dash/src/util/strencodings.h

291 lines
10 KiB
C
Raw Normal View History

// Copyright (c) 2009-2010 Satoshi Nakamoto
// Copyright (c) 2009-2015 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.
*/
merge bitcoin#14555: Move util files to directory (script modified to account for Dash backports, doesn't account for rebasing) ------------- BEGIN SCRIPT --------------- mkdir -p src/util git mv src/util.h src/util/system.h git mv src/util.cpp src/util/system.cpp git mv src/utilmemory.h src/util/memory.h git mv src/utilmoneystr.h src/util/moneystr.h git mv src/utilmoneystr.cpp src/util/moneystr.cpp git mv src/utilstrencodings.h src/util/strencodings.h git mv src/utilstrencodings.cpp src/util/strencodings.cpp git mv src/utiltime.h src/util/time.h git mv src/utiltime.cpp src/util/time.cpp git mv src/utilasmap.h src/util/asmap.h git mv src/utilasmap.cpp src/util/asmap.cpp git mv src/utilstring.h src/util/string.h git mv src/utilstring.cpp src/util/string.cpp gsed -i 's/<util\.h>/<util\/system\.h>/g' $(git ls-files 'src/*.h' 'src/*.cpp') gsed -i 's/<utilmemory\.h>/<util\/memory\.h>/g' $(git ls-files 'src/*.h' 'src/*.cpp') gsed -i 's/<utilmoneystr\.h>/<util\/moneystr\.h>/g' $(git ls-files 'src/*.h' 'src/*.cpp') gsed -i 's/<utilstrencodings\.h>/<util\/strencodings\.h>/g' $(git ls-files 'src/*.h' 'src/*.cpp') gsed -i 's/<utiltime\.h>/<util\/time\.h>/g' $(git ls-files 'src/*.h' 'src/*.cpp') gsed -i 's/<utilasmap\.h>/<util\/asmap\.h>/g' $(git ls-files 'src/*.h' 'src/*.cpp') gsed -i 's/<utilstring\.h>/<util\/string\.h>/g' $(git ls-files 'src/*.h' 'src/*.cpp') gsed -i 's/BITCOIN_UTIL_H/BITCOIN_UTIL_SYSTEM_H/g' src/util/system.h gsed -i 's/BITCOIN_UTILMEMORY_H/BITCOIN_UTIL_MEMORY_H/g' src/util/memory.h gsed -i 's/BITCOIN_UTILMONEYSTR_H/BITCOIN_UTIL_MONEYSTR_H/g' src/util/moneystr.h gsed -i 's/BITCOIN_UTILSTRENCODINGS_H/BITCOIN_UTIL_STRENCODINGS_H/g' src/util/strencodings.h gsed -i 's/BITCOIN_UTILTIME_H/BITCOIN_UTIL_TIME_H/g' src/util/time.h gsed -i 's/BITCOIN_UTILASMAP_H/BITCOIN_UTIL_ASMAP_H/g' src/util/asmap.h gsed -i 's/BITCOIN_UTILSTRING_H/BITCOIN_UTIL_STRING_H/g' src/util/string.h gsed -i 's/ util\.\(h\|cpp\)/ util\/system\.\1/g' src/Makefile.am gsed -i 's/utilmemory\.\(h\|cpp\)/util\/memory\.\1/g' src/Makefile.am gsed -i 's/utilmoneystr\.\(h\|cpp\)/util\/moneystr\.\1/g' src/Makefile.am gsed -i 's/utilstrencodings\.\(h\|cpp\)/util\/strencodings\.\1/g' src/Makefile.am gsed -i 's/utiltime\.\(h\|cpp\)/util\/time\.\1/g' src/Makefile.am gsed -i 's/utilasmap\.\(h\|cpp\)/util\/asmap\.\1/g' src/Makefile.am gsed -i 's/utilstring\.\(h\|cpp\)/util\/string\.\1/g' src/Makefile.am gsed -i 's/-> util ->/-> util\/system ->/' test/lint/lint-circular-dependencies.sh gsed -i 's/src\/util\.cpp/src\/util\/system\.cpp/g' test/lint/lint-format-strings.py test/lint/lint-locale-dependence.sh gsed -i 's/src\/utilmoneystr\.cpp/src\/util\/moneystr\.cpp/g' test/lint/lint-locale-dependence.sh gsed -i 's/src\/utilstrencodings\.\(h\|cpp\)/src\/util\/strencodings\.\1/g' test/lint/lint-locale-dependence.sh ------------- END SCRIPT ---------------
2021-06-27 08:33:13 +02:00
#ifndef BITCOIN_UTIL_STRENCODINGS_H
#define BITCOIN_UTIL_STRENCODINGS_H
#include <attributes.h>
#include <span.h>
#include <charconv>
#include <cstdint>
#include <optional>
#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 integral type T.
*
* @returns std::nullopt if the entire string could not be parsed, or if the
* parsed value is not in the range representable by the type T.
