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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369
|
//===-- StringExtractor.cpp -----------------------------------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
#include "lldb/Utility/StringExtractor.h"
#include "llvm/ADT/StringExtras.h"
#include <tuple>
#include <cctype>
#include <cstdlib>
#include <cstring>
static inline int xdigit_to_sint(char ch) {
if (ch >= 'a' && ch <= 'f')
return 10 + ch - 'a';
if (ch >= 'A' && ch <= 'F')
return 10 + ch - 'A';
if (ch >= '0' && ch <= '9')
return ch - '0';
return -1;
}
// StringExtractor constructor
StringExtractor::StringExtractor() : m_packet() {}
StringExtractor::StringExtractor(llvm::StringRef packet_str) : m_packet() {
m_packet.assign(packet_str.begin(), packet_str.end());
}
StringExtractor::StringExtractor(const char *packet_cstr) : m_packet() {
if (packet_cstr)
m_packet.assign(packet_cstr);
}
// Destructor
StringExtractor::~StringExtractor() = default;
char StringExtractor::GetChar(char fail_value) {
if (m_index < m_packet.size()) {
char ch = m_packet[m_index];
++m_index;
return ch;
}
m_index = UINT64_MAX;
return fail_value;
}
// If a pair of valid hex digits exist at the head of the StringExtractor they
// are decoded into an unsigned byte and returned by this function
//
// If there is not a pair of valid hex digits at the head of the
// StringExtractor, it is left unchanged and -1 is returned
int StringExtractor::DecodeHexU8() {
SkipSpaces();
if (GetBytesLeft() < 2) {
return -1;
}
const int hi_nibble = xdigit_to_sint(m_packet[m_index]);
const int lo_nibble = xdigit_to_sint(m_packet[m_index + 1]);
if (hi_nibble == -1 || lo_nibble == -1) {
return -1;
}
m_index += 2;
return static_cast<uint8_t>((hi_nibble << 4) + lo_nibble);
}
// Extract an unsigned character from two hex ASCII chars in the packet string,
// or return fail_value on failure
uint8_t StringExtractor::GetHexU8(uint8_t fail_value, bool set_eof_on_fail) {
// On success, fail_value will be overwritten with the next character in the
// stream
GetHexU8Ex(fail_value, set_eof_on_fail);
return fail_value;
}
bool StringExtractor::GetHexU8Ex(uint8_t &ch, bool set_eof_on_fail) {
int byte = DecodeHexU8();
if (byte == -1) {
if (set_eof_on_fail || m_index >= m_packet.size())
m_index = UINT64_MAX;
// ch should not be changed in case of failure
return false;
}
ch = static_cast<uint8_t>(byte);
return true;
}
uint32_t StringExtractor::GetU32(uint32_t fail_value, int base) {
if (m_index < m_packet.size()) {
char *end = nullptr;
const char *start = m_packet.c_str();
const char *cstr = start + m_index;
uint32_t result = static_cast<uint32_t>(::strtoul(cstr, &end, base));
if (end && end != cstr) {
m_index = end - start;
return result;
}
}
return fail_value;
}
int32_t StringExtractor::GetS32(int32_t fail_value, int base) {
if (m_index < m_packet.size()) {
char *end = nullptr;
const char *start = m_packet.c_str();
const char *cstr = start + m_index;
int32_t result = static_cast<int32_t>(::strtol(cstr, &end, base));
if (end && end != cstr) {
m_index = end - start;
return result;
}
}
return fail_value;
}
uint64_t StringExtractor::GetU64(uint64_t fail_value, int base) {
if (m_index < m_packet.size()) {
char *end = nullptr;
const char *start = m_packet.c_str();
const char *cstr = start + m_index;
uint64_t result = ::strtoull(cstr, &end, base);
if (end && end != cstr) {
m_index = end - start;
return result;
}
}
return fail_value;
}
int64_t StringExtractor::GetS64(int64_t fail_value, int base) {
if (m_index < m_packet.size()) {
char *end = nullptr;
const char *start = m_packet.c_str();
const char *cstr = start + m_index;
int64_t result = ::strtoll(cstr, &end, base);
if (end && end != cstr) {
m_index = end - start;
return result;
}
}
return fail_value;
}
uint32_t StringExtractor::GetHexMaxU32(bool little_endian,
uint32_t fail_value) {
uint32_t result = 0;
uint32_t nibble_count = 0;
SkipSpaces();
if (little_endian) {
uint32_t shift_amount = 0;
while (m_index < m_packet.size() && ::isxdigit(m_packet[m_index])) {
// Make sure we don't exceed the size of a uint32_t...
if (nibble_count >= (sizeof(uint32_t) * 2)) {
m_index = UINT64_MAX;
return fail_value;
}
uint8_t nibble_lo;
uint8_t nibble_hi = xdigit_to_sint(m_packet[m_index]);
++m_index;
if (m_index < m_packet.size() && ::isxdigit(m_packet[m_index])) {
nibble_lo = xdigit_to_sint(m_packet[m_index]);
++m_index;
result |= (static_cast<uint32_t>(nibble_hi) << (shift_amount + 4));
result |= (static_cast<uint32_t>(nibble_lo) << shift_amount);
nibble_count += 2;
shift_amount += 8;
} else {
result |= (static_cast<uint32_t>(nibble_hi) << shift_amount);
nibble_count += 1;
shift_amount += 4;
}
}
} else {
while (m_index < m_packet.size() && ::isxdigit(m_packet[m_index])) {
// Make sure we don't exceed the size of a uint32_t...
