separate config parameters

src/config.py

+from pathlib import Path
+from typing import Dict, List
+
+# Base directories
+BASE_DIR: Path = Path(__file__).resolve().parent
+csv_file: Path = BASE_DIR.parent / "Tables/original_tables/ct_ecmwf.rc"
+json_output_path: Path = BASE_DIR.parent / "Tables/era5-cmor-tables/Tables"
+search_dirs: List[Path] = [
+    BASE_DIR.parent / "Tables/source_tables/obs4MIPs-cmor-tables/Tables",
+    BASE_DIR.parent / "Tables/source_tables/cmip6-cmor-tables/Tables"
+]
+
+# Frequency priority
+frequency_priority: Dict[str, List[str]] = {
+    "1hr": [
+        "A1hr", "A3hr", "A6hr",         # Atmospheric hourly tables
+        "E1hr", "E3hr", "E6hrZ",        # Earth system / energy hourly
+        "E1hrClimMon", "E3hrPt",        # Other energy system hourly
+        "CF3hr", "CFsubhr", "Esubhr",   # High-res and subhourly
+        "3hr", "6hrLev", "6hrPlev", "6hrPlevPt",  # More coarse-hourly or pressure-level
+        "AERhr"                         # Aerosol-specific hourly
+    ],
+    "day": [
+        "Aday", "Eday", "EdayZ",        # Standard and energy/dynamics daily
+        "CFday",                        # High-res daily
+        "SIday",                        # Sea ice daily
+        "Oday",                         # Ocean daily
+        "AERday",                       # Aerosol daily
+        "day"                           # Generic fallback
+    ],
+    "mon": [
+        "Amon", "Lmon", "Omon",        # Atmosphere, land, ocean monthly
+        "Emon", "EmonZ",               # Energy system monthly
+        "CFmon",                       # High-res monthly
+        "SImon",                       # Sea ice monthly
+        "AERmon", "AERmonZ",           # Aerosol monthly
+        "ImonAnt", "ImonGre", "LImon"  # Ice-specific monthly
+    ],
+    "fx": [
+        "fx", "Ofx", "Efx", "IfxAnt", "IfxGre"  # Fixed fields (land, ocean, earth system, ice)
+    ]
+}
+
+# Level groupings
+level_categories: Dict[str, List[str]] = {
+    "sfc": ["sfc_an", "sfc_fc"],
+    "sfc_land": ["sfc_an_land", "sfc_fc_land"],
+    "pl": ["pl_an", "pl_fc"],
+    "ml": ["ml_an"]
+}
+
+# Realm → prefix
+realm_prefix_map: Dict[str, str] = {
+    "aerosol": "AER",
+    "atmos": "A",
+    "atmosChem": "AER",
+    "ice": "I",
+    "land": "L",
+    "landIce": "LI",
+    "ocean": "O",
+    "seaIce": "SI"
+}
+
+# Approximate intervals in days
+approx_interval_map: Dict[str, float] = {
+    "1hr": round(1 / 24, 5),    # 0.04167
+    "day": 1.00000,
+    "mon": 30.00000,
+    "fx": 0.00000
+}
+
+# Number of levels
+level_number: Dict[str, int] = {
+    "pl": 37,
+    "ml": 137
+}

src/converter.py

@@ -3,81 +3,23 @@ import json
 import pandas as pd
 from io import StringIO
 from pathlib import Path
-from typing import Optional, Dict, List
+from typing import Optional, Union, Dict, List
 from datetime import datetime
 import re
 import glob
+from config import (
+    csv_file,
+    json_output_path,
+    search_dirs,
+    frequency_priority,
+    level_categories,
+    approx_interval_map,
+    realm_prefix_map,
+    level_number,
+)
 
 today_date: str = datetime.today().strftime("%d %B %Y")
 
