updating the scripts

legacy/gen-hash/generate-hash.js

@@ -0,0 +1,7 @@
+const bcrypt = require('bcrypt');
+const password = 'Shakkal123!'; // Replace with the exact password you want to use
+const saltRounds = 10;
+bcrypt.hash(password, saltRounds, (err, hash) => {
+  if (err) console.error('Error:', err);
+  else console.log('Hash:', hash);
+});

legacy/gen-hash/package-lock.json

@@ -0,0 +1,46 @@
+{
+  "name": "scripts",
+  "lockfileVersion": 3,
+  "requires": true,
+  "packages": {
+    "": {
+      "dependencies": {
+        "bcrypt": "^6.0.0"
+      }
+    },
+    "node_modules/bcrypt": {
+      "version": "6.0.0",
+      "resolved": "https://registry.npmjs.org/bcrypt/-/bcrypt-6.0.0.tgz",
+      "integrity": "sha512-cU8v/EGSrnH+HnxV2z0J7/blxH8gq7Xh2JFT6Aroax7UohdmiJJlxApMxtKfuI7z68NvvVcmR78k2LbT6efhRg==",
+      "hasInstallScript": true,
+      "license": "MIT",
+      "dependencies": {
+        "node-addon-api": "^8.3.0",
+        "node-gyp-build": "^4.8.4"
+      },
+      "engines": {
+        "node": ">= 18"
+      }
+    },
+    "node_modules/node-addon-api": {
+      "version": "8.5.0",
+      "resolved": "https://registry.npmjs.org/node-addon-api/-/node-addon-api-8.5.0.tgz",
+      "integrity": "sha512-/bRZty2mXUIFY/xU5HLvveNHlswNJej+RnxBjOMkidWfwZzgTbPG1E3K5TOxRLOR+5hX7bSofy8yf1hZevMS8A==",
+      "license": "MIT",
+      "engines": {
+        "node": "^18 || ^20 || >= 21"
+      }
+    },
+    "node_modules/node-gyp-build": {
+      "version": "4.8.4",
+      "resolved": "https://registry.npmjs.org/node-gyp-build/-/node-gyp-build-4.8.4.tgz",
+      "integrity": "sha512-LA4ZjwlnUblHVgq0oBF3Jl/6h/Nvs5fzBLwdEF4nuxnFdsfajde4WfxtJr3CaiH+F6ewcIB/q4jQ4UzPyid+CQ==",
+      "license": "MIT",
+      "bin": {
+        "node-gyp-build": "bin.js",
+        "node-gyp-build-optional": "optional.js",
+        "node-gyp-build-test": "build-test.js"
+      }
+    }
+  }
+}

