#include "unicode/utypes.h"
Go to the source code of this file.
Defines | |
#define | U_STRING_DECL(var, cs, length) static const wchar_t var[(length)+1]={ L ## cs } |
Unicode String literals in C. More... | |
#define | U_STRING_INIT(var, cs, length) |
Functions | |
U_CAPI int32_t U_EXPORT2 | u_strlen (const UChar *s) |
Determine the length of an array of UChar. More... | |
U_CAPI UChar* U_EXPORT2 | u_strcat (UChar *dst, const UChar *src) |
Concatenate two ustrings. More... | |
U_CAPI UChar* U_EXPORT2 | u_strncat (UChar *dst, const UChar *src, int32_t n) |
Concatenate two ustrings. More... | |
U_CAPI UChar* U_EXPORT2 | u_strchr (const UChar *s, UChar c) |
Find the first occurrence of a specified character in a ustring. More... | |
U_CAPI UChar* U_EXPORT2 | u_strstr (const UChar *s, const UChar *substring) |
Find the first occurrence of a substring in a string. More... | |
U_CAPI UChar* U_EXPORT2 | u_strchr32 (const UChar *s, UChar32 c) |
Find the first occurence of a specified code point in a string. More... | |
U_CAPI UChar* U_EXPORT2 | u_strpbrk (const UChar *string, const UChar *matchSet) |
Locates the first occurrence in the string str of any of the characters in the string accept. More... | |
U_CAPI int32_t U_EXPORT2 | u_strcspn (const UChar *string, const UChar *matchSet) |
Returns the number of consecutive characters in string1, beginning with the first, that do not occur somewhere in string2. More... | |
U_CAPI int32_t U_EXPORT2 | u_strspn (const UChar *string, const UChar *matchSet) |
Returns the number of consecutive characters in string1, beginning with the first, that occur somewhere in string2. More... | |
U_CAPI UChar* U_EXPORT2 | u_strtok_r (UChar *src, const UChar *delim, UChar **saveState) |
The string tokenizer API allows an application to break a string into tokens. More... | |
U_CAPI int32_t U_EXPORT2 | u_strcmp (const UChar *s1, const UChar *s2) |
Compare two Unicode strings for bitwise equality (code unit order). More... | |
U_CAPI int32_t U_EXPORT2 | u_strcmpCodePointOrder (const UChar *s1, const UChar *s2) |
Compare two Unicode strings in code point order. More... | |
U_CAPI int32_t U_EXPORT2 | u_strncmp (const UChar *ucs1, const UChar *ucs2, int32_t n) |
Compare two ustrings for bitwise equality. More... | |
U_CAPI int32_t U_EXPORT2 | u_strcasecmp (const UChar *s1, const UChar *s2, uint32_t options) |
Compare two strings case-insensitively using full case folding. More... | |
U_CAPI int32_t U_EXPORT2 | u_strncasecmp (const UChar *s1, const UChar *s2, int32_t n, uint32_t options) |
Compare two strings case-insensitively using full case folding. More... | |
U_CAPI int32_t U_EXPORT2 | u_memcasecmp (const UChar *s1, const UChar *s2, int32_t length, uint32_t options) |
Compare two strings case-insensitively using full case folding. More... | |
U_CAPI UChar* U_EXPORT2 | u_strcpy (UChar *dst, const UChar *src) |
Copy a ustring. More... | |
U_CAPI UChar* U_EXPORT2 | u_strncpy (UChar *dst, const UChar *src, int32_t n) |
Copy a ustring. More... | |
U_CAPI UChar* U_EXPORT2 | u_uastrcpy (UChar *dst, const char *src ) |
Copy a byte string encoded in the default codepage to a ustring. More... | |
U_CAPI UChar* U_EXPORT2 | u_uastrncpy (UChar *dst, const char *src, int32_t n) |
Copy a byte string encoded in the default codepage to a ustring. More... | |
U_CAPI char* U_EXPORT2 | u_austrcpy (char *dst, const UChar *src ) |
Copy ustring to a byte string encoded in the default codepage. More... | |
U_CAPI char* U_EXPORT2 | u_austrncpy (char *dst, const UChar *src, int32_t n ) |
Copy ustring to a byte string encoded in the default codepage. More... | |
U_CAPI UChar* U_EXPORT2 | u_memcpy (UChar *dest, const UChar *src, int32_t count) |
Synonym for uprv_memcpy(), but with UChars only. More... | |
U_CAPI UChar* U_EXPORT2 | u_memmove (UChar *dest, const UChar *src, int32_t count) |
Synonym for uprv_memmove(), but with UChars only. More... | |
U_CAPI UChar* U_EXPORT2 | u_memset (UChar *dest, UChar c, int32_t count) |
Initialize count characters of dest to c . More... | |
U_CAPI int32_t U_EXPORT2 | u_memcmp (UChar *buf1, UChar *buf2, int32_t count) |
Compare the first count UChars of each buffer. More... | |
