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
|
/* normcode.cpp
* Transcodes Latin-1/UTF-8 to canonically normalized UTF-8/SCSU
*/
#include <iostream>
#include <string>
#include <fstream>
#include "unicode/utypes.h"
#include "unicode/convert.h"
#include "unicode/ustring.h"
#include "unicode/normlzr.h"
#define BUFSIZE 65536
int main (char argc, char** argv) {
if (argc < 5) {
cout << "usage: " << argv[0] << " -[8|l] <input file> -[8|s] <outputfile> -[c|d]" << endl;
cout << "The first argument should be -8 if input is UTF-8 or -l if it is Latin-1/Codepage 1252." << endl;
cout << "The third argument should be -8 for UTF-8 output or -s for SCSU output." << endl;
cout << "The fifth arg should be -c if you want to pre-compose or -d if you want to decompose (default)." << endl;
return -1;
}
fstream inf, outf;
char* buffer = new char[BUFSIZE];
UnicodeString source, norm;
UErrorCode err;
int32_t buf32;
UnicodeConverter latin("Latin-1", err);
if (U_FAILURE(err)) cout << "Latin-1 converter error" << endl;
UnicodeConverter scsu("SCSU", err);
if (U_FAILURE(err)) cout << "SCSU converter error" << endl;
UnicodeConverter utf8("UTF-8", err);
if (U_FAILURE(err)) cout << "UTF-8 converter error" << endl;
inf.open(argv[2], fstream::in);
outf.open(argv[4], fstream::out);
while (!inf.eof()) {
inf.getline(buffer, BUFSIZE);
buf32 = inf.gcount();
if (buf32 == 0) {
outf << endl;
continue;
}
buffer[buf32-1] = '\n';
buffer[buf32] = 0;
if (argv[1][1] == 'l') {
latin.toUnicodeString(source, buffer, buf32, err);
if (U_FAILURE(err)) cout << "Latin-1 conversion error" << endl;
} else {
utf8.toUnicodeString(source, buffer, buf32, err);
if (U_FAILURE(err)) cout << "UTF-8 conversion error" << endl;
}
if (argc > 5) {
if (argv[5][1] == 'c') {
Normalizer::normalize(source, UNORM_NFC, 0, norm, err); //canonical composition
} else {
Normalizer::normalize(source, UNORM_NFD, 0, norm, err); //canonical decomposition
}
} else {
Normalizer::normalize(source, UNORM_NFD, 0, norm, err); //canonical decomposition
}
buf32 = BUFSIZE;
if (argv[3][1] == 's') {
scsu.fromUnicodeString((char*)buffer, buf32, norm, err);
if (U_FAILURE(err)) cout << "SCSU conversion error" << endl;
// scsu.toUnicodeString(norm, buffer, buf32, err);
// buf32 = BUFSIZE;
// utf8.fromUnicodeString((char*)buffer, buf32, norm, err);
} else {
utf8.fromUnicodeString((char*)buffer, buf32, norm, err);
if (U_FAILURE(err)) cout << "UTF-8 conversion error" << endl;
}
if (U_SUCCESS(err) && !inf.eof()) {
buffer[buf32] = 0;
}
outf.write(buffer, buf32);
}
outf.close();
inf.close();
delete buffer;
return 0;
}
|
