os/textandloc/fontservices/textshaperplugin/IcuSource/common/unicode/usprep.h
author sl
Tue, 10 Jun 2014 14:32:02 +0200
changeset 1 260cb5ec6c19
permissions -rw-r--r--
Update contrib.
sl@0
     1
/*
sl@0
     2
 *******************************************************************************
sl@0
     3
 *
sl@0
     4
 *   Copyright (C) 2003-2005, International Business Machines
sl@0
     5
 *   Corporation and others.  All Rights Reserved.
sl@0
     6
 *
sl@0
     7
 *******************************************************************************
sl@0
     8
 *   file name:  usprep.h
sl@0
     9
 *   encoding:   US-ASCII
sl@0
    10
 *   tab size:   8 (not used)
sl@0
    11
 *   indentation:4
sl@0
    12
 *
sl@0
    13
 *   created on: 2003jul2
sl@0
    14
 *   created by: Ram Viswanadha
sl@0
    15
 */
sl@0
    16
sl@0
    17
#ifndef __USPREP_H__
sl@0
    18
#define __USPREP_H__
sl@0
    19
sl@0
    20
/**
sl@0
    21
 * \file 
sl@0
    22
 * \brief C API: Implements the StringPrep algorithm.
sl@0
    23
 */
sl@0
    24
sl@0
    25
#include "unicode/utypes.h"
sl@0
    26
/**
sl@0
    27
 *
sl@0
    28
 * StringPrep API implements the StingPrep framework as described by RFC 3454.
sl@0
    29
 * StringPrep prepares Unicode strings for use in network protocols.
sl@0
    30
 * Profiles of StingPrep are set of rules and data according to with the
sl@0
    31
 * Unicode Strings are prepared. Each profiles contains tables which describe
sl@0
    32
 * how a code point should be treated. The tables are broadly classied into
sl@0
    33
 * <ul>
sl@0
    34
 *     <li> Unassinged Table: Contains code points that are unassigned 
sl@0
    35
 *          in the Unicode Version supported by StringPrep. Currently 
sl@0
    36
 *          RFC 3454 supports Unicode 3.2. </li>
sl@0
    37
 *     <li> Prohibited Table: Contains code points that are prohibted from
sl@0
    38
 *          the output of the StringPrep processing function. </li>
sl@0
    39
 *     <li> Mapping Table: Contains code ponts that are deleted from the output or case mapped. </li>
sl@0
    40
 * </ul>
sl@0
    41
 * 
sl@0
    42
 * The procedure for preparing Unicode strings:
sl@0
    43
 * <ol>
sl@0
    44
 *      <li> Map: For each character in the input, check if it has a mapping
sl@0
    45
 *           and, if so, replace it with its mapping. </li>
sl@0
    46
 *      <li> Normalize: Possibly normalize the result of step 1 using Unicode
sl@0
    47
 *           normalization. </li>
sl@0
    48
 *      <li> Prohibit: Check for any characters that are not allowed in the
sl@0
    49
 *        output.  If any are found, return an error.</li>
sl@0
    50
 *      <li> Check bidi: Possibly check for right-to-left characters, and if
sl@0
    51
 *           any are found, make sure that the whole string satisfies the
sl@0
    52
 *           requirements for bidirectional strings.  If the string does not
sl@0
    53
 *           satisfy the requirements for bidirectional strings, return an
sl@0
    54
 *           error.  </li>
sl@0
    55
 * </ol>
sl@0
    56
 * @author Ram Viswanadha
sl@0
    57
 */
sl@0
    58
#if !UCONFIG_NO_IDNA
sl@0
    59
sl@0
    60
#include "unicode/parseerr.h"
sl@0
    61
sl@0
    62
#ifndef U_HIDE_DRAFT_API
sl@0
    63
sl@0
    64
/**
sl@0
    65
 * The StringPrep profile
sl@0
    66
 * @stable ICU 2.8
sl@0
    67
 */
sl@0
    68
typedef struct UStringPrepProfile UStringPrepProfile;
sl@0
    69
sl@0
    70
sl@0
    71
/** 
sl@0
    72
 * Option to prohibit processing of unassigned code points in the input
sl@0
    73
 * 
sl@0
    74
 * @see  usprep_prepare
sl@0
    75
 * @stable ICU 2.8
sl@0
    76
 */
sl@0
    77
#define USPREP_DEFAULT 0x0000
sl@0
    78
sl@0
    79
/** 
sl@0
    80
 * Option to allow processing of unassigned code points in the input
sl@0
    81
 * 
sl@0
    82
 * @see  usprep_prepare
sl@0
    83
 * @stable ICU 2.8
sl@0
    84
 */
sl@0
    85
#define USPREP_ALLOW_UNASSIGNED 0x0001
sl@0
    86
sl@0
    87
sl@0
    88
#endif /*U_HIDE_DRAFT_API*/
sl@0
    89
sl@0
    90
/**
sl@0
    91
 * Creates a StringPrep profile from the data file.
