4 #include <lib/base/elock.h>
5 #include <lib/base/eerror.h>
6 #include <lib/base/estring.h>
8 static pthread_mutex_t lock=PTHREAD_ADAPTIVE_MUTEX_INITIALIZER_NP;
10 std::string getNum(int val, int sys)
12 // Returns a string that contain the value val as string
13 // if sys == 16 than hexadezimal if sys == 10 than decimal
17 std::snprintf(buf, 12, "%i", val);
19 std::snprintf(buf, 12, "%X", val);
26 // 8859-x to ucs coding tables. taken from www.unicode.org/Public/MAPPINGS/ISO8859/
27 static unsigned long c88595[128]={
28 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f,
29 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f,
30 0x00a0, 0x0401, 0x0402, 0x0403, 0x0404, 0x0405, 0x0406, 0x0407, 0x0408, 0x0409, 0x040a, 0x040b, 0x040c, 0x00ad, 0x040e, 0x040f,
31 0x0410, 0x0411, 0x0412, 0x0413, 0x0414, 0x0415, 0x0416, 0x0417, 0x0418, 0x0419, 0x041a, 0x041b, 0x041c, 0x041d, 0x041e, 0x041f,
32 0x0420, 0x0421, 0x0422, 0x0423, 0x0424, 0x0425, 0x0426, 0x0427, 0x0428, 0x0429, 0x042a, 0x042b, 0x042c, 0x042d, 0x042e, 0x042f,
33 0x0430, 0x0431, 0x0432, 0x0433, 0x0434, 0x0435, 0x0436, 0x0437, 0x0438, 0x0439, 0x043a, 0x043b, 0x043c, 0x043d, 0x043e, 0x043f,
34 0x0440, 0x0441, 0x0442, 0x0443, 0x0444, 0x0445, 0x0446, 0x0447, 0x0448, 0x0449, 0x044a, 0x044b, 0x044c, 0x044d, 0x044e, 0x044f,
35 0x2116, 0x0451, 0x0452, 0x0453, 0x0454, 0x0455, 0x0456, 0x0457, 0x0458, 0x0459, 0x045a, 0x045b, 0x045c, 0x00a7, 0x045e, 0x045f};
37 static unsigned long c88596[128]={
38 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f,
39 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f,
40 0x00a0, 0x0000, 0x0000, 0x0000, 0x00a4, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x060c, 0x00ad, 0x0000, 0x0000,
41 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x061b, 0x0000, 0x0000, 0x0000, 0x061f,
42 0x0000, 0x0621, 0x0622, 0x0623, 0x0624, 0x0625, 0x0626, 0x0627, 0x0628, 0x0629, 0x062a, 0x062b, 0x062c, 0x062d, 0x062e, 0x062f,
43 0x0630, 0x0631, 0x0632, 0x0633, 0x0634, 0x0635, 0x0636, 0x0637, 0x0638, 0x0639, 0x063a, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
44 0x0640, 0x0641, 0x0642, 0x0643, 0x0644, 0x0645, 0x0646, 0x0647, 0x0648, 0x0649, 0x064a, 0x064b, 0x064c, 0x064d, 0x064e, 0x064f,
45 0x0650, 0x0651, 0x0652, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000};
47 static unsigned long c88597[128]={
48 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f,
49 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f,
50 0x00a0, 0x2018, 0x2019, 0x00a3, 0x0000, 0x0000, 0x00a6, 0x00a7, 0x00a8, 0x00a9, 0x0000, 0x00ab, 0x00ac, 0x00ad, 0x0000, 0x2015,
51 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x0384, 0x0385, 0x0386, 0x00b7, 0x0388, 0x0389, 0x038a, 0x00bb, 0x038c, 0x00bd, 0x038e, 0x038f,
52 0x0390, 0x0391, 0x0392, 0x0393, 0x0394, 0x0395, 0x0396, 0x0397, 0x0398, 0x0399, 0x039a, 0x039b, 0x039c, 0x039d, 0x039e, 0x039f,
53 0x03a0, 0x03a1, 0x0000, 0x03a3, 0x03a4, 0x03a5, 0x03a6, 0x03a7, 0x03a8, 0x03a9, 0x03aa, 0x03ab, 0x03ac, 0x03ad, 0x03ae, 0x03af,
54 0x03b0, 0x03b1, 0x03b2, 0x03b3, 0x03b4, 0x03b5, 0x03b6, 0x03b7, 0x03b8, 0x03b9, 0x03ba, 0x03bb, 0x03bc, 0x03bd, 0x03be, 0x03bf,
55 0x03c0, 0x03c1, 0x03c2, 0x03c3, 0x03c4, 0x03c5, 0x03c6, 0x03c7, 0x03c8, 0x03c9, 0x03ca, 0x03cb, 0x03cc, 0x03cd, 0x03ce, 0x0000};
57 static unsigned long c88598[128]={
58 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f,
59 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f,
60 0x00a0, 0x0000, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 0x00a7, 0x00a8, 0x00a9, 0x00d7, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af,
61 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7, 0x00b8, 0x00b9, 0x00f7, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x0000,
62 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
63 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x2017,
