seed_gen.py

import pandas as pd
import yaml

# 读取CSV文件
df = pd.read_csv('dex_base_trades_seed.csv')

# 初始化schema字典
schema = {
    "version": 2,
    "seeds": []
}

# 按'project'和'blockchain'字段分组并处理CSV文件和schema
for (project, blockchain), group in df.groupby(['project', 'blockchain']):
    # 只取'project'字段中的第一个词
    project_name = project.split()[0]
    filename = f"{project_name}_{blockchain}_base_trades_seed.csv"
    group.to_csv(filename, index=False)

    # 添加到schema字典
    seed_name = f"{project_name}_{blockchain}_base_trades_seed"
    seed_config = {
        "name": seed_name,
        "config": {
            "column_types": {
                "blockchain": "varchar",
                "project": "varchar",
                "version": "varchar",
                "tx_hash": "varbinary",
                "evt_index": "uint256",
                "block_number": "uint256",
                "token_bought_address": "varbinary",
                "token_sold_address": "varbinary",
                "token_bought_amount_raw": "uint256",
                "token_sold_amount_raw": "uint256",
                "block_date": "timestamp"
            }
        }
    }
    schema["seeds"].append(seed_config)

# 将schema字典转换为YAML格式字符串
schema_yaml = yaml.dump(schema, sort_keys=False)

# 打印或保存schema
# print(schema_yaml)
# 可以选择将schema写入文件
with open('schema.yml', 'w') as file:
    file.write(schema_yaml)