icuSources/common/unicode/usprep.h

   1 // © 2016 and later: Unicode, Inc. and others.
   2 // License & terms of use: http://www.unicode.org/copyright.html
   3 /*
   4  *******************************************************************************
   5  *
   6  *   Copyright (C) 2003-2014, International Business Machines
   7  *   Corporation and others.  All Rights Reserved.
   8  *
   9  *******************************************************************************
  10  *   file name:  usprep.h
  11  *   encoding:   UTF-8
  12  *   tab size:   8 (not used)
  13  *   indentation:4
  14  *
  15  *   created on: 2003jul2
  16  *   created by: Ram Viswanadha
  17  */
  18
  19 #ifndef __USPREP_H__
  20 #define __USPREP_H__
  21
  22 /**
  23  * \file
  24  * \brief C API: Implements the StringPrep algorithm.
  25  */
  26
  27 #include "unicode/utypes.h"
  28 #include "unicode/localpointer.h"
  29
  30 /**
  31  *
  32  * StringPrep API implements the StingPrep framework as described by RFC 3454.
  33  * StringPrep prepares Unicode strings for use in network protocols.
  34  * Profiles of StingPrep are set of rules and data according to with the
  35  * Unicode Strings are prepared. Each profiles contains tables which describe
  36  * how a code point should be treated. The tables are broadly classified into
  37  * <ul>
  38  *     <li> Unassigned Table: Contains code points that are unassigned
  39  *          in the Unicode Version supported by StringPrep. Currently
  40  *          RFC 3454 supports Unicode 3.2. </li>
  41  *     <li> Prohibited Table: Contains code points that are prohibited from
  42  *          the output of the StringPrep processing function. </li>
  43  *     <li> Mapping Table: Contains code points that are deleted from the output or case mapped. </li>
  44  * </ul>
  45  *
  46  * The procedure for preparing Unicode strings:
  47  * <ol>
  48  *      <li> Map: For each character in the input, check if it has a mapping
  49  *           and, if so, replace it with its mapping. </li>
  50  *      <li> Normalize: Possibly normalize the result of step 1 using Unicode
  51  *           normalization. </li>
  52  *      <li> Prohibit: Check for any characters that are not allowed in the
  53  *        output.  If any are found, return an error.</li>
  54  *      <li> Check bidi: Possibly check for right-to-left characters, and if
  55  *           any are found, make sure that the whole string satisfies the
  56  *           requirements for bidirectional strings.  If the string does not
  57  *           satisfy the requirements for bidirectional strings, return an
  58  *           error.  </li>
  59  * </ol>
  60  * @author Ram Viswanadha
  61  */
  62 #if !UCONFIG_NO_IDNA
  63
  64 #include "unicode/parseerr.h"
  65
  66 /**
  67  * The StringPrep profile
  68  * @stable ICU 2.8
  69  */
  70 typedef struct UStringPrepProfile UStringPrepProfile;
  71
  72
  73 /**
  74  * Option to prohibit processing of unassigned code points in the input
  75  *
  76  * @see  usprep_prepare
  77  * @stable ICU 2.8
  78  */
  79 #define USPREP_DEFAULT 0x0000
  80
  81 /**
  82  * Option to allow processing of unassigned code points in the input
  83  *
  84  * @see  usprep_prepare
  85  * @stable ICU 2.8
  86  */
  87 #define USPREP_ALLOW_UNASSIGNED 0x0001
  88
  89 /**
  90  * enums for the standard stringprep profile types
  91  * supported by usprep_openByType.
  92  * @see usprep_openByType
  93  * @stable ICU 4.2
  94  */
  95 typedef enum UStringPrepProfileType {
  96     /**
  97      * RFC3491 Nameprep
  98      * @stable ICU 4.2
  99      */
 100     USPREP_RFC3491_NAMEPREP,
 101     /**
 102      * RFC3530 nfs4_cs_prep
 103      * @stable ICU 4.2
 104      */
 105         USPREP_RFC3530_NFS4_CS_PREP,
 106     /**
 107      * RFC3530 nfs4_cs_prep with case insensitive option
 108      * @stable ICU 4.2
 109      */
 110         USPREP_RFC3530_NFS4_CS_PREP_CI,
 111     /**
 112      * RFC3530 nfs4_cis_prep
 113      * @stable ICU 4.2
 114      */
 115         USPREP_RFC3530_NFS4_CIS_PREP,
 116     /**
 117      * RFC3530 nfs4_mixed_prep for prefix
 118      * @stable ICU 4.2
 119      */
 120         USPREP_RFC3530_NFS4_MIXED_PREP_PREFIX,
 121     /**
 122      * RFC3530 nfs4_mixed_prep for suffix
 123      * @stable ICU 4.2
 124      */
 125         USPREP_RFC3530_NFS4_MIXED_PREP_SUFFIX,
 126     /**
 127      * RFC3722 iSCSI
 128      * @stable ICU 4.2
 129      */
 130         USPREP_RFC3722_ISCSI,
 131     /**
 132      * RFC3920 XMPP Nodeprep
 133      * @stable ICU 4.2
 134      */
 135         USPREP_RFC3920_NODEPREP,
 136     /**
 137      * RFC3920 XMPP Resourceprep
 138      * @stable ICU 4.2
 139      */
 140         USPREP_RFC3920_RESOURCEPREP,
 141     /**
 142      * RFC4011 Policy MIB Stringprep
 143      * @stable ICU 4.2
 144      */
 145         USPREP_RFC4011_MIB,
 146     /**
 147      * RFC4013 SASLprep
 148      * @stable ICU 4.2
 149      */
 150     USPREP_RFC4013_SASLPREP,
 151     /**
 152      * RFC4505 trace
 153      * @stable ICU 4.2
 154      */
 155         USPREP_RFC4505_TRACE,
 156     /**
 157      * RFC4518 LDAP
 158      * @stable ICU 4.2
 159      */
 160         USPREP_RFC4518_LDAP,
 161     /**
 162      * RFC4518 LDAP for case ignore, numeric and stored prefix
 163      * matching rules
 164      * @stable ICU 4.2
 165      */
 166         USPREP_RFC4518_LDAP_CI
 167 } UStringPrepProfileType;
 168
 169 /**
 170  * Creates a StringPrep profile from the data file.
