Initial history collector implementation

app/main.py

@@ -0,0 +1,114 @@
+import asyncio
+import json
+import logging
+import os
+import sqlite3
+from contextlib import closing
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Literal
+
+import httpx
+from fastapi import FastAPI, Header, HTTPException, Request, status
+from pydantic import BaseModel, Field, HttpUrl
+
+logging.basicConfig(level=os.getenv("LOG_LEVEL", "INFO"), format="%(asctime)s %(levelname)s %(message)s")
+logger = logging.getLogger("history-collector")
+
+DATA_DIR = Path(os.getenv("DATA_DIR", "/data"))
+DB_PATH = DATA_DIR / "history.sqlite3"
+API_TOKEN = os.getenv("API_TOKEN", "")
+DISCORD_WEBHOOK_URL = os.getenv("DISCORD_WEBHOOK_URL", "")
+MAX_VISITS_PER_REQUEST = int(os.getenv("MAX_VISITS_PER_REQUEST", "100"))
+
+class Visit(BaseModel):
+    url: HttpUrl
+    title: str = Field(default="", max_length=1000)
+    visit_time: datetime
+    transition: str = Field(default="observed", max_length=100)
+
+class VisitBatch(BaseModel):
+    device_id: str = Field(min_length=1, max_length=128, pattern=r"^[a-zA-Z0-9._-]+$")
+    visits: list[Visit] = Field(min_length=1, max_length=MAX_VISITS_PER_REQUEST)
+
+app = FastAPI(title="Local History Collector", docs_url=None, redoc_url=None)
+
+def connect():
+    DATA_DIR.mkdir(parents=True, exist_ok=True)
+    conn = sqlite3.connect(DB_PATH)
+    conn.row_factory = sqlite3.Row
+    conn.execute("PRAGMA journal_mode=WAL")
+    conn.execute("""CREATE TABLE IF NOT EXISTS visits (
+      id INTEGER PRIMARY KEY,
+      device_id TEXT NOT NULL,
+      url TEXT NOT NULL,
+      title TEXT NOT NULL DEFAULT '',
+      visit_time TEXT NOT NULL,
+      transition TEXT NOT NULL,
+      received_at TEXT NOT NULL,
+      UNIQUE(device_id, url, visit_time)
+    )""")
+    conn.execute("CREATE INDEX IF NOT EXISTS idx_visits_device_time ON visits(device_id, visit_time DESC)")
+    return conn
+
+@app.on_event("startup")
+def startup():
+    if len(API_TOKEN) < 24:
+        raise RuntimeError("API_TOKEN must contain at least 24 characters")
+    with closing(connect()):
+        pass
+
+
+def require_token(authorization: str | None):
+    expected = f"Bearer {API_TOKEN}"
+    if authorization != expected:
+        raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED, detail="Invalid API token")
+
+
+def save_batch(batch: VisitBatch) -> int:
+    received_at = datetime.now(timezone.utc).isoformat()
+    rows = [(batch.device_id, str(v.url), v.title, v.visit_time.astimezone(timezone.utc).isoformat(),
+             v.transition, received_at) for v in batch.visits]
+    with closing(connect()) as conn:
+        before = conn.total_changes
+        conn.executemany("""INSERT OR IGNORE INTO visits
+          (device_id, url, title, visit_time, transition, received_at)
+          VALUES (?, ?, ?, ?, ?, ?)""", rows)
+        inserted = conn.total_changes - before
+        conn.commit()
+    return inserted
+
+async def post_discord(batch: VisitBatch):
+    if not DISCORD_WEBHOOK_URL:
+        return
+    lines = [f"• {v.visit_time.astimezone(timezone.utc):%Y-%m-%d %H:%M UTC} — {v.title or '(brez naslova)'}\n  <{v.url}>" for v in batch.visits]
+    content = f"**Zgodovina brskanja · {batch.device_id}**\n" + "\n".join(lines)
+    # Discord accepts message content up to 2,000 characters; split safely by visit.
+    chunks, current = [], "**Zgodovina brskanja · %s**\n" % batch.device_id
+    for line in lines:
+        candidate = current + line + "\n"
+        if len(candidate) > 1900 and current.strip():
+            chunks.append(current)
+            current = "**Zgodovina brskanja · %s (nadaljevanje)**\n%s\n" % (batch.device_id, line)
+        else:
+            current = candidate
+    if current.strip(): chunks.append(current)
+    try:
+        async with httpx.AsyncClient(timeout=10) as client:
+            for content in chunks:
+                response = await client.post(DISCORD_WEBHOOK_URL, json={"content": content})
+                response.raise_for_status()
+    except Exception:
+        # The visits are already safely persisted; don't reject them because Discord is unavailable.
+        logger.exception("Discord relay failed")
+
+@app.get("/healthz")
+def healthz():
+    return {"ok": True}
+
+@app.post("/v1/visits", status_code=status.HTTP_202_ACCEPTED)
+async def receive_visits(batch: VisitBatch, authorization: str | None = Header(default=None)):
+    require_token(authorization)
+    stored = save_batch(batch)
+    asyncio.create_task(post_discord(batch))
+    return {"accepted": len(batch.visits), "stored": stored}