1

/* $Id$ */

     2

     3

/** @file string.h */

     4

     5

#ifndef STRING_H

     6

#define STRING_H

     7

     8

#include "macros.h"

     9

    10

/**

    11

 * usage ttd_strlcpy(dst, src, lengthof(dst));

    12

 * @param dst destination buffer

    13

 * @param src string to copy/concatenate

    14

 * @param size size of the destination buffer

    15

 */

    16

void ttd_strlcat(char *dst, const char *src, size_t size);

    17

void ttd_strlcpy(char *dst, const char *src, size_t size);

    18

    19

/**

    20

 * usage: strecpy(dst, src, lastof(dst));

    21

 * @param dst destination buffer

    22

 * @param src string to copy

    23

 * @param last pointer to the last element in the dst array

    24

 *             if NULL no boundary check is performed

    25

 * @return a pointer to the terminating \0 in the destination buffer

    26

 */

    27

char* strecat(char* dst, const char* src, const char* last);

    28

char* strecpy(char* dst, const char* src, const char* last);

    29

    30

char* CDECL str_fmt(const char* str, ...);

    31

    32

/** Scans the string for valid characters and if it finds invalid ones,

    33

 * replaces them with a question mark '?' */

    34

void str_validate(char *str);

    35

    36

/** Scans the string for colour codes and strips them */

    37

void str_strip_colours(char *str);

    38

    39

/**

    40

 * Valid filter types for IsValidChar.

    41

 */

    42

enum CharSetFilter {

    43

	CS_ALPHANUMERAL,      ///< Both numeric and alphabetic and spaces and stuff

    44

	CS_NUMERAL,           ///< Only numeric ones

    45

	CS_ALPHA,             ///< Only alphabetic values

    46

};

    47

    48

/** Convert the given string to lowercase, only works with ASCII! */

    49

void strtolower(char *str);

    50

    51

    52

static inline bool StrEmpty(const char* s) { return s[0] == '\0'; }

    53

    54

    55

/** Get the length of a string, within a limited buffer */

    56

static inline int ttd_strnlen(const char *str, int maxlen)

    57

{

    58

	const char *t;

    59

	for (t = str; *t != '\0' && t - str < maxlen; t++);

    60

	return t - str;

    61

}

    62

    63

/** Convert the md5sum number to a 'hexadecimal' string, return next pos in buffer */

    64

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

    65

    66

typedef uint32 WChar;

    67

    68

/**

    69

 * Only allow certain keys. You can define the filter to be used. This makes

    70

 *  sure no invalid keys can get into an editbox, like BELL.

    71

 * @param key character to be checked

    72

 * @param afilter the filter to use

    73

 * @return true or false depending if the character is printable/valid or not

    74

 */

    75

bool IsValidChar(WChar key, CharSetFilter afilter);

    76

    77

size_t Utf8Decode(WChar *c, const char *s);

    78

size_t Utf8Encode(char *buf, WChar c);

    79

size_t Utf8TrimString(char *s, size_t maxlen);

    80

    81

    82

static inline WChar Utf8Consume(const char **s)

    83

{

    84

	WChar c;

    85

	*s += Utf8Decode(&c, *s);

    86

	return c;

    87

}

    88

    89

    90

/** Return the length of a UTF-8 encoded character.

    91

 * @param c Unicode character.

    92

 * @return Length of UTF-8 encoding for character.

    93

 */

    94

static inline size_t Utf8CharLen(WChar c)

    95

{

    96

	if (c < 0x80)       return 1;

    97

	if (c < 0x800)      return 2;

    98

	if (c < 0x10000)    return 3;

    99

	if (c < 0x110000)   return 4;

   100

   101

	/* Invalid valid, we encode as a '?' */

   102

	return 1;

   103

}

   104

   105

   106

/**

   107

 * Return the length of an UTF-8 encoded value based on a single char. This

   108

 * char should be the first byte of the UTF-8 encoding. If not, or encoding

   109

 * is invalid, return value is 0

   110

 * @param c char to query length of

   111

 * @return requested size

   112

 */

   113

static inline size_t Utf8EncodedCharLen(char c)

   114

{

   115

	if (GB(c, 3, 5) == 0x1E) return 4;

   116

	if (GB(c, 4, 4) == 0x0E) return 3;

   117

	if (GB(c, 5, 3) == 0x06) return 2;

   118

	if (GB(c, 7, 1) == 0x00) return 1;

   119

   120

	/* Invalid UTF8 start encoding */

   121

	return 0;

   122

}

   123

   124

   125

/* Check if the given character is part of a UTF8 sequence */

   126

static inline bool IsUtf8Part(char c)

   127

{

   128

	return GB(c, 6, 2) == 2;

   129

}

   130

   131

/**

   132

 * Retrieve the previous UNICODE character in an UTF-8 encoded string.

   133

 * @param s char pointer pointing to (the first char of) the next character

   134

 * @return a pointer in 's' to the previous UNICODE character's first byte

   135

 * @note The function should not be used to determine the length of the previous

   136

 * encoded char because it might be an invalid/corrupt start-sequence

   137

 */

   138

static inline char *Utf8PrevChar(const char *s)

   139

{

   140

	const char *ret = s;

   141

	while (IsUtf8Part(*--ret));

   142

	return (char*)ret;

   143

}

   144

   145

   146

static inline bool IsPrintable(WChar c)

   147

{

   148

	if (c < 0x20)   return false;

   149

	if (c < 0xE000) return true;

   150

	if (c < 0xE200) return false;

   151

	return true;

   152

}

   153

   154

/**

   155

 * Check whether UNICODE character is whitespace or not

   156

 * @param c UNICODE character to check

   157

 * @return a boolean value whether 'c' is a whitespace character or not

   158

 * @see http://www.fileformat.info/info/unicode/category/Zs/list.htm

   159

 */

   160

static inline bool IsWhitespace(WChar c)

   161

{

   162

	return

   163

	  c == 0x0020 /* SPACE */ ||

   164

	  c == 0x00A0 /* NO-BREAK SPACE */ ||

   165

	  c == 0x3000 /* IDEOGRAPHIC SPACE */

   166

	;

   167

}

   168

   169

   170

#endif /* STRING_H */