forked from hush/hush3
zanzibar
3 years ago
4 changed files with 975 additions and 0 deletions
@ -0,0 +1,605 @@ |
|||
// Copyright (c) 2009-2010 Satoshi Nakamoto
|
|||
// Copyright (c) 2009-2020 The Bitcoin Core developers
|
|||
// Distributed under the MIT software license, see the accompanying
|
|||
// file COPYING or http://www.opensource.org/licenses/mit-license.php.
|
|||
|
|||
#include <util/strencodings.h> |
|||
#include <util/string.h> |
|||
|
|||
#include <tinyformat.h> |
|||
|
|||
#include <algorithm> |
|||
#include <cstdlib> |
|||
#include <cstring> |
|||
#include <errno.h> |
|||
#include <limits> |
|||
|
|||
static const std::string CHARS_ALPHA_NUM = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789"; |
|||
|
|||
static const std::string SAFE_CHARS[] = |
|||
{ |
|||
CHARS_ALPHA_NUM + " .,;-_/:?@()", // SAFE_CHARS_DEFAULT
|
|||
CHARS_ALPHA_NUM + " .,;-_?@", // SAFE_CHARS_UA_COMMENT
|
|||
CHARS_ALPHA_NUM + ".-_", // SAFE_CHARS_FILENAME
|
|||
CHARS_ALPHA_NUM + "!*'();:@&=+$,/?#[]-_.~%", // SAFE_CHARS_URI
|
|||
}; |
|||
|
|||
std::string SanitizeString(const std::string& str, int rule) |
|||
{ |
|||
std::string strResult; |
|||
for (std::string::size_type i = 0; i < str.size(); i++) |
|||
{ |
|||
if (SAFE_CHARS[rule].find(str[i]) != std::string::npos) |
|||
strResult.push_back(str[i]); |
|||
} |
|||
return strResult; |
|||
} |
|||
|
|||
const signed char p_util_hexdigit[256] = |
|||
{ -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1, |
|||
-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1, |
|||
-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1, |
|||
0,1,2,3,4,5,6,7,8,9,-1,-1,-1,-1,-1,-1, |
|||
-1,0xa,0xb,0xc,0xd,0xe,0xf,-1,-1,-1,-1,-1,-1,-1,-1,-1, |
|||
-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1, |
|||
-1,0xa,0xb,0xc,0xd,0xe,0xf,-1,-1,-1,-1,-1,-1,-1,-1,-1, |
|||
-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1, |
|||
-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1, |
|||
-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1, |
|||
-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1, |
|||
-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1, |
|||
-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1, |
|||
-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1, |
|||
-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1, |
|||
-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1, }; |
|||
|
|||
signed char HexDigit(char c) |
|||
{ |
|||
return p_util_hexdigit[(unsigned char)c]; |
|||
} |
|||
|
|||
bool IsHex(const std::string& str) |
|||
{ |
|||
for(std::string::const_iterator it(str.begin()); it != str.end(); ++it) |
|||
{ |
|||
if (HexDigit(*it) < 0) |
|||
return false; |
|||
} |
|||
return (str.size() > 0) && (str.size()%2 == 0); |
|||
} |
|||
|
|||
bool IsHexNumber(const std::string& str) |
|||
{ |
|||
size_t starting_location = 0; |
|||
if (str.size() > 2 && *str.begin() == '0' && *(str.begin()+1) == 'x') { |
|||
starting_location = 2; |
|||
} |
|||
for (const char c : str.substr(starting_location)) { |
|||
if (HexDigit(c) < 0) return false; |
|||
} |
|||
// Return false for empty string or "0x".
|
|||
return (str.size() > starting_location); |
|||
} |
|||
|
|||
std::vector<unsigned char> ParseHex(const char* psz) |
|||
{ |
|||
// convert hex dump to vector
|
|||
std::vector<unsigned char> vch; |
|||
while (true) |
|||
{ |
|||
while (IsSpace(*psz)) |
|||
psz++; |
|||
signed char c = HexDigit(*psz++); |
|||
if (c == (signed char)-1) |
|||
break; |
|||
unsigned char n = (c << 4); |
|||
c = HexDigit(*psz++); |
|||
if (c == (signed char)-1) |
|||
break; |
|||
n |= c; |
|||
vch.push_back(n); |
|||
} |
|||
return vch; |
|||
} |
|||
|
|||
std::vector<unsigned char> ParseHex(const std::string& str) |
|||
{ |
|||
return ParseHex(str.c_str()); |
|||
} |
|||
|
|||
void SplitHostPort(std::string in, uint16_t& portOut, std::string& hostOut) |
|||
{ |
|||
size_t colon = in.find_last_of(':'); |
|||
// if a : is found, and it either follows a [...], or no other : is in the string, treat it as port separator
|
|||
bool fHaveColon = colon != in.npos; |
|||
bool fBracketed = fHaveColon && (in[0] == '[' && in[colon - 1] == ']'); // if there is a colon, and in[0]=='[', colon is not 0, so in[colon-1] is safe
|
|||
bool fMultiColon = fHaveColon && (in.find_last_of(':', colon - 1) != in.npos); |
|||
if (fHaveColon && (colon == 0 || fBracketed || !fMultiColon)) { |
|||
uint16_t n; |
|||
if (ParseUInt16(in.substr(colon + 1), &n)) { |
|||
in = in.substr(0, colon); |
|||
portOut = n; |
|||
} |
|||
} |
|||
if (in.size() > 0 && in[0] == '[' && in[in.size() - 1] == ']') { |
