radio95/rds95
0
1
Fork 0
mirror of https://github.com/radio95-rnt/rds95.git synced 2026-07-30 08:49:15 +02:00
Code Issues Wiki Activity

more smart

Browse Source
This commit is contained in:
kuba
2026-03-20 20:35:42 +01:00
parent 130a83e4d5
commit 35bbb2aa99
3 changed files with 280 additions and 383 deletions
Download Patch File Download Diff File Expand all files Collapse all files
charset.py
+266 -142
View File
@@ -4,132 +4,237 @@ import unicodedata
# RDS code to UCS-2 # RDS code to UCS-2
charset = {} charset = {}
charset[0x24] = 0x00A4 # ¤ # The data comes directly from the rdscharset.pdf, which comes from the R22_039_1 standard
charset[0x5E] = 0x2015 # ―
charset[0x60] = 0x2016 # ║ data = """33 0x21 ! 0x0021 EXCLAMATION MARK
charset[0x7E] = 0x203E # ¯ 34 0x22 " 0x0022 QUOTATION MARK
charset[0x80] = 0x00E1 # á 35 0x23 # 0x0023 NUMBER SIGN
charset[0x81] = 0x00E0 # à 36 0x24 ¤ 0x00A4 CURRENCY SIGN
charset[0x82] = 0x00E9 # é 37 0x25 % 0x0025 PERCENT SIGN
charset[0x83] = 0x00E8 # è 38 0x26 & 0x0026 AMPERSAND
charset[0x84] = 0x00ED # í 39 0x27 ' 0x0027 APOSTROPHE
charset[0x85] = 0x00EC # ì 40 0x28 ( 0x0028 LEFT PARENTHESIS
charset[0x86] = 0x00F3 # ó 41 0x29 ) 0x0029 RIGHT PARENTHESIS
charset[0x87] = 0x00F2 # ò 42 0x2A * 0x002A ASTERISK
charset[0x88] = 0x00FA # ú 43 0x2B + 0x002B PLUS SIGN
charset[0x89] = 0x00F9 # ù 44 0x2C , 0x002C COMMA
charset[0x8A] = 0x00D1 # Ñ 45 0x2D - 0x002D HYPHEN-MINUS
charset[0x8B] = 0x00C7 # Ç 46 0x2E . 0x002E FULL STOP
charset[0x8C] = 0x015E # Ş 47 0x2F / 0x002F SOLIDUS
charset[0x8D] = 0x00DF # ß 48 0x30 0 0x0030 DIGIT ZERO
charset[0x8E] = 0x00A1 # ¡ 49 0x31 1 0x0031 DIGIT ONE
charset[0x8F] = 0x0132 # IJ 50 0x32 2 0x0032 DIGIT TWO
charset[0x90] = 0x00E2 # â 51 0x33 3 0x0033 DIGIT THREE
charset[0x91] = 0x00E4 # ä 52 0x34 4 0x0034 DIGIT FOUR
charset[0x92] = 0x00EA # ê 53 0x35 5 0x0035 DIGIT FIVE
charset[0x93] = 0x00EB # ë 54 0x36 6 0x0036 DIGIT SIX
charset[0x94] = 0x00EE # î 55 0x37 7 0x0037 DIGIT SEVEN
charset[0x95] = 0x00EF # ï 56 0x38 8 0x0038 DIGIT EIGHT
charset[0x96] = 0x00F4 # ô 57 0x39 9 0x0039 DIGIT NINE
charset[0x97] = 0x00F6 # ö 58 0x3A : 0x003A COLON
charset[0x98] = 0x00FB # û 59 0x3B ; 0x003B SEMICOLON
charset[0x99] = 0x00FC # ü 60 0x3C < 0x003C LESS-THAN SIGN
charset[0x9A] = 0x00F1 # ñ 61 0x3D = 0x003D EQUALS SIGN
charset[0x9B] = 0x00E7 # ç 62 0x3E > 0x003E GREATER-THAN SIGN
charset[0x9C] = 0x015F # ş 63 0x3F ? 0x003F QUESTION MARK
charset[0x9D] = 0x011F # ğ 64 0x40 @ 0x0040 COMMERCIAL AT
charset[0x9E] = 0x0131 # ı 65 0x41 A 0x0041 LATIN CAPITAL LETTER A
charset[0x9F] = 0x0133 # ij 66 0x42 B 0x0042 LATIN CAPITAL LETTER B
charset[0xA0] = 0x00AA # ª 67 0x43 C 0x0043 LATIN CAPITAL LETTER C
charset[0xA1] = 0x03B1 # α 68 0x44 D 0x0044 LATIN CAPITAL LETTER D
charset[0xA2] = 0x00A9 # © 69 0x45 E 0x0045 LATIN CAPITAL LETTER E
charset[0xA3] = 0x2030 # ‰ 70 0x46 F 0x0046 LATIN CAPITAL LETTER F
charset[0xA4] = 0x011E # Ğ 71 0x47 G 0x0047 LATIN CAPITAL LETTER G
charset[0xA5] = 0x011B # ĕ 72 0x48 H 0x0048 LATIN CAPITAL LETTER H
charset[0xA6] = 0x0148 # ň 73 0x49 I 0x0049 LATIN CAPITAL LETTER I
charset[0xA7] = 0x0151 # ő 74 0x4A J 0x004A LATIN CAPITAL LETTER J
charset[0xA8] = 0x03C0 # π 75 0x4B K 0x004B LATIN CAPITAL LETTER K
charset[0xA9] = 0x20AC # € 76 0x4C L 0x004C LATIN CAPITAL LETTER L
charset[0xAA] = 0x00A3 # ₤ 77 0x4D M 0x004D LATIN CAPITAL LETTER M
charset[0xAB] = 0x0024 # $ 78 0x4E N 0x004E LATIN CAPITAL LETTER N
charset[0xAC] = 0x2190 # ← 79 0x4F O 0x004F LATIN CAPITAL LETTER O
charset[0xAD] = 0x2191 # ↑ 80 0x50 P 0x0050 LATIN CAPITAL LETTER P
charset[0xAE] = 0x2192 # → 81 0x51 Q 0x0051 LATIN CAPITAL LETTER Q
charset[0xAF] = 0x2193 # ↓ 82 0x52 R 0x0052 LATIN CAPITAL LETTER R
charset[0xB0] = 0x00BA # º 83 0x53 S 0x0053 LATIN CAPITAL LETTER S