 171  *
 172  * @param path      string containing the full path pointing to the directory
 173  *                  where the profile reside followed by the package name
 174  *                  e.g. "/usr/resource/my_app/profiles/mydata" on a Unix system.
 175  *                  if NULL, ICU default data files will be used.
 176  * @param fileName  name of the profile file to be opened
 177  * @param status    ICU error code in/out parameter. Must not be NULL.
 178  *                  Must fulfill U_SUCCESS before the function call.
 179  * @return Pointer to UStringPrepProfile that is opened. Should be closed by
 180  * calling usprep_close()
 181  * @see usprep_close()
 182  * @stable ICU 2.8
 183  */
 184 U_STABLE UStringPrepProfile* U_EXPORT2
 185 usprep_open(const char* path,
 186             const char* fileName,
 187             UErrorCode* status);
 188
 189 /**
 190  * Creates a StringPrep profile for the specified profile type.
 191  *
 192  * @param type          The profile type
 193  * @param status    ICU error code in/out parameter. Must not be NULL.
 194  *                  Must fulfill U_SUCCESS before the function call.
 195  * @return          Pointer to UStringPrepProfile that is opened. Should be closed by
 196  *                  calling usprep_close()
 197  * @see usprep_close()
 198  * @stable ICU 4.2
 199  */
 200 U_STABLE UStringPrepProfile* U_EXPORT2
 201 usprep_openByType(UStringPrepProfileType type,
 202                                   UErrorCode* status);
 203
 204 /**
 205  * Closes the profile
 206  * @param profile The profile to close
 207  * @stable ICU 2.8
 208  */
 209 U_STABLE void U_EXPORT2
 210 usprep_close(UStringPrepProfile* profile);
 211
 212 #if U_SHOW_CPLUSPLUS_API
 213
 214 U_NAMESPACE_BEGIN
 215
 216 /**
 217  * \class LocalUStringPrepProfilePointer
 218  * "Smart pointer" class, closes a UStringPrepProfile via usprep_close().
 219  * For most methods see the LocalPointerBase base class.
 220  *
 221  * @see LocalPointerBase
 222  * @see LocalPointer
 223  * @stable ICU 4.4
 224  */
 225 U_DEFINE_LOCAL_OPEN_POINTER(LocalUStringPrepProfilePointer, UStringPrepProfile, usprep_close);
 226
 227 U_NAMESPACE_END
 228
 229 #endif
 230
 231 /**
 232  * Prepare the input buffer for use in applications with the given profile. This operation maps, normalizes(NFKC),
 233  * checks for prohibited and BiDi characters in the order defined by RFC 3454
 234  * depending on the options specified in the profile.
 235  *
 236  * @param prep          The profile to use
 237  * @param src           Pointer to UChar buffer containing the string to prepare
 238  * @param srcLength     Number of characters in the source string
 239  * @param dest          Pointer to the destination buffer to receive the output
 240  * @param destCapacity  The capacity of destination array
 241  * @param options       A bit set of options:
 242  *
 243  *  - USPREP_DEFAULT            Prohibit processing of unassigned code points in the input
 244  *
 245  *  - USPREP_ALLOW_UNASSIGNED   Treat the unassigned code points are in the input
 246  *                              as normal Unicode code points.
 247  *
 248  * @param parseError        Pointer to UParseError struct to receive information on position
 249  *                          of error if an error is encountered. Can be NULL.
 250  * @param status            ICU in/out error code parameter.
 251  *                          U_INVALID_CHAR_FOUND if src contains
 252  *                          unmatched single surrogates.
 253  *                          U_INDEX_OUTOFBOUNDS_ERROR if src contains
 254  *                          too many code points.
 255  *                          U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough
 256  * @return The number of UChars in the destination buffer
 257  * @stable ICU 2.8
 258  */
 259
 260 U_STABLE int32_t U_EXPORT2
 261 usprep_prepare(   const UStringPrepProfile* prep,
 262                   const UChar* src, int32_t srcLength,
 263                   UChar* dest, int32_t destCapacity,
 264                   int32_t options,
 265                   UParseError* parseError,
 266                   UErrorCode* status );
 267
 268
 269 #endif /* #if !UCONFIG_NO_IDNA */
 270
 271 #endif