U_CAPI UChar* U_EXPORT2 | u_memchr (UChar *src, UChar ch, int32_t count) |
Search for a UChar within a Unicode string until count is reached. More... | |
U_CAPI UChar* U_EXPORT2 | u_memchr32 (UChar *src, UChar32 ch, int32_t count) |
Search for a UChar32 within a Unicode string until count is reached. More... | |
U_CAPI int32_t U_EXPORT2 | u_unescape (const char *src, UChar *dest, int32_t destCapacity) |
Unescape a string of characters and write the resulting Unicode characters to the destination buffer. More... | |
U_CDECL_END U_CAPI UChar32 U_EXPORT2 | u_unescapeAt (UNESCAPE_CHAR_AT charAt, int32_t *offset, int32_t length, void *context) |
Unescape a single sequence. More... | |
U_CAPI int32_t U_EXPORT2 | u_strToUpper (UChar *dest, int32_t destCapacity, const UChar *src, int32_t srcLength, const char *locale, UErrorCode *pErrorCode) |
Uppercase the characters in a string. More... | |
U_CAPI int32_t U_EXPORT2 | u_strToLower (UChar *dest, int32_t destCapacity, const UChar *src, int32_t srcLength, const char *locale, UErrorCode *pErrorCode) |
Lowercase the characters in a string. More... | |
U_CAPI int32_t U_EXPORT2 | u_strFoldCase (UChar *dest, int32_t destCapacity, const UChar *src, int32_t srcLength, uint32_t options, UErrorCode *pErrorCode) |
Case-fold the characters in a string. More... | |
Variables | |
U_CDECL_BEGIN typedef UChar (* | UNESCAPE_CHAR_AT )(int32_t offset, void *context) |
Callback function for u_unescapeAt() that returns a character of the source text given an offset and a context pointer. More... |
|
Unicode String literals in C. We need one macro to declare a variable for the string and to statically preinitialize it if possible, and a second macro to dynamically intialize such a string variable if necessary. The macros are defined for maximum performance. They work only for strings that contain "invariant characters", i.e., only latin letters, digits, and some punctuation. See utypes.h for details.
A pair of macros for a single string must be used with the same parameters. The string parameter must be a C string literal. The length of the string, not including the terminating Usage:   U_STRING_DECL(ustringVar1, "Quick-Fox 2", 11);   U_STRING_DECL(ustringVar2, "jumps 5%", 8);   static UBool didInit=FALSE;     int32_t function() {   if(!didInit) {   U_STRING_INIT(ustringVar1, "Quick-Fox 2", 11);   U_STRING_INIT(ustringVar2, "jumps 5%", 8);   didInit=TRUE;   }   return u_strcmp(ustringVar1, ustringVar2);   } |
|
|
|
Copy ustring to a byte string encoded in the default codepage. Adds a null terminator. Performs a UChar to host byte conversion
|
|
Copy ustring to a byte string encoded in the default codepage.
Copies at most
|
|
Compare two strings case-insensitively using full case folding. This is equivalent to u_strcmp(u_strFoldCase(s1, n, options), u_strFoldCase(s2, n, options)).
|
|
Search for a UChar within a Unicode string until
|
|
Search for a UChar32 within a Unicode string until This also includes surrogates in UTF-16.
|
|
Compare the first
|
|
Synonym for uprv_memcpy(), but with UChars only.
|
|
Synonym for uprv_memmove(), but with UChars only.
|
|
Initialize
|
|
Case-fold the characters in a string. Case-folding is locale-independent and not context-sensitive, but there is an option for whether to include or exclude mappings for dotted I and dotless i that are marked with 'I' in CaseFolding.txt. The result may be longer or shorter than the original. The source string and the destination buffer are allowed to overlap.
|
|
Lowercase the characters in a string. Casing is locale-dependent and context-sensitive. The result may be longer or shorter than the original. The source string and the destination buffer are allowed to overlap.
|
|
Uppercase the characters in a string. Casing is locale-dependent and context-sensitive. The result may be longer or shorter than the original. The source string and the destination buffer are allowed to overlap.
|
|
Compare two strings case-insensitively using full case folding. This is equivalent to u_strcmp(u_strFoldCase(s1, options), u_strFoldCase(s2, options)).
|
|
Concatenate two ustrings.
