forked from LiveCarta/BookConverter
Merge processing tags[Docx, Epub]
This commit is contained in:
Kiryl
@@ -13,7 +13,7 @@ from src.util.helpers import BookLogger
|
||||
from src.livecarta_config import LiveCartaConfig
|
||||
from src.data_objects import ChapterItem, NavPoint
|
||||
from src.style_preprocessor import StylePreprocessor
|
||||
from src.epub_converter.html_epub_processor import HtmlEpubProcessor
|
||||
from src.epub_converter.html_epub_processor import HTMLEpubProcessor
|
||||
from src.epub_converter.image_processing import update_images_src_links
|
||||
from src.epub_converter.footnotes_processing import preprocess_footnotes
|
||||
from src.tag_inline_style_processor import modify_html_soup_with_css_styles
|
||||
@@ -21,7 +21,7 @@ from src.tag_inline_style_processor import modify_html_soup_with_css_styles
|
||||
|
||||
class EpubConverter:
|
||||
def __init__(self, book_path, access=None, logger: BookLogger = None,
|
||||
style_processor: StylePreprocessor = None, html_processor: HtmlEpubProcessor = None):
|
||||
style_processor: StylePreprocessor = None, html_processor: HTMLEpubProcessor = None):
|
||||
self.book_path = book_path
|
||||
self.access = access
|
||||
self.logger: BookLogger = logger
|
||||
|
||||
@@ -30,13 +30,16 @@ class EpubBook(BookSolver):
|
||||
json for LiveCarta platform
|
||||
|
||||
"""
|
||||
style_processor = StylePreprocessor()
|
||||
html_processor = HtmlEpubProcessor(
|
||||
logger=self.logger_object)
|
||||
html_preprocessor = HtmlPreprocessor(
|
||||
logger=self.logger_object, preset_path="presets/epub_presets.json")
|
||||
style_preprocessor = StylePreprocessor()
|
||||
html_processor = HTMLEpubProcessor(logger=self.logger_object,
|
||||
html_preprocessor=html_preprocessor)
|
||||
json_converter = EpubConverter(
|
||||
self.book_path, access=self.access, logger=self.logger_object,
|
||||
style_processor=style_processor, html_processor=html_processor)
|
||||
style_processor=style_preprocessor, html_processor=html_processor)
|
||||
content_dict = json_converter.convert_to_dict()
|
||||
|
||||
return content_dict
|
||||
|
||||
|
||||
|
||||
@@ -1,58 +1,16 @@
|
||||
import re
|
||||
import json
|
||||
from typing import List, Dict, Union
|
||||
from typing import Union
|
||||
from bs4.element import PageElement
|
||||
from bs4 import BeautifulSoup, Tag, NavigableString, Comment
|
||||
|
||||
from src.util.helpers import BookLogger
|
||||
from src.html_preprocessor import _preprocess_html
|
||||
|
||||
|
||||
class HtmlEpubProcessor:
|
||||
def __init__(self, preset_path: str = "presets/epub_presets.json", logger: BookLogger = None):
|
||||
self.preset = json.load(open(preset_path))
|
||||
class HTMLEpubProcessor:
|
||||
def __init__(self, logger: BookLogger = None, html_preprocessor=None):
|
||||
self.logger = logger
|
||||
self.name2action = {
|
||||
"table_wrapper": self._process_tag_using_table,
|
||||
"replacer": self._replace_tag,
|
||||
"attr_replacer": self._replace_attr,
|
||||
"unwrapper": self._unwrap_tag,
|
||||
"inserter": self._insert_tag
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def _add_span_to_save_ids_for_links(tag_to_be_removed: Union[PageElement, BeautifulSoup],
|
||||
chapter_tag: BeautifulSoup):
|
||||
"""
|
||||
Function adds span with id from tag_to_be_removed
|
||||
because this tag will be removed(unwrapped/extract)
|
||||
Parameters
|
||||
----------
|
||||
