mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 10:26:35 +03:00
52f3c95004
I have added alpha support for the Tagalog language from the Philippines. It is the basis for the country's national language Filipino. I have heavily based the format to the EN and ES languages. I have provided several words in the lemmatizer lookup table, added stop words from a source, translated numeric words to its Tagalog counterpart, added some tokenizer exceptions, and kept the tag map the same as the English language. While the alpha language passed the preliminary testing that you provided, I think it needs more data to be useful for most cases. * Added alpha support for Tagalog language * Edited contributor template * Included SCA; Reverted templates * Fixed SCA template * Fixed changes in SCA template
44 lines
1.5 KiB
Python
44 lines
1.5 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
# import the symbols for the attrs you want to overwrite
|
|
from ...attrs import LIKE_NUM
|
|
|
|
|
|
# Overwriting functions for lexical attributes
|
|
# Documentation: https://localhost:1234/docs/usage/adding-languages#lex-attrs
|
|
# Most of these functions, like is_lower or like_url should be language-
|
|
# independent. Others, like like_num (which includes both digits and number
|
|
# words), requires customisation.
|
|
|
|
|
|
# Example: check if token resembles a number
|
|
|
|
_num_words = ['sero', 'isa', 'dalawa', 'tatlo', 'apat', 'lima', 'anim', 'pito',
|
|
'walo', 'siyam', 'sampu', 'labing-isa', 'labindalawa', 'labintatlo', 'labing-apat',
|
|
'labinlima', 'labing-anim', 'labimpito', 'labing-walo', 'labinsiyam', 'dalawampu',
|
|
'tatlumpu', 'apatnapu', 'limampu', 'animnapu', 'pitumpu', 'walumpu', 'siyamnapu',
|
|
'daan', 'libo', 'milyon', 'bilyon', 'trilyon', 'quadrilyon',
|
|
'gajilyon', 'bazilyon']
|
|
|
|
|
|
def like_num(text):
|
|
text = text.replace(',', '').replace('.', '')
|
|
if text.isdigit():
|
|
return True
|
|
if text.count('/') == 1:
|
|
num, denom = text.split('/')
|
|
if num.isdigit() and denom.isdigit():
|
|
return True
|
|
if text in _num_words:
|
|
return True
|
|
return False
|
|
|
|
|
|
# Create dictionary of functions to overwrite. The default lex_attr_getters are
|
|
# updated with this one, so only the functions defined here are overwritten.
|
|
|
|
LEX_ATTRS = {
|
|
LIKE_NUM: like_num
|
|
}
|