# Copyright (C) 2024 The Meme Factory, Inc., http://www.karlpinc.com/
#
# This file is part of Babase.
#
# Babase is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with Babase. If not, see .
#
# Convert encoded "characters". Either to Unicode or to plain 7-bit ASCII.
#
#
# Karl O. Pinc
#
import sys
ASCII_MAP = {
0x2026: '...', # … (ALLMISCS.Text for AlMID 10478)
0xdcd5: "'", # ’ Mac OS Roman, RIGHT SINGLE QUOTATION MARK
0xdc92: "'", # Windows-1252, RIGHT SINGLE QUOTATION MARK
0xd4: 'u', # Ô Part of a sequence all replaced with "u"
0xf8: '', # ø Part of a sequence all replaced with "u"
0x03a9: '', # Ω Part of a sequence all replaced with "u"
0xdcb5: 'u', # µ
0xdca0: ' ', # U+00a0 Windows-1252 20
# NO-BREAK SPACE
0xdc91: "'", # ‘ U+2018 Windows-1252 ' 27
# LEFT SINGLE QUOTATION MARK
0xdc83: 'E', # É U+00c9 Mac OS Roman E 54
# LATIN CAPITAL LETTER E WITH ACUTE
0xdce0: 'a', # à U+00e0 Windows-1252 a 61
# LATIN SMALL LETTER A WITH GRAVE
0xdcc6: "'", # Used as an apostrophe ' 27
0x01f412: '', # 🐒 Removed
0xdcca: ' ', # Appears to be used in place of EOL??
# replacing with space (0x20)
0xb5: 'u', # µ U+00b5 u 75 MICRO SIGN
}
UNICODE_MAP = {
0xdc8e: chr(0x00e9), # é U+00e8 Mac OS Roman e 65
# LATIN SMALL LETTER E WITH ACUTE
0xdc92: chr(0x2019), # ’ U+2019 Windows-1252 ' 72
# RIGHT SINGLE QUOTATION MARK
0xdc90: chr(0x00ea), # ê U+00ea Mac OS Roman e 65
# LATIN SMALL LETTER E WITH CIRUMFLEX
0xdc8b: chr(0x00e3), # ã U+00e3 Mac OS Roman a 16
# LATIN SMALL LETTER A WITH TILDE
0xdc87: chr(0x00e1), # á U+00e1 Mac OS Roman a 16
# LATIN SMALL LETTER A WITH ACUTE
0xdc97: chr(0x00f3), # ó U+00f3 Mac OS Roman o f7
# LATIN SMALL LETTER O WITH ACUTE
0xdc8d: chr(0x00e7), # ç U+00e7 Mac OS Roman c 36
# LATIN SMALL LETTER O WITH CEDILLA
0xdcd5: chr(0x2019), # ’ U+2019 Mac OS Roman ' 72
# RIGHT SINGLE QUOTATION MARK
0xdca0: chr(0x00a0), # U+00a0 Windows-1252 to unicode non-break
# NO-BREAK SPACE
0xdc91: chr(0x2018), # ‘ U+2018 Windows-1252 ' 27
# LEFT SINGLE QUOTATION MARK
0xdc83: chr(0x00c9), # É U+00c9 Mac OS Roman E 54
# LATIN CAPITAL LETTER E WITH ACUTE
0xdce0: chr(0x00e0), # à U+00e0 Windows-1252 a 61
# LATIN SMALL LETTER A WITH GRAVE
0xdcc6: "'", # Used as an apostrophe ' 27
0xdcca: ' ', # Appears to be used in place of EOL??
# replacing with space (0x20)
0xdcb5: chr(0x00b5), # µ U+00b5 [both] u 75
# MICRO SIGN
0xdcc9: chr(0x2026), # … U+2026 Mac OS Roman
# HORIZONTAL ELLIPSES
0xdcaf: '0', # Ø U+00D8 Windows-1252 0 30
# LATIN CHARACTER O WITH A STROKE
0xdcf3: chr(0x00f3), # ó U+00F3 Windows-1252 o 6f
# LATIN SMALL LETTER O WITH ACUTE
0xdce3: chr(0x00e3), # ã U+00E3 Windows-1252 a 61
# LATIN SMALL LETTER A WITH TILDE
0xdce9: chr(0x00e9), # é U+00E9 Windows-1252 e 65
# LATIN SMALL LETTER E WITH ACUTE
0xdced: chr(0x00ed), # í U+00ED Windows-1252 i 69
# LATIN SMALL LETTER I WITH ACUTE
0xdcea: chr(0x00ea), # ê U+00EA Windows-1252 e 65
# LATIN SMALL LETTER E WITH CIRCUMFLEX
0xdce1: chr(0x00e1), # á U+00E1 Windows-1252 a 61
# LATIN SMALL LETTER A WITH ACUTE
0xdce7: chr(0x00e7), # ç U+00E7 Windows-1252 c 63
# LATIN SMALL LETTER C WITH CEDILLA
0xdcfa: chr(0x00fa), # ú U+00FA Windows-1252 u 75
# LATIN SMALL LETTER U WITH ACUTE
0xdcf4: chr(0x00f4), # ô U+00F4 Windows-1252 o 6f
# LATIN SMALL LETTER O WITH CIRCUMFLEX
0xdccd: chr(0x00cd), # Í U+00CD Windows-1252 I 49
# LATIN CAPITAL LETTER i WITH ACUTE
0xdce2: chr(0x00e1), # á U+00E1 Windows-1252 a 61
# LATIN SMALL LETTER A WITH ACUTE
0xdcc1: chr(0x00c1), # Á U+00C1 Windows-1252 A 65
# LATIN CAPITAL LETTER A WITH ACUTE
0xdcc7: chr(0x00c7), # Ç U+00C7 Windows-1252 C 67
# LATIN CAPITAL LETTER C WITH CEDILLA
0xdc85: chr(0x2026), # … U+2026 Windows-1252
# HORIZONTAL ELLIPSES
}
def unicode_convert(char):
try:
char.encode()
except UnicodeEncodeError:
return UNICODE_MAP[ord(char)]
return char
def ascii_convert(char):
return ASCII_MAP.get(ord(char), char)
# Universal newlines, so we can read a line at a time, but with EOL
# chars produced "as-is".
sys.stdin.reconfigure(newline='', errors='surrogateescape')
if len(sys.argv) > 1 and sys.argv[1] == '-u':
convert_char = unicode_convert
else:
convert_char = ascii_convert
for line in sys.stdin:
for char in line:
if char.isascii():
print(char, end='')
else:
print(convert_char(char), end='')