refactor code to implement new config; correct tests

nb/00_Setup.ipynb

@@ -17,9 +17,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "\n",
     "import dotenv\n",
     "import pystatis\n",
-    "import pystatis.config\n",
+    "from pystatis.config import get_supported_db, config\n",
     "\n",
     "print(\"pystatis version: \", pystatis.__version__)\n",
     "dotenv.load_dotenv()"
@@ -32,7 +33,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    " # only execute if you want to delete your config file for test purposes\n",
+    "# only execute if you want to delete your config file for test purposes\n",
     "pystatis.config.delete_config()\n",
     "pystatis.config.init_config()"
    ]
@@ -86,20 +87,12 @@
    "source": [
     "from pprint import pprint\n",
     "\n",
-    "config = pystatis.config.load_config()\n",
-    "\n",
-    "for db in pystatis.config.get_supported_db():\n",
-    "    for field in [\"username\", \"password\"]:\n",
-    "        print(f\"{db} {field}: {config[db][field]}\")"
+    "for db in get_supported_db():\n",
+    "    print(\"Database: \", db)\n",
+    "    for k, v in config[db].items():\n",
+    "        print(k, v)\n",
+    "    print()"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "faa25df3",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {

nb/01_Databases.ipynb

@@ -25,6 +25,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# expected to fail!\n",
     "pystatdb.set_db(\"test\")"
    ]
   },
@@ -47,13 +48,6 @@
     "pystatdb.set_db(\"zensus\")\n",
     "logincheck()"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {

nb/cache.ipynb

@@ -11,18 +11,18 @@
     "logging.basicConfig(level=logging.INFO)\n",
     "\n",
     "import pystatis\n",
-    "from pystatis import Cube, Table, init_config, clear_cache"
+    "from pystatis import Cube, Table, clear_cache\n",
+    "from pystatis.db import set_db"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "6c4b965e",
+   "id": "5c944d20",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# only run this if you haven't done so earlier\n",
-    "# init_config()"
+    "set_db(\"genesis\")"
    ]
   },
   {
@@ -34,7 +34,7 @@
    "source": [
     "# first, let's download two data sets\n",
     "# these will be cached under your \n",
-    "Cube(name=\"22922KJ1141\").get_data()\n",
+    "#Cube(name=\"22922KJ1141\").get_data()\n",
     "Table(name=\"21311-0001\").get_data()"
    ]
   },
@@ -60,6 +60,14 @@
     "# Or without a name to clear the whole cache at once\n",
     "clear_cache()"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7219b44b",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -78,7 +86,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.7"
+   "version": "3.11.5"
   },
   "vscode": {
    "interpreter": {

nb/cube.ipynb

@@ -10,7 +10,18 @@
     "import logging\n",
     "logging.basicConfig(level=logging.INFO)\n",
     "\n",
-    "from pystatis import Cube"
+    "from pystatis import Cube\n",
+    "from pystatis.db import set_db"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "812c0e39",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "set_db(\"genesis\")"
    ]
   },
   {
@@ -30,7 +41,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "c.get_data()"
+    "c.get_data() # TODO: currently broken?"
    ]
   },
   {
@@ -105,7 +116,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.7"
+   "version": "3.11.5"
   },
   "vscode": {
    "interpreter": {