|||
hostOut = in.substr(1, in.size() - 2); |
|||
} else { |
|||
hostOut = in; |
|||
} |
|||
} |
|||
|
|||
std::string EncodeBase64(Span<const unsigned char> input) |
|||
{ |
|||
static const char *pbase64 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"; |
|||
|
|||
std::string str; |
|||
str.reserve(((input.size() + 2) / 3) * 4); |
|||
ConvertBits<8, 6, true>([&](int v) { str += pbase64[v]; }, input.begin(), input.end()); |
|||
while (str.size() % 4) str += '='; |
|||
return str; |
|||
} |
|||
|
|||
std::string EncodeBase64(const std::string& str) |
|||
{ |
|||
return EncodeBase64(MakeUCharSpan(str)); |
|||
} |
|||
|
|||
std::vector<unsigned char> DecodeBase64(const char* p, bool* pf_invalid) |
|||
{ |
|||
static const int decode64_table[256] = |
|||
{ |
|||
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, |
|||
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, |
|||
-1, -1, -1, 62, -1, -1, -1, 63, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, -1, -1, |
|||
-1, -1, -1, -1, -1, 0, 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, -1, -1, -1, -1, -1, -1, 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, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, |
|||
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, |
|||
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, |
|||
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, |
|||
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, |
|||
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, |
|||
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 |
|||
}; |
|||
|
|||
const char* e = p; |
|||
std::vector<uint8_t> val; |
|||
val.reserve(strlen(p)); |
|||
while (*p != 0) { |
|||
int x = decode64_table[(unsigned char)*p]; |
|||
if (x == -1) break; |
|||
val.push_back(x); |
|||
++p; |
|||
} |
|||
|
|||
std::vector<unsigned char> ret; |
|||
ret.reserve((val.size() * 3) / 4); |
|||
bool valid = ConvertBits<6, 8, false>([&](unsigned char c) { ret.push_back(c); }, val.begin(), val.end()); |
|||
|
|||
const char* q = p; |
|||
while (valid && *p != 0) { |
|||
if (*p != '=') { |
|||
valid = false; |
|||
break; |
|||
} |
|||
++p; |
|||
} |
|||
valid = valid && (p - e) % 4 == 0 && p - q < 4; |
|||
if (pf_invalid) *pf_invalid = !valid; |
|||
|
|||
return ret; |
|||
} |
|||
|
|||
std::string DecodeBase64(const std::string& str, bool* pf_invalid) |
|||
{ |
|||
if (!ValidAsCString(str)) { |
|||
if (pf_invalid) { |
|||
*pf_invalid = true; |
|||
} |
|||
return {}; |
|||
} |
|||
std::vector<unsigned char> vchRet = DecodeBase64(str.c_str(), pf_invalid); |
|||
return std::string((const char*)vchRet.data(), vchRet.size()); |
|||
} |
|||
|
|||
std::string EncodeBase32(Span<const unsigned char> input, bool pad) |
|||
{ |
|||
static const char *pbase32 = "abcdefghijklmnopqrstuvwxyz234567"; |
|||
|
|||
std::string str; |
|||
str.reserve(((input.size() + 4) / 5) * 8); |
|||
ConvertBits<8, 5, true>([&](int v) { str += pbase32[v]; }, input.begin(), input.end()); |
|||
if (pad) { |
|||
while (str.size() % 8) { |
|||
str += '='; |
|||
} |
|||
} |
|||
return str; |
|||
} |
|||
|
|||
std::string EncodeBase32(const std::string& str, bool pad) |
|||
{ |
|||
return EncodeBase32(MakeUCharSpan(str), pad); |
|||
} |
|||
|
|||
std::vector<unsigned char> DecodeBase32(const char* p, bool* pf_invalid) |
|||
{ |
|||
static const int decode32_table[256] = |
|||
{ |
|||
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, |
|||
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, |
|||
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 26, 27, 28, 29, 30, 31, -1, -1, -1, -1, |
|||
-1, -1, -1, -1, -1, 0, 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, -1, -1, -1, -1, -1, -1, 0, 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, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, |
|||
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, |
|||
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, |
|||
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, |
|||
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, |
|||
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, |
|||
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 |
|||
}; |
|||
|
|||
const char* e = p; |
|||
std::vector<uint8_t> val; |
|||
val.reserve(strlen(p)); |
|||
while (*p != 0) { |
|||
int x = decode32_table[(unsigned char)*p]; |
|||
if (x == -1) break; |
|||
val.push_back(x); |
|||
++p; |
|||
} |
|||
|
|||
std::vector<unsigned char> ret; |
|||
ret.reserve((val.size() * 5) / 8); |
|||