charset[0xB1] = 0x00B9 # ¹ 84 0x54 T 0x0054 LATIN CAPITAL LETTER T
charset[0xB4] = 0x00B1 # ± 85 0x55 U 0x0055 LATIN CAPITAL LETTER U
charset[0xB5] = 0x0130 # İ 86 0x56 V 0x0056 LATIN CAPITAL LETTER V
charset[0xB6] = 0x0144 # ń 87 0x57 W 0x0057 LATIN CAPITAL LETTER W
charset[0xB7] = 0x0171 # ű 88 0x58 X 0x0058 LATIN CAPITAL LETTER X
charset[0xB8] = 0x00B5 # µ 89 0x59 Y 0x0059 LATIN CAPITAL LETTER Y
charset[0xB9] = 0x00BF # ¿ 90 0x5A Z 0x005A LATIN CAPITAL LETTER Z
charset[0xBA] = 0x00F7 # ÷ 91 0x5B [ 0x005B LEFT SQUARE BRACKET
charset[0xBB] = 0x00B0 # º 92 0x5C \\ 0x005C REVERSE SOLIDUS
charset[0xBF] = 0x00A7 # § 93 0x5D ] 0x005D RIGHT SQUARE BRACKET
charset[0xC0] = 0x00C1 # Á 94 0x5E ― 0x2015 HORIZONTAL BAR
charset[0xC1] = 0x00C0 # À 95 0x5F _ 0x005F LOW LINE
charset[0xC2] = 0x00C9 # É 96 0x60 ║ 0x2016 DOUBLE VERTICAL LINE
charset[0xC3] = 0x00C8 # È 97 0x61 a 0x0061 LATIN SMALL LETTER A
charset[0xC4] = 0x00CD # Í 98 0x62 b 0x0062 LATIN SMALL LETTER B
charset[0xC5] = 0x00CC # Ì 99 0x63 c 0x0063 LATIN SMALL LETTER C
charset[0xC6] = 0x00D3 # Ó 100 0x64 d 0x0064 LATIN SMALL LETTER D
charset[0xC7] = 0x00D2 # Ò 101 0x65 e 0x0065 LATIN SMALL LETTER E
charset[0xC8] = 0x00DA # Ú 102 0x66 f 0x0066 LATIN SMALL LETTER F
charset[0xC9] = 0x00D9 # Ù 103 0x67 g 0x0067 LATIN SMALL LETTER G
charset[0xCA] = 0x0158 # Ř 104 0x68 h 0x0068 LATIN SMALL LETTER H
charset[0xCB] = 0x010C # Č 105 0x69 i 0x0069 LATIN SMALL LETTER I
charset[0xCC] = 0x0160 # Š 106 0x6A j 0x006A LATIN SMALL LETTER J
charset[0xCD] = 0x017D # Ž 107 0x6B k 0x006B LATIN SMALL LETTER K
charset[0xCE] = 0x00D0 # Ð 108 0x6C l 0x006C LATIN SMALL LETTER L
charset[0xCF] = 0x013F # Ŀ 109 0x6D m 0x006D LATIN SMALL LETTER M
charset[0xD0] = 0x00C2 # Â 110 0x6E n 0x006E LATIN SMALL LETTER N
charset[0xD1] = 0x00C4 # Ä 111 0x6F o 0x006F LATIN SMALL LETTER O
charset[0xD2] = 0x00CA # Ê 112 0x70 p 0x0070 LATIN SMALL LETTER P
charset[0xD3] = 0x00CB # Ë 113 0x71 q 0x0071 LATIN SMALL LETTER Q
charset[0xD4] = 0x00CE # Î 114 0x72 r 0x0072 LATIN SMALL LETTER R
charset[0xD5] = 0x00CF # Ï 115 0x73 s 0x0073 LATIN SMALL LETTER S
charset[0xD6] = 0x00D4 # Ô 116 0x74 t 0x0074 LATIN SMALL LETTER T
charset[0xD7] = 0x00D6 # Ö 117 0x75 u 0x0075 LATIN SMALL LETTER U
charset[0xD8] = 0x00DB # Û 118 0x76 v 0x0076 LATIN SMALL LETTER V
charset[0xD9] = 0x00DC # Ü 119 0x77 w 0x0077 LATIN SMALL LETTER W
charset[0xDA] = 0x0159 # ř 120 0x78 x 0x0078 LATIN SMALL LETTER X
charset[0xDB] = 0x010D # č 121 0x79 y 0x0079 LATIN SMALL LETTER Y
charset[0xDC] = 0x0161 # š 122 0x7A z 0x007A LATIN SMALL LETTER Z
charset[0xDD] = 0x017E # ž 123 0x7B { 0x007B LEFT CURLY BRACKET
charset[0xDE] = 0x0111 # đ 124 0x7C | 0x007C VERTICAL LINE
charset[0xDF] = 0x0140 # ŀ 125 0x7D } 0x007D RIGHT CURLY BRACKET
charset[0xE0] = 0x00C3 # Ã 126 0x7E ¯ 0x203E OVERLINE
charset[0xE1] = 0x00C5 # Å 128 0x80 á 0x00E1 LATIN SMALL LETTER A WITH ACUTE
charset[0xE2] = 0x00C6 # Æ 129 0x81 à 0x00E0 LATIN SMALL LETTER A WITH GRAVE
charset[0xE3] = 0x0152 # Œ 130 0x82 é 0x00E9 LATIN SMALL LETTER E WITH ACUTE
charset[0xE4] = 0x0177 # ŷ 131 0x83 è 0x00E8 LATIN SMALL LETTER E WITH GRAVE
charset[0xE5] = 0x00DD # Ý 132 0x84 í 0x00ED LATIN SMALL LETTER I WITH ACUTE
charset[0xE6] = 0x00D5 # Õ 133 0x85 ì 0x00EC LATIN SMALL LETTER I WITH GRAVE
charset[0xE7] = 0x00D8 # Ø 134 0x86 ó 0x00F3 LATIN SMALL LETTER O WITH ACUTE
charset[0xE8] = 0x00DE # Þ 135 0x87 ò 0x00F2 LATIN SMALL LETTER O WITH GRAVE
charset[0xE9] = 0x014A # Ŋ 136 0x88 ú 0x00FA LATIN SMALL LETTER U WITH ACUTE
charset[0xEA] = 0x0154 # Ŕ 137 0x89 ù 0x00F9 LATIN SMALL LETTER U WITH GRAVE
charset[0xEB] = 0x0106 # Ć 138 0x8A Ñ 0x00D1 LATIN CAPITAL LETTER N WITH TILDE
charset[0xEC] = 0x015A # Ś 139 0x8B Ç 0x00C7 LATIN CAPITAL LETTER C WITH CEDILLA
charset[0xED] = 0x0179 # Ź 140 0x8C Ş 0x015E LATIN CAPITAL LETTER S WITH CEDILLA