-BASE_DIR: Path = Path(__file__).resolve().parent 
-csv_file: Path = BASE_DIR.parent / "Tables/original_tables/ct_ecmwf.rc"
-json_output_path: Path = BASE_DIR.parent / "Tables/era5-cmor-tables/Tables"
-search_dirs: List[Path] = [
-    BASE_DIR.parent / "Tables/source_tables/obs4MIPs-cmor-tables/Tables",
-    BASE_DIR.parent / "Tables/source_tables/cmip6-cmor-tables/Tables"
-]
-
-frequency_priority: Dict[str, List[str]] = {
-    "1hr": [
-        "A1hr", "A3hr", "A6hr",         # Atmospheric hourly tables
-        "E1hr", "E3hr", "E6hrZ",        # Earth system / energy hourly
-        "E1hrClimMon", "E3hrPt",        # Other energy system hourly
-        "CF3hr", "CFsubhr", "Esubhr",   # High-res and subhourly
-        "3hr", "6hrLev", "6hrPlev", "6hrPlevPt",  # More coarse-hourly or pressure-level
-        "AERhr"                         # Aerosol-specific hourly
-    ],
-    "day": [
-        "Aday", "Eday", "EdayZ",        # Standard and energy/dynamics daily
-        "CFday",                        # High-res daily
-        "SIday",                        # Sea ice daily
-        "Oday",                         # Ocean daily
-        "AERday",                       # Aerosol daily
-        "day"                           # Generic fallback
-    ],
-    "mon": [
-        "Amon", "Lmon", "Omon",        # Atmosphere, land, ocean monthly
-        "Emon", "EmonZ",               # Energy system monthly
-        "CFmon",                       # High-res monthly
-        "SImon",                       # Sea ice monthly
-        "AERmon", "AERmonZ",           # Aerosol monthly
-        "ImonAnt", "ImonGre", "LImon"  # Ice-specific monthly
-    ],
-    "fx": [
-        "fx", "Ofx", "Efx", "IfxAnt", "IfxGre"  # Fixed fields (land, ocean, earth system, ice)
-    ]
-}
-
-level_categories: Dict[str, List[str]] = {
-    "sfc": ["sfc_an", "sfc_fc"],
-    "sfc_land": ["sfc_an_land", "sfc_fc_land"],
-    "pl": ["pl_an", "pl_fc"],
-    "ml": ["ml_an"]
-}
-
-approx_interval_map: Dict[str, float] = {
-    "1hr": round(1 / 24, 5),    # 0.04167
-    "day": 1.00000,
-    "mon": 30.00000,
-    "fx": 0.00000
-}
-
-realm_prefix_map: Dict[str, str] = {
-    "aerosol": "AER",
-    "atmos": "A",
-    "atmosChem": "AER",
-    "ice": "I",
-    "land": "L",
-    "landIce": "LI",
-    "ocean": "O",
-    "seaIce": "SI"
-}
-
-level_number: Dict[str, int] = {
-    "pl": 37,
-    "ml": 137
-}
-
 def _determine_level_category(level_type: str) -> str:
     for category, values in level_categories.items():
         if level_type in values:
@@ -325,12 +267,11 @@ def _add_areacella(grouped_json: dict, search_dirs: List[str]) -> None:
     Adds areacella into fx_sfc group if not already present.
     Pulls the entry from matching source table, and adds minimal required metadata.
     """
-    print("in areacella")     
     fx_sfc_keys: List[tuple[str, str]] = [("fx", "sfc"), ("fx", "sfc_land")]
     if all(key not in grouped_json or "areacella" in grouped_json[key] for key in fx_sfc_keys):
         return
 
-    matched = _find_best_matching_variable("areacella", "fx", search_dirs)
+    matched: Optional[Dict] = _find_best_matching_variable("areacella", "fx", search_dirs)
     if not matched:
         print("⚠️  Warning: 'areacella' not found in any fx tables.")
         return
@@ -361,23 +302,22 @@ def _add_areacella(grouped_json: dict, search_dirs: List[str]) -> None:
         grouped_json[fx_sfc_key]["areacella"] = {**matched, **extra_metadata}
     print("✅ added areacella into fx_sfc.")
 
-def _ensure_list(val):
+def _ensure_list(val) -> Optional[List[str]]:
     if val is None:
         return None
     return val if isinstance(val, list) else [val]
 
 def csv_to_cmor_json(
-    csv_filepath=csv_file,
-    json_output_path=json_output_path,
-    var=None,
-    freq=None,
-    ltype=None,
+    csv_filepath: Path = csv_file,
+    json_output_path: Path = json_output_path,
+    var: Optional[Union[str, List[str]]] = None,
+    freq: Optional[Union[str, List[str]]] = None,
+    ltype: Optional[Union[str, List[str]]] = None,
     clean_output: bool = False
 ) -> None:
-
-    var = _ensure_list(var)
-    freq = _ensure_list(freq)
-    ltype = _ensure_list(ltype)
+    var: Optional[List[str]] = _ensure_list(var)
+    freq: Optional[List[str]] = _ensure_list(freq)
+    ltype: Optional[List[str]] = _ensure_list(ltype)
 
     if clean_output:
         for file in glob.glob(os.path.join(json_output_path, "*.json")):