llvm-project/lldb/source/Utility/StringExtractor.cpp

428 lines
12 KiB
C++
Raw Normal View History

//===-- StringExtractor.cpp -------------------------------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#include "lldb/Utility/StringExtractor.h"
#include <tuple>
#include <ctype.h> // for isxdigit, isspace
#include <stdlib.h>
#include <string.h> // for memset
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(), m_index(0) {}
StringExtractor::StringExtractor(llvm::StringRef packet_str)
: m_packet(), m_index(0) {
m_packet.assign(packet_str.begin(), packet_str.end());
}
StringExtractor::StringExtractor(const char *packet_cstr)
: m_packet(), m_index(0) {
if (packet_cstr)
m_packet.assign(packet_cstr);
}
//----------------------------------------------------------------------
// StringExtractor copy constructor
//----------------------------------------------------------------------
StringExtractor::StringExtractor(const StringExtractor &rhs)
: m_packet(rhs.m_packet), m_index(rhs.m_index) {}
//----------------------------------------------------------------------
// StringExtractor assignment operator
//----------------------------------------------------------------------
const StringExtractor &StringExtractor::operator=(const StringExtractor &rhs) {
if (this != &rhs) {
m_packet = rhs.m_packet;
m_index = rhs.m_index;
}
return *this;
}
//----------------------------------------------------------------------
// Destructor
//----------------------------------------------------------------------
StringExtractor::~StringExtractor() {}
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 (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 = (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;
Many improvements to the Platform base class and subclasses. The base Platform class now implements the Host functionality for a lot of things that make sense by default so that subclasses can check: int PlatformSubclass::Foo () { if (IsHost()) return Platform::Foo (); // Let the platform base class do the host specific stuff // Platform subclass specific code... int result = ... return result; } Added new functions to the platform: virtual const char *Platform::GetUserName (uint32_t uid); virtual const char *Platform::GetGroupName (uint32_t gid); The user and group names are cached locally so that remote platforms can avoid sending packets multiple times to resolve this information. Added the parent process ID to the ProcessInfo class. Added a new ProcessInfoMatch class which helps us to match processes up and changed the Host layer over to using this new class. The new class allows us to search for processs: 1 - by name (equal to, starts with, ends with, contains, and regex) 2 - by pid 3 - And further check for parent pid == value, uid == value, gid == value, euid == value, egid == value, arch == value, parent == value. This is all hookup up to the "platform process list" command which required adding dumping routines to dump process information. If the Host class implements the process lookup routines, you can now lists processes on your local machine: machine1.foo.com % lldb (lldb) platform process list PID PARENT USER GROUP EFF USER EFF GROUP TRIPLE NAME ====== ====== ========== ========== ========== ========== ======================== ============================ 99538 1 username usergroup username usergroup x86_64-apple-darwin FileMerge 94943 1 username usergroup username usergroup x86_64-apple-darwin mdworker 94852 244 username usergroup username usergroup x86_64-apple-darwin Safari 94727 244 username usergroup username usergroup x86_64-apple-darwin Xcode 92742 92710 username usergroup username usergroup i386-apple-darwin debugserver This of course also works remotely with the lldb-platform: machine1.foo.com % lldb-platform --listen 1234 machine2.foo.com % lldb (lldb) platform create remote-macosx Platform: remote-macosx Connected: no (lldb) platform connect connect://localhost:1444 Platform: remote-macosx Triple: x86_64-apple-darwin OS Version: 10.6.7 (10J869) Kernel: Darwin Kernel Version 10.7.0: Sat Jan 29 15:17:16 PST 2011; root:xnu-1504.9.37~1/RELEASE_I386 Hostname: machine1.foo.com Connected: yes (lldb) platform process list PID PARENT USER GROUP EFF USER EFF GROUP TRIPLE NAME ====== ====== ========== ========== ========== ========== ======================== ============================ 99556 244 username usergroup username usergroup x86_64-apple-darwin trustevaluation 99548 65539 username usergroup username usergroup x86_64-apple-darwin lldb 99538 1 username usergroup username usergroup x86_64-apple-darwin FileMerge 94943 1 username usergroup username usergroup