charset[0xEE] = 0x0166 # Ŧ 141 0x8D ß 0x00DF LATIN SMALL LETTER SHARP S (German)
charset[0xEF] = 0x00F0 # ð 142 0x8E ¡ 0x00A1 INVERTED EXCLAMATION MARK
charset[0xF0] = 0x00E3 # ã 143 0x8F IJ 0x0132 LATIN CAPITAL LIGATURE IJ
charset[0xF1] = 0x00E5 # å 144 0x90 â 0x00E2 LATIN SMALL LETTER A WITH CIRCUMFLEX
charset[0xF2] = 0x00E6 # æ 145 0x91 ä 0x00E4 LATIN SMALL LETTER A WITH DIAERESIS
charset[0xF3] = 0x0153 # œ 146 0x92 ê 0x00EA LATIN SMALL LETTER E WITH CIRCUMFLEX
charset[0xF4] = 0x0175 # ŵ 147 0x93 ë 0x00EB LATIN SMALL LETTER E WITH DIAERESIS
charset[0xF5] = 0x00FD # ý 148 0x94 î 0x00EE LATIN SMALL LETTER I WITH CIRCUMFLEX
charset[0xF6] = 0x00F5 # õ 149 0x95 ï 0x00EF LATIN SMALL LETTER I WITH DIAERESIS
charset[0xF7] = 0x00F8 # ø 150 0x96 ô 0x00F4 LATIN SMALL LETTER O WITH CIRCUMFLEX
charset[0xF8] = 0x00FE # þ 151 0x97 ö 0x00F6 LATIN SMALL LETTER O WITH DIAERESIS
charset[0xF9] = 0x014B # ŋ 152 0x98 û 0x00FB LATIN SMALL LETTER U WITH CIRCUMFLEX
charset[0xFA] = 0x0155 # ŕ 153 0x99 ü 0x00FC LATIN SMALL LETTER U WITH DIAERESIS
charset[0xFB] = 0x0107 # ć 154 0x9A ñ 0x00F1 LATIN SMALL LETTER N WITH TILDE
charset[0xFC] = 0x015B # ś 155 0x9B ç 0x00E7 LATIN SMALL LETTER C WITH CEDILLA
charset[0xFD] = 0x017A # ź 156 0x9C ş 0x015F LATIN SMALL LETTER S WITH CEDILLA
charset[0xFE] = 0x0167 # ŧ 157 0x9D ğ 0x011F LATIN SMALL LETTER G WITH BREVE
158 0x9E ı 0x0131 LATIN SMALL LETTER DOTLESS I
159 0x9F ij 0x0133 LATIN SMALL LIGATURE IJ
160 0xA0 ª 0x00AA FEMININE ORDINAL INDICATOR
161 0xA1 α 0x03B1 GREEK SMALL LETTER ALPHA
162 0xA2 © 0x00A9 COPYRIGHT SIGN
163 0xA3 ‰ 0x2030 PER THOUSAND SIGN
164 0xA4 Ğ 0x011E LATIN CAPITAL LETTER G WITH BREVE
165 0xA5 ĕ 0x011B LATIN SMALL LETTER WITH CARON
166 0xA6 ň 0x0148 LATIN SMALL LETTER N WITH CARON
167 0xA7 ő 0x0151 LATIN SMALL LETTER O WITH DOUBLE ACUTE
168 0xA8 π 0x03C0 GREEK SMALL LETTER PI
169 0xA9 € 0x20AC EURO SIGN
170 0xAA ₤ 0x00A3 POUND SIGN
171 0xAB $ 0x0024 DOLLAR SIGN
172 0xAC ← 0x2190 LEFTWARDS ARROW
173 0xAD ↑ 0x2191 UPWARDS ARROW
174 0xAE → 0x2192 RIGHTWARDS ARROW
175 0xAF ↓ 0x2193 DOWNWARDS ARROW
176 0xB0 º 0x00BA MASCULIN ORDINAL INDICATOR
177 0xB1 ¹ 0x00B9 SUPERSCRIPT ONE
178 0xB2 ² 0x00B2 SUPERSCRIPT TWO
179 0xB3 ³ 0x00B3 SUPERSCRIPT THREE
180 0xB4 ± 0x00B1 PLUS-MINUS SIGN
181 0xB5 İ 0x0130 LATIN CAPITAL LETTER I WITH DOT ABOVE
182 0xB6 ń 0x0144 LATIN SMALL LETTER N WITH ACUTE
183 0xB7 ű 0x0171 LATIN SMALL LETTER U WITH DOUBLE ACUTE
184 0xB8 µ 0x00B5 MIKRO SIGN
185 0xB9 ¿ 0x00BF INVERTED QUESTION MARK
186 0xBA ÷ 0x00F7 DIVISION SIGN
187 0xBB º 0x00B0 DEGREE SIGN
188 0xBC ¼ 0x00BC VULGAR FRACTION ONE QUARTER
189 0xBD ½ 0x00BD VULGAR FRACTION ONE HALF
190 0xBE ¾ 0x00BE VULGAR FRACTION THREE QUARTERS
191 0xBF § 0x00A7 SECTION SIGN
192 0xC0 Á 0x00C1 LATIN CAPITAL LETTER A WITH ACUTE
193 0xC1 À 0x00C0 LATIN CAPITAL LETTER A WITH GRAVE
194 0xC2 É 0x00C9 LATIN CAPITAL LETTER E WITH ACUTE
195 0xC3 È 0x00C8 LATIN CAPITAL LETTER E WITH GRAVE
196 0xC4 Í 0x00CD LATIN CAPITAL LETTER I WITH ACUTE
197 0xC5 Ì 0x00CC LATIN CAPITAL LETTER I WITH GRAVE
198 0xC6 Ó 0x00D3 LATIN CAPITAL LETTER O WITH ACUTE
199 0xC7 Ò 0x00D2 LATIN CAPITAL LETTER O WITH GRAVE
200 0xC8 Ú 0x00DA LATIN CAPITAL LETTER U WITH ACUTE
201 0xC9 Ù 0x00D9 LATIN CAPITAL LETTER U WITH GRAVE
202 0xCA Ř 0x0158 LATIN CAPITAL LETTER R WITH CARON
203 0xCB Č 0x010C LATIN CAPITAL LETTER C WITH CARON
204 0xCC Š 0x0160 LATIN CAPITAL LETTER S WITH CARON
205 0xCD Ž 0x017D LATIN CAPITAL LETTER Z WITH CARON
206 0xCE Ð 0x00D0 LATIN CAPITAL LETTER ETH
207 0xCF Ŀ 0x013F LATIN CAPITAL LETTER L WITH MIDDLE DOT
208 0xD0 Â 0x00C2 LATIN CAPITAL LETTER A WITH CIRCUMFLEX
209 0xD1 Ä 0x00C4 LATIN CAPITAL LETTER A WITH DIAERESIS
210 0xD2 Ê 0x00CA LATIN CAPITAL LETTER E WITH CIRCUMFLEX
