lxbfYeaa/BookConverter
Archived
Template
1
0
Fork 0
forked from LiveCarta/BookConverter
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix error on book without right TOC

Browse Source
This commit is contained in:
shirshasa
2020-07-21 15:43:41 +03:00
parent 2c014ae36e
commit 89989b66f4
1 changed files with 22 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
src/book.py
View File

@@ -594,7 +594,6 @@ class Book:
footnotes.append(content)
self.footnotes = footnotes
def _process_images(self):
@@ -705,28 +704,29 @@ class Book:
headers_info = []
header_tags = self.body_tag.find_all(re.compile("^h[1-9]$"))
headers_outline = [int(re.sub(r"^h", "", tag.name)) for tag in header_tags]
top_level_outline = min(headers_outline)
top_level_headers = [tag for tag in header_tags
if int(re.sub(r"^h", "", tag.name)) == top_level_outline]
if headers_outline:
top_level_outline = min(headers_outline)
top_level_headers = [tag for tag in header_tags
if int(re.sub(r"^h", "", tag.name)) == top_level_outline]
for tag in top_level_headers:
if tag.parent.name == "li":
tag.parent.unwrap()
while tag.parent.name == "ol":
for tag in top_level_headers:
if tag.parent.name == "li":
tag.parent.unwrap()
while tag.parent.name == "ol":
tag.parent.unwrap()
title = tag.text
title = re.sub(r'\s+', ' ', title).strip()
number = re.match(r'^(?:\.?\d+\.? ?)+', title)
is_numbered = number is not None
title = tag.text
title = re.sub(r'\s+', ' ', title).strip()
number = re.match(r'^(?:\.?\d+\.? ?)+', title)
is_numbered = number is not None
cleaned_title = self.clean_header_title(tag.text)
is_introduction = cleaned_title.lower() == 'introduction'
cleaned_title = self.clean_header_title(tag.text)
is_introduction = cleaned_title.lower() == 'introduction'
headers_info.append({
'title': cleaned_title,
'is_numbered': is_numbered,
'is_introduction': is_introduction})
headers_info.append({
'title': cleaned_title,
'is_numbered': is_numbered,
'is_introduction': is_introduction})
return headers_info
@@ -973,10 +973,11 @@ class Book:
# Add is_introduction field to json structure
# after deleting content before toc, some chapters can be deleted
same_first_titles = self.top_level_headers[0]['title'] == json_strc[0]['title']
is_first_header_introduction = not self.top_level_headers[0]['should_be_numbered']
if self.top_level_headers:
same_first_titles = self.top_level_headers[0]['title'] == json_strc[0]['title']
is_first_header_introduction = not self.top_level_headers[0]['should_be_numbered']
json_strc[0]['is_introduction'] = is_first_header_introduction and same_first_titles
json_strc[0]['is_introduction'] = is_first_header_introduction and same_first_titles
self.content_dict = {
"content": json_strc,