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

Remove paragraph processing

Browse Source
This commit is contained in:
Kiryl
2022-09-06 13:19:58 +03:00
parent 96c7421e71
commit 2c6f999c95
1 changed files with 28 additions and 91 deletions
Download Patch File Download Diff File Expand all files Collapse all files

119
src/docx_converter/html_docx_processor.py
View File

@@ -137,57 +137,6 @@ class HTMLDocxProcessor:
for tag in body_tag.find_all([re.compile(tag) for tag in tags]):
action(body_tag=body_tag, tag=tag, rule=rule)
def _process_paragraph(self):
"""Function to process <p> tags (text-align and text-indent value)."""
# todo debug and remove if inline is enough
paragraphs = self.body_tag.find_all("p")
for p in paragraphs:
# libre converts some \n into <p> with 2 </br>
# there we remove 1 unnecessary <br>
brs = p.find_all("br")
text = p.text
if brs and text == "\n\n" and len(brs) == 2:
brs[0].decompose()
indent_should_be_added = False
if text and ((text[0:1] == "\t") or (text[:2] == "\n\t")):
indent_should_be_added = True
align = p.get("align")
style = p.get("style")
if style:
indent = re.search(r"text-indent: ([\d.]{1,4})in", style)
margin_left = re.search(r"margin-left: ([\d.]{1,4})in", style)
margin_right = re.search(
r"margin-right: ([\d.]{1,4})in", style)
margin_top = re.search(r"margin-top: ([\d.]{1,4})in", style)
margin_bottom = re.search(
r"margin-bottom: ([\d.]{1,4})in", style)
else:
indent = margin_left = margin_right = \
margin_top = margin_bottom = None
if margin_left and margin_right and margin_top and margin_bottom and \
margin_left.group(1) == "0.6" and margin_right.group(1) == "0.6" and \
margin_top.group(1) == "0.14" and margin_bottom.group(1) == "0.11":
p.wrap(BeautifulSoup(features="lxml").new_tag("blockquote"))
p.attrs = {}
style = ""
if align is not None and align != LiveCartaConfig.DEFAULT_ALIGN_STYLE:
style += f"text-align: {align};"
if indent is not None or indent_should_be_added:
# indent = indent.group(1)
style += f"text-indent: {LiveCartaConfig.INDENT};"
if style:
p.attrs["style"] = style
def _process_quotes(self):
"""
Function to process block quotes.
@@ -247,10 +196,8 @@ class HTMLDocxProcessor:
if match:
size = match.group(1)
units = match.group(2)
if units == "pt":
size = self.convert_pt_to_px(size)
sizes.append(float(size))
width = td.get("width")
td.attrs = {}
@@ -259,7 +206,6 @@ class HTMLDocxProcessor:
if sizes:
border_size = sum(sizes) / len(sizes)
table.attrs["border"] = f"{border_size:.2}"
self.tables_amount = len(tables)
def _process_hrefs(self):
@@ -278,13 +224,6 @@ class HTMLDocxProcessor:
tag.string = tag.text.replace("\u200b", "") # zero-width-space
tag["href"] = tag.attrs.get("href").replace("%E2%80%8C", "")
def _process_div(self):
# todo unwrapper
"""Function to process <div> tags. All the tags will be deleted from file, all content of the tags will stay."""
divs = self.body_tag.find_all("div")
for div in divs:
div.unwrap()
def _get_top_level_headers(self) -> List[Dict[str, Union[str, bool]]]:
"""
Function for gathering info about top-level chapters.
@@ -439,35 +378,6 @@ class HTMLDocxProcessor:
"""Process html code to satisfy LiveCarta formatting."""
self.logger.log("Beginning of processing .html file.")
self.logger.log(f"Processing TOC and headers.")
self._process_toc_links()
for rule in self.preset:
self.logger.log(rule["preset_name"] + " process.")
action = self.name2action[rule["preset_name"]]
self._process_tags(self.body_tag, rule["rules"], action)
self.logger.log("CSS inline style preprocessing.")
self.style_processor.process_inline_styles_in_html_soup(self.html_soup)
self.logger.log("CSS inline style processing.")
modify_html_soup_with_css_styles(self.html_soup)
# process main elements of the .html doc
self.logger.log(f"Processing main elements of html.")
self._process_paragraph()
self.logger.log("Block quotes processing.")
self._process_quotes()
self.logger.log("Tables processing.")
self._process_tables()
self.logger.log(
f"{self.tables_amount} tables have been processed.")
self.logger.log("Hrefs processing.")
self._process_hrefs()
self.logger.log("Image processing.")
self.images = process_images(access, path_to_html=html_path,
book_id=book_id, body_tag=self.body_tag)
@@ -479,7 +389,34 @@ class HTMLDocxProcessor:
self.logger.log(
f"{len(self.footnotes)} footnotes have been processed.")
self._process_div()
self.logger.log(f"Processing TOC and headers.")
self._process_toc_links()
for rule in self.preset:
self.logger.log(rule["preset_name"].title() + " process.")
action = self.name2action[rule["preset_name"]]
self._process_tags(self.body_tag, rule["rules"], action)
# CSS after html processing cause of <fonts> that aren't supported by html
self.logger.log("CSS inline style preprocessing.")
self.style_processor.process_inline_styles_in_html_soup(self.body_tag)
self.logger.log("CSS inline style processing.")
modify_html_soup_with_css_styles(self.body_tag)
# process main elements of the .html doc
self.logger.log(f"Processing main elements of html.")
self.logger.log("Block quotes processing.")
self._process_quotes()
self.logger.log("Tables processing.")
self._process_tables()
self.logger.log(
f"{self.tables_amount} tables have been processed.")
self.logger.log("Hrefs processing.")
self._process_hrefs()
self.top_level_headers: List[Dict[str, Union[str, bool]]]\
= self._get_top_level_headers()