211 0xD3 Ë 0x00CB LATIN CAPITAL LETTER A WITH DIAERESIS
212 0xD4 Î 0x00CE LATIN CAPITAL LETTER I WITH CIRCUMFLEX
213 0xD5 Ï 0x00CF LATIN CAPITAL LETTER I WITH DIAERESIS
214 0xD6 Ô 0x00D4
215 0xD7 Ö 0x00D6
216 0xD8 Û 0x00DB
217 0xD9 Ü 0x00DC
218 0xDA ř 0x0159
219 0xDB č 0x010D
220 0xDC š 0x0161
221 0xDD ž 0x017E
222 0xDE đ 0x0111
223 0xDF ŀ 0x0140
224 0xE0 Ã 0x00C3
225 0xE1 Å 0x00C5
226 0xE2 Æ 0x00C6
227 0xE3 Π0x0152
228 0xE4 ŷ 0x0177
229 0xE5 Ý 0x00DD
230 0xE6 Õ 0x00D5
231 0xE7 Ø 0x00D8
232 0xE8 Þ 0x00DE
233 0xE9 Ŋ 0x014A
234 0xEA Ŕ 0x0154
235 0xEB Ć 0x0106
236 0xEC Ś 0x015A
237 0xED Ź 0x0179
238 0xEE Ŧ 0x0166
239 0xEF ð 0x00F0
240 0xF0 ã 0x00E3
241 0xF1 å 0x00E5
242 0xF2 æ 0x00E6
243 0xF3 œ 0x0153
244 0xF4 ŵ 0x0175
245 0xF5 ý 0x00FD
246 0xF6 õ 0x00F5
247 0xF7 ø 0x00F8
248 0xF8 þ 0x00FE
249 0xF9 ŋ 0x014B
250 0xFA ŕ 0x0155
251 0xFB ć 0x0107
252 0xFC ś 0x015B
253 0xFD ź 0x017A
254 0xFE ŧ 0x0167
"""
for line in data.splitlines():
parts = line.split()
num, rds_code, symbol, ucs2, *_ = parts
code = int(rds_code, 16)
ucs = int(ucs2, 16)
if code != ucs: charset[code] = ucs
table = {} table = {}
@@ -147,30 +252,49 @@ for rds_code, ucs2 in charset.items():
if byte not in node: if byte not in node:
node[byte] = {} node[byte] = {}
node = node[byte] node = node[byte]
def generate_switch(node, indent=0): def generate_switch(node, indent=0, level=0):
""" ind = "\t" * indent
Recursively generates nested C switch statements from the table.
`node` is the current dictionary level.
`indent` is used for formatting the output.
"""
ind = " " * indent
code_lines = [f"{ind}switch(*str) {{"] code_lines = [f"{ind}switch(*str) {{"]
for byte, child in node.items(): for byte, child in node.items():
if isinstance(child, dict): if isinstance(child, dict):
code_lines.append(f"{ind} case (char)0x{byte:02x}:") code_lines.append(f"{ind}\tcase (char)0x{byte:02x}:")
code_lines.append(f"{ind} str++;") code_lines.append(f"{ind}\t\tstr++;")
code_lines.extend(generate_switch(child, indent + 2)) code_lines.extend(generate_switch(child, indent + 2, level + 1))
code_lines.append(f"{ind} break;") code_lines.append(f"{ind}\t\tbreak;")
else: else:
comment = unicodedata.name(struct.pack("!H", charset[child]).decode("utf-16-be")) comment = unicodedata.name(struct.pack("!H", charset[child]).decode("utf-16-be"))
code_lines.append(f"{ind} case (char)0x{byte:02x}: new_str[i] = (char)0x{child:02x}; break; // {comment}") code_lines.append(f"{ind}\tcase (char)0x{byte:02x}: new_str[i] = (char)0x{child:02x}; break; // {comment}")
code_lines.append(f"{ind} default: new_str[i] = *str; break;") if level == 0: code_lines.append(f"{ind}\tdefault: new_str[i] = *str; break;")
else: code_lines.append(f"{ind}\tdefault: new_str[i] = (char)0x3f; break; // {unicodedata.name("?")}") # Question mark
code_lines.append(f"{ind}}}") code_lines.append(f"{ind}}}")
return code_lines return code_lines
data = generate_switch(table) data = generate_switch(table, 2)
with open("switch.c", "w", encoding="utf-8") as f:
for line in data: lines = []
lines_end = []
with open("src/lib.c", "r", encoding="utf-8") as f:
while True:
pos = f.tell()
line = f.readline()
if f.tell() == pos: break
lines.append(line.rstrip())
if "// CHARSET START" in line: break
while True:
pos = f.tell()
line = f.readline()
if f.tell() == pos: break
if "// CHARSET END" in line:
lines_end.append(line.rstrip())
break
while True:
pos = f.tell()
line = f.readline()
if f.tell() == pos: break
lines_end.append(line.rstrip())
with open("src/lib.c", "w", encoding="utf-8") as f:
for line in lines + data + lines_end:
f.write(line + "\n") f.write(line + "\n")
charset2.py
-230
View File
@@ -1,230 +0,0 @@
# The data comes directly from the rdscharset.pdf, which comes from the R22_039_1 standard
data = """33 0x21 ! 0x0021 EXCLAMATION MARK
