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