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
|
// go-encode-id.cc -- Go identifier encoding hooks
// Copyright 2016 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
#include "go-system.h"
#include "gogo.h"
#include "go-location.h"
#include "go-linemap.h"
#include "go-encode-id.h"
#include "lex.h"
// Return whether the character c is OK to use in the assembler. We
// only permit ASCII alphanumeric characters, underscore, and dot.
static bool
char_needs_encoding(char c)
{
switch (c)
{
case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
case 'G': case 'H': case 'I': case 'J': case 'K': case 'L':
case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R':
case 'S': case 'T': case 'U': case 'V': case 'W': case 'X':
case 'Y': case 'Z':
case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
case 'g': case 'h': case 'i': case 'j': case 'k': case 'l':
case 'm': case 'n': case 'o': case 'p': case 'q': case 'r':
case 's': case 't': case 'u': case 'v': case 'w': case 'x':
case 'y': case 'z':
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9':
case '_': case '.':
return false;
default:
return true;
}
}
// Return whether the identifier needs to be translated because it
// contains non-ASCII characters.
bool
go_id_needs_encoding(const std::string& str)
{
for (std::string::const_iterator p = str.begin();
p != str.end();
++p)
if (char_needs_encoding(*p))
return true;
return false;
}
// Pull the next UTF-8 character out of P and store it in *PC. Return
// the number of bytes read.
static size_t
fetch_utf8_char(const char* p, unsigned int* pc)
{
unsigned char c = *p;
if ((c & 0x80) == 0)
{
*pc = c;
return 1;
}
size_t len = 0;
while ((c & 0x80) != 0)
{
++len;
c <<= 1;
}
unsigned int rc = *p & ((1 << (7 - len)) - 1);
for (size_t i = 1; i < len; i++)
{
unsigned int u = p[i];
rc <<= 6;
rc |= u & 0x3f;
}
*pc = rc;
return len;
}
// Encode an identifier using ASCII characters. The encoding is
// described in detail near the end of the long comment at the start
// of names.cc. Short version: translate all non-ASCII-alphanumeric
// characters into ..uXXXX or ..UXXXXXXXX.
std::string
go_encode_id(const std::string &id)
{
if (Lex::is_invalid_identifier(id))
{
go_assert(saw_errors());
return id;
}
// The encoding is only unambiguous if the input string does not
// contain ..u or ..U.
go_assert(id.find("..u") == std::string::npos);
go_assert(id.find("..U") == std::string::npos);
std::string ret;
const char* p = id.c_str();
const char* pend = p + id.length();
// A leading ".0" is a space introduced before a mangled type name
// that starts with a 'u' or 'U', to avoid confusion with the
// mangling used here. We don't need a leading ".0", and we don't
// want symbols that start with '.', so remove it.
if (p[0] == '.' && p[1] == '0')
p += 2;
while (p < pend)
{
unsigned int c;
size_t len = fetch_utf8_char(p, &c);
if (len == 1)
{
// At this point we should only be seeing alphanumerics or
// underscore or dot.
go_assert(!char_needs_encoding(c));
ret += c;
}
else
{
char buf[16];
if (c < 0x10000)
snprintf(buf, sizeof buf, "..u%04x", c);
else
snprintf(buf, sizeof buf, "..U%08x", c);
// We don't want a symbol to start with '.', so add a prefix
// if needed.
if (ret.empty())
ret += '_';
ret += buf;
}
p += len;
}
return ret;
}
std::string
go_selectively_encode_id(const std::string &id)
{
if (go_id_needs_encoding(id))
return go_encode_id(id);
return std::string();
}
// Encode a struct field tag. This is only used when we need to
// create a type descriptor for an anonymous struct type with field
// tags. This mangling is applied before go_encode_id. We skip
// alphanumerics and underscore, replace every other single byte
// character with .xNN, and leave larger UTF-8 characters for
// go_encode_id.
std::string
go_mangle_struct_tag(const std::string& tag)
{
std::string ret;
const char* p = tag.c_str();
const char* pend = p + tag.length();
while (p < pend)
{
unsigned int c;
size_t len = fetch_utf8_char(p, &c);
if (len > 1)
ret.append(p, len);
else if (!char_needs_encoding(c) && c != '.')
ret += c;
else
{
char buf[16];
snprintf(buf, sizeof buf, ".x%02x", c);
ret += buf;
}
p += len;
}
return ret;
}
|
