path: root/.ai/scripts/flashcard-to-anki.py

#!/usr/bin/env -S uv run --script
# /// script
# requires-python = ">=3.11"
# dependencies = [
#   "genanki>=0.13",
# ]
# ///
"""Convert an org-drill file into an Anki .apkg deck.

Parses org-drill structure:
  - Top-level "* Section" headings become tags on every card under them.
  - Each "** Card name :drill:" entry becomes a card. Front = heading
    text (sans :drill: tag). Back = entry body with newlines converted
    to <br>.

Deck name defaults to the input basename, case preserved. Deck and model
IDs are derived from the deck name via stable hash so re-importing the
same deck updates existing cards instead of duplicating them.

Output defaults to ~/sync/phone/anki/<input-basename>.apkg. The .apkg is
a mobile-Anki artifact the phone picks up from its sync dir, so it lands
there rather than next to the org source.

Usage:
  flashcard-to-anki.py <input.org>
  flashcard-to-anki.py <input.org> --deck "My Deck Name"
  flashcard-to-anki.py <input.org> --output /path/to/deck.apkg

Requires genanki, which uv resolves automatically via the PEP 723
script metadata above. No venv or system install needed.
"""
from __future__ import annotations

import argparse
import hashlib
import re
import sys
from pathlib import Path

import genanki

# 32-bit integer space genanki accepts. Start above the conventional
# "user model" floor so collisions with hand-written decks stay
# unlikely.
ID_BASE = 1_500_000_000
ID_RANGE = 500_000_000


def stable_id(name: str, salt: str) -> int:
    """Derive a deterministic 32-bit id from `name` and a `salt`.

    Same (name, salt) pair always returns the same id, so re-running
    against the same source produces a stable deck/model id pair and
    Anki imports update existing cards in place rather than duplicating.
    """
    h = hashlib.sha256(f"{salt}:{name}".encode()).hexdigest()
    return ID_BASE + (int(h[:8], 16) % ID_RANGE)


def make_model(deck_name: str) -> genanki.Model:
    return genanki.Model(
        stable_id(deck_name, "model"),
        f"{deck_name} (Craig)",
        fields=[{"name": "Front"}, {"name": "Back"}],
        templates=[
            {
                "name": "Card 1",
                "qfmt": "{{Front}}",
                "afmt": '{{FrontSide}}<hr id="answer">{{Back}}',
            }
        ],
        css=(
            ".card { font-family: sans-serif; font-size: 18px; "
            "color: #222; background: #fafafa; line-height: 1.45; }\n"
            "hr#answer { margin: 14px 0; }\n"
        ),
    )


def section_to_tag(title: str) -> str:
    return re.sub(r"[^a-z0-9]+", "-", title.lower()).strip("-")


def escape_html(s: str) -> str:
    return (
        s.replace("&", "&amp;")
        .replace("<", "&lt;")
        .replace(">", "&gt;")
    )


def strip_org_metadata(body_lines: list[str]) -> list[str]:
    """Drop :PROPERTIES: drawers, planning lines, and created-date lines.

    Org-drill needs these in the source file (SRS state lives in the
    PROPERTIES drawer; SCHEDULED carries the next-review date), but they
    are noise on the back of an Anki card. A created/added date never
    belongs on a card, so a stray "Created:" or ":CREATED:" body line is
    dropped too.
    """
    cleaned: list[str] = []
    in_drawer = False
    planning_re = re.compile(r"^\s*(SCHEDULED|DEADLINE|CLOSED):\s")
    created_re = re.compile(r"^\s*:?created:?\s", re.IGNORECASE)
    drawer_start_re = re.compile(r"^\s*:PROPERTIES:\s*$")
    drawer_end_re = re.compile(r"^\s*:END:\s*$")
    for line in body_lines:
        if in_drawer:
            if drawer_end_re.match(line):
                in_drawer = False
            continue
        if drawer_start_re.match(line):
            in_drawer = True
            continue
        if planning_re.match(line) or created_re.match(line):
            continue
        cleaned.append(line)
    return cleaned


def parse(org_text: str) -> list[tuple[str, str, str]]:
    """Return [(front, back_html, tag), ...] for every :drill: card."""
    cards: list[tuple[str, str, str]] = []
    current_section: str | None = None

    section_re = re.compile(r"^\*\s+(.+?)\s*$")
    card_re = re.compile(r"^\*\*\s+(.+?)\s+:drill:\s*$")

    lines = org_text.splitlines()
    i = 0
    while i < len(lines):
        line = lines[i]

        sec = section_re.match(line)
        if sec:
            current_section = sec.group(1).strip()
            i += 1
            continue

        card = card_re.match(line)
        if card:
            front = card.group(1).strip()
            body_lines: list[str] = []
            i += 1
            while i < len(lines):
                nxt = lines[i]
                if nxt.startswith("* ") or card_re.match(nxt):
                    break
                body_lines.append(nxt)
                i += 1
            body_lines = strip_org_metadata(body_lines)
            while body_lines and not body_lines[0].strip():
                body_lines.pop(0)
            while body_lines and not body_lines[-1].strip():
                body_lines.pop()
            back_html = "<br>".join(escape_html(ln) for ln in body_lines)
            tag = section_to_tag(current_section) if current_section else "drill"
            cards.append((front, back_html, tag))
            continue

        i += 1

    return cards


def build(cards: list[tuple[str, str, str]], deck_name: str) -> genanki.Deck:
    deck = genanki.Deck(stable_id(deck_name, "deck"), deck_name)
    model = make_model(deck_name)
    for front, back, tag in cards:
        note = genanki.Note(
            model=model,
            fields=[front, back],
            tags=[tag],
            guid=genanki.guid_for(front),
        )
        deck.add_note(note)
    return deck


def default_deck_name(input_path: Path) -> str:
    return input_path.stem


def default_output_path(input_path: Path) -> Path:
    anki_dir = Path.home() / "sync" / "phone" / "anki"
    return anki_dir / f"{input_path.stem}.apkg"


def main() -> int:
    parser = argparse.ArgumentParser(
        description="Convert an org-drill file into an Anki .apkg deck.",
    )
    parser.add_argument(
        "input",
        type=Path,
        help="Path to the org-drill source file.",
    )
    parser.add_argument(
        "--deck",
        help="Deck name. Defaults to the input basename.",
    )
    parser.add_argument(
        "--output",
        type=Path,
        help="Output .apkg path. Defaults to "
             "~/sync/phone/anki/<input-basename>.apkg.",
    )
    args = parser.parse_args()

    input_path: Path = args.input.expanduser().resolve()
    if not input_path.is_file():
        print(f"error: {input_path} not found", file=sys.stderr)
        return 1

    org_text = input_path.read_text(encoding="utf-8")
    deck_name = args.deck or default_deck_name(input_path)
    output_path: Path = (args.output or default_output_path(input_path)).expanduser().resolve()
    output_path.parent.mkdir(parents=True, exist_ok=True)

    cards = parse(org_text)
    if not cards:
        print(f"error: no :drill: cards found in {input_path}", file=sys.stderr)
        return 1

    deck = build(cards, deck_name)
    genanki.Package(deck).write_to_file(str(output_path))
    print(f"wrote {output_path} ({len(cards)} cards, deck '{deck_name}')")
    return 0


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