Created
June 19, 2019 09:45
-
-
Save bunyk/688a457acfc24f682d8bc2ef1a00d693 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
trans_table = { | |
'A': ('A', 0), 'a': ('a', 0), | |
'Ą': ('A', 1), 'ą': ('a', 1), | |
'C': ('C', 0), 'c': ('c', 0), | |
'Ć': ('C', 1), 'ć': ('c', 1), | |
'E': ('E', 0), 'e': ('e', 0), | |
'Ę': ('E', 1), 'ę': ('e', 1), | |
'L': ('L', 0), 'l': ('l', 0), | |
'Ł': ('L', 1), 'ł': ('l', 1), | |
'N': ('N', 0), 'n': ('n', 0), | |
'Ń': ('N', 1), 'ń': ('n', 1), | |
'O': ('O', 0), 'o': ('o', 0), | |
'Ó': ('O', 1), 'ó': ('o', 1), | |
'S': ('S', 0), 's': ('s', 0), | |
'Ś': ('S', 1), 'ś': ('s', 1), | |
'Z': ('Z', 0), 'z': ('z', 0), | |
'Ź': ('Z', 2), 'ź': ('z', 2), | |
'Ż': ('Z', 3), 'ż': ('z', 3), | |
} | |
ternary_chars = {'Z', 'z'} | |
def pol2ascii(text): | |
plain = [] | |
diacritics = [] | |
for c in text: | |
if c in trans_table: | |
ascii_char, diacritic = trans_table.get(c, (c, 0)) | |
diacritics.append(bin(diacritic)[2:][::-1]) | |
else: | |
ascii_char = c | |
plain.append(ascii_char) | |
return ''.join(plain) + '_' + hex(int(''.join(reversed(diacritics)), 2))[2:] | |
reverse_trans_table = { | |
k: v for v, k in trans_table.items() | |
} | |
def ascii2pol(text): | |
plain, diacritics = text.rsplit('_', 1) | |
diacritics = int(diacritics, base=16) | |
res = [] | |
for c in plain: | |
if c in trans_table: | |
diacritic = diacritics % 2 | |
diacritics = diacritics // 2 | |
if c in ternary_chars and diacritic == 1: | |
diacritic = diacritic * 2 + (diacritics % 2) | |
diacritics = diacritics // 2 | |
pol_char = reverse_trans_table.get((c, diacritic), c) | |
else: | |
pol_char = c | |
res.append(pol_char) | |
return ''.join(res) | |
TESTS = ''' | |
Świętosław Milczący | |
Dzierżykraj Łaźniński | |
Józef Soćko | |
jedną rzucających się zachodzących języka męskorzeczowego męskożywotny. słów, które w polszczyźnie standardowej były | |
''' | |
for l in TESTS.strip().splitlines(): | |
plain = pol2ascii(l) | |
original = ascii2pol(plain) | |
print(original, plain, f'+{(len(plain) / len(original) - 1) * 100:.1f}%') | |
print(l) | |
assert original == l |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment