81 lines
2.2 KiB
Python
81 lines
2.2 KiB
Python
'''
|
|
Cleaners are transformations that run over the input text at both training and eval time.
|
|
|
|
Cleaners can be selected by passing a comma-delimited list of cleaner names as the "cleaners"
|
|
hyperparameter. Some cleaners are English-specific. You'll typically want to use:
|
|
1. "english_cleaners" for English text
|
|
2. "transliteration_cleaners" for non-English text that can be transliterated to ASCII using
|
|
the Unidecode library (https://pypi.python.org/pypi/Unidecode)
|
|
3. "basic_cleaners" if you do not want to transliterate (in this case, you should also update
|
|
the symbols in symbols.py to match your data).
|
|
'''
|
|
|
|
import re
|
|
from .korean import tokenize as ko_tokenize
|
|
|
|
|
|
# Regular expression matching whitespace:
|
|
_whitespace_re = re.compile(r'\s+')
|
|
|
|
|
|
def korean_cleaners(text):
|
|
'''Pipeline for Korean text, including number and abbreviation expansion.'''
|
|
text = ko_tokenize(text)
|
|
return text
|
|
|
|
|
|
# List of (regular expression, replacement) pairs for abbreviations:
|
|
_abbreviations = [(re.compile('\\b%s\\.' % x[0], re.IGNORECASE), x[1]) for x in [
|
|
('mrs', 'misess'),
|
|
('mr', 'mister'),
|
|
('dr', 'doctor'),
|
|
('st', 'saint'),
|
|
('co', 'company'),
|
|
('jr', 'junior'),
|
|
('maj', 'major'),
|
|
('gen', 'general'),
|
|
('drs', 'doctors'),
|
|
('rev', 'reverend'),
|
|
('lt', 'lieutenant'),
|
|
('hon', 'honorable'),
|
|
('sgt', 'sergeant'),
|
|
('capt', 'captain'),
|
|
('esq', 'esquire'),
|
|
('ltd', 'limited'),
|
|
('col', 'colonel'),
|
|
('ft', 'fort'),
|
|
]]
|
|
|
|
|
|
def expand_abbreviations(text):
|
|
for regex, replacement in _abbreviations:
|
|
text = re.sub(regex, replacement, text)
|
|
return text
|
|
|
|
|
|
def expand_numbers(text):
|
|
return normalize_numbers(text)
|
|
|
|
|
|
def lowercase(text):
|
|
return text.lower()
|
|
|
|
|
|
def collapse_whitespace(text):
|
|
return re.sub(_whitespace_re, ' ', text)
|
|
|
|
|
|
def basic_cleaners(text):
|
|
'''Basic pipeline that lowercases and collapses whitespace without transliteration.'''
|
|
text = lowercase(text)
|
|
text = collapse_whitespace(text)
|
|
return text
|
|
|
|
|
|
def transliteration_cleaners(text):
|
|
'''Pipeline for non-English text that transliterates to ASCII.'''
|
|
text = convert_to_ascii(text)
|
|
text = lowercase(text)
|
|
text = collapse_whitespace(text)
|
|
return text
|