src/pystatis/__init__.py

@@ -7,6 +7,14 @@
 print("Version:", pstat.__version__)
 ```
 """
+import pystatis.cache
+import pystatis.config
+import pystatis.cube
+import pystatis.db
+import pystatis.find
+import pystatis.helloworld
+import pystatis.profile
+import pystatis.table
 from pystatis.cache import clear_cache
 from pystatis.config import setup_credentials
 from pystatis.cube import Cube

src/pystatis/cache.py

@@ -6,17 +6,19 @@
 import shutil
 import zipfile
 from datetime import date
+from operator import attrgetter
 from pathlib import Path
 from typing import Optional
 
-from pystatis.config import load_config
+from pystatis.config import get_cache_dir
 
 logger = logging.getLogger(__name__)
+
 JOB_ID_PATTERN = r"\d+"
 
 
 def cache_data(
-    cache_dir: Path,
+    cache_dir: str,
     name: Optional[str],
     params: dict,
     data: str,
@@ -28,10 +30,8 @@ def cache_data(
     This allows to cache different results for different params.
 
     Args:
-        cache_dir (Path): The cash directory as configured in the config.
+        cache_dir (str): The cash directory as configured in the config.
         name (str): The unique identifier in GENESIS-Online.
-        endpoint (str): The endpoint for this data request.
-        method (str): The method for this data request.
         params (dict): The dictionary holding the params for this data request.
         data (str): The actual raw text data as returned by GENESIS-Online.
     """
@@ -73,8 +73,6 @@ def read_from_cache(
     Args:
         cache_dir (Path): The cash directory as configured in the config.
         name (str): The unique identifier in GENESIS-Online.
-        endpoint (str): The endpoint for this data request.
-        method (str): The method for this data request.
         params (dict): The dictionary holding the params for this data request.
 
     Returns:
@@ -85,11 +83,11 @@ def read_from_cache(
 
     data_dir = _build_file_path(cache_dir, name, params)
 
-    versions = sorted(
+    latest_version = sorted(
         data_dir.glob("*"),
-        key=lambda path: int(path.stem),
-    )
-    file_name = versions[-1].name
+        key=attrgetter("stem"),
+    )[-1]
+    file_name = latest_version.name
     file_path = data_dir / file_name
     with zipfile.ZipFile(file_path, "r") as myzip:
         with myzip.open(file_name.replace(".zip", ".txt")) as file:
@@ -98,15 +96,13 @@ def read_from_cache(
     return data
 
 
-def _build_file_path(cache_dir: Path, name: str, params: dict) -> Path:
+def _build_file_path(cache_dir: str, name: str, params: dict) -> Path:
     """Builds a unique cache directory name from name and hashed params dictionary.
 
-    The way this method works is that it creates a path under cache dir that is unique
-        because the name is a unique EVAS identifier number in Destatis and the hash
-        is (close enough) unique to a given dictionary with query parameter values.
+    The way this method works is that it creates a path under cache dir that is unique because the name is a unique EVAS identifier number in Destatis and the hash is (close enough) unique to a given dictionary with query parameter values.
 
     Args:
-        cache_dir (Path): The root cache directory as configured in the config.ini.
+        cache_dir (str): The root cache directory as configured in the config.ini.
         name (str): The unique identifier for an object in Destatis.
         params (dict): The query parameters for a given call to the Destatis API.
 
@@ -120,7 +116,7 @@ def _build_file_path(cache_dir: Path, name: str, params: dict) -> Path:
         del params_["job"]
     params_hash = hashlib.blake2s(digest_size=10, usedforsecurity=False)
     params_hash.update(json.dumps(params_).encode("UTF-8"))
-    data_dir = cache_dir / name / params_hash.hexdigest()
+    data_dir = Path(cache_dir) / name / params_hash.hexdigest()
 
     return data_dir
 
@@ -141,17 +137,15 @@ def normalize_name(name: str) -> str:
 
 
 def hit_in_cash(
-    cache_dir: Path,
+    cache_dir: str,
     name: Optional[str],
     params: dict,
 ) -> bool:
     """Check if data is already cached.
 
     Args:
-        cache_dir (Path): The cash directory as configured in the config.
+        cache_dir (str): The cash directory as configured in the config.
         name (str): The unique identifier in GENESIS-Online.
-        endpoint (str): The endpoint for this data request.
-        method (str): The method for this data request.
         params (dict): The dictionary holding the params for this data request.
 
     Returns:
@@ -170,8 +164,7 @@ def clear_cache(name: Optional[str] = None) -> None:
     Args:
         name (str, optional): Unique name to be deleted from cached data.
     """
-    config = load_config()
-    cache_dir = Path(config["DATA"]["cache_dir"])
+    cache_dir = Path(get_cache_dir())
 
     # remove specified file (directory) from the data cache
     # or clear complete cache (remove childs, preserve base)