GithubBackup/MoviePilot
1
0
Fork 0
mirror of https://github.com/jxxghp/MoviePilot.git synced 2026-09-07 08:26:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor(string): split utilities by responsibility

Browse Source
This commit is contained in:
jxxghp
2026-08-15 08:03:55 +08:00
parent a2117bafc8
commit 96118e73e7
99 changed files with 1608 additions and 1424 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/domain/meta/infopath.py
+2 -2
View File
@@ -1,7 +1,7 @@
import regex as re
from app.domain.meta.metabase import MetaBase
from app.domain.string import StringUtils
from app.foundation import text as text_tools
AUXILIARY_CN_STEM_FULLMATCH_RE = re.compile(
r"^(双语|字幕|特效|内封|外挂|官译|简体|繁体|繁中|简中|中英|简英|多语|"
@@ -27,7 +27,7 @@ def should_use_parent_title_for_file_stem(
return False
if not PARENT_LATIN_TITLE_RE.search(parent_dir_name):
return False
if not StringUtils.is_all_chinese(stem):
if not text_tools.is_all_chinese(stem):
return False
if len(stem) > 16:
return False
app/domain/meta/metaanime.py
+10 -9
View File
@@ -6,7 +6,8 @@ import anitopy
from app.domain.meta.customization import CustomizationMatcher
from app.domain.meta.metabase import MetaBase
from app.domain.meta.releasegroup import ReleaseGroupsMatcher
from app.domain.string import StringUtils
from app.domain import title as title_rules
from app.foundation import text as text_tools
from app.foundation.text import convert as zhconv_convert
from app.schemas.types import MediaType
@@ -64,11 +65,11 @@ class MetaAnime(MetaBase):
if anitopy_info:
# 名称
name = anitopy_info.get("anime_title")
if not name or name in self._anime_no_words or (len(name) < 5 and not StringUtils.is_chinese(name)):
if not name or name in self._anime_no_words or (len(name) < 5 and not text_tools.contains_chinese(name)):
anitopy_info = anitopy.parse("[ANIME]" + title)
if anitopy_info:
name = anitopy_info.get("anime_title")
if not name or name in self._anime_no_words or (len(name) < 5 and not StringUtils.is_chinese(name)):
if not name or name in self._anime_no_words or (len(name) < 5 and not text_tools.contains_chinese(name)):
name_match = BRACKET_TITLE_RE.search(title)
if name_match and name_match.group(1):
name = name_match.group(1).strip()
@@ -78,12 +79,12 @@ class MetaAnime(MetaBase):
# 按/拆分中英文
if name.find("/") != -1:
names = name.split("/")
if StringUtils.is_chinese(names[0]):
if text_tools.contains_chinese(names[0]):
self.cn_name = names[0]
if len(names) > 1:
self.en_name = names[1]
_split_flag = False
elif StringUtils.is_chinese(names[-1]):
elif text_tools.contains_chinese(names[-1]):
self.cn_name = names[-1]
if len(names) > 1:
self.en_name = names[0]
@@ -103,19 +104,19 @@ class MetaAnime(MetaBase):
self.cn_name = "%s %s" % (self.cn_name or "", word)
elif lastword_type == "en":
self.en_name = "%s %s" % (self.en_name or "", word)
elif StringUtils.is_chinese(word):
elif text_tools.contains_chinese(word):
self.cn_name = "%s %s" % (self.cn_name or "", word)
lastword_type = "cn"
else:
self.en_name = "%s %s" % (self.en_name or "", word)
lastword_type = "en"
if self.cn_name:
_, self.cn_name, _, _, _, _ = StringUtils.get_keyword(self.cn_name)
_, self.cn_name, _, _, _, _ = title_rules.parse_search_keyword(self.cn_name)
if self.cn_name:
self.cn_name = self._name_nostring_pattern.sub('', self.cn_name).strip()
if self.en_name:
self.en_name = self._name_nostring_pattern.sub('', self.en_name).strip().title()
self._name = StringUtils.str_title(self.en_name)
self._name = text_tools.title_case(self.en_name)
# 年份
year = anitopy_info.get("anime_year")
if str(year).isdigit():
@@ -271,7 +272,7 @@ class MetaAnime(MetaBase):
else:
titles.append("%s%s" % (left_char, name.split("/")[0].strip()))
elif name:
if StringUtils.is_chinese(name) and not StringUtils.is_all_chinese(name):
if text_tools.contains_chinese(name) and not text_tools.is_all_chinese(name):
if not NUMERIC_BRACKET_RE.search(name):
name = MIXED_CHINESE_TOKEN_RE.sub('', name).strip()
if not name or name.strip().isdigit():
app/domain/meta/metabase.py
+3 -3
View File
@@ -8,7 +8,7 @@ import regex as re
from app.schemas.types import MediaSource, MediaType
from app.schemas.media import resolve_media_identity
from app.domain.string import StringUtils
from app.foundation import text as text_tools
logger = logging.getLogger(__name__)
@@ -128,7 +128,7 @@ class MetaBase(object):
"""
返回名称
"""
if self.cn_name and StringUtils.is_all_chinese(self.cn_name):
if self.cn_name and text_tools.is_all_chinese(self.cn_name):
return self.cn_name
elif self.en_name:
return self.en_name
@@ -141,7 +141,7 @@ class MetaBase(object):
"""
设置名称
"""
if StringUtils.is_all_chinese(name):
if text_tools.is_all_chinese(name):
self.cn_name = name
else:
self.en_name = name
app/domain/meta/metavideo.py
+4 -4
View File
@@ -7,7 +7,7 @@ from app.domain.meta.customization import CustomizationMatcher
from app.domain.meta.metabase import MetaBase
from app.domain.meta.releasegroup import ReleaseGroupsMatcher
from app.schemas.types import MediaType
from app.domain.string import StringUtils
from app.foundation import text as text_tools
from app.domain.tokens import Tokens
from app.domain.meta.streamingplatform import StreamingPlatforms
from app.domain.meta.runtime import get_media_extensions
@@ -218,7 +218,7 @@ class MetaVideo(MetaBase):
self.init_subtitle(self.subtitle)
# 去掉名字中不需要的干扰字符，过短的纯数字不要
self.cn_name = self.__fix_name(self.cn_name)
self.en_name = StringUtils.str_title(self.__fix_name(self.en_name))
self.en_name = text_tools.title_case(self.__fix_name(self.en_name))
# 处理part
if self.part and self.part.upper() == "PART":
self.part = None
@@ -245,7 +245,7 @@ class MetaVideo(MetaBase):
if not description:
return None
titles = DESCRIPTION_SPLIT_RE.split(description)
if StringUtils.is_chinese(titles[0]):
if text_tools.contains_chinese(titles[0]):
return titles[0]
return None
@@ -308,7 +308,7 @@ class MetaVideo(MetaBase):
if token in self._name_se_words:
self._last_token_type = 'name_se_words'
return
if StringUtils.is_chinese(token):
if text_tools.contains_chinese(token):
# 含有中文，直接做为标题（连着的数字或者英文会保留），且不再取用后面出现的中文
self._last_token_type = "cnname"
if not self.cn_name: