Diff of
/tests/unit/str/test_str.py
[000000]
..
[79668b]
Switch to unified view
| a | b/tests/unit/str/test_str.py | ||
|---|---|---|---|
| 1 | import docdeid as dd |
||
| 2 | |||
| 3 | from deduce.str import ( |
||
| 4 | Acronimify, |
||
| 5 | FilterBasedOnLookupSet, |
||
| 6 | RemoveValues, |
||
| 7 | TakeLastToken, |
||
| 8 | TitleCase, |
||
| 9 | UpperCase, |
||
| 10 | UpperCaseFirstChar, |
||
| 11 | ) |
||
| 12 | |||
| 13 | |||
| 14 | class TestStr: |
||
| 15 | def test_uppercase(self): |
||
| 16 | processor = UpperCase() |
||
| 17 | |||
| 18 | assert processor.process("test") == "TEST" |
||
| 19 | assert processor.process("Test") == "TEST" |
||
| 20 | assert processor.process("TEST") == "TEST" |
||
| 21 | assert processor.process("123") == "123" |
||
| 22 | assert processor.process("test_123") == "TEST_123" |
||
| 23 | |||
| 24 | def test_uppercase_first_char(self): |
||
| 25 | processor = UpperCaseFirstChar() |
||
| 26 | |||
| 27 | assert processor.process("test") == "Test" |
||
| 28 | assert processor.process("Test") == "Test" |
||
| 29 | assert processor.process("t") == "T" |
||
| 30 | assert processor.process("T") == "T" |
||
| 31 | assert processor.process("A3") == "A3" |
||
| 32 | assert processor.process("a3") == "A3" |
||
| 33 | |||
| 34 | def test_titlecase(self): |
||
| 35 | processor = TitleCase() |
||
| 36 | |||
| 37 | assert processor.process("test") == "Test" |
||
| 38 | assert processor.process("Test") == "Test" |
||
| 39 | assert processor.process("Test test") == "Test Test" |
||
| 40 | assert processor.process("t") == "T" |
||
| 41 | assert processor.process("T") == "T" |
||
| 42 | assert processor.process("T t") == "T T" |
||
| 43 | assert processor.process("A3") == "A3" |
||
| 44 | assert processor.process("a3") == "A3" |
||
| 45 | assert processor.process("a3 a4") == "A3 A4" |
||
| 46 | |||
| 47 | def test_take_last_token(self): |
||
| 48 | processor = TakeLastToken() |
||
| 49 | |||
| 50 | assert processor.process("test") == "test" |
||
| 51 | assert processor.process("dit is een test") == "test" |
||
| 52 | assert processor.process("") == "" |
||
| 53 | |||
| 54 | def test_remove_values(self): |
||
| 55 | processor = RemoveValues(filter_values=["de", "het", "een"]) |
||
| 56 | |||
| 57 | assert processor.process("de boot") == "boot" |
||
| 58 | assert processor.process("debiet") == "debiet" |
||
| 59 | assert ( |
||
| 60 | processor.process("van het Schip") == "vanSchip" |
||
| 61 | ) # TODO Is this intended? |
||
| 62 | assert processor.process("nummer een") == "nummer" |
||
| 63 | |||
| 64 | def test_acronimify(self): |
||
| 65 | processor = Acronimify() |
||
| 66 | |||
| 67 | assert processor.process("Elizabeth Tweesteden Ziekenhuis") == "ETZ" |
||
| 68 | assert processor.process("Umcu") == "U" |
||
| 69 | assert processor.process("Universitair Medisch Centrum Utrecht") == "UMCU" |
||
| 70 | assert processor.process("universitair medisch centrum utrecht") == "umcu" |
||
| 71 | |||
| 72 | def test_filter_based_on_lookupset(self): |
||
| 73 | lookup_set = dd.ds.LookupSet() |
||
| 74 | lookup_set.add_items_from_iterable(["arts", "bakker", "slager"]) |
||
| 75 | |||
| 76 | processor = FilterBasedOnLookupSet(filter_set=lookup_set) |
||
| 77 | |||
| 78 | assert processor.filter("") |
||
| 79 | assert processor.filter("visser") |
||
| 80 | assert not processor.filter("arts") |
||
| 81 | assert not processor.filter("bakker") |
||
| 82 | assert not processor.filter("slager") |