#!/usr/bin/env python3
"""Generate frontal building plates from the local reference photography.

Each study takes one photograph we already hold (`Art/reference/`, gitignored) as
the geometric anchor and asks an image model to re-stage it as a clean **frontal
view of the building** — the whole elevation, the entrance in its facade, or the
building with its neighbours — evenly lit, no crowd, no staging, so the modelling
pass has something measurable instead of a tourist photo.

Deliberately **not** close-up detail crops: a doorway or cornice crop cannot be
measured for proportion, which is what the modelling pass actually needs.

    python3 Tools/gen/facade_detail_concepts.py --list
    python3 Tools/gen/facade_detail_concepts.py --only door-recess,parapet-motto
    python3 Tools/gen/facade_detail_concepts.py --all
    python3 Tools/gen/facade_detail_concepts.py --all --model google/gemini-2.5-flash-image

Output: `Art/reference/facade-details/<study>.png` plus a `<study>.refgen.json`
sidecar recording the model, the source photograph, the prompt and the SHA-256 of
the result. `Art/reference/` is gitignored, so **neither the images nor the
sidecars are committed** — they are local working material. The study list and
the tool are the committed part.

Design notes
------------
* Standard library only: the OpenRouter chat-completions call is `urllib`, and
  the returned `data:` URL is decoded with `base64` and written straight to disk.
* An existing output is never overwritten; `-v2`, `-v3` … are used instead, so
  re-running after a prompt edit keeps both studies comparable.
* Generation costs money, so it is never automatic: `--list` is free, and every
  generating run prints the model and the study count first.
* The token is read from `OPENROUTER_API_KEY` or the ignored `.env` and is never
  written to a sidecar or a log line.
"""

from __future__ import annotations

import argparse
import base64
import json
import os
import re
import sys
import time
import urllib.error
import urllib.request

ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", ".."))
REFERENCE_DIR = os.path.join(ROOT, "Art", "reference")
OUT_DIR = os.path.join(REFERENCE_DIR, "facade-details")
API_URL = "https://openrouter.ai/api/v1/chat/completions"
DEFAULT_MODEL = "google/gemini-2.5-flash-image"

# The instruction appended to every study. Kept identical to the sibling
# project's convention so the two sets stay comparable: the photograph fixes the
# geometry, the prompt only restages light, weather, people and surface.
ANCHOR_SUFFIX = (
    "Use the attached reference photograph as the source of the architecture: keep "
    "the building's proportions, storey count, column rhythm, band heights and "
    "signage placement exactly as photographed. You may REFRAME — step back across "
    "the street, zoom out or widen the field of view — so that the whole building "
    "fits in the frame from the pavement to the parapet; the reference is often "
    "cropped and the plate must not be. Keep the view exterior and frontal (or "
    "three-quarter where asked). Restage only lighting, weather, people and surface "
    "condition. Do not invent extra storeys, wings or ornaments, and do not change "
    "the architecture to fit the frame."
)

# name -> (reference photo relative to Art/reference/, what the plate must show)
#
# Verified framing (vision pre-check, 2026-11-09): the model follows the reference
# crop closely, so a plate is only as wide as its source photo. `building-entrance`
# and `building-street-front` come back as full-elevation frontal views; the studies
# anchored on the tightly cropped 2009 facade photo stay cropped, because the model
# will not invent the parapet and sky that the photograph does not contain. A full
# building plate for 6840 needs a full-elevation photograph, which the local set
# does not have (see Docs/reference-notes-hollywood.md).
#
# Every study asks for a *frontal view of a building*, not a crop of one detail:
# the whole elevation, the entrance in its facade, or the building together with
# its neighbours. Close-up framing is deliberately absent — a detail crop cannot
# be measured for proportion, which is what the modelling pass needs.
STUDIES: dict[str, tuple[str, str]] = {
    "building-front": (
        "hollywood/el-capitan-facade-day-wikimedia-2009-10-27.jpg",
        "A frontal view of the complete building shown in the reference "
        "photograph: the whole elevation from the pavement to the parapet fits in "
        "the frame with clear sky above the roofline and pavement below the ground "
        "floor, shot straight on and centred. Nothing may be cut off at the top or "
        "bottom. Even daylight, no crowd, no vehicles.",
    ),
    "building-entrance": (
        "el-capitan-entrance/01-hollywood-el-capitan-entrance.jpg",
        "A frontal view of the building in the reference photograph, framed so its "
        "street entrance is clearly visible as part of the facade — the doors and "
        "the wall around them in proportion, not a close-up of the doorway. "
        "Include the pavement in front. Even daylight, no crowd.",
    ),
    "building-with-neighbours": (
        "hollywood/el-capitan-theatre-blade-sign-day-wikimedia-2008-10.jpg",
        "A straight-on view of the street wall in the reference photograph: the "
        "building and its neighbouring buildings either side, each at full height "
        "from pavement to parapet with sky above, the joins between them visible, "
        "nothing cut off. Shot from across the road, parallel to the frontage. "
        "Even daylight, no crowd.",
    ),
    "building-street-front": (
        "hollywood/walk-of-fame-terrazzo-ovation-day-cc0-2019-06-20.jpg",
        "A frontal view along the pavement of the building in the reference "
        "photograph: the building's frontage seen from street level with its "
        "neighbours continuing either side and the pavement in the foreground. "
        "Straight on, even daylight, no crowd.",
    ),
    "building-front-oblique": (
        "hollywood/el-capitan-facade-day-wikimedia-2009-10-27.jpg",
        "A three-quarter view of the complete building in the reference "
        "photograph: the frontal elevation and one side visible together so the "
        "building's depth and mass read, with its neighbouring building at one "
        "edge. The whole building stays in frame. Even daylight, no crowd.",
    ),
    "theatre-front-with-neighbours": (
        "el-capitan-theater-detail/01-el-capitan-marquee.jpg",
        "A frontal view of the theatre in the reference photograph together with "
        "the buildings either side of it, the whole frontage and its full height "
        "in frame, shot from across the road. Even daylight, no crowd, marquee "
        "lettering blocked out as unreadable texture.",
    ),
}


