Fix logger (#274)

* remove automatic setup_logger() call

* update test logger

* use root logger in public api if setup_config() has not been called

* add publicAPI Dataset logger test

* add setup_logging() call in publicAPI doc notebooks

---------

Co-authored-by: Gauthier BERTHOMIEU <gauthier.berthomieu@ensta.fr> (rien à voir avec Gautzilla 🥷)

Author: mathieudpnt

docs/source/example_ltas_public.ipynb

@@ -11,10 +11,17 @@
    },
    "outputs": [],
    "source": [
-    "# Executing this cell will disable all TQDM outputs in stdout.\n",
+    "# Executing this cell will:\n",
+    "\n",
+    "# Disable all TQDM outputs in stdout.\n",
     "import os\n",
     "\n",
-    "os.environ[\"DISABLE_TQDM\"] = \"True\""
+    "os.environ[\"DISABLE_TQDM\"] = \"True\"\n",
+    "\n",
+    "# Setup the python logger for the Public API\n",
+    "from osekit import setup_logging\n",
+    "\n",
+    "setup_logging()  # Overwrites the default logger to"
    ]
   },
   {

docs/source/example_multiple_spectrograms_public.ipynb

@@ -11,10 +11,17 @@
    },
    "outputs": [],
    "source": [
-    "# Executing this cell will disable all TQDM outputs in stdout.\n",
+    "# Executing this cell will:\n",
+    "\n",
+    "# Disable all TQDM outputs in stdout.\n",
     "import os\n",
     "\n",
-    "os.environ[\"DISABLE_TQDM\"] = \"True\""
+    "os.environ[\"DISABLE_TQDM\"] = \"True\"\n",
+    "\n",
+    "# Setup the python logger for the Public API\n",
+    "from osekit import setup_logging\n",
+    "\n",
+    "setup_logging()  # Overwrites the default logger to"
    ]
   },
   {

docs/source/example_reshaping_multiple_files_public.ipynb

@@ -2,20 +2,27 @@
  "cells": [
   {
    "cell_type": "code",
+   "execution_count": null,
    "id": "dc7ebca70b3b5da",
    "metadata": {
     "tags": [
      "remove-cell"
     ]
    },
+   "outputs": [],
    "source": [
-    "# Executing this cell will disable all TQDM outputs in stdout.\n",
+    "# Executing this cell will:\n",
+    "\n",
+    "# Disable all TQDM outputs in stdout.\n",
     "import os\n",
     "\n",
-    "os.environ[\"DISABLE_TQDM\"] = \"True\""
-   ],
-   "outputs": [],
-   "execution_count": null
+    "os.environ[\"DISABLE_TQDM\"] = \"True\"\n",
+    "\n",
+    "# Setup the python logger for the Public API\n",
+    "from osekit import setup_logging\n",
+    "\n",
+    "setup_logging()  # Overwrites the default logger to"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -35,10 +42,12 @@
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "id": "bb002105fc9632e8",
    "metadata": {
     "tags": []
    },
+   "outputs": [],
    "source": [
     "from pathlib import Path\n",
     "\n",
@@ -52,9 +61,7 @@
     ")\n",
     "\n",
     "dataset.build()"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "cell_type": "markdown",
@@ -64,8 +71,10 @@
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "id": "a29c761d4bbd5303",
    "metadata": {},
+   "outputs": [],
    "source": [
     "print(f\"{' DATASET ':#^60}\")\n",
     "print(f\"{'Begin:':<30}{str(dataset.origin_dataset.begin):>30}\")\n",
@@ -86,9 +95,7 @@
     "        for f in dataset.origin_files\n",
     "    ],\n",
     ").set_index(\"Name\")"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "cell_type": "markdown",
@@ -98,10 +105,12 @@
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "id": "b4c2c3857ffcb60f",
    "metadata": {
     "tags": []
    },
+   "outputs": [],
    "source": [
     "from osekit.public_api.analysis import Analysis, AnalysisType\n",
     "from pandas import Timestamp, Timedelta\n",
@@ -113,9 +122,7 @@
     "    data_duration=Timedelta(seconds=5),\n",
     "    name=\"reshape_example\",\n",
     ")"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "cell_type": "markdown",
@@ -128,19 +135,19 @@
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "id": "2f799a26d626e418",
    "metadata": {
     "tags": []
    },
+   "outputs": [],
    "source": [
     "# Returns a Core API AudioDataset that matches the analysis\n",
     "audio_dataset = dataset.get_analysis_audiodataset(analysis=analysis)\n",
     "\n",
     "# Filter the returned AudioDataset\n",
     "audio_dataset.data = [ad for ad in audio_dataset.data if not ad.is_empty]"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "cell_type": "markdown",
@@ -150,15 +157,15 @@
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "id": "9b65cfdc720d50e6",
    "metadata": {
     "tags": []
    },
+   "outputs": [],
    "source": [
     "dataset.run_analysis(analysis=analysis, audio_dataset=audio_dataset)"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "cell_type": "markdown",
@@ -168,8 +175,10 @@
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "id": "3cb0adbb96d2251a",
    "metadata": {},
+   "outputs": [],
    "source": [
     "pd.DataFrame(\n",
     "    [\n",
@@ -182,25 +191,23 @@
     "        for ad in dataset.get_dataset(analysis.name).data\n",
     "    ],\n",
     ").set_index(\"Exported file\")"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "id": "58b7aec2d8863a02",
    "metadata": {
     "tags": [
      "remove-cell"
     ]
    },
+   "outputs": [],
    "source": [
     "# Reset the dataset to get all files back to place.\n",
     "\n",
     "dataset.reset()"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   }
  ],
  "metadata": {

