Create custom user dictionary for use in MeCab through Fugashi

build_dict.py

# Generate custom MeCab dictionary to be used with unidic-lite
import sys


from fugashi.fugashi import build_dictionary
import unidic_lite


args = (
    sys.argv[0]
    + f" -f utf8 -t utf8 -d {unidic_lite.DICDIR} -u custom.dic custom_entries.csv"
)
print(args)
build_dictionary(args)

custom_entries.csv

# REMOVE COMMENTS FIRST (MeCab doesn't allow comments)
# see https://twitter.com/zakki/status/920977351059554304 for a description of the fields
かい,830,830,6319,助詞,終助詞,*,*,*,*,カイ,かい,かい,カイ,かい,カイ,和,*,*,*,*

tagger.py

from fugashi import Tagger  # type: ignore

# use the generated custom dictionary (plus unidic-lite)
TAGGER = Tagger("-Owakati -u custom.dic")

print(TAGGER("皆様こんにちは。本日はですね　とっても特別なお客様にお伺いしたいと思いま〜す"))
# expected output: [皆, 様, こんにちは, 。, 本日, は, です, ね, 　, とっても, 特別, な, お, 客, 様, に, お, 伺い, し, たい, と, 思い, ま, 〜, す]