bool valid = ConvertBits<5, 8, false>([&](unsigned char c) { ret.push_back(c); }, val.begin(), val.end()); |
|||
|
|||
const char* q = p; |
|||
while (valid && *p != 0) { |
|||
if (*p != '=') { |
|||
valid = false; |
|||
break; |
|||
} |
|||
++p; |
|||
} |
|||
valid = valid && (p - e) % 8 == 0 && p - q < 8; |
|||
if (pf_invalid) *pf_invalid = !valid; |
|||
|
|||
return ret; |
|||
} |
|||
|
|||
std::string DecodeBase32(const std::string& str, bool* pf_invalid) |
|||
{ |
|||
if (!ValidAsCString(str)) { |
|||
if (pf_invalid) { |
|||
*pf_invalid = true; |
|||
} |
|||
return {}; |
|||
} |
|||
std::vector<unsigned char> vchRet = DecodeBase32(str.c_str(), pf_invalid); |
|||
return std::string((const char*)vchRet.data(), vchRet.size()); |
|||
} |
|||
|
|||
[[nodiscard]] static bool ParsePrechecks(const std::string& str) |
|||
{ |
|||
if (str.empty()) // No empty string allowed
|
|||
return false; |
|||
if (str.size() >= 1 && (IsSpace(str[0]) || IsSpace(str[str.size()-1]))) // No padding allowed
|
|||
return false; |
|||
if (!ValidAsCString(str)) // No embedded NUL characters allowed
|
|||
return false; |
|||
return true; |
|||
} |
|||
|
|||
bool ParseInt32(const std::string& str, int32_t *out) |
|||
{ |
|||
if (!ParsePrechecks(str)) |
|||
return false; |
|||
char *endp = nullptr; |
|||
errno = 0; // strtol will not set errno if valid
|
|||
long int n = strtol(str.c_str(), &endp, 10); |
|||
if(out) *out = (int32_t)n; |
|||
// Note that strtol returns a *long int*, so even if strtol doesn't report an over/underflow
|
|||
// we still have to check that the returned value is within the range of an *int32_t*. On 64-bit
|
|||
// platforms the size of these types may be different.
|
|||
return endp && *endp == 0 && !errno && |
|||
n >= std::numeric_limits<int32_t>::min() && |
|||
n <= std::numeric_limits<int32_t>::max(); |
|||
} |
|||
|
|||
bool ParseInt64(const std::string& str, int64_t *out) |
|||
{ |
|||
if (!ParsePrechecks(str)) |
|||
return false; |
|||
char *endp = nullptr; |
|||
errno = 0; // strtoll will not set errno if valid
|
|||
long long int n = strtoll(str.c_str(), &endp, 10); |
|||
if(out) *out = (int64_t)n; |
|||
// Note that strtoll returns a *long long int*, so even if strtol doesn't report an over/underflow
|
|||
// we still have to check that the returned value is within the range of an *int64_t*.
|
|||
return endp && *endp == 0 && !errno && |
|||
n >= std::numeric_limits<int64_t>::min() && |
|||
n <= std::numeric_limits<int64_t>::max(); |
|||
} |
|||
|
|||
bool ParseUInt8(const std::string& str, uint8_t *out) |
|||
{ |
|||
uint32_t u32; |
|||
if (!ParseUInt32(str, &u32) || u32 > std::numeric_limits<uint8_t>::max()) { |
|||
return false; |
|||
} |
|||
if (out != nullptr) { |
|||
*out = static_cast<uint8_t>(u32); |
|||
} |
|||
return true; |
|||
} |
|||
|
|||
bool ParseUInt16(const std::string& str, uint16_t* out) |
|||
{ |
|||
uint32_t u32; |
|||
if (!ParseUInt32(str, &u32) || u32 > std::numeric_limits<uint16_t>::max()) { |
|||
return false; |
|||
} |
|||
if (out != nullptr) { |
|||
*out = static_cast<uint16_t>(u32); |
|||
} |
|||
return true; |
|||
} |
|||
|
|||
bool ParseUInt32(const std::string& str, uint32_t *out) |
|||
{ |
|||
if (!ParsePrechecks(str)) |
|||
return false; |
|||
if (str.size() >= 1 && str[0] == '-') // Reject negative values, unfortunately strtoul accepts these by default if they fit in the range
|
|||
return false; |
|||
char *endp = nullptr; |
|||
errno = 0; // strtoul will not set errno if valid
|
|||
unsigned long int n = strtoul(str.c_str(), &endp, 10); |
|||
if(out) *out = (uint32_t)n; |
|||
// Note that strtoul returns a *unsigned long int*, so even if it doesn't report an over/underflow
|
|||
// we still have to check that the returned value is within the range of an *uint32_t*. On 64-bit
|
|||
// platforms the size of these types may be different.
|
|||
return endp && *endp == 0 && !errno && |
|||
n <= std::numeric_limits<uint32_t>::max(); |
|||
} |
|||
|
|||
bool ParseUInt64(const std::string& str, uint64_t *out) |
|||
{ |
|||
if (!ParsePrechecks(str)) |
|||
return false; |
|||
if (str.size() >= 1 && str[0] == '-') // Reject negative values, unfortunately strtoull accepts these by default if they fit in the range
|
|||
return false; |
|||
char *endp = nullptr; |
|||
errno = 0; // strtoull will not set errno if valid
|
|||
unsigned long long int n = strtoull(str.c_str(), &endp, 10); |
|||
if(out) *out = (uint64_t)n; |
|||
// Note that strtoull returns a *unsigned long long int*, so even if it doesn't report an over/underflow
|
|||
// we still have to check that the returned value is within the range of an *uint64_t*.