*/
template <typename T>
std::optional<T> ToIntegral(const std::string& str)
{
static_assert(std::is_integral<T>::value);
T result;
const auto [first_nonmatching, error_condition] = std::from_chars(str.data(), str.data() + str.size(), result);
if (first_nonmatching != str.data() + str.size() || error_condition != std::errc{}) {
return std::nullopt;
}
return {result};
}
/**
* 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)); }
2015-05-31 15:36:44 +02:00
/**
* Format a paragraph of text to a fixed width, adding spaces for
* indentation to any added line.
*/
2015-05-31 15:36:44 +02:00
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 http://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);
2018-08-08 23:27:20 +02:00
/** Parse an HD keypaths like "m/7/0'/2000". */
bool ParseHDKeypath(const std::string& keypath_str, std::vector<uint32_t>& keypath);
merge bitcoin#14555: Move util files to directory (script modified to account for Dash backports, doesn't account for rebasing) ------------- BEGIN SCRIPT --------------- mkdir -p src/util git mv src/util.h src/util/system.h git mv src/util.cpp src/util/system.cpp git mv src/utilmemory.h src/util/memory.h git mv src/utilmoneystr.h src/util/moneystr.h git mv src/utilmoneystr.cpp src/util/moneystr.cpp git mv src/utilstrencodings.h src/util/strencodings.h git mv src/utilstrencodings.cpp src/util/strencodings.cpp git mv src/utiltime.h src/util/time.h git mv src/utiltime.cpp src/util/time.cpp git mv src/utilasmap.h src/util/asmap.h git mv src/utilasmap.cpp src/util/asmap.cpp git mv src/utilstring.h src/util/string.h git mv src/utilstring.cpp src/util/string.cpp gsed -i 's/<util\.h>/<util\/system\.h>/g' $(git ls-files 'src/*.h' 'src/*.cpp') gsed -i 's/<utilmemory\.h>/<util\/memory\.h>/g' $(git ls-files 'src/*.h' 'src/*.cpp') gsed -i 's/<utilmoneystr\.h>/<util\/moneystr\.h>/g' $(git ls-files 'src/*.h' 'src/*.cpp') gsed -i 's/<utilstrencodings\.h>/<util\/strencodings\.h>/g' $(git ls-files 'src/*.h' 'src/*.cpp') gsed -i 's/<utiltime\.h>/<util\/time\.h>/g' $(git ls-files 'src/*.h' 'src/*.cpp') gsed -i 's/<utilasmap\.h>/<util\/asmap\.h>/g' $(git ls-files 'src/*.h' 'src/*.cpp') gsed -i 's/<utilstring\.h>/<util\/string\.h>/g' $(git ls-files 'src/*.h' 'src/*.cpp') gsed -i 's/BITCOIN_UTIL_H/BITCOIN_UTIL_SYSTEM_H/g' src/util/system.h gsed -i 's/BITCOIN_UTILMEMORY_H/BITCOIN_UTIL_MEMORY_H/g' src/util/memory.h gsed -i 's/BITCOIN_UTILMONEYSTR_H/BITCOIN_UTIL_MONEYSTR_H/g' src/util/moneystr.h gsed -i 's/BITCOIN_UTILSTRENCODINGS_H/BITCOIN_UTIL_STRENCODINGS_H/g' src/util/strencodings.h gsed -i 's/BITCOIN_UTILTIME_H/BITCOIN_UTIL_TIME_H/g' src/util/time.h gsed -i 's/BITCOIN_UTILASMAP_H/BITCOIN_UTIL_ASMAP_H/g' src/util/asmap.h gsed -i 's/BITCOIN_UTILSTRING_H/BITCOIN_UTIL_STRING_H/g' src/util/string.h gsed -i 's/ util\.\(h\|cpp\)/ util\/system\.\1/g' src/Makefile.am gsed -i 's/utilmemory\.\(h\|cpp\)/util\/memory\.\1/g' src/Makefile.am gsed -i 's/utilmoneystr\.\(h\|cpp\)/util\/moneystr\.\1/g' src/Makefile.am gsed -i 's/utilstrencodings\.\(h\|cpp\)/util\/strencodings\.\1/g' src/Makefile.am gsed -i 's/utiltime\.\(h\|cpp\)/util\/time\.\1/g' src/Makefile.am gsed -i 's/utilasmap\.\(h\|cpp\)/util\/asmap\.\1/g' src/Makefile.am gsed -i 's/utilstring\.\(h\|cpp\)/util\/string\.\1/g' src/Makefile.am gsed -i 's/-> util ->/-> util\/system ->/' test/lint/lint-circular-dependencies.sh gsed -i 's/src\/util\.cpp/src\/util\/system\.cpp/g' test/lint/lint-format-strings.py test/lint/lint-locale-dependence.sh gsed -i 's/src\/utilmoneystr\.cpp/src\/util\/moneystr\.cpp/g' test/lint/lint-locale-dependence.sh gsed -i 's/src\/utilstrencodings\.\(h\|cpp\)/src\/util\/strencodings\.\1/g' test/lint/lint-locale-dependence.sh ------------- END SCRIPT ---------------
2021-06-27 08:33:13 +02:00
#endif // BITCOIN_UTIL_STRENCODINGS_H