src/osekit/__init__.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import logging.config
 import os.path
 from pathlib import Path
@@ -9,14 +11,25 @@
 
 __all__ = [
     "Job_builder",
+    "setup_logging",
     "utils",
 ]
 
-
-def _setup_logging(
-    config_file="logging_config.yaml",
+def setup_logging(
+    config_file: str | Path = "logging_config.yaml",
     default_level: int = logging.INFO,
 ) -> None:
+    """Configure logger using a configuration yaml file.
+
+    Parameters
+    ----------
+    config_file: str | Path
+        Path to a logging configuration file
+    default_level: int
+        Logging level to use
+        Default value, `logging.INFO`
+
+    """
     user_config_file_path = Path(os.getenv("OSMOSE_USER_CONFIG", ".")) / config_file
     default_config_file_path = Path(__file__).parent / config_file
 
@@ -35,6 +48,5 @@ def _setup_logging(
         logging.config.dictConfig(logging_config)
     else:
         logging.basicConfig(level=default_level)
-
-
-_setup_logging()
+        msg = "Configuration file not found, using default configuration."
+        logging.getLogger(__name__).warning(msg)

src/osekit/public_api/dataset.py

@@ -136,7 +136,11 @@ def build(self) -> None:
             source=self.folder,
             destination=self.folder / "other",
             excluded_paths={file.path for file in ads.files}
-            | set((self.folder / "log").iterdir())
+            | set(
+                (self.folder / "log").iterdir()
+                if (self.folder / "log").exists()
+                else ()
+            )
             | {self.folder / "log"},
         )
         self._sort_dataset(ads)
@@ -146,6 +150,16 @@ def build(self) -> None:
         self.logger.info("Build done!")
 
     def _create_logger(self) -> None:
+        if not logging.getLogger("dataset").handlers:
+            message = (
+                "Logging has not been configured. "
+                "The dataset will use the root logger. "
+                "Use osekit.setup_logging() if wanted."
+            )
+            logging.warning(message)
+            self.logger = logging.getLogger()
+            return
+
         logs_directory = self.folder / "log"
         if not logs_directory.exists():
             logs_directory.mkdir(mode=DPDEFAULT)