roo_io
API Documentation for roo_io
Loading...
Searching...
No Matches
u8c.cpp
Go to the documentation of this file.
1/*
2** (C) by Remo Dentato (rdentato@gmail.com)
3**
4** This software is distributed under the terms of the MIT license:
5** https://opensource.org/licenses/MIT
6**
7*/
8#include <stdio.h>
9#include <string.h>
10#include <stdint.h>
11#include "u8c.h"
12
13#define fsm goto fsm_state_START;
14#define fsmGOTO(x) goto fsm_state_##x
15#define fsmSTATE(x) fsm_state_##x :
16
17// Returns the length of the next UTF8 character and stores in ch
18// (if it's not null) the corresponding codepoint.
19// It is based on a work by Bjoern Hoehrmann:
20// http://bjoern.hoehrmann.de/utf-8/decoder/dfa
21// but it's faster and has been extended to include C0 80 as the
22// encoding for U+0000
23
24/* This is the FSM in dot vizgraph format:
25
26digraph finite_state_machine {
27 rankdir=LR;
28 node [style = dashed]; LEN3; LEN4;
29 node [style = solid];
30 node [shape = ellipse]; START ;
31 node [shape = ellipse];
32
33 START -> END [ label = "00..00 / len=0" ];
34 START -> END [ label = "01..7F / len=1" ];
35 START -> NULL [ label = "C0..C0 / len=2" ];
36
37 START -> LEN2_0 [ label = "C2..DF / len=2" ];
38
39 START -> LEN3_0 [ label = "E0..E0 / len=3" ];
40 START -> LEN3_1 [ label = "E1..EC,EE..EF / len=3" ];
41 START -> LEN3_2 [ label = "ED..ED / len=3" ];
42
43 START -> LEN4_0 [ label = "F0..F0 / len=4" ];
44 START -> LEN4_1 [ label = "F1..F3 / len=4" ];
45 START -> LEN4_2 [ label = "F4..F4 / len=4" ];
46
47 NULL -> END [label = "80..80" ];
48
49 LEN2_0 -> END [ label = "80..BF" ];
50
51 LEN3_0 -> LEN3 [ label = "A0..BF" ];
52 LEN3_1 -> LEN3 [ label = "80..BF" ];
53 LEN3_2 -> LEN3 [ label = "80..9F" ];
54 LEN3 -> LEN2_0 [style=dashed ];
55
56 LEN4_0 -> LEN4 [ label = "90..BF" ];
57 LEN4_1 -> LEN4 [ label = "80..BF" ];
58 LEN4_2 -> LEN4 [ label = "80..8F" ];
59
60 LEN4 -> LEN3_1 [style=dashed ];
61 }
62 */
63
64namespace u8c {
65
66size_t u8next_(const char *start, const char* end, char32_t &val)
67{
68 size_t len = 0;
69 const unsigned char *s = (const unsigned char *)start;
70 const unsigned char *e = (const unsigned char *)end;
71 if (s == e) return 0;
72 char first = *s;
73
74 val = first;
75 fsm {
76 fsmSTATE(START) {
77 if (*s < 0x80) { len = 1; fsmGOTO(end); }
78 // if (*s == 0xC0) { len = 2; fsmGOTO(null); }
79 if (*s <= 0xC1) { fsmGOTO(invalid); }
80 if (*s <= 0xDF) { val &= 0x1F; len = 2; fsmGOTO(len2_0); }
81 if (*s == 0xE0) { val &= 0x0F; len = 3; fsmGOTO(len3_0); }
82 if (*s <= 0xEC) { val &= 0x0F; len = 3; fsmGOTO(len3_1); }
83 if (*s == 0xED) { val &= 0x0F; len = 3; fsmGOTO(len3_2); }
84 if (*s <= 0xEF) { val &= 0x0F; len = 3; fsmGOTO(len3_1); }
85 if (*s == 0xF0) { val &= 0x07; len = 4; fsmGOTO(len4_0); }
86 if (*s <= 0xF3) { val &= 0x07; len = 4; fsmGOTO(len4_1); }
87 if (*s == 0xF4) { val &= 0x07; len = 4; fsmGOTO(len4_2); }
88 fsmGOTO(invalid);
89 }
90
91 // fsmSTATE(null) { // Modified UTF-8 encodes NULL (U+0000) to C0 80
92 // val = 0;
93 // s++; if (s == e || *s != 0x80) fsmGOTO(invalid);
94 // fsmGOTO(end);
95 // }
96
97 fsmSTATE(len4_0) {
98 s++; if (s == e || *s < 0x90 || 0xBF < *s) fsmGOTO(invalid);
99 fsmGOTO(len4);
100 }
101
102 fsmSTATE(len4_1) {
103 s++; if (s == e || *s < 0x80 || 0xBF < *s) fsmGOTO(invalid);
104 fsmGOTO(len4);
105 }
106
107 fsmSTATE(len4_2) {
108 s++; if (s == e || *s < 0x80 || 0x8F < *s) fsmGOTO(invalid);
109 fsmGOTO(len4);
110 }
111
112 fsmSTATE(len4) {
113 val = (val << 6) | (*s & 0x3F);
114 fsmGOTO(len3_1);
115 }
116
117 fsmSTATE(len3_0) {
118 s++; if (s == e || *s < 0xA0 || 0xBF < *s) fsmGOTO(invalid);
119 fsmGOTO(len3);
120 }
121
122 fsmSTATE(len3_1) {
123 s++; if (s == e || *s < 0x80 || 0xBF < *s) fsmGOTO(invalid);
124 fsmGOTO(len3);
125 }
126
127 fsmSTATE(len3_2) {
128 s++; if (s == e || *s < 0x80 || 0x9F < *s) fsmGOTO(invalid);
129 fsmGOTO(len3);
130 }
131
132 fsmSTATE(len3) {
133 val = (val << 6) | (*s & 0x3F);
134 fsmGOTO(len2_0);
135 }
136
137 fsmSTATE(len2_0) {
138 s++; if (s == e || *s < 0x80 || 0xBF < *s) fsmGOTO(invalid);
139 val = (val << 6) | (*s & 0x3F);
140 fsmGOTO(end);
141 }
142
143 // Try rewinding one byte, but consume at least one.
