multi-source-data-cleaner-pro

EN: Production-grade data cleaning across heterogeneous sources (CSV/Excel/JSON/Parquet/SQL dumps/log files). Profiles schemas, detects encoding/delimiter, normalizes types, handles missing values, deduplicates fuzzy records, reconciles schema across sources, and outputs a clean unified dataset plus a full data-quality report. Use when user provides one or more dirty datasets and asks "清洗数据 / 合并数据 / 去重 / 缺失值处理 / data cleaning / dedup / schema reconcile". 中文：跨异构来源（CSV/Excel/JSON/Parquet/SQL 导出/日志文件）的工业级数据清洗。剖析 schema、自动识别编码与分隔符、归一化类型、处理缺失值、模糊去重、跨源字段对齐，输出统一的干净数据集与完整数据质量报告。当用户提供脏数据并要求"清洗/合并/去重/缺失值处理"时触发。

by @boboy-j (boboy)·MIT-0