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

put style processors on general level

Browse Source
This commit is contained in:
Kiryl
2022-09-01 18:12:04 +03:00
parent 39d5e27df2
commit 115a53e366
5 changed files with 35 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
src/epub_converter/epub_converter.py
View File

@@ -15,15 +15,15 @@ from bs4 import BeautifulSoup, Tag, NavigableString
from src.util.helpers import BookLogger
from src.livecarta_config import LiveCartaConfig
from src.data_objects import ChapterItem, NavPoint
from src.epub_converter.css_processor import CSSPreprocessor
from src.style_preprocessor import CSSPreprocessor
from src.epub_converter.html_epub_processor import HtmlEpubPreprocessor
from src.epub_converter.image_processing import update_images_src_links
from src.epub_converter.footnotes_processing import preprocess_footnotes
from src.epub_converter.tag_inline_style_processor import TagInlineStyleProcessor
from src.tag_inline_style_processor import TagInlineStyleProcessor
class EpubConverter:
def __init__(self, book_path, access=None, logger=None, css_processor=None, html_processor=None):
def __init__(self, book_path, access=None, logger: BookLogger = None, css_processor: CSSPreprocessor = None, html_processor: HtmlEpubPreprocessor = None):
self.book_path = book_path
self.access = access
self.logger: BookLogger = logger
@@ -257,7 +257,7 @@ class EpubConverter:
sub_nodes = []
for elem in second:
if (bool(re.search('^section$|^part$', first.title.lower()))) and lvl == 1:
if (bool(re.search("^section$|^part$", first.title.lower()))) and lvl == 1:
self.offset_sub_nodes.append(
self.build_adjacency_list_from_toc(elem, lvl))
else:
@@ -291,7 +291,7 @@ class EpubConverter:
return False
def build_adjacency_list_from_spine(self):
def build_manifest_id2html_href() -> dict:
def build_manifest_id2html_href() -> Dict[int, str]:
links = dict()
for item in self.ebooklib_book.get_items_of_type(ebooklib.ITEM_DOCUMENT):
links[item.id] = item.file_name
@@ -607,7 +607,7 @@ class EpubConverter:
self.logger.log(indent + "Process title.")
title_preprocessed: str = self.html_processor.prepare_title(title)
self.logger.log(indent + "Process content.")
content_preprocessed: BeautifulSoup = self.html_processor.prepare_content(
content_preprocessed: Union[Tag, BeautifulSoup] = self.html_processor.prepare_content(
title_preprocessed, content, remove_title_from_chapter=is_chapter)
self.book_image_src_path2aws_path = update_images_src_links(content_preprocessed,