Initial commit: shared DB, fetcher, and CSV import utilities

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

import_csv.py

@@ -0,0 +1,80 @@
+"""
+One-shot migration: import all NewBellCurve CSV candle files into data/candles.db.
+
+Usage:
+    python -m shared.import_csv
+    python -m shared.import_csv --csv-dir /path/to/other/csvs
+    python -m shared.import_csv --dry-run
+"""
+import argparse
+import logging
+import re
+import sys
+from pathlib import Path
+
+import pandas as pd
+
+# Allow running from repo root or any subdirectory
+sys.path.insert(0, str(Path(__file__).parent.parent))
+from shared.db import upsert_candles, list_available, DB_PATH
+
+logger = logging.getLogger(__name__)
+
+DEFAULT_CSV_DIR = Path(__file__).parent.parent / "NewBellCurve" / "simulation" / "data"
+_FILENAME_RE = re.compile(r"^([A-Z]+)_([A-Z0-9]+)\.csv$")
+
+
+def import_directory(csv_dir: Path, dry_run: bool = False) -> dict[str, int]:
+    csv_files = sorted(csv_dir.glob("*.csv"))
+    if not csv_files:
+        logger.warning("No CSV files found in %s", csv_dir)
+        return {}
+
+    results = {}
+    for path in csv_files:
+        m = _FILENAME_RE.match(path.name)
+        if not m:
+            logger.warning("Skipping unrecognised filename: %s", path.name)
+            continue
+
+        symbol, timeframe = m.group(1), m.group(2)
+        df = pd.read_csv(path, parse_dates=["time"])
+
+        if dry_run:
+            logger.info("DRY RUN  %-10s %-5s  %d candles", symbol, timeframe, len(df))
+            results[path.name] = len(df)
+            continue
+
+        n = upsert_candles(symbol, timeframe, df)
+        logger.info("%-10s %-5s  %d candles written", symbol, timeframe, n)
+        results[path.name] = n
+
+    return results
+
+
+def main():
+    logging.basicConfig(level=logging.INFO, format="%(asctime)s %(message)s")
+    parser = argparse.ArgumentParser(description="Import CSV candle files into shared candles.db")
+    parser.add_argument("--csv-dir", default=str(DEFAULT_CSV_DIR), help="Directory of CSV files")
+    parser.add_argument("--dry-run", action="store_true", help="Parse only, do not write to DB")
+    args = parser.parse_args()
+
+    csv_dir = Path(args.csv_dir)
+    if not csv_dir.exists():
+        logger.error("CSV directory not found: %s", csv_dir)
+        sys.exit(1)
+
+    logger.info("Importing from: %s", csv_dir)
+    logger.info("Database:       %s", DB_PATH)
+
+    results = import_directory(csv_dir, dry_run=args.dry_run)
+    total = sum(results.values())
+    logger.info("Done — %d files, %d candles total", len(results), total)
+
+    if not args.dry_run:
+        print("\nAvailable data in candles.db:")
+        print(list_available().to_string(index=False))
+
+
+if __name__ == "__main__":
+    main()