Appends a copy of
|
|
Find the first occurrence of a specified character in a ustring.
|
|
Find the first occurence of a specified code point in a string.
|
|
Compare two Unicode strings for bitwise equality (code unit order).
|
|
Compare two Unicode strings in code point order. This is different in UTF-16 from u_strcmp() if supplementary characters are present: In UTF-16, supplementary characters (with code points U+10000 and above) are stored with pairs of surrogate code units. These have values from 0xd800 to 0xdfff, which means that they compare as less than some other BMP characters like U+feff. This function compares Unicode strings in code point order. If eihter of the UTF-16 strings is malformed (i.e., it contains unpaired surrogates), then the result is not defined.
|
|
Copy a ustring. Adds a null terminator.
|
|
Returns the number of consecutive characters in string1, beginning with the first, that do not occur somewhere in string2. Works just like C's strcspn but with Unicode.
|
|
Determine the length of an array of UChar.
|
|
Compare two strings case-insensitively using full case folding. This is equivalent to u_strcmp(u_strFoldCase(s1, at most n, options), u_strFoldCase(s2, at most n, options)).
|
|
Concatenate two ustrings.
Appends at most
|
|
Compare two ustrings for bitwise equality.
Compares at most
|
|
Copy a ustring.
Copies at most
|
|
Locates the first occurrence in the string str of any of the characters in the string accept. Works just like C's strpbrk but with Unicode.
|
|
Returns the number of consecutive characters in string1, beginning with the first, that occur somewhere in string2. Works just like C's strspn but with Unicode.
|
|
Find the first occurrence of a substring in a string.
|
|
The string tokenizer API allows an application to break a string into tokens. Unlike strtok(), the saveState (the current pointer within the original string) is maintained in saveState. In the first call, the argument src is a pointer to the string. In subsequent calls to return successive tokens of that string, src must be specified as NULL. The value saveState is set by this function to maintain the function's position within the string, and on each subsequent call you must return the same value. This function does handle surrogate pairs. This function is similar to the strtok_r() the POSIX Threads Extension (1003.1c-1995) version.
|
|
Copy a byte string encoded in the default codepage to a ustring. Adds a null terminator. Performs a host byte to UChar conversion
|
|
Copy a byte string encoded in the default codepage to a ustring.
Copies at most
|
|
Unescape a string of characters and write the resulting Unicode characters to the destination buffer. The following escape sequences are recognized: \uhhhh 4 hex digits; h in [0-9A-Fa-f] \Uhhhhhhhh 8 hex digits \xhh 1-2 hex digits \ooo 1-3 octal digits; o in [0-7] as well as the standard ANSI C escapes:
=> U+0007, => U+0008, \t => U+0009, Anything else following a backslash is generically escaped. For example, "[a\-z]" returns "[a-z]". If an escape sequence is ill-formed, this method returns an empty string. An example of an ill-formed sequence is "\u" followed by fewer than 4 hex digits. The above characters are recognized in the compiler's codepage, that is, they are coded as 'u', '\', etc. Characters that are not parts of escape sequences are converted using u_charsToUChars(). This function is similar to UnicodeString::unescape() but not identical to it. The latter takes a source UnicodeString, so it does escape recognition but no conversion.
|
|
Unescape a single sequence. The character at offset-1 is assumed (without checking) to be a backslash. This method takes a callback pointer to a function that returns the UChar at a given offset. By varying this callback, ICU functions are able to unescape char* strings, UnicodeString objects, and UFILE pointers. If offset is out of range, or if the escape sequence is ill-formed, (UChar32)0xFFFFFFFF is returned. See documentation of u_unescape() for a list of recognized sequences.
|
|
Callback function for u_unescapeAt() that returns a character of the source text given an offset and a context pointer. The context pointer will be whatever is passed into u_unescapeAt().
|