34 0x22 " 0x0022 QUOTATION MARK
35 0x23 # 0x0023 NUMBER SIGN
36 0x24 ¤ 0x00A4 CURRENCY SIGN
37 0x25 % 0x0025 PERCENT SIGN
38 0x26 & 0x0026 AMPERSAND
39 0x27 ' 0x0027 APOSTROPHE
40 0x28 ( 0x0028 LEFT PARENTHESIS
41 0x29 ) 0x0029 RIGHT PARENTHESIS
42 0x2A * 0x002A ASTERISK
43 0x2B + 0x002B PLUS SIGN
44 0x2C , 0x002C COMMA
45 0x2D - 0x002D HYPHEN-MINUS
46 0x2E . 0x002E FULL STOP
47 0x2F / 0x002F SOLIDUS
48 0x30 0 0x0030 DIGIT ZERO
49 0x31 1 0x0031 DIGIT ONE
50 0x32 2 0x0032 DIGIT TWO
51 0x33 3 0x0033 DIGIT THREE
52 0x34 4 0x0034 DIGIT FOUR
53 0x35 5 0x0035 DIGIT FIVE
54 0x36 6 0x0036 DIGIT SIX
55 0x37 7 0x0037 DIGIT SEVEN
56 0x38 8 0x0038 DIGIT EIGHT
57 0x39 9 0x0039 DIGIT NINE
58 0x3A : 0x003A COLON
59 0x3B ; 0x003B SEMICOLON
60 0x3C < 0x003C LESS-THAN SIGN
61 0x3D = 0x003D EQUALS SIGN
62 0x3E > 0x003E GREATER-THAN SIGN
63 0x3F ? 0x003F QUESTION MARK
64 0x40 @ 0x0040 COMMERCIAL AT
65 0x41 A 0x0041 LATIN CAPITAL LETTER A
66 0x42 B 0x0042 LATIN CAPITAL LETTER B
67 0x43 C 0x0043 LATIN CAPITAL LETTER C
68 0x44 D 0x0044 LATIN CAPITAL LETTER D
69 0x45 E 0x0045 LATIN CAPITAL LETTER E
70 0x46 F 0x0046 LATIN CAPITAL LETTER F
71 0x47 G 0x0047 LATIN CAPITAL LETTER G
72 0x48 H 0x0048 LATIN CAPITAL LETTER H
73 0x49 I 0x0049 LATIN CAPITAL LETTER I
74 0x4A J 0x004A LATIN CAPITAL LETTER J
75 0x4B K 0x004B LATIN CAPITAL LETTER K
76 0x4C L 0x004C LATIN CAPITAL LETTER L
77 0x4D M 0x004D LATIN CAPITAL LETTER M
78 0x4E N 0x004E LATIN CAPITAL LETTER N
79 0x4F O 0x004F LATIN CAPITAL LETTER O
80 0x50 P 0x0050 LATIN CAPITAL LETTER P
81 0x51 Q 0x0051 LATIN CAPITAL LETTER Q
82 0x52 R 0x0052 LATIN CAPITAL LETTER R
83 0x53 S 0x0053 LATIN CAPITAL LETTER S
84 0x54 T 0x0054 LATIN CAPITAL LETTER T
85 0x55 U 0x0055 LATIN CAPITAL LETTER U
86 0x56 V 0x0056 LATIN CAPITAL LETTER V
87 0x57 W 0x0057 LATIN CAPITAL LETTER W
88 0x58 X 0x0058 LATIN CAPITAL LETTER X
89 0x59 Y 0x0059 LATIN CAPITAL LETTER Y
90 0x5A Z 0x005A LATIN CAPITAL LETTER Z
91 0x5B [ 0x005B LEFT SQUARE BRACKET
92 0x5C \\ 0x005C REVERSE SOLIDUS
93 0x5D ] 0x005D RIGHT SQUARE BRACKET
94 0x5E ― 0x2015 HORIZONTAL BAR
95 0x5F _ 0x005F LOW LINE
96 0x60 ║ 0x2016 DOUBLE VERTICAL LINE
97 0x61 a 0x0061 LATIN SMALL LETTER A
98 0x62 b 0x0062 LATIN SMALL LETTER B
99 0x63 c 0x0063 LATIN SMALL LETTER C
100 0x64 d 0x0064 LATIN SMALL LETTER D
101 0x65 e 0x0065 LATIN SMALL LETTER E
102 0x66 f 0x0066 LATIN SMALL LETTER F
103 0x67 g 0x0067 LATIN SMALL LETTER G
104 0x68 h 0x0068 LATIN SMALL LETTER H
105 0x69 i 0x0069 LATIN SMALL LETTER I
106 0x6A j 0x006A LATIN SMALL LETTER J
107 0x6B k 0x006B LATIN SMALL LETTER K
108 0x6C l 0x006C LATIN SMALL LETTER L
109 0x6D m 0x006D LATIN SMALL LETTER M
110 0x6E n 0x006E LATIN SMALL LETTER N
111 0x6F o 0x006F LATIN SMALL LETTER O
112 0x70 p 0x0070 LATIN SMALL LETTER P
113 0x71 q 0x0071 LATIN SMALL LETTER Q
114 0x72 r 0x0072 LATIN SMALL LETTER R
115 0x73 s 0x0073 LATIN SMALL LETTER S
116 0x74 t 0x0074 LATIN SMALL LETTER T
117 0x75 u 0x0075 LATIN SMALL LETTER U
118 0x76 v 0x0076 LATIN SMALL LETTER V
119 0x77 w 0x0077 LATIN SMALL LETTER W
120 0x78 x 0x0078 LATIN SMALL LETTER X
121 0x79 y 0x0079 LATIN SMALL LETTER Y
122 0x7A z 0x007A LATIN SMALL LETTER Z
123 0x7B { 0x007B LEFT CURLY BRACKET
124 0x7C | 0x007C VERTICAL LINE
125 0x7D } 0x007D RIGHT CURLY BRACKET
126 0x7E ¯ 0x203E OVERLINE
128 0x80 á 0x00E1 LATIN SMALL LETTER A WITH ACUTE
129 0x81 à 0x00E0 LATIN SMALL LETTER A WITH GRAVE
130 0x82 é 0x00E9 LATIN SMALL LETTER E WITH ACUTE
131 0x83 è 0x00E8 LATIN SMALL LETTER E WITH GRAVE
132 0x84 í 0x00ED LATIN SMALL LETTER I WITH ACUTE
133 0x85 ì 0x00EC LATIN SMALL LETTER I WITH GRAVE
134 0x86 ó 0x00F3 LATIN SMALL LETTER O WITH ACUTE
135 0x87 ò 0x00F2 LATIN SMALL LETTER O WITH GRAVE
136 0x88 ú 0x00FA LATIN SMALL LETTER U WITH ACUTE
