refactoring the code for pairs, models, strategy

lib/tools/filetools.py

@@ -0,0 +1,33 @@
+import os
+import glob
+from typing import Dict, List, Tuple
+
+DayT = str
+DataFileNameT = str
+
+def resolve_datafiles(
+    config: Dict, date_pattern: str, instruments: List[Dict[str, str]]
+) -> List[Tuple[DayT, DataFileNameT]]:
+    resolved_files: List[Tuple[DayT, DataFileNameT]] = []
+    for inst in instruments:
+        pattern = date_pattern
+        inst_type = inst["instrument_type"]
+        data_dir = config["market_data_loading"][inst_type]["data_directory"]
+        if "*" in pattern or "?" in pattern:
+            # Handle wildcards
+            if not os.path.isabs(pattern):
+                pattern = os.path.join(data_dir, f"{pattern}.mktdata.ohlcv.db")
+            matched_files = glob.glob(pattern)
+            for matched_file in matched_files:
+                import re
+                match = re.search(r"(\d{8})\.mktdata\.ohlcv\.db$", matched_file)
+                assert match is not None
+                day = match.group(1)
+                resolved_files.append((day, matched_file))
+        else:
+            # Handle explicit file path
+            if not os.path.isabs(pattern):
+                pattern = os.path.join(data_dir, f"{pattern}.mktdata.ohlcv.db")
+            resolved_files.append((date_pattern, pattern))
+    return sorted(list(set(resolved_files)))  # Remove duplicates and sort
+

lib/tools/instruments.py

@@ -0,0 +1,21 @@
+import argparse
+from typing import Dict, List
+
+def get_instruments(args: argparse.Namespace, config: Dict) -> List[Dict[str, str]]:
+
+    instruments = [
+        {
+            "symbol": inst.split(":")[0],
+            "instrument_type": inst.split(":")[1],
+            "exchange_id": inst.split(":")[2],
+            "instrument_id_pfx": config["market_data_loading"][inst.split(":")[1]][
+                "instrument_id_pfx"
+            ],
+            "db_table_name": config["market_data_loading"][inst.split(":")[1]][
+                "db_table_name"
+            ],
+        }
+        for inst in args.instruments.split(",")
+    ]
+    return instruments
+