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
|
// Copyright Vespa.ai. Licensed under the terms of the Apache 2.0 license. See LICENSE in the project root.
/*
* Extract case information from Unicode property files.
* This program reads the UnicodeData-4.0.0.txt file and generates
* the unicodeutil-lowercase.cpp file that gives a mapping from
* unicode characters to their lowercase equivalents.
*
* Author: Tor Egge
* Author: Vidar Larsen
*/
#include <vespa/fastlib/io/bufferedfile.h>
unsigned int lowercase[65536];
int pages[256];
int pageoff[256];
char linebuf[1024];
static int hexval(char cp)
{
if (cp >= '0' && cp <= '9')
return cp - '0';
if (cp >= 'a' && cp <= 'f')
return cp - 'a' + 10;
if (cp >= 'A' && cp <= 'F')
return cp - 'A' + 10;
return -1;
}
void DumpCase(void)
{
Fast_BufferedFile file;
unsigned int code;
int xpage, checkpage, allocpage;
file.WriteOpen("unicodeutil-lowercase.cpp.NEW");
allocpage = 0;
for (xpage = 0; xpage < 256; xpage++) {
for (checkpage = (xpage == 0) ? 0 : 1; checkpage < xpage; checkpage++) {
for (code = 0; code < 256; code++)
if (lowercase[code + 256 * xpage] != lowercase[code + 256 * checkpage])
break;
if (code >= 256)
break;
}
pages[xpage] = checkpage;
if (checkpage >= xpage) {
pageoff[xpage] = allocpage * 256;
allocpage++;
} else
pageoff[xpage] = pageoff[checkpage];
}
printf("allocpage=%d\n", allocpage);
file.WriteString("/*\n"
" * This file is auto-generated by extcase.cpp\n"
" */\n"
"\n"
"static unsigned short Fast_intCompLowerCase[");
file.addNum(256 * allocpage, 0, ' ');
file.WriteString("]={\n");
for (xpage = 0; xpage < 256; xpage++) {
if (pages[xpage] == xpage) {
for (code = 0; code < 256; code++) {
if ((code & 7) == 0)
file.WriteString(" ");
file.WriteString("0x");
file.addHexNum(lowercase[code + 256 * xpage], 4, '0');
file.WriteString("u");
if (code + 1 < static_cast<unsigned int>(256 * allocpage))
file.WriteString(",");
if ((code & 7) < 7)
file.WriteString(" ");
else
file.WriteString("\n");
}
}
}
file.WriteString("};\n"
"\n"
"unsigned short *"
"Fast_UnicodeUtil::_compLowerCase[256]={\n");
for (xpage = 0; xpage < 256; xpage++) {
file.WriteString(" Fast_intCompLowerCase+0x");
file.addHexNum(pageoff[xpage], 4, '0');
if (xpage < 255)
file.WriteString(",");
else
file.WriteString(" ");
file.WriteString(" /* Page 0x");
file.addHexNum(xpage, 2, '0');
file.WriteString(" */\n");
}
file.WriteString("};\n"
"\n"
"/* End of auto-generated file */\n");
file.Close();
rename("unicodeutil-lowercase.cpp.NEW", "unicodeutil-lowercase.cpp");
}
int
main(int argc, char **argv)
{
(void)argc;
(void)argv;
Fast_BufferedFile file;
size_t len;
int lowcode, code, i, j;
bool badline;
int semcnt;
file.ReadOpenExisting("UnicodeData-4.0.0.txt");
while (!file.Eof()) {
(void) file.ReadLine(linebuf, sizeof(linebuf));
len = strlen(linebuf);
if (len > 0 && linebuf[len - 1] == '\n')
len--;
if (len > 0 && linebuf[len - 1] == '\r')
len--;
linebuf[len] = '\0';
badline = false;
if (hexval(linebuf[0]) >= 0) {
code = 0;
for (i = 0; i < 4; i++) {
if (hexval(linebuf[i]) < 0)
badline = true;
code = code * 16 + hexval(linebuf[i]);
}
if (linebuf[4] == ';') {
semcnt = 0;
i = 4;
while (linebuf[i] != '\0') {
if (linebuf[i] == ';') {
semcnt++;
}
i++;
if (semcnt >= 13)
break;
}
lowcode = 0;
if (hexval(linebuf[i]) >= 0) {
for (j = 0; j < 4; j++) {
if (hexval(linebuf[i + j]) < 0)
badline = true;
lowcode = lowcode * 16 + hexval(linebuf[i + j]);
}
} else
badline = true;
if (!badline) {
lowercase[code] = lowcode;
} else {
}
}
}
}
file.Close();
DumpCase();
return 0;
}
|
