1 /* 2 ******************************************************************************* 3 * 4 * Copyright (C) 2003-2006, International Business Machines 5 * Corporation and others. All Rights Reserved. 6 * 7 ******************************************************************************* 8 * file name: usprep.h 9 * encoding: US-ASCII 10 * tab size: 8 (not used) 11 * indentation:4 12 * 13 * created on: 2003jul2 14 * created by: Ram Viswanadha 15 */ 16 17 #ifndef __USPREP_H__ 18 #define __USPREP_H__ 19 20 /** 21 * \file 22 * \brief C API: Implements the StringPrep algorithm. 23 */ 24 25 #include "unicode/utypes.h" 26 /** 27 * 28 * StringPrep API implements the StingPrep framework as described by RFC 3454. 29 * StringPrep prepares Unicode strings for use in network protocols. 30 * Profiles of StingPrep are set of rules and data according to with the 31 * Unicode Strings are prepared. Each profiles contains tables which describe 32 * how a code point should be treated. The tables are broadly classied into 33 * <ul> 34 * <li> Unassinged Table: Contains code points that are unassigned 35 * in the Unicode Version supported by StringPrep. Currently 36 * RFC 3454 supports Unicode 3.2. </li> 37 * <li> Prohibited Table: Contains code points that are prohibted from 38 * the output of the StringPrep processing function. </li> 39 * <li> Mapping Table: Contains code ponts that are deleted from the output or case mapped. </li> 40 * </ul> 41 * 42 * The procedure for preparing Unicode strings: 43 * <ol> 44 * <li> Map: For each character in the input, check if it has a mapping 45 * and, if so, replace it with its mapping. </li> 46 * <li> Normalize: Possibly normalize the result of step 1 using Unicode 47 * normalization. </li> 48 * <li> Prohibit: Check for any characters that are not allowed in the 49 * output. If any are found, return an error.</li> 50 * <li> Check bidi: Possibly check for right-to-left characters, and if 51 * any are found, make sure that the whole string satisfies the 52 * requirements for bidirectional strings. If the string does not 53 * satisfy the requirements for bidirectional strings, return an 54 * error. </li> 55 * </ol> 56 * @author Ram Viswanadha 57 */ 58 #if !UCONFIG_NO_IDNA 59 60 #include "unicode/parseerr.h" 61 62 /** 63 * The StringPrep profile 64 * @stable ICU 2.8 65 */ 66 typedef struct UStringPrepProfile UStringPrepProfile; 67 68 69 /** 70 * Option to prohibit processing of unassigned code points in the input 71 * 72 * @see usprep_prepare 73 * @stable ICU 2.8 74 */ 75 #define USPREP_DEFAULT 0x0000 76 77 /** 78 * Option to allow processing of unassigned code points in the input 79 * 80 * @see usprep_prepare 81 * @stable ICU 2.8 82 */ 83 #define USPREP_ALLOW_UNASSIGNED 0x0001 84 85 86 /** 87 * Creates a StringPrep profile from the data file. 88 * 89 * @param path string containing the full path pointing to the directory 90 * where the profile reside followed by the package name 91 * e.g. "/usr/resource/my_app/profiles/mydata" on a Unix system. 92 * if NULL, ICU default data files will be used. 93 * @param fileName name of the profile file to be opened 94 * @param status ICU error code in/out parameter. Must not be NULL. 95 * Must fulfill U_SUCCESS before the function call. 96 * @return Pointer to UStringPrepProfile that is opened. Should be closed by 97 * calling usprep_close() 98 * @see usprep_close() 99 * @stable ICU 2.8 100 */ 101 U_STABLE UStringPrepProfile* U_EXPORT2 102 usprep_open(const char* path, 103 const char* fileName, 104 UErrorCode* status); 105 106 107 /** 108 * Closes the profile 109 * @param profile The profile to close 110 * @stable ICU 2.8 111 */ 112 U_STABLE void U_EXPORT2 113 usprep_close(UStringPrepProfile* profile); 114 115 116 /** 117 * Prepare the input buffer for use in applications with the given profile. This operation maps, normalizes(NFKC), 118 * checks for prohited and BiDi characters in the order defined by RFC 3454 119 * depending on the options specified in the profile. 120 * 121 * @param prep The profile to use 122 * @param src Pointer to UChar buffer containing the string to prepare 123 * @param srcLength Number of characters in the source string 124 * @param dest Pointer to the destination buffer to receive the output 125 * @param destCapacity The capacity of destination array 126 * @param options A bit set of options: 127 * 128 * - USPREP_NONE Prohibit processing of unassigned code points in the input 129 * 130 * - USPREP_ALLOW_UNASSIGNED Treat the unassigned code points are in the input 131 * as normal Unicode code points. 132 * 133 * @param parseError Pointer to UParseError struct to receive information on position 134 * of error if an error is encountered. Can be NULL. 135 * @param status ICU in/out error code parameter. 136 * U_INVALID_CHAR_FOUND if src contains 137 * unmatched single surrogates. 138 * U_INDEX_OUTOFBOUNDS_ERROR if src contains 139 * too many code points. 140 * U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough 141 * @return The number of UChars in the destination buffer 142 * @stable ICU 2.8 143 */ 144 145 U_STABLE int32_t U_EXPORT2 146 usprep_prepare( const UStringPrepProfile* prep, 147 const UChar* src, int32_t srcLength, 148 UChar* dest, int32_t destCapacity, 149 int32_t options, 150 UParseError* parseError, 151 UErrorCode* status ); 152 153 154 #endif /* #if !UCONFIG_NO_IDNA */ 155 156 #endif 157