17 #include "string_base.h" 30 #include <unicode/ustring.h> 50 int CDECL
vseprintf(
char *str,
const char *last,
const char *format, va_list ap)
52 ptrdiff_t diff = last - str;
53 if (diff < 0)
return 0;
54 return min((
int)diff, vsnprintf(str, diff + 1, format, ap));
73 char *
strecat(
char *dst,
const char *src,
const char *last)
76 while (*dst !=
'\0') {
77 if (dst == last)
return dst;
101 char *
strecpy(
char *dst,
const char *src,
const char *last)
104 while (dst != last && *src !=
'\0') {
109 if (dst == last && *src !=
'\0') {
110 #if defined(STRGEN) || defined(SETTINGSGEN) 111 error(
"String too long for destination buffer");
113 DEBUG(misc, 0,
"String too long for destination buffer");
126 char *
stredup(
const char *s,
const char *last)
128 size_t len = last == NULL ? strlen(s) :
ttd_strnlen(s, last - s + 1);
129 char *tmp = CallocT<char>(len + 1);
147 char *p = MallocT<char>(len + 1);
148 memcpy(p, buf, len + 1);
160 while (str <= last && *str !=
'\0') {
162 if ((len == 0 && str + 4 > last) || str + len > last)
break;
166 if (c ==
'\0')
break;
168 if (c == 0xE028 || c == 0xE02A) {
189 while (str <= last && *str !=
'\0') {
196 if ((len == 0 && str + 4 > last) || str + len > last)
break;
203 if (c ==
'\0')
break;
205 if ((IsPrintable(c) && (c < SCC_SPRITE_START || c > SCC_SPRITE_END)) || ((settings &
SVS_ALLOW_CONTROL_CODE) != 0 && c == SCC_ENCODED)) {
211 }
while (--len != 0);
215 if ((settings & SVS_ALLOW_NEWLINE) != 0 && c ==
'\r' && str[1] ==
'\n') {
236 str_validate(const_cast<char *>(str), str + strlen(str) + 1);
251 while (str <= last && *str !=
'\0') {
257 if (len == 0 || str + len > last)
return false;
261 if (!IsPrintable(c) || (c >= SCC_SPRITE_START && c <= SCC_SPRITE_END)) {
279 if (c < SCC_BLUE || c > SCC_BLACK) {
285 }
while (--len != 0);
304 while (Utf8Consume(&t) != 0) len++;
322 bool changed =
false;
323 for (; *str !=
'\0'; str++) {
324 char new_str = tolower(*str);
325 changed |= new_str != *str;
342 case CS_NUMERAL:
return (key >=
'0' && key <=
'9');
344 case CS_ALPHA:
return IsPrintable(key) && !(key >=
'0' && key <=
'9');
345 case CS_HEXADECIMAL:
return (key >=
'0' && key <=
'9') || (key >=
'a' && key <= 'f') || (key >=
'A' && key <=
'F');
352 #if defined(_MSC_VER) && _MSC_VER < 1900 360 int CDECL vsnprintf(
char *str,
size_t size,
const char *format, va_list ap)
362 if (size == 0)
return 0;
365 int ret = _vsnprintf(str, size, format, ap);
368 if (errno != ERANGE) {
373 }
else if ((
size_t)ret < size) {
382 str[size - 1] =
'\0';
398 int CDECL
seprintf(
char *str,
const char *last,
const char *format, ...)
402 va_start(ap, format);
403 int ret =
vseprintf(str, last, format, ap);
420 for (uint i = 0; i < 16; i++) {
421 p +=
seprintf(p, last,
"%02X", md5sum[i]);
445 }
else if (
GB(s[0], 5, 3) == 6) {
446 if (IsUtf8Part(s[1])) {
448 *c =
GB(s[0], 0, 5) << 6 |
GB(s[1], 0, 6);
449 if (*c >= 0x80)
return 2;
451 }
else if (
GB(s[0], 4, 4) == 14) {
452 if (IsUtf8Part(s[1]) && IsUtf8Part(s[2])) {
454 *c =
GB(s[0], 0, 4) << 12 |
GB(s[1], 0, 6) << 6 |
GB(s[2], 0, 6);
455 if (*c >= 0x800)
return 3;
457 }
else if (
GB(s[0], 3, 5) == 30) {
458 if (IsUtf8Part(s[1]) && IsUtf8Part(s[2]) && IsUtf8Part(s[3])) {
460 *c =
GB(s[0], 0, 3) << 18 |
GB(s[1], 0, 6) << 12 |
GB(s[2], 0, 6) << 6 |
GB(s[3], 0, 6);
461 if (*c >= 0x10000 && *c <= 0x10FFFF)
return 4;
482 }
else if (c < 0x800) {
483 *buf++ = 0xC0 +
GB(c, 6, 5);
484 *buf = 0x80 +
GB(c, 0, 6);
486 }
else if (c < 0x10000) {
487 *buf++ = 0xE0 +
GB(c, 12, 4);
488 *buf++ = 0x80 +
GB(c, 6, 6);
489 *buf = 0x80 +
GB(c, 0, 6);
491 }
else if (c < 0x110000) {
492 *buf++ = 0xF0 +
GB(c, 18, 3);
493 *buf++ = 0x80 +
GB(c, 12, 6);
494 *buf++ = 0x80 +
GB(c, 6, 6);
495 *buf = 0x80 +
GB(c, 0, 6);
515 for (
const char *ptr = strchr(s,
'\0'); *s !=
'\0';) {
518 if (len == 0) len = 1;
522 if (length + len >= maxlen || (s + len > ptr))
break;
531 #ifdef DEFINE_STRCASESTR 532 char *strcasestr(
const char *haystack,
const char *needle)
534 size_t hay_len = strlen(haystack);
535 size_t needle_len = strlen(needle);
536 while (hay_len >= needle_len) {
537 if (strncasecmp(haystack, needle, needle_len) == 0)
return const_cast<char *
>(haystack);
569 int strnatcmp(
const char *s1,
const char *s2,
bool ignore_garbage_at_front)
571 if (ignore_garbage_at_front) {
577 UErrorCode status = U_ZERO_ERROR;
579 if (U_SUCCESS(status))
return result;
585 return strcasecmp(s1, s2);
590 #include <unicode/utext.h> 591 #include <unicode/brkiter.h> 605 UErrorCode status = U_ZERO_ERROR;
609 *this->utf16_str.
