"""Heuristic page classifier for Boots Production Packs.

Tags each page of a multi-page production pack with a `page_type` so the
dispatcher can:

  • run the same QC checks on every page (the user wants cover-page logo /
    typography / brand-name compliance to be QC'd, not skipped)
  • flag non-artwork pages as exempt from the strict-grade override
    (a cover page with no offer roundel shouldn't tank the overall grade
    just because `boots_offer_mechanics` finds nothing to evaluate)

Categories observed across the 10 sample packs in
`/Users/nickviljoen/Desktop/AI_QC_Bitbucket/boots/PPacks to Test/`:

    cover      — title page: "Production Pack / P7B IMODIUM / 21.11.25"
    checklist  — asset suitability tick-list ("Asset suitable", "Fonts present", ...)
    palette    — creative-guidance colour spec page (CMYK / RGB / Hex blocks)
    notes      — copywriter / yellow-notes commentary page
    artwork    — actual ad layout (default — anything that isn't one of the above)

Only `artwork` counts towards strict-grade Pass/Fail. Everything else is
informational. The classifier never raises — unknown pages default to
`artwork` because false positives there are recoverable (an extra check
on a cover page just produces an N/A score) whereas missing artwork is not.
"""

from __future__ import annotations

import re
from typing import Dict, List


PAGE_TYPES = ('cover', 'checklist', 'palette', 'notes', 'artwork')


# ── Regex patterns derived from observed text on the 10 sample packs ──────────
# These are intentionally conservative — they only fire when the page is
# unambiguously one of the admin types. Anything fuzzy falls through to artwork.

_RE_PRODUCTION_PACK_TITLE = re.compile(r'\bProduction Pack\b', re.IGNORECASE)
_RE_VERSION_LINE = re.compile(r'^\s*Version\s+\d+\s*$', re.IGNORECASE | re.MULTILINE)
_RE_JOB_NUMBER = re.compile(r'\bJob number:\s*\d', re.IGNORECASE)

# Asset checklist markers — the suitability tick-list
_CHECKLIST_TOKENS = (
    'Asset suitable', 'Assets suitable',
    'Fonts present',
    'Resolution fine',
    'Print ready asset',
    'Asset low res',
    'Supplied visual',
    'More info required',
    'Content complete',
    'Colours resolved',
    'IS PACK A',  # appears on No7 Bundle Wobbler P9 cover/checklist combo
)

# Creative guidance / colour palette markers
_PALETTE_TOKENS = ('CMYK', 'RGB', 'Hexadecimal')
_RE_HEX_COLOUR = re.compile(r'#[0-9a-fA-F]{6}\b')

# Copywriter / yellow-notes markers
_RE_YELLOW_NOTES = re.compile(r'\bYellow Notes\b', re.IGNORECASE)
_RE_CLIENT_QUERIES = re.compile(r'\bCLIENT QUERIES\b', re.IGNORECASE)

# Strong artwork signals — text that only appears on real ad layouts.
# Used to override notes/checklist classification when an artwork page
# happens to include a Yellow Notes footer or a supplied-assets sidebar.
_RE_PRICE = re.compile(r'£\s*\d')
_RE_OFFER_MECHANIC = re.compile(
    r'\b(?:3\s*FOR\s*2|BOGOF|2\s*FOR\s*£|BUY\s+\d|FREE|GIFT|MULTIBUY)\b',
    re.IGNORECASE,
)
_RE_OFFER_DATES = re.compile(r'\bOffer valid (?:from|on)\b', re.IGNORECASE)
_RE_CLICK_COLLECT = re.compile(r'\bClick\s*&\s*Collect\b', re.IGNORECASE)
_RE_GSL_BARCODE = re.compile(r'\bGSL\b\s*\d', re.IGNORECASE)


def _has_artwork_signals(text: str) -> bool:
    """True if the page contains at least one strong artwork-only signal."""
    return any(rx.search(text) for rx in (
        _RE_PRICE,
        _RE_OFFER_MECHANIC,
        _RE_OFFER_DATES,
        _RE_CLICK_COLLECT,
        _RE_GSL_BARCODE,
    ))


def classify_page(page: Dict) -> str:
    """Classify a single ingested page dict.

    Decision order:
        1. Strong palette match (multi-token + hex colours) → palette
        2. Strong checklist match (≥3 suitability tokens) → checklist
        3. Pages that pass _has_artwork_signals() → artwork
           (catches Maybelline p5 that has Yellow Notes footer + T&Cs)
        4. Yellow Notes / Client Queries with no artwork signals → notes
        5. Sparse Production Pack title block → cover (covers brief / context too)
        6. Fallthrough → artwork

    Strong palette/checklist precede artwork signals because some palette
    and checklist pages render thumbnail previews of the artwork (e.g.
    Nicorette's "£3 off offer ellipse" sample on the palette page) that
    otherwise look like artwork.

    Defaults to 'artwork' on any uncertainty — false positives there are
    cheap (an N/A score on a non-applicable check) whereas missing artwork
    means a real compliance issue would slip through.
    """
    text = (page.get('raw_text') or '').strip()
    if not text:
        return 'artwork'

    # ── 1. Palette ────────────────────────────────────────────────────────
    palette_tokens_found = sum(1 for tok in _PALETTE_TOKENS if tok in text)
    hex_count = len(_RE_HEX_COLOUR.findall(text))
    if palette_tokens_found >= 3 and hex_count >= 2:
        return 'palette'
    # Looser palette match for short palette pages with only one swatch
    if palette_tokens_found >= 2 and hex_count >= 1 and 'COLOUR PALETTE' in text.upper():
        return 'palette'

    # ── 2. Checklist ──────────────────────────────────────────────────────
    checklist_tokens_found = sum(1 for tok in _CHECKLIST_TOKENS if tok in text)
    if checklist_tokens_found >= 3:
        return 'checklist'

    # ── 3. Artwork signals (T&Cs, offer mechanics, prices) ─────────────────
    if _has_artwork_signals(text):
        return 'artwork'

    # ── 4. Notes / client queries ─────────────────────────────────────────
    if _RE_YELLOW_NOTES.search(text) or _RE_CLIENT_QUERIES.search(text):
        return 'notes'

    # ── 5. Cover / brief / context page ───────────────────────────────────
    line_count = len([ln for ln in text.splitlines() if ln.strip()])
    if (
        line_count <= 15
        and _RE_PRODUCTION_PACK_TITLE.search(text)
        and _RE_VERSION_LINE.search(text)
        and _RE_JOB_NUMBER.search(text)
    ):
        return 'cover'

    # ── 6. Fallthrough ────────────────────────────────────────────────────
    return 'artwork'


def classify_pages(pages: List[Dict]) -> List[str]:
    """Classify every page in an ingest_pdf result. Returns parallel list."""
    return [classify_page(p) for p in pages]


def is_artwork(page_type: str) -> bool:
    """Convenience predicate for the strict-grade override."""
    return page_type == 'artwork'


# Human-readable labels for report rendering.
PAGE_TYPE_LABELS = {
    'cover': 'Cover',
    'checklist': 'Asset Checklist',
    'palette': 'Creative Guidance / Colour Palette',
    'notes': 'Yellow Notes',
    'artwork': 'Artwork',
}