summaryrefslogtreecommitdiffstats
path: root/Utilities/cmlibrhash/librhash/hex.c
blob: cfd5892b9630d48fd66ad45201f283c324921598 (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
/* hex.c - conversion for hexadecimal and base32 strings.
 *
 * Copyright (c) 2008, Aleksey Kravchenko <rhash.admin@gmail.com>
 *
 * Permission to use, copy, modify, and/or distribute this software for any
 * purpose with or without fee is hereby granted.
 *
 * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH
 * REGARD TO THIS SOFTWARE  INCLUDING ALL IMPLIED WARRANTIES OF  MERCHANTABILITY
 * AND FITNESS.  IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT,
 * INDIRECT,  OR CONSEQUENTIAL DAMAGES  OR ANY DAMAGES WHATSOEVER RESULTING FROM
 * LOSS OF USE,  DATA OR PROFITS,  WHETHER IN AN ACTION OF CONTRACT,  NEGLIGENCE
 * OR OTHER TORTIOUS ACTION,  ARISING OUT OF  OR IN CONNECTION  WITH THE USE  OR
 * PERFORMANCE OF THIS SOFTWARE.
 */
#include "hex.h"
#include <assert.h>
#include <ctype.h>
#include <string.h>

/**
 * Store hexadecimal representation of a binary string to given buffer.
 *
 * @param dst the buffer to receive hexadecimal representation
 * @param src binary string
 * @param length string length
 * @param upper_case flag to print string in uppercase
 */
void rhash_byte_to_hex(char* dst, const unsigned char* src, size_t length, int upper_case)
{
	const char hex_add = (upper_case ? 'A' - 10 : 'a' - 10);
	for (; length > 0; src++, length--) {
		const unsigned char hi = (*src >> 4) & 15;
		const unsigned char lo = *src & 15;
		*dst++ = (hi > 9 ? hi + hex_add : hi + '0');
		*dst++ = (lo > 9 ? lo + hex_add : lo + '0');
	}
	*dst = '\0';
}

/**
 * Encode a binary string to base32.
 *
 * @param dst the buffer to store result
 * @param src binary string
 * @param length string length
 * @param upper_case flag to print string in uppercase
 */
void rhash_byte_to_base32(char* dst, const unsigned char* src, size_t length, int upper_case)
{
	const char a = (upper_case ? 'A' : 'a');
	unsigned shift = 0;
	unsigned char word;
	const unsigned char* e = src + length;
	while (src < e) {
		if (shift > 3) {
			word = (*src & (0xFF >> shift));
			shift = (shift + 5) % 8;
			word <<= shift;
			if (src + 1 < e)
				word |= *(src + 1) >> (8 - shift);
			++src;
		} else {
			shift = (shift + 5) % 8;
			word = ( *src >> ( (8 - shift) & 7 ) ) & 0x1F;
			if (shift == 0) src++;
		}
		*dst++ = ( word < 26 ? word + a : word + '2' - 26 );
	}
	*dst = '\0';
}

/**
 * Encode a binary string to base64.
 * Encoded output length is always a multiple of 4 bytes.
 *
 * @param dst the buffer to store result
 * @param src binary string
 * @param length string length
 */
void rhash_byte_to_base64(char* dst, const unsigned char* src, size_t length)
{
	static const char* tail = "0123456789+/";
	unsigned shift = 0;
	unsigned char word;
	const unsigned char* e = src + length;
	while (src < e) {
		if (shift > 2) {
			word = (*src & (0xFF >> shift));
			shift = (shift + 6) % 8;
			word <<= shift;
			if (src + 1 < e)
				word |= *(src + 1) >> (8 - shift);
			++src;
		} else {
			shift = (shift + 6) % 8;
			word = ( *src >> ( (8 - shift) & 7 ) ) & 0x3F;
			if (shift == 0) src++;
		}
		*dst++ = ( word < 52 ? (word < 26 ? word + 'A' : word - 26 + 'a') : tail[word - 52]);
	}
	if (shift > 0) {
		*dst++ = '=';
		if (shift == 4) *dst++ = '=';
	}
	*dst = '\0';
}

