125 lines
3.7 KiB
Python
125 lines
3.7 KiB
Python
import re
|
||
from bot.data import load_variant_kanji
|
||
|
||
|
||
__KATA_TO_HIRA_MAP = {
|
||
i: i - 96 for i in [
|
||
*range(0x30A1, 0x30F7),
|
||
*range(0x30FD, 0x30FF),
|
||
]
|
||
}
|
||
|
||
|
||
__HALFWIDTH_TO_FULLWIDTH_MAP = {
|
||
i: i + 0xFEE0 for i in [
|
||
*range(0x21, 0x7F),
|
||
]
|
||
}
|
||
|
||
|
||
def kata_to_hira(text):
|
||
hira = text.translate(__KATA_TO_HIRA_MAP)
|
||
return hira
|
||
|
||
|
||
def add_fullwidth(expressions):
|
||
for expression in expressions:
|
||
new_exp = expression.translate(__HALFWIDTH_TO_FULLWIDTH_MAP)
|
||
if new_exp not in expressions:
|
||
expressions.append(new_exp)
|
||
|
||
|
||
def add_variant_kanji(expressions):
|
||
variant_kanji = load_variant_kanji()
|
||
for old_kanji, new_kanji in variant_kanji.items():
|
||
new_exps = []
|
||
for expression in expressions:
|
||
if old_kanji in expression:
|
||
new_exp = expression.replace(old_kanji, new_kanji)
|
||
new_exps.append(new_exp)
|
||
for new_exp in new_exps:
|
||
if new_exp not in expressions:
|
||
expressions.append(new_exp)
|
||
|
||
|
||
def remove_iteration_mark(expressions):
|
||
iterated_kanji = r"(.)々"
|
||
for expression in expressions:
|
||
for char in re.findall(iterated_kanji, expression):
|
||
new_exp = expression.replace(f"{char}々", f"{char}{char}")
|
||
if new_exp not in expressions:
|
||
expressions.append(new_exp)
|
||
|
||
|
||
def add_iteration_mark(expressions):
|
||
repeat_kanji = r"([^0-z０-ｚぁ-ヿ])\1"
|
||
for expression in expressions:
|
||
for char in re.findall(repeat_kanji, expression):
|
||
new_exp = expression.replace(f"{char}{char}", f"{char}々")
|
||
if new_exp not in expressions:
|
||
expressions.append(new_exp)
|
||
|
||
|
||
def expand_abbreviation(abbreviated_expression):
|
||
"""Return a list of words described by a 省略 notation."""
|
||
groups = re.findall(r"([^（]*)(（([^（]+)）)?", abbreviated_expression)
|
||
expressions = [""]
|
||
for group in groups:
|
||
new_exps = []
|
||
for expression in expressions:
|
||
new_exps.append(expression + group[0])
|
||
expressions = new_exps.copy()
|
||
if group[2] == '':
|
||
continue
|
||
new_exps = []
|
||
for expression in expressions:
|
||
new_exps.append(expression + group[2])
|
||
expressions = new_exps.copy() + expressions.copy()
|
||
return expressions
|
||
|
||
|
||
def expand_abbreviation_list(expressions):
|
||
new_exps = []
|
||
for expression in expressions:
|
||
for new_exp in expand_abbreviation(expression):
|
||
if new_exp not in new_exps:
|
||
new_exps.append(new_exp)
|
||
return new_exps
|
||
|
||
|
||
def expand_smk_alternatives(text):
|
||
"""Return a list of strings described by △ notation."""
|
||
m = re.search(r"△([^（]+)（([^（]+)）", text)
|
||
if m is None:
|
||
return [text]
|
||
alt_parts = [m.group(1)]
|
||
for alt_part in m.group(2).split("・"):
|
||
alt_parts.append(alt_part)
|
||
alts = []
|
||
for alt_part in alt_parts:
|
||
alt_exp = re.sub(r"△[^（]+（[^（]+）", alt_part, text)
|
||
alts.append(alt_exp)
|
||
return alts
|
||
|
||
|
||
def expand_daijirin_alternatives(text):
|
||
"""Return a list of strings described by ＝ notation."""
|
||
group_pattern = r"([^＝]+)(＝([^（]+)（＝([^（]+)）)?"
|
||
groups = re.findall(group_pattern, text)
|
||
expressions = [""]
|
||
for group in groups:
|
||
new_exps = []
|
||
for expression in expressions:
|
||
new_exps.append(expression + group[0])
|
||
expressions = new_exps.copy()
|
||
if group[1] == "":
|
||
continue
|
||
new_exps = []
|
||
for expression in expressions:
|
||
new_exps.append(expression + group[2])
|
||
for expression in expressions:
|
||
for alt in group[3].split("・"):
|
||
new_exps.append(expression + alt)
|
||
expressions = new_exps.copy()
|
||
return expressions
|