3 Copyright (C) 2010-2013 celeron55, Perttu Ahola <celeron55@gmail.com>
5 This program is free software; you can redistribute it and/or modify
6 it under the terms of the GNU Lesser General Public License as published by
7 the Free Software Foundation; either version 2.1 of the License, or
8 (at your option) any later version.
10 This program is distributed in the hope that it will be useful,
11 but WITHOUT ANY WARRANTY; without even the implied warranty of
12 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13 GNU Lesser General Public License for more details.
15 You should have received a copy of the GNU Lesser General Public License along
16 with this program; if not, write to the Free Software Foundation, Inc.,
17 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
22 #include "irrlichttypes_bloated.h"
23 #include "irrString.h"
32 #include <unordered_map>
36 #define STRINGIFY(x) #x
37 #define TOSTRING(x) STRINGIFY(x)
39 // Checks whether a value is an ASCII printable character
40 #define IS_ASCII_PRINTABLE_CHAR(x) \
41 (((unsigned int)(x) >= 0x20) && \
42 ( (unsigned int)(x) <= 0x7e))
44 // Checks whether a byte is an inner byte for an utf-8 multibyte sequence
45 #define IS_UTF8_MULTB_INNER(x) \
46 (((unsigned char)(x) >= 0x80) && \
47 ( (unsigned char)(x) <= 0xbf))
49 // Checks whether a byte is a start byte for an utf-8 multibyte sequence
50 #define IS_UTF8_MULTB_START(x) \
51 (((unsigned char)(x) >= 0xc2) && \
52 ( (unsigned char)(x) <= 0xf4))
54 // Given a start byte x for an utf-8 multibyte sequence
55 // it gives the length of the whole sequence in bytes.
56 #define UTF8_MULTB_START_LEN(x) \
57 (((unsigned char)(x) < 0xe0) ? 2 : \
58 (((unsigned char)(x) < 0xf0) ? 3 : 4))
60 typedef std::unordered_map
<std::string
, std::string
> StringMap
;
67 // try not to convert between wide/utf8 encodings; this can result in data loss
68 // try to only convert between them when you need to input/output stuff via Irrlicht
69 std::wstring
utf8_to_wide(const std::string
&input
);
70 std::string
wide_to_utf8(const std::wstring
&input
);
72 wchar_t *utf8_to_wide_c(const char *str
);
74 // NEVER use those two functions unless you have a VERY GOOD reason to
75 // they just convert between wide and multibyte encoding
76 // multibyte encoding depends on current locale, this is no good, especially on Windows
78 // You must free the returned string!
79 // The returned string is allocated using new
80 wchar_t *narrow_to_wide_c(const char *str
);
81 std::wstring
narrow_to_wide(const std::string
&mbs
);
82 std::string
wide_to_narrow(const std::wstring
&wcs
);
84 std::string
urlencode(const std::string
&str
);
85 std::string
urldecode(const std::string
&str
);
86 u32
readFlagString(std::string str
, const FlagDesc
*flagdesc
, u32
*flagmask
);
87 std::string
writeFlagString(u32 flags
, const FlagDesc
*flagdesc
, u32 flagmask
);
88 size_t mystrlcpy(char *dst
, const char *src
, size_t size
);
89 char *mystrtok_r(char *s
, const char *sep
, char **lasts
);
90 u64
read_seed(const char *str
);
91 bool parseColorString(const std::string
&value
, video::SColor
&color
, bool quiet
,
92 unsigned char default_alpha
= 0xff);
96 * Returns a copy of \p str with spaces inserted at the right hand side to ensure
97 * that the string is \p len characters in length. If \p str is <= \p len then the
98 * returned string will be identical to str.
100 inline std::string
padStringRight(std::string str
, size_t len
)
102 if (len
> str
.size())
103 str
.insert(str
.end(), len
- str
.size(), ' ');
109 * Returns a version of \p str with the first occurrence of a string
110 * contained within ends[] removed from the end of the string.
113 * @param ends A NULL- or ""- terminated array of strings to remove from s in
114 * the copy produced. Note that once one of these strings is removed
115 * that no further postfixes contained within this array are removed.
117 * @return If no end could be removed then "" is returned.
119 inline std::string
removeStringEnd(const std::string
&str
,
122 const char **p
= ends
;
124 for (; *p
&& (*p
)[0] != '\0'; p
++) {
125 std::string end
= *p
;
126 if (str
.size() < end
.size())
128 if (str
.compare(str
.size() - end
.size(), end
.size(), end
) == 0)
129 return str
.substr(0, str
.size() - end
.size());
137 * Check two strings for equivalence. If \p case_insensitive is true
138 * then the case of the strings is ignored (default is false).
