From 1a479ceb247789e8e07e5a0280e05c1071a84118 Mon Sep 17 00:00:00 2001
From: Leo Vasanko <git@vasanko.com>
Date: Fri, 21 Aug 2026 03:09:04 +0000
Subject: [PATCH] Add --dbip CLI flag to auto-download/update the DB-IP MMDB
 database.

Downloads the latest dbip-city-lite-YYYY-MM.mmdb.gz before starting the
server, skipping when the local database is current, falling back to the
previous month on 404, and removing older databases after an update.
Promotes httpx to a runtime dependency.
---
 docs/analytics.md    |  6 +++-
 pagerite/__main__.py | 69 +++++++++++++++++++++++++++++++++++++++++++-
 pyproject.toml       |  5 ++--
 3 files changed, 75 insertions(+), 5 deletions(-)

diff --git a/docs/analytics.md b/docs/analytics.md
index 40783de..ec3cc37 100644
--- a/docs/analytics.md
+++ b/docs/analytics.md
@@ -57,7 +57,11 @@ The client (`pagerite.js`) POSTs fire-and-forget pings to `/_a` with
   `country`.  The MMDB lookup and the reverse-DNS lookup run in background
   tasks after the visit is stored, so the `/ _a` response is never delayed.
   The decompressed `dbip-*.mmdb` file is kept in the repository root and
-  ignored by git.
+  ignored by git.  The CLI flag `--dbip` (`uv run pagerite --dbip`) downloads
+  the latest `dbip-city-lite-YYYY-MM.mmdb.gz` from DB-IP before the server
+  starts, skipping the download when the local database is already current and
+  removing older versions after an update; without the flag only an existing
+  file is used.
 - **Crawler hits**: every document GET is queued in RAM as a pending crawler
   hit.  If a ping from the same (IP, User-Agent) pair arrives within 10
   seconds the hit is discarded; otherwise it is written to `crawlers`.
diff --git a/pagerite/__main__.py b/pagerite/__main__.py
index f5c02a4..dafe3f2 100644
--- a/pagerite/__main__.py
+++ b/pagerite/__main__.py
@@ -1,14 +1,74 @@
-# auto-upgrade@fastapi-vue-setup - remove this if you modify this file
 """Command-line entry point for running the backend server."""
 
 import argparse
+import gzip
 import os
+import sys
+from datetime import date
+from pathlib import Path
 
+import httpx
 from fastapi_vue import server
 
 DEFAULT_PORT = 8100
 DEVMODE = os.getenv("PAGERITE_DEV") == "1"
 
+# Repository root (pagerite/__main__.py -> ..), where the MMDB lives.
+_REPO_ROOT = Path(__file__).resolve().parent.parent
+
+DBIP_URL = "https://download.db-ip.com/free/dbip-city-lite-{month}.mmdb.gz"
+
+
+def _download_dbip() -> None:
+    """Download the latest dbip-city-lite MMDB if ours is missing or older."""
+    today = date.today()
+    months = [f"{today:%Y-%m}"]
+    # The current month's file may not be published yet; fall back to last month.
+    prev = (today.replace(day=1) - date.resolution).replace(day=1)
+    months.append(f"{prev:%Y-%m}")
+
+    existing = sorted(
+        p.stem.removeprefix("dbip-city-lite-").removesuffix(".mmdb")
+        for p in _REPO_ROOT.glob("dbip-city-lite-*.mmdb*")
+    )
+    if existing and existing[-1] >= months[0]:
+        print(f"pagerite: DB-IP database is current ({existing[-1]}), skipping download")
+        return
+
+    for month in months:
+        url = DBIP_URL.format(month=month)
+        target = _REPO_ROOT / f"dbip-city-lite-{month}.mmdb.gz"
+        tmp = target.with_suffix(".mmdb.gz.tmp")
+        print(f"pagerite: downloading {url}")
+        try:
+            with httpx.stream("GET", url, follow_redirects=True, timeout=120) as r:
+                if r.status_code == 404:
+                    continue
+                r.raise_for_status()
+                with open(tmp, "wb") as f:
+                    for chunk in r.iter_bytes():
+                        f.write(chunk)
+        except httpx.HTTPError as e:
+            print(f"pagerite: DB-IP download failed: {e}", file=sys.stderr)
+            tmp.unlink(missing_ok=True)
+            continue
+        # Verify it is actually gzip data before installing it.
+        try:
+            with gzip.open(tmp, "rb") as f:
+                f.read(1)
+        except OSError:
+            print(f"pagerite: DB-IP download for {month} was not valid gzip", file=sys.stderr)
+            tmp.unlink(missing_ok=True)
+            continue
+        os.replace(tmp, target)
+        # Drop older databases so the app never picks up a stale one.
+        for old in _REPO_ROOT.glob("dbip-city-lite-*.mmdb*"):
+            if old.name != target.name:
+                old.unlink()
+        print(f"pagerite: DB-IP database updated to {target.name}")
+        return
+    print("pagerite: could not download a DB-IP database", file=sys.stderr)
+
 
 def main() -> None:
     """Run the backend server with optional arguments."""
@@ -19,7 +79,14 @@ def main() -> None:
         action="append",
         help=(f"Endpoint (default: localhost:{DEFAULT_PORT})."),
     )
+    parser.add_argument(
+        "--dbip",
+        action="store_true",
+        help="Download/update the DB-IP city lite database before starting.",
+    )
     args = parser.parse_args()
+    if args.dbip:
+        _download_dbip()
     dev = {"reload": True, "reload_dirs": ["pagerite"]} if DEVMODE else {}
     server.run(
         "pagerite.app:app",
diff --git a/pyproject.toml b/pyproject.toml
index 02168d9..e9d23ee 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -20,6 +20,7 @@ dependencies = [
     "fastapi-vue>=1.3.1",
     "fastapi[standard]>=0.141.1",
     "html5tagger>=2.0.0",
+    "httpx>=0.28.1",
     "kanta>=0.8.1",
     "markdown-it-py>=4.2.0",
     "maxminddb>=3.1.1",
@@ -35,9 +36,7 @@ pagerite = "pagerite.__main__:main"
 Repository = "https://git.zi.fi/LeoVasanko/pagerite"
 
 [dependency-groups]
-dev = [
-    "httpx>=0.28.1",
-]
+dev = []
 
 [tool.hatch.version]
 source = "vcs"