Yuki Okuda yagays

JVSコーパス内のtranscripts_utf8.txtとファイル名の不一致を修正するスクリプト。

	"""
	$ python modify_sudachi_json.py --user_dict path/to/user.dic --debug
	"""

	import argparse
	import errno
	import json
	import os
	import site
	from pathlib import Path

	import json
	from http.server import HTTPServer, SimpleHTTPRequestHandler

	class CustomHandler(SimpleHTTPRequestHandler):
	def do_GET(self):
	SimpleHTTPRequestHandler.do_GET(self)
	print("===headers===\n", self.headers)
	print("===path===\n", self.path)

	def do_POST(self):

	# Ref. http://www.cs.cmu.edu/~wcohen/10-605/notes/autodiff.pdf

	from collections import namedtuple

	Assignment = namedtuple("Item", ("z", "g", "y_list"))

	# f(x_1, x_2) = (2x_1 + x_2)^2
	l = [Assignment(z="z1", g="add", y_list=["x1", "x1"]),
	Assignment(z="z2", g="add", y_list=["z1", "x2"]),
	Assignment(z="f", g="square", y_list=["z2"])]

	# for Python 3.6
	import unicodedata

	# from 0 through 1,114,111 (https://docs.python.org/3.6/library/functions.html#chr)
	for unicode_id in range(1114111):
	char = chr(unicode_id)
	normalized_char = unicodedata.normalize("NFKC", char)
	if char != normalized_char:
	if len(normalized_char) == 1:
	code_point = ord(normalized_char)