drain3学习笔记

原创

已于 2024-05-05 18:36:35 修改 · 1.1k 阅读

标签

#自然语言处理

收录于

于 2024-05-05 18:33:36 首次发布

介绍

由于众所周知的原因，Github访问不稳定。官网虽然介绍，但是案例连接无效，因此保存于此，方便参考学习。

配置

官网样例（GitHub）

drain3.ini

[SNAPSHOT]
snapshot_interval_minutes = 10
compress_state = True

[MASKING]
masking = [
          {"regex_pattern":"((?<=[^A-Za-z0-9])|^)(([0-9a-f]{2,}:){3,}([0-9a-f]{2,}))((?=[^A-Za-z0-9])|$)", "mask_with": "ID"},
          {"regex_pattern":"((?<=[^A-Za-z0-9])|^)(\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3})((?=[^A-Za-z0-9])|$)", "mask_with": "IP"},
          {"regex_pattern":"((?<=[^A-Za-z0-9])|^)([0-9a-f]{6,} ?){3,}((?=[^A-Za-z0-9])|$)", "mask_with": "SEQ"},
          {"regex_pattern":"((?<=[^A-Za-z0-9])|^)([0-9A-F]{4} ?){4,}((?=[^A-Za-z0-9])|$)", "mask_with": "SEQ"},
          {"regex_pattern":"((?<=[^A-Za-z0-9])|^)(0x[a-f0-9A-F]+)((?=[^A-Za-z0-9])|$)", "mask_with": "HEX"},
          {"regex_pattern":"((?<=[^A-Za-z0-9])|^)([\\-\\+]?\\d+)((?=[^A-Za-z0-9])|$)", "mask_with": "NUM"},
          {"regex_pattern":"(?<=executed cmd )(\".+?\")", "mask_with": "CMD"}
          ]
mask_prefix = <:
mask_suffix = :>

[DRAIN]
# engine is Optional parameter. Engine will be "Drain" if the engine argument is not specified.
# engine has two options: 'Drain' and 'JaccardDrain'.
# engine = Drain
sim_th = 0.4
depth = 4
max_children = 100
max_clusters = 1024
extra_delimiters = ["_"]

[PROFILING]
enabled = True
report_sec = 30