0 GˆÌÖ „u¡?ÐÁÓ?÷G// © 2016 and later: Unicode, Inc. and others. // License & terms of use: http://www.unicode.org/copyright.html /* ********************************************************************** * Copyright (C) 1998-2014, International Business Machines * Corporation and others. All Rights Reserved. ********************************************************************** * * File ustring.h * * Modification History: * * Date Name Description * 12/07/98 bertrand Creation. ****************************************************************************** */ #ifndef USTRING_H #define USTRING_H #include "unicode/utypes.h" #include "unicode/putil.h" #include "unicode/uiter.h" /** * \def UBRK_TYPEDEF_UBREAK_ITERATOR * @internal */ #ifndef UBRK_TYPEDEF_UBREAK_ITERATOR # define UBRK_TYPEDEF_UBREAK_ITERATOR /** Simple declaration for u_strToTitle() to avoid including unicode/ubrk.h. @stable ICU 2.1*/ typedef struct UBreakIterator UBreakIterator; #endif /** * \file * \brief C API: Unicode string handling functions * * These C API functions provide general Unicode string handling. * * Some functions are equivalent in name, signature, and behavior to the ANSI C * 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. * (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 UTF-16 superseded UCS-2 with Unicode 2.0 * in 1996.) * * Some APIs accept a 32-bit UChar32 value for a single code point. * * ICU also handles 16-bit Unicode text with unpaired surrogates. * Such text is not well-formed UTF-16. * Code-point-related functions treat unpaired surrogates as surrogate code points, * i.e., as separate units. * * 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. * * 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). * * For more details see the User Guide Strings chapter (http://icu-project.org/userguide/strings.html). * For a discussion of the handling of unpaired surrogates see also * Jitterbug 2145 and its icu mailing list proposal on 2002-sep-18. */ /** * \defgroup ustring_ustrlen String Length * \ingroup ustring_strlen */ /*@{*/ /** * Determine the length of an array of UChar. * * @param s The array of UChars, NULL (U+0000) terminated. * @return The number of UChars in chars, minus the terminator. * @stable ICU 2.0 */ U_STABLE int32_t U_EXPORT2 u_strlen(const UChar *s); /*@}*/ /** * 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 U16_FWD_N() macro (see utf.h). * * @param s The input string. * @param length The number of UChar code units to be checked, or -1 to count all * code points before the first NUL (U+0000). * @return The number of code points in t