142 * @param case_insensitive
143 * @return true if the strings match
145 template <typename T
>
146 inline bool str_equal(const std::basic_string
<T
> &s1
,
147 const std::basic_string
<T
> &s2
,
148 bool case_insensitive
= false)
150 if (!case_insensitive
)
153 if (s1
.size() != s2
.size())
156 for (size_t i
= 0; i
< s1
.size(); ++i
)
157 if(tolower(s1
[i
]) != tolower(s2
[i
]))
165 * Check whether \p str begins with the string prefix. If \p case_insensitive
166 * is true then the check is case insensitve (default is false; i.e. case is
171 * @param case_insensitive
172 * @return true if the str begins with prefix
174 template <typename T
>
175 inline bool str_starts_with(const std::basic_string
<T
> &str
,
176 const std::basic_string
<T
> &prefix
,
177 bool case_insensitive
= false)
179 if (str
.size() < prefix
.size())
182 if (!case_insensitive
)
183 return str
.compare(0, prefix
.size(), prefix
) == 0;
185 for (size_t i
= 0; i
< prefix
.size(); ++i
)
186 if (tolower(str
[i
]) != tolower(prefix
[i
]))
192 * Check whether \p str begins with the string prefix. If \p case_insensitive
193 * is true then the check is case insensitve (default is false; i.e. case is
198 * @param case_insensitive
199 * @return true if the str begins with prefix
201 template <typename T
>
202 inline bool str_starts_with(const std::basic_string
<T
> &str
,
204 bool case_insensitive
= false)
206 return str_starts_with(str
, std::basic_string
<T
>(prefix
),
212 * Check whether \p str ends with the string suffix. If \p case_insensitive
213 * is true then the check is case insensitve (default is false; i.e. case is
218 * @param case_insensitive
219 * @return true if the str begins with suffix
221 template <typename T
>
222 inline bool str_ends_with(const std::basic_string
<T
> &str
,
223 const std::basic_string
<T
> &suffix
,
224 bool case_insensitive
= false)
226 if (str
.size() < suffix
.size())
229 size_t start
= str
.size() - suffix
.size();
230 if (!case_insensitive
)
231 return str
.compare(start
, suffix
.size(), suffix
) == 0;
233 for (size_t i
= 0; i
< suffix
.size(); ++i
)
234 if (tolower(str
[start
+ i
]) != tolower(suffix
[i
]))
241 * Check whether \p str ends with the string suffix. If \p case_insensitive
242 * is true then the check is case insensitve (default is false; i.e. case is
247 * @param case_insensitive
248 * @return true if the str begins with suffix
250 template <typename T
>
251 inline bool str_ends_with(const std::basic_string
<T
> &str
,
253 bool case_insensitive
= false)
255 return str_ends_with(str
, std::basic_string
<T
>(suffix
),
261 * Splits a string into its component parts separated by the character
264 * @return An std::vector<std::basic_string<T> > of the component parts
266 template <typename T
>
267 inline std::vector
<std::basic_string
<T
> > str_split(
268 const std::basic_string
<T
> &str
,
271 std::vector
<std::basic_string
<T
> > parts
;
272 std::basic_stringstream
<T
> sstr(str
);
273 std::basic_string
<T
> part
;
275 while (std::getline(sstr
, part
, delimiter
))
276 parts
.push_back(part
);
284 * @return A copy of \p str converted to all lowercase characters.
286 inline std::string
lowercase(const std::string
&str
)
290 s2
.reserve(str
.size());
301 * @return A copy of \p str with leading and trailing whitespace removed.
303 inline std::string
trim(const std::string
&str
)
307 while (std::isspace(str
[front
]))
310 size_t back
= str
.size();
311 while (back
> front
&& std::isspace(str
[back
- 1]))
314 return str
.substr(front
, back
- front
);
319 * Returns whether \p str should be regarded as (bool) true. Case and leading
320 * and trailing whitespace are ignored. Values that will return
321 * true are "y", "yes", "true" and any number that is not 0.
324 inline bool is_yes(const std::string
&str
)
326 std::string s2
= lowercase(trim(str
));
328 return s2
== "y" || s2
== "yes" || s2
== "true" || atoi(s2
.c_str()) != 0;
333 * Converts the string \p str to a signed 32-bit integer. The converted value
334 * is constrained so that min <= value <= max.
