feat: more kata work

Author: gadomski

docs/katas/0_full_scan.ipynb

@@ -0,0 +1,69 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "f9521565",
+   "metadata": {},
+   "source": [
+    "# Miscellaneous checks\n",
+    "\n",
+    "Answering some questions, e.g. those in https://github.com/developmentseed/labs-375-stac-geoparquet-backend/issues/71.\n",
+    "First, how does **rustac** compare to DuckDB's Python client?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "56d3efc8",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Retrieved 10000 in 1.54s (6498.29 items/s)\n",
+      "Retrieved 10000 in 0.34s (29430.88 items/s)\n"
+     ]
+    }
+   ],
+   "source": [
+    "import duckdb\n",
+    "from rustac import DuckdbClient\n",
+    "\n",
+    "from labs_375 import NAIP_GEOPARQUET_URI, Timer\n",
+    "\n",
+    "rustac_client = DuckdbClient()\n",
+    "rustac_client.execute(\"CREATE SECRET (TYPE S3, PROVIDER CREDENTIAL_CHAIN)\")\n",
+    "with Timer() as timer:\n",
+    "    items = rustac_client.search(NAIP_GEOPARQUET_URI)\n",
+    "    timer.report(items)\n",
+    "\n",
+    "# duckdb.sql(\"CREATE SECRET (TYPE S3, PROVIDER CREDENTIAL_CHAIN)\")\n",
+    "with Timer() as timer:\n",
+    "    items = duckdb.sql(f\"SELECT * from '{NAIP_GEOPARQUET_URI}'\")\n",
+    "    timer.report(items)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/katas/9_misc.ipynb

@@ -19,5 +19,7 @@
     extension_directory=extension_directory,
 )
 duckdb_client.execute("CREATE SECRET (TYPE S3, PROVIDER CREDENTIAL_CHAIN)")
+duckdb_client.execute("SET parquet_metadata_cache = true;")
+duckdb_client.execute("SET force_download = true;")
 api = stac_fastapi.geoparquet.api.create(duckdb_client=duckdb_client)
 handler = Mangum(api.app, lifespan="on")

infrastructure/aws/lambda/handler.py

@@ -30,9 +30,11 @@ dev = [
     "ruff>=0.9.10",
 ]
 katas = [
+    "duckdb>=1.2.2",
     "ipykernel>=6.29.5",
- "matplotlib>=3.10.1",
- "pystac-client>=0.8.5",
+    "matplotlib>=3.10.1",
+    "pystac-client>=0.8.5",
+    "rustac==0.7.0b3",
 ]
 
 [tool.mypy]