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

Merge pull request #139 from Teqniksoft/refactoring

Browse Source 
Refactoring: converter
This commit is contained in:
gregory-p
2021-04-14 14:19:03 +03:00
committed by GitHub
parent 3f19336a0b a353f0346f
commit 4eb30bd80c
3 changed files with 9 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/consumer.py
View File

@@ -10,7 +10,7 @@ from threading import Event
import pika
from access import Access
from book import Book
from docx_converter import Book
def configure_file_logger(name, filename='logs/converter_log.log', filemode='w+',

8
src/book.py → src/docx_converter.py
View File

@@ -11,7 +11,7 @@ from bs4 import BeautifulSoup, NavigableString
from config import BookLogger, BookApiWrapper, LawCartaConfig
from html_preprocessor import HTMLPreprocessor
from json_converter import JSONConverter
from json_postprocessor import JSONConverter
class Book:
@@ -202,7 +202,7 @@ class Book:
parser = HTMLPreprocessor(html_soup, self.logger_object)
content, footnotes, top_level_headers = parser.process_html(self.access, self.html_path, self.book_id)
json_converter = JSONConverter(content, footnotes, top_level_headers, self.logger_object, self.book_api_wrapper)
content_dict = json_converter.convert_to_json()
content_dict = json_converter.convert_to_dict()
self.write_to_json(content_dict)
self.write_html_from_list(parser.body_tag)
@@ -223,7 +223,7 @@ class Book:
content, footnotes, top_level_headers = parser.process_html(self.access, self.html_path, self.book_id)
json_converter = JSONConverter(content, footnotes, top_level_headers, self.logger_object, self.book_api_wrapper)
content_dict = json_converter.convert_to_json()
content_dict = json_converter.convert_to_dict()
self.write_to_json(content_dict)
self.write_html_from_list(parser.body_tag)
@@ -246,7 +246,7 @@ class Book:
self.book_api_wrapper.set_generate_status()
json_converter = JSONConverter(content, footnotes, top_level_headers, self.logger_object, self.book_api_wrapper)
content_dict = json_converter.convert_to_json()
content_dict = json_converter.convert_to_dict()
self.write_to_json(content_dict)
self.send_json_content(content_dict)
self.logger_object.log(f'End of the conversion to LawCarta format. Check {self.output_path}.')

8
src/json_converter.py → src/json_postprocessor.py
View File

@@ -26,7 +26,7 @@ class JSONConverter:
return new_text
# TODO: rethink the function structure without indexes.
def header_to_json(self, ind):
def header_to_livecarta_chapter_item(self, ind) -> (dict, int):
"""
Function process header and collects all content for it.
@@ -53,7 +53,7 @@ class JSONConverter:
outline = int(re.sub(r"^h", "", self.content[ind].name))
# - recursion step until h_i > h_initial
if outline > curr_outline:
header_dict, ind = self.header_to_json(ind)
header_dict, ind = self.header_to_livecarta_chapter_item(ind)
if ch_content:
result['contents'].append("".join(ch_content))
ch_content = []
@@ -89,7 +89,7 @@ class JSONConverter:
return True
def convert_to_json(self):
def convert_to_dict(self):
"""
Function which convert list of html nodes to appropriate json structure.
"""
@@ -103,7 +103,7 @@ class JSONConverter:
res = {}
if self.content[ind].name in LawCartaConfig.SUPPORTED_HEADERS:
res, ind = self.header_to_json(ind)
res, ind = self.header_to_livecarta_chapter_item(ind)
else:
chapter_title = f'Untitled chapter {ch_num}'