#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. | |
#define | U_STRING_INIT(var, cs, length) |
Typedefs | |
typedef void * | UBreakIterator |
Simple declaration for u_strToTitle() to avoid including unicode/ubrk.h. | |
Functions | |
U_CAPI int32_t U_EXPORT2 | u_strlen (const UChar *s) |
Determine the length of an array of UChar. | |
U_CAPI int32_t U_EXPORT2 | u_countChar32 (const UChar *s, int32_t length) |
Count Unicode code points in the length UChar code units of the string. | |
U_CAPI UChar *U_EXPORT2 | u_strcat (UChar *dst, const UChar *src) |
Concatenate two ustrings. | |
U_CAPI UChar *U_EXPORT2 | u_strncat (UChar *dst, const UChar *src, int32_t n) |
Concatenate two ustrings. | |
U_CAPI UChar *U_EXPORT2 | u_strchr (const UChar *s, UChar c) |
Find the first occurrence of a specified character in a ustring. | |
U_CAPI UChar *U_EXPORT2 | u_strstr (const UChar *s, const UChar *substring) |
Find the first occurrence of a substring in a string. | |
U_CAPI UChar *U_EXPORT2 | u_strchr32 (const UChar *s, UChar32 c) |
Find the first occurence of a specified code point in a string. | |
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. | |
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. | |
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. | |
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. | |
U_CAPI int32_t U_EXPORT2 | u_strcmp (const UChar *s1, const UChar *s2) |
Compare two Unicode strings for bitwise equality (code unit order). | |
U_CAPI int32_t U_EXPORT2 | u_strcmpCodePointOrder (const UChar *s1, const UChar *s2) |
Compare two Unicode strings in code point order. | |
U_CAPI int32_t U_EXPORT2 | u_strncmp (const UChar *ucs1, const UChar *ucs2, int32_t n) |
Compare two ustrings for bitwise equality. | |
U_CAPI int32_t U_EXPORT2 | u_strncmpCodePointOrder (const UChar *s1, const UChar *s2, int32_t n) |
Compare two Unicode strings in code point order. | |
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. | |
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. | |
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. | |
U_CAPI UChar *U_EXPORT2 | u_strcpy (UChar *dst, const UChar *src) |
Copy a ustring. | |
U_CAPI UChar *U_EXPORT2 | u_strncpy (UChar *dst, const UChar *src, int32_t n) |
Copy a ustring. | |
U_CAPI UChar *U_EXPORT2 | u_uastrcpy (UChar *dst, const char *src) |
Copy a byte string encoded in the default codepage to a ustring. | |
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. | |
U_CAPI char *U_EXPORT2 | u_austrcpy (char *dst, const UChar *src) |
Copy ustring to a byte string encoded in the default codepage. | |
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. | |
U_CAPI UChar *U_EXPORT2 | u_memcpy (UChar *dest, const UChar *src, int32_t count) |
Synonym for memcpy(), but with UChars only. | |
U_CAPI UChar *U_EXPORT2 | u_memmove (UChar *dest, const UChar *src, int32_t count) |
Synonym for memmove(), but with UChars only. | |
U_CAPI UChar *U_EXPORT2 | u_memset (UChar *dest, UChar c, int32_t count) |
Initialize count characters of dest to c . | |
U_CAPI int32_t U_EXPORT2 | u_memcmp (const UChar *buf1, const UChar *buf2, int32_t count) |
Compare the first count UChars of each buffer. | |
U_CAPI int32_t U_EXPORT2 | u_memcmpCodePointOrder (const UChar *s1, const UChar *s2, int32_t count) |
Compare two Unicode strings in code point order. | |
U_CAPI UChar *U_EXPORT2 | u_memchr (const UChar *src, UChar ch, int32_t count) |
Search for a UChar within a Unicode string until count is reached. | |
U_CAPI UChar *U_EXPORT2 | u_memchr32 (const UChar *src, UChar32 ch, int32_t count) |
Find the first occurence of a specified code point in a string. | |
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. | |
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. | |
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. | |
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. | |
U_CAPI int32_t U_EXPORT2 | u_strToTitle (UChar *dest, int32_t destCapacity, const UChar *src, int32_t srcLength, UBreakIterator *titleIter, const char *locale, UErrorCode *pErrorCode) |
Titlecase a string. | |
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. | |
U_CAPI wchar_t *U_EXPORT2 | u_strToWCS (wchar_t *dest, int32_t destCapacity, int32_t *pDestLength, const UChar *src, int32_t srcLength, UErrorCode *pErrorCode) |
Converts a sequence of UChars to wchar_t units. | |
U_CAPI UChar *U_EXPORT2 | u_strFromWCS (UChar *dest, int32_t destCapacity, int32_t *pDestLength, const wchar_t *src, int32_t srcLength, UErrorCode *pErrorCode) |
Converts a sequence of wchar_t units to UChars. | |
U_CAPI char *U_EXPORT2 | u_strToUTF8 (char *dest, int32_t destCapacity, int32_t *pDestLength, const UChar *src, int32_t srcLength, UErrorCode *pErrorCode) |
Converts a sequence of UChars (UTF-16) to UTF-8 bytes. | |
U_CAPI UChar *U_EXPORT2 | u_strFromUTF8 (UChar *dest, int32_t destCapacity, int32_t *pDestLength, const char *src, int32_t srcLength, UErrorCode *pErrorCode) |
Converts a sequence of UTF-8 bytes to UChars (UTF-16). | |
U_CAPI UChar32 *U_EXPORT2 | u_strToUTF32 (UChar32 *dest, int32_t destCapacity, int32_t *pDestLength, const UChar *src, int32_t srcLength, UErrorCode *pErrorCode) |
Converts a sequence of UTF32 units to UChars. | |
U_CAPI UChar *U_EXPORT2 | u_strFromUTF32 (UChar *dest, int32_t destCapacity, int32_t *pDestLength, const UChar32 *src, int32_t srcLength, UErrorCode *pErrorCode) |
Converts a sequence of UChars to UTF32 units. | |
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. |
These C API functions provide Unicode string handling.
