1 /* 2 ******************************************************************************* 3 * 4 * Copyright (C) 2003-2009, 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 * enums for the standard stringprep profile types 87 * supported by usprep_openByType. 88 * @see usprep_openByType 89 * @draft ICU 4.2 90 */ 91 typedef enum UStringPrepProfileType { 92 /** 93 * RFC3491 Nameprep 94 * @draft ICU 4.2 95 */ 96 USPREP_RFC3491_NAMEPREP, 97 /** 98 * RFC3530 nfs4_cs_prep 99 * @draft ICU 4.2 100 */ 101 USPREP_RFC3530_NFS4_CS_PREP, 102 /** 103 * RFC3530 nfs4_cs_prep with case insensitive option 104 * @draft ICU 4.2 105 */ 106 USPREP_RFC3530_NFS4_CS_PREP_CI, 107 /** 108 * RFC3530 nfs4_cis_prep 109 * @draft ICU 4.2 110 */ 111 USPREP_RFC3530_NFS4_CIS_PREP, 112 /** 113 * RFC3530 nfs4_mixed_prep for prefix 114 * @draft ICU 4.2 115 */ 116 USPREP_RFC3530_NFS4_MIXED_PREP_PREFIX, 117 /** 118 * RFC3530 nfs4_mixed_prep for suffix 119 * @draft ICU 4.2 120 */ 121 USPREP_RFC3530_NFS4_MIXED_PREP_SUFFIX, 122 /** 123 * RFC3722 iSCSI 124 * @draft ICU 4.2 125 */ 126 USPREP_RFC3722_ISCSI, 127 /** 128 * RFC3920 XMPP Nodeprep 129 * @draft ICU 4.2 130 */ 131 USPREP_RFC3920_NODEPREP, 132 /** 133 * RFC3920 XMPP Resourceprep 134 * @draft ICU 4.2 135 */ 136 USPREP_RFC3920_RESOURCEPREP, 137 /** 138 * RFC4011 Policy MIB Stringprep 139 * @draft ICU 4.2 140 */ 141 USPREP_RFC4011_MIB, 142 /** 143 * RFC4013 SASLprep 144 * @draft ICU 4.2 145 */ 146 USPREP_RFC4013_SASLPREP, 147 /** 148 * RFC4505 trace 149 * @draft ICU 4.2 150 */ 151 USPREP_RFC4505_TRACE, 152 /** 153 * RFC4518 LDAP 154 * @draft ICU 4.2 155 */ 156 USPREP_RFC4518_LDAP, 157 /** 158 * RFC4518 LDAP for case ignore, numeric and stored prefix 159 * matching rules 160 * @draft ICU 4.2 161 */ 162 USPREP_RFC4518_LDAP_CI 163 } UStringPrepProfileType; 164 165 /** 166 * Creates a StringPrep profile from the data file. 167 * 168 * @param path string containing the full path pointing to the directory 169 * where the profile reside followed by the package name 170 * e.g. "/usr/resource/my_app/profiles/mydata" on a Unix system. 171 * if NULL, ICU default data files will be used. 172 * @param fileName name of the profile file to be opened 173 * @param status ICU error code in/out parameter. Must not be NULL. 174 * Must fulfill U_SUCCESS before the function call. 175 * @return Pointer to UStringPrepProfile that is opened. Should be closed by 176 * calling usprep_close() 177 * @see usprep_close() 178 * @stable ICU 2.8 179 */ 180 U_STABLE UStringPrepProfile* U_EXPORT2 181 usprep_open(const char* path, 182 const char* fileName, 183 UErrorCode* status); 184 185 /** 186 * Creates a StringPrep profile for the specified profile type. 187 * 188 * @param type The profile type 189 * @param status ICU error code in/out parameter. Must not be NULL. 190 * Must fulfill U_SUCCESS before the function call. 191 * @return Pointer to UStringPrepProfile that is opened. Should be closed by 192 * calling usprep_close() 193 * @see usprep_close() 194 * @draft ICU 4.2 195 */ 196 U_DRAFT UStringPrepProfile* U_EXPORT2 197 usprep_openByType(UStringPrepProfileType type, 198 UErrorCode* status); 199 200 /** 201 * Closes the profile 202 * @param profile The profile to close 203 * @stable ICU 2.8 204 */ 205 U_STABLE void U_EXPORT2 206 usprep_close(UStringPrepProfile* profile); 207 208 209 /** 210 * Prepare the input buffer for use in applications with the given profile. This operation maps, normalizes(NFKC), 211 * checks for prohited and BiDi characters in the order defined by RFC 3454 212 * depending on the options specified in the profile. 213 * 214 * @param prep The profile to use 215 * @param src Pointer to UChar buffer containing the string to prepare 216 * @param srcLength Number of characters in the source string 217 * @param dest Pointer to the destination buffer to receive the output 218 * @param destCapacity The capacity of destination array 219 * @param options A bit set of options: 220 * 221 * - USPREP_NONE Prohibit processing of unassigned code points in the input 222 * 223 * - USPREP_ALLOW_UNASSIGNED Treat the unassigned code points are in the input 224 * as normal Unicode code points. 225 * 226 * @param parseError Pointer to UParseError struct to receive information on position 227 * of error if an error is encountered. Can be NULL. 228 * @param status ICU in/out error code parameter. 229 * U_INVALID_CHAR_FOUND if src contains 230 * unmatched single surrogates. 231 * U_INDEX_OUTOFBOUNDS_ERROR if src contains 232 * too many code points. 233 * U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough 234 * @return The number of UChars in the destination buffer 235 * @stable ICU 2.8 236 */ 237 238 U_STABLE int32_t U_EXPORT2 239 usprep_prepare( const UStringPrepProfile* prep, 240 const UChar* src, int32_t srcLength, 241 UChar* dest, int32_t destCapacity, 242 int32_t options, 243 UParseError* parseError, 244 UErrorCode* status ); 245 246 247 #endif /* #if !UCONFIG_NO_IDNA */ 248 249 #endif 250