144 fsmSTATE(invalid) {
145 size_t adv = s - (const unsigned char*)start;
146 len = (adv <= 1 ? 1 : adv);
147 val = 0xFFFD;
148 }
149
150 fsmSTATE(end) { }
151 }
152 return len;
153}
154
155/* ACTUALLY NOT FASTER!!! DO NOT USE! */
156int u8next_FAST(const char *txt, int *ch)
157{
158 int len = 0;
159 unsigned char *s = (unsigned char *)txt;
160 unsigned char first = *s;
161 int val = 0;
162
163 if (first) {
164 val = first;
165 if (first > 0x7F) {
166 val = *++s & 0x3F;
167 if ((first & 0xF8) == 0xF0) { val |= (first & 0x07)<<6; goto L4;}
168 else if ((first & 0xF0) == 0xE0) { val |= (first & 0x0F)<<6; goto L3;}
169 else { val |= (first & 0x1F)<<6; goto L2;}
170
171 L4: val <<= 6; if (*s) s++; val |= (*s & 0x3F);
172 L3: val <<= 6; if (*s) s++; val |= (*s & 0x3F);
173 L2: ;
174 }
175 len = 1+(s-(unsigned char *)txt);
176 }
177
178 if (ch) *ch = val;
179 return len;
180}
181
182// NOTE(dejwk): it may count differently than u8next_ in case of malformed input.
183// size_t u8strlen(const char *s)
184// {
185// size_t len=0;
186// while (*s) {
187// if ((*s & 0xC0) != 0x80) len++ ;
188// s++;
189// }
190// return len;
191// }
192
193// int u8encode_(int ch, char *s)
194// {
195// int len = -1;
196// char t[8];
197// if (s == NULL) s = t;
198// if (ch == 0) {
199// len=2;
200// *s++ = 0xC0;
201// *s++ = 0x80;
202// }
203// else if (ch < 0x80) {
204// len = 1;
205// *s++ = ch;
206// }
207// else if (ch < 0x0800) {
208// len = 2;
209// *s++ = 0xC0 | (ch >> 6);
210// *s++ = 0x80 | (ch & 0x3F);
211// }
212// else if (ch < 0x10000) {
213// len = 3;
214// *s++ = 0xE0 | (ch >> 12);
215// *s++ = 0x80 | ((ch >> 6 ) & 0x3F);
216// *s++ = 0x80 | (ch & 0x3F);
217// } else if (ch < 0x110000) {
218// len = 4;
219// *s++ = 0xF0 | (ch >> 18);
220// *s++ = 0x80 | ((ch >> 12) & 0x3F);
221// *s++ = 0x80 | ((ch >> 6 ) & 0x3F);
222// *s++ = 0x80 | (ch & 0x3F);
223// }
224// *s = '\0';
225// return len;
226// }
227
228// char *u8strncpy(char *dest, const char *src, size_t n)
229// {
230// int k = n-1;
231// int i;
232// if (n) {
233// dest[k] = 0;
234// strncpy(dest,src,n);
235// if (dest[k] & 0x80) { // Last byte has been overwritten
236// for (i=k; (i>0) && ((k-i) < 3) && ((dest[i] & 0xC0) == 0x80); i--) ;
237// switch(k-i) {
238// case 0: dest[i] = '\0'; break;
239// case 1: if ( (dest[i] & 0xE0) != 0xC0) dest[i] = '\0'; break;
240// case 2: if ( (dest[i] & 0xF0) != 0xE0) dest[i] = '\0'; break;
241// case 3: if ( (dest[i] & 0xF8) != 0xF0) dest[i] = '\0'; break;
242// }
243// }
244// }
245// return dest;
246// }
247
248// char *u8strncat(char *dest, const char *src, size_t n)
249// {
250// char *d = dest;
251// while (*d) d++;
252// u8strncpy(d,src,n);
253// d[n] = '\0';