336 * @see atoi(3) for limitations
339 * @param min Range minimum
340 * @param max Range maximum
341 * @return The value converted to a signed 32-bit integer and constrained
342 * within the range defined by min and max (inclusive)
344 inline s32
mystoi(const std::string
&str
, s32 min
, s32 max
)
346 s32 i
= atoi(str
.c_str());
357 // MSVC2010 includes it's own versions of these
358 //#if !defined(_MSC_VER) || _MSC_VER < 1600
362 * Returns a 32-bit value reprensented by the string \p str (decimal).
363 * @see atoi(3) for further limitations
365 inline s32
mystoi(const std::string
&str
)
367 return atoi(str
.c_str());
372 * Returns s 32-bit value represented by the wide string \p str (decimal).
373 * @see atoi(3) for further limitations
375 inline s32
mystoi(const std::wstring
&str
)
377 return mystoi(wide_to_narrow(str
));
382 * Returns a float reprensented by the string \p str (decimal).
385 inline float mystof(const std::string
&str
)
387 return atof(str
.c_str());
395 /// Returns a value represented by the string \p val.
396 template <typename T
>
397 inline T
from_string(const std::string
&str
)
399 std::stringstream
tmp(str
);
405 /// Returns a 64-bit signed value represented by the string \p str (decimal).
406 inline s64
stoi64(const std::string
&str
) { return from_string
<s64
>(str
); }
408 #if __cplusplus < 201103L
411 /// Returns a string representing the value \p val.
412 template <typename T
>
413 inline string
to_string(T val
)
419 #define DEFINE_STD_TOSTRING_FLOATINGPOINT(T) \
421 inline string to_string<T>(T val) \
425 << std::setprecision(6) \
429 DEFINE_STD_TOSTRING_FLOATINGPOINT(float)
430 DEFINE_STD_TOSTRING_FLOATINGPOINT(double)
431 DEFINE_STD_TOSTRING_FLOATINGPOINT(long double)
433 #undef DEFINE_STD_TOSTRING_FLOATINGPOINT
435 /// Returns a wide string representing the value \p val
436 template <typename T
>
437 inline wstring
to_wstring(T val
)
439 return utf8_to_wide(to_string(val
));
444 /// Returns a string representing the decimal value of the 32-bit value \p i.
445 inline std::string
itos(s32 i
) { return std::to_string(i
); }
446 /// Returns a string representing the decimal value of the 64-bit value \p i.
447 inline std::string
i64tos(s64 i
) { return std::to_string(i
); }
449 // std::to_string uses the '%.6f' conversion, which is inconsistent with
450 // std::ostream::operator<<() and impractical too. ftos() uses the
451 // more generic and std::ostream::operator<<()-compatible '%G' format.
452 /// Returns a string representing the decimal value of the float value \p f.
453 inline std::string
ftos(float f
)
455 std::ostringstream oss
;
462 * Replace all occurrences of \p pattern in \p str with \p replacement.
464 * @param str String to replace pattern with replacement within.
465 * @param pattern The pattern to replace.
466 * @param replacement What to replace the pattern with.
468 inline void str_replace(std::string
&str
, const std::string
&pattern
,
469 const std::string
&replacement
)
471 std::string::size_type start
= str
.find(pattern
, 0);
472 while (start
!= str
.npos
) {
473 str
.replace(start
, pattern
.size(), replacement
);
474 start
= str
.find(pattern
, start
+ replacement
.size());
479 * Escapes characters [ ] \ , ; that can not be used in formspecs
481 inline void str_formspec_escape(std::string
&str
)
483 str_replace(str
, "\\", "\\\\");
484 str_replace(str
, "]", "\\]");
485 str_replace(str
, "[", "\\[");
486 str_replace(str
, ";", "\\;");
487 str_replace(str
, ",", "\\,");
491 * Replace all occurrences of the character \p from in \p str with \p to.
493 * @param str The string to (potentially) modify.
494 * @param from The character in str to replace.
495 * @param to The replacement character.
497 void str_replace(std::string
&str
, char from
, char to
);
501 * Check that a string only contains whitelisted characters. This is the
502 * opposite of string_allowed_blacklist().
504 * @param str The string to be checked.
505 * @param allowed_chars A string containing permitted characters.
506 * @return true if the string is allowed, otherwise false.
508 * @see string_allowed_blacklist()
510 inline bool string_allowed(const std::string
&str
, const std::string
&allowed_chars
)
512 return str
.find_first_not_of(allowed_chars
) == str
.npos
;
517 * Check that a string contains no blacklisted characters. This is the
518 * opposite of string_allowed().
520 * @param str The string to be checked.
521 * @param blacklisted_chars A string containing prohibited characters.
522 * @return true if the string is allowed, otherwise false.
