Refactor: Format Code with Ruff and Update Deprecated G2PW Link (#2255)

* ruff check --fix

* ruff format --line-length 120 --target-version py39

* Change the link for G2PW Model

* update pytorch version and colab
This commit is contained in:
XXXXRT666
2025-04-07 09:42:47 +01:00
committed by GitHub
parent 9da7e17efe
commit 53cac93589
132 changed files with 8185 additions and 6648 deletions

View File

@@ -18,10 +18,7 @@ from pypinyin.constants import SUPPORT_UCS4
# 全角半角转换
# 英文字符全角 -> 半角映射表 (num: 52)
F2H_ASCII_LETTERS = {
ord(char) + 65248: ord(char)
for char in string.ascii_letters
}
F2H_ASCII_LETTERS = {ord(char) + 65248: ord(char) for char in string.ascii_letters}
# 英文字符半角 -> 全角映射表
H2F_ASCII_LETTERS = {value: key for key, value in F2H_ASCII_LETTERS.items()}
@@ -37,26 +34,29 @@ F2H_PUNCTUATIONS = {ord(char) + 65248: ord(char) for char in string.punctuation}
H2F_PUNCTUATIONS = {value: key for key, value in F2H_PUNCTUATIONS.items()}
# 空格 (num: 1)
F2H_SPACE = {'\u3000': ' '}
H2F_SPACE = {' ': '\u3000'}
F2H_SPACE = {"\u3000": " "}
H2F_SPACE = {" ": "\u3000"}
# 非"有拼音的汉字"的字符串可用于NSW提取
if SUPPORT_UCS4:
RE_NSW = re.compile(r'(?:[^'
r'\u3007' #
r'\u3400-\u4dbf' # CJK扩展A:[3400-4DBF]
r'\u4e00-\u9fff' # CJK基本:[4E00-9FFF]
r'\uf900-\ufaff' # CJK兼容:[F900-FAFF]
r'\U00020000-\U0002A6DF' # CJK扩展B:[20000-2A6DF]
r'\U0002A703-\U0002B73F' # CJK扩展C:[2A700-2B73F]
r'\U0002B740-\U0002B81D' # CJK扩展D:[2B740-2B81D]
r'\U0002F80A-\U0002FA1F' # CJK兼容扩展:[2F800-2FA1F]
r'])+')
RE_NSW = re.compile(
r"(?:[^"
r"\u3007" #
r"\u3400-\u4dbf" # CJK扩展A:[3400-4DBF]
r"\u4e00-\u9fff" # CJK基本:[4E00-9FFF]
r"\uf900-\ufaff" # CJK兼容:[F900-FAFF]
r"\U00020000-\U0002A6DF" # CJK扩展B:[20000-2A6DF]
r"\U0002A703-\U0002B73F" # CJK扩展C:[2A700-2B73F]
r"\U0002B740-\U0002B81D" # CJK扩展D:[2B740-2B81D]
r"\U0002F80A-\U0002FA1F" # CJK兼容扩展:[2F800-2FA1F]
r"])+"
)
else:
RE_NSW = re.compile( # pragma: no cover
r'(?:[^'
r'\u3007' #
r'\u3400-\u4dbf' # CJK扩展A:[3400-4DBF]
r'\u4e00-\u9fff' # CJK基本:[4E00-9FFF]
r'\uf900-\ufaff' # CJK兼容:[F900-FAFF]
r'])+')
r"(?:[^"
r"\u3007" #
r"\u3400-\u4dbf" # CJK扩展A:[3400-4DBF]
r"\u4e00-\u9fff" # CJK基本:[4E00-9FFF]
r"\uf900-\ufaff" # CJK兼容:[F900-FAFF]
r"])+"
)