sonatoki 0.3.2__py3-none-any.whl → 0.3.3__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
sonatoki/utils.py CHANGED
@@ -1,12 +1,15 @@
1
1
  # STL
2
2
  import re
3
- from typing import Set, List, Iterable
3
+ import itertools
4
+ from typing import Set, List, TypeVar, Iterable
4
5
 
5
6
  # LOCAL
6
7
  from sonatoki.Cleaners import Lowercase, ConsecutiveDuplicates
7
8
 
8
9
  TO_ESCAPE = ["\\", "^", "[", "]", "-"]
9
10
 
11
+ T = TypeVar("T")
12
+
10
13
 
11
14
  def prep_dictionary(words: Iterable[str]) -> Set[str]:
12
15
  out: Set[str] = set()
@@ -19,7 +22,8 @@ def prep_dictionary(words: Iterable[str]) -> Set[str]:
19
22
 
20
23
 
21
24
  def regex_escape(s: str) -> str:
22
- """Escape all characters which must be escaped when embedded in a character class."""
25
+ """Escape all characters which must be escaped when embedded in a character
26
+ class."""
23
27
  for c in TO_ESCAPE:
24
28
  s = s.replace(c, rf"\{c}") # one backslash
25
29
  return s
@@ -69,10 +73,24 @@ def find_unicode_chars(ranges: List[str]) -> str:
69
73
  return "".join(result)
70
74
 
71
75
 
76
+ def overlapping_pairs(iterable: Iterable[T]) -> Iterable[T]:
77
+ "s -> (s0,s1), (s1,s2), (s2, s3), ..."
78
+ return overlapping_ntuples(iterable, n=2)
79
+
80
+
81
+ def overlapping_ntuples(iterable: Iterable[T], n: int) -> Iterable[T]:
82
+ teed = itertools.tee(iterable, n)
83
+ for i in range(1, n):
84
+ for j in range(i):
85
+ _ = next(teed[i], None)
86
+ # offset start by position
87
+
88
+ # ends when any iter is empty; all groups will be same size
89
+ return zip(*teed)
90
+
91
+
72
92
  if __name__ == "__main__":
73
- """
74
- Helper script to fetch UNICODE_PUNCT in constants.py
75
- """
93
+ """Helper script to fetch UNICODE_PUNCT in constants.py."""
76
94
 
77
95
  PUNCT_CATEGORIES = {
78
96
  "Pc",
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: sonatoki
3
- Version: 0.3.2
3
+ Version: 0.3.3
4
4
  Summary: ilo li moku e toki li pana e sona ni: ni li toki ala toki pona?
5
5
  Author-Email: "jan Kekan San (@gregdan3)" <gregory.danielson3@gmail.com>
6
6
  License: AGPL-3.0-or-later
@@ -0,0 +1,18 @@
1
+ sonatoki-0.3.3.dist-info/METADATA,sha256=b78h2-lsc4aBzkEWrzXTslfvJb-ZVbFjCpgPOF_kYrg,6341
2
+ sonatoki-0.3.3.dist-info/WHEEL,sha256=SOP-4bEE0jbVaCHQGVvF08uWxk5rcSsfEybvoQVHlD8,90
3
+ sonatoki-0.3.3.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
4
+ sonatoki/Cleaners.py,sha256=x2dT3MpDUfbrHA0EP2D3n1sTiKFFi5jw9ha-1dX973o,1958
5
+ sonatoki/Configs.py,sha256=ZNKJGeAxgolAxqNSeS7iADvQEcN4X3tY0iaoiAaL95U,4160
6
+ sonatoki/Filters.py,sha256=mpJBl-YPMF-Yl6mKFXf0D6DwkPR6H424RlvrkSeh4Dc,10714
7
+ sonatoki/Preprocessors.py,sha256=nvAzxpWP9WwT6gOCKcuiz5F8xYDdKIt9bOVUvy9o-G0,4459
8
+ sonatoki/Scorers.py,sha256=LRQLgXKTU2VqhkMHFPVxyVt83DXf85_zrpDGk4ThU24,3811
9
+ sonatoki/Tokenizers.py,sha256=So5_Tu6J98MD3yVcwB_X3lw2uMG0TN6XHcTbQjFCu5Q,4254
10
+ sonatoki/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
11
+ sonatoki/__main__.py,sha256=6xc-wIrrFo9wTyn4zRQNAmqwmJBtVvCMwV-CrM-hueA,82
12
+ sonatoki/constants.py,sha256=wH3iR32-Ic7vSkrMjAZIvmIysTtkJ-KBVU5zv3Oamqs,12656
13
+ sonatoki/ilo.py,sha256=yyLgNPI0Hmb4f1BzX6IRHr11FPChfL2xDR_9odlr8_8,3849
14
+ sonatoki/linku.json,sha256=fm4-dks5s9x1bs7q82GNngAedVCWilMPCQ_o-j35QL0,270950
15
+ sonatoki/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
16
+ sonatoki/sandbox.json,sha256=zPtZgJ_CpJa-2Den0gTNlk52f-YEwFVcjMarQXeeu5U,77563
17
+ sonatoki/utils.py,sha256=L984aXxvzfJaZ6GSWRKs7LweOGZYTLK11CdAhpLQr0g,4067
18
+ sonatoki-0.3.3.dist-info/RECORD,,
@@ -1,4 +1,4 @@
1
1
  Wheel-Version: 1.0
2
- Generator: pdm-backend (2.3.0)
2
+ Generator: pdm-backend (2.3.1)
3
3
  Root-Is-Purelib: true
4
4
  Tag: py3-none-any
@@ -1,18 +0,0 @@
1
- sonatoki-0.3.2.dist-info/METADATA,sha256=9cnhaaYFLxN3uaubD0jfTAU_CC9wUGtzho4fs1UGLFc,6341
2
- sonatoki-0.3.2.dist-info/WHEEL,sha256=vnE8JVcI2Wz7GRKorsPArnBdnW2SWKWGow5gu5tHlRU,90
3
- sonatoki-0.3.2.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
4
- sonatoki/Cleaners.py,sha256=m0j1a1vs9Mdqp724r9Xfh1Y_tyP6GYCkihv8rH8m7lA,1871
5
- sonatoki/Configs.py,sha256=o_uFp-Z6sbhbMi8drgQTkdu8S5LaTr0Xnns6Cg0cHSY,3548
6
- sonatoki/Filters.py,sha256=-7zIV_IBsbASR7pF5WuoABNtBW5a7L135Ev_Rrn35o4,10664
7
- sonatoki/Preprocessors.py,sha256=aMXXuFBDlJudvzvukvCa7BixuROXXEb62un7I-TGOGs,4441
8
- sonatoki/Scorers.py,sha256=W-1uYiqjsDejJzoe592ixs7wHazjJXPhuo-41zuJ26U,3643
9
- sonatoki/Tokenizers.py,sha256=So5_Tu6J98MD3yVcwB_X3lw2uMG0TN6XHcTbQjFCu5Q,4254
10
- sonatoki/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
11
- sonatoki/__main__.py,sha256=6xc-wIrrFo9wTyn4zRQNAmqwmJBtVvCMwV-CrM-hueA,82
12
- sonatoki/constants.py,sha256=qq1_ZTsVKG_d7nqlJv3a-KS6ZvYwfUSHWA--e0BuyXc,13268
13
- sonatoki/ilo.py,sha256=yyLgNPI0Hmb4f1BzX6IRHr11FPChfL2xDR_9odlr8_8,3849
14
- sonatoki/linku.json,sha256=B5KNdhyM5UEfMciROgh1ECHr3i-ASBeMvwrkzNJX47c,271013
15
- sonatoki/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
16
- sonatoki/sandbox.json,sha256=hx6LRsfvmmTtqXcXIyCsfSaGK3DZ-GCdbM8xhZQBHoA,77650
17
- sonatoki/utils.py,sha256=OMaRyoNvKGKYQCBDjQyaCI58-wMpQ0wrrNjTJKsEZ9Y,3550
18
- sonatoki-0.3.2.dist-info/RECORD,,