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
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
|
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
*
* Copyright (C) 1998-2014, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
*
* File ufmt_cmn.c
*
* Modification History:
*
* Date Name Description
* 12/02/98 stephen Creation.
* 03/12/99 stephen Modified for new C API.
* 03/15/99 stephen Added defaultCPToUnicode, unicodeToDefaultCP
* 07/19/99 stephen Fixed bug in defaultCPToUnicode
******************************************************************************
*/
#include "cstring.h"
#include "cmemory.h"
#include "ufmt_cmn.h"
#include "unicode/uchar.h"
#include "unicode/ucnv.h"
#include "ustr_cnv.h"
#if !UCONFIG_NO_CONVERSION
#define DIGIT_0 0x0030
#define DIGIT_9 0x0039
#define LOWERCASE_A 0x0061
#define UPPERCASE_A 0x0041
#define LOWERCASE_Z 0x007A
#define UPPERCASE_Z 0x005A
int
ufmt_digitvalue(char16_t c)
{
if( ((c>=DIGIT_0)&&(c<=DIGIT_9)) ||
((c>=LOWERCASE_A)&&(c<=LOWERCASE_Z)) ||
((c>=UPPERCASE_A)&&(c<=UPPERCASE_Z)) )
{
return c - DIGIT_0 - (c >= 0x0041 ? (c >= 0x0061 ? 39 : 7) : 0);
}
else
{
return -1;
}
}
UBool
ufmt_isdigit(char16_t c,
int32_t radix)
{
int digitVal = ufmt_digitvalue(c);
return (UBool)(digitVal < radix && digitVal >= 0);
}
#define TO_UC_DIGIT(a) a <= 9 ? (DIGIT_0 + a) : (0x0037 + a)
#define TO_LC_DIGIT(a) a <= 9 ? (DIGIT_0 + a) : (0x0057 + a)
void
ufmt_64tou(char16_t *buffer,
int32_t *len,
uint64_t value,
uint8_t radix,
UBool uselower,
int32_t minDigits)
{
int32_t length = 0;
uint32_t digit;
char16_t *left, *right, temp;
do {
digit = (uint32_t)(value % radix);
value = value / radix;
buffer[length++] = (char16_t)(uselower ? TO_LC_DIGIT(digit)
: TO_UC_DIGIT(digit));
} while(value);
/* pad with zeroes to make it minDigits long */
if(minDigits != -1 && length < minDigits) {
while(length < minDigits && length < *len)
buffer[length++] = DIGIT_0; /*zero padding */
}
/* reverse the buffer */
left = buffer;
right = buffer + length;
while(left < --right) {
temp = *left;
*left++ = *right;
*right = temp;
}
*len = length;
}
void
ufmt_ptou(char16_t *buffer,
int32_t *len,
void *value,
UBool uselower)
{
int32_t i;
int32_t length = 0;
uint8_t *ptrIdx = (uint8_t *)&value;
#if U_IS_BIG_ENDIAN
for (i = 0; i < (int32_t)sizeof(void *); i++)
#else
for (i = (int32_t)sizeof(void *)-1; i >= 0 ; i--)
#endif
{
uint8_t byteVal = ptrIdx[i];
uint16_t firstNibble = (uint16_t)(byteVal>>4);
uint16_t secondNibble = (uint16_t)(byteVal&0xF);
if (uselower) {
buffer[length++]=TO_LC_DIGIT(firstNibble);
buffer[length++]=TO_LC_DIGIT(secondNibble);
}
else {
buffer[length++]=TO_UC_DIGIT(firstNibble);
buffer[length++]=TO_UC_DIGIT(secondNibble);
}
}
*len = length;
}
int64_t
ufmt_uto64(const char16_t *buffer,
int32_t *len,
int8_t radix)
{
const char16_t *limit;
int32_t count;
uint64_t result;
/* initialize parameters */
limit = buffer + *len;
count = 0;
result = 0;
/* iterate through buffer */
while(ufmt_isdigit(*buffer, radix) && buffer < limit) {
/* read the next digit */
result *= radix;
result += ufmt_digitvalue(*buffer++);
/* increment our count */
++count;
}
*len = count;
return static_cast<int64_t>(result);
}
#define NIBBLE_PER_BYTE 2
void *
ufmt_utop(const char16_t *buffer,
int32_t *len)
{
int32_t count, resultIdx, incVal, offset;
/* This union allows the pointer to be written as an array. */
union {
void *ptr;
uint8_t bytes[sizeof(void*)];
} result;
/* initialize variables */
count = 0;
offset = 0;
result.ptr = nullptr;
/* Skip the leading zeros */
while(buffer[count] == DIGIT_0 || u_isspace(buffer[count])) {
count++;
offset++;
}
/* iterate through buffer, stop when you hit the end */
while(count < *len && ufmt_isdigit(buffer[count], 16)) {
/* increment the count consumed */
++count;
}
/* detect overflow */
if (count - offset > (int32_t)(sizeof(void*)*NIBBLE_PER_BYTE)) {
offset = count - (int32_t)(sizeof(void*)*NIBBLE_PER_BYTE);
}
/* Initialize the direction of the input */
#if U_IS_BIG_ENDIAN
incVal = -1;
resultIdx = (int32_t)(sizeof(void*) - 1);
#else
incVal = 1;
resultIdx = 0;
#endif
/* Write how much was consumed. */
*len = count;
while(--count >= offset) {
/* Get the first nibble of the byte */
uint8_t byte = (uint8_t)ufmt_digitvalue(buffer[count]);
if (count > offset) {
/* Get the second nibble of the byte when available */
byte = (uint8_t)(byte + (ufmt_digitvalue(buffer[--count]) << 4));
}
/* Write the byte into the array */
result.bytes[resultIdx] = byte;
resultIdx += incVal;
}
return result.ptr;
}
char16_t*
ufmt_defaultCPToUnicode(const char *s, int32_t sSize,
char16_t *target, int32_t tSize)
{
char16_t *alias;
UErrorCode status = U_ZERO_ERROR;
UConverter *defConverter = u_getDefaultConverter(&status);
if(U_FAILURE(status) || defConverter == 0)
return 0;
if(sSize <= 0) {
sSize = static_cast<int32_t>(uprv_strlen(s)) + 1;
}
/* perform the conversion in one swoop */
if(target != 0) {
alias = target;
ucnv_toUnicode(defConverter, &alias, alias + tSize, &s, s + sSize - 1,
nullptr, true, &status);
/* add the null terminator */
*alias = 0x0000;
}
u_releaseDefaultConverter(defConverter);
return target;
}
#endif
|