|
|||
return endp && *endp == 0 && !errno && |
|||
n <= std::numeric_limits<uint64_t>::max(); |
|||
} |
|||
|
|||
|
|||
bool ParseDouble(const std::string& str, double *out) |
|||
{ |
|||
if (!ParsePrechecks(str)) |
|||
return false; |
|||
if (str.size() >= 2 && str[0] == '0' && str[1] == 'x') // No hexadecimal floats allowed
|
|||
return false; |
|||
std::istringstream text(str); |
|||
text.imbue(std::locale::classic()); |
|||
double result; |
|||
text >> result; |
|||
if(out) *out = result; |
|||
return text.eof() && !text.fail(); |
|||
} |
|||
|
|||
std::string FormatParagraph(const std::string& in, size_t width, size_t indent) |
|||
{ |
|||
std::stringstream out; |
|||
size_t ptr = 0; |
|||
size_t indented = 0; |
|||
while (ptr < in.size()) |
|||
{ |
|||
size_t lineend = in.find_first_of('\n', ptr); |
|||
if (lineend == std::string::npos) { |
|||
lineend = in.size(); |
|||
} |
|||
const size_t linelen = lineend - ptr; |
|||
const size_t rem_width = width - indented; |
|||
if (linelen <= rem_width) { |
|||
out << in.substr(ptr, linelen + 1); |
|||
ptr = lineend + 1; |
|||
indented = 0; |
|||
} else { |
|||
size_t finalspace = in.find_last_of(" \n", ptr + rem_width); |
|||
if (finalspace == std::string::npos || finalspace < ptr) { |
|||
// No place to break; just include the entire word and move on
|
|||
finalspace = in.find_first_of("\n ", ptr); |
|||
if (finalspace == std::string::npos) { |
|||
// End of the string, just add it and break
|
|||
out << in.substr(ptr); |
|||
break; |
|||
} |
|||
} |
|||
out << in.substr(ptr, finalspace - ptr) << "\n"; |
|||
if (in[finalspace] == '\n') { |
|||
indented = 0; |
|||
} else if (indent) { |
|||
out << std::string(indent, ' '); |
|||
indented = indent; |
|||
} |
|||
ptr = finalspace + 1; |
|||
} |
|||
} |
|||
return out.str(); |
|||
} |
|||
|
|||
int64_t atoi64(const std::string& str) |
|||
{ |
|||
#ifdef _MSC_VER |
|||
return _atoi64(str.c_str()); |
|||
#else |
|||
return strtoll(str.c_str(), nullptr, 10); |
|||
#endif |
|||
} |
|||
|
|||
int atoi(const std::string& str) |
|||
{ |
|||
return atoi(str.c_str()); |
|||
} |
|||
|
|||
/** Upper bound for mantissa.
|
|||
* 10^18-1 is the largest arbitrary decimal that will fit in a signed 64-bit integer. |
|||
* Larger integers cannot consist of arbitrary combinations of 0-9: |
|||
* |
|||
* 999999999999999999 1^18-1 |
|||
* 9223372036854775807 (1<<63)-1 (max int64_t) |
|||
* 9999999999999999999 1^19-1 (would overflow) |
|||
*/ |
|||
static const int64_t UPPER_BOUND = 1000000000000000000LL - 1LL; |
|||
|
|||
/** Helper function for ParseFixedPoint */ |
|||
static inline bool ProcessMantissaDigit(char ch, int64_t &mantissa, int &mantissa_tzeros) |
|||
{ |
|||
if(ch == '0') |
|||
++mantissa_tzeros; |
|||
else { |
|||
for (int i=0; i<=mantissa_tzeros; ++i) { |
|||
if (mantissa > (UPPER_BOUND / 10LL)) |
|||
return false; /* overflow */ |
|||
mantissa *= 10; |
|||
} |
|||
mantissa += ch - '0'; |
|||
mantissa_tzeros = 0; |
|||
} |
|||
return true; |
|||
} |
|||
|
|||
bool ParseFixedPoint(const std::string &val, int decimals, int64_t *amount_out) |
|||
{ |
|||
int64_t mantissa = 0; |
|||
int64_t exponent = 0; |
|||
int mantissa_tzeros = 0; |
|||
bool mantissa_sign = false; |
|||
bool exponent_sign = false; |
|||
int ptr = 0; |
|||
int end = val.size(); |
|||
int point_ofs = 0; |
|||
|
|||
if (ptr < end && val[ptr] == '-') { |
|||
mantissa_sign = true; |
|||
++ptr; |
|||
} |
|||
if (ptr < end) |
|||
{ |
|||
