src/string_func.h

   1 /*
   2  * This file is part of OpenTTD.
   3  * 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.
   4  * 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.
   5  * 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/>.
   6  */
   7
   8 /**
   9  * @file string_func.h Functions related to low-level strings.
  10  */
  11
  12 #ifndef STRING_FUNC_H
  13 #define STRING_FUNC_H
  14
  15 #include <iosfwd>
  16
  17 #include "core/bitmath_func.hpp"
  18 #include "string_type.h"
  19
  20 char *strecpy(char *dst, const char *src, const char *last) NOACCESS(3);
  21
  22 std::string FormatArrayAsHex(std::span<const byte> data);
  23
  24 void StrMakeValidInPlace(char *str, const char *last, StringValidationSettings settings = SVS_REPLACE_WITH_QUESTION_MARK) NOACCESS(2);
  25 [[nodiscard]] std::string StrMakeValid(std::string_view str, StringValidationSettings settings = SVS_REPLACE_WITH_QUESTION_MARK);
  26 void StrMakeValidInPlace(char *str, StringValidationSettings settings = SVS_REPLACE_WITH_QUESTION_MARK);
  27
  28 bool strtolower(std::string &str, std::string::size_type offs = 0);
  29
  30 [[nodiscard]] bool StrValid(const char *str, const char *last) NOACCESS(2);
  31 void StrTrimInPlace(std::string &str);
  32
  33 [[nodiscard]] bool StrStartsWithIgnoreCase(std::string_view str, const std::string_view prefix);
  34 [[nodiscard]] bool StrEndsWithIgnoreCase(std::string_view str, const std::string_view suffix);
  35
  36 [[nodiscard]] int StrCompareIgnoreCase(const std::string_view str1, const std::string_view str2);
  37 [[nodiscard]] bool StrEqualsIgnoreCase(const std::string_view str1, const std::string_view str2);
  38 [[nodiscard]] int StrNaturalCompare(std::string_view s1, std::string_view s2, bool ignore_garbage_at_front = false);
  39 [[nodiscard]] bool StrNaturalContains(const std::string_view str, const std::string_view value);
  40 [[nodiscard]] bool StrNaturalContainsIgnoreCase(const std::string_view str, const std::string_view value);
  41
  42 bool ConvertHexToBytes(std::string_view hex, std::span<uint8_t> bytes);
  43
  44 /** Case insensitive comparator for strings, for example for use in std::map. */
  45 struct CaseInsensitiveComparator {
  46         bool operator()(const std::string_view s1, const std::string_view s2) const { return StrCompareIgnoreCase(s1, s2) < 0; }
  47 };
  48
  49 /**
  50  * Check if a string buffer is empty.
  51  *
  52  * @param s The pointer to the first element of the buffer
  53  * @return true if the buffer starts with the terminating null-character or
  54  *         if the given pointer points to nullptr else return false
  55  */
  56 inline bool StrEmpty(const char *s)
  57 {
  58         return s == nullptr || s[0] == '\0';
  59 }
  60
  61 /**
  62  * Get the length of a string, within a limited buffer.
  63  *
  64  * @param str The pointer to the first element of the buffer
  65  * @param maxlen The maximum size of the buffer
  66  * @return The length of the string
  67  */
  68 inline size_t ttd_strnlen(const char *str, size_t maxlen)
  69 {
  70         const char *t;
  71         for (t = str; (size_t)(t - str) < maxlen && *t != '\0'; t++) {}
  72         return t - str;
  73 }
  74
  75 bool IsValidChar(char32_t key, CharSetFilter afilter);
  76
  77 size_t Utf8Decode(char32_t *c, const char *s);
  78 size_t Utf8Encode(char *buf, char32_t c);
  79 size_t Utf8Encode(std::ostreambuf_iterator<char> &buf, char32_t c);
  80 size_t Utf8Encode(std::back_insert_iterator<std::string> &buf, char32_t c);
  81 size_t Utf8TrimString(char *s, size_t maxlen);
  82
  83
  84 inline char32_t Utf8Consume(const char **s)
  85 {
  86         char32_t c;
  87         *s += Utf8Decode(&c, *s);
  88         return c;
  89 }
  90
  91 template <class Titr>
  92 inline char32_t Utf8Consume(Titr &s)
  93 {
  94         char32_t c;
  95         s += Utf8Decode(&c, &*s);
  96         return c;
  97 }
  98
  99 /**
 100  * Return the length of a UTF-8 encoded character.
 101  * @param c Unicode character.
 102  * @return Length of UTF-8 encoding for character.
 103  */
 104 inline int8_t Utf8CharLen(char32_t c)
 105 {
 106         if (c < 0x80)       return 1;
 107         if (c < 0x800)      return 2;
 108         if (c < 0x10000)    return 3;
 109         if (c < 0x110000)   return 4;
 110
 111         /* Invalid valid, we encode as a '?' */
 112         return 1;
 113 }
 114
 115
 116 /**
 117  * Return the length of an UTF-8 encoded value based on a single char. This
 118  * char should be the first byte of the UTF-8 encoding. If not, or encoding
 119  * is invalid, return value is 0
 120  * @param c char to query length of
 121  * @return requested size
 122  */
 123 inline int8_t Utf8EncodedCharLen(char c)
 124 {
 125         if (GB(c, 3, 5) == 0x1E) return 4;
 126         if (GB(c, 4, 4) == 0x0E) return 3;
 127         if (GB(c, 5, 3) == 0x06) return 2;
 128         if (GB(c, 7, 1) == 0x00) return 1;
 129
 130         /* Invalid UTF8 start encoding */
 131         return 0;
 132 }
 133
 134
 135 /* Check if the given character is part of a UTF8 sequence */
 136 inline bool IsUtf8Part(char c)
 137 {
 138         return GB(c, 6, 2) == 2;
 139 }
 140
 141 /**
 142  * Retrieve the previous UNICODE character in an UTF-8 encoded string.
