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

Set up local docx_converter

Browse Source
This commit is contained in:
Kiryl
2022-07-14 19:13:34 +03:00
parent 7b35d8a7c2
commit b1ccd796c9
2 changed files with 8 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
src/docx_converter/docx_solver.py
View File

@@ -35,7 +35,7 @@ class DocxBook(BookSolver):
""" """
# 1. Converts docx to html with LibreOffice # 1. Converts docx to html with LibreOffice
html_converter = Docx2LibreHTML(self.book_id, self.file_path, self.access, html_converter = Docx2LibreHTML(self.book_id, self.file_path, self.access,
self.logger_object, self.status_wrapper, self.libre_locker) self.logger_object, self.libre_locker)
# TODO presets # TODO presets
# 2. Parses and cleans html, gets list of tags, gets footnotes # 2. Parses and cleans html, gets list of tags, gets footnotes
@@ -46,7 +46,7 @@ class DocxBook(BookSolver):
# 3. Parses from line structure to nested structure with JSONConverter # 3. Parses from line structure to nested structure with JSONConverter
json_converter = LibreHTML2JSONConverter(bs_tags, footnotes, top_level_headers, json_converter = LibreHTML2JSONConverter(bs_tags, footnotes, top_level_headers,
self.logger_object, self.status_wrapper) self.logger_object)
content_dict = json_converter.convert_to_dict() content_dict = json_converter.convert_to_dict()
return content_dict return content_dict
@@ -56,12 +56,15 @@ if __name__ == "__main__":
docx_file_path = '../../docx/music_inquiry.docx' docx_file_path = '../../docx/music_inquiry.docx'
logger_object = BookLogger( logger_object = BookLogger(
name='docx', book_id=docx_file_path.split('/')[-1]) name='docx', book_id=docx_file_path.split('/')[-1])
locker = Event()
locker.set()
html_converter = Docx2LibreHTML(file_path=docx_file_path) html_converter = Docx2LibreHTML(file_path=docx_file_path,
logger=logger_object, libre_locker=locker)
parser = HTMLDocxPreprocessor(html_converter.html_soup, logger_object) parser = HTMLDocxPreprocessor(html_converter.html_soup, logger_object)
content, footnotes, top_level_headers = parser.process_html( content, footnotes, top_level_headers = parser.process_html(
html_converter.html_path) html_path=html_converter.html_path, book_id=html_converter.book_id)
json_converter = LibreHTML2JSONConverter( json_converter = LibreHTML2JSONConverter(
content, footnotes, top_level_headers, logger_object) content, footnotes, top_level_headers, logger_object)

4
src/epub_converter/footnotes_processing.py
View File

@@ -26,15 +26,13 @@ def preprocess_footnotes(source_html_tag: Tag, href2soup_html: dict = None, note
<aside epub:type="footnote" id="n1"><p>With a footnote here.</p></aside> <aside epub:type="footnote" id="n1"><p>With a footnote here.</p></aside>
""" """
footnotes = [] footnotes, new_noterefs_tags, new_footnotes_tags = [], [], []
noterefs_tags = source_html_tag.find_all( noterefs_tags = source_html_tag.find_all(
attrs={noteref_attr_name: "noteref"}) attrs={noteref_attr_name: "noteref"})
bad_noterefs_tags = set( bad_noterefs_tags = set(
[tag for tag in noterefs_tags if not tag.attrs.get("href")]) [tag for tag in noterefs_tags if not tag.attrs.get("href")])
noterefs_tags = [ noterefs_tags = [
tag for tag in noterefs_tags if tag not in bad_noterefs_tags] tag for tag in noterefs_tags if tag not in bad_noterefs_tags]
new_noterefs_tags = []
new_footnotes_tags = []
[tag.decompose() for tag in bad_noterefs_tags] [tag.decompose() for tag in bad_noterefs_tags]
def parse_a_tag_href(s: str) -> Tuple[str, str]: def parse_a_tag_href(s: str) -> Tuple[str, str]: