| 1 | # To fully test this module, we would need a copy of the stringprep tables.
|
|---|
| 2 | # Since we don't have them, this test checks only a few codepoints.
|
|---|
| 3 |
|
|---|
| 4 | from test.test_support import verify, vereq
|
|---|
| 5 |
|
|---|
| 6 | import stringprep
|
|---|
| 7 | from stringprep import *
|
|---|
| 8 |
|
|---|
| 9 | verify(in_table_a1(u"\u0221"))
|
|---|
| 10 | verify(not in_table_a1(u"\u0222"))
|
|---|
| 11 |
|
|---|
| 12 | verify(in_table_b1(u"\u00ad"))
|
|---|
| 13 | verify(not in_table_b1(u"\u00ae"))
|
|---|
| 14 |
|
|---|
| 15 | verify(map_table_b2(u"\u0041"), u"\u0061")
|
|---|
| 16 | verify(map_table_b2(u"\u0061"), u"\u0061")
|
|---|
| 17 |
|
|---|
| 18 | verify(map_table_b3(u"\u0041"), u"\u0061")
|
|---|
| 19 | verify(map_table_b3(u"\u0061"), u"\u0061")
|
|---|
| 20 |
|
|---|
| 21 | verify(in_table_c11(u"\u0020"))
|
|---|
| 22 | verify(not in_table_c11(u"\u0021"))
|
|---|
| 23 |
|
|---|
| 24 | verify(in_table_c12(u"\u00a0"))
|
|---|
| 25 | verify(not in_table_c12(u"\u00a1"))
|
|---|
| 26 |
|
|---|
| 27 | verify(in_table_c12(u"\u00a0"))
|
|---|
| 28 | verify(not in_table_c12(u"\u00a1"))
|
|---|
| 29 |
|
|---|
| 30 | verify(in_table_c11_c12(u"\u00a0"))
|
|---|
| 31 | verify(not in_table_c11_c12(u"\u00a1"))
|
|---|
| 32 |
|
|---|
| 33 | verify(in_table_c21(u"\u001f"))
|
|---|
| 34 | verify(not in_table_c21(u"\u0020"))
|
|---|
| 35 |
|
|---|
| 36 | verify(in_table_c22(u"\u009f"))
|
|---|
| 37 | verify(not in_table_c22(u"\u00a0"))
|
|---|
| 38 |
|
|---|
| 39 | verify(in_table_c21_c22(u"\u009f"))
|
|---|
| 40 | verify(not in_table_c21_c22(u"\u00a0"))
|
|---|
| 41 |
|
|---|
| 42 | verify(in_table_c3(u"\ue000"))
|
|---|
| 43 | verify(not in_table_c3(u"\uf900"))
|
|---|
| 44 |
|
|---|
| 45 | verify(in_table_c4(u"\uffff"))
|
|---|
| 46 | verify(not in_table_c4(u"\u0000"))
|
|---|
| 47 |
|
|---|
| 48 | verify(in_table_c5(u"\ud800"))
|
|---|
| 49 | verify(not in_table_c5(u"\ud7ff"))
|
|---|
| 50 |
|
|---|
| 51 | verify(in_table_c6(u"\ufff9"))
|
|---|
| 52 | verify(not in_table_c6(u"\ufffe"))
|
|---|
| 53 |
|
|---|
| 54 | verify(in_table_c7(u"\u2ff0"))
|
|---|
| 55 | verify(not in_table_c7(u"\u2ffc"))
|
|---|
| 56 |
|
|---|
| 57 | verify(in_table_c8(u"\u0340"))
|
|---|
| 58 | verify(not in_table_c8(u"\u0342"))
|
|---|
| 59 |
|
|---|
| 60 | # C.9 is not in the bmp
|
|---|
| 61 | # verify(in_table_c9(u"\U000E0001"))
|
|---|
| 62 | # verify(not in_table_c8(u"\U000E0002"))
|
|---|
| 63 |
|
|---|
| 64 | verify(in_table_d1(u"\u05be"))
|
|---|
| 65 | verify(not in_table_d1(u"\u05bf"))
|
|---|
| 66 |
|
|---|
| 67 | verify(in_table_d2(u"\u0041"))
|
|---|
| 68 | verify(not in_table_d2(u"\u0040"))
|
|---|
| 69 |
|
|---|
| 70 | # This would generate a hash of all predicates. However, running
|
|---|
| 71 | # it is quite expensive, and only serves to detect changes in the
|
|---|
| 72 | # unicode database. Instead, stringprep.py asserts the version of
|
|---|
| 73 | # the database.
|
|---|
| 74 |
|
|---|
| 75 | # import hashlib
|
|---|
| 76 | # predicates = [k for k in dir(stringprep) if k.startswith("in_table")]
|
|---|
| 77 | # predicates.sort()
|
|---|
| 78 | # for p in predicates:
|
|---|
| 79 | # f = getattr(stringprep, p)
|
|---|
| 80 | # # Collect all BMP code points
|
|---|
| 81 | # data = ["0"] * 0x10000
|
|---|
| 82 | # for i in range(0x10000):
|
|---|
| 83 | # if f(unichr(i)):
|
|---|
| 84 | # data[i] = "1"
|
|---|
| 85 | # data = "".join(data)
|
|---|
| 86 | # h = hashlib.sha1()
|
|---|
| 87 | # h.update(data)
|
|---|
| 88 | # print p, h.hexdigest()
|
|---|