254// return dest;
255// }
256
257// static uint16_t fold_from[] = {
258// 0x0041,0x0042,0x0043,0x0044,0x0045,0x0046,0x0047,0x0048,0x0049,0x004A,0x004B,0x004C,0x004D,0x004E,0x004F,0x0050,
259// 0x0051,0x0052,0x0053,0x0054,0x0055,0x0056,0x0057,0x0058,0x0059,0x005A,0x00B5,0x00C0,0x00C1,0x00C2,0x00C3,0x00C4,
260// 0x00C5,0x00C6,0x00C7,0x00C8,0x00C9,0x00CA,0x00CB,0x00CC,0x00CD,0x00CE,0x00CF,0x00D0,0x00D1,0x00D2,0x00D3,0x00D4,
261// 0x00D5,0x00D6,0x00D8,0x00D9,0x00DA,0x00DB,0x00DC,0x00DD,0x00DE,0x0100,0x0102,0x0104,0x0106,0x0108,0x010A,0x010C,
262// 0x010E,0x0110,0x0112,0x0114,0x0116,0x0118,0x011A,0x011C,0x011E,0x0120,0x0122,0x0124,0x0126,0x0128,0x012A,0x012C,
263// 0x012E,0x0132,0x0134,0x0136,0x0139,0x013B,0x013D,0x013F,0x0141,0x0143,0x0145,0x0147,0x014A,0x014C,0x014E,0x0150,
264// 0x0152,0x0154,0x0156,0x0158,0x015A,0x015C,0x015E,0x0160,0x0162,0x0164,0x0166,0x0168,0x016A,0x016C,0x016E,0x0170,
265// 0x0172,0x0174,0x0176,0x0178,0x0179,0x017B,0x017D,0x017F,0x0181,0x0182,0x0184,0x0186,0x0187,0x0189,0x018A,0x018B,
266// 0x018E,0x018F,0x0190,0x0191,0x0193,0x0194,0x0196,0x0197,0x0198,0x019C,0x019D,0x019F,0x01A0,0x01A2,0x01A4,0x01A6,
267// 0x01A7,0x01A9,0x01AC,0x01AE,0x01AF,0x01B1,0x01B2,0x01B3,0x01B5,0x01B7,0x01B8,0x01BC,0x01C4,0x01C5,0x01C7,0x01C8,
268// 0x01CA,0x01CB,0x01CD,0x01CF,0x01D1,0x01D3,0x01D5,0x01D7,0x01D9,0x01DB,0x01DE,0x01E0,0x01E2,0x01E4,0x01E6,0x01E8,
269// 0x01EA,0x01EC,0x01EE,0x01F1,0x01F2,0x01F4,0x01F6,0x01F7,0x01F8,0x01FA,0x01FC,0x01FE,0x0200,0x0202,0x0204,0x0206,
270// 0x0208,0x020A,0x020C,0x020E,0x0210,0x0212,0x0214,0x0216,0x0218,0x021A,0x021C,0x021E,0x0220,0x0222,0x0224,0x0226,
271// 0x0228,0x022A,0x022C,0x022E,0x0230,0x0232,0x023A,0x023B,0x023D,0x023E,0x0241,0x0243,0x0244,0x0245,0x0246,0x0248,
272// 0x024A,0x024C,0x024E,0x0345,0x0370,0x0372,0x0376,0x0386,0x0388,0x0389,0x038A,0x038C,0x038E,0x038F,0x0391,0x0392,
273// 0x0393,0x0394,0x0395,0x0396,0x0397,0x0398,0x0399,0x039A,0x039B,0x039C,0x039D,0x039E,0x039F,0x03A0,0x03A1,0x03A3,
274// 0x03A4,0x03A5,0x03A6,0x03A7,0x03A8,0x03A9,0x03AA,0x03AB,0x03C2,0x03CF,0x03D0,0x03D1,0x03D5,0x03D6,0x03D8,0x03DA,
275// 0x03DC,0x03DE,0x03E0,0x03E2,0x03E4,0x03E6,0x03E8,0x03EA,0x03EC,0x03EE,0x03F0,0x03F1,0x03F4,0x03F5,0x03F7,0x03F9,
276// 0x03FA,0x03FD,0x03FE,0x03FF,0x0400,0x0401,0x0402,0x0403,0x0404,0x0405,0x0406,0x0407,0x0408,0x0409,0x040A,0x040B,
277// 0x040C,0x040D,0x040E,0x040F,0x0410,0x0411,0x0412,0x0413,0x0414,0x0415,0x0416,0x0417,0x0418,0x0419,0x041A,0x041B,
278// 0x041C,0x041D,0x041E,0x041F,0x0420,0x0421,0x0422,0x0423,0x0424,0x0425,0x0426,0x0427,0x0428,0x0429,0x042A,0x042B,
279// 0x042C,0x042D,0x042E,0x042F,0x0460,0x0462,0x0464,0x0466,0x0468,0x046A,0x046C,0x046E,0x0470,0x0472,0x0474,0x0476,