524 * @see string_allowed()
526 inline bool string_allowed_blacklist(const std::string
&str
,
527 const std::string
&blacklisted_chars
)
529 return str
.find_first_of(blacklisted_chars
) == str
.npos
;
534 * Create a string based on \p from where a newline is forcefully inserted
535 * every \p row_len characters.
537 * @note This function does not honour word wraps and blindy inserts a newline
538 * every \p row_len characters whether it breaks a word or not. It is
539 * intended to be used for, for example, showing paths in the GUI.
541 * @note This function doesn't wrap inside utf-8 multibyte sequences and also
542 * counts multibyte sequences correcly as single characters.
544 * @param from The (utf-8) string to be wrapped into rows.
545 * @param row_len The row length (in characters).
546 * @return A new string with the wrapping applied.
548 inline std::string
wrap_rows(const std::string
&from
,
553 size_t character_idx
= 0;
554 for (size_t i
= 0; i
< from
.size(); i
++) {
555 if (!IS_UTF8_MULTB_INNER(from
[i
])) {
556 // Wrap string after last inner byte of char
557 if (character_idx
> 0 && character_idx
% row_len
== 0)
569 * Removes backslashes from an escaped string (FormSpec strings)
571 template <typename T
>
572 inline std::basic_string
<T
> unescape_string(const std::basic_string
<T
> &s
)
574 std::basic_string
<T
> res
;
576 for (size_t i
= 0; i
< s
.length(); i
++) {
589 * Remove all escape sequences in \p s.
591 * @param s The string in which to remove escape sequences.
592 * @return \p s, with escape sequences removed.
594 template <typename T
>
595 std::basic_string
<T
> unescape_enriched(const std::basic_string
<T
> &s
)
597 std::basic_string
<T
> output
;
599 while (i
< s
.length()) {
600 if (s
[i
] == '\x1b') {
602 if (i
== s
.length()) continue;
605 while (i
< s
.length() && s
[i
] != ')') {
623 template <typename T
>
624 std::vector
<std::basic_string
<T
> > split(const std::basic_string
<T
> &s
, T delim
)
626 std::vector
<std::basic_string
<T
> > tokens
;
628 std::basic_string
<T
> current
;
629 bool last_was_escape
= false;
630 for (size_t i
= 0; i
< s
.length(); i
++) {
632 if (last_was_escape
) {
635 last_was_escape
= false;
638 tokens
.push_back(current
);
639 current
= std::basic_string
<T
>();
640 last_was_escape
= false;
641 } else if (si
== '\\') {
642 last_was_escape
= true;
645 last_was_escape
= false;
650 tokens
.push_back(current
);
655 std::wstring
translate_string(const std::wstring
&s
, Translations
*translations
);
657 std::wstring
translate_string(const std::wstring
&s
);
659 inline std::wstring
unescape_translate(const std::wstring
&s
) {
660 return unescape_enriched(translate_string(s
));
664 * Checks that all characters in \p to_check are a decimal digits.
667 * @return true if to_check is not empty and all characters in to_check are
668 * decimal digits, otherwise false
670 inline bool is_number(const std::string
&to_check
)
672 for (char i
: to_check
)
673 if (!std::isdigit(i
))
676 return !to_check
.empty();
681 * Returns a C-string, either "true" or "false", corresponding to \p val.
683 * @return If \p val is true, then "true" is returned, otherwise "false".
685 inline const char *bool_to_cstr(bool val
)
687 return val
? "true" : "false";
690 inline const std::string
duration_to_string(int sec
)
697 std::stringstream ss
;
714 * Joins a vector of strings by the string \p delimiter.
716 * @return A std::string
718 inline std::string
str_join(const std::vector
<std::string
> &list
,
719 const std::string
&delimiter
)
721 std::ostringstream oss
;
723 for (const auto &part
: list
) {
733 * Create a UTF8 std::string from a irr::core::stringw.
735 inline std::string
stringw_to_utf8(const irr::core::stringw
&input
)
737 std::wstring
str(input
.c_str());
738 return wide_to_utf8(str
);
742 * Create a irr::core:stringw from a UTF8 std::string.
744 inline irr::core::stringw
utf8_to_stringw(const std::string
&input
)
746 std::wstring str
= utf8_to_wide(input
);
747 return irr::core::stringw(str
.c_str());
751 * Sanitize the name of a new directory. This consists of two stages:
752 * 1. Check for 'reserved filenames' that can't be used on some filesystems
754 * 2. Remove 'unsafe' characters from the name by replacing them with '_'
756 std::string
sanitizeDirName(const std::string
&str
, const std::string
&optional_prefix
);