the entire check — and this is the one genuinely fiddly piece of the feature.
Extraction happens here where pytest can assert on it; the comparison itself is
set arithmetic and stays in the browser, where the live token values are.

WHY NOT NLP. Rule statements are prose written for humans, and they should stay
that way — they are read by people far more often than they are parsed. So this
extracts only what is unambiguous in ANY prose: the hex colours and CSS custom
property names a rule mentions. Everything subtler (padding scales, type ramps)
needs a rule author to opt into a structured form, which is deliberately left for
when someone wants it rather than invented up front.

RULE #115. Nothing here assumes a design rulebook exists, or that it is this
operator's. An install designates one; an install that hasn't gets an empty
result and a panel that explains itself.
"""
from __future__ import annotations

import logging
import re
from dataclasses import dataclass, field

from scribe.models.rulebook import Rule
from scribe.services.settings import get_setting

logger = logging.getLogger(__name__)

# Which rulebook describes this install's design system. A plain setting rather
# than a column: no migration, discoverable in the Settings UI (rule #25), and
# honest about being a per-install choice rather than a property of the rulebook.
DESIGN_RULEBOOK_SETTING = "design_rulebook_id"

# `#abc` and `#aabbcc`, plus the 4/8-digit alpha forms.
_HEX = re.compile(r"#([0-9a-fA-F]{3,8})\b")

# A custom-property name as written in prose, including the slash shorthand the
# rulebook uses: `--fs-radius-sm/md/lg/xl`, `--fs-obsidian/iron/slate/pewter`.
_TOKEN = re.compile(r"(--[a-zA-Z][\w-]*(?:/[\w-]+)*)")

# Sentence-ish split. Rules use semicolons as hard breaks as often as periods.
_SENTENCE_SPLIT = re.compile(r"(?<=[.;])\s+|\n+")

# Negation markers. Checked PER SENTENCE, which is the whole trick — see
# _extract_from_sentence.
_NEGATIONS = ("never", "not ", "no ", "avoid", "don't", "must not", "excluded")


@dataclass
class Expectation:
    """One mechanically-checkable claim a rule makes."""

    kind: str          # "token" | "color" | "prohibited_color"
    value: str         # "--fs-obsidian" | "#14171a"
    rule_id: int
    rule_title: str
    context: str       # the sentence it came from, for showing your work

    def as_dict(self) -> dict:
        return {
            "kind": self.kind,
            "value": self.value,
            "rule_id": self.rule_id,
            "rule_title": self.rule_title,
            "context": self.context,
        }


@dataclass
class ExpectationSet:
    rulebook_id: int | None = None
    expectations: list[Expectation] = field(default_factory=list)

    def as_dict(self) -> dict:
        return {
            "rulebook_id": self.rulebook_id,
            "expectations": [e.as_dict() for e in self.expectations],
        }


def normalize_hex(value: str) -> str | None:
    """Fold a hex colour to a comparable form, or None if it isn't one.

    Load-bearing for the whole comparison: the rulebook writes `#FFFFFF` and the
    code writes `#fff`, and those must compare equal or the single largest drift
    finding (#2275) reads as zero. Expands 3-digit shorthand and lowercases.

    Alpha forms (4 and 8 digit) keep their alpha — `#fff` and `#ffff` are not the
    same colour, and silently dropping the alpha would invent equality.
    """
    match = _HEX.fullmatch(value.strip()) or _HEX.match(value.strip())
    if not match:
        return None
    digits = match.group(1).lower()
    if len(digits) in (3, 4):
        digits = "".join(c * 2 for c in digits)
    if len(digits) not in (6, 8):
        return None
    return f"#{digits}"


def expand_token_shorthand(raw: str) -> list[str]:
    """`--fs-radius-sm/md/lg/xl` -> the four names it stands for.

    The rulebook writes token families in a slash shorthand, and both forms it
    uses expand correctly under one rule: take everything up to and including the
    LAST hyphen of the first segment as the prefix, then append each alternative.

