#!/usr/bin/env python2.7
# -*- coding: UTF-8 -*-

from __future__ import print_function
from __future__ import unicode_literals

import re
import regex
import sys
import os

if not (("PYTHONIOENCODING" in os.environ)
            and
        re.search("^utf-?8$", os.environ["PYTHONIOENCODING"], re.I)):
    sys.stderr.write(sys.argv[0] + ": Please set your PYTHONIOENCODING envariable to utf8\n")
    sys.exit(1)

import unicodedata
if unicodedata.unidata_version < "6.0.0":
    print("WARNING: Your old UCD is out of date, expected 6.0.0 but got", 
           unicodedata.unidata_version)

wide_enough = (sys.maxunicode > 65536)
if not wide_enough:
    print("WARNING: Narrow build detected, your Python lacks full Unicode support!!")

data_rows = [
    [ "\N{COMBINING GREEK YPOGEGRAMMENI}", "\N{GREEK CAPITAL LETTER IOTA}" ],
    [ "\N{MICRO SIGN}", "\N{GREEK CAPITAL LETTER MU}" ],
    [ "\N{LATIN SMALL LETTER S}", "\N{LATIN SMALL LETTER LONG S}" ],
    [ "στιγμας", "ΣΤΙΓΜΑΣ" ],
    [  "poſt", "POST" ],
]

re_pass,    re_fail    = 0, 0 
regex_pass, regex_fail = 0, 0 

for lc, uc in data_rows:

    if re.match(uc, lc, re.IGNORECASE + re.UNICODE):
        print("PASS: re    pattern", uc, "is indeed the same as string", lc)
        re_pass = re_pass + 1
    else:
        print("FAIL: re    pattern", uc, "is    not the same as string", lc)
        re_fail = re_fail + 1

    if regex.match(uc, lc, regex.IGNORECASE + regex.UNICODE):
        print("PASS: regex pattern", uc, "is indeed the same as string", lc)
        regex_pass = regex_pass + 1
    else:
        print("FAIL: regex pattern", uc, "is    not the same as string", lc)
        regex_fail = regex_fail + 1


re_total    = re_pass    + re_fail
regex_total = regex_pass + regex_fail

print("")

print("re    lib passed",    re_pass,    "of", re_total,    "tests")
print("regex lib passed", regex_pass, "of", regex_total, "tests")

##########################################
# FAIL: re    pattern Ι is    not the same as string ͅ
# PASS: regex pattern Ι is indeed the same as string ͅ
# FAIL: re    pattern Μ is    not the same as string µ
# PASS: regex pattern Μ is indeed the same as string µ
# FAIL: re    pattern ſ is    not the same as string s
# PASS: regex pattern ſ is indeed the same as string s
# FAIL: re    pattern ΣΤΙΓΜΑΣ is    not the same as string στιγμας
# PASS: regex pattern ΣΤΙΓΜΑΣ is indeed the same as string στιγμας
# FAIL: re    pattern POST is    not the same as string poſt
# PASS: regex pattern POST is indeed the same as string poſt
#
# re    lib passed 0 of 5 tests
# regex lib passed 5 of 5 tests