if (val[ptr] == '0') { |
|||
/* pass single 0 */ |
|||
++ptr; |
|||
} else if (val[ptr] >= '1' && val[ptr] <= '9') { |
|||
while (ptr < end && IsDigit(val[ptr])) { |
|||
if (!ProcessMantissaDigit(val[ptr], mantissa, mantissa_tzeros)) |
|||
return false; /* overflow */ |
|||
++ptr; |
|||
} |
|||
} else return false; /* missing expected digit */ |
|||
} else return false; /* empty string or loose '-' */ |
|||
if (ptr < end && val[ptr] == '.') |
|||
{ |
|||
++ptr; |
|||
if (ptr < end && IsDigit(val[ptr])) |
|||
{ |
|||
while (ptr < end && IsDigit(val[ptr])) { |
|||
if (!ProcessMantissaDigit(val[ptr], mantissa, mantissa_tzeros)) |
|||
return false; /* overflow */ |
|||
++ptr; |
|||
++point_ofs; |
|||
} |
|||
} else return false; /* missing expected digit */ |
|||
} |
|||
if (ptr < end && (val[ptr] == 'e' || val[ptr] == 'E')) |
|||
{ |
|||
++ptr; |
|||
if (ptr < end && val[ptr] == '+') |
|||
++ptr; |
|||
else if (ptr < end && val[ptr] == '-') { |
|||
exponent_sign = true; |
|||
++ptr; |
|||
} |
|||
if (ptr < end && IsDigit(val[ptr])) { |
|||
while (ptr < end && IsDigit(val[ptr])) { |
|||
if (exponent > (UPPER_BOUND / 10LL)) |
|||
return false; /* overflow */ |
|||
exponent = exponent * 10 + val[ptr] - '0'; |
|||
++ptr; |
|||
} |
|||
} else return false; /* missing expected digit */ |
|||
} |
|||
if (ptr != end) |
|||
return false; /* trailing garbage */ |
|||
|
|||
/* finalize exponent */ |
|||
if (exponent_sign) |
|||
exponent = -exponent; |
|||
exponent = exponent - point_ofs + mantissa_tzeros; |
|||
|
|||
/* finalize mantissa */ |
|||
if (mantissa_sign) |
|||
mantissa = -mantissa; |
|||
|
|||
/* convert to one 64-bit fixed-point value */ |
|||
exponent += decimals; |
|||
if (exponent < 0) |
|||
return false; /* cannot represent values smaller than 10^-decimals */ |
|||
if (exponent >= 18) |
|||
return false; /* cannot represent values larger than or equal to 10^(18-decimals) */ |
|||
|
|||
for (int i=0; i < exponent; ++i) { |
|||
if (mantissa > (UPPER_BOUND / 10LL) || mantissa < -(UPPER_BOUND / 10LL)) |
|||
return false; /* overflow */ |
|||
mantissa *= 10; |
|||
} |
|||
if (mantissa > UPPER_BOUND || mantissa < -UPPER_BOUND) |
|||
return false; /* overflow */ |
|||
|
|||
if (amount_out) |
|||
*amount_out = mantissa; |
|||
|
|||
return true; |
|||
} |
|||
|
|||
std::string ToLower(const std::string& str) |
|||
{ |
|||
std::string r; |
|||
for (auto ch : str) r += ToLower((unsigned char)ch); |
|||
return r; |
|||
} |
|||
|
|||
std::string ToUpper(const std::string& str) |
|||
{ |
|||
std::string r; |
|||
for (auto ch : str) r += ToUpper((unsigned char)ch); |
|||
return r; |
|||
} |
|||
|
|||
std::string Capitalize(std::string str) |
|||
{ |
|||
if (str.empty()) return str; |
|||
str[0] = ToUpper(str.front()); |
|||
return str; |
|||
} |
|||
|
|||
std::string HexStr(const Span<const uint8_t> s) |
|||
{ |
|||
std::string rv; |
|||
static constexpr char hexmap[16] = { '0', '1', '2', '3', '4', '5', '6', '7', |
|||
'8', '9', 'a', 'b', 'c', 'd', 'e', 'f' }; |
|||
rv.reserve(s.size() * 2); |
|||
for (uint8_t v: s) { |
|||
rv.push_back(hexmap[v >> 4]); |
|||
rv.push_back(hexmap[v & 15]); |
|||
} |
|||
return rv; |
|||
} |
|||
@ -0,0 +1,267 @@ |
|||
// Copyright (c) 2009-2010 Satoshi Nakamoto
|
|||
// Copyright (c) 2009-2020 The Bitcoin Core developers
|
|||
// Distributed under the MIT software license, see the accompanying
|
|||
// file COPYING or http://www.opensource.org/licenses/mit-license.php.