sl@0
    92
 *
sl@0
    93
 * @param path      string containing the full path pointing to the directory
sl@0
    94
 *                  where the profile reside followed by the package name
sl@0
    95
 *                  e.g. "/usr/resource/my_app/profiles/mydata" on a Unix system.
sl@0
    96
 *                  if NULL, ICU default data files will be used.
sl@0
    97
 * @param fileName  name of the profile file to be opened
sl@0
    98
 * @param status    ICU error code in/out parameter. Must not be NULL.
sl@0
    99
 *                  Must fulfill U_SUCCESS before the function call.
sl@0
   100
 * @return Pointer to UStringPrepProfile that is opened. Should be closed by
sl@0
   101
 * calling usprep_close()
sl@0
   102
 * @see usprep_close()
sl@0
   103
 * @stable ICU 2.8
sl@0
   104
 */
sl@0
   105
U_STABLE UStringPrepProfile* U_EXPORT2
sl@0
   106
usprep_open(const char* path, 
sl@0
   107
            const char* fileName,
sl@0
   108
            UErrorCode* status);
sl@0
   109
sl@0
   110
sl@0
   111
/**
sl@0
   112
 * Closes the profile
sl@0
   113
 * @param profile The profile to close
sl@0
   114
 * @stable ICU 2.8
sl@0
   115
 */
sl@0
   116
U_STABLE void U_EXPORT2
sl@0
   117
usprep_close(UStringPrepProfile* profile);
sl@0
   118
sl@0
   119
sl@0
   120
/**
sl@0
   121
 * Prepare the input buffer for use in applications with the given profile. This operation maps, normalizes(NFKC),
sl@0
   122
 * checks for prohited and BiDi characters in the order defined by RFC 3454
sl@0
   123
 * depending on the options specified in the profile.
sl@0
   124
 *
sl@0
   125
 * @param prep          The profile to use 
sl@0
   126
 * @param src           Pointer to UChar buffer containing the string to prepare
sl@0
   127
 * @param srcLength     Number of characters in the source string
sl@0
   128
 * @param dest          Pointer to the destination buffer to receive the output
sl@0
   129
 * @param destCapacity  The capacity of destination array
sl@0
   130
 * @param options       A bit set of options:
sl@0
   131
 *
sl@0
   132
 *  - USPREP_NONE               Prohibit processing of unassigned code points in the input
sl@0
   133
 *
sl@0
   134
 *  - USPREP_ALLOW_UNASSIGNED   Treat the unassigned code points are in the input 
sl@0
   135
 *                              as normal Unicode code points.
sl@0
   136
 *
sl@0
   137
 * @param parseError        Pointer to UParseError struct to receive information on position 
sl@0
   138
 *                          of error if an error is encountered. Can be NULL.
sl@0
   139
 * @param status            ICU in/out error code parameter.
sl@0
   140
 *                          U_INVALID_CHAR_FOUND if src contains
sl@0
   141
 *                          unmatched single surrogates.
sl@0
   142
 *                          U_INDEX_OUTOFBOUNDS_ERROR if src contains
sl@0
   143
 *                          too many code points.
sl@0
   144
 *                          U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough
sl@0
   145
 * @return The number of UChars in the destination buffer
sl@0
   146
 * @stable ICU 2.8
sl@0
   147
 */
sl@0
   148
sl@0
   149
U_STABLE int32_t U_EXPORT2
sl@0
   150
usprep_prepare(   const UStringPrepProfile* prep,
sl@0
   151
                  const UChar* src, int32_t srcLength, 
sl@0
   152
                  UChar* dest, int32_t destCapacity,
sl@0
   153
                  int32_t options,
sl@0
   154
                  UParseError* parseError,
sl@0
   155
                  UErrorCode* status );
sl@0
   156
sl@0
   157
sl@0
   158
#endif /* #if !UCONFIG_NO_IDNA */
sl@0
   159
sl@0
   160
#endif