280// 0x0478,0x047A,0x047C,0x047E,0x0480,0x048A,0x048C,0x048E,0x0490,0x0492,0x0494,0x0496,0x0498,0x049A,0x049C,0x049E,
281// 0x04A0,0x04A2,0x04A4,0x04A6,0x04A8,0x04AA,0x04AC,0x04AE,0x04B0,0x04B2,0x04B4,0x04B6,0x04B8,0x04BA,0x04BC,0x04BE,
282// 0x04C0,0x04C1,0x04C3,0x04C5,0x04C7,0x04C9,0x04CB,0x04CD,0x04D0,0x04D2,0x04D4,0x04D6,0x04D8,0x04DA,0x04DC,0x04DE,
283// 0x04E0,0x04E2,0x04E4,0x04E6,0x04E8,0x04EA,0x04EC,0x04EE,0x04F0,0x04F2,0x04F4,0x04F6,0x04F8,0x04FA,0x04FC,0x04FE,
284// 0x0500,0x0502,0x0504,0x0506,0x0508,0x050A,0x050C,0x050E,0x0510,0x0512,0x0514,0x0516,0x0518,0x051A,0x051C,0x051E,
285// 0x0520,0x0522,0x0531,0x0532,0x0533,0x0534,0x0535,0x0536,0x0537,0x0538,0x0539,0x053A,0x053B,0x053C,0x053D,0x053E,
286// 0x053F,0x0540,0x0541,0x0542,0x0543,0x0544,0x0545,0x0546,0x0547,0x0548,0x0549,0x054A,0x054B,0x054C,0x054D,0x054E,
287// 0x054F,0x0550,0x0551,0x0552,0x0553,0x0554,0x0555,0x0556,0x10A0,0x10A1,0x10A2,0x10A3,0x10A4,0x10A5,0x10A6,0x10A7,
288// 0x10A8,0x10A9,0x10AA,0x10AB,0x10AC,0x10AD,0x10AE,0x10AF,0x10B0,0x10B1,0x10B2,0x10B3,0x10B4,0x10B5,0x10B6,0x10B7,
289// 0x10B8,0x10B9,0x10BA,0x10BB,0x10BC,0x10BD,0x10BE,0x10BF,0x10C0,0x10C1,0x10C2,0x10C3,0x10C4,0x10C5,0x1E00,0x1E02,
290// 0x1E04,0x1E06,0x1E08,0x1E0A,0x1E0C,0x1E0E,0x1E10,0x1E12,0x1E14,0x1E16,0x1E18,0x1E1A,0x1E1C,0x1E1E,0x1E20,0x1E22,
291// 0x1E24,0x1E26,0x1E28,0x1E2A,0x1E2C,0x1E2E,0x1E30,0x1E32,0x1E34,0x1E36,0x1E38,0x1E3A,0x1E3C,0x1E3E,0x1E40,0x1E42,
292// 0x1E44,0x1E46,0x1E48,0x1E4A,0x1E4C,0x1E4E,0x1E50,0x1E52,0x1E54,0x1E56,0x1E58,0x1E5A,0x1E5C,0x1E5E,0x1E60,0x1E62,
293// 0x1E64,0x1E66,0x1E68,0x1E6A,0x1E6C,0x1E6E,0x1E70,0x1E72,0x1E74,0x1E76,0x1E78,0x1E7A,0x1E7C,0x1E7E,0x1E80,0x1E82,
294// 0x1E84,0x1E86,0x1E88,0x1E8A,0x1E8C,0x1E8E,0x1E90,0x1E92,0x1E94,0x1E9B,0x1E9E,0x1EA0,0x1EA2,0x1EA4,0x1EA6,0x1EA8,
295// 0x1EAA,0x1EAC,0x1EAE,0x1EB0,0x1EB2,0x1EB4,0x1EB6,0x1EB8,0x1EBA,0x1EBC,0x1EBE,0x1EC0,0x1EC2,0x1EC4,0x1EC6,0x1EC8,
296// 0x1ECA,0x1ECC,0x1ECE,0x1ED0,0x1ED2,0x1ED4,0x1ED6,0x1ED8,0x1EDA,0x1EDC,0x1EDE,0x1EE0,0x1EE2,0x1EE4,0x1EE6,0x1EE8,
297// 0x1EEA,0x1EEC,0x1EEE,0x1EF0,0x1EF2,0x1EF4,0x1EF6,0x1EF8,0x1EFA,0x1EFC,0x1EFE,0x1F08,0x1F09,0x1F0A,0x1F0B,0x1F0C,
298// 0x1F0D,0x1F0E,0x1F0F,0x1F18,0x1F19,0x1F1A,0x1F1B,0x1F1C,0x1F1D,0x1F28,0x1F29,0x1F2A,0x1F2B,0x1F2C,0x1F2D,0x1F2E,
299// 0x1F2F,0x1F38,0x1F39,0x1F3A,0x1F3B,0x1F3C,0x1F3D,0x1F3E,0x1F3F,0x1F48,0x1F49,0x1F4A,0x1F4B,0x1F4C,0x1F4D,0x1F59,
300// 0x1F5B,0x1F5D,0x1F5F,0x1F68,0x1F69,0x1F6A,0x1F6B,0x1F6C,0x1F6D,0x1F6E,0x1F6F,0x1F88,0x1F89,0x1F8A,0x1F8B,0x1F8C,
301// 0x1F8D,0x1F8E,0x1F8F,0x1F98,0x1F99,0x1F9A,0x1F9B,0x1F9C,0x1F9D,0x1F9E,0x1F9F,0x1FA8,0x1FA9,0x1FAA,0x1FAB,0x1FAC,
302// 0x1FAD,0x1FAE,0x1FAF,0x1FB8,0x1FB9,0x1FBA,0x1FBB,0x1FBC,0x1FBE,0x1FC8,0x1FC9,0x1FCA,0x1FCB,0x1FCC,0x1FD8,0x1FD9,
