Add script to generate LPS distribution JSON

scripts/generate-lps-distribution-json.py

@@ -0,0 +1,83 @@
+import sys
+import requests
+import pandas as pd
+import json
+import re
+
+def get_excel_download_url(google_sheet_url):
+    """
+    Convert a Google Sheets URL to its Excel export URL.
+    """
+    match = re.search(r'/d/([a-zA-Z0-9-_]+)', google_sheet_url)
+    if not match:
+        raise ValueError('Invalid Google Sheets URL')
+    sheet_id = match.group(1)
+    # Export the first sheet as Excel
+    return f'https://docs.google.com/spreadsheets/d/{sheet_id}/export?format=xlsx&id={sheet_id}'
+
+
+def download_excel(url, output_path):
+    """
+    Download the Excel file from the given URL.
+    """
+    response = requests.get(url)
+    if response.status_code != 200:
+        raise Exception(f'Failed to download file: {response.status_code}')
+    with open(output_path, 'wb') as f:
+        f.write(response.content)
+
+
+def convert_excel_to_json(excel_path, json_path):
+    """
+    Read the Excel file, extract columns from the 'Genesis Allocation' sheet, and save as JSON.
+    """
+    df = pd.read_excel(excel_path, sheet_name='Genesis Allocation')
+    # Ensure columns exist
+    required_columns = [
+        'Placeholder',
+        'Laconic Address',
+        'Total LPS Allocation',
+        'Lock (months)',
+        'Vest (months)'
+    ]
+    for col in required_columns:
+        if col not in df.columns:
+            raise Exception(f'Missing required column: {col}')
+
+    result = {}
+    for _, row in df.iterrows():
+        placeholder = str(row['Placeholder']) if not pd.isna(row['Placeholder']) else ''
+        laconic_address = str(row['Laconic Address']) if not pd.isna(row['Laconic Address']) else ''
+        # Use laconic_address as key if placeholder is missing or empty
+        key = placeholder if placeholder and placeholder.lower() != 'nan' else laconic_address
+        if not key or key.lower() == 'nan':
+            continue
+        entry = {
+            'total_lps_allocation': row['Total LPS Allocation'] if not pd.isna(row['Total LPS Allocation']) else None,
+            'lock_months': row['Lock (months)'] if not pd.isna(row['Lock (months)']) else None,
+            'vest_months': row['Vest (months)'] if not pd.isna(row['Vest (months)']) else None,
+            'laconic_address': row['Laconic Address'] if not pd.isna(row['Laconic Address']) else None
+        }
+        result[key] = entry
+
+    with open(json_path, 'w') as f:
+        json.dump(result, f, indent=2)
+
+
+def main():
+    if len(sys.argv) != 2:
+        print('Usage: python download_and_convert_google_sheet.py <google_sheet_url>')
+        sys.exit(1)
+    google_sheet_url = sys.argv[1]
+    excel_url = get_excel_download_url(google_sheet_url)
+    excel_path = 'sheet.xlsx'
+    json_path = 'distribution.json'
+    print(f'Downloading Excel file from: {excel_url}')
+    download_excel(excel_url, excel_path)
+    print('Converting Excel to JSON...')
+    convert_excel_to_json(excel_path, json_path)
+    print(f'JSON saved to {json_path}')
+
+
+if __name__ == '__main__':
+    main()