tag_to_be_removed: Union[PageElement, BeautifulSoup]
|
||||
|
||||
chapter_tag: BeautifulSoup
|
||||
|
||||
Returns
|
||||
-------
|
||||
NoReturn
|
||||
updated body tag
|
||||
|
||||
"""
|
||||
def _insert_span_with_attrs_before_tag(chapter_tag: BeautifulSoup,
|
||||
tag_to_be_removed: Tag,
|
||||
id_: str,
|
||||
class_: Union[List[str], str]):
|
||||
"""Function inserts span before tag aren't supported by LiveCarta"""
|
||||
new_tag: Tag = chapter_tag.new_tag("span")
|
||||
new_tag.attrs["id"] = id_ or ""
|
||||
new_tag.attrs["class"] = class_ or ""
|
||||
new_tag.string = "\xa0"
|
||||
tag_to_be_removed.insert_before(new_tag)
|
||||
|
||||
if tag_to_be_removed.attrs.get("id"):
|
||||
_insert_span_with_attrs_before_tag(chapter_tag=chapter_tag,
|
||||
tag_to_be_removed=tag_to_be_removed,
|
||||
id_=tag_to_be_removed.attrs["id"],
|
||||
class_=tag_to_be_removed.attrs.get("class"))
|
||||
self.html_preprocessor = html_preprocessor
|
||||
|
||||
@staticmethod
|
||||
def prepare_title(title_of_chapter: str) -> str:
|
||||
@@ -116,111 +74,6 @@ class HtmlEpubProcessor:
|
||||
p_tag.append(str(node))
|
||||
node.replace_with(p_tag)
|
||||
|
||||
def _process_tag_using_table(self, **kwargs):
|
||||
def _wrap_tag_with_table(width: str = "100", border: str = "", bg_color: str = None) -> Tag:
|
||||
table = kwargs["chapter_tag"].new_tag("table")
|
||||
table.attrs["border"], table.attrs["align"], table.attrs["style"] \
|
||||
= border, "center", f"width:{width}%;"
|
||||
tbody, tr, td = \
|
||||
kwargs["chapter_tag"].new_tag("tbody"), kwargs["chapter_tag"].new_tag(
|
||||
"tr"), kwargs["chapter_tag"].new_tag("td")
|
||||
td.attrs["bgcolor"] = bg_color
|
||||
kwargs["tag"].wrap(td)
|
||||
td.wrap(tr)
|
||||
tr.wrap(tbody)
|
||||
tbody.wrap(table)
|
||||
table.insert_after(BeautifulSoup(features="lxml").new_tag("br"))
|
||||
return table
|
||||
_wrap_tag_with_table(
|
||||
width=kwargs["tag"].attrs["width"] if kwargs["tag"].attrs.get(
|
||||
"width") else "100",
|
||||
border=kwargs["tag"].attrs["border"] if kwargs["tag"].attrs.get(
|
||||
"border") else None,
|
||||
bg_color=kwargs["tag"].attrs["bgcolor"] if kwargs["tag"].attrs.get("bgcolor") else None)
|
||||
self._add_span_to_save_ids_for_links(kwargs["tag"], kwargs["chapter_tag"])
|
||||
kwargs["tag"].unwrap()
|
||||
|
||||
@staticmethod
|
||||
def _replace_tag(**kwargs):
|
||||
tag_to_replace: str = kwargs["rule"]["tag_to_replace"]
|
||||
kwargs["tag"].name = tag_to_replace
|
||||
|
||||
@staticmethod
|
||||
def _replace_attr(**kwargs):
|
||||
attr, attr_value =\
|
||||
kwargs["rule"]["attr"]["name"], kwargs["rule"]["attr"]["value"]
|
||||
attr_to_replace, attr_value_to_replace =\
|
||||
kwargs["rule"]["attr_to_replace"]["name"], kwargs["rule"]["attr_to_replace"]["value"]
|
||||
if attr_to_replace:
|
||||
kwargs["tag"][attr_to_replace] = kwargs["tag"][attr]
|
||||
if attr_value_to_replace:
|
||||
kwargs["tag"].attrs[attr_to_replace] = attr_value_to_replace
|
||||
del kwargs["tag"][attr]
|
||||
elif attr_value_to_replace:
|
||||
kwargs["tag"].attrs[attr] = attr_value_to_replace
|
||||
|
||||
@staticmethod
|
||||
def _unwrap_tag(**kwargs):
|
||||
kwargs["tag"].unwrap()
|
||||
|
||||
@staticmethod
|
||||
def _insert_tag(**kwargs):
|
||||
tag_to_insert = \
|
||||
kwargs["chapter_tag"].new_tag(kwargs["rule"]["tag_to_insert"])
|
||||
# insert all items that was in tag to subtag and remove from tag
|
||||
