def process_file(filepath: str) -> (str, str):
"""
Run through each file, locating titles and updating <title> tag.
INPUTS:
filepath: path to content file
OUTPUTS:
altered xhtml file text and new section ID (as a tuple)
"""
xhtml = gethtml(filepath)
soup = BeautifulSoup(xhtml, "html.parser")
heading = soup.find(
["h2", "h3", "h4", "h5",
"h6"]) # find first heading, not interested in h1 in halftitle
if heading:
title_info = process_first_heading(heading)
title_tag = soup.find("title")
sections = heading.find_parents("section")
get_part_prefix(title_info, sections)
new_id = title_info.generate_id()
section = heading.find_parent("section")
if section:
section["id"] = new_id
if title_tag:
title_tag.clear()
title_tag.append(title_info.output_title_tag())
return format_xhtml(str(soup)), new_id
# failure, so return blanks
return "", ""
def recreate(textpath: str, notes_soup: BeautifulSoup, endnotes: list):
"""
rebuilds endnotes.xhtml in the correct (possibly new) order
:param textpath: path to text folder in SE project
:param notes_soup:
:param endnotes:
:return:
"""
ol = notes_soup.ol
ol.clear()
endnotes.sort(key=lambda enote: enote.number)
for endnote in endnotes:
if endnote.matched:
li = notes_soup.new_tag("li")
li["id"] = "note-" + str(endnote.number)
li["epub:type"] = "endnote"
for content in endnote.contents:
if isinstance(content, Tag):
links = content.find_all("a")
for link in links:
epub_type = link.get("epub:type") or ""
if "se:referrer" in epub_type or "backlink" in epub_type:
href = link.get("href") or ""
if href:
link[
"href"] = endnote.source_file + "#noteref-" + str(
endnote.number)
li.append(content)
ol.append(li)
new_file = open(os.path.join(textpath, "endnotes.xhtml"), "w")
new_file.write(format_xhtml(str(notes_soup)))
new_file.close()
def output_toc(item_list: list, landmark_list, toc_path: str, work_type: str,
work_title: str) -> str:
"""
Outputs the contructed ToC based on the lists of items and landmarks found,
either to stdout or overwriting the existing ToC file
"""
if len(item_list) < 2:
raise se.InvalidInputException("Too few ToC items found.")
existing_toc: BeautifulSoup = get_existing_toc(toc_path)
if existing_toc is None:
raise se.InvalidInputException("Existing ToC not found.")
# There should be exactly two nav sections.
navs = existing_toc.find_all("nav")
if len(navs) < 2:
raise se.InvalidInputException(
"Existing ToC has too few nav sections.")
item_ol = navs[0].find("ol")
item_ol.clear()
landmark_ol = navs[1].find("ol")
landmark_ol.clear()
new_items = BeautifulSoup(process_items(item_list), "html.parser")
item_ol.append(new_items)
new_landmarks = BeautifulSoup(
process_landmarks(landmark_list, work_type, work_title), "html.parser")
landmark_ol.append(new_landmarks)
return format_xhtml(str(existing_toc))
def process_file(text_path: str, file_name: str, endnotes: list,
de_orphan: bool, current_note_number: int) -> int:
"""
Reads a content file, locates and processes the endnotes,
accumulating info on them in a global list, and returns the next note number
:param text_path: path to the text files in the project
:param file_name: the name of the file being processed eg chapter-1.xhtml
:param endnotes: list of notes we are building
:param de_orphan: remove reference in text if no matching endnote
:param current_note_number: the current note number we are allocating
:return: the next note number to use
"""
global notes_changed
file_path = os.path.join(text_path, file_name)
xhtml = gethtml(file_path)
soup = BeautifulSoup(xhtml, "lxml")
links = soup.find_all("a")
needs_rewrite = False
for link in links:
epub_type = link.get("epub:type") or ""
if epub_type == "noteref":
old_anchor = ""
href = link.get("href") or ""
if href:
old_anchor = extract_anchor(href)
new_anchor = "note-{:d}".format(current_note_number)
if new_anchor != old_anchor:
print("Changed " + old_anchor + " to " + new_anchor + " in " +
file_path)
notes_changed += 1
# update the link in the soup object
link["href"] = 'endnotes.xhtml#' + new_anchor
link["id"] = 'noteref-{:d}'.format(current_note_number)
link.string = str(current_note_number)
needs_rewrite = True
# now try to find this in endnotes
matches = list(filter(lambda x: x.anchor == old_anchor, endnotes))
if len(matches) == 0:
print("Couldn't find endnote with anchor " + old_anchor)
if de_orphan:
print("Removing orphan note ref in text")
link.clear()
needs_rewrite = True
elif len(matches) > 1:
print("Duplicate anchors in endnotes file for anchor " +
old_anchor)
else: # found a single match, which is what we want
listnote = matches[0]
listnote.number = current_note_number
listnote.matched = True
# we don't change the anchor or the back ref just yet
listnote.source_file = file_name
current_note_number += 1
# if we need to write back the body text file
if needs_rewrite:
new_file = open(file_path, "w")
new_file.write(format_xhtml(str(soup)))
# new_file.write(str(soup))
new_file.close()
return current_note_number