303// 0x1FDA,0x1FDB,0x1FE8,0x1FE9,0x1FEA,0x1FEB,0x1FEC,0x1FF8,0x1FF9,0x1FFA,0x1FFB,0x1FFC,0x2126,0x212A,0x212B,0x2132,
304// 0x2160,0x2161,0x2162,0x2163,0x2164,0x2165,0x2166,0x2167,0x2168,0x2169,0x216A,0x216B,0x216C,0x216D,0x216E,0x216F,
305// 0x2183,0x24B6,0x24B7,0x24B8,0x24B9,0x24BA,0x24BB,0x24BC,0x24BD,0x24BE,0x24BF,0x24C0,0x24C1,0x24C2,0x24C3,0x24C4,
306// 0x24C5,0x24C6,0x24C7,0x24C8,0x24C9,0x24CA,0x24CB,0x24CC,0x24CD,0x24CE,0x24CF,0x2C00,0x2C01,0x2C02,0x2C03,0x2C04,
307// 0x2C05,0x2C06,0x2C07,0x2C08,0x2C09,0x2C0A,0x2C0B,0x2C0C,0x2C0D,0x2C0E,0x2C0F,0x2C10,0x2C11,0x2C12,0x2C13,0x2C14,
308// 0x2C15,0x2C16,0x2C17,0x2C18,0x2C19,0x2C1A,0x2C1B,0x2C1C,0x2C1D,0x2C1E,0x2C1F,0x2C20,0x2C21,0x2C22,0x2C23,0x2C24,
309// 0x2C25,0x2C26,0x2C27,0x2C28,0x2C29,0x2C2A,0x2C2B,0x2C2C,0x2C2D,0x2C2E,0x2C60,0x2C62,0x2C63,0x2C64,0x2C67,0x2C69,
310// 0x2C6B,0x2C6D,0x2C6E,0x2C6F,0x2C72,0x2C75,0x2C80,0x2C82,0x2C84,0x2C86,0x2C88,0x2C8A,0x2C8C,0x2C8E,0x2C90,0x2C92,
311// 0x2C94,0x2C96,0x2C98,0x2C9A,0x2C9C,0x2C9E,0x2CA0,0x2CA2,0x2CA4,0x2CA6,0x2CA8,0x2CAA,0x2CAC,0x2CAE,0x2CB0,0x2CB2,
312// 0x2CB4,0x2CB6,0x2CB8,0x2CBA,0x2CBC,0x2CBE,0x2CC0,0x2CC2,0x2CC4,0x2CC6,0x2CC8,0x2CCA,0x2CCC,0x2CCE,0x2CD0,0x2CD2,
313// 0x2CD4,0x2CD6,0x2CD8,0x2CDA,0x2CDC,0x2CDE,0x2CE0,0x2CE2,0xA640,0xA642,0xA644,0xA646,0xA648,0xA64A,0xA64C,0xA64E,
314// 0xA650,0xA652,0xA654,0xA656,0xA658,0xA65A,0xA65C,0xA65E,0xA662,0xA664,0xA666,0xA668,0xA66A,0xA66C,0xA680,0xA682,
315// 0xA684,0xA686,0xA688,0xA68A,0xA68C,0xA68E,0xA690,0xA692,0xA694,0xA696,0xA722,0xA724,0xA726,0xA728,0xA72A,0xA72C,
316// 0xA72E,0xA732,0xA734,0xA736,0xA738,0xA73A,0xA73C,0xA73E,0xA740,0xA742,0xA744,0xA746,0xA748,0xA74A,0xA74C,0xA74E,
317// 0xA750,0xA752,0xA754,0xA756,0xA758,0xA75A,0xA75C,0xA75E,0xA760,0xA762,0xA764,0xA766,0xA768,0xA76A,0xA76C,0xA76E,
318// 0xA779,0xA77B,0xA77D,0xA77E,0xA780,0xA782,0xA784,0xA786,0xA78B,0xFF21,0xFF22,0xFF23,0xFF24,0xFF25,0xFF26,0xFF27,
319// 0xFF28,0xFF29,0xFF2A,0xFF2B,0xFF2C,0xFF2D,0xFF2E,0xFF2F,0xFF30,0xFF31,0xFF32,0xFF33,0xFF34,0xFF35,0xFF36,0xFF37,
320// 0xFF38,0xFF39,0xFF3A
321// };
322
323// static uint16_t fold_to[] = {
324// 0x0061,0x0062,0x0063,0x0064,0x0065,0x0066,0x0067,0x0068,0x0069,0x006A,0x006B,0x006C,0x006D,0x006E,0x006F,0x0070,
325// 0x0071,0x0072,0x0073,0x0074,0x0075,0x0076,0x0077,0x0078,0x0079,0x007A,0x03BC,0x00E0,0x00E1,0x00E2,0x00E3,0x00E4,
326// 0x00E5,0x00E6,0x00E7,0x00E8,0x00E9,0x00EA,0x00EB,0x00EC,0x00ED,0x00EE,0x00EF,0x00F0,0x00F1,0x00F2,0x00F3,0x00F4,
327// 0x00F5,0x00F6,0x00F8,0x00F9,0x00FA,0x00FB,0x00FC,0x00FD,0x00FE,0x0101,0x0103,0x0105,0x0107,0x0109,0x010B,0x010D,
328// 0x010F,0x0111,0x0113,0x0115,0x0117,0x0119,0x011B,0x011D,0x011F,0x0121,0x0123,0x0125,0x0127,0x0129,0x012B,0x012D,