def load_token() -> str:
    token = os.environ.get("OPENROUTER_API_KEY")
    if token:
        return token.strip()
    env_path = os.path.join(ROOT, ".env")
    if os.path.exists(env_path):
        with open(env_path, encoding="utf-8") as handle:
            for line in handle:
                line = line.strip()
                if line.startswith("OPENROUTER_API_KEY="):
                    return line.split("=", 1)[1].strip().strip('"').strip("'")
    raise SystemExit("no OpenRouter key: set OPENROUTER_API_KEY or add it to .env")


def build_prompt(study: str) -> str:
    """The full prompt for a study: its request plus the fixed anchor suffix."""
    if study not in STUDIES:
        raise KeyError(f"unknown study {study!r}; known: {sorted(STUDIES)}")
    return f"{STUDIES[study][1]}\n\n{ANCHOR_SUFFIX}"


def reference_path(study: str) -> str:
    return os.path.join(REFERENCE_DIR, STUDIES[study][0])


def missing_references() -> list[str]:
    """Studies whose source photograph is not present locally."""
    return [name for name in STUDIES if not os.path.isfile(reference_path(name))]


def next_free_path(study: str, directory: str = OUT_DIR) -> str:
    """`<study>.png`, or `<study>-v2.png`, `-v3` … if the name is taken."""
    base = os.path.join(directory, f"{study}.png")
    if not os.path.exists(base):
        return base
    index = 2
    while True:
        candidate = os.path.join(directory, f"{study}-v{index}.png")
        if not os.path.exists(candidate):
            return candidate
        index += 1


def data_url(path: str) -> str:
    suffix = os.path.splitext(path)[1].lower()
    mime = {".jpg": "image/jpeg", ".jpeg": "image/jpeg", ".png": "image/png"}.get(suffix)
    if not mime:
        raise SystemExit(f"unsupported reference type: {path}")
    with open(path, "rb") as handle:
        return f"data:{mime};base64,{base64.b64encode(handle.read()).decode('ascii')}"


def decode_image(payload: dict) -> bytes:
    """Extract the returned image bytes from a chat-completions payload."""
    message = (payload.get("choices") or [{}])[0].get("message", {})
    urls = [item.get("image_url", {}).get("url", "")
            for item in (message.get("images") or []) if isinstance(item, dict)]
    if not urls:
        match = re.search(r"data:image/[a-z]+;base64,[A-Za-z0-9+/=]+",
                          str(message.get("content") or ""))
        if match:
            urls.append(match.group(0))
    if not urls or not urls[0]:
        raise SystemExit(f"model returned no image data: {json.dumps(payload)[:400]}")
    url = urls[0]
    if url.startswith("data:"):
        return base64.b64decode(url.split(",", 1)[1])
    with urllib.request.urlopen(urllib.request.Request(url), timeout=120) as response:
        return response.read()


