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

37
src/epub_converter/css_processor.py
View File

@@ -37,6 +37,7 @@ class CSSPreprocessor:
"margin-left": self.convert_indents_tag_values,
"margin-top": self.convert_tag_style_values,
"margin": self.convert_indents_tag_values,
"width": self.convert_tag_style_values,
}
@staticmethod
@@ -104,16 +105,23 @@ class CSSPreprocessor:
return size_value
@staticmethod
def style_conditions(style_value, style_name):
def clean_value(style_value: str, style_name: str):
cleaned_value = style_value.replace("\"", "")
# cleaned_value = style_value.replace("+", "%2B")
if style_name == 'font-family':
for symbol in ["+", "*", ".", "%", "?", "$", "^", "[", "]"]:
cleaned_value = re.sub(
re.escape(f"{symbol}"), rf"\\{symbol}", cleaned_value)
return cleaned_value
@staticmethod
def style_conditions(style_value: str, style_name: str) -> tuple[bool, bool]:
constraints_on_value = LiveCartaConfig.LIVECARTA_STYLE_ATTRS.get(
style_name)
value_not_in_possible_values_list = cleaned_value not in LiveCartaConfig.LIVECARTA_STYLE_ATTRS[
value_not_in_possible_values_list = style_value not in LiveCartaConfig.LIVECARTA_STYLE_ATTRS[
style_name]
return cleaned_value, constraints_on_value, value_not_in_possible_values_list
return constraints_on_value, value_not_in_possible_values_list
def update_inline_styles_to_livecarta_convention(self, split_style: list):
def update_inline_styles_to_livecarta_convention(self, split_style: list) -> list:
for i, style in enumerate(split_style):
style_name, style_value = style.split(":")
if style_name not in LiveCartaConfig.LIVECARTA_STYLE_ATTRS:
@@ -121,9 +129,8 @@ class CSSPreprocessor:
split_style[i] = ""
return split_style
cleaned_value, constraints_on_value, value_not_in_possible_values_list =\
self.style_conditions(style_value, style_name)
if constraints_on_value and value_not_in_possible_values_list:
cleaned_value = self.clean_value(style_value, style_name)
if all(self.style_conditions(cleaned_value, style_name)):
# there are constraints + value not in LIVECARTA_STYLE_ATTRS, remove from css file
split_style[i] = ""
else:
@@ -138,18 +145,18 @@ class CSSPreprocessor:
"""Build inline style with LiveCarta convention"""
# replace all spaces between "; & letter" to ";"
style = re.sub(r"; *", ";", style)
# when we split style by ";", last element of the list is "" - None
# remove it
# when we split style by ";", last element of the list is "" - None (we remove it)
split_style: list = list(filter(None, style.split(";")))
# replace all spaces between ": & letter" to ":"
split_style = [el.replace(
re.search(r"(:\s*)", el).group(1), ":") for el in split_style]
split_style = self.update_inline_styles_to_livecarta_convention(split_style)
split_style = self.update_inline_styles_to_livecarta_convention(
split_style)
style = "; ".join(split_style)
return style
def process_inline_styles_in_html_soup(self, html_href2html_body_soup):
def process_inline_styles_in_html_soup(self, html_href2html_body_soup: dict):
"""This function is designed to convert inline html styles"""
for html_href in html_href2html_body_soup:
html_content: BeautifulSoup = html_href2html_body_soup[html_href]
@@ -185,16 +192,14 @@ class CSSPreprocessor:
css_rule.style[style_type.name] = ""
return
cleaned_value, constraints_on_value, value_not_in_possible_values_list =\
self.style_conditions(style_type.value, style_type.name)
if constraints_on_value and value_not_in_possible_values_list:
cleaned_value = self.clean_value(style_type.value, style_type.name)
if all(self.style_conditions(cleaned_value, style_type.name)):
# there are constraints + value not in LIVECARTA_STYLE_ATTRS, remove from css file
css_rule.style[style_type.name] = ""
else:
if style_type.name in self.LIVECARTA_STYLE_ATTRS_MAPPING:
# function that converts our data
func = self.LIVECARTA_STYLE_ATTRS_MAPPING[style_type.name]
print(cleaned_value)
css_rule.style[style_type.name] = func(cleaned_value)
def build_css_file_content(self, css_content: str) -> str:

2
src/epub_converter/epub_converter.py
View File

@@ -305,7 +305,7 @@ class EpubConverter:
self.adjacency_list[-1].append(nav_point)
self.hrefs_added_to_toc.add(nav_point.href)
def add_not_added_files_to_adjacency_list(self, not_added):
def add_not_added_files_to_adjacency_list(self, not_added: list):
"""Function add files that not added to adjacency list"""
for i, file in enumerate(not_added):
nav_point = NavPoint(

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