british2american

#!/usr/bin/env python3

import argparse
import os
import fnmatch
import regex

IGNORED_FILES = ["colophon.xhtml", "titlepage.xhtml", "imprint.xhtml", "uncopyright.xhtml", "halftitle.xhtml", "toc.xhtml", "loi.xhtml"]

def main():
	parser = argparse.ArgumentParser(description="Try to convert British quote style to American quote style.  Quotes must already be \"typogrified\"--i.e. curly.  This script isn't perfect; proofreading is required, especially near closing quotes near to em-dashes.")
	parser.add_argument("-v", "--verbose", action="store_true", help="increase output verbosity")
	parser.add_argument("targets", metavar="TARGET", nargs="+", help="an XHTML file, or a directory containing XHTML files")
	args = parser.parse_args()

	for target in args.targets:
		target = os.path.abspath(target)

		if args.verbose:
			print("Processing {} ...".format(target), end="", flush=True)

		target_filenames = set()
		if os.path.isdir(target):
			for root, _, filenames in os.walk(target):
				for filename in fnmatch.filter(filenames, "*.xhtml"):
					if filename not in IGNORED_FILES:
						target_filenames.add(os.path.join(root, filename))
		else:
			target_filenames.add(target)

		for filename in target_filenames:
			with open(filename, "r+", encoding="utf-8") as file:
				xhtml = file.read()
				new_xhtml = xhtml

				new_xhtml = british_to_american(new_xhtml)

				if new_xhtml != xhtml:
					file.seek(0)
					file.write(new_xhtml)
					file.truncate()

		if args.verbose:
			print(" OK")

def british_to_american(xhtml):
	xhtml = regex.sub(r"“", r"<ldq>", xhtml)
	xhtml = regex.sub(r"”", r"<rdq>", xhtml)
	xhtml = regex.sub(r"‘", r"<lsq>", xhtml)
	xhtml = regex.sub(r"<rdq>⁠ ’(\s+)", r"<rdq> <rsq>\1", xhtml)
	xhtml = regex.sub(r"<rdq>⁠ ’</", r"<rdq> <rsq></", xhtml)
	xhtml = regex.sub(r"([\.\,\!\?\…\:\;])’", r"\1<rsq>", xhtml)
	xhtml = regex.sub(r"—’(\s+)", r"—<rsq>\1", xhtml)
	xhtml = regex.sub(r"—’</", r"—<rsq></", xhtml)
	xhtml = regex.sub(r"([a-z])’([a-z])", r"\1<ap>\2", xhtml)
	xhtml = regex.sub(r"(\s+)’([a-z])", r"\1<ap>\2", xhtml)
	xhtml = regex.sub(r"<ldq>", r"‘", xhtml)
	xhtml = regex.sub(r"<rdq>", r"’", xhtml)
	xhtml = regex.sub(r"<lsq>", r"“", xhtml)
	xhtml = regex.sub(r"<rsq>", r"”", xhtml)
	xhtml = regex.sub(r"<ap>", r"’", xhtml)
	xhtml = regex.sub(r"’ ’", r"’ ”", xhtml)	#Correct a common error

	return xhtml

if __name__ == "__main__":
	main()