forked from coolwanglu/pdf2htmlEX
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathunicode.cc
More file actions
157 lines (138 loc) · 3.28 KB
/
Copy pathunicode.cc
File metadata and controls
157 lines (138 loc) · 3.28 KB
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
/*
* Unicode manipulation functions
*
* by WangLu
* 2012.11.29
*/
#include <GlobalParams.h>
#include "unicode.h"
namespace pdf2htmlEX {
using std::cerr;
using std::endl;
using std::ostream;
bool isLegalUnicode(Unicode u)
{
/*
if((u == 9) || (u == 10) || (u == 13))
return true;
*/
if(u <= 31)
return false;
if((u >= 127) && (u <= 159))
return false;
if((u >= 0xd800) && (u <= 0xdfff))
return false;
return true;
}
Unicode map_to_private(CharCode code)
{
Unicode private_mapping = (Unicode)(code + 0xE000);
if(private_mapping > 0xF8FF)
{
private_mapping = (Unicode)((private_mapping - 0xF8FF) + 0xF0000);
if(private_mapping > 0xFFFFD)
{
private_mapping = (Unicode)((private_mapping - 0xFFFFD) + 0x100000);
if(private_mapping > 0x10FFFD)
{
cerr << "Warning: all private use unicode are used" << endl;
}
}
}
return private_mapping;
}
Unicode unicode_from_font (CharCode code, GfxFont * font)
{
if(!font->isCIDFont())
{
char * cname = dynamic_cast<Gfx8BitFont*>(font)->getCharName(code);
// may be untranslated ligature
if(cname)
{
Unicode ou = globalParams->mapNameToUnicode(cname);
if(isLegalUnicode(ou))
return ou;
}
}
return map_to_private(code);
}
Unicode check_unicode(Unicode * u, int len, CharCode code, GfxFont * font)
{
if(len == 0)
return map_to_private(code);
if(len == 1)
{
if(isLegalUnicode(*u))
return *u;
}
return unicode_from_font(code, font);
}
/*
* Copied from UTF.h / UTF8.h in poppler
*/
static int mapUTF8(Unicode u, char *buf, int bufSize) {
if (u <= 0x0000007f) {
if (bufSize < 1) {
return 0;
}
buf[0] = (char)u;
return 1;
} else if (u <= 0x000007ff) {
if (bufSize < 2) {
return 0;
}
buf[0] = (char)(0xc0 + (u >> 6));
buf[1] = (char)(0x80 + (u & 0x3f));
return 2;
} else if (u <= 0x0000ffff) {
if (bufSize < 3) {
return 0;
}
buf[0] = (char)(0xe0 + (u >> 12));
buf[1] = (char)(0x80 + ((u >> 6) & 0x3f));
buf[2] = (char)(0x80 + (u & 0x3f));
return 3;
} else if (u <= 0x0010ffff) {
if (bufSize < 4) {
return 0;
}
buf[0] = (char)(0xf0 + (u >> 18));
buf[1] = (char)(0x80 + ((u >> 12) & 0x3f));
buf[2] = (char)(0x80 + ((u >> 6) & 0x3f));
buf[3] = (char)(0x80 + (u & 0x3f));
return 4;
} else {
return 0;
}
}
void outputUnicodes(ostream & out, const Unicode * u, int uLen)
{
for(int i = 0; i < uLen; ++i)
{
switch(u[i])
{
case '&':
out << "&";
break;
case '\"':
out << """;
break;
case '\'':
out << "'";
break;
case '<':
out << "<";
break;
case '>':
out << ">";
break;
default:
{
char buf[4];
auto n = mapUTF8(u[i], buf, 4);
out.write(buf, n);
}
}
}
}
} //namespace pdf2htmlEX