|
|||
|
|||
/**
|
|||
* Utilities for converting data from/to strings. |
|||
*/ |
|||
#ifndef BITCOIN_UTIL_STRENCODINGS_H |
|||
#define BITCOIN_UTIL_STRENCODINGS_H |
|||
|
|||
#include <attributes.h> |
|||
#include <span.h> |
|||
|
|||
#include <cstdint> |
|||
#include <iterator> |
|||
#include <string> |
|||
#include <vector> |
|||
|
|||
/** Used by SanitizeString() */ |
|||
enum SafeChars |
|||
{ |
|||
SAFE_CHARS_DEFAULT, //!< The full set of allowed chars
|
|||
SAFE_CHARS_UA_COMMENT, //!< BIP-0014 subset
|
|||
SAFE_CHARS_FILENAME, //!< Chars allowed in filenames
|
|||
SAFE_CHARS_URI, //!< Chars allowed in URIs (RFC 3986)
|
|||
}; |
|||
|
|||
/**
|
|||
* Remove unsafe chars. Safe chars chosen to allow simple messages/URLs/email |
|||
* addresses, but avoid anything even possibly remotely dangerous like & or > |
|||
* @param[in] str The string to sanitize |
|||
* @param[in] rule The set of safe chars to choose (default: least restrictive) |
|||
* @return A new string without unsafe chars |
|||
*/ |
|||
std::string SanitizeString(const std::string& str, int rule = SAFE_CHARS_DEFAULT); |
|||
std::vector<unsigned char> ParseHex(const char* psz); |
|||
std::vector<unsigned char> ParseHex(const std::string& str); |
|||
signed char HexDigit(char c); |
|||
/* Returns true if each character in str is a hex character, and has an even
|
|||
* number of hex digits.*/ |
|||
bool IsHex(const std::string& str); |
|||
/**
|
|||
* Return true if the string is a hex number, optionally prefixed with "0x" |
|||
*/ |
|||
bool IsHexNumber(const std::string& str); |
|||
std::vector<unsigned char> DecodeBase64(const char* p, bool* pf_invalid = nullptr); |
|||
std::string DecodeBase64(const std::string& str, bool* pf_invalid = nullptr); |
|||
std::string EncodeBase64(Span<const unsigned char> input); |
|||
std::string EncodeBase64(const std::string& str); |
|||
std::vector<unsigned char> DecodeBase32(const char* p, bool* pf_invalid = nullptr); |
|||
std::string DecodeBase32(const std::string& str, bool* pf_invalid = nullptr); |
|||
|
|||
/**
|
|||
* Base32 encode. |
|||
* If `pad` is true, then the output will be padded with '=' so that its length |
|||
* is a multiple of 8. |
|||
*/ |
|||
std::string EncodeBase32(Span<const unsigned char> input, bool pad = true); |
|||
|
|||
/**
|
|||
* Base32 encode. |
|||
* If `pad` is true, then the output will be padded with '=' so that its length |
|||
* is a multiple of 8. |
|||
*/ |
|||
std::string EncodeBase32(const std::string& str, bool pad = true); |
|||
|
|||
void SplitHostPort(std::string in, uint16_t& portOut, std::string& hostOut); |
|||
int64_t atoi64(const std::string& str); |
|||
int atoi(const std::string& str); |
|||
|
|||
/**
|
|||
* Tests if the given character is a decimal digit. |
|||
* @param[in] c character to test |
|||
* @return true if the argument is a decimal digit; otherwise false. |
|||
*/ |
|||
constexpr bool IsDigit(char c) |
|||
{ |
|||
return c >= '0' && c <= '9'; |
|||
} |
|||
|
|||
/**
|
|||
* Tests if the given character is a whitespace character. The whitespace characters |
|||
* are: space, form-feed ('\f'), newline ('\n'), carriage return ('\r'), horizontal |
|||
* tab ('\t'), and vertical tab ('\v'). |
|||
* |
|||
* This function is locale independent. Under the C locale this function gives the |
|||
* same result as std::isspace. |
|||
* |
|||
* @param[in] c character to test |
|||
* @return true if the argument is a whitespace character; otherwise false |
|||
*/ |
|||
constexpr inline bool IsSpace(char c) noexcept { |
|||
return c == ' ' || c == '\f' || c == '\n' || c == '\r' || c == '\t' || c == '\v'; |
|||
} |
|||
|
|||
/**
|
|||
* Convert string to signed 32-bit integer with strict parse error feedback. |
|||
* @returns true if the entire string could be parsed as valid integer, |
|||
* false if not the entire string could be parsed or when overflow or underflow occurred. |
|||
*/ |
|||
[[nodiscard]] bool ParseInt32(const std::string& str, int32_t *out); |
|||
|
|||
/**
|
|||
* Convert string to signed 64-bit integer with strict parse error feedback. |
|||
* @returns true if the entire string could be parsed as valid integer, |
|||
* false if not the entire string could be parsed or when overflow or underflow occurred. |
|||
*/ |
|||
[[nodiscard]] bool ParseInt64(const std::string& str, int64_t *out); |
|||
|
|||
/**
|
|||
* Convert decimal string to unsigned 8-bit integer with strict parse error feedback. |
|||
* @returns true if the entire string could be parsed as valid integer, |
|||
* false if not the entire string could be parsed or when overflow or underflow occurred. |
|||
*/ |
|||
[[nodiscard]] bool ParseUInt8(const std::string& str, uint8_t *out); |
|||
|
|||
/**
|
|||
* Convert decimal string to unsigned 16-bit integer with strict parse error feedback. |
|||
* @returns true if the entire string could be parsed as valid integer, |
|||
* false if the entire string could not be parsed or if overflow or underflow occurred. |
|||
*/ |
|||
[[nodiscard]] bool ParseUInt16(const std::string& str, uint16_t* out); |
|||
|
|||
/**
|
|||
* Convert decimal string to unsigned 32-bit integer with strict parse error feedback. |
|||
* @returns true if the entire string could be parsed as valid integer, |
|||
* false if not the entire string could be parsed or when overflow or underflow occurred. |
|||
*/ |
|||
[[nodiscard]] bool ParseUInt32(const std::string& str, uint32_t *out); |