Some functions are equivalent in name, signature, and behavior to the ANSI C <string.h> functions. (For example, they do not check for bad arguments like NULL string pointers.) In some cases, only the thread-safe variant of such a function is implemented here (see u_strtok_r()).
Other functions provide more Unicode-specific functionality like locale-specific upper/lower-casing and string comparison in code point order.
ICU uses 16-bit Unicode (UTF-16) in the form of arrays of UChar code units. UTF-16 encodes each Unicode code point with either one or two UChar code units. Some APIs accept a 32-bit UChar32 value for a single code point. (This is the default form of Unicode, and a forward-compatible extension of the original, fixed-width form that was known as UCS-2. UTF-16 superseded UCS-2 with Unicode 2.0 in 1996.)
Although UTF-16 is a variable-width encoding form (like some legacy multi-byte encodings), it is much more efficient even for random access because the code unit values for single-unit characters vs. lead units vs. trail units are completely disjoint. This means that it is easy to determine character (code point) boundaries from random offsets in the string. (It also means, e.g., that u_strstr() does not need to verify that a match was found on actual character boundaries; with some legacy encodings, strstr() may need to scan back to the start of the text to verify this.)
Unicode (UTF-16) string processing is optimized for the single-unit case. Although it is important to support supplementary characters (which use pairs of lead/trail code units called "surrogates"), their occurrence is rare. Almost all characters in modern use require only a single UChar code unit (i.e., their code point values are <=0xffff).
|
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:
|
|
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
|
|
Count Unicode code points in the length UChar code units of the string. A code point may occupy either one or two UChar code units. Counting code points involves reading all code units. This functions is basically the inverse of the UTF_FWD_N() macro (see utf.h).
|
|
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
|
|
Find the first occurence of a specified code point in a string. This function finds code points, which differs for BMP code points from u_memchr() only for surrogates: While u_memchr() finds any surrogate code units in a string, u_memchr32() finds only unmatched surrogate code points, i.e., only those that do not combine with an adjacent surrogate to form a supplementary code point. For example, in a string "\ud800\udc00" u_memchr() will find code units U+d800 at 0 and U+dc00 at 1, but u_memchr32() will find neither because they combine to the code point U+10000. Either function will find U+d800 in "a\ud800b". This behavior ensures that UTF_GET_CHAR(u_memchr32(c))==c.
|
|
Compare the first
|
|
Compare two Unicode strings in code point order. This is different in UTF-16 from u_memcmp() if supplementary characters are present. For details, see u_strcmpCodePointOrder().
|
|
Synonym for memcpy(), but with UChars only.
|
|
Synonym for memmove(), but with UChars only.
|
|
Initialize
|
|
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. This function finds code points, which differs for BMP code points from u_strchr() only for surrogates: While u_strchr() finds any surrogate code units in a string, u_strchr32() finds only unmatched surrogate code points, i.e., only those that do not combine with an adjacent surrogate to form a supplementary code point. For example, in a string "\ud800\udc00" u_strchr() will find code units U+d800 at 0 and U+dc00 at 1, but u_strchr32() will find neither because they combine to the code point U+10000. Either function will find U+d800 in "a\ud800b". This behavior ensures that UTF_GET_CHAR(u_strchr32(c))==c.
|
|
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.
|
|
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.
|
|
Converts a sequence of UChars to UTF32 units.
|
|
Converts a sequence of UTF-8 bytes to UChars (UTF-16).
|
|
Converts a sequence of wchar_t units to UChars.
|
|
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
|
|
Compare two Unicode strings in code point order. This is different in UTF-16 from u_strncmp() if supplementary characters are present. For details, see u_strcmpCodePointOrder().
|
|
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 give this argument the same variable. This function does handle surrogate pairs. This function is similar to the strtok_r() the POSIX Threads Extension (1003.1c-1995) version.
|
|
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.
|
|
Titlecase a string. Casing is locale-dependent and context-sensitive. Titlecasing uses a break iterator to find the first characters of words that are to be titlecased. It titlecases those characters and lowercases all others. The titlecase break iterator can be provided to customize for arbitrary styles, using rules and dictionaries beyond the standard iterators. It may be more efficient to always provide an iterator to avoid opening and closing one for each string. The standard titlecase iterator for the root locale implements the algorithm of Unicode TR 21. This function uses only the first() and next() methods of the provided break iterator. 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.
|
|
Converts a sequence of UTF32 units to UChars.
|
|
Converts a sequence of UChars (UTF-16) to UTF-8 bytes.
|
|
Converts a sequence of UChars to wchar_t units.
|
|
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: 4 hex digits; h in [0-9A-Fa-f] 8 hex digits 1-2 hex digits 1-3 octal digits; o in [0-7] as well as the standard ANSI C escapes:
=> U+0007, => U+0008, => 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().
|