329// 0x012F,0x0133,0x0135,0x0137,0x013A,0x013C,0x013E,0x0140,0x0142,0x0144,0x0146,0x0148,0x014B,0x014D,0x014F,0x0151,
330// 0x0153,0x0155,0x0157,0x0159,0x015B,0x015D,0x015F,0x0161,0x0163,0x0165,0x0167,0x0169,0x016B,0x016D,0x016F,0x0171,
331// 0x0173,0x0175,0x0177,0x00FF,0x017A,0x017C,0x017E,0x0073,0x0253,0x0183,0x0185,0x0254,0x0188,0x0256,0x0257,0x018C,
332// 0x01DD,0x0259,0x025B,0x0192,0x0260,0x0263,0x0269,0x0268,0x0199,0x026F,0x0272,0x0275,0x01A1,0x01A3,0x01A5,0x0280,
333// 0x01A8,0x0283,0x01AD,0x0288,0x01B0,0x028A,0x028B,0x01B4,0x01B6,0x0292,0x01B9,0x01BD,0x01C6,0x01C6,0x01C9,0x01C9,
334// 0x01CC,0x01CC,0x01CE,0x01D0,0x01D2,0x01D4,0x01D6,0x01D8,0x01DA,0x01DC,0x01DF,0x01E1,0x01E3,0x01E5,0x01E7,0x01E9,
335// 0x01EB,0x01ED,0x01EF,0x01F3,0x01F3,0x01F5,0x0195,0x01BF,0x01F9,0x01FB,0x01FD,0x01FF,0x0201,0x0203,0x0205,0x0207,
336// 0x0209,0x020B,0x020D,0x020F,0x0211,0x0213,0x0215,0x0217,0x0219,0x021B,0x021D,0x021F,0x019E,0x0223,0x0225,0x0227,
337// 0x0229,0x022B,0x022D,0x022F,0x0231,0x0233,0x2C65,0x023C,0x019A,0x2C66,0x0242,0x0180,0x0289,0x028C,0x0247,0x0249,
338// 0x024B,0x024D,0x024F,0x03B9,0x0371,0x0373,0x0377,0x03AC,0x03AD,0x03AE,0x03AF,0x03CC,0x03CD,0x03CE,0x03B1,0x03B2,
339// 0x03B3,0x03B4,0x03B5,0x03B6,0x03B7,0x03B8,0x03B9,0x03BA,0x03BB,0x03BC,0x03BD,0x03BE,0x03BF,0x03C0,0x03C1,0x03C3,
340// 0x03C4,0x03C5,0x03C6,0x03C7,0x03C8,0x03C9,0x03CA,0x03CB,0x03C3,0x03D7,0x03B2,0x03B8,0x03C6,0x03C0,0x03D9,0x03DB,
341// 0x03DD,0x03DF,0x03E1,0x03E3,0x03E5,0x03E7,0x03E9,0x03EB,0x03ED,0x03EF,0x03BA,0x03C1,0x03B8,0x03B5,0x03F8,0x03F2,
342// 0x03FB,0x037B,0x037C,0x037D,0x0450,0x0451,0x0452,0x0453,0x0454,0x0455,0x0456,0x0457,0x0458,0x0459,0x045A,0x045B,
343// 0x045C,0x045D,0x045E,0x045F,0x0430,0x0431,0x0432,0x0433,0x0434,0x0435,0x0436,0x0437,0x0438,0x0439,0x043A,0x043B,
344// 0x043C,0x043D,0x043E,0x043F,0x0440,0x0441,0x0442,0x0443,0x0444,0x0445,0x0446,0x0447,0x0448,0x0449,0x044A,0x044B,
345// 0x044C,0x044D,0x044E,0x044F,0x0461,0x0463,0x0465,0x0467,0x0469,0x046B,0x046D,0x046F,0x0471,0x0473,0x0475,0x0477,
346// 0x0479,0x047B,0x047D,0x047F,0x0481,0x048B,0x048D,0x048F,0x0491,0x0493,0x0495,0x0497,0x0499,0x049B,0x049D,0x049F,
347// 0x04A1,0x04A3,0x04A5,0x04A7,0x04A9,0x04AB,0x04AD,0x04AF,0x04B1,0x04B3,0x04B5,0x04B7,0x04B9,0x04BB,0x04BD,0x04BF,
348// 0x04CF,0x04C2,0x04C4,0x04C6,0x04C8,0x04CA,0x04CC,0x04CE,0x04D1,0x04D3,0x04D5,0x04D7,0x04D9,0x04DB,0x04DD,0x04DF,
349// 0x04E1,0x04E3,0x04E5,0x04E7,0x04E9,0x04EB,0x04ED,0x04EF,0x04F1,0x04F3,0x04F5,0x04F7,0x04F9,0x04FB,0x04FD,0x04FF,
350// 0x0501,0x0503,0x0505,0x0507,0x0509,0x050B,0x050D,0x050F,0x0511,0x0513,0x0515,0x0517,0x0519,0x051B,0x051D,0x051F,