|||
|
|||
/**
|
|||
* Convert decimal string to unsigned 64-bit integer with strict parse error feedback. |
|||
* @returns true if the entire string could be parsed as valid integer, |
|||
* false if not the entire string could be parsed or when overflow or underflow occurred. |
|||
*/ |
|||
[[nodiscard]] bool ParseUInt64(const std::string& str, uint64_t *out); |
|||
|
|||
/**
|
|||
* Convert string to double with strict parse error feedback. |
|||
* @returns true if the entire string could be parsed as valid double, |
|||
* false if not the entire string could be parsed or when overflow or underflow occurred. |
|||
*/ |
|||
[[nodiscard]] bool ParseDouble(const std::string& str, double *out); |
|||
|
|||
/**
|
|||
* Convert a span of bytes to a lower-case hexadecimal string. |
|||
*/ |
|||
std::string HexStr(const Span<const uint8_t> s); |
|||
inline std::string HexStr(const Span<const char> s) { return HexStr(MakeUCharSpan(s)); } |
|||
|
|||
/**
|
|||
* Format a paragraph of text to a fixed width, adding spaces for |
|||
* indentation to any added line. |
|||
*/ |
|||
std::string FormatParagraph(const std::string& in, size_t width = 79, size_t indent = 0); |
|||
|
|||
/**
|
|||
* Timing-attack-resistant comparison. |
|||
* Takes time proportional to length |
|||
* of first argument. |
|||
*/ |
|||
template <typename T> |
|||
bool TimingResistantEqual(const T& a, const T& b) |
|||
{ |
|||
if (b.size() == 0) return a.size() == 0; |
|||
size_t accumulator = a.size() ^ b.size(); |
|||
for (size_t i = 0; i < a.size(); i++) |
|||
accumulator |= a[i] ^ b[i%b.size()]; |
|||
return accumulator == 0; |
|||
} |
|||
|
|||
/** Parse number as fixed point according to JSON number syntax.
|
|||
* See https://json.org/number.gif
|
|||
* @returns true on success, false on error. |
|||
* @note The result must be in the range (-10^18,10^18), otherwise an overflow error will trigger. |
|||
*/ |
|||
[[nodiscard]] bool ParseFixedPoint(const std::string &val, int decimals, int64_t *amount_out); |
|||
|
|||
/** Convert from one power-of-2 number base to another. */ |
|||
template<int frombits, int tobits, bool pad, typename O, typename I> |
|||
bool ConvertBits(const O& outfn, I it, I end) { |
|||
size_t acc = 0; |
|||
size_t bits = 0; |
|||
constexpr size_t maxv = (1 << tobits) - 1; |
|||
constexpr size_t max_acc = (1 << (frombits + tobits - 1)) - 1; |
|||
while (it != end) { |
|||
acc = ((acc << frombits) | *it) & max_acc; |
|||
bits += frombits; |
|||
while (bits >= tobits) { |
|||
bits -= tobits; |
|||
outfn((acc >> bits) & maxv); |
|||
} |
|||
++it; |
|||
} |
|||
if (pad) { |
|||
if (bits) outfn((acc << (tobits - bits)) & maxv); |
|||
} else if (bits >= frombits || ((acc << (tobits - bits)) & maxv)) { |
|||
return false; |
|||
} |
|||
return true; |
|||
} |
|||
|
|||
/**
|
|||
* Converts the given character to its lowercase equivalent. |
|||
* This function is locale independent. It only converts uppercase |
|||
* characters in the standard 7-bit ASCII range. |
|||
* This is a feature, not a limitation. |
|||
* |
|||
* @param[in] c the character to convert to lowercase. |
|||
* @return the lowercase equivalent of c; or the argument |
|||
* if no conversion is possible. |
|||
*/ |
|||
constexpr char ToLower(char c) |
|||
{ |
|||
return (c >= 'A' && c <= 'Z' ? (c - 'A') + 'a' : c); |
|||
} |
|||
|
|||
/**
|
|||
* Returns the lowercase equivalent of the given string. |
|||
* This function is locale independent. It only converts uppercase |
|||
* characters in the standard 7-bit ASCII range. |
|||
* This is a feature, not a limitation. |
|||
* |
|||
* @param[in] str the string to convert to lowercase. |
|||
* @returns lowercased equivalent of str |
|||
*/ |
|||
std::string ToLower(const std::string& str); |
|||
|
|||
/**
|
|||
* Converts the given character to its uppercase equivalent. |
|||
* This function is locale independent. It only converts lowercase |
|||
* characters in the standard 7-bit ASCII range. |
|||
* This is a feature, not a limitation. |
|||
* |
|||
* @param[in] c the character to convert to uppercase. |
|||
* @return the uppercase equivalent of c; or the argument |
|||
* if no conversion is possible. |
|||
*/ |
|||
constexpr char ToUpper(char c) |
|||
{ |
|||
return (c >= 'a' && c <= 'z' ? (c - 'a') + 'A' : c); |
|||
} |
|||
|
|||
/**
|
|||
* Returns the uppercase equivalent of the given string. |
|||
* This function is locale independent. It only converts lowercase |
|||
* characters in the standard 7-bit ASCII range. |
|||
* This is a feature, not a limitation. |
|||
* |
|||
* @param[in] str the string to convert to uppercase. |
|||
* @returns UPPERCASED EQUIVALENT OF str |
|||
*/ |
|||
std::string ToUpper(const std::string& str); |
|||
|
|||
/**
|
|||
* Capitalizes the first character of the given string. |
|||
* This function is locale independent. It only converts lowercase |
|||
* characters in the standard 7-bit ASCII range. |
|||
* This is a feature, not a limitation. |
|||
* |
|||
* @param[in] str the string to capitalize. |
|||
* @returns string with the first letter capitalized. |
|||
*/ |
|||
std::string Capitalize(std::string str); |
|||
|
|||
#endif // BITCOIN_UTIL_STRENCODINGS_H
|
|||
@ -0,0 +1,5 @@ |
|||
// Copyright (c) 2019 The Bitcoin Core developers
|
|||
// Distributed under the MIT software license, see the accompanying
|
|||
// file COPYING or http://www.opensource.org/licenses/mit-license.php.