if (nibble_count >= (sizeof(uint32_t) * 2)) {
m_index = UINT64_MAX;
return fail_value;
}
uint8_t nibble = xdigit_to_sint(m_packet[m_index]);
// Big Endian
result <<= 4;
result |= nibble;
++m_index;
++nibble_count;
}
}
return result;
}
uint64_t StringExtractor::GetHexMaxU64(bool little_endian,
uint64_t fail_value) {
uint64_t result = 0;
uint32_t nibble_count = 0;
SkipSpaces();
if (little_endian) {
uint32_t shift_amount = 0;
while (m_index < m_packet.size() && ::isxdigit(m_packet[m_index])) {
// Make sure we don't exceed the size of a uint64_t...
if (nibble_count >= (sizeof(uint64_t) * 2)) {
m_index = UINT64_MAX;
return fail_value;
}
uint8_t nibble_lo;
uint8_t nibble_hi = xdigit_to_sint(m_packet[m_index]);
++m_index;
if (m_index < m_packet.size() && ::isxdigit(m_packet[m_index])) {
nibble_lo = xdigit_to_sint(m_packet[m_index]);
++m_index;
result |= (static_cast<uint64_t>(nibble_hi) << (shift_amount + 4));
result |= (static_cast<uint64_t>(nibble_lo) << shift_amount);
nibble_count += 2;
shift_amount += 8;
} else {
result |= (static_cast<uint64_t>(nibble_hi) << shift_amount);
nibble_count += 1;
shift_amount += 4;
}
}
} else {
while (m_index < m_packet.size() && ::isxdigit(m_packet[m_index])) {
// Make sure we don't exceed the size of a uint64_t...
if (nibble_count >= (sizeof(uint64_t) * 2)) {
m_index = UINT64_MAX;
return fail_value;
}
uint8_t nibble = xdigit_to_sint(m_packet[m_index]);
// Big Endian
result <<= 4;
result |= nibble;
++m_index;
++nibble_count;
}
}
return result;
}
bool StringExtractor::ConsumeFront(const llvm::StringRef &str) {
llvm::StringRef S = GetStringRef();
if (!S.startswith(str))
return false;
else
m_index += str.size();
return true;
}
size_t StringExtractor::GetHexBytes(llvm::MutableArrayRef<uint8_t> dest,
uint8_t fail_fill_value) {
size_t bytes_extracted = 0;
while (!dest.empty() && GetBytesLeft() > 0) {
dest[0] = GetHexU8(fail_fill_value);
if (!IsGood())
break;
++bytes_extracted;
dest = dest.drop_front();
}
if (!dest.empty())
::memset(dest.data(), fail_fill_value, dest.size());
return bytes_extracted;
}
// Decodes all valid hex encoded bytes at the head of the StringExtractor,
// limited by dst_len.
//
// Returns the number of bytes successfully decoded
size_t StringExtractor::GetHexBytesAvail(llvm::MutableArrayRef<uint8_t> dest) {
size_t bytes_extracted = 0;
while (!dest.empty()) {
int decode = DecodeHexU8();
if (decode == -1)
break;
dest[0] = static_cast<uint8_t>(decode);
dest = dest.drop_front();
++bytes_extracted;
}
return bytes_extracted;
}
size_t StringExtractor::GetHexByteString(std::string &str) {
str.clear();
str.reserve(GetBytesLeft() / 2);
char ch;
while ((ch = GetHexU8()) != '\0')
str.append(1, ch);
return str.size();
}
size_t StringExtractor::GetHexByteStringFixedLength(std::string &str,
uint32_t nibble_length) {
str.clear();
uint32_t nibble_count = 0;
for (const char *pch = Peek();
(nibble_count < nibble_length) && (pch != nullptr);
str.append(1, GetHexU8(0, false)), pch = Peek(), nibble_count += 2) {
}
return str.size();
}
size_t StringExtractor::GetHexByteStringTerminatedBy(std::string &str,
char terminator) {
str.clear();
char ch;
while ((ch = GetHexU8(0, false)) != '\0')
str.append(1, ch);
if (Peek() && *Peek() == terminator)
return str.size();
str.clear();
return str.size();
}
bool StringExtractor::GetNameColonValue(llvm::StringRef &name,
llvm::StringRef &value) {
// Read something in the form of NNNN:VVVV; where NNNN is any character that
// is not a colon, followed by a ':' character, then a value (one or more ';'
// chars), followed by a ';'
if (m_index >= m_packet.size())
return fail();
llvm::StringRef view(m_packet);
if (view.empty())
return fail();
llvm::StringRef a, b, c, d;
view = view.substr(m_index);
std::tie(a, b) = view.split(':');
if (a.empty() || b.empty())
return fail();
std::tie(c, d) = b.split(';');
if (b == c && d.empty())
return fail();
name = a;
value = c;
if (d.empty())
m_index = m_packet.size();
else {
size_t bytes_consumed = d.data() - view.data();
m_index += bytes_consumed;
}
return true;
}
void StringExtractor::SkipSpaces() {
const size_t n = m_packet.size();
while (m_index < n && llvm::isSpace(m_packet[m_index]))
++m_index;
}
|