/usr/share/systemtap/runtime/stp_string.c is in systemtap-common 3.1-3ubuntu0.1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 | /* -*- linux-c -*-
* String Functions
* Copyright (C) 2005-2016 Red Hat Inc.
*
* This file is part of systemtap, and is free software. You can
* redistribute it and/or modify it under the terms of the GNU General
* Public License (GPL); either version 2, or (at your option) any
* later version.
*/
#ifndef _STP_STRING_C_
#define _STP_STRING_C_
#include "stp_string.h"
/** @file stp_string.c
* @brief Implements string functions.
*/
/** @addtogroup string String Functions
*
* @{
*/
/** Sprintf into a string.
* Like printf, except output goes into a string.
*
* NB: these are script language printf formatting directives, where
* %d ints are 64-bits etc, so we can't use gcc level attribute printf
* to type-check the arguments.
*
* @param str string
* @param fmt A printf-style format string followed by a
* variable number of args.
*/
static int _stp_snprintf(char *buf, size_t size, const char *fmt, ...)
{
va_list args;
int i;
va_start(args, fmt);
i = _stp_vsnprintf(buf,size,fmt,args);
va_end(args);
return i;
}
static int _stp_vscnprintf(char *buf, size_t size, const char *fmt, va_list args)
{
unsigned i = _stp_vsnprintf(buf,size,fmt,args);
return (i >= size) ? (size - 1) : i;
}
/**
* Decode a UTF-8 sequence into its codepoint.
*
* @param buf The input buffer.
* @param size The size of the input buffer.
* @param user Flag to mark user memory, vs kernel.
* @param c_ret The return pointer for the codepoint.
*
* @return The number of bytes consumed,
* or -EFAULT for unreadable memory address.
*/
static int _stp_decode_utf8(const char* buf, int size, int user, int* c_ret)
{
int c;
char b = '\0';
int i, n;
if (size <= 0)
return -EFAULT;
if (_stp_deref_nofault(b, 1, buf, (user ? USER_DS : KERNEL_DS)))
return -EFAULT;
++buf;
--size;
if ((b & 0xE0) == 0xC0 && size >= 1) {
/* 110xxxxx 10xxxxxx */
/* Two-byte UTF-8, one more byte to read. */
n = 2;
c = b & 0x1F;
} else if ((b & 0xF0) == 0xE0 && size >= 2) {
/* 1110xxxx 10xxxxxx 10xxxxxx */
/* Three-byte UTF-8, two more bytes to read. */
n = 3;
c = b & 0xF;
} else if ((b & 0xF8) == 0xF0 && size >= 3) {
/* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */
/* Four-byte UTF-8, three more bytes to read. */
n = 4;
c = b & 0x7;
} else {
/* Return everything else verbatim, whether it's ASCII, longer
* UTF-8 (against RFC 3629), invalid UTF-8, or just not enough
* bytes left in the input buffer. */
goto verbatim;
}
/* Mix in the UTF-8 continuation bytes. */
for (i = 1; i < n; ++i) {
char b2 = '\0';
if (_stp_deref_nofault(b2, 1, buf, (user ? USER_DS : KERNEL_DS)))
return -EFAULT;
++buf;
--size;
if ((b2 & 0xC0) != 0x80) /* Bad continuation. */
goto verbatim;
c = (c << 6) | (b2 & 0x3F);
}
/* Reject UTF-16 surrogates. */
if (0xD800 <= c && c <= 0xDFFF)
goto verbatim;
/* Reject values that exceed RFC 3629. */
if (c > 0x10FFFF)
goto verbatim;
/* Reject values that were encoded longer than necessary, so we don't
* hide that fact in our output. (e.g. 0xC0 0x80 -> 0!) */
if (c < 0x80 || (n == 3 && c < 0x800) || (n == 4 && c < 0x10000))
goto verbatim;
/* Successfully consumed the continuation bytes. */
*c_ret = c;
return n;
verbatim:
*c_ret = (unsigned char) b;
return 1;
}
/** Return a printable text string.
*
* Takes a string, and any ASCII characters that are not printable are
* replaced by the corresponding escape sequence in the returned
* string.
*
* @param outstr Output string pointer
* @param in Input string pointer
* @param inlen Maximum length of string to read not including terminating 0.
* @param outlen Maximum length of string to return not including terminating 0.
* 0 means MAXSTRINGLEN.
* @param quoted Put double quotes around the string. If input string is truncated
* in will have "..." after the second quote.
