Merge branch 'main' of github.com:harmonydata/harmony into main

setup.py

@@ -1,48 +1,56 @@
 import setuptools
 
-with open('README.md', 'r', encoding='utf-8') as fh:
+with open("README.md", "r", encoding="utf-8") as fh:
     long_description = fh.read()
 
 setuptools.setup(
-    name='harmonydata',
-    author='Thomas Wood',
-    author_email='thomas@fastdatascience.com',
-    description='Harmony Tool for Retrospective Data Harmonisation',
-    keywords='harmony, harmonisation, harmonization, harmonise, harmonize',
+    name="harmonydata",
+    author="Thomas Wood",
+    author_email="thomas@fastdatascience.com",
+    description="Harmony Tool for Retrospective Data Harmonisation",
+    keywords="harmony, harmonisation, harmonization, harmonise, harmonize",
     long_description=long_description,
-    long_description_content_type='text/markdown',
-    url='https://github.com/harmonydata/harmony',
+    long_description_content_type="text/markdown",
+    url="https://github.com/harmonydata/harmony",
     project_urls={
-        'Documentation': 'https://harmonydata.org/',
-        'Bug Reports':
-        'https://github.com/harmonydata/harmony/issues',
-        'Source Code': 'https://github.com/harmonydata/harmony',
+        "Documentation": "https://harmonydata.org/",
+        "Bug Reports": "https://github.com/harmonydata/harmony/issues",
+        "Source Code": "https://github.com/harmonydata/harmony",
         # 'Funding': '',
         # 'Say Thanks!': '',
     },
-    package_dir={'': 'src'},
-    packages=setuptools.find_packages(where='src'),
+    package_dir={"": "src"},
+    packages=setuptools.find_packages(where="src"),
     classifiers=[
         # see https://pypi.org/classifiers/
-        'Development Status :: 5 - Production/Stable',
-
-        'Intended Audience :: Developers',
-        'Topic :: Software Development :: Build Tools',
-
-        'Programming Language :: Python :: 3',
-        'Programming Language :: Python :: 3.6',
-        'Programming Language :: Python :: 3.7',
-        'Programming Language :: Python :: 3.8',
-        'Programming Language :: Python :: 3.9',
-        'Programming Language :: Python :: 3.10',
-        'Programming Language :: Python :: 3 :: Only',
-        'License :: OSI Approved :: MIT License',
-        'Operating System :: OS Independent',
+        "Development Status :: 5 - Production/Stable",
+        "Intended Audience :: Developers",
+        "Topic :: Software Development :: Build Tools",
+        "Programming Language :: Python :: 3",
+        "Programming Language :: Python :: 3.6",
+        "Programming Language :: Python :: 3.7",
+        "Programming Language :: Python :: 3.8",
+        "Programming Language :: Python :: 3.9",
+        "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3 :: Only",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+    ],
+    python_requires=">=3.6",
+    install_requires=[
+        "azure-storage-blob==12.16.0",
+        "pydantic==1.10.7",
+        "pandas==2.0.0",
+        "tika==2.6.0",
+        "lxml==4.9.2",
+        "langdetect==1.0.9",
+        "XlsxWriter==3.0.9",
+        "openpyxl==3.1.2",
+        "spacy==3.5.3",
+        "wget==3.2",
     ],
-    python_requires='>=3.6',
-    install_requires=['pydantic==1.10.7','pandas==2.0.0','tika==2.6.0','lxml==4.9.2','langdetect==1.0.9','XlsxWriter==3.0.9','openpyxl==3.1.2','spacy==3.5.3','wget==3.2'],
     extras_require={
-        'dev': ['check-manifest'],
+        "dev": ["check-manifest"],
         # 'test': ['coverage'],
     },
     # entry_points={

src/harmony/parsing/wrapper_all_parsers.py

@@ -1,4 +1,3 @@
-import os
 from typing import List
 
 from harmony.parsing.excel_parser import convert_excel_to_instruments
@@ -19,7 +18,10 @@ def _get_instruments_from_file(file):
         instruments_from_this_file = []
     return instruments_from_this_file
 
+
 def convert_files_to_instruments(files: List[RawFile]) -> List[Instrument]:
+    """Get cached instruments of files or convert files to instruments"""
+
     instruments = []
 
     for file in files: