reorder-endnotes

#!/usr/bin/env python3

import argparse
import os
import sys
import fnmatch
import regex
from bs4 import BeautifulSoup

def is_positive_integer(value):
	int_value = int(value)
	if int_value <= 0:
		raise argparse.ArgumentTypeError("{} is not a positive integer".format(value))

	return int_value

def main():
	parser = argparse.ArgumentParser(description="Increment the specified endnote and all following endnotes by 1.")
	parser.add_argument("target_endnote_number", metavar="ENDNOTE-NUMBER", type=is_positive_integer, help="the endnote number to start incrementing at")
	parser.add_argument("directory", metavar="DIRECTORY", help="a Standard Ebooks source directory")
	args = parser.parse_args()

	directory = os.path.abspath(args.directory)
	target_endnote_number = int(args.target_endnote_number)
	endnote_count = 0
	source_directory = os.path.join(directory, "src/")

	#First get the highest numbered endnote
	try:
		endnotes_filename = os.path.join(source_directory, "epub/text/endnotes.xhtml")
		with open(endnotes_filename, "r+", encoding="utf-8") as file:
			xhtml = file.read()
			soup = BeautifulSoup(xhtml, "lxml")

			endnote_count = len(soup.select("li[data-se-note-number]"))

			for endnote_number in range(endnote_count, target_endnote_number - 1, -1):
				xhtml = xhtml.replace("id=\"note-{}\"".format(endnote_number), "id=\"note-{}\"".format(endnote_number + 1))
				xhtml = xhtml.replace("data-se-note-number=\"{}\"".format(endnote_number), "data-se-note-number=\"{}\"".format(endnote_number + 1))
				xhtml = xhtml.replace("#note-{}\"".format(endnote_number), "#note-{}\"".format(endnote_number + 1))

			file.seek(0)
			file.write(xhtml)
			file.truncate()

	except Exception:
		print("Error: Couldn't open endnotes file: {}".format(endnotes_filename), file=sys.stderr)
		exit(1)

	for root, _, filenames in os.walk(source_directory):
		for filename in fnmatch.filter(filenames, "*.xhtml"):
			#Skip endnotes.xhtml since we already processed it
			if filename == "endnotes.xhtml":
				continue

			with open(os.path.join(root, filename), "r+", encoding="utf-8") as file:
				xhtml = file.read()

				for endnote_number in range(endnote_count, target_endnote_number - 1, -1):
					xhtml = regex.sub(r"(<a[^>]*?>){}</a>".format(endnote_number), "\g<1>{}</a>".format(endnote_number + 1), xhtml, flags=regex.MULTILINE | regex.DOTALL)
					xhtml = xhtml.replace("id=\"note-{}\"".format(endnote_number), "id=\"note-{}\"".format(endnote_number + 1))
					xhtml = xhtml.replace("#note-{}\"".format(endnote_number), "#note-{}\"".format(endnote_number + 1))

				file.seek(0)
				file.write(xhtml)
				file.truncate()

if __name__ == "__main__":
	main()