137 0x89 ù 0x00F9 LATIN SMALL LETTER U WITH GRAVE
138 0x8A Ñ 0x00D1 LATIN CAPITAL LETTER N WITH TILDE
139 0x8B Ç 0x00C7 LATIN CAPITAL LETTER C WITH CEDILLA
140 0x8C Ş 0x015E LATIN CAPITAL LETTER S WITH CEDILLA
141 0x8D ß 0x00DF LATIN SMALL LETTER SHARP S (German)
142 0x8E ¡ 0x00A1 INVERTED EXCLAMATION MARK
143 0x8F IJ 0x0132 LATIN CAPITAL LIGATURE IJ
144 0x90 â 0x00E2 LATIN SMALL LETTER A WITH CIRCUMFLEX
145 0x91 ä 0x00E4 LATIN SMALL LETTER A WITH DIAERESIS
146 0x92 ê 0x00EA LATIN SMALL LETTER E WITH CIRCUMFLEX
147 0x93 ë 0x00EB LATIN SMALL LETTER E WITH DIAERESIS
148 0x94 î 0x00EE LATIN SMALL LETTER I WITH CIRCUMFLEX
149 0x95 ï 0x00EF LATIN SMALL LETTER I WITH DIAERESIS
150 0x96 ô 0x00F4 LATIN SMALL LETTER O WITH CIRCUMFLEX
151 0x97 ö 0x00F6 LATIN SMALL LETTER O WITH DIAERESIS
152 0x98 û 0x00FB LATIN SMALL LETTER U WITH CIRCUMFLEX
153 0x99 ü 0x00FC LATIN SMALL LETTER U WITH DIAERESIS
154 0x9A ñ 0x00F1 LATIN SMALL LETTER N WITH TILDE
155 0x9B ç 0x00E7 LATIN SMALL LETTER C WITH CEDILLA
156 0x9C ş 0x015F LATIN SMALL LETTER S WITH CEDILLA
157 0x9D ğ 0x011F LATIN SMALL LETTER G WITH BREVE
158 0x9E ı 0x0131 LATIN SMALL LETTER DOTLESS I
159 0x9F ij 0x0133 LATIN SMALL LIGATURE IJ
160 0xA0 ª 0x00AA FEMININE ORDINAL INDICATOR
161 0xA1 α 0x03B1 GREEK SMALL LETTER ALPHA
162 0xA2 © 0x00A9 COPYRIGHT SIGN
163 0xA3 ‰ 0x2030 PER THOUSAND SIGN
164 0xA4 Ğ 0x011E LATIN CAPITAL LETTER G WITH BREVE
165 0xA5 ĕ 0x011B LATIN SMALL LETTER WITH CARON
166 0xA6 ň 0x0148 LATIN SMALL LETTER N WITH CARON
167 0xA7 ő 0x0151 LATIN SMALL LETTER O WITH DOUBLE ACUTE
168 0xA8 π 0x03C0 GREEK SMALL LETTER PI
169 0xA9 € 0x20AC EURO SIGN
170 0xAA ₤ 0x00A3 POUND SIGN
171 0xAB $ 0x0024 DOLLAR SIGN
172 0xAC ← 0x2190 LEFTWARDS ARROW
173 0xAD ↑ 0x2191 UPWARDS ARROW
174 0xAE → 0x2192 RIGHTWARDS ARROW
175 0xAF ↓ 0x2193 DOWNWARDS ARROW
176 0xB0 º 0x00BA MASCULIN ORDINAL INDICATOR
177 0xB1 ¹ 0x00B9 SUPERSCRIPT ONE
178 0xB2 ² 0x00B2 SUPERSCRIPT TWO
179 0xB3 ³ 0x00B3 SUPERSCRIPT THREE
180 0xB4 ± 0x00B1 PLUS-MINUS SIGN
181 0xB5 İ 0x0130 LATIN CAPITAL LETTER I WITH DOT ABOVE
182 0xB6 ń 0x0144 LATIN SMALL LETTER N WITH ACUTE
183 0xB7 ű 0x0171 LATIN SMALL LETTER U WITH DOUBLE ACUTE
184 0xB8 µ 0x00B5 MIKRO SIGN
185 0xB9 ¿ 0x00BF INVERTED QUESTION MARK
186 0xBA ÷ 0x00F7 DIVISION SIGN
187 0xBB º 0x00B0 DEGREE SIGN
188 0xBC ¼ 0x00BC VULGAR FRACTION ONE QUARTER
189 0xBD ½ 0x00BD VULGAR FRACTION ONE HALF
190 0xBE ¾ 0x00BE VULGAR FRACTION THREE QUARTERS
191 0xBF § 0x00A7 SECTION SIGN
192 0xC0 Á 0x00C1 LATIN CAPITAL LETTER A WITH ACUTE
193 0xC1 À 0x00C0 LATIN CAPITAL LETTER A WITH GRAVE
194 0xC2 É 0x00C9 LATIN CAPITAL LETTER E WITH ACUTE
195 0xC3 È 0x00C8 LATIN CAPITAL LETTER E WITH GRAVE
196 0xC4 Í 0x00CD LATIN CAPITAL LETTER I WITH ACUTE
197 0xC5 Ì 0x00CC LATIN CAPITAL LETTER I WITH GRAVE
198 0xC6 Ó 0x00D3 LATIN CAPITAL LETTER O WITH ACUTE
199 0xC7 Ò 0x00D2 LATIN CAPITAL LETTER O WITH GRAVE
200 0xC8 Ú 0x00DA LATIN CAPITAL LETTER U WITH ACUTE
201 0xC9 Ù 0x00D9 LATIN CAPITAL LETTER U WITH GRAVE
202 0xCA Ř 0x0158 LATIN CAPITAL LETTER R WITH CARON
203 0xCB Č 0x010C LATIN CAPITAL LETTER C WITH CARON
204 0xCC Š 0x0160 LATIN CAPITAL LETTER S WITH CARON
205 0xCD Ž 0x017D LATIN CAPITAL LETTER Z WITH CARON
206 0xCE Ð 0x00D0 LATIN CAPITAL LETTER ETH
207 0xCF Ŀ 0x013F LATIN CAPITAL LETTER L WITH MIDDLE DOT
208 0xD0 Â 0x00C2 LATIN CAPITAL LETTER A WITH CIRCUMFLEX
209 0xD1 Ä 0x00C4 LATIN CAPITAL LETTER A WITH DIAERESIS
210 0xD2 Ê 0x00CA LATIN CAPITAL LETTER E WITH CIRCUMFLEX
211 0xD3 Ë 0x00CB LATIN CAPITAL LETTER A WITH DIAERESIS
212 0xD4 Î 0x00CE LATIN CAPITAL LETTER I WITH CIRCUMFLEX
213 0xD5 Ï 0x00CF LATIN CAPITAL LETTER I WITH DIAERESIS
214 0xD6 Ô 0x00D4 LATIN CAPITAL LETTER O WITH CIRCUMFLEX
215 0xD7 Ö 0x00D6 LATIN CAPITAL LETTER O WITH DIAERESIS
216 0xD8 Û 0x00DB LATIN CAPITAL LETTER U WITH CIRCUMFLEX
