aboutsummaryrefslogtreecommitdiff
path: root/src/util/strencodings.h
blob: 7c4364a082538ea72b44b712b75008f1991cd50b (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
// Copyright (c) 2009-2010 Satoshi Nakamoto
// Copyright (c) 2009-2018 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 <cstdint>
#include <iterator>
#include <string>
#include <vector>

#define ARRAYLEN(array)     (sizeof(array)/sizeof((array)[0]))

/** 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(const unsigned char* pch, size_t len);
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);
std::string EncodeBase32(const unsigned char* pch, size_t len);
std::string EncodeBase32(const std::string& str);

void SplitHostPort(std::string in, int &portOut, std::string &hostOut);
std::string i64tostr(int64_t n);
std::string itostr(int n);
int64_t atoi64(const char* psz);
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 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);

template<typename T>
std::string HexStr(const T itbegin, const T itend)
{
    std::string rv;
    static const char hexmap[16] = { '0', '1', '2', '3', '4', '5', '6', '7',
                                     '8', '9', 'a', 'b', 'c', 'd', 'e', 'f' };
    rv.reserve(std::distance(itbegin, itend) * 2);
    for(T it = itbegin; it < itend; ++it)
    {
        unsigned char val = (unsigned char)(*it);
        rv.push_back(hexmap[val>>4]);
        rv.push_back(hexmap[val&15]);
    }
    return rv;
}

template<typename T>
inline std::string HexStr(const T& vch)
{
    return HexStr(vch.begin(), vch.end());
}

/**
 * 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 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.
 * @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);
}

/**
 * Converts the given string to its lowercase equivalent.
 * This function is locale independent. It only converts uppercase
 * characters in the standard 7-bit ASCII range.
 * @param[in,out] str   the string to convert to lowercase.
 */
void Downcase(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.
 * @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);
}

/**
 * Capitalizes the first character of the given string.
 * This function is locale independent. It only capitalizes the
 * first character of the argument if it has an uppercase equivalent
 * in the standard 7-bit ASCII range.
 * @param[in] str   the string to capitalize.
 * @return          string with the first letter capitalized.
 */
std::string Capitalize(std::string str);

#endif // BITCOIN_UTIL_STRENCODINGS_H