1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
|
/******************************************************************************
*
* Copyright (C) 1997-2021 by Dimitri van Heesch.
*
* Permission to use, copy, modify, and distribute this software and its
* documentation under the terms of the GNU General Public License is hereby
* granted. No representations are made about the suitability of this software
* for any purpose. It is provided "as is" without express or implied warranty.
* See the GNU General Public License for more details.
*
* Documents produced by Doxygen are derivative works derived from the
* input used in their production; they are not affected by this license.
*
*/
#include <cstdint>
#include <sstream>
#include "utf8.h"
#include "caseconvert.h"
#include "textstream.h"
uint8_t getUTF8CharNumBytes(char c)
{
uint8_t num=1;
unsigned char uc = static_cast<unsigned char>(c);
if (uc>=0x80u) // multibyte character
{
if ((uc&0xE0u)==0xC0u)
{
num=2; // 110x.xxxx: 2 byte character
}
if ((uc&0xF0u)==0xE0u)
{
num=3; // 1110.xxxx: 3 byte character
}
if ((uc&0xF8u)==0xF0u)
{
num=4; // 1111.0xxx: 4 byte character
}
if ((uc&0xFCu)==0xF8u)
{
num=5; // 1111.10xx: 5 byte character
}
if ((uc&0xFEu)==0xFCu)
{
num=6; // 1111.110x: 6 byte character
}
}
return num;
}
//! Decodes a given input of utf8 data to a unicode code point
//! given the number of bytes it's made of
static inline uint32_t decode_utf8( const char* data , int numBytes ) noexcept
{
uint32_t cp = (unsigned char)*data;
if (numBytes>1)
{
cp &= 0x7F >> numBytes; // Mask out the header bits
for (int i=1 ; i<numBytes ; i++)
{
cp = (cp<<6) | ((unsigned char)data[i]&0x3F);
}
}
return cp;
}
static inline uint32_t convertUTF8CharToUnicode(const char *s,size_t bytesLeft,int &len)
{
if (s==0 || bytesLeft==0)
{
len=0;
return 0;
}
unsigned char uc = static_cast<unsigned char>(*s);
switch (bytesLeft)
{
default:
if ((uc&0xFEu)==0xFCu)// 1111110X six bytes
{
len=6;
return decode_utf8(s,len);
}
// fall through
case 5:
if ((uc&0xFCu)==0xF8u) // 111110XX five bytes
{
len=5;
return decode_utf8(s,len);
}
// fall through
case 4:
if ((uc&0xF8u)==0xF0u) // 11110XXX four bytes
{
len=4;
return decode_utf8(s,len);
}
// fall through
case 3:
if ((uc&0xF0u)==0xE0u) // 1110XXXX three bytes
{
len=3;
return decode_utf8(s,len);
}
// fall through
case 2:
if ((uc&0xE0u)==0xC0u) // 110XXXXX two bytes
{
len=2;
return decode_utf8(s,len);
}
// fall through
case 1:
{
len=1;
return uc;
}
}
len=0;
return 0;
}
std::string getUTF8CharAt(const std::string &input,size_t pos)
{
if (input.length()<=pos) return std::string();
int numBytes=getUTF8CharNumBytes(input[pos]);
if (input.length()<pos+numBytes) return std::string();
return input.substr(pos,pos+numBytes);
}
uint32_t getUnicodeForUTF8CharAt(const std::string &input,size_t pos)
{
std::string charS = getUTF8CharAt(input,pos);
int len;
return convertUTF8CharToUnicode(charS.c_str(),charS.length(),len);
}
static inline std::string caseConvert(const std::string &input,
const char *(*conversionFunc)(uint32_t code))
{
uint32_t code;
TextStream result;
int len;
size_t bytesLeft = input.length();
const char *p = input.c_str();
while ((code=convertUTF8CharToUnicode(p,bytesLeft,len)))
{
const char *conv = conversionFunc(code);
if (conv==nullptr) // no difference between lower and upper case
{
result.write(p,len);
}
else // replace the input character with the conversion result
{
result << conv;
}
p+=len;
bytesLeft-=len;
}
return result.str();
}
std::string convertUTF8ToLower(const std::string &input)
{
return caseConvert(input,convertUnicodeToLower);
}
std::string convertUTF8ToUpper(const std::string &input)
{
return caseConvert(input,convertUnicodeToUpper);
}
const char *writeUTF8Char(TextStream &t,const char *s)
{
if (s==0) return 0;
uint8_t len = getUTF8CharNumBytes(*s);
for (uint8_t i=0;i<len;i++)
{
if (s[i]==0) // detect premature end of string (due to invalid UTF8 char)
{
len=i;
}
}
t.write(s,len);
return s+len;
}
bool lastUTF8CharIsMultibyte(const std::string &input)
{
// last byte is part of a multibyte UTF8 char if bit 8 is set and bit 7 is not
return !input.empty() && (((unsigned char)input[input.length()-1])&0xC0)==0x80;
}
bool isUTF8CharUpperCase(const std::string &input,size_t pos)
{
if (input.length()<=pos) return false;
int len;
// turn the UTF8 character at position pos into a unicode value
uint32_t code = convertUTF8CharToUnicode(input.c_str()+pos,input.length()-pos,len);
// check if the character can be converted to lower case, if so it was an upper case character
return convertUnicodeToLower(code)!=nullptr;
}
int isUTF8NonBreakableSpace(const char *input)
{
return (static_cast<unsigned char>(input[0])==0xC2 &&
static_cast<unsigned char>(input[1])==0xA0) ? 2 : 0;
}
|