217 0xD9 Ü 0x00DC LATIN CAPITAL LETTER U WITH DIAERESIS
218 0xDA ř 0x0159 LATIN SMALL LETTER R WITH CARON
219 0xDB č 0x010D LATIN SMALL LETTER C WITH CARON
220 0xDC š 0x0161 LATIN SMALL LETTER S WITH CARON
221 0xDD ž 0x017E LATIN SMALL LETTER Z WITH CARON
222 0xDE đ 0x0111 LATIN SMALL LETTER D WITH STROKE
223 0xDF ŀ 0x0140 LATIN SMALL LETTER L WITH MIDDLE DOT
224 0xE0 Ã 0x00C3 LATIN CAPITAL LETTER A WITH TILDE
225 0xE1 Å 0x00C5 LATIN CAPITAL LETTER A WITH RING ABOVE
226 0xE2 Æ 0x00C6 LATIN CAPITAL LETTER AE
227 0xE3 Π0x0152 LATIN CAPITAL LIGATURE OE
228 0xE4 ŷ 0x0177 LATIN SMALL LETTER Y WITH CIRCUMFLEX
229 0xE5 Ý 0x00DD LATIN CAPITAL LETTER Y WITH ACUTE
230 0xE6 Õ 0x00D5 LATIN CAPITAL LETTER O WITH TILDE
231 0xE7 Ø 0x00D8 LATIN CAPITAL LETTER O WITH STROKE
232 0xE8 Þ 0x00DE LATIN CAPITAL LETTER THORN
233 0xE9 Ŋ 0x014A LATIN CAPITAL LETTER ENG
234 0xEA Ŕ 0x0154 LATIN CAPITAL LETTER R WITH ACUTE
235 0xEB Ć 0x0106 LATIN SMALL LETTER C WITH ACUTE
236 0xEC Ś 0x015A LATIN CAPITAL LETTER S WITH ACUTE
237 0xED Ź 0x0179 LATIN CAPITAL LETTER Z WITH ACUTE
238 0xEE Ŧ 0x0166 LATIN CAPITAL LETTER T WITH STROKE
239 0xEF ð 0x00F0 LATIN SMALL LETTER ETH
240 0xF0 ã 0x00E3 LATIN SMALL LETTER A WITH TILDE
241 0xF1 å 0x00E5 LATIN SMALL LETTER A WITH RING
242 0xF2 æ 0x00E6 LATIN SMALL LETTER AE
243 0xF3 œ 0x0153
244 0xF4 ŵ 0x0175
245 0xF5 ý 0x00FD
246 0xF6 õ 0x00F5
247 0xF7 ø 0x00F8
248 0xF8 þ 0x00FE
249 0xF9 ŋ 0x014B
250 0xFA ŕ 0x0155
251 0xFB ć 0x0107
252 0xFC ś 0x015B
253 0xFD ź 0x017A
254 0xFE ŧ 0x0167
"""
for line in data.splitlines():
parts = line.split()
num, rds_code, symbol, ucs2, *_ = parts
if int(rds_code, 16) != int(ucs2, 16):
print(f"charset[{rds_code}] = {ucs2} # {symbol}")
src/lib.c
+14 -11
View File
@@ -81,6 +81,8 @@ char *convert_to_rdscharset(const char *str) {
uint8_t i = 0; uint8_t i = 0;
while (*str != 0 && i < 255) { while (*str != 0 && i < 255) {
// The following line is neccesary for the charset.py to work properly
// CHARSET START
switch(*str) { switch(*str) {
case (char)0xc2: case (char)0xc2:
str++; str++;
@@ -97,7 +99,7 @@ char *convert_to_rdscharset(const char *str) {
case (char)0xbf: new_str[i] = (char)0xb9; break; // INVERTED QUESTION MARK case (char)0xbf: new_str[i] = (char)0xb9; break; // INVERTED QUESTION MARK
case (char)0xb0: new_str[i] = (char)0xbb; break; // DEGREE SIGN case (char)0xb0: new_str[i] = (char)0xbb; break; // DEGREE SIGN
case (char)0xa7: new_str[i] = (char)0xbf; break; // SECTION SIGN case (char)0xa7: new_str[i] = (char)0xbf; break; // SECTION SIGN
default: new_str[i] = *str; break; default: new_str[i] = (char)0x3f; break; // QUESTION MARK
} }
break; break;
case (char)0xe2: case (char)0xe2:
@@ -110,14 +112,14 @@ char *convert_to_rdscharset(const char *str) {
case (char)0x96: new_str[i] = (char)0x60; break; // DOUBLE VERTICAL LINE case (char)0x96: new_str[i] = (char)0x60; break; // DOUBLE VERTICAL LINE
case (char)0xbe: new_str[i] = (char)0x7e; break; // OVERLINE case (char)0xbe: new_str[i] = (char)0x7e; break; // OVERLINE
case (char)0xb0: new_str[i] = (char)0xa3; break; // PER MILLE SIGN case (char)0xb0: new_str[i] = (char)0xa3; break; // PER MILLE SIGN
default: new_str[i] = *str; break; default: new_str[i] = (char)0x3f; break; // QUESTION MARK
} }
break; break;
case (char)0x82: case (char)0x82:
str++; str++;
switch(*str) { switch(*str) {
case (char)0xac: new_str[i] = (char)0xa9; break; // EURO SIGN case (char)0xac: new_str[i] = (char)0xa9; break; // EURO SIGN
default: new_str[i] = *str; break; default: new_str[i] = (char)0x3f; break; // QUESTION MARK
} }
break; break;
case (char)0x86: case (char)0x86:
@@ -127,10 +129,10 @@ char *convert_to_rdscharset(const char *str) {
case (char)0x91: new_str[i] = (char)0xad; break; // UPWARDS ARROW case (char)0x91: new_str[i] = (char)0xad; break; // UPWARDS ARROW
