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

Change paths to books

Browse Source
This commit is contained in:
Kiryl
2022-07-27 20:44:19 +03:00
parent 253c4ebe26
commit af466cbc27
9 changed files with 62 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
src/docx_converter/libre_html2json_converter.py
View File

@@ -29,7 +29,7 @@ class LibreHTML2JSONConverter:
cleaned text
"""
new_text = re.sub(r'([\n\t])', ' ', html_text)
new_text = re.sub(r"([\n\t])", " ", html_text)
return new_text
# TODO: rethink the function structure without indexes.
@@ -48,16 +48,16 @@ class LibreHTML2JSONConverter:
"""
if self.content[ind].name in LiveCartaConfig.SUPPORTED_HEADERS:
title = str(self.content[ind])
title = title.replace(f'<{self.content[ind].name}>', '')
title = title.replace(f'</{self.content[ind].name}>', '')
title = re.sub(r'^\n', '', title)
title = title.replace(f"<{self.content[ind].name}>", "")
title = title.replace(f"</{self.content[ind].name}>", "")
title = re.sub(r"^\n", "", title)
# extract outline from tag
curr_outline = int(re.sub(r"^h", "", self.content[ind].name))
result = {
'title': f'{title}',
'contents': [],
'sub_items': []
"title": f"{title}",
"contents": [],
"sub_items": []
}
ch_content = []
ind += 1
@@ -71,9 +71,9 @@ class LibreHTML2JSONConverter:
header_dict, ind = self.header_to_livecarta_chapter_item(
ind)
if ch_content:
result['contents'].append("".join(ch_content))
result["contents"].append("".join(ch_content))
ch_content = []
result['sub_items'].append(header_dict)
result["sub_items"].append(header_dict)
# - current h_i <= h_initial, end of recursion
else:
# return result, ind
@@ -85,21 +85,21 @@ class LibreHTML2JSONConverter:
ind += 1
if ch_content:
result['contents'].append("".join(ch_content))
result["contents"].append("".join(ch_content))
return result, ind
return ''
return ""
@staticmethod
def _is_empty_p_tag(tag):
if tag.name != 'p':
if tag.name != "p":
return False
temp_tag = copy(tag)
brs = temp_tag.find_all('br')
brs = temp_tag.find_all("br")
for br in brs:
br.decompose()
text = re.sub(r'\s+', '', temp_tag.text)
text = re.sub(r"\s+", "", temp_tag.text)
if text:
return False
@@ -117,7 +117,7 @@ class LibreHTML2JSONConverter:
res, ind = self.header_to_livecarta_chapter_item(ind)
else:
chapter_title = f'Untitled chapter {ch_num}'
chapter_title = f"Untitled chapter {ch_num}"
chapter = []
while ind < len(self.content) and self.content[ind].name not in LiveCartaConfig.SUPPORTED_HEADERS:
if not self._is_empty_p_tag(self.content[ind]):
@@ -126,9 +126,9 @@ class LibreHTML2JSONConverter:
ind += 1
if chapter:
res = {
'title': chapter_title,
'contents': ["".join(chapter)],
'sub_items': []
"title": chapter_title,
"contents": ["".join(chapter)],
"sub_items": []
}
ch_num += 1
@@ -136,10 +136,10 @@ class LibreHTML2JSONConverter:
json_strc.append(res)
ch_amt += 1
self.logger_object.log(
f'Chapter {ch_amt} has been added to structure.')
f"Chapter {ch_amt} has been added to structure.")
except Exception as exc:
self.logger_object.log(
'Error has occurred while making json structure.', logging.ERROR)
"Error has occurred while making json structure.", logging.ERROR)
self.logger_object.log_error_to_main_log()
if self.book_api_status:
self.book_api_status.set_error()
@@ -148,10 +148,10 @@ class LibreHTML2JSONConverter:
# Add is_introduction field to json structure
# after deleting content before toc, some chapters can be deleted
if self.top_level_headers:
same_first_titles = self.top_level_headers[0]['title'] == json_strc[0]['title']
is_first_header_introduction = not self.top_level_headers[0]['should_be_numbered']
same_first_titles = self.top_level_headers[0]["title"] == json_strc[0]["title"]
is_first_header_introduction = not self.top_level_headers[0]["should_be_numbered"]
json_strc[0]['is_introduction'] = is_first_header_introduction
json_strc[0]["is_introduction"] = is_first_header_introduction
self.content_dict = {
"content": json_strc,