Append() =
'\0';
610 *this->utf16_to_utf8.
Append() = 0;
621 const char *string_base = s;
627 this->utf16_str.
Clear();
628 this->utf16_to_utf8.
Clear();
631 size_t idx = s - string_base;
633 WChar c = Utf8Consume(&s);
635 *this->utf16_str.
Append() = (UChar)c;
638 *this->utf16_str.
Append() = (UChar)(0xD800 + ((c - 0x10000) >> 10));
639 *this->utf16_str.
Append() = (UChar)(0xDC00 + ((c - 0x10000) & 0x3FF));
640 *this->utf16_to_utf8.
Append() = idx;
642 *this->utf16_to_utf8.
Append() = idx;
644 *this->utf16_str.
Append() =
'\0';
645 *this->utf16_to_utf8.
Append() = s - string_base;
647 UText text = UTEXT_INITIALIZER;
648 UErrorCode status = U_ZERO_ERROR;
649 utext_openUChars(&text, this->utf16_str.
Begin(), this->utf16_str.
Length() - 1, &status);
650 this->char_itr->setText(&text, status);
651 this->word_itr->setText(&text, status);
652 this->char_itr->first();
653 this->word_itr->first();
660 for (uint i = 0; i < this->utf16_to_utf8.
Length(); i++) {
661 if (this->utf16_to_utf8[i] == pos) {
670 this->char_itr->isBoundary(utf16_pos);
671 return this->utf16_to_utf8[this->char_itr->current()];
679 pos = this->char_itr->next();
683 pos = this->word_itr->following(this->char_itr->current());
687 while (pos != icu::BreakIterator::DONE &&
689 int32_t new_pos = this->word_itr->next();
692 if (new_pos == icu::BreakIterator::DONE)
break;
696 this->char_itr->isBoundary(pos);
703 return pos == icu::BreakIterator::DONE ?
END : this->utf16_to_utf8[pos];
711 pos = this->char_itr->previous();
715 pos = this->word_itr->preceding(this->char_itr->current());
719 while (pos != icu::BreakIterator::DONE &&
721 int32_t new_pos = this->word_itr->previous();
724 if (new_pos == icu::BreakIterator::DONE)
break;
728 this->char_itr->isBoundary(pos);
735 return pos == icu::BreakIterator::DONE ?
END : this->utf16_to_utf8[pos];
754 DefaultStringIterator() : string(NULL), len(0), cur_pos(0)
761 this->len = strlen(s);
767 assert(this->
string != NULL && pos <= this->len);
769 while (pos > 0 && IsUtf8Part(this->
string[pos])) pos--;
770 return this->cur_pos = pos;
775 assert(this->
string != NULL);
778 if (this->cur_pos >= this->len)
return END;
783 this->cur_pos +=
Utf8Decode(&c, this->
string + this->cur_pos);
784 return this->cur_pos;
790 size_t offs =
Utf8Decode(&c, this->
string + this->cur_pos);
792 this->cur_pos += offs;
793 offs =
Utf8Decode(&c, this->
string + this->cur_pos);
797 this->cur_pos += offs;
798 offs =
Utf8Decode(&c, this->
string + this->cur_pos);
801 return this->cur_pos;
813 assert(this->
string != NULL);
816 if (this->cur_pos == 0)
return END;
820 return this->cur_pos =
Utf8PrevChar(this->
string + this->cur_pos) - this->string;
823 const char *s = this->
string + this->cur_pos;
838 return this->cur_pos = s - this->string;
851 return new DefaultStringIterator();
char *CDECL str_fmt(const char *str,...)
Format, "printf", into a newly allocated string.
Control codes that are embedded in the translation strings.
virtual void SetString(const char *s)
Set a new iteration string.
static bool IsInsideMM(const T x, const uint min, const uint max)
Checks if a value is in an interval.
int CDECL seprintf(char *str, const char *last, const char *format,...)
Safer implementation of snprintf; same as snprintf except:
Only hexadecimal characters.
static const size_t END
Sentinel to indicate end-of-iteration.
Functions related to debugging.
static StringIterator * Create()
Create a new iterator instance.
SmallVector< size_t, 32 > utf16_to_utf8
Mapping from UTF-16 code point position to index in the UTF-8 source string.
icu::BreakIterator * word_itr
ICU iterator for words.
int CDECL vseprintf(char *str, const char *last, const char *format, va_list ap)
Safer implementation of vsnprintf; same as vsnprintf except:
char * strecpy(char *dst, const char *src, const char *last)
Copies characters from one buffer to another.
const LanguageMetadata * _current_language
The currently loaded language.
static bool IsWhitespace(WChar c)
Check whether UNICODE character is whitespace or not, i.e.
char * strecat(char *dst, const char *src, const char *last)
Appends characters from one string to another.
char * md5sumToString(char *buf, const char *last, const uint8 md5sum[16])
Convert the md5sum to a hexadecimal string representation.
static const char * SkipGarbage(const char *str)
Skip some of the 'garbage' in the string that we don't want to use to sort on.
void Clear()
Remove all items from the list.
const T * Begin() const
Get the pointer to the first item (const)
icu::BreakIterator * char_itr
ICU iterator for characters.
size_t Utf8Decode(WChar *c, const char *s)
Decode and consume the next UTF-8 encoded character.
#define lastof(x)
Get the last element of an fixed size array.
bool strtolower(char *str)
Convert a given ASCII string to lowercase.
virtual size_t SetCurPosition(size_t pos)
Change the current string cursor.
T * Append(uint to_add=1)
Append an item and return it.
StringValidationSettings
Settings for the string validation.
Iterate over characters (or more exactly grapheme clusters).
static int8 Utf8EncodedCharLen(char c)
Return the length of an UTF-8 encoded value based on a single char.
Functions related to low-level strings.
bool IsValidChar(WChar key, CharSetFilter afilter)
Only allow certain keys.
SmallVector< UChar, 32 > utf16_str
UTF-16 copy of the string.
uint Length() const
Get the number of items in the list.
void str_validate(char *str, const char *last, StringValidationSettings settings)
Scans the string for valid characters and if it finds invalid ones, replaces them with a question mar...
virtual size_t Next(IterType what)
Advance the cursor by one iteration unit.
static WChar Utf16DecodeChar(const uint16 *c)
Decode an UTF-16 character.
Functions related to the allocation of memory.
size_t Utf8TrimString(char *s, size_t maxlen)
Properly terminate an UTF8 string to some maximum length.
Functions related to the gfx engine.
Definition of base types and functions in a cross-platform compatible way.
A number of safeguards to prevent using unsafe methods.
IterType
Type of the iterator.
Information about languages and their files.
char * stredup(const char *s, const char *last)
Create a duplicate of the given string.
static T min(const T a, const T b)
Returns the minimum of two values.
void str_strip_colours(char *str)
Scans the string for colour codes and strips them.
CharSetFilter
Valid filter types for IsValidChar.
#define DEBUG(name, level,...)
Output a line of debugging information.
Both numeric and alphabetic and spaces and stuff.
int strnatcmp(const char *s1, const char *s2, bool ignore_garbage_at_front)
Compares two strings using case insensitive natural sort.
static size_t ttd_strnlen(const char *str, size_t maxlen)
Get the length of a string, within a limited buffer.
size_t Utf8StringLength(const char *s)
Get the length of an UTF-8 encoded string in number of characters and thus not the number of bytes th...
Replace the unknown/bad bits with question marks.
void CDECL error(const char *s,...)
Error handling for fatal non-user errors.
static uint GB(const T x, const uint8 s, const uint8 n)
Fetch n bits from x, started at bit s.
static char * Utf8PrevChar(char *s)
Retrieve the previous UNICODE character in an UTF-8 encoded string.
Collator * _current_collator
Collator for the language currently in use.
Class for iterating over different kind of parts of a string.
void str_fix_scc_encoded(char *str, const char *last)
Scan the string for old values of SCC_ENCODED and fix it to it's new, static value.
Allow the special control codes.
size_t Utf8Encode(char *buf, WChar c)
Encode a unicode character and place it in the buffer.
static bool HasBit(const T x, const uint8 y)
Checks if a bit in a value is set.
void ValidateString(const char *str)
Scans the string for valid characters and if it finds invalid ones, replaces them with a question mar...
String iterator using ICU as a backend.
virtual size_t Prev(IterType what)
Move the cursor back by one iteration unit.
uint32 WChar
Type for wide characters, i.e.
bool StrValid(const char *str, const char *last)
Checks whether the given string is valid, i.e.