for content in reversed(kwargs["tag"].contents):
|
||||
tag_to_insert.insert(0, content.extract())
|
||||
# wrap subtag with items
|
||||
kwargs["tag"].append(tag_to_insert)
|
||||
|
||||
@staticmethod
|
||||
def _process_tags(chapter_tag: BeautifulSoup,
|
||||
rules: List[Dict[str, Union[List[str], str, Dict[str, Union[List[Dict[str, str]], int, str]]]]],
|
||||
action):
|
||||
"""
|
||||
Function do action with tags
|
||||
Parameters
|
||||
----------
|
||||
chapter_tag: BeautifulSoup
|
||||
Tag & contents of the chapter tag
|
||||
rules: List[Dict[str, Union[List[str], str, Dict[str, Union[List[Dict[str, str]], int, str]]]]]
|
||||
list of conditions when fire function
|
||||
action: function
|
||||
action what to do with tag
|
||||
Returns
|
||||
-------
|
||||
NoReturn
|
||||
Body Tag with processed certain tags
|
||||
|
||||
"""
|
||||
for rule in rules:
|
||||
tags: List[str] = rule["tags"] if rule.get("tags") else rule["condition"]["tags"]
|
||||
if rule["condition"]:
|
||||
for condition_on_tag in ((k, v) for k, v in rule["condition"].items() if v):
|
||||
if condition_on_tag[0] == "parent_tags":
|
||||
for tag in chapter_tag.select(', '.join([condition_on_tag[1] + " > " + re.sub(r"[\^$]", "", tag)
|
||||
for tag in tags])):
|
||||
tag.parent.attrs.update(tag.attrs)
|
||||
action(chapter_tag=chapter_tag, tag=tag, rule=rule)
|
||||
elif condition_on_tag[0] == "child_tags":
|
||||
for tag in chapter_tag.select(', '.join([re.sub(r"[\^$]", "", tag) + condition_on_tag[1]
|
||||
for tag in tags])):
|
||||
action(chapter_tag=chapter_tag, tag=tag, rule=rule)
|
||||
elif condition_on_tag[0] == "attrs":
|
||||
for attr in rule["condition"]["attrs"]:
|
||||
for tag in chapter_tag.find_all([re.compile(tag) for tag in tags],
|
||||
{attr["name"]: re.compile(fr"{attr['value']}")}):
|
||||
action(chapter_tag=chapter_tag, tag=tag, rule=rule)
|
||||
# attr replacer
|
||||
elif condition_on_tag[0] == "tags":
|
||||
attr = rule["attr"]
|
||||
for tag in chapter_tag.find_all([re.compile(tag) for tag in tags],
|
||||
{attr['name']: re.compile(fr"{attr['value']}")}):
|
||||
action(chapter_tag=chapter_tag, tag=tag, rule=rule)
|
||||
else:
|
||||
for tag in chapter_tag.find_all([re.compile(tag) for tag in tags]):
|
||||
action(chapter_tag=chapter_tag, tag=tag, rule=rule)
|
||||
|
||||
def _remove_headings_content(self, chapter_tag: Union[BeautifulSoup, PageElement], title_of_chapter: str):
|
||||
"""
|
||||
Function
|
||||
@@ -250,7 +103,8 @@ class HtmlEpubProcessor:
|
||||
if title_of_chapter == text or \
|
||||
(title_of_chapter in text and
|
||||
re.findall(r"^h[1-3]$", tag.name or chapter_tag.name)):
|
||||
self._add_span_to_save_ids_for_links(tag, chapter_tag)
|
||||
self.html_preprocessor._add_span_to_save_ids_for_links(
|
||||
tag, chapter_tag)
|
||||
tag.extract()
|
||||
return
|
||||
elif not self._remove_headings_content(tag, title_of_chapter):
|
||||
@@ -350,9 +204,8 @@ class HtmlEpubProcessor:
|
||||
# 2.
|
||||
self._wrap_strings_with_p(chapter_tag)
|
||||
# 3-6.
|
||||
for rule in self.preset:
|
||||
action = self.name2action[rule["preset_name"]]
|
||||
self._process_tags(chapter_tag, rule["rules"], action)
|
||||
_preprocess_html(
|
||||
html_preprocessor=self.html_preprocessor, html_soup=chapter_tag)
|
||||
# 7.
|
||||
if remove_title_from_chapter:
|
||||
self._remove_headings_content(chapter_tag, title_str)
|
||||
|
||||
Reference in New Issue
Block a user