def generate(study: str, token: str, model: str, force: bool = False) -> str:
    """Generate one study; returns the written path. Never overwrites by default."""
    path = next_free_path(study)
    if force and os.path.exists(os.path.join(OUT_DIR, f"{study}.png")):
        path = os.path.join(OUT_DIR, f"{study}.png")
        # Write to a temp name then replace, so a failed call cannot destroy the
        # previous result.
        target = path + ".new"
    else:
        target = path

    body = {
        "model": model,
        "messages": [{
            "role": "user",
            "content": [
                {"type": "text", "text": build_prompt(study)},
                {"type": "image_url", "image_url": {"url": data_url(reference_path(study))}},
            ],
        }],
    }
    request = urllib.request.Request(
        API_URL,
        data=json.dumps(body).encode("utf-8"),
        headers={
            "Authorization": f"Bearer {token}",
            "Content-Type": "application/json",
            "HTTP-Referer": "https://git.allucanget.biz/zwitschi/gig-line",
            "X-Title": "gig-line facade details",
        },
        method="POST",
    )

    payload = None
    for attempt in range(3):
        try:
            with urllib.request.urlopen(request, timeout=180) as response:
                payload = json.load(response)
            break
        except urllib.error.HTTPError as exc:
            if exc.code == 429 or exc.code >= 500:
                wait = 5 * (attempt + 1)
                sys.stderr.write(f"  HTTP {exc.code}; retrying in {wait}s\n")
                time.sleep(wait)
                continue
            detail = exc.read().decode("utf-8", "replace")[:300]
            raise SystemExit(f"{study}: HTTP {exc.code} — {detail}")
        except urllib.error.URLError as exc:
            sys.stderr.write(f"  network error ({exc.reason}); retrying\n")
            time.sleep(5 * (attempt + 1))
    if payload is None:
        raise SystemExit(f"{study}: no response after retries")

    image = decode_image(payload)
    os.makedirs(OUT_DIR, exist_ok=True)
    with open(target, "wb") as handle:
        handle.write(image)
    if target != path:
        os.replace(target, path)

    import hashlib
    sidecar = {
        "study": study,
        "generated": os.path.basename(path),
        "generated_utc": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
        "model": model,
        "prompt": build_prompt(study),
        "reference": {
            "file": STUDIES[study][0],
            "note": "local reference photography; Art/reference is gitignored and never shipped",
        },
        "sha256": hashlib.sha256(image).hexdigest(),
        "bytes": len(image),
        "redistribution": "local development reference only; not committed, not shipped",
    }
    sidecar_path = os.path.splitext(path)[0] + ".refgen.json"
    with open(sidecar_path, "w", encoding="utf-8") as handle:
        json.dump(sidecar, handle, indent=2)
    if token in json.dumps(sidecar):
        raise SystemExit("refusing to write a sidecar containing the token")
    return path


def main(argv=None) -> int:
    ap = argparse.ArgumentParser(description=__doc__,
                                 formatter_class=argparse.RawDescriptionHelpFormatter)
    ap.add_argument("--list", action="store_true", help="list studies and exit (free)")
    ap.add_argument("--all", action="store_true", help="generate every study")
    ap.add_argument("--only", help="comma-separated study names")
    ap.add_argument("--model", default=DEFAULT_MODEL)
    ap.add_argument("--force", action="store_true",
                    help="replace the existing <study>.png instead of writing a -vN")
    args = ap.parse_args(argv)

    if args.list or not (args.all or args.only):
        missing = set(missing_references())
        print(f"{len(STUDIES)} studies; model {args.model}")
        for name, (ref, _prompt) in STUDIES.items():
            state = "MISSING reference" if name in missing else "ready"
            print(f"  {name:22} {state:18} <- {ref}")
        if missing:
            print(f"\n{len(missing)} study(ies) cannot run without their reference photograph.")
        return 0

    names = list(STUDIES) if args.all else [s.strip() for s in args.only.split(",") if s.strip()]
    unknown = [n for n in names if n not in STUDIES]
    if unknown:
        raise SystemExit(f"unknown study(ies): {unknown}; known: {sorted(STUDIES)}")
    blocked = [n for n in names if n in set(missing_references())]
    if blocked:
        raise SystemExit(f"missing reference photograph for: {blocked}")
    token = load_token()

    print(f"generating {len(names)} study(ies) with {args.model} -> {OUT_DIR}")
    for index, name in enumerate(names, 1):
        print(f"[{index}/{len(names)}] {name}")
        try:
            path = generate(name, token, args.model, force=args.force)
        except SystemExit as exc:
            sys.stderr.write(f"  FAILED: {exc}\n")
            continue
        print(f"  wrote {os.path.relpath(path, ROOT)}")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())