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

typedef 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

} CharSetFilter;

    45

    46

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

    47

void strtolower(char *str);

    48

    49

    50

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

    51

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

    52

{

    53

	const char *t;

    54

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

    55

	return t - str;

    56

}

    57

    58

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

    59

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

    60

    61

typedef uint32 WChar;

    62

    63

/**

    64

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

    65

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

    66

 * @param key character to be checked

    67

 * @param afilter the filter to use

    68

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

    69

 */

    70

bool IsValidChar(WChar key, CharSetFilter afilter);

    71

    72

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

    73

size_t Utf8Encode(char *buf, WChar c);

    74

size_t Utf8TrimString(char *s, size_t maxlen);

    75

    76

    77

static inline WChar Utf8Consume(const char **s)

    78

{

    79

	WChar c;

    80

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

    81

	return c;

    82

}

    83

    84

    85

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

    86

 * @param c Unicode character.

    87

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

    88

 */

    89

static inline size_t Utf8CharLen(WChar c)

    90

{

    91

	if (c < 0x80)       return 1;

    92

	if (c < 0x800)      return 2;

    93

	if (c < 0x10000)    return 3;

    94

	if (c < 0x110000)   return 4;

    95

    96

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

    97

	return 1;

    98

}

    99

   100

   101

/**

   102

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

   103

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

   104

 * is invalid, return value is 0

   105

 */

   106

static inline size_t Utf8EncodedCharLen(char c)

   107

{

   108

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

   109

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

   110

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

   111

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

   112

   113

	/* Invalid UTF8 start encoding */

   114

	return 0;

   115

}

   116

   117

   118

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

   119

static inline bool IsUtf8Part(char c)

   120

{

   121

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

   122

}

   123

   124

/**

   125

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

   126

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

   127

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

   128

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

   129

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

   130

 */

   131

static inline char *Utf8PrevChar(const char *s)

   132

{

   133

	const char *ret = s;

   134

	while (IsUtf8Part(*--ret));

   135

	return (char*)ret;

   136

}

   137

   138

   139

static inline bool IsPrintable(WChar c)

   140

{

   141

	if (c < 0x20)   return false;

   142

	if (c < 0xE000) return true;

   143

	if (c < 0xE200) return false;

   144

	return true;

   145

}

   146

   147

/**

   148

 * Check whether UNICODE character is whitespace or not

   149

 * @param c UNICODE character to check

   150

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

   151

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

   152

 */

   153

static inline bool IsWhitespace(WChar c)

   154

{

   155

	return

   156

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

   157

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

   158

	  c == 0x3000 /* IDEOGRAPHIC SPACE */

   159

	;

   160

}

   161

   162

   163

#endif /* STRING_H */