Copy StringExtractor to StdStringExtractor.

I have some improvements to make to StringExtractor that require
using LLVM.  debugserver can't take a dependency on LLVM but uses
this file, so I'm forking it off into StdStringExtractor and
StringExtractor, so that StringExtractor can take advantage of
some performance improvements and readability improvements that
LLVM can provide.

llvm-svn: 279997
This commit is contained in:
Zachary Turner 2016-08-29 19:45:59 +00:00
parent 47ca88ace2
commit 44c35e80b1
6 changed files with 700 additions and 16 deletions

View File

@ -0,0 +1,181 @@
//===-- StdStringExtractor.h ------------------------------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#ifndef utility_StdStringExtractor_h_
#define utility_StdStringExtractor_h_
// C Includes
// C++ Includes
#include <string>
#include <stdint.h>
// Other libraries and framework includes
// Project includes
// Based on StringExtractor, with the added limitation that this file should not
// take a dependency on LLVM, as it is used from debugserver.
class StdStringExtractor
{
public:
enum {
BigEndian = 0,
LittleEndian = 1
};
//------------------------------------------------------------------
// Constructors and Destructors
//------------------------------------------------------------------
StdStringExtractor();
StdStringExtractor(const char *packet_cstr);
StdStringExtractor(const StdStringExtractor& rhs);
virtual ~StdStringExtractor();
//------------------------------------------------------------------
// Operators
//------------------------------------------------------------------
const StdStringExtractor&
operator=(const StdStringExtractor& rhs);
// Returns true if the file position is still valid for the data
// contained in this string extractor object.
bool
IsGood() const
{
return m_index != UINT64_MAX;
}
uint64_t
GetFilePos () const
{
return m_index;
}
void
SetFilePos (uint32_t idx)
{
m_index = idx;
}
void
Clear ()
{
m_packet.clear();
m_index = 0;
}
void
SkipSpaces ();
std::string &
GetStringRef ()
{
return m_packet;
}
const std::string &
GetStringRef () const
{
return m_packet;
}
bool
Empty()
{
return m_packet.empty();
}
size_t
GetBytesLeft ()
{
if (m_index < m_packet.size())
return m_packet.size() - m_index;
return 0;
}
char
GetChar (char fail_value = '\0');
char
PeekChar (char fail_value = '\0')
{
const char *cstr = Peek();
if (cstr)
return cstr[0];
return fail_value;
}
int
DecodeHexU8();
uint8_t
GetHexU8 (uint8_t fail_value = 0, bool set_eof_on_fail = true);
bool
GetHexU8Ex (uint8_t& ch, bool set_eof_on_fail = true);
bool
GetNameColonValue (std::string &name, std::string &value);
int32_t
GetS32 (int32_t fail_value, int base = 0);
uint32_t
GetU32 (uint32_t fail_value, int base = 0);
int64_t
GetS64 (int64_t fail_value, int base = 0);
uint64_t
GetU64 (uint64_t fail_value, int base = 0);
uint32_t
GetHexMaxU32 (bool little_endian, uint32_t fail_value);
uint64_t
GetHexMaxU64 (bool little_endian, uint64_t fail_value);
size_t
GetHexBytes (void *dst, size_t dst_len, uint8_t fail_fill_value);
size_t
GetHexBytesAvail (void *dst, size_t dst_len);
uint64_t
GetHexWithFixedSize (uint32_t byte_size, bool little_endian, uint64_t fail_value);
size_t
GetHexByteString (std::string &str);
size_t
GetHexByteStringFixedLength (std::string &str, uint32_t nibble_length);
size_t
GetHexByteStringTerminatedBy (std::string &str,
char terminator);
const char *
Peek ()
{
if (m_index < m_packet.size())
return m_packet.c_str() + m_index;
return nullptr;
}
protected:
//------------------------------------------------------------------
// For StdStringExtractor only
//------------------------------------------------------------------
std::string m_packet; // The string in which to extract data.
uint64_t m_index; // When extracting data from a packet, this index
// will march along as things get extracted. If set
// to UINT64_MAX the end of the packet data was
// reached when decoding information
};
#endif // utility_StringExtractor_h_

View File

@ -12,6 +12,7 @@ add_lldb_library(lldbUtility
RegisterNumber.cpp
SelectHelper.cpp
SharingPtr.cpp
StdStringExtractor.cpp
StringExtractor.cpp
StringExtractorGDBRemote.cpp
StringLexer.cpp