legacy/gen-hash/package.json

@@ -0,0 +1,5 @@
+{
+  "dependencies": {
+    "bcrypt": "^6.0.0"
+  }
+}

legacy/halifax/clean-halifax-actual-2.py

@@ -0,0 +1,162 @@
+#!/usr/bin/env python3
+
+import csv
+from decimal import Decimal, InvalidOperation
+import sys
+from pathlib import Path
+import json
+from datetime import datetime
+
+SCRIPT_DIR = Path(__file__).resolve().parent
+STATE_FILE = SCRIPT_DIR / "halifax_state.json"
+
+def load_state():
+    if STATE_FILE.exists():
+        try:
+            return json.loads(STATE_FILE.read_text())
+        except json.JSONDecodeError:
+            # If it ever gets corrupted, start fresh
+            return {"seen_keys": []}
+    return {"seen_keys": []}
+
+
+def save_state(state):
+    STATE_FILE.write_text(json.dumps(state, indent=2))
+
+
+def normalize_text(s: str) -> str:
+    # collapse whitespace + lowercase
+    return " ".join(s.split()).lower()
+
+
+def make_key(date_str: str, payee: str, desc: str, amount: Decimal) -> str:
+    """
+    Build a dedupe key: normalized date + payee + description + amount.
+    We normalize:
+      - date into ISO (YYYY-MM-DD)
+      - payee/desc into lowercased, collapsed whitespace
+      - amount to 2 decimal places
+    """
+
+    # Halifax gives dd/mm/yyyy – convert to ISO for consistency
+    date_str = date_str.strip()
+    try:
+        # If it's already ISO, this will work too
+        try:
+            d = datetime.fromisoformat(date_str).date()
+        except ValueError:
+            d = datetime.strptime(date_str, "%d/%m/%Y").date()
+        norm_date = d.isoformat()
+    except Exception:
+        # If parsing fails for some reason, just use the raw string
+        norm_date = date_str
+
+    norm_payee = normalize_text(payee)
+    norm_desc = normalize_text(desc)
+    norm_amount = amount.quantize(Decimal("0.01"))
+
+    return f"{norm_date}|{norm_payee}|{norm_desc}|{norm_amount}"
+
+
+def convert(in_path, out_path):
+    # Load state
+    state = load_state()
+    seen_keys = set(state.get("seen_keys", []))
+
+    written_count = 0
+    skipped_count = 0
+
+    # Read Halifax CSV and write a cleaned CSV for Actual
+    with open(in_path, newline="", encoding="utf-8-sig") as f_in, \
+         open(out_path, "w", newline="", encoding="utf-8") as f_out:
+
+        reader = csv.DictReader(f_in)
+
+        # Output columns tailored for Actual’s CSV import
+        fieldnames = ["Date", "Payee", "Description", "Amount"]
+        writer = csv.DictWriter(f_out, fieldnames=fieldnames)
+        writer.writeheader()
+
+        for row in reader:
+            if not row:
+                continue
+
+            # Date in Halifax export (dd/mm/yyyy)
+            date = (row.get("Transaction Date") or "").strip()
+            if not date:
+                # Skip lines without a date
+                continue
+
+            desc = (row.get("Transaction Description") or "").strip()
+            payee = desc or (row.get("Transaction Type") or "").strip()
+
+            # Halifax has separate Debit / Credit columns
+            debit_str = (row.get("Debit Amount") or "").replace(",", "").strip()
+            credit_str = (row.get("Credit Amount") or "").replace(",", "").strip()
+
+            amount = None
+
+            # Debits (money going out) → negative
+            if debit_str:
+                try:
+                    amount = -Decimal(debit_str)
+                except InvalidOperation:
+                    amount = None
+
+            # Credits (money coming in) → positive
+            elif credit_str:
+                try:
+                    amount = Decimal(credit_str)
+                except InvalidOperation:
+                    amount = None
+
+            # If we still don't have an amount, skip the row
+            if amount is None:
+                continue
+
+            key = make_key(date, payee, desc, amount)
+            if key in seen_keys:
+                skipped_count += 1
+                continue
+
+            seen_keys.add(key)
+            written_count += 1
+
+            writer.writerow({
+                "Date": date,
+                "Payee": payee,
+                "Description": desc,
+                "Amount": f"{amount:.2f}",
+            })
+
+    # Keep the state from growing forever – remember last N keys
+    max_keys = 50000
+    seen_list = list(seen_keys)
+    if len(seen_list) > max_keys:
+        seen_list = seen_list[-max_keys:]
+
+    save_state({"seen_keys": seen_list})
+
+    print(f"Written cleaned file to {out_path}")
+    print(f"  New transactions written: {written_count}")
+    print(f"  Transactions skipped as duplicates: {skipped_count}")
+
+
+def main():
+    if len(sys.argv) < 2:
+        print("Usage: python clean-halifax-actual.py input.csv [output.csv]")
+        sys.exit(1)
+
+    in_path = Path(sys.argv[1])
+
+    if len(sys.argv) >= 3:
+        out_path = Path(sys.argv[2])
+    else:
+        # Default to inputname_actual.csv
+        out_path = in_path.with_name(in_path.stem + "_actual.csv")
+
+    convert(in_path, out_path)
+
+
+if __name__ == "__main__":
+    main()

