Diff of
/tests/unit/test_redactor.py
[000000]
..
[79668b]
Switch to unified view
| a | b/tests/unit/test_redactor.py | ||
|---|---|---|---|
| 1 | import docdeid as dd |
||
| 2 | |||
| 3 | from deduce.redactor import DeduceRedactor |
||
| 4 | |||
| 5 | |||
| 6 | class TestDeduceRedactor: |
||
| 7 | def test_redact_patient(self): |
||
| 8 | proc = DeduceRedactor() |
||
| 9 | text = "Jan Jansen" |
||
| 10 | |||
| 11 | annotations = dd.AnnotationSet( |
||
| 12 | [ |
||
| 13 | dd.Annotation(text="Jan", start_char=0, end_char=3, tag="patient"), |
||
| 14 | dd.Annotation(text="Jansen", start_char=4, end_char=10, tag="patient"), |
||
| 15 | ] |
||
| 16 | ) |
||
| 17 | |||
| 18 | expected_text = "[PATIENT] [PATIENT]" |
||
| 19 | |||
| 20 | assert proc.redact(text, annotations) == expected_text |
||
| 21 | |||
| 22 | def test_redact_mixed(self): |
||
| 23 | proc = DeduceRedactor() |
||
| 24 | text = "Jan Jansen, wonende in Rotterdam" |
||
| 25 | |||
| 26 | annotations = dd.AnnotationSet( |
||
| 27 | [ |
||
| 28 | dd.Annotation( |
||
| 29 | text="Jan Jansen", start_char=0, end_char=10, tag="patient" |
||
| 30 | ), |
||
| 31 | dd.Annotation( |
||
| 32 | text="Rotterdam", start_char=23, end_char=32, tag="woonplaats" |
||
| 33 | ), |
||
| 34 | ] |
||
| 35 | ) |
||
| 36 | |||
| 37 | expected_text = "[PATIENT], wonende in [WOONPLAATS-1]" |
||
| 38 | |||
| 39 | assert proc.redact(text, annotations) == expected_text |
||
| 40 | |||
| 41 | def test_redact_count_multiple(self): |
||
| 42 | proc = DeduceRedactor() |
||
| 43 | text = "Jan Jansen, wonende in Rotterdam, verhuisd vanuit Groningen" |
||
| 44 | |||
| 45 | annotations = dd.AnnotationSet( |
||
| 46 | [ |
||
| 47 | dd.Annotation( |
||
| 48 | text="Rotterdam", start_char=23, end_char=32, tag="woonplaats" |
||
| 49 | ), |
||
| 50 | dd.Annotation( |
||
| 51 | text="Groningen", start_char=50, end_char=59, tag="woonplaats" |
||
| 52 | ), |
||
| 53 | ] |
||
| 54 | ) |
||
| 55 | |||
| 56 | expected_text = ( |
||
| 57 | "Jan Jansen, wonende in [WOONPLAATS-1], verhuisd vanuit [WOONPLAATS-2]" |
||
| 58 | ) |
||
| 59 | |||
| 60 | assert proc.redact(text, annotations) == expected_text |
||
| 61 | |||
| 62 | def test_redact_count_multiple_fuzzy(self): |
||
| 63 | proc = DeduceRedactor() |
||
| 64 | text = "Jan Jansen, wonende in Ommen, verhuisd vanuit Emmen" |
||
| 65 | |||
| 66 | annotations = dd.AnnotationSet( |
||
| 67 | [ |
||
| 68 | dd.Annotation( |
||
| 69 | text="Ommen", start_char=23, end_char=28, tag="woonplaats" |
||
| 70 | ), |
||
| 71 | dd.Annotation( |
||
| 72 | text="Emmen", start_char=46, end_char=51, tag="woonplaats" |
||
| 73 | ), |
||
| 74 | ] |
||
| 75 | ) |
||
| 76 | |||
| 77 | expected_text = ( |
||
| 78 | "Jan Jansen, wonende in [WOONPLAATS-1], verhuisd vanuit [WOONPLAATS-1]" |
||
| 79 | ) |
||
| 80 | |||
| 81 | assert proc.redact(text, annotations) == expected_text |