View File

@ -0,0 +1,502 @@
//===-- StdStringExtractor.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/StdStringExtractor.h"
// C Includes
#include <stdlib.h>
// C++ Includes
// Other libraries and framework includes
// Project includes
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;
}
//----------------------------------------------------------------------
// StdStringExtractor constructor
//----------------------------------------------------------------------
StdStringExtractor::StdStringExtractor() :
m_packet(),
m_index (0)
{
}
StdStringExtractor::StdStringExtractor(const char *packet_cstr) :
m_packet(),
m_index (0)
{
if (packet_cstr)
m_packet.assign (packet_cstr);
}
//----------------------------------------------------------------------
// StdStringExtractor copy constructor
//----------------------------------------------------------------------
StdStringExtractor::StdStringExtractor(const StdStringExtractor& rhs) :
m_packet (rhs.m_packet),
m_index (rhs.m_index)
{
}
//----------------------------------------------------------------------
// StdStringExtractor assignment operator
//----------------------------------------------------------------------
const StdStringExtractor&
StdStringExtractor::operator=(const StdStringExtractor& rhs)
{
if (this != &rhs)
{
m_packet = rhs.m_packet;
m_index = rhs.m_index;
}
return *this;
}
//----------------------------------------------------------------------
// Destructor
//----------------------------------------------------------------------
StdStringExtractor::~StdStringExtractor()
{
}
char
StdStringExtractor::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
// StdStringExtractor 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
// StdStringExtractor, it is left unchanged and -1 is returned
//----------------------------------------------------------------------
int
StdStringExtractor::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
StdStringExtractor::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
StdStringExtractor::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
StdStringExtractor::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
StdStringExtractor::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
StdStringExtractor::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
StdStringExtractor::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
StdStringExtractor::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
StdStringExtractor::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;
}
size_t
StdStringExtractor::GetHexBytes (void *dst_void, size_t dst_len, uint8_t fail_fill_value)
{
uint8_t *dst = (uint8_t*)dst_void;
size_t bytes_extracted = 0;
while (bytes_extracted < dst_len && GetBytesLeft ())
{
dst[bytes_extracted] = GetHexU8 (fail_fill_value);
if (IsGood())
++bytes_extracted;
else
break;
}
for (size_t i = bytes_extracted; i < dst_len; ++i)
dst[i] = fail_fill_value;
return bytes_extracted;
}
//----------------------------------------------------------------------
// Decodes all valid hex encoded bytes at the head of the
// StdStringExtractor, limited by dst_len.
//
// Returns the number of bytes successfully decoded
//----------------------------------------------------------------------
size_t
StdStringExtractor::GetHexBytesAvail (void *dst_void, size_t dst_len)
{
uint8_t *dst = (uint8_t*)dst_void;
size_t bytes_extracted = 0;
while (bytes_extracted < dst_len)
{
int decode = DecodeHexU8();
if (decode == -1)
{
break;
}
dst[bytes_extracted++] = (uint8_t)decode;
}
return bytes_extracted;
}
// Consume ASCII hex nibble character pairs until we have decoded byte_size
// bytes of data.
uint64_t
StdStringExtractor::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
StdStringExtractor::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
StdStringExtractor::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
StdStringExtractor::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
StdStringExtractor::GetNameColonValue (std::string &name, std::string &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())
{
const size_t colon_idx = m_packet.find (':', m_index);
if (colon_idx != std::string::npos)
{
const size_t semicolon_idx = m_packet.find (';', colon_idx);
if (semicolon_idx != std::string::npos)
{
name.assign (m_packet, m_index, colon_idx - m_index);
value.assign (m_packet, colon_idx + 1, semicolon_idx - (colon_idx + 1));
m_index = semicolon_idx + 1;
return true;
}
}
}
m_index = UINT64_MAX;
return false;
}
void
StdStringExtractor::SkipSpaces ()
{
const size_t n = m_packet.size();
while (m_index < n && isspace(m_packet[m_index]))
++m_index;
}

View File

@ -319,7 +319,7 @@ JSONArray::GetNumElements ()
JSONParser::JSONParser (const char *cstr) :
StringExtractor(cstr)
StdStringExtractor(cstr)
{
}

View File

@ -10,9 +10,9 @@
#ifndef utility_JSON_h_
#define utility_JSON_h_
// This cross-project usage is fine as StringExtractor.h is entirely
// This cross-project usage is fine as StdStringExtractor.h is entirely
// self-contained.
#include "lldb/Utility/StringExtractor.h"
#include "lldb/Utility/StdStringExtractor.h"
// C includes
#include <inttypes.h>
@ -338,7 +338,7 @@ public:
Vector m_elements;
};
class JSONParser : public StringExtractor
class JSONParser : public StdStringExtractor
{
public:
enum Token

