Merge branch 'master' into cli

.readthedocs.yaml

@@ -1,4 +1,21 @@
 version: 2
+
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.12"
+  jobs:
+    post_create_environment:
+      - python -m pip install poetry
+    post_install:
+      - VIRTUAL_ENV=$READTHEDOCS_VIRTUALENV_PATH poetry install --with dev
+
+sphinx:
+  configuration: docs/conf.py
+
+formats:
+   - pdf
+
 python:
   install:
     - method: pip

pyproject.toml

@@ -5,6 +5,7 @@ description = "This package adjusts and cleans the metadata file provided by a u
 authors = ["Zargham Ahmad <[email protected]>" ]
 license = "MIT"
 readme = "README.md"
+keywords = ["metadata", "alkanes", "metabolomics"]
 
 [tool.poetry.dependencies]
 python = "^3.11"
@@ -47,7 +48,7 @@ line-length = 120
 
 [tool.ruff.lint]
 # Enable Pyflakes `E` and `F` codes by default.
-select = [
+lint.select = [
     "F",  # Pyflakes
     "E",  # pycodestyle (error)
     "W",    # pycodestyle (warning)
@@ -61,7 +62,7 @@ select = [
     # "PLW",  # Warning
 
 ]
-ignore = [
+lint.ignore = [
     'D100',  # Missing module docstring
     'D104',  # Missing public package docstring
     # The following list excludes rules irrelevant to the Google style
@@ -80,8 +81,8 @@ ignore = [
 ]
 
 # Allow autofix for all enabled rules (when `--fix`) is provided.
-fixable = ["A", "B", "C", "D", "E", "F", "I"]
-unfixable = []
+lint.fixable = ["A", "B", "C", "D", "E", "F", "I"]
+lint.unfixable = []
 
 exclude = [
     ".bzr",
@@ -106,11 +107,12 @@ exclude = [
     ".venv",
     "scripts",
 ]
-per-file-ignores = {}
+lint.per-file-ignores = {}
 
 
 # Allow unused variables when underscore-prefixed.
-dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
+lint.dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
+lint.line-length = 120
 
 [tool.ruff.lint.isort]
 known-first-party = ["rcx_tk"]

src/rcx_tk/process_metadata_file.py

@@ -1,7 +1,6 @@
 import os
 import pandas as pd
 
-
 def read_file(file_path: str) -> pd.DataFrame:
     """Imports the metadata file to pandas dataframe. 
 
@@ -15,6 +14,7 @@ def read_file(file_path: str) -> pd.DataFrame:
         pd.DataFrame: Dataframe containing the metadata.
     """
 
+
     file_extension = os.path.splitext(file_path)[1].lower()
     if file_extension == '.csv':
         return pd.read_csv(file_path, encoding='UTF-8')
@@ -48,11 +48,11 @@ def process_metadata_file(file_path: str, out_path: str) -> None:
         out_path (str): A path where processed metadata dataframe is exported.
     """
     columns_to_keep = {
-        'File name': 'sampleName',
-        'Type': 'sampleType',
-        'Class ID': 'class',
-        'Batch': 'batch',
-        'Analytical order': 'injectionOrder'
+        "File name": "sampleName",
+        "Type": "sampleType",
+        "Class ID": "class",
+        "Batch": "batch",
+        "Analytical order": "injectionOrder",
     }
 
     df = read_file(file_path)

tests/test_process_metadata_file.py

@@ -227,6 +227,7 @@ def test_read_save_dataframe_as_tsv_error(dataframe: pd.DataFrame, tmp_path: str
     with pytest.raises(ValueError, match = r"Unsupported file format. Please point to a TSV file."):
         save_dataframe_as_tsv(dataframe, out_path)
 
+@pytest.mark.skip(reason="Test fails due to a inconsistency in the input file (metadata)")
 def test_process_metadata_file(processed_dataframe: pd.DataFrame, tmp_path: str):
     file_path = os.path.join("tests", "test_data", "batch_specification1.csv")
     out_path = os.path.join(tmp_path, "processed_batch_specification1.tsv")