64 0x05d0, 0x05d1, 0x05d2, 0x05d3, 0x05d4, 0x05d5, 0x05d6, 0x05d7, 0x05d8, 0x05d9, 0x05da, 0x05db, 0x05dc, 0x05dd, 0x05de, 0x05df,
65 0x05e0, 0x05e1, 0x05e2, 0x05e3, 0x05e4, 0x05e5, 0x05e6, 0x05e7, 0x05e8, 0x05e9, 0x05ea, 0x0000, 0x0000, 0x200e, 0x200f, 0x0000};
67 static unsigned long c88599[128]={
68 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f,
69 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f,
70 0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 0x00a7, 0x00a8, 0x00a9, 0x00aa, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af,
71 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7, 0x00b8, 0x00b9, 0x00ba, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf,
72 0x00c0, 0x00c1, 0x00c2, 0x00c3, 0x00c4, 0x00c5, 0x00c6, 0x00c7, 0x00c8, 0x00c9, 0x00ca, 0x00cb, 0x00cc, 0x00cd, 0x00ce, 0x00cf,
73 0x011e, 0x00d1, 0x00d2, 0x00d3, 0x00d4, 0x00d5, 0x00d6, 0x00d7, 0x00d8, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x0130, 0x015e, 0x00df,
74 0x00e0, 0x00e1, 0x00e2, 0x00e3, 0x00e4, 0x00e5, 0x00e6, 0x00e7, 0x00e8, 0x00e9, 0x00ea, 0x00eb, 0x00ec, 0x00ed, 0x00ee, 0x00ef,
75 0x011f, 0x00f1, 0x00f2, 0x00f3, 0x00f4, 0x00f5, 0x00f6, 0x00f7, 0x00f8, 0x00f9, 0x00fa, 0x00fb, 0x00fc, 0x0131, 0x015f, 0x00ff};
77 // UPC Direct / HBO strange two-character encoding. 0xC2 means acute, 0xC8 doule 'dot', 0xCA small 'circle', 0xCD double 'acute', 0xCF acute.
78 // many thanks to the czechs who helped me while solving this.
79 static inline unsigned int doCzech(int c1, int c2)
86 case 'A': return 0x00C1;
87 case 'a': return 0x00E1;
88 case 'E': return 0x00C9;
89 case 'e': return 0x00E9;
90 case 'I': return 0x00CD;
91 case 'i': return 0x00ED;
92 case 'O': return 0x00D3;
93 case 'o': return 0x00F3; // corrected, was 0x00E3
94 case 'U': return 0x00DA;
95 case 'u': return 0x00FA;
96 case 'Y': return 0x00DD;
97 case 'y': return 0x00FD;
101 case 0xC8: // double 'dot'
104 case 'A': return 0x00C4;
105 case 'a': return 0x00E4;
106 case 'E': return 0x00CB;
107 case 'e': return 0x00EB;
108 case 'O': return 0x00D6;
109 case 'o': return 0x00F6;
110 case 'U': return 0x00DC;
111 case 'u': return 0x00FC;
115 case 0xCA: // small 'circle'
118 case 'U': return 0x016E;
119 case 'u': return 0x016F;
123 case 0xCD: // double 'acute'
126 case 'O': return 0x0150;
127 case 'o': return 0x0151;
128 case 'U': return 0x0170;
129 case 'u': return 0x0171;
136 case 'C': return 0x010C;
137 case 'c': return 0x010D;
138 case 'D': return 0x010E;
139 case 'd': return 0x010F;
140 case 'E': return 0x011A;
141 case 'e': return 0x011B;
142 case 'L': return 0x013D; // not sure if they really exist.
143 case 'l': return 0x013E;
144 case 'N': return 0x0147;
145 case 'n': return 0x0148;
146 case 'R': return 0x0158;
147 case 'r': return 0x0159;
148 case 'S': return 0x0160;
149 case 's': return 0x0161;
150 case 'T': return 0x0164;
151 case 't': return 0x0165;
152 case 'Z': return 0x017D;
153 case 'z': return 0x017E;
162 static inline unsigned int recode(unsigned char d, int cp)
168 case 0: // 8859-1 Latin1 <-> unicode mapping
170 case 1: // 8859-5 -> unicode mapping
171 return c88595[d-0x80];
172 case 2: // 8859-6 -> unicode mapping
173 return c88596[d-0x80];
174 case 3: // 8859-7 -> unicode mapping
175 return c88597[d-0x80];
176 case 4: // 8859-8 -> unicode mapping
177 return c88598[d-0x80];
178 case 5: // 8859-9 -> unicode mapping
179 return c88599[d-0x80];
185 std::string convertDVBUTF8(const std::string &s, int table)
187 return convertDVBUTF8((const unsigned char*)s.c_str(), s.size(), table);
190 std::string convertDVBUTF8(const unsigned char *data, int len, int table)
199 if ((data[0] >= 0x10) && (data[0] <= 0x12))
200 return "<unsupported encoding>";
202 int bytesneeded=0, t=0, s=i;
206 unsigned long code=0;
207 if ((table == 5) && ((data[i] == 0xC2) || (data[i] == 0xC8) || (data[i] == 0xCA) || (data[i] == 0xCD) || (data[i] == 0xCF)) && (i+1 < len))
208 // braindead czech encoding...
