summaryrefslogtreecommitdiff
path: root/src/string_func.h
blob: 4fe9d7b825fe50866d1530db6dec3c09f485c21c (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
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
/*
 * This file is part of OpenTTD.
 * OpenTTD is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, version 2.
 * OpenTTD is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
 * See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with OpenTTD. If not, see <http://www.gnu.org/licenses/>.
 */

/**
 * @file string_func.h Functions related to low-level strings.
 *
 * @note Be aware of "dangerous" string functions; string functions that
 * have behaviour that could easily cause buffer overruns and such:
 * - strncpy: does not '\0' terminate when input string is longer than
 *   the size of the output string. Use strecpy instead.
 * - [v]snprintf: returns the length of the string as it would be written
 *   when the output is large enough, so it can be more than the size of
 *   the buffer and than can underflow size_t (uint-ish) which makes all
 *   subsequent snprintf alikes write outside of the buffer. Use
 *   [v]seprintf instead; it will return the number of bytes actually
 *   added so no [v]seprintf will cause outside of bounds writes.
 * - [v]sprintf: does not bounds checking: use [v]seprintf instead.
 */

#ifndef STRING_FUNC_H
#define STRING_FUNC_H

#include <stdarg.h>
#include <iosfwd>

#include "core/bitmath_func.hpp"
#include "string_type.h"

char *strecat(char *dst, const char *src, const char *last) NOACCESS(3);
char *strecpy(char *dst, const char *src, const char *last) NOACCESS(3);
char *stredup(const char *src, const char *last = nullptr) NOACCESS(2);

int CDECL seprintf(char *str, const char *last, const char *format, ...) WARN_FORMAT(3, 4) NOACCESS(2);
int CDECL vseprintf(char *str, const char *last, const char *format, va_list ap) WARN_FORMAT(3, 0) NOACCESS(2);

char *CDECL str_fmt(const char *str, ...) WARN_FORMAT(1, 2);

void str_validate(char *str, const char *last, StringValidationSettings settings = SVS_REPLACE_WITH_QUESTION_MARK) NOACCESS(2);
std::string str_validate(const std::string &str, StringValidationSettings settings = SVS_REPLACE_WITH_QUESTION_MARK);
void ValidateString(const char *str);

void str_fix_scc_encoded(char *str, const char *last) NOACCESS(2);
void str_strip_colours(char *str);
bool strtolower(char *str);
bool strtolower(std::string &str, std::string::size_type offs = 0);

bool StrValid(const char *str, const char *last) NOACCESS(2);
void StrTrimInPlace(char *str);

/**
 * Check if a string buffer is empty.
 *
 * @param s The pointer to the first element of the buffer
 * @return true if the buffer starts with the terminating null-character or
 *         if the given pointer points to nullptr else return false
 */
static inline bool StrEmpty(const char *s)
{
	return s == nullptr || s[0] == '\0';
}

/**
 * Get the length of a string, within a limited buffer.
 *
 * @param str The pointer to the first element of the buffer
 * @param maxlen The maximum size of the buffer
 * @return The length of the string
 */
static inline size_t ttd_strnlen(const char *str, size_t maxlen)
{
	const char *t;
	for (t = str; (size_t)(t - str) < maxlen && *t != '\0'; t++) {}
	return t - str;
}

char *md5sumToString(char *buf, const char *last, const uint8 md5sum[16]);

bool IsValidChar(WChar key, CharSetFilter afilter);

size_t Utf8Decode(WChar *c, const char *s);
size_t Utf8Encode(char *buf, WChar c);
size_t Utf8Encode(std::ostreambuf_iterator<char> &buf, WChar c);
size_t Utf8TrimString(char *s, size_t maxlen);


static inline WChar Utf8Consume(const char **s)
{
	WChar c;
	*s += Utf8Decode(&c, *s);
	return c;
}

template <class Titr>
static inline WChar Utf8Consume(Titr &s)
{
	WChar c;
	s += Utf8Decode(&c, &*s);
	return c;
}

/**
 * Return the length of a UTF-8 encoded character.
 * @param c Unicode character.
 * @return Length of UTF-8 encoding for character.
 */
static inline int8 Utf8CharLen(WChar c)
{
	if (c < 0x80)       return 1;
	if (c < 0x800)      return 2;
	if (c < 0x10000)    return 3;
	if (c < 0x110000)   return 4;