        --fs-radius-sm/md/lg/xl        prefix `--fs-radius-`  -> sm, md, lg, xl
        --fs-obsidian/iron/slate       prefix `--fs-`         -> obsidian, iron, slate
        --fs-dur-fast/base/slow        prefix `--fs-dur-`     -> fast, base, slow

    A name with no slash is returned as-is.
    """
    if "/" not in raw:
        return [raw]
    head, *rest = raw.split("/")
    cut = head.rfind("-")
    if cut <= 1:                      # no hyphen beyond the leading `--`
        return [head, *rest]
    prefix = head[: cut + 1]
    return [head, *[f"{prefix}{part}" for part in rest if part]]


def _is_negated(sentence: str) -> bool:
    return any(marker in sentence.lower() for marker in _NEGATIONS)


def _extract_from_sentence(sentence: str, rule: Rule) -> list[Expectation]:
    """Claims in ONE sentence, with negation scoped to that sentence.

    Sentence scope is what makes the prohibition detection usable. Rule 52 reads:

        "Text tokens: Parchment #E8E4D8 …, Vellum #C2BFB4 …, Ash #9C9A92 ….
         Pure white #FFFFFF is NEVER used as text color."

    Three colours the palette REQUIRES and one it FORBIDS, in one statement.
    Detecting negation across the whole statement would mark all four as
    forbidden; detecting it per sentence gets all four right.
    """
    out: list[Expectation] = []
    negated = _is_negated(sentence)

    for match in _HEX.finditer(sentence):
        value = normalize_hex(match.group(0))
        if not value:
            continue
        out.append(Expectation(
            kind="prohibited_color" if negated else "color",
            value=value,
            rule_id=int(rule.id),
            rule_title=rule.title,
            context=sentence.strip(),
        ))

    # Token names are not negated in practice — a rule says which tokens should
    # exist, never which must not — so they are recorded as expectations
    # regardless. If that ever changes, it needs its own kind rather than
    # borrowing the colour one.
    for match in _TOKEN.finditer(sentence):
        for name in expand_token_shorthand(match.group(1)):
            out.append(Expectation(
                kind="token",
                value=name,
                rule_id=int(rule.id),
                rule_title=rule.title,
                context=sentence.strip(),
            ))

    return out


def extract_expectations(rules: list[Rule]) -> list[Expectation]:
    """Every checkable claim across a set of rules, deduped on (kind, value).

    First occurrence wins so the reported rule is the one that introduced the
    claim, which is usually the most specific place to send a reader.
    """
    seen: set[tuple[str, str]] = set()
    out: list[Expectation] = []
    for rule in rules:
        text = " ".join(filter(None, [rule.statement or "", rule.how_to_apply or ""]))
        for sentence in _SENTENCE_SPLIT.split(text):
            if not sentence.strip():
                continue
            for expectation in _extract_from_sentence(sentence, rule):
                key = (expectation.kind, expectation.value)
                if key in seen:
                    continue
                seen.add(key)
                out.append(expectation)
    return out


async def get_design_rulebook_id(user_id: int) -> int | None:
    """The rulebook this install designated as its design system, if any."""
    raw = (await get_setting(user_id, DESIGN_RULEBOOK_SETTING, "")).strip()
    if not raw:
        return None
    try:
        value = int(raw)
    except (TypeError, ValueError):
        return None
    return value if value > 0 else None


async def design_expectations(user_id: int) -> ExpectationSet:
    """Checkable claims from the designated design rulebook.

    Returns an empty set when no rulebook is designated — the normal case for
    any install but the one that set it up (rule #115). The caller shows an
    explanatory empty state rather than treating this as an error.
    """
    rulebook_id = await get_design_rulebook_id(user_id)
    if rulebook_id is None:
        return ExpectationSet()

    from scribe.services import rulebooks as rulebooks_svc

    try:
        rules = await rulebooks_svc.list_rules(user_id, rulebook_id=rulebook_id)
    except Exception:
        logger.warning("Design rulebook %s could not be read", rulebook_id, exc_info=True)
        return ExpectationSet(rulebook_id=rulebook_id)

    return ExpectationSet(rulebook_id=rulebook_id, expectations=extract_expectations(rules))