mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-20 19:09:21 +03:00
b0228d8ea6
* chore: add cython-linter dev dependency * fix: lexeme.pyx * fix: morphology.pxd * fix: tokenizer.pxd * fix: vocab.pxd * fix: morphology.pxd (line length) * ci: add cython-lint * ci: fix cython-lint call * Fix kb/candidate.pyx. * Fix kb/kb.pyx. * Fix kb/kb_in_memory.pyx. * Fix kb. * Fix training/ partially. * Fix training/. Ignore trailing whitespaces and too long lines. * Fix ml/. * Fix matcher/. * Fix pipeline/. * Fix tokens/. * Fix build errors. Fix vocab.pyx. * Fix cython-lint install and run. * Fix lexeme.pyx, parts_of_speech.pxd, vectors.pyx. Temporarily disable cython-lint execution. * Fix attrs.pyx, lexeme.pyx, symbols.pxd, isort issues. * Make cython-lint install conditional. Fix tokenizer.pyx. * Fix remaining files. Reenable cython-lint check. * Readded parentheses. * Fix test_build_dependencies(). * Add explanatory comment to cython-lint execution. --------- Co-authored-by: Raphael Mitsch <r.mitsch@outlook.com>
100 lines
1.1 KiB
Cython
100 lines
1.1 KiB
Cython
# Reserve 64 values for flag features
|
|
from . cimport symbols
|
|
|
|
|
|
cdef enum attr_id_t:
|
|
NULL_ATTR
|
|
IS_ALPHA
|
|
IS_ASCII
|
|
IS_DIGIT
|
|
IS_LOWER
|
|
IS_PUNCT
|
|
IS_SPACE
|
|
IS_TITLE
|
|
IS_UPPER
|
|
LIKE_URL
|
|
LIKE_NUM
|
|
LIKE_EMAIL
|
|
IS_STOP
|
|
IS_OOV_DEPRECATED
|
|
IS_BRACKET
|
|
IS_QUOTE
|
|
IS_LEFT_PUNCT
|
|
IS_RIGHT_PUNCT
|
|
IS_CURRENCY
|
|
|
|
FLAG19 = 19
|
|
FLAG20
|
|
FLAG21
|
|
FLAG22
|
|
FLAG23
|
|
FLAG24
|
|
FLAG25
|
|
FLAG26
|
|
FLAG27
|
|
FLAG28
|
|
FLAG29
|
|
FLAG30
|
|
FLAG31
|
|
FLAG32
|
|
FLAG33
|
|
FLAG34
|
|
FLAG35
|
|
FLAG36
|
|
FLAG37
|
|
FLAG38
|
|
FLAG39
|
|
FLAG40
|
|
FLAG41
|
|
FLAG42
|
|
FLAG43
|
|
FLAG44
|
|
FLAG45
|
|
FLAG46
|
|
FLAG47
|
|
FLAG48
|
|
FLAG49
|
|
FLAG50
|
|
FLAG51
|
|
FLAG52
|
|
FLAG53
|
|
FLAG54
|
|
FLAG55
|
|
FLAG56
|
|
FLAG57
|
|
FLAG58
|
|
FLAG59
|
|
FLAG60
|
|
FLAG61
|
|
FLAG62
|
|
FLAG63
|
|
|
|
ID
|
|
ORTH
|
|
LOWER
|
|
NORM
|
|
SHAPE
|
|
PREFIX
|
|
SUFFIX
|
|
|
|
LENGTH
|
|
CLUSTER
|
|
LEMMA
|
|
POS
|
|
TAG
|
|
DEP
|
|
ENT_IOB
|
|
ENT_TYPE
|
|
HEAD
|
|
SENT_START
|
|
SPACY
|
|
PROB
|
|
|
|
LANG
|
|
ENT_KB_ID = symbols.ENT_KB_ID
|
|
MORPH
|
|
ENT_ID = symbols.ENT_ID
|
|
|
|
IDX
|
|
SENT_END
|