script dumper that works for kamimaho (based on kssize.py)

dump.py

# Modified to spit out main script content in utf-8
# Extract script with xp3viewer

import glob
import os
import re
import sys

# count mode
# not used

COUNT_MODE = 1

def is_iscript(s):
	return s.find('@iscript') == 0 or s.find('[iscript]') == 0
	
def is_endscript(s):
	return s.find('@endscript') == 0 or s.find('[endscript]') == 0

def remove_formatting(s):
	s = re.sub(r';.*', "", s)
	s = re.sub(r'^\*.*', "", s)
	s = re.sub(r'^@.*', "", s)
	s = re.sub(r'\[ruby text="(.*?)"\](.*?)\[/ruby\]', "〈\2〉《\1》", s)
	s = re.sub(r'\[ps\]', "\n", s)
	s = re.sub(r'\[[lr]\]', "", s)
	s = re.sub(r'\[[^ ]+([ ]+(([^" ]*[ ]*=[ ]*(("[^"]*")|([^ \]]*)))|(\*)|([^"= \]]*)))*[ ]*\]', "", s)
	#s = re.sub(r'\[.*?\]', "", s)
	return s

outfile = open("out.txt", "w+", encoding="utf-8")

def txtsize(fi):
	in_script = False
	lines = size = 0
	prevline_t = ''
	for line in fi.readlines():
		line_s = line.strip()
		if is_endscript(line_s):
			in_script = False
		if not in_script:
			line_t = remove_formatting(line_s)
			if(line_t != ""):
				outfile.write("%s\n" % line_t);
		if is_iscript(line_s):
			in_script = True
		prevline_t = line_t
	return lines,size
	
def get_encoding(fname):
	data = open(fname,'rb').read(2)
	if data == b'\xFF\xFE' or data == b'\xFE\xFF':
		return 'utf-16'
	else:
		return 'cp932'
	
if __name__ == '__main__':
	glines = gsize = 0
	for path in sys.argv:
		if path == '.':
			continue
		if path[-3:] != ".ks":
			continue
		for file in glob.glob(path):
			txtsize(open(file,'r',encoding=get_encoding(file)))