| 1 | """Test of gis library tokenizing of text
|
|---|
| 2 |
|
|---|
| 3 | @author Vaclav Petras
|
|---|
| 4 | """
|
|---|
| 5 |
|
|---|
| 6 | from grass.gunittest.case import TestCase
|
|---|
| 7 | from grass.gunittest.main import test
|
|---|
| 8 |
|
|---|
| 9 | import grass.lib.gis as libgis
|
|---|
| 10 |
|
|---|
| 11 | # TODO: add tests for content (now testing only number of items)
|
|---|
| 12 |
|
|---|
| 13 |
|
|---|
| 14 | class TokenizeTestCase(TestCase):
|
|---|
| 15 | """Test C function G_tokenize() from gis library"""
|
|---|
| 16 |
|
|---|
| 17 | def test_tokenize_comma(self):
|
|---|
| 18 | """Test G_tokenize with comma as delim"""
|
|---|
| 19 | tokens = libgis.G_tokenize("a,b,c,d", ",")
|
|---|
| 20 | num_of_tokens = libgis.G_number_of_tokens(tokens)
|
|---|
| 21 | self.assertEqual(num_of_tokens, 4, msg="Got wrong number of tokens")
|
|---|
| 22 |
|
|---|
| 23 | def test_tokenize_alternative_delim(self):
|
|---|
| 24 | """Test G_tokenize with semi colon as delim"""
|
|---|
| 25 | tokens = libgis.G_tokenize("a;b;c", ";")
|
|---|
| 26 | num_of_tokens = libgis.G_number_of_tokens(tokens)
|
|---|
| 27 | self.assertEqual(num_of_tokens, 3, msg="Got wrong number of tokens")
|
|---|
| 28 |
|
|---|
| 29 | def test_tokenize_with_text_delim(self):
|
|---|
| 30 | """Test G_tokenize with comma as delim and single quote text delim
|
|---|
| 31 |
|
|---|
| 32 | Expecting the 'wrong' number of tokens here.
|
|---|
| 33 | """
|
|---|
| 34 | tokens = libgis.G_tokenize("a,'b,c',d", ",")
|
|---|
| 35 | num_of_tokens = libgis.G_number_of_tokens(tokens)
|
|---|
| 36 | self.assertEqual(
|
|---|
| 37 | num_of_tokens, 4,
|
|---|
| 38 | msg="Got wrong number of tokens (expecting that the text"
|
|---|
| 39 | "delimiter is ignored)")
|
|---|
| 40 | # alternatively this can be done using test with expected failure
|
|---|
| 41 |
|
|---|
| 42 |
|
|---|
| 43 | class Tokenize2TestCase(TestCase):
|
|---|
| 44 | """Test C function G_tokenize2() from gis library"""
|
|---|
| 45 |
|
|---|
| 46 | def test_tokenize2_comma(self):
|
|---|
| 47 | """Test G_tokenize2 without any text delim"""
|
|---|
| 48 | tokens = libgis.G_tokenize2("a,b,c,d", ",", "'")
|
|---|
| 49 | num_of_tokens = libgis.G_number_of_tokens(tokens)
|
|---|
| 50 | self.assertEqual(num_of_tokens, 4, msg="Got wrong number of tokens")
|
|---|
| 51 |
|
|---|
| 52 | def test_tokenize2_with_text_delim(self):
|
|---|
| 53 | """Test G_tokenize2 with , as delim and single quote text delim"""
|
|---|
| 54 | tokens = libgis.G_tokenize2("a,'b,c',d", ",", "'")
|
|---|
| 55 | num_of_tokens = libgis.G_number_of_tokens(tokens)
|
|---|
| 56 | self.assertEqual(num_of_tokens, 3, msg="Got wrong number of tokens")
|
|---|
| 57 |
|
|---|
| 58 | def test_tokenize2_with_alternative_text_delim(self):
|
|---|
| 59 | """Test G_tokenize2 with ; as delim and double quote text delim"""
|
|---|
| 60 | tokens = libgis.G_tokenize2('a;"b;c";d', ';', '"')
|
|---|
| 61 | num_of_tokens = libgis.G_number_of_tokens(tokens)
|
|---|
| 62 | self.assertEqual(num_of_tokens, 3, msg="Got wrong number of tokens")
|
|---|
| 63 |
|
|---|
| 64 | def test_tokenize2_with_text_delim_more_text_tokens(self):
|
|---|
| 65 | """Test G_tokenize2 with comma as delim and hash as text delim"""
|
|---|
| 66 | tokens = libgis.G_tokenize2("a,#b,c#,#5,d#,#7,2#", ",", "#")
|
|---|
| 67 | num_of_tokens = libgis.G_number_of_tokens(tokens)
|
|---|
| 68 | self.assertEqual(num_of_tokens, 4, msg="Got wrong number of tokens")
|
|---|
| 69 |
|
|---|
| 70 | def test_tokenize2_with_real_text(self):
|
|---|
| 71 | """Test G_tokenize2 with real world text"""
|
|---|
| 72 | tokens = libgis.G_tokenize2(
|
|---|
| 73 | '440,617722.81,3464034.494,951.987,'
|
|---|
| 74 | '"Low Erosion (1,5)","High Deposition (8,6)"',
|
|---|
| 75 | ',', '"')
|
|---|
| 76 | num_of_tokens = libgis.G_number_of_tokens(tokens)
|
|---|
| 77 | self.assertEqual(num_of_tokens, 6, msg="Got wrong number of tokens")
|
|---|
| 78 |
|
|---|
| 79 |
|
|---|
| 80 | if __name__ == '__main__':
|
|---|
| 81 | test()
|
|---|