351// 0x0521,0x0523,0x0561,0x0562,0x0563,0x0564,0x0565,0x0566,0x0567,0x0568,0x0569,0x056A,0x056B,0x056C,0x056D,0x056E,
352// 0x056F,0x0570,0x0571,0x0572,0x0573,0x0574,0x0575,0x0576,0x0577,0x0578,0x0579,0x057A,0x057B,0x057C,0x057D,0x057E,
353// 0x057F,0x0580,0x0581,0x0582,0x0583,0x0584,0x0585,0x0586,0x2D00,0x2D01,0x2D02,0x2D03,0x2D04,0x2D05,0x2D06,0x2D07,
354// 0x2D08,0x2D09,0x2D0A,0x2D0B,0x2D0C,0x2D0D,0x2D0E,0x2D0F,0x2D10,0x2D11,0x2D12,0x2D13,0x2D14,0x2D15,0x2D16,0x2D17,
355// 0x2D18,0x2D19,0x2D1A,0x2D1B,0x2D1C,0x2D1D,0x2D1E,0x2D1F,0x2D20,0x2D21,0x2D22,0x2D23,0x2D24,0x2D25,0x1E01,0x1E03,
356// 0x1E05,0x1E07,0x1E09,0x1E0B,0x1E0D,0x1E0F,0x1E11,0x1E13,0x1E15,0x1E17,0x1E19,0x1E1B,0x1E1D,0x1E1F,0x1E21,0x1E23,
357// 0x1E25,0x1E27,0x1E29,0x1E2B,0x1E2D,0x1E2F,0x1E31,0x1E33,0x1E35,0x1E37,0x1E39,0x1E3B,0x1E3D,0x1E3F,0x1E41,0x1E43,
358// 0x1E45,0x1E47,0x1E49,0x1E4B,0x1E4D,0x1E4F,0x1E51,0x1E53,0x1E55,0x1E57,0x1E59,0x1E5B,0x1E5D,0x1E5F,0x1E61,0x1E63,
359// 0x1E65,0x1E67,0x1E69,0x1E6B,0x1E6D,0x1E6F,0x1E71,0x1E73,0x1E75,0x1E77,0x1E79,0x1E7B,0x1E7D,0x1E7F,0x1E81,0x1E83,
360// 0x1E85,0x1E87,0x1E89,0x1E8B,0x1E8D,0x1E8F,0x1E91,0x1E93,0x1E95,0x1E61,0x00DF,0x1EA1,0x1EA3,0x1EA5,0x1EA7,0x1EA9,
361// 0x1EAB,0x1EAD,0x1EAF,0x1EB1,0x1EB3,0x1EB5,0x1EB7,0x1EB9,0x1EBB,0x1EBD,0x1EBF,0x1EC1,0x1EC3,0x1EC5,0x1EC7,0x1EC9,
362// 0x1ECB,0x1ECD,0x1ECF,0x1ED1,0x1ED3,0x1ED5,0x1ED7,0x1ED9,0x1EDB,0x1EDD,0x1EDF,0x1EE1,0x1EE3,0x1EE5,0x1EE7,0x1EE9,
363// 0x1EEB,0x1EED,0x1EEF,0x1EF1,0x1EF3,0x1EF5,0x1EF7,0x1EF9,0x1EFB,0x1EFD,0x1EFF,0x1F00,0x1F01,0x1F02,0x1F03,0x1F04,
364// 0x1F05,0x1F06,0x1F07,0x1F10,0x1F11,0x1F12,0x1F13,0x1F14,0x1F15,0x1F20,0x1F21,0x1F22,0x1F23,0x1F24,0x1F25,0x1F26,
365// 0x1F27,0x1F30,0x1F31,0x1F32,0x1F33,0x1F34,0x1F35,0x1F36,0x1F37,0x1F40,0x1F41,0x1F42,0x1F43,0x1F44,0x1F45,0x1F51,
366// 0x1F53,0x1F55,0x1F57,0x1F60,0x1F61,0x1F62,0x1F63,0x1F64,0x1F65,0x1F66,0x1F67,0x1F80,0x1F81,0x1F82,0x1F83,0x1F84,
367// 0x1F85,0x1F86,0x1F87,0x1F90,0x1F91,0x1F92,0x1F93,0x1F94,0x1F95,0x1F96,0x1F97,0x1FA0,0x1FA1,0x1FA2,0x1FA3,0x1FA4,
368// 0x1FA5,0x1FA6,0x1FA7,0x1FB0,0x1FB1,0x1F70,0x1F71,0x1FB3,0x03B9,0x1F72,0x1F73,0x1F74,0x1F75,0x1FC3,0x1FD0,0x1FD1,
369// 0x1F76,0x1F77,0x1FE0,0x1FE1,0x1F7A,0x1F7B,0x1FE5,0x1F78,0x1F79,0x1F7C,0x1F7D,0x1FF3,0x03C9,0x006B,0x00E5,0x214E,
370// 0x2170,0x2171,0x2172,0x2173,0x2174,0x2175,0x2176,0x2177,0x2178,0x2179,0x217A,0x217B,0x217C,0x217D,0x217E,0x217F,
371// 0x2184,0x24D0,0x24D1,0x24D2,0x24D3,0x24D4,0x24D5,0x24D6,0x24D7,0x24D8,0x24D9,0x24DA,0x24DB,0x24DC,0x24DD,0x24DE,
372// 0x24DF,0x24E0,0x24E1,0x24E2,0x24E3,0x24E4,0x24E5,0x24E6,0x24E7,0x24E8,0x24E9,0x2C30,0x2C31,0x2C32,0x2C33,0x2C34,
373// 0x2C35,0x2C36,0x2C37,0x2C38,0x2C39,0x2C3A,0x2C3B,0x2C3C,0x2C3D,0x2C3E,0x2C3F,0x2C40,0x2C41,0x2C42,0x2C43,0x2C44,
