spaCy/spacy/lang/bn/lemmatizer.py
2017-05-08 20:00:40 +02:00

69 lines
1.7 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# coding: utf8
from __future__ import unicode_literals
# Source: āωāĻšā§āϚāϤāϰ āĻŦāĻžāĻ‚āϞāĻž āĻŦā§āϝāĻžāĻ•āϰāĻŖ āĻ“ āϰāϚāύāĻž - āĻ…āĻ§ā§āϝāĻžāĻĒāĻ• āύāĻŋāϰāĻžā§āϜāύ āĻ…āϧāĻŋāĻ•āĻžāϰ⧀ āĻ“ āĻ…āĻ§ā§āϝāĻžāĻĒāĻ• āĻĄ. āϏāĻĢāĻŋāωāĻĻā§āĻĻāĻŋāύ āφāĻšāĻŽāĻĻ
LEMMA_RULES = {
"noun": [
["āϟāĻž", ""],
["āϟāĻŋ", ""],
["āĻ–āĻžāύ", ""],
["āĻ–āĻžāύāĻž", ""],
["āĻ–āĻžāύāĻŋ", ""],
["āĻ—āĻžāĻ›āĻž", ""],
["āĻ—āĻžāĻ›āĻŋ", ""],
["āĻ›āĻĄāĻŧāĻž", ""],
["āϕ⧇", ""],
["⧇", ""],
["āϤ⧇", ""],
["āϰ", ""],
["āϰāĻž", ""],
["āϰ⧇", ""],
["⧇āϰ", ""], # āĻāϰ
["⧇āϰāĻž", ""], # āĻāϰāĻž
["āĻĻ⧇āϰ", ""],
["āĻĻ⧇āϰāϕ⧇", ""],
["āϗ⧁āϞāĻž", ""],
["āϗ⧁āϞ⧋", ""],
["āϗ⧁āϞāĻŋ", ""],
["āϕ⧁āϞ", ""],
["āĻ—āĻŖ", ""],
["āĻĻāϞ", ""],
["āĻĒāĻžāϞ", ""],
["āĻĒ⧁āĻžā§āϜ", ""],
["āĻŽāĻŖā§āĻĄāϞ⧀", ""],
["āĻŽāĻžāϞāĻž", ""],
["āϰāĻžāϜāĻŋ", ""],
["āĻŦ⧃āĻ¨ā§āĻĻ", ""],
["āĻŦāĻ°ā§āĻ—", ""],
["āĻļā§āϰ⧇āĻŖā§€", ""],
["āĻļā§āϰ⧇āύāĻŋ", ""],
["āϰāĻžāĻļāĻŋ", ""],
["āϏāĻ•āϞ", ""],
["āĻŽāĻšāϞ", ""],
["āĻžāĻŦāϞāĻŋ", ""], # āφāĻŦāϞāĻŋ
# Bengali digit representations
["ā§Ļ", "0"],
["ā§§", "1"],
["⧍", "2"],
["ā§Š", "3"],
["ā§Ē", "4"],
["ā§Ģ", "5"],
["ā§Ŧ", "6"],
["ā§­", "7"],
["ā§Ž", "8"],
["⧝", "9"],
],
"punct": [
["“", "\""],
["”", "\""],
["\u2018", "'"],
["\u2019", "'"]
]
}