icuSources/common/punycode.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) 2002-2003, International Business Machines
   7 *   Corporation and others.  All Rights Reserved.
   8 *
   9 *******************************************************************************
  10 *   file name:  punycode.h
  11 *   encoding:   UTF-8
  12 *   tab size:   8 (not used)
  13 *   indentation:4
  14 *
  15 *   created on: 2002jan31
  16 *   created by: Markus W. Scherer
  17 */
  18
  19 /* This ICU code derived from: */
  20 /*
  21 punycode.c 0.4.0 (2001-Nov-17-Sat)
  22 http://www.cs.berkeley.edu/~amc/idn/
  23 Adam M. Costello
  24 http://www.nicemice.net/amc/
  25 */
  26
  27 #ifndef __PUNYCODE_H__
  28 #define __PUNYCODE_H__
  29
  30 #include "unicode/utypes.h"
  31
  32 #if !UCONFIG_NO_IDNA
  33
  34 /**
  35  * u_strToPunycode() converts Unicode to Punycode.
  36  *
  37  * The input string must not contain single, unpaired surrogates.
  38  * The output will be represented as an array of ASCII code points.
  39  *
  40  * The output string is NUL-terminated according to normal ICU
  41  * string output rules.
  42  *
  43  * @param src Input Unicode string.
  44  *            This function handles a limited amount of code points
  45  *            (the limit is >=64).
  46  *            U_INDEX_OUTOFBOUNDS_ERROR is set if the limit is exceeded.
  47  * @param srcLength Number of UChars in src, or -1 if NUL-terminated.
  48  * @param dest Output Punycode array.
  49  * @param destCapacity Size of dest.
  50  * @param caseFlags Vector of boolean values, one per input UChar,
  51  *                  indicating that the corresponding character is to be
  52  *                  marked for the decoder optionally
  53  *                  uppercasing (TRUE) or lowercasing (FALSE)
  54  *                  the character.
  55  *                  ASCII characters are output directly in the case as marked.
  56  *                  Flags corresponding to trail surrogates are ignored.
  57  *                  If caseFlags==NULL then input characters are not
  58  *                  case-mapped.
  59  * @param pErrorCode ICU in/out error code parameter.
  60  *                   U_INVALID_CHAR_FOUND if src contains
  61  *                   unmatched single surrogates.
  62  *                   U_INDEX_OUTOFBOUNDS_ERROR if src contains
  63  *                   too many code points.
  64  * @return Number of ASCII characters in puny.
  65  *
  66  * @see u_strFromPunycode
  67  */
  68 U_CFUNC int32_t
  69 u_strToPunycode(const UChar *src, int32_t srcLength,
  70                 UChar *dest, int32_t destCapacity,
  71                 const UBool *caseFlags,
  72                 UErrorCode *pErrorCode);
  73
  74 /**
  75  * u_strFromPunycode() converts Punycode to Unicode.
  76  * The Unicode string will be at most as long (in UChars)
  77  * than the Punycode string (in chars).
  78  *
  79  * @param src Input Punycode string.
  80  * @param srcLength Length of puny, or -1 if NUL-terminated
  81  * @param dest Output Unicode string buffer.
  82  * @param destCapacity Size of dest in number of UChars,
  83  *                     and of caseFlags in numbers of UBools.
  84  * @param caseFlags Output array for case flags as
  85  *                  defined by the Punycode string.
  86  *                  The caller should uppercase (TRUE) or lowercase (FASLE)
  87  *                  the corresponding character in dest.
  88  *                  For supplementary characters, only the lead surrogate
  89  *                  is marked, and FALSE is stored for the trail surrogate.
  90  *                  This is redundant and not necessary for ASCII characters
  91  *                  because they are already in the case indicated.
  92  *                  Can be NULL if the case flags are not needed.
  93  * @param pErrorCode ICU in/out error code parameter.
  94  *                   U_INVALID_CHAR_FOUND if a non-ASCII character
  95  *                   precedes the last delimiter ('-'),
  96  *                   or if an invalid character (not a-zA-Z0-9) is found
  97  *                   after the last delimiter.
  98  *                   U_ILLEGAL_CHAR_FOUND if the delta sequence is ill-formed.
  99  * @return Number of UChars written to dest.
 100  *
 101  * @see u_strToPunycode
 102  */
 103 U_CFUNC int32_t
 104 u_strFromPunycode(const UChar *src, int32_t srcLength,
 105                   UChar *dest, int32_t destCapacity,
 106                   UBool *caseFlags,
 107                   UErrorCode *pErrorCode);
 108
 109 #endif /* #if !UCONFIG_NO_IDNA */
 110
 111 #endif
 112
 113 /*
 114  * Hey, Emacs, please set the following:
 115  *
 116  * Local Variables:
 117  * indent-tabs-mode: nil
 118  * End:
 119  *
 120  */