374// 0x2C45,0x2C46,0x2C47,0x2C48,0x2C49,0x2C4A,0x2C4B,0x2C4C,0x2C4D,0x2C4E,0x2C4F,0x2C50,0x2C51,0x2C52,0x2C53,0x2C54,
375// 0x2C55,0x2C56,0x2C57,0x2C58,0x2C59,0x2C5A,0x2C5B,0x2C5C,0x2C5D,0x2C5E,0x2C61,0x026B,0x1D7D,0x027D,0x2C68,0x2C6A,
376// 0x2C6C,0x0251,0x0271,0x0250,0x2C73,0x2C76,0x2C81,0x2C83,0x2C85,0x2C87,0x2C89,0x2C8B,0x2C8D,0x2C8F,0x2C91,0x2C93,
377// 0x2C95,0x2C97,0x2C99,0x2C9B,0x2C9D,0x2C9F,0x2CA1,0x2CA3,0x2CA5,0x2CA7,0x2CA9,0x2CAB,0x2CAD,0x2CAF,0x2CB1,0x2CB3,
378// 0x2CB5,0x2CB7,0x2CB9,0x2CBB,0x2CBD,0x2CBF,0x2CC1,0x2CC3,0x2CC5,0x2CC7,0x2CC9,0x2CCB,0x2CCD,0x2CCF,0x2CD1,0x2CD3,
379// 0x2CD5,0x2CD7,0x2CD9,0x2CDB,0x2CDD,0x2CDF,0x2CE1,0x2CE3,0xA641,0xA643,0xA645,0xA647,0xA649,0xA64B,0xA64D,0xA64F,
380// 0xA651,0xA653,0xA655,0xA657,0xA659,0xA65B,0xA65D,0xA65F,0xA663,0xA665,0xA667,0xA669,0xA66B,0xA66D,0xA681,0xA683,
381// 0xA685,0xA687,0xA689,0xA68B,0xA68D,0xA68F,0xA691,0xA693,0xA695,0xA697,0xA723,0xA725,0xA727,0xA729,0xA72B,0xA72D,
382// 0xA72F,0xA733,0xA735,0xA737,0xA739,0xA73B,0xA73D,0xA73F,0xA741,0xA743,0xA745,0xA747,0xA749,0xA74B,0xA74D,0xA74F,
383// 0xA751,0xA753,0xA755,0xA757,0xA759,0xA75B,0xA75D,0xA75F,0xA761,0xA763,0xA765,0xA767,0xA769,0xA76B,0xA76D,0xA76F,
384// 0xA77A,0xA77C,0x1D79,0xA77F,0xA781,0xA783,0xA785,0xA787,0xA78C,0xFF41,0xFF42,0xFF43,0xFF44,0xFF45,0xFF46,0xFF47,
385// 0xFF48,0xFF49,0xFF4A,0xFF4B,0xFF4C,0xFF4D,0xFF4E,0xFF4F,0xFF50,0xFF51,0xFF52,0xFF53,0xFF54,0xFF55,0xFF56,0xFF57,
386// 0xFF58,0xFF59,0xFF5A
387// };
388
389
390// static int fold_search(int cp)
391// {
392// int i=0, j=995, k;
393// while (i<=j) {
394// k=(i+j)/2;
395// if (cp == fold_from[k]) return fold_to[k];
396
397// if (cp < fold_from[k]) j=k-1;
398// else i = k+1;
399// }
400// return cp;
401// }
402
403// int u8fold(int cp)
404// {
405// // DESERET is the only one above 0xFFFF to be folded)
406// if (0x10400 <= cp && cp <= 0x10427) cp += 40;
407
408// if (cp <= 0xFFFF) cp = fold_search(cp);
409
410// return cp;
411// }
412
413// int u8stricmp(char *s, char *t)
414// {
415// int ls, lt;
416// int cs = 0, ct =0 ;
417
418// for(int chk=0; chk < 1024*1024; chk++) {
419// ls=u8decode(s,&cs); lt=u8decode(t,&ct);
420// cs = u8fold(cs); ct = u8fold(ct);
421// if (cs != ct) return cs-ct;
422// if (ls == 0) return 0;
423// if (ls<0) ls=-ls;
424// if (lt<0) lt=-ls;
425// s += ls;
426// t += lt;
427// }
428// return 0;
429// }
430
431} // namespace u8c
Definition u8c.cpp:64
int u8next_FAST(const char *txt, int *ch)
Definition u8c.cpp:156
size_t u8next_(const char *start, const char *end, char32_t &val)
Definition u8c.cpp:66
#define fsmGOTO(x)
Definition u8c.cpp:14
#define fsmSTATE(x)
Definition u8c.cpp:15
#define fsm
Definition u8c.cpp:13