text_to_outline.py

# markdown headline
import sys
import re
import pprint

'''
ベタ/tab-outline/markdownの変換
元が何か判別
変換先は何か
コマンドラインオプション
'''

def main():
	fh = get_fh()
	readdata = fh.readlines()
	# データをパース、解釈
	inner_data = arrange_data(data)
	# outdata = arrange_data(data)
	for line in outdata:
		print(line)

def get_fh():
	fh = None
	if (len(sys.argv)>1):
		# ファイルの存在確認、なければ終了
		datafile = sys.argv[1]
		fh = open(datafile,mode="r",encoding="utf-8")
	else:
		fh = sys.stdin
	return fh

def read_from_fh(fh):
	data = []
	with fh:
		ln = fh.readlines()
		for l in ln:
			# l=l.rstrip()
			l=l.strip()
			if re.search('^#{2,}',l):
				data.append(l)
			else:
				continue
	return data


def set_data_structure(data):
	# remove null line
	# (group lines)
	# determine type
	# check '-': markdown
	# check spaces: outline
	# none: plaintext
	pass


class CnvMarkdown:
	NAME='md'
	def __init__(self):
		pass
	def check(self,line):
		re.search('^\-',line)
	def strip_all(self,lines):
		ra = []
		for line in lines:
			line = re.sub('^\-','',line)
			ra.append({'lv':0, 'text':line})
		return ra
	def add_all(self,data_lines):
		ra = []
		for dl in data_lines:
			ra.append('- ' + dl['text'])
		return ra

class CnvTabtext:
	NAME='tab'
	def __init__(self):
		pass
	def check(self,line):
		re.search('^\s+',line)
	def strip_all(self,lines):
		ra = []
		for line in lines:
			line = re.sub('^\s+','',line)
			ra.append({'lv':0, 'text':line})
		return ra
	def add_all(self,data_lines):
		ra = []
		for dl in data_lines:
			ra.append('- ' + dl['text'])
		return ra




lines = 'aaa bbb ccc ddd'.split()
cM = CnvMarkdown()

i_lines = cM.strip_all(lines)
o_lines = cM.add_all(i_lines)
print(cM.NAME)
print(o_lines)
## debug output
# pprint.PrettyPrinter(indent=2).pprint('test')


#if __name__ == "__main__":
#	main()