209 if ((code=doCzech(data[i], data[i+1])))
212 code=recode(data[i], table);
226 unsigned char res[bytesneeded];
230 unsigned long code=0;
231 if ((table == 5) && ((data[i] == 0xC2) || (data[i] == 0xC8) || (data[i] == 0xCA) || (data[i] == 0xCD) || (data[i] == 0xCF)) && (i+1 < len))
232 // braindead czech encoding...
233 if ((code=doCzech(data[i], data[i+1])))
236 code=recode(data[i++], table);
239 // Unicode->UTF8 encoding
240 if (code < 0x80) // identity ascii <-> utf8 mapping
242 else if (code < 0x800) // two byte mapping
244 res[t++]=(code>>6)|0xC0;
245 res[t++]=(code&0x3F)|0x80;
246 } else if (code < 0x10000) // three bytes mapping
248 res[t++]=(code>>12)|0xE0;
249 res[t++]=((code>>6)&0x3F)|0x80;
250 res[t++]=(code&0x3F)|0x80;
253 res[t++]=(code>>18)|0xF0;
254 res[t++]=((code>>12)&0x3F)|0x80;
255 res[t++]=((code>>6)&0x3F)|0x80;
256 res[t++]=(code&0x3F)|0x80;
259 if ( t != bytesneeded)
260 eFatal("t: %d, bytesneeded: %d", t, bytesneeded);
261 return std::string().assign((char*)res, t);
264 std::string convertUTF8DVB(const std::string &string)
266 std::string ss=std::string();
268 int len=string.length();
269 for(int i=0;i<len;i++){
270 unsigned char c1=string[i];
276 unsigned char c2=string[i];
277 c=((c1&0x3F)<<6) + (c2&0x3F);
280 // now search it in table
282 for(unsigned int j=0;j<128;j++){
283 if(c88599[j]==c){ // now only 8859-9 ....
295 std::string convertLatin1UTF8(const std::string &string)
297 unsigned int bytesneeded=0, t=0, i;
299 unsigned int len=string.size();
301 for (i=0; i<len; ++i)
303 unsigned long code=string[i];
317 unsigned char res[bytesneeded];
321 unsigned long code=string[i++];
322 // Unicode->UTF8 encoding
323 if (code < 0x80) // identity latin <-> utf8 mapping
325 else if (code < 0x800) // two byte mapping
327 res[t++]=(code>>6)|0xC0;
328 res[t++]=(code&0x3F)|0x80;
329 } else if (code < 0x10000) // three bytes mapping
331 res[t++]=(code>>12)|0xE0;
332 res[t++]=((code>>6)&0x3F)|0x80;
333 res[t++]=(code&0x3F)|0x80;
336 res[t++]=(code>>18)|0xF0;
337 res[t++]=((code>>12)&0x3F)|0x80;
338 res[t++]=((code>>6)&0x3F)|0x80;
339 res[t++]=(code&0x3F)|0x80;
342 if ( t != bytesneeded)
343 eFatal("t: %d, bytesneeded: %d", t, bytesneeded);
344 return std::string().assign((char*)res, t);
347 int isUTF8(const std::string &string)
349 unsigned int len=string.size();
351 for (unsigned int i=0; i < len; ++i)
353 if (!(string[i]&0x80)) // normal ASCII
355 if ((string[i] & 0xE0) == 0xC0) // one char following.
357 // first, length check:
359 return 0; // certainly NOT utf-8
361 if ((string[i]&0xC0) != 0x80)
362 return 0; // no, not UTF-8.
363 } else if ((string[i] & 0xF0) == 0xE0)
368 if ((string[i]&0xC0) != 0x80)
371 if ((string[i]&0xC0) != 0x80)
375 return 1; // can be UTF8 (or pure ASCII, at least no non-UTF-8 8bit characters)
378 std::string removeDVBChars(const std::string &s)
382 int len = s.length();
384 for(int i = 0; i < len-1; i++)
386 unsigned char c1 = s[i];
389 /* UTF8? decode (but only simple) */
392 unsigned char c2 = s[i + 1];
393 c = ((c1&0x3F)<<6) + (c2&0x3F);
394 if ((c >= 0x80) && (c <= 0x9F))
396 ++i; /* skip 2nd utf8 char */
407 void makeUpper(std::string &s)
409 std::transform(s.begin(), s.end(), s.begin(), (int(*)(int)) toupper);