1
|
|
|
/* |
2
|
|
|
* Copyright 2014-2020, Armenak Grigoryan, and individual contributors as indicated |
3
|
|
|
* by the @authors tag. See the copyright.txt in the distribution for a |
4
|
|
|
* full listing of individual contributors. |
5
|
|
|
* |
6
|
|
|
* This is free software; you can redistribute it and/or modify it |
7
|
|
|
* under the terms of the GNU Lesser General Public License as |
8
|
|
|
* published by the Free Software Foundation; either version 2.1 of |
9
|
|
|
* the License, or (at your option) any later version. |
10
|
|
|
* |
11
|
|
|
* This software is distributed in the hope that it will be useful, |
12
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
13
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
14
|
|
|
* Lesser General Public License for more details. |
15
|
|
|
*/ |
16
|
|
|
package com.strider.datadefender; |
17
|
|
|
|
18
|
|
|
import com.strider.datadefender.discoverer.Discoverer; |
19
|
|
|
import java.io.File; |
20
|
|
|
import java.util.List; |
21
|
|
|
import java.util.Optional; |
22
|
|
|
|
23
|
|
|
import picocli.CommandLine.Option; |
24
|
|
|
|
25
|
|
|
import lombok.Getter; |
26
|
|
|
import lombok.extern.log4j.Log4j2; |
27
|
|
|
|
28
|
|
|
/** |
29
|
|
|
* Database configuration options for picocli. |
30
|
|
|
* |
31
|
|
|
* @author Zaahid Bateson |
32
|
|
|
*/ |
33
|
|
|
@Getter |
34
|
|
|
@Log4j2 |
35
|
|
|
public class ModelDiscoveryConfig { |
36
|
|
|
|
37
|
|
|
@Option(names = { "-l", "--limit" }, description = "Limit discovery to a set number of rows in a table", defaultValue = "1000") |
38
|
|
|
private Integer limit; |
39
|
|
|
|
40
|
|
|
private List<String> models; |
41
|
|
|
|
42
|
|
|
@Option(names = { "-e", "--extension" }, description = "Adds a call to an extension method " |
43
|
|
|
+ "(e.g. com.strider.datadefender.specialcase.SinDetector.detectSin)") |
44
|
|
|
private List<String> extensions; |
45
|
|
|
|
46
|
|
|
@Option(names = { "--model-file" }, description = "Adds a custom made opennlp TokenizerME file for data discovery.") |
47
|
|
|
private List<File> fileModels; |
48
|
|
|
|
49
|
|
|
@Option(names = { "--token-model" }, description = "Override the default built-in token model (English tokens, " |
50
|
|
|
+ "en-token.bin) with a custom token file for use by opennlp's TokenizerModel") |
51
|
|
|
private File tokenModel; |
52
|
|
|
|
53
|
|
|
@Option(names = { "--probability-threshold" }, description = "Minimum NLP match score to return results for", defaultValue = "0.55") |
54
|
|
|
private Double probabilityThreshold; |
55
|
|
|
|
56
|
|
|
@Option(names = { "--no-score-calculation" }, description = "If set, includes a column score", negatable = true) |
57
|
|
|
private Boolean calculateScore = true; |
58
|
|
|
|
59
|
|
|
@Option(names = { "--threshold-count" }, description = "Reports if number of rows found are greater than the defined threshold", defaultValue = "6") |
60
|
|
|
private Integer thresholdCount; |
61
|
|
|
|
62
|
|
|
@Option(names = { "--threshold-high" }, description = "Reports if number of high risk columns found are greater than the defined threshold", defaultValue = "3") |
63
|
|
|
private Integer thresholdHighRisk; |
64
|
|
|
|
65
|
|
|
@Option(names = { "-m", "--model" }, description = "Adds a built-in configured opennlp TokenizerME model for data discovery. " |
66
|
|
|
+ "Available models are: ${AVAILABLE-MODELS}") |
67
|
|
|
public void setModels(List<String> models) { |
68
|
|
|
Optional<String> unmatched = models.stream().filter((m) -> !Discoverer.BUILT_IN_MODELS.containsKey(m)).findFirst(); |
69
|
|
|
if (unmatched.isPresent()) { |
70
|
|
|
log.error( |
71
|
|
|
"A built-in model with the name \"{}\" does not exist. Please specify one of: {}", |
72
|
|
|
unmatched.get(), |
73
|
|
|
System.getProperty("AVAILABLE-MODELS") |
74
|
|
|
); |
75
|
|
|
throw new IllegalArgumentException("Unmatched built-in model."); |
76
|
|
|
} |
77
|
|
|
this.models = models; |
78
|
|
|
} |
79
|
|
|
} |
80
|
|
|
|