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

Clear font-family value of regex characters

Browse Source
This commit is contained in:
Kiryl
2022-07-15 14:18:53 +03:00
parent 16a8690738
commit 20fa1bfa86
3 changed files with 34 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
src/epub_converter/html_epub_processor.py
View File

@@ -66,7 +66,7 @@ class HtmlEpubPreprocessor:
return title
@staticmethod
def _remove_comments(chapter_tag):
def _remove_comments(chapter_tag: BeautifulSoup):
"""
Function remove comments
Parameters
@@ -85,7 +85,7 @@ class HtmlEpubPreprocessor:
element.extract()
@staticmethod
def _wrap_strings_with_p(chapter_tag):
def _wrap_strings_with_p(chapter_tag: BeautifulSoup):
"""
Function converts headings that aren't supported by LiveCarta with <p>
Parameters
@@ -108,7 +108,7 @@ class HtmlEpubPreprocessor:
p_tag.append(str(node))
node.replace_with(p_tag)
def _wrap_tags_with_table(self, chapter_tag, rules: list):
def _wrap_tags_with_table(self, chapter_tag: BeautifulSoup, rules: list):
"""
Function wraps <tag> with <table>
Parameters
@@ -153,7 +153,7 @@ class HtmlEpubPreprocessor:
process_tag_using_table()
@staticmethod
def _tags_to_correspond_livecarta_tag(chapter_tag, rules: list):
def _tags_to_correspond_livecarta_tag(chapter_tag: BeautifulSoup, rules: list):
"""
Function to replace all tags to correspond LiveCarta tags
Parameters
@@ -190,7 +190,7 @@ class HtmlEpubPreprocessor:
# todo can cause appearance of \n <p><p>...</p></p> -> <p>\n</p> <p>...</p> <p>\n</p> (section)
tag.name = tag_to_replace
def _unwrap_tags(self, chapter_tag, rules: dict):
def _unwrap_tags(self, chapter_tag: BeautifulSoup, rules: dict):
"""
Function unwrap tags and moves id to span
Parameters
@@ -213,7 +213,7 @@ class HtmlEpubPreprocessor:
tag.unwrap()
@staticmethod
def _insert_tags_into_correspond_tags(chapter_tag, rules: list):
def _insert_tags_into_correspond_tags(chapter_tag: BeautifulSoup, rules: list):
"""
Function inserts tags into correspond tags
Parameters
@@ -257,14 +257,14 @@ class HtmlEpubPreprocessor:
for tag in chapter_tag.find_all([re.compile(tag) for tag in tags]):
insert(tag)
def _remove_headings_content(self, content_tag, title_of_chapter: str):
def _remove_headings_content(self, chapter_tag, title_of_chapter: str):
"""
Function
- cleans/removes headings from chapter in order to avoid duplication of chapter titles in the content
- adds span with id in order to
Parameters
----------
content_tag: soup object
chapter_tag: soup object
Tag of the page
title_of_chapter: str
Chapter title
@@ -276,15 +276,15 @@ class HtmlEpubPreprocessor:
"""
title_of_chapter = title_of_chapter.lower()
for tag in content_tag.contents:
for tag in chapter_tag.contents:
text = tag if isinstance(tag, NavigableString) else tag.text
if re.sub(r"[\s\xa0]", "", text):
text = re.sub(r"[\s\xa0]", " ", text).lower()
text = text.strip() # delete extra spaces
if title_of_chapter == text or \
(title_of_chapter in text and
re.findall(r"^h[1-3]$", tag.name or content_tag.name)):
self._add_span_to_save_ids_for_links(tag, content_tag)
re.findall(r"^h[1-3]$", tag.name or chapter_tag.name)):
self._add_span_to_save_ids_for_links(tag, chapter_tag)
tag.extract()
return
elif not isinstance(tag, NavigableString):
@@ -329,7 +329,7 @@ class HtmlEpubPreprocessor:
table.attrs["border"] = "1"
@staticmethod
def _class_removing(chapter_tag):
def _class_removing(chapter_tag: BeautifulSoup):
"""
Function removes classes that aren't created by converter
Parameters