Skip to content

feat: better byte handling #479

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
yihong0618 merged 1 commit into from
Nov 15, 2025
Merged

feat: better byte handling #479

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 12 additions & 9 deletions book_maker/loader/epub_loader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -323,8 +323,9 @@ def find_items_containing_string(self, book, search_string):
matching_items = []

for item in book.get_items_of_type(ITEM_DOCUMENT):
content = item.get_content().decode("utf-8")
if search_string in content:
content = item.get_content()
soup = bs(content, "html.parser")
if search_string in soup.get_text():
matching_items.append(item)

return matching_items
Expand Down Expand Up @@ -358,8 +359,10 @@ def retranslate_book(self, index, p_to_save_len, pbar, trans_taglist, retranslat
if ori_item is None:
return

soup_complete = bs(complete_item.content, "html.parser")
soup_ori = bs(ori_item.content, "html.parser")
content_complete = complete_item.content
content_ori = ori_item.content
soup_complete = bs(content_complete, "html.parser")
soup_ori = bs(content_ori, "html.parser")

p_list_complete = soup_complete.findAll(trans_taglist)
p_list_ori = soup_ori.findAll(trans_taglist)
Expand Down Expand Up @@ -458,7 +461,8 @@ def process_item(
if not os.path.exists("log"):
os.makedirs("log")

soup = bs(item.content, "html.parser")
content = item.content
soup = bs(content, "html.parser")
p_list = soup.findAll(trans_taglist)

p_list = self.filter_nest_list(p_list, trans_taglist)
Expand Down Expand Up @@ -531,7 +535,7 @@ def process_item(
)

if soup:
item.content = soup.encode()
item.content = soup.encode(encoding="utf-8")
new_book.add_item(item)

return index
Expand Down Expand Up @@ -574,8 +578,6 @@ def _process_chapter_parallel(self, chapter_data):
thread_translator = self._create_chapter_translator()

content = item.content
if isinstance(content, bytes):
content = content.decode("utf-8")
soup = bs(content, "html.parser")
p_list = soup.findAll(trans_taglist)
p_list = self.filter_nest_list(p_list, trans_taglist)
Expand Down Expand Up @@ -987,7 +989,8 @@ def _save_temp_book(self):
try:
for item in origin_book_temp.get_items():
if item.get_type() == ITEM_DOCUMENT:
soup = bs(item.content, "html.parser")
content = item.content
soup = bs(content, "html.parser")
p_list = soup.findAll(trans_taglist)
if self.allow_navigable_strings:
p_list.extend(soup.findAll(text=True))
Expand Down