github/bilingual_book_maker
1
1
Fork 0
mirror of https://github.com/yihong0618/bilingual_book_maker.git synced 2025-06-06 19:45:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

clean helper and shorter link in --accumulated_num

Browse Source
This commit is contained in:
h 2023-03-19 21:30:34 +08:00
parent 1d680a1ccf
commit 5bab5addb5
1 changed files with 24 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
book_maker/loader/helper.py
View File

@ -20,7 +20,9 @@ class EPUBBookLoaderHelper:
def deal_new(self, p, wait_p_list): def deal_new(self, p, wait_p_list):
self.deal_old(wait_p_list) self.deal_old(wait_p_list)
self.insert_trans( self.insert_trans(
p, self.translate_model.translate(p.text), self.translation_style p,
shorter_result_link(self.translate_model.translate(p.text)),
self.translation_style,
) )
def deal_old(self, wait_p_list): def deal_old(self, wait_p_list):
@ -32,24 +34,35 @@ class EPUBBookLoaderHelper:
for i in range(len(wait_p_list)): for i in range(len(wait_p_list)):
if i < len(result_txt_list): if i < len(result_txt_list):
p = wait_p_list[i] p = wait_p_list[i]
self.insert_trans(p, result_txt_list[i], self.translation_style) self.insert_trans(
p,
shorter_result_link(result_txt_list[i]),
self.translation_style,
)
wait_p_list.clear() wait_p_list.clear()
url_pattern = r"(http[s]?://|www\.)+(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+"
def is_text_link(text): def is_text_link(text):
url_pattern = re.compile( return bool(re.compile(url_pattern).match(text.strip()))
r"(http[s]?://|www\.)+(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+"
)
return bool(url_pattern.match(text.strip()))
def is_text_tail_link(text, num=100): def is_text_tail_link(text, num=80):
text = text.strip() text = text.strip()
url_pattern = re.compile( pattern = r".*" + url_pattern + r"$"
r".*http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+$" return bool(re.compile(pattern).match(text)) and len(text) < num
)
return bool(url_pattern.match(text)) and len(text) < num
def shorter_result_link(text, num=20):
match = re.search(url_pattern, text)
if not match or len(match.group()) < num:
return text
return re.compile(url_pattern).sub("...", text)
def is_text_source(text): def is_text_source(text):