sonatoki 0.6.0__tar.gz → 0.6.2__tar.gz
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-0.6.0 → sonatoki-0.6.2}/PKG-INFO +1 -1
- {sonatoki-0.6.0 → sonatoki-0.6.2}/pyproject.toml +1 -1
- {sonatoki-0.6.0 → sonatoki-0.6.2}/src/sonatoki/constants.py +2 -2
- {sonatoki-0.6.0 → sonatoki-0.6.2}/tests/test_ilo.py +2 -1
- {sonatoki-0.6.0 → sonatoki-0.6.2}/LICENSE +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/README.md +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/src/sonatoki/Cleaners.py +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/src/sonatoki/Configs.py +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/src/sonatoki/Filters.py +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/src/sonatoki/Preprocessors.py +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/src/sonatoki/Scorers.py +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/src/sonatoki/Tokenizers.py +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/src/sonatoki/__init__.py +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/src/sonatoki/__main__.py +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/src/sonatoki/alphabetic.txt +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/src/sonatoki/ilo.py +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/src/sonatoki/linku.json +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/src/sonatoki/py.typed +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/src/sonatoki/sandbox.json +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/src/sonatoki/syllabic.txt +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/src/sonatoki/utils.py +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/tests/__init__.py +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/tests/test_cleaners.py +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/tests/test_filters.py +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/tests/test_preprocessors.py +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/tests/test_properties.py +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/tests/test_scorers.py +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/tests/test_tokenize.py +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/tests/test_utils.py +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/tests/tokenize_cases/tokenize_sentences_tok.yml +0 -0
- {sonatoki-0.6.0 → sonatoki-0.6.2}/tests/tokenize_cases/tokenize_words_tok.yml +0 -0
@@ -498,10 +498,10 @@ ALL_PUNCT = "".join(sorted(list(set(POSIX_PUNCT + UNICODE_PUNCT))))
|
|
498
498
|
ALL_PUNCT_RANGES_STR = "".join(find_unicode_ranges(ALL_PUNCT))
|
499
499
|
# combined bc the result could be simpler
|
500
500
|
|
501
|
-
SENTENCE_PUNCT = """.?!:;()[-]
|
501
|
+
SENTENCE_PUNCT = """.?!:;()[-]·•…"""
|
502
502
|
# NOTE: quotes were previously included, but in TP they are *not* reliably sentence boundaries
|
503
503
|
|
504
|
-
INTRA_WORD_PUNCT = """-'"""
|
504
|
+
INTRA_WORD_PUNCT = """-'’"""
|
505
505
|
|
506
506
|
|
507
507
|
LINKU = Path(__file__).resolve().parent / Path("linku.json")
|
@@ -192,10 +192,11 @@ FALSE_NEGATIVES = [
|
|
192
192
|
"poan",
|
193
193
|
"mtue",
|
194
194
|
"mi nasa B^)", # emoticon
|
195
|
+
"lete li ike x.x", # this is an emoticon but passes because 'x' is in Filters.Miscellaneous
|
195
196
|
]
|
196
197
|
|
197
198
|
FALSE_POSITIVES = [
|
198
|
-
"
|
199
|
+
"Knowing a little toki pona",
|
199
200
|
]
|
200
201
|
|
201
202
|
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|