content-atom/stage3/compositions.py

#!/usr/bin/env python3
"""
MVP stage 3: compositions — сборка выходов из атомов.

Собирает composition (пост/рассылку) из атомов по рецепту:
- hook (цепляющий заголовок) → stat (доказательство) → cta (призыв к действию)
- порядок атомов задаётся recipe (JSONB)

Запись в compositions + atom_ids.

Запуск:
    python3 stage3/compositions.py --channel telegram --project rabota-ufa
    python3 stage3/compositions.py --channel newsletter --project rabota-ufa
"""

import argparse
import json
import os
import sys
import time
import uuid

import psycopg2

POSTGRES = {
    "host": os.environ.get("POSTGRES_HOST", "127.0.0.1"),
    "port": int(os.environ.get("POSTGRES_PORT", "5434")),
    "user": os.environ.get("POSTGRES_USER", "atom"),
    "dbname": os.environ.get("POSTGRES_DB", "content_atom"),
    "password": os.environ.get("POSTGRES_PASSWORD", "atompass123"),
}


def get_conn():
    return psycopg2.connect(**POSTGRES)


def get_project_id(conn, project: str) -> str:
    with conn.cursor() as cur:
        cur.execute("SELECT id FROM projects WHERE slug=%s", (project,))
        row = cur.fetchone()
        if row:
            return row[0]
        cur.execute(
            "INSERT INTO projects (slug, name, kind, role, status) VALUES (%s, %s, 'site', 'satellite', 'active') RETURNING id",
            (project, project),
        )
        return cur.fetchone()[0]


def get_atoms(conn, project_id: str) -> list[dict]:
    """Атомы по типам для сборки (hook → stat → cta)."""
    with conn.cursor() as cur:
        cur.execute("""
            SELECT id, type, plain_text, word_count
            FROM atoms
            WHERE project_id = %s AND plain_text IS NOT NULL
            ORDER BY created_at
        """, (project_id,))
        cols = [d[0] for d in cur.description]
        return [dict(zip(cols, row)) for row in cur.fetchall()]


def build_composition(atoms: list[dict], channel: str, project: str) -> dict:
    """Сборка: hook → stat → cta (в порядке recipe)."""
    # recipe: порядок типов
    recipe_order = ["hook", "stat", "comparison", "cta", "claim"]

    ordered = []
    for t in recipe_order:
        for atom in atoms:
            if atom["type"] == t:
                ordered.append(atom)
    # дополняем оставшимися
    for atom in atoms:
        if atom["type"] not in recipe_order:
            ordered.append(atom)

    atom_ids = [str(a["id"]) for a in ordered]

    # текст композиции
    if channel == "telegram":
        content = _build_telegram_post(ordered)
    else:
        content = _build_newsletter(ordered)

    return {
        "slug": f"{project}_{channel}",
        "title": f"{channel} — {project}",
        "recipe": {"order": recipe_order, "types": list({a["type"] for a in ordered})},
        "atom_ids": atom_ids,
        "content": content,
    }


def _build_telegram_post(atoms: list[dict]) -> str:
    """Telegram-пост: hook + stat + cta."""
    lines = []
    for atom in atoms[:8]:  # не более 8 атомов в пост
        text = atom["plain_text"]
        if len(text) > 200:
            text = text[:200].rstrip() + "…"
        t = atom["type"]
        if t == "hook":
            lines.append(f"🔥 {text}")
        elif t == "stat":
            lines.append(f"📊 {text}")
        elif t == "cta":
            lines.append(f"👉 {text}")
        else:
            lines.append(text)
    return "\n\n".join(lines)


def _build_newsletter(atoms: list[dict]) -> str:
    """Рассылка: hook (заголовок) + body."""
    lines = []
    for atom in atoms[:10]:
        text = atom["plain_text"]
        if len(text) > 300:
            text = text[:300].rstrip() + "…"
        lines.append(text)
    return "\n\n".join(lines)


def insert_composition(conn, project_id: str, comp: dict, channel: str) -> str:
    """Вставить composition. Возвращает composition_id."""
    composition_id = str(uuid.uuid4())
    with conn.cursor() as cur:
        cur.execute("""
            INSERT INTO compositions
            (id, project_id, channel, slug, title, status, recipe, atom_ids, content)
            VALUES (%s, %s, %s, %s, %s, %s, %s, %s::uuid[], %s)
            ON CONFLICT (project_id, channel, slug) DO UPDATE
            SET content = EXCLUDED.content, atom_ids = EXCLUDED.atom_ids
        """, (
            composition_id, project_id, channel, comp["slug"], comp["title"],
            "ready", json.dumps(comp["recipe"]), comp["atom_ids"], comp["content"],
        ))
    conn.commit()
    return composition_id


def main():
    ap = argparse.ArgumentParser(description="MVP stage 3: compositions")
    ap.add_argument("--channel", default="telegram", help="канал")
    ap.add_argument("--project", default="rabota-ufa", help="project slug")
    args = ap.parse_args()

    conn = get_conn()
    project_id = get_project_id(conn, args.project)
    atoms = get_atoms(conn, project_id)
    print(f"  • {len(atoms)} атомов для {args.channel}")

    start = time.time()
    comp = build_composition(atoms, args.channel, args.project)
    comp_id = insert_composition(conn, project_id, comp, args.channel)
    conn.close()

    print(f"  ✓ composition: {comp['slug']} за {time.time()-start:.1f}с")
    print(f"  • atom_ids: {len(comp['atom_ids'])}")
    print(f"\nMVP stage 3 compositions OK: {comp['slug']} → {comp_id}")
    return 0


if __name__ == "__main__":
    sys.exit(main())