case (char)0x92: new_str[i] = (char)0xae; break; // RIGHTWARDS ARROW case (char)0x92: new_str[i] = (char)0xae; break; // RIGHTWARDS ARROW
case (char)0x93: new_str[i] = (char)0xaf; break; // DOWNWARDS ARROW case (char)0x93: new_str[i] = (char)0xaf; break; // DOWNWARDS ARROW
default: new_str[i] = *str; break; default: new_str[i] = (char)0x3f; break; // QUESTION MARK
} }
break; break;
default: new_str[i] = *str; break; default: new_str[i] = (char)0x3f; break; // QUESTION MARK
} }
break; break;
case (char)0xc3: case (char)0xc3:
@@ -198,7 +200,7 @@ char *convert_to_rdscharset(const char *str) {
case (char)0xb5: new_str[i] = (char)0xf6; break; // LATIN SMALL LETTER O WITH TILDE case (char)0xb5: new_str[i] = (char)0xf6; break; // LATIN SMALL LETTER O WITH TILDE
case (char)0xb8: new_str[i] = (char)0xf7; break; // LATIN SMALL LETTER O WITH STROKE case (char)0xb8: new_str[i] = (char)0xf7; break; // LATIN SMALL LETTER O WITH STROKE
case (char)0xbe: new_str[i] = (char)0xf8; break; // LATIN SMALL LETTER THORN case (char)0xbe: new_str[i] = (char)0xf8; break; // LATIN SMALL LETTER THORN
default: new_str[i] = *str; break; default: new_str[i] = (char)0x3f; break; // QUESTION MARK
} }
break; break;
case (char)0xc5: case (char)0xc5:
@@ -231,7 +233,7 @@ char *convert_to_rdscharset(const char *str) {
case (char)0x9b: new_str[i] = (char)0xfc; break; // LATIN SMALL LETTER S WITH ACUTE case (char)0x9b: new_str[i] = (char)0xfc; break; // LATIN SMALL LETTER S WITH ACUTE
case (char)0xba: new_str[i] = (char)0xfd; break; // LATIN SMALL LETTER Z WITH ACUTE case (char)0xba: new_str[i] = (char)0xfd; break; // LATIN SMALL LETTER Z WITH ACUTE
case (char)0xa7: new_str[i] = (char)0xfe; break; // LATIN SMALL LETTER T WITH STROKE case (char)0xa7: new_str[i] = (char)0xfe; break; // LATIN SMALL LETTER T WITH STROKE
default: new_str[i] = *str; break; default: new_str[i] = (char)0x3f; break; // QUESTION MARK
} }
break; break;
case (char)0xc4: case (char)0xc4:
@@ -250,26 +252,27 @@ char *convert_to_rdscharset(const char *str) {
case (char)0x91: new_str[i] = (char)0xde; break; // LATIN SMALL LETTER D WITH STROKE case (char)0x91: new_str[i] = (char)0xde; break; // LATIN SMALL LETTER D WITH STROKE
case (char)0x86: new_str[i] = (char)0xeb; break; // LATIN CAPITAL LETTER C WITH ACUTE case (char)0x86: new_str[i] = (char)0xeb; break; // LATIN CAPITAL LETTER C WITH ACUTE
case (char)0x87: new_str[i] = (char)0xfb; break; // LATIN SMALL LETTER C WITH ACUTE case (char)0x87: new_str[i] = (char)0xfb; break; // LATIN SMALL LETTER C WITH ACUTE
default: new_str[i] = *str; break; default: new_str[i] = (char)0x3f; break; // QUESTION MARK
} }
break; break;
case (char)0xce: case (char)0xce:
str++; str++;
switch(*str) { switch(*str) {
case (char)0xb1: new_str[i] = (char)0xa1; break; // GREEK SMALL LETTER ALPHA case (char)0xb1: new_str[i] = (char)0xa1; break; // GREEK SMALL LETTER ALPHA
default: new_str[i] = *str; break; default: new_str[i] = (char)0x3f; break; // QUESTION MARK
} }
break; break;
case (char)0xcf: case (char)0xcf:
str++; str++;
switch(*str) { switch(*str) {
case (char)0x80: new_str[i] = (char)0xa8; break; // GREEK SMALL LETTER PI case (char)0x80: new_str[i] = (char)0xa8; break; // GREEK SMALL LETTER PI
default: new_str[i] = *str; break; default: new_str[i] = (char)0x3f; break; // QUESTION MARK
} }
break; break;
case (char)0x24: new_str[i] = (char)0xab; break; // DOLLAR SIGN case (char)0x24: new_str[i] = (char)0xab; break; // DOLLAR SIGN
default: new_str[i] = *str; break; default: new_str[i] = *str; break;
} }
// CHARSET END
i++; i++;
str++; str++;
@@ -277,4 +280,4 @@ char *convert_to_rdscharset(const char *str) {
new_str[i] = 0; new_str[i] = 0;
return new_str; return new_str;
} }