View File

@ -38,7 +38,7 @@
#include "RNBServices.h"
#include "RNBSocket.h"
#include "JSON.h"
#include "lldb/Utility/StringExtractor.h"
#include "lldb/Utility/StdStringExtractor.h"
#include "MacOSX/Genealogy.h"
#include "JSONGenerator.h"
@ -2329,7 +2329,7 @@ RNBRemote::HandlePacket_QSetSTDIO (const char *p)
// QSetSTDIN
// QSetSTDOUT
// QSetSTDERR
StringExtractor packet(p);
StdStringExtractor packet(p);
packet.SetFilePos (7);
char ch = packet.GetChar();
while (packet.GetChar() != ':')
@ -2368,7 +2368,7 @@ RNBRemote::HandlePacket_QSetWorkingDir (const char *p)
// Only set the working directory if we don't already have a process
if (!m_ctx.HasValidProcessID())
{
StringExtractor packet(p += sizeof ("QSetWorkingDir:") - 1);
StdStringExtractor packet(p += sizeof ("QSetWorkingDir:") - 1);
if (packet.GetHexByteString (m_ctx.GetWorkingDir()))
{
struct stat working_dir_stat;
@ -3473,7 +3473,7 @@ RNBRemote::HandlePacket_G (const char *p)
if (g_num_reg_entries == 0)
InitializeRegisters ();
StringExtractor packet(p);
StdStringExtractor packet(p);
packet.SetFilePos(1); // Skip the 'G'
nub_process_t pid = m_ctx.ProcessID();
@ -3540,10 +3540,10 @@ RNBRemoteShouldCancelCallback (void *not_used)
rnb_err_t
RNBRemote::HandlePacket_AllocateMemory (const char *p)
{
StringExtractor packet (p);
StdStringExtractor packet (p);
packet.SetFilePos(2); // Skip the "_M"
nub_addr_t size = packet.GetHexMaxU64 (StringExtractor::BigEndian, 0);
nub_addr_t size = packet.GetHexMaxU64 (StdStringExtractor::BigEndian, 0);
if (size != 0)
{
if (packet.GetChar() == ',')
@ -3590,9 +3590,9 @@ RNBRemote::HandlePacket_AllocateMemory (const char *p)
rnb_err_t
RNBRemote::HandlePacket_DeallocateMemory (const char *p)
{
StringExtractor packet (p);
StdStringExtractor packet (p);
packet.SetFilePos(2); // Skip the "_m"
nub_addr_t addr = packet.GetHexMaxU64 (StringExtractor::BigEndian, INVALID_NUB_ADDRESS);
nub_addr_t addr = packet.GetHexMaxU64 (StdStringExtractor::BigEndian, INVALID_NUB_ADDRESS);
if (addr != INVALID_NUB_ADDRESS)
{
@ -3669,7 +3669,7 @@ RNBRemote::HandlePacket_RestoreRegisterState (const char *p)
return HandlePacket_ILLFORMED (__FILE__, __LINE__, p, "No thread was is set with the Hg packet");
}
StringExtractor packet (p);
StdStringExtractor packet (p);
packet.SetFilePos(strlen("QRestoreRegisterState:")); // Skip the "QRestoreRegisterState:"
const uint32_t save_id = packet.GetU32(0);
@ -4222,7 +4222,7 @@ RNBRemote::HandlePacket_P (const char *p)
nub_process_t pid = m_ctx.ProcessID();
StringExtractor packet (p);
StdStringExtractor packet (p);
const char cmd_char = packet.GetChar();
// Register ID is always in big endian
@ -4372,7 +4372,7 @@ RNBRemote::HandlePacket_GetProfileData (const char *p)
if (pid == INVALID_NUB_PROCESS)
return SendPacket ("OK");
StringExtractor packet(p += sizeof ("qGetProfileData"));
StdStringExtractor packet(p += sizeof ("qGetProfileData"));
DNBProfileDataScanType scan_type = eProfileAll;
std::string name;
std::string value;
@ -4408,7 +4408,7 @@ RNBRemote::HandlePacket_SetEnableAsyncProfiling (const char *p)
if (pid == INVALID_NUB_PROCESS)
return SendPacket ("OK");
StringExtractor packet(p += sizeof ("QSetEnableAsyncProfiling"));
StdStringExtractor packet(p += sizeof ("QSetEnableAsyncProfiling"));
bool enable = false;
uint64_t interval_usec = 0;
DNBProfileDataScanType scan_type = eProfileAll;