1 // 2016 and later: Unicode, Inc. and others. 2 // License & terms of use: http://www.unicode.org/copyright.html 3 /* 4 ********************************************************************** 5 * Copyright (C) 1999-2015, International Business Machines 6 * Corporation and others. All Rights Reserved. 7 ********************************************************************** 8 * file name: ustr_imp.h 9 * encoding: UTF-8 10 * tab size: 8 (not used) 11 * indentation:4 12 * 13 * created on: 2001jan30 14 * created by: Markus W. Scherer 15 */ 16 17 #ifndef __USTR_IMP_H__ 18 #define __USTR_IMP_H__ 19 20 #include "unicode/utypes.h" 21 #include "unicode/utf8.h" 22 23 /** 24 * Internal option for unorm_cmpEquivFold() for strncmp style. 25 * If set, checks for both string length and terminating NUL. 26 */ 27 #define _STRNCMP_STYLE 0x1000 28 29 /** 30 * Compare two strings in code point order or code unit order. 31 * Works in strcmp style (both lengths -1), 32 * strncmp style (lengths equal and >=0, flag TRUE), 33 * and memcmp/UnicodeString style (at least one length >=0). 34 */ 35 U_CFUNC int32_t U_EXPORT2 36 uprv_strCompare(const UChar *s1, int32_t length1, 37 const UChar *s2, int32_t length2, 38 UBool strncmpStyle, UBool codePointOrder); 39 40 U_CAPI int32_t U_EXPORT2 41 ustr_hashUCharsN(const UChar *str, int32_t length); 42 43 U_CAPI int32_t U_EXPORT2 44 ustr_hashCharsN(const char *str, int32_t length); 45 46 U_CAPI int32_t U_EXPORT2 47 ustr_hashICharsN(const char *str, int32_t length); 48 49 /** 50 * NUL-terminate a UChar * string if possible. 51 * If length < destCapacity then NUL-terminate. 52 * If length == destCapacity then do not terminate but set U_STRING_NOT_TERMINATED_WARNING. 53 * If length > destCapacity then do not terminate but set U_BUFFER_OVERFLOW_ERROR. 54 * 55 * @param dest Destination buffer, can be NULL if destCapacity==0. 56 * @param destCapacity Number of UChars available at dest. 57 * @param length Number of UChars that were (to be) written to dest. 58 * @param pErrorCode ICU error code. 59 * @return length 60 */ 61 U_CAPI int32_t U_EXPORT2 62 u_terminateUChars(UChar *dest, int32_t destCapacity, int32_t length, UErrorCode *pErrorCode); 63 64 /** 65 * NUL-terminate a char * string if possible. 66 * Same as u_terminateUChars() but for a different string type. 67 */ 68 U_CAPI int32_t U_EXPORT2 69 u_terminateChars(char *dest, int32_t destCapacity, int32_t length, UErrorCode *pErrorCode); 70 71 /** 72 * NUL-terminate a UChar32 * string if possible. 73 * Same as u_terminateUChars() but for a different string type. 74 */ 75 U_CAPI int32_t U_EXPORT2 76 u_terminateUChar32s(UChar32 *dest, int32_t destCapacity, int32_t length, UErrorCode *pErrorCode); 77 78 /** 79 * NUL-terminate a wchar_t * string if possible. 80 * Same as u_terminateUChars() but for a different string type. 81 */ 82 U_CAPI int32_t U_EXPORT2 83 u_terminateWChars(wchar_t *dest, int32_t destCapacity, int32_t length, UErrorCode *pErrorCode); 84 85 /** 86 * Counts the bytes of any whole valid sequence for a UTF-8 lead byte. 87 * Returns 1 for ASCII 0..0x7f. 88 * Returns 0 for 0x80..0xc1 as well as for 0xf5..0xff. 89 * leadByte might be evaluated multiple times. 90 * 91 * @param leadByte The first byte of a UTF-8 sequence. Must be 0..0xff. 92 * @return 0..4 93 */ 94 #define U8_COUNT_BYTES(leadByte) \ 95 (U8_IS_SINGLE(leadByte) ? 1 : U8_COUNT_BYTES_NON_ASCII(leadByte)) 96 97 /** 98 * Counts the bytes of any whole valid sequence for a UTF-8 lead byte. 99 * Returns 0 for 0x00..0xc1 as well as for 0xf5..0xff. 100 * leadByte might be evaluated multiple times. 101 * 102 * @param leadByte The first byte of a UTF-8 sequence. Must be 0..0xff. 103 * @return 0 or 2..4 104 */ 105 #define U8_COUNT_BYTES_NON_ASCII(leadByte) \ 106 (U8_IS_LEAD(leadByte) ? ((uint8_t)(leadByte)>=0xe0)+((uint8_t)(leadByte)>=0xf0)+2 : 0) 107 108 #ifdef __cplusplus 109 110 U_NAMESPACE_BEGIN 111 112 class UTF8 { 113 public: 114 UTF8() = delete; // all static 115 116 /** 117 * Is t a valid UTF-8 trail byte? 118 * 119 * @param prev Must be the preceding lead byte if i==1 and length>=3; 120 * otherwise ignored. 121 * @param t The i-th byte following the lead byte. 122 * @param i The index (1..3) of byte t in the byte sequence. 0<i<length 123 * @param length The length (2..4) of the byte sequence according to the lead byte. 124 * @return TRUE if t is a valid trail byte in this context. 125 */ 126 static inline UBool isValidTrail(int32_t prev, uint8_t t, int32_t i, int32_t length) { 127 // The first trail byte after a 3- or 4-byte lead byte 128 // needs to be validated together with its lead byte. 129 if (length <= 2 || i > 1) { 130 return U8_IS_TRAIL(t); 131 } else if (length == 3) { 132 return U8_IS_VALID_LEAD3_AND_T1(prev, t); 133 } else { // length == 4 134 return U8_IS_VALID_LEAD4_AND_T1(prev, t); 135 } 136 } 137 }; 138 139 U_NAMESPACE_END 140 141 #endif // __cplusplus 142 143 #endif 144