|
|||
|
|||
#include <util/string.h> |
|||
@ -0,0 +1,98 @@ |
|||
// Copyright (c) 2019-2020 The Bitcoin Core developers
|
|||
// Distributed under the MIT software license, see the accompanying
|
|||
// file COPYING or http://www.opensource.org/licenses/mit-license.php.
|
|||
|
|||
#ifndef BITCOIN_UTIL_STRING_H |
|||
#define BITCOIN_UTIL_STRING_H |
|||
|
|||
#include <attributes.h> |
|||
|
|||
#include <algorithm> |
|||
#include <array> |
|||
#include <cstring> |
|||
#include <locale> |
|||
#include <sstream> |
|||
#include <string> |
|||
#include <vector> |
|||
|
|||
[[nodiscard]] inline std::string TrimString(const std::string& str, const std::string& pattern = " \f\n\r\t\v") |
|||
{ |
|||
std::string::size_type front = str.find_first_not_of(pattern); |
|||
if (front == std::string::npos) { |
|||
return std::string(); |
|||
} |
|||
std::string::size_type end = str.find_last_not_of(pattern); |
|||
return str.substr(front, end - front + 1); |
|||
} |
|||
|
|||
[[nodiscard]] inline std::string RemovePrefix(const std::string& str, const std::string& prefix) |
|||
{ |
|||
if (str.substr(0, prefix.size()) == prefix) { |
|||
return str.substr(prefix.size()); |
|||
} |
|||
return str; |
|||
} |
|||
|
|||
/**
|
|||
* Join a list of items |
|||
* |
|||
* @param list The list to join |
|||
* @param separator The separator |
|||
* @param unary_op Apply this operator to each item in the list |
|||
*/ |
|||
template <typename T, typename BaseType, typename UnaryOp> |
|||
auto Join(const std::vector<T>& list, const BaseType& separator, UnaryOp unary_op) |
|||
-> decltype(unary_op(list.at(0))) |
|||
{ |
|||
decltype(unary_op(list.at(0))) ret; |
|||
for (size_t i = 0; i < list.size(); ++i) { |
|||
if (i > 0) ret += separator; |
|||
ret += unary_op(list.at(i)); |
|||
} |
|||
return ret; |
|||
} |
|||
|
|||
template <typename T> |
|||
T Join(const std::vector<T>& list, const T& separator) |
|||
{ |
|||
return Join(list, separator, [](const T& i) { return i; }); |
|||
} |
|||
|
|||
// Explicit overload needed for c_str arguments, which would otherwise cause a substitution failure in the template above.
|
|||
inline std::string Join(const std::vector<std::string>& list, const std::string& separator) |
|||
{ |
|||
return Join<std::string>(list, separator); |
|||
} |
|||
|
|||
/**
|
|||
* Check if a string does not contain any embedded NUL (\0) characters |
|||
*/ |
|||
[[nodiscard]] inline bool ValidAsCString(const std::string& str) noexcept |
|||
{ |
|||
return str.size() == strlen(str.c_str()); |
|||
} |
|||
|
|||
/**
|
|||
* Locale-independent version of std::to_string |
|||
*/ |
|||
template <typename T> |
|||
std::string ToString(const T& t) |
|||
{ |
|||
std::ostringstream oss; |
|||
oss.imbue(std::locale::classic()); |
|||
oss << t; |
|||
return oss.str(); |
|||
} |
|||
|
|||
/**
|
|||
* Check whether a container begins with the given prefix. |
|||
*/ |
|||
template <typename T1, size_t PREFIX_LEN> |
|||
[[nodiscard]] inline bool HasPrefix(const T1& obj, |
|||
const std::array<uint8_t, PREFIX_LEN>& prefix) |
|||
{ |
|||
return obj.size() >= PREFIX_LEN && |
|||
std::equal(std::begin(prefix), std::end(prefix), std::begin(obj)); |
|||
} |
|||
|
|||
#endif // BITCOIN_UTIL_STRENCODINGS_H
|
|||
Loading…
Reference in new issue