80 lines
2.3 KiB
Python
80 lines
2.3 KiB
Python
|
|
"""
|
|
Teletext Character Sets (G0).
|
|
Maps the specific code points (0x23, 0x24, 0x40, 0x5B-0x5E, 0x60, 0x7B-0x7E)
|
|
to Unicode characters based on the National Option (3 bits).
|
|
"""
|
|
|
|
# Default (English) - Option 000
|
|
ENGLISH = {
|
|
0x23: '#', 0x24: '$', 0x40: '@',
|
|
0x5B: '[', 0x5C: '\\', 0x5D: ']', 0x5E: '^',
|
|
0x5F: '_', 0x60: '`',
|
|
0x7B: '{', 0x7C: '|', 0x7D: '}', 0x7E: '~'
|
|
}
|
|
|
|
# Swedish/Finnish/Hungarian - Option 010 (2)
|
|
SWEDISH_FINNISH = {
|
|
0x23: '#', 0x24: '\u00A4', 0x40: '\u00C9',
|
|
0x5B: '\u00C4', 0x5C: '\u00D6', 0x5D: '\u00C5', 0x5E: '\u00DC',
|
|
0x5F: '_', 0x60: '\u00E9',
|
|
0x7B: '\u00E4', 0x7C: '\u00F6', 0x7D: '\u00E5', 0x7E: '\u00FC'
|
|
}
|
|
|
|
# German - Option 001 (1)
|
|
GERMAN = {
|
|
0x23: '#', 0x24: '$', 0x40: '§',
|
|
0x5B: 'Ä', 0x5C: 'Ö', 0x5D: 'Ü', 0x5E: '^',
|
|
0x5F: '_', 0x60: '`',
|
|
0x7B: 'ä', 0x7C: 'ö', 0x7D: 'ü', 0x7E: 'ß'
|
|
}
|
|
|
|
# We can add more as needed.
|
|
|
|
SETS = [
|
|
ENGLISH, # 000
|
|
GERMAN, # 001
|
|
SWEDISH_FINNISH, # 010
|
|
ENGLISH, # Italian (011) - placeholder
|
|
ENGLISH, # French (100) - placeholder
|
|
ENGLISH, # Portuguese/Spanish (101) - placeholder
|
|
ENGLISH, # Turkish (110) - placeholder
|
|
ENGLISH, # Romania (111) - placeholder
|
|
]
|
|
|
|
def get_char(byte_val, subset_idx):
|
|
if subset_idx < 0 or subset_idx >= len(SETS):
|
|
subset_idx = 0
|
|
|
|
mapping = SETS[subset_idx]
|
|
|
|
# If byte is in mapping, return mapped char.
|
|
# Else return ASCII equivalent (for basic chars)
|
|
|
|
valid_byte = byte_val & 0x7F # Strip parity if present (though our packet data is 8-bit usually already stripping parity?)
|
|
# Packet data we store is raw bytes. We should probably strip parity bit 7 before lookup.
|
|
|
|
if valid_byte in mapping:
|
|
return mapping[valid_byte]
|
|
|
|
return chr(valid_byte)
|
|
|
|
import unicodedata
|
|
|
|
def get_byte_from_char(char, subset_idx):
|
|
if len(char) != 1: return 0
|
|
|
|
# Normalize input to NFC to match our map keys (if they are NFC, which python literals usually are)
|
|
char = unicodedata.normalize('NFC', char)
|
|
|
|
if subset_idx < 0 or subset_idx >= len(SETS):
|
|
subset_idx = 0
|
|
|
|
mapping = SETS[subset_idx]
|
|
|
|
for code, mapped_char in mapping.items():
|
|
if mapped_char == char:
|
|
return code
|
|
|
|
return ord(char)
|