legacy/halifax/halifax_state.json

@@ -0,0 +1,29 @@
+{
+  "seen_keys": [
+    "2025-11-03|naveed qayyum|naveed qayyum|-100.00",
+    "2025-11-13|mfg new john stree|mfg new john stree|-20.00",
+    "2025-11-28|naveed qayyum|naveed qayyum|-50.00",
+    "2025-11-27|mfg new john stree|mfg new john stree|-15.01",
+    "2025-11-27|subway @mfg new jo|subway @mfg new jo|-1.49",
+    "2025-11-20|n qayyum|n qayyum|10.00",
+    "2025-11-21|wm morrisons store|wm morrisons store|-11.65",
+    "2025-11-03|mrs farzana k qayy|mrs farzana k qayy|-100.00",
+    "2025-11-18|hockley service st|hockley service st|-30.01",
+    "2025-11-26|refresh vending|refresh vending|-3.00",
+    "2025-11-25|hockley service st|hockley service st|-35.01",
+    "2025-11-17|n qayyum|n qayyum|30.00",
+    "2025-11-28|microlise limited|microlise limited|2058.30",
+    "2025-11-11|sky digital|sky digital|-27.00",
+    "2025-11-03|ummah welfare trus|ummah welfare trus|-50.00",
+    "2025-11-20|www.voxi.co.uk|www.voxi.co.uk|-10.00",
+    "2025-11-20|mfg new john stree|mfg new john stree|-24.15",
+    "2025-11-05|hockley service st|hockley service st|-30.01",
+    "2025-11-03|amina qayyum|amina qayyum|-300.00",
+    "2025-11-06|the gym ltd|the gym ltd|-17.99",
+    "2025-11-28|mrs farzana k qayy|mrs farzana k qayy|-100.00",
+    "2025-11-17|naveed qayyum|naveed qayyum|-100.00",
+    "2025-11-24|p.o. 107 lozells r|p.o. 107 lozells r|-300.00",
+    "2025-11-10|morr birmingham ca|morr birmingham ca|-40.00",
+    "2025-11-03|lnk notemachine|lnk notemachine|-250.00"
+  ]
+}

legacy/halifax/new-cleaned.py

@@ -0,0 +1,99 @@
+#!/usr/bin/env python3
+
+import csv
+from decimal import Decimal, InvalidOperation
+import sys
+from pathlib import Path
+import hashlib
+from collections import defaultdict
+
+
+def transaction_hash(date, payee, desc, amount):
+    """Generate a stable hash for each transaction."""
+    base = f"{date}|{payee}|{desc}|{amount}"
+    return hashlib.md5(base.encode("utf-8")).hexdigest()[:10]  # short ID
+
+
+def convert(in_path, out_path):
+    with open(in_path, newline="", encoding="utf-8-sig") as f_in, \
+         open(out_path, "w", newline="", encoding="utf-8") as f_out:
+
+        reader = csv.DictReader(f_in)
+
+        # Add UniqueID field to prevent Actual from treating repeated merchants as duplicates
+        fieldnames = ["Date", "Payee", "Description", "Amount", "UniqueID"]
+        writer = csv.DictWriter(f_out, fieldnames=fieldnames)
+        writer.writeheader()
+
+        seen_hashes = defaultdict(int)
+        skipped = 0
+
+        for row in reader:
+            if not row:
+                continue
+
+            date = (row.get("Transaction Date") or "").strip()
+            if not date:
+                continue
+
+            desc = (row.get("Transaction Description") or "").strip()
+            payee = desc or (row.get("Transaction Type") or "").strip()
+
+            debit_str = (row.get("Debit Amount") or "").replace(",", "").strip()
+            credit_str = (row.get("Credit Amount") or "").replace(",", "").strip()
+            amount = None
+
+            if debit_str:
+                try:
+                    amount = -Decimal(debit_str)
+                except InvalidOperation:
+                    continue
+            elif credit_str:
+                try:
+                    amount = Decimal(credit_str)
+                except InvalidOperation:
+                    continue
+            else:
+                continue
+
+            # Generate transaction fingerprint
+            unique_id = transaction_hash(date, payee, desc, amount)
+
+            # Check if we've seen this transaction hash already
+            seen_hashes[unique_id] += 1
+            if seen_hashes[unique_id] > 1:
+                # Optional: skip true duplicates or just warn
+                print(f"⚠️ Duplicate detected: {date} | {payee} | {amount}")
+                skipped += 1
+                continue
+
+            writer.writerow({
+                "Date": date,
+                "Payee": payee,
+                "Description": desc,
+                "Amount": f"{amount:.2f}",
+                "UniqueID": unique_id,
+            })
+
+    print(f"\n✅ Written cleaned file to {out_path}")
+    if skipped:
+        print(f"⚠️ Skipped {skipped} duplicate entries based on content hash.")
+
+
+def main():
+    if len(sys.argv) < 2:
+        print("Usage: python clean_halifax_actual.py input.csv [output.csv]")
+        sys.exit(1)
+
+    in_path = Path(sys.argv[1])
+
+    if len(sys.argv) >= 3:
+        out_path = Path(sys.argv[2])
+    else:
+        out_path = in_path.with_name(in_path.stem + "_actual.csv")
+
+    convert(in_path, out_path)
+
+
+if __name__ == "__main__":
+    main()