x86_64-apple-darwin mdworker 94852 244 username usergroup username usergroup x86_64-apple-darwin Safari The lldb-platform implements everything with the Host:: layer, so this should "just work" for linux. I will probably be adding more stuff to the Host layer for launching processes and attaching to processes so that this support should eventually just work as well. Modified the target to be able to be created with an architecture that differs from the main executable. This is needed for iOS debugging since we can have an "armv6" binary which can run on an "armv7" machine, so we want to be able to do: % lldb (lldb) platform create remote-ios (lldb) file --arch armv7 a.out Where "a.out" is an armv6 executable. The platform then can correctly decide to open all "armv7" images for all dependent shared libraries. Modified the disassembly to show the current PC value. Example output: (lldb) disassemble --frame a.out`main: 0x1eb7: pushl %ebp 0x1eb8: movl %esp, %ebp 0x1eba: pushl %ebx 0x1ebb: subl $20, %esp 0x1ebe: calll 0x1ec3 ; main + 12 at test.c:18 0x1ec3: popl %ebx -> 0x1ec4: calll 0x1f12 ; getpid 0x1ec9: movl %eax, 4(%esp) 0x1ecd: leal 199(%ebx), %eax 0x1ed3: movl %eax, (%esp) 0x1ed6: calll 0x1f18 ; printf 0x1edb: leal 213(%ebx), %eax 0x1ee1: movl %eax, (%esp) 0x1ee4: calll 0x1f1e ; puts 0x1ee9: calll 0x1f0c ; getchar 0x1eee: movl $20, (%esp) 0x1ef5: calll 0x1e6a ; sleep_loop at test.c:6 0x1efa: movl $12, %eax 0x1eff: addl $20, %esp 0x1f02: popl %ebx 0x1f03: leave 0x1f04: ret This can be handy when dealing with the new --line options that was recently added: (lldb) disassemble --line a.out`main + 13 at test.c:19 18 { -> 19 printf("Process: %i\n\n", getpid()); 20 puts("Press any key to continue..."); getchar(); -> 0x1ec4: calll 0x1f12 ; getpid 0x1ec9: movl %eax, 4(%esp) 0x1ecd: leal 199(%ebx), %eax 0x1ed3: movl %eax, (%esp) 0x1ed6: calll 0x1f18 ; printf Modified the ModuleList to have a lookup based solely on a UUID. Since the UUID is typically the MD5 checksum of a binary image, there is no need to give the path and architecture when searching for a pre-existing image in an image list. Now that we support remote debugging a bit better, our lldb_private::Module needs to be able to track what the original path for file was as the platform knows it, as well as where the file is locally. The module has the two following functions to retrieve both paths: const FileSpec &Module::GetFileSpec () const; const FileSpec &Module::GetPlatformFileSpec () const; llvm-svn: 128563
2011-03-31 02:16:51 +08:00
}
}
return fail_value;
Many improvements to the Platform base class and subclasses. The base Platform class now implements the Host functionality for a lot of things that make sense by default so that subclasses can check: int PlatformSubclass::Foo () { if (IsHost()) return Platform::Foo (); // Let the platform base class do the host specific stuff // Platform subclass specific code... int result = ... return result; } Added new functions to the platform: virtual const char *Platform::GetUserName (uint32_t uid); virtual const char *Platform::GetGroupName (uint32_t gid); The user and group names are cached locally so that remote platforms can avoid sending packets multiple times to resolve this information. Added the parent process ID to the ProcessInfo class. Added a new ProcessInfoMatch class which helps us to match processes up and changed the Host layer over to using this new class. The new class allows us to search for processs: 1 - by name (equal to, starts with, ends with, contains, and regex) 2 - by pid 3 - And further check for parent pid == value, uid == value, gid == value, euid == value, egid == value, arch == value, parent == value. This is all hookup up to the "platform process list" command which required adding dumping routines to dump process information. If the Host class implements the process lookup routines, you can now lists processes on your local machine: machine1.foo.com % lldb (lldb) platform process list PID PARENT USER GROUP EFF USER EFF GROUP TRIPLE NAME ====== ====== ========== ========== ========== ========== ======================== ============================ 99538 1 username usergroup username usergroup x86_64-apple-darwin FileMerge 94943 1 username usergroup username usergroup x86_64-apple-darwin mdworker 94852 244 username usergroup username usergroup x86_64-apple-darwin Safari 94727 244 username usergroup username usergroup x86_64-apple-darwin Xcode 92742 92710 username usergroup username usergroup i386-apple-darwin debugserver This of course also works remotely with the lldb-platform: machine1.foo.com % lldb-platform --listen 1234 machine2.foo.com % lldb (lldb) platform create remote-macosx Platform: remote-macosx Connected: no (lldb) platform connect connect://localhost:1444 Platform: remote-macosx Triple: x86_64-apple-darwin OS Version: 10.6.7 (10J869) Kernel: Darwin Kernel Version 10.7.0: Sat Jan 29 15:17:16 PST 2011; root:xnu-1504.9.37~1/RELEASE_I386 Hostname: machine1.foo.com Connected: yes (lldb) platform process list PID PARENT USER GROUP EFF USER EFF GROUP TRIPLE NAME ====== ====== ========== ========== ========== ========== ======================== ============================ 99556 244 username usergroup username usergroup x86_64-apple-darwin trustevaluation 99548 65539 username usergroup username usergroup x86_64-apple-darwin lldb 99538 1 username usergroup username usergroup x86_64-apple-darwin FileMerge 94943 1 username usergroup username usergroup x86_64-apple-darwin mdworker 94852 244 username usergroup username usergroup x86_64-apple-darwin Safari The lldb-platform implements everything with the Host:: layer, so this should "just work" for linux. I will probably be adding more stuff to the Host layer for launching processes and attaching to processes so that this support should eventually just work as well. Modified the target to be able to be created with an architecture that differs from the main executable. This is needed for iOS debugging since we can have an "armv6" binary which can run on an "armv7" machine, so we want to be able to do: % lldb (lldb) platform create remote-ios (lldb) file --arch armv7 a.out Where "a.out" is an armv6 executable. The platform then can correctly decide to open all "armv7" images for all dependent shared libraries. Modified the disassembly to show the current PC value. Example output: (lldb) disassemble --frame a.out`main: 0x1eb7: pushl %ebp 0x1eb8: movl %esp, %ebp 0x1eba: pushl %ebx 0x1ebb: subl $20, %esp 0x1ebe: calll 0x1ec3 ; main + 12 at test.c:18 0x1ec3: popl %ebx -> 0x1ec4: calll 0x1f12 ; getpid 0x1ec9: movl %eax, 4(%esp) 0x1ecd: leal 199(%ebx), %eax 0x1ed3: movl %eax, (%esp) 0x1ed6: calll 0x1f18 ; printf 0x1edb: leal 213(%ebx), %eax 0x1ee1: movl %eax, (%esp) 0x1ee4: calll 0x1f1e ; puts 0x1ee9: calll 0x1f0c ; getchar 0x1eee: movl $20, (%esp) 0x1ef5: calll 0x1e6a ; sleep_loop at test.c:6 0x1efa: movl $12, %eax 0x1eff: addl $20, %esp 0x1f02: popl %ebx 0x1f03: leave 0x1f04: ret This can be handy when dealing with the new --line options that was recently added: (lldb) disassemble --line a.out`main + 13 at test.c:19 18 { -> 19 printf("Process: %i\n\n", getpid()); 20 puts("Press any key to continue..."); getchar(); -> 0x1ec4: calll 0x1f12 ; getpid 0x1ec9: movl %eax, 4(%esp) 0x1ecd: leal 199(%ebx), %eax 0x1ed3: movl %eax, (%esp) 0x1ed6: calll 0x1f18 ; printf Modified the ModuleList to have a lookup based solely on a UUID. Since the UUID is typically the MD5 checksum of a binary image, there is no need to give the path and architecture when searching for a pre-existing image in an image list. Now that we support remote debugging a bit better, our lldb_private::Module needs to be able to track what the original path for file was as the platform knows it, as well as where the file is locally. The module has the two following functions to retrieve both paths: const FileSpec &Module::GetFileSpec () const; const FileSpec &Module::GetPlatformFileSpec () const; llvm-svn: 128563
2011-03-31 02:16:51 +08:00
}
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 |= ((uint32_t)nibble_hi << (shift_amount + 4));
result |= ((uint32_t)nibble_lo << shift_amount);
nibble_count += 2;
shift_amount += 8;
} else {
result |= ((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 |= ((uint64_t)nibble_hi << (shift_amount + 4));
result |= ((uint64_t)nibble_lo << shift_amount);
nibble_count += 2;
shift_amount += 8;
} else {
result |= ((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] = (uint8_t)decode;
dest = dest.drop_front();
++bytes_extracted;
}
return bytes_extracted;
}
// Consume ASCII hex nibble character pairs until we have decoded byte_size
// bytes of data.
uint64_t StringExtractor::GetHexWithFixedSize(uint32_t byte_size,
bool little_endian,
uint64_t fail_value) {
if (byte_size <= 8 && GetBytesLeft() >= byte_size * 2) {
uint64_t result = 0;
uint32_t i;
if (little_endian) {
// Little Endian
uint32_t shift_amount;
for (i = 0, shift_amount = 0; i < byte_size && IsGood();
++i, shift_amount += 8) {
result |= ((uint64_t)GetHexU8() << shift_amount);
}
} else {
// Big Endian
for (i = 0; i < byte_size && IsGood(); ++i) {
result <<= 8;
result |= GetHexU8();
}
}
}
m_index = UINT64_MAX;
return fail_value;
}
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 && isspace(m_packet[m_index]))
++m_index;
}