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

small refactoring

Browse Source
This commit is contained in:
Kiryl
2022-07-14 19:14:49 +03:00
parent a6a54abb0a
commit 16a8690738
1 changed files with 14 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
src/docx_converter/html_docx_preprocessor.py
View File

@@ -173,11 +173,8 @@ class HTMLDocxPreprocessor:
margin_bottom = re.search( margin_bottom = re.search(
r'margin-bottom: ([\d.]{1,4})in', style) r'margin-bottom: ([\d.]{1,4})in', style)
else: else:
indent = None indent = margin_left = margin_right = \
margin_left = None margin_top = margin_bottom = None
margin_right = None
margin_top = None
margin_bottom = None
if margin_left and margin_right and margin_top and margin_bottom and \ if margin_left and margin_right and margin_top and margin_bottom and \
margin_left.group(1) == '0.6' and margin_right.group(1) == '0.6' and \ margin_left.group(1) == '0.6' and margin_right.group(1) == '0.6' and \
@@ -328,23 +325,23 @@ class HTMLDocxPreprocessor:
"a", {'name': re.compile(r'^_Toc\d+')}) "a", {'name': re.compile(r'^_Toc\d+')})
headers = [link.parent for link in toc_links] headers = [link.parent for link in toc_links]
outline_level = "1" # All the unknown outlines will be predicted as <h1> outline_level = "1" # All the unknown outlines will be predicted as <h1>
for tag in headers: for h_tag in headers:
if re.search(r"^h\d$", tag.name): if re.search(r"^h\d$", h_tag.name):
tag.a.unwrap() h_tag.a.unwrap()
# outline_level = tag.name[-1] # TODO: add prediction of the outline level # outline_level = tag.name[-1] # TODO: add prediction of the outline level
elif tag.name == "p": elif h_tag.name == "p":
exist_in_toc = self._check_parent_link_exist_in_toc(tag) exist_in_toc = self._check_parent_link_exist_in_toc(h_tag)
if tag in self.body_tag.find_all("p") and exist_in_toc: if h_tag in self.body_tag.find_all("p") and exist_in_toc:
new_tag = BeautifulSoup( new_tag = BeautifulSoup(
features="lxml").new_tag("h" + outline_level) features="lxml").new_tag("h" + outline_level)
text = tag.text text = h_tag.text
tag.replaceWith(new_tag) h_tag.replaceWith(new_tag)
new_tag.string = text new_tag.string = text
else: else:
# rethink document structure when you have toc_links, other cases? # rethink document structure when you have toc_links, other cases?
self.logger_object.log(f'Something went wrong in processing toc_links.' self.logger_object.log(f'Something went wrong in processing toc_links.'
f' Check the structure of the file. ' f' Check the structure of the file. '
f'Tag name: {tag.name}') f'Tag name: {h_tag.name}')
@staticmethod @staticmethod
def clean_title_from_numbering(title: str): def clean_title_from_numbering(title: str):
@@ -568,7 +565,7 @@ class HTMLDocxPreprocessor:
ind = self.content.index(toc_tag) + 1 ind = self.content.index(toc_tag) + 1
self.content = self.content[ind:] self.content = self.content[ind:]
def process_html(self, access=None, html_path='', book_id='local'): def process_html(self, access=None, html_path='', book_id=0):
"""Process html code to satisfy LiveCarta formatting.""" """Process html code to satisfy LiveCarta formatting."""
self.logger_object.log('Beginning of processing .html file.') self.logger_object.log('Beginning of processing .html file.')
try: try:
@@ -600,7 +597,8 @@ class HTMLDocxPreprocessor:
f'{len(self.footnotes)} footnotes have been processed.') f'{len(self.footnotes)} footnotes have been processed.')
self.logger_object.log('Image processing.') self.logger_object.log('Image processing.')
self.images = process_images(self.body_tag, access=access, html_path=html_path, book_id=book_id) self.images = process_images(access=access, html_path=html_path,
book_id=book_id, body_tag=self.body_tag)
self.logger_object.log( self.logger_object.log(
f'{len(self.images)} images have been processed.') f'{len(self.images)} images have been processed.')