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

Add inline style processor [Docx]

Browse Source
This commit is contained in:
Kiryl
2022-09-02 14:47:06 +03:00
parent b97c5d8371
commit dfdf6bc7e9
3 changed files with 50 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
src/docx_converter/docx_solver.py
View File

@@ -5,19 +5,20 @@ from threading import Event
from src.book_solver import BookSolver
from src.util.helpers import BookLogger
from src.style_preprocessor import StylePreprocessor
from src.docx_converter.docx2libre_html import Docx2LibreHTML
from src.docx_converter.html_docx_preprocessor import HTMLDocxPreprocessor
from src.docx_converter.html_docx_processor import HTMLDocxProcessor
from src.docx_converter.libre_html2json_converter import LibreHTML2JSONConverter
class DocxBook(BookSolver):
"""Class of .docx type book - child of BookSolver"""
def __init__(self, book_id: int = 0, access=None, main_logger=None, libre_locker=None):
def __init__(self, book_id: int = 0, access=None, main_logger=None, libre_locker: Event = None):
super().__init__(book_id, access, main_logger)
self.book_type = "docx"
# critical section for occupying libreoffice by one thread
self.libre_locker: Event() = libre_locker
self.libre_locker = libre_locker
def get_converted_book(self):
"""
@@ -47,8 +48,9 @@ class DocxBook(BookSolver):
# 2. Parses and cleans html, gets list of tags, gets footnotes
try:
parser = HTMLDocxPreprocessor(
html_converter.html_soup, self.logger_object)
style_processor = StylePreprocessor()
parser = HTMLDocxProcessor(html_soup=html_converter.html_soup,
logger=self.logger_object, style_processor=style_processor)
bs_tags, footnotes, top_level_headers = parser.process_html(
self.access, html_converter.html_path, self.book_id)
except Exception as exc:
@@ -73,7 +75,7 @@ class DocxBook(BookSolver):
if __name__ == "__main__":
docx_file_path = "../../books/docx/music_inquiry.docx"
docx_file_path = "../../books/docx/Bar_Exam_MPT_2e_prepared.docx"
logger_object = BookLogger(
name="docx", book_id=docx_file_path.split("/")[-1])
locker = Event()
@@ -82,7 +84,9 @@ if __name__ == "__main__":
html_converter = Docx2LibreHTML(file_path=docx_file_path,
logger=logger_object, libre_locker=locker)
parser = HTMLDocxPreprocessor(html_converter.html_soup, logger_object)
css_processor = StylePreprocessor()
parser = HTMLDocxProcessor(html_soup=html_converter.html_soup, logger=logger_object,
style_processor=css_processor, preset_path="../../presets/docx_presets.json")
content, footnotes, top_level_headers = parser.process_html(
html_path=html_converter.html_path, book_id=html_converter.book_id)