* @param user Set this to indicate the input string pointer is a userspace pointer.
*/
static int _stp_text_str(char *outstr, const char *in, int inlen, int outlen,
int quoted, int user, int buffer)
{
int c = 0;
char *out = outstr;
if (inlen <= 0 || inlen > MAXSTRINGLEN-1)
inlen = MAXSTRINGLEN-1;
if (outlen <= 0 || outlen > MAXSTRINGLEN-1)
outlen = MAXSTRINGLEN-1;
if (quoted) {
outlen = max(outlen, 5) - 2;
*out++ = '"';
}
while (inlen > 0) {
int num = 1;
int n = _stp_decode_utf8(in, inlen, user, &c);
if (n <= 0)
goto bad;
if ((c == 0 && !buffer) || outlen <= 0)
break;
in += n;
inlen -= n;
if (n > 1) {
/* UTF-8, print \uXXXX or \UXXXXXXXX */
int i;
num = (c <= 0xFFFF) ? 6 : 10;
if (outlen < num)
break;
*out++ = '\\';
*out++ = (c <= 0xFFFF) ? 'u' : 'U';
for (i = num - 3; i >= 0; --i) {
char nibble = (c >> (i * 4)) & 0xF;
*out++ = to_hex_digit(nibble);
}
}
else if (isascii(c) && isprint(c)
&& c != '"' && c != '\\') /* quoteworthy characters */
*out++ = c;
else {
switch (c) {
case '\0':
case '\a':
case '\b':
case '\f':
case '\n':
case '\r':
case '\t':
case '\v':
case '"':
case '\\':
num = 2; // "\c"
break;
default:
num = 4; // "\ooo"
break;
}
if (outlen < num)
break;
*out++ = '\\';
switch (c) {
case '\0':
*out++ = '0';
break;
case '\a':
*out++ = 'a';
break;
case '\b':
*out++ = 'b';
break;
case '\f':
*out++ = 'f';
break;
case '\n':
*out++ = 'n';
break;
case '\r':
*out++ = 'r';
break;
case '\t':
*out++ = 't';
break;
case '\v':
*out++ = 'v';
break;
case '"':
*out++ = '"';
break;
case '\\':
*out++ = '\\';
break;
default: /* output octal representation */
*out++ = to_oct_digit((c >> 6) & 03);
*out++ = to_oct_digit((c >> 3) & 07);
*out++ = to_oct_digit(c & 07);
break;
}
}
outlen -= num;
}
if (quoted) {
if (c && inlen > 0) {
out = out - 3 + outlen;
*out++ = '"';
*out++ = '.';
*out++ = '.';
*out++ = '.';
} else
*out++ = '"';
}
*out = '\0';
return 0;
bad:
strlcpy (outstr, "<unknown>", outlen);
return -1; // PR15044
}
/**
* Convert a UTF-32 character into a UTF-8 string.
*
* @param buf The output buffer.
* @param size The size of the output buffer.
* @param c The character to convert.
*
* @return The number of bytes written (not counting \0),
* 0 if there's not enough room for the full character,
* or < 0 for invalid characters (with buf untouched).
*/
static int _stp_convert_utf32(char* buf, int size, u32 c)
{
int i, n;
/* 0xxxxxxx */
if (c <= 0x7F)
n = 1;
/* 110xxxxx 10xxxxxx */
else if (c <= 0x7FF)
n = 2;
/* UTF-16 surrogates are not valid by themselves.
* XXX We could decide to be lax and just encode it anyway...
*/
else if (c >= 0xD800 && c <= 0xDFFF)
return -EINVAL;
/* 1110xxxx 10xxxxxx 10xxxxxx */
else if (c <= 0xFFFF)
n = 3;
/* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */
else if (c <= 0x10FFFF)
n = 4;
/* The original UTF-8 design could go up to 0x7FFFFFFF, but RFC 3629
* sets the upperbound to 0x10FFFF; thus all higher values are errors.
*/
else
return -EINVAL;
if (size < n + 1)
return 0;
buf[n] = '\0';
if (n == 1)
buf[0] = c;
else {
u8 msb = ((1 << n) - 1) << (8 - n);
for (i = n - 1; i > 0; --i) {
buf[i] = 0x80 | (c & 0x3F);
c >>= 6;
}
buf[0] = msb | c;
}
return n;
}
/** @} */
#endif /* _STP_STRING_C_ */
|