1

/* $Id$ */

     2

     3

#ifndef STRING_H

     4

#define STRING_H

     5

     6

#include "macros.h"

     7

     8

/*

     9

 * dst: destination buffer

    10

 * src: string to copy/concatenate

    11

 * size: size of the destination buffer

    12

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

    13

 */

    14

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

    15

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

    16

    17

/*

    18

 * dst: destination buffer

    19

 * src: string to copy

    20

 * last: pointer to the last element in the dst array

    21

 *       if NULL no boundary check is performed

    22

 * returns a pointer to the terminating \0 in the destination buffer

    23

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

    24

 */

    25

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

    26

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

    27

    28

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

    29

    30

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

    31

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

    32

void str_validate(char *str);

    33

    34

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

    35

void str_strip_colours(char *str);

    36

    37

/**

    38

 * Valid filter types for IsValidChar.

    39

 */

    40

enum CharSetFilter {

    41

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

    42

	CS_NUMERAL,           //! Only numeric ones

    43

	CS_ALPHA,             //! Only alphabetic values

    44

};

    45

    46

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

    47

void strtolower(char *str);

    48

    49

    50

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

    51

    52

    53

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

    54

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

    55

{

    56

	const char *t;

    57

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

    58

	return t - str;

    59

}

    60

    61

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

    62

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

    63

    64

typedef uint32 WChar;

    65

    66

/**

    67

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

    68

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

    69

 * @param key character to be checked

    70

 * @param afilter the filter to use

    71

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

    72

 */

    73

bool IsValidChar(WChar key, CharSetFilter afilter);

    74

    75

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

    76

size_t Utf8Encode(char *buf, WChar c);

    77

size_t Utf8TrimString(char *s, size_t maxlen);

    78

    79

    80

static inline WChar Utf8Consume(const char **s)

    81

{

    82

	WChar c;

    83

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

    84

	return c;

    85

}

    86

    87

    88

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

    89

 * @param c Unicode character.

    90

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

    91

 */

    92

static inline size_t Utf8CharLen(WChar c)

    93

{

    94

	if (c < 0x80)       return 1;

    95

	if (c < 0x800)      return 2;

    96

	if (c < 0x10000)    return 3;

    97

	if (c < 0x110000)   return 4;

    98

    99

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

   100

	return 1;

   101

}

   102

   103

   104

/**

   105

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

   106

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

   107

 * is invalid, return value is 0

   108

 */

   109

static inline size_t Utf8EncodedCharLen(char c)

   110

{

   111

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

   112

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

   113

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

   114

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

   115

   116

	/* Invalid UTF8 start encoding */

   117

	return 0;

   118

}

   119

   120

   121

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

   122

static inline bool IsUtf8Part(char c)

   123

{

   124

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

   125

}

   126

   127

/**

   128

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

   129

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

   130

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

   131

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

   132

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

   133

 */

   134

static inline char *Utf8PrevChar(const char *s)

   135

{

   136

	const char *ret = s;

   137

	while (IsUtf8Part(*--ret));

   138

	return (char*)ret;

   139

}

   140

   141

   142

static inline bool IsPrintable(WChar c)

   143

{

   144

	if (c < 0x20)   return false;

   145

	if (c < 0xE000) return true;

   146

	if (c < 0xE200) return false;

   147

	return true;

   148

}

   149

   150

/**

   151

 * Check whether UNICODE character is whitespace or not

   152

 * @param c UNICODE character to check

   153

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

   154

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

   155

 */

   156

static inline bool IsWhitespace(WChar c)

   157

{

   158

	return

   159

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

   160

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

   161

	  c == 0x3000 /* IDEOGRAPHIC SPACE */

   162

	;

   163

}

   164

   165

   166

#endif /* STRING_H */