	/* Invalid valid, we encode as a '?' */
	return 1;
}


/**
 * Return the length of an UTF-8 encoded value based on a single char. This
 * char should be the first byte of the UTF-8 encoding. If not, or encoding
 * is invalid, return value is 0
 * @param c char to query length of
 * @return requested size
 */
static inline int8 Utf8EncodedCharLen(char c)
{
	if (GB(c, 3, 5) == 0x1E) return 4;
	if (GB(c, 4, 4) == 0x0E) return 3;
	if (GB(c, 5, 3) == 0x06) return 2;
	if (GB(c, 7, 1) == 0x00) return 1;

	/* Invalid UTF8 start encoding */
	return 0;
}


/* Check if the given character is part of a UTF8 sequence */
static inline bool IsUtf8Part(char c)
{
	return GB(c, 6, 2) == 2;
}

/**
 * Retrieve the previous UNICODE character in an UTF-8 encoded string.
 * @param s char pointer pointing to (the first char of) the next character
 * @return a pointer in 's' to the previous UNICODE character's first byte
 * @note The function should not be used to determine the length of the previous
 * encoded char because it might be an invalid/corrupt start-sequence
 */
static inline char *Utf8PrevChar(char *s)
{
	char *ret = s;
	while (IsUtf8Part(*--ret)) {}
	return ret;
}

static inline const char *Utf8PrevChar(const char *s)
{
	const char *ret = s;
	while (IsUtf8Part(*--ret)) {}
	return ret;
}

size_t Utf8StringLength(const char *s);

/**
 * Is the given character a lead surrogate code point?
 * @param c The character to test.
 * @return True if the character is a lead surrogate code point.
 */
static inline bool Utf16IsLeadSurrogate(uint c)
{
	return c >= 0xD800 && c <= 0xDBFF;
}

/**
 * Is the given character a lead surrogate code point?
 * @param c The character to test.
 * @return True if the character is a lead surrogate code point.
 */
static inline bool Utf16IsTrailSurrogate(uint c)
{
	return c >= 0xDC00 && c <= 0xDFFF;
}

/**
 * Convert an UTF-16 surrogate pair to the corresponding Unicode character.
 * @param lead Lead surrogate code point.
 * @param trail Trail surrogate code point.
 * @return Decoded Unicode character.
 */
static inline WChar Utf16DecodeSurrogate(uint lead, uint trail)
{
	return 0x10000 + (((lead - 0xD800) << 10) | (trail - 0xDC00));
}

/**
 * Decode an UTF-16 character.
 * @param c Pointer to one or two UTF-16 code points.
 * @return Decoded Unicode character.
 */
static inline WChar Utf16DecodeChar(const uint16 *c)
{
	if (Utf16IsLeadSurrogate(c[0])) {
		return Utf16DecodeSurrogate(c[0], c[1]);
	} else {
		return *c;
	}
}

/**
 * Is the given character a text direction character.
 * @param c The character to test.
 * @return true iff the character is used to influence
 *         the text direction.
 */
static inline bool IsTextDirectionChar(WChar c)
{
	switch (c) {
		case CHAR_TD_LRM:
		case CHAR_TD_RLM:
		case CHAR_TD_LRE:
		case CHAR_TD_RLE:
		case CHAR_TD_LRO:
		case CHAR_TD_RLO:
		case CHAR_TD_PDF:
			return true;

		default:
			return false;
	}
}

static inline bool IsPrintable(WChar c)
{
	if (c < 0x20)   return false;
	if (c < 0xE000) return true;
	if (c < 0xE200) return false;
	return true;
}

/**
 * Check whether UNICODE character is whitespace or not, i.e. whether
 * this is a potential line-break character.
 * @param c UNICODE character to check
 * @return a boolean value whether 'c' is a whitespace character or not
 * @see http://www.fileformat.info/info/unicode/category/Zs/list.htm
 */
static inline bool IsWhitespace(WChar c)
{
	return c == 0x0020 /* SPACE */ || c == 0x3000; /* IDEOGRAPHIC SPACE */
}

/* Needed for NetBSD version (so feature) testing */
#if defined(__NetBSD__) || defined(__FreeBSD__)
#include <sys/param.h>
#endif

/* strcasestr is available for _GNU_SOURCE, BSD and some Apple */
#if defined(_GNU_SOURCE) || (defined(__BSD_VISIBLE) && __BSD_VISIBLE) || (defined(__APPLE__) && (!defined(_POSIX_C_SOURCE) || defined(_DARWIN_C_SOURCE))) || defined(_NETBSD_SOURCE)
#	undef DEFINE_STRCASESTR
#else
#	define DEFINE_STRCASESTR
char *strcasestr(const char *haystack, const char *needle);
#endif /* strcasestr is available */

int strnatcmp(const char *s1, const char *s2, bool ignore_garbage_at_front = false);

#endif /* STRING_FUNC_H */