size_t rhash_base64_url_encoded_helper(char* dst, const unsigned char* src, size_t length, int url_encode, int upper_case)
{
#define B64_CHUNK_SIZE 120
	char buffer[164];
	#ifdef __clang_analyzer__
	memset(buffer, 0, sizeof(buffer));
	#endif
	assert((BASE64_LENGTH(B64_CHUNK_SIZE) + 4) <= sizeof(buffer));
	assert((B64_CHUNK_SIZE % 6) == 0);
	if (url_encode) {
		size_t result_length = 0;
		for (; length > 0; src += B64_CHUNK_SIZE) {
			size_t chunk_size = (length < B64_CHUNK_SIZE ? length : B64_CHUNK_SIZE);
			size_t encoded_length;
			rhash_byte_to_base64(buffer, src, chunk_size);
			encoded_length = rhash_urlencode(dst, buffer, BASE64_LENGTH(chunk_size), upper_case);
			result_length += encoded_length;
			dst += encoded_length;
			length -= chunk_size;
		}
		return result_length;
	}
	rhash_byte_to_base64(dst, src, length);
	return BASE64_LENGTH(length);
}

/* RFC 3986: safe url characters are ascii alpha-numeric and "-._~", other characters should be percent-encoded */
static unsigned url_safe_char_mask[4] = { 0, 0x03ff6000, 0x87fffffe, 0x47fffffe };
#define IS_URL_GOOD_CHAR(c) ((unsigned)(c) < 128 && (url_safe_char_mask[c >> 5] & (1 << (c & 31))))

/**
 * URL-encode specified binary string.
 *
 * @param dst (nullable) buffer to output encoded string to,
 *            NULL to just calculate the lengths of encoded string
 * @param src binary string to encode
 * @param size size of the binary string
 * @param upper_case flag to output hex-codes in uppercase
 * @return the length of the result string
 */
size_t rhash_urlencode(char* dst, const char* src, size_t size, int upper_case)
{
	const char* start;
	size_t i;
	if (!dst) {
		size_t length = size;
		for (i = 0; i < size; i++)
			if (!IS_URL_GOOD_CHAR(src[i]))
				length += 2;
		return length;
	} else {
		const char hex_add = (upper_case ? 'A' - 10 : 'a' - 10);
		start = dst;
		/* percent-encode all but unreserved URL characters */
		for (i = 0; i < size; i++) {
			if (IS_URL_GOOD_CHAR(src[i])) {
				*dst++ = src[i];
			} else {
				unsigned char hi = ((unsigned char)(src[i]) >> 4) & 0x0f;
				unsigned char lo = (unsigned char)(src[i]) & 0x0f;
				*dst++ = '%';
				*dst++ = (hi > 9 ? hi + hex_add : hi + '0');
				*dst++ = (lo > 9 ? lo + hex_add : lo + '0');
			}
		}
		*dst = 0;
	}
	return dst - start;
}

/**
 * Print 64-bit number with trailing '\0' to a string buffer.
 * if dst is NULL, then just return the length of the number.
 *
 * @param dst output buffer
 * @param number the number to print
 * @return length of the printed number (without trailing '\0')
 */
int rhash_sprintI64(char* dst, uint64_t number)
{
	/* The biggest number has 20 digits: 2^64 = 18 446 744 073 709 551 616 */
	char buf[24];
	char* p;
	size_t length;

	if (dst == NULL) {
		/* just calculate the length of the number */
		if (number == 0) return 1;
		for (length = 0; number != 0; number /= 10) length++;
		return (int)length;
	}

	p = buf + 23;
	*p = '\0'; /* last symbol should be '\0' */
	if (number == 0) {
		*(--p) = '0';
	} else {
		for (; p >= buf && number != 0; number /= 10) {
			*(--p) = '0' + (char)(number % 10);
		}
	}
	length = buf + 23 - p;
	memcpy(dst, p, length + 1);
	return (int)length;
}