Files
scud_ai/scripts/diagnostics/make_etl_snapshot.py
T

98 lines
3.4 KiB
Python

#!/usr/bin/env python3
"""
===============================================================================
FILE: scripts/diagnostics/make_etl_snapshot.py
ROLE: Генерация компактного слепка ETL-конвейера, генераторов отчетов и БД.
===============================================================================
"""
import os
ROOT_DIR = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", ".."))
OUTPUT_FILE = os.path.join(ROOT_DIR, "etl_code_snapshot.md")
TARGET_FILES = [
# Конфигурация и точка входа
"config.py",
"exceptions.json",
"main_etl.py",
"scripts/db_cli.py",
# Крон скрипты
"scripts/cron/run_hourly_snapshot.sh",
"scripts/cron/run_reports_only.sh",
"scripts/cron/run_cron_etl.sh",
# Ядро БД
"core/connection.py",
"core/database.py",
"core/schema.py",
"core/repositories/scud_repo.py",
"core/repositories/zup_repo.py",
# Сервисный слой загрузки и реестров
"services/data_loader.py",
"services/scud_export.py",
"services/share_copier.py",
"services/excel_exporter.py",
"services/exceptions_repo.py",
"services/manual_absences_repo.py",
"services/zup_extractor.py",
"services/ai_verifier.py",
"services/knowledge_base.py",
"services/knowledge/service.py",
# Модули генерации отчетов Excel
"services/reports/styles.py",
"services/reports/calculators.py",
"services/reports/svodka_builder.py",
"services/reports/otchet_builder.py",
"services/reports/raw_scud_builder.py",
# Модули сборки Сводки, Отчета и запросы
"services/scud_etl/pipeline.py",
"services/scud_etl/merger.py",
"services/scud_etl/svodka_generator.py",
"services/scud_etl/otchet_generator.py",
"services/scud_etl/anomaly_detector.py",
"services/scud_etl/sql_queries.py",
"services/snapshots/service.py",
"services/tasks/repository.py",
"services/tasks/service.py"
]
def create_etl_snapshot():
content = ["# 📦 ETL-СЛЕПОК ИСХОДНОГО КОДА (СКУД ⟷ 1С & DB CORE)\n"]
included_count = 0
for rel_path in TARGET_FILES:
full_path = os.path.join(ROOT_DIR, rel_path)
if os.path.exists(full_path):
ext = os.path.splitext(rel_path)[1].replace(".", "")
lang_map = {
"py": "py",
"json": "json",
"sh": "bash"
}
lang = lang_map.get(ext, "text")
try:
with open(full_path, "r", encoding="utf-8") as f:
file_text = f.read()
content.append(f"## File: `./{rel_path}`\n```{lang}\n{file_text}\n```\n")
included_count += 1
except Exception as e:
print(f"[⚠️] Ошибка чтения {rel_path}: {e}")
else:
print(f"[ℹ️] Пропущен отсутствующий файл: {rel_path}")
with open(OUTPUT_FILE, "w", encoding="utf-8") as f:
f.write("\n".join(content))
size_kb = os.path.getsize(OUTPUT_FILE) / 1024
print(f"\n[✓] ETL-слепок создан: {OUTPUT_FILE}")
print(f" Включено файлов: {included_count} | Размер: {size_kb:.1f} KB\n")
if __name__ == "__main__":
create_etl_snapshot()