 143  * @param s char pointer pointing to (the first char of) the next character
 144  * @return a pointer in 's' to the previous UNICODE character's first byte
 145  * @note The function should not be used to determine the length of the previous
 146  * encoded char because it might be an invalid/corrupt start-sequence
 147  */
 148 inline char *Utf8PrevChar(char *s)
 149 {
 150         char *ret = s;
 151         while (IsUtf8Part(*--ret)) {}
 152         return ret;
 153 }
 154
 155 inline const char *Utf8PrevChar(const char *s)
 156 {
 157         const char *ret = s;
 158         while (IsUtf8Part(*--ret)) {}
 159         return ret;
 160 }
 161
 162 size_t Utf8StringLength(const char *s);
 163 size_t Utf8StringLength(const std::string &str);
 164
 165 /**
 166  * Is the given character a lead surrogate code point?
 167  * @param c The character to test.
 168  * @return True if the character is a lead surrogate code point.
 169  */
 170 inline bool Utf16IsLeadSurrogate(uint c)
 171 {
 172         return c >= 0xD800 && c <= 0xDBFF;
 173 }
 174
 175 /**
 176  * Is the given character a lead surrogate code point?
 177  * @param c The character to test.
 178  * @return True if the character is a lead surrogate code point.
 179  */
 180 inline bool Utf16IsTrailSurrogate(uint c)
 181 {
 182         return c >= 0xDC00 && c <= 0xDFFF;
 183 }
 184
 185 /**
 186  * Convert an UTF-16 surrogate pair to the corresponding Unicode character.
 187  * @param lead Lead surrogate code point.
 188  * @param trail Trail surrogate code point.
 189  * @return Decoded Unicode character.
 190  */
 191 inline char32_t Utf16DecodeSurrogate(uint lead, uint trail)
 192 {
 193         return 0x10000 + (((lead - 0xD800) << 10) | (trail - 0xDC00));
 194 }
 195
 196 /**
 197  * Decode an UTF-16 character.
 198  * @param c Pointer to one or two UTF-16 code points.
 199  * @return Decoded Unicode character.
 200  */
 201 inline char32_t Utf16DecodeChar(const uint16_t *c)
 202 {
 203         if (Utf16IsLeadSurrogate(c[0])) {
 204                 return Utf16DecodeSurrogate(c[0], c[1]);
 205         } else {
 206                 return *c;
 207         }
 208 }
 209
 210 /**
 211  * Is the given character a text direction character.
 212  * @param c The character to test.
 213  * @return true iff the character is used to influence
 214  *         the text direction.
 215  */
 216 inline bool IsTextDirectionChar(char32_t c)
 217 {
 218         switch (c) {
 219                 case CHAR_TD_LRM:
 220                 case CHAR_TD_RLM:
 221                 case CHAR_TD_LRE:
 222                 case CHAR_TD_RLE:
 223                 case CHAR_TD_LRO:
 224                 case CHAR_TD_RLO:
 225                 case CHAR_TD_PDF:
 226                         return true;
 227
 228                 default:
 229                         return false;
 230         }
 231 }
 232
 233 inline bool IsPrintable(char32_t c)
 234 {
 235         if (c < 0x20)   return false;
 236         if (c < 0xE000) return true;
 237         if (c < 0xE200) return false;
 238         return true;
 239 }
 240
 241 /**
 242  * Check whether UNICODE character is whitespace or not, i.e. whether
 243  * this is a potential line-break character.
 244  * @param c UNICODE character to check
 245  * @return a boolean value whether 'c' is a whitespace character or not
 246  * @see http://www.fileformat.info/info/unicode/category/Zs/list.htm
 247  */
 248 inline bool IsWhitespace(char32_t c)
 249 {
 250         return c == 0x0020 /* SPACE */ || c == 0x3000; /* IDEOGRAPHIC SPACE */
 251 }
 252
 253 /* Needed for NetBSD version (so feature) testing */
 254 #if defined(__NetBSD__) || defined(__FreeBSD__)
 255 #include <sys/param.h>
 256 #endif
 257
 258 /* strcasestr is available for _GNU_SOURCE, BSD and some Apple */
 259 #if defined(_GNU_SOURCE) || (defined(__BSD_VISIBLE) && __BSD_VISIBLE) || (defined(__APPLE__) && (!defined(_POSIX_C_SOURCE) || defined(_DARWIN_C_SOURCE))) || defined(_NETBSD_SOURCE)
 260 #       undef DEFINE_STRCASESTR
 261 #else
 262 #       define DEFINE_STRCASESTR
 263 char *strcasestr(const char *haystack, const char *needle);
 264 #endif /* strcasestr is available */
 265
 266 #endif /* STRING_FUNC_H */