split-file

#!/usr/bin/env python3

import argparse
import os
import regex
import se.epub

def main():
	parser = argparse.ArgumentParser(description="Split an XHTML file into many files at all instances of <!--se:split-->, and include a header template for each file.")
	parser.add_argument("filename", metavar="FILE", help="an XHTML file")
	args = parser.parse_args()

	with open(args.filename, "r", encoding="utf-8") as file:
		xhtml = se.epub.strip_bom(file.read())

	with open(os.path.join(os.path.dirname(os.path.realpath(__file__)), "templates", "header.xhtml"), "r", encoding="utf-8") as file:
		header_xhtml = file.read()

	chapter_number = 1
	chapter_xhtml = ""

	#Remove leading split tags
	xhtml = regex.sub(r"^\s*<\!--se:split-->", "", xhtml)

	for line in xhtml.splitlines():
		if "<!--se:split-->" in line:
			prefix, suffix = line.split("<!--se:split-->")
			chapter_xhtml = chapter_xhtml + prefix
			output(chapter_number, header_xhtml, chapter_xhtml)

			chapter_number = chapter_number + 1
			chapter_xhtml = suffix

		else:
			chapter_xhtml = chapter_xhtml + "\n" + line

	if chapter_xhtml and not chapter_xhtml.isspace():
		output(chapter_number, header_xhtml, chapter_xhtml)

def output(chapter_number, header_xhtml, chapter_xhtml):
	with open("chapter-" + str(chapter_number) + ".xhtml", "w", encoding="utf-8") as file:
		file.write(header_xhtml.replace("NUMBER", str(chapter_number)) + "\n" + chapter_xhtml + "\n</section></body></html>")
		file.truncate()

if __name__ == "__main__":
	main()