ICU 56 update step 1

source/i18n/unicode/uspoof.h

 /*
 ***************************************************************************
-* Copyright (C) 2008-2014, International Business Machines Corporation
+* Copyright (C) 2008-2015, International Business Machines Corporation
 * and others. All Rights Reserved.
 ***************************************************************************
 *   file name:  uspoof.h
 *   encoding:   US-ASCII
 *   tab size:   8 (not used)
 *   indentation:4
 *
 *   created on: 2008Feb13
 *   created by: Andy Heninger
 *
@@ skipping 118 matching lines @@
  *  a set of identifiers, and then quickly test whether a new identifier is
  *  confusable with an identifier already in the set.  The uspoof_getSkeleton()
  *  family of functions will produce the skeleton from an identifier.
  *
  *  Note that skeletons are not guaranteed to be stable between versions 
  *  of Unicode or ICU, so an applications should not rely on creating a permanent,
  *  or difficult to update, database of skeletons.  Instabilities result from
  *  identifying new pairs or sequences of characters that are visually
  *  confusable, and thus must be mapped to the same skeleton character(s).
  *
+ *  Skeletons are computed using the algorithm and data describe in Unicode UAX 39.
+ *  The latest proposed update, UAX 39 Version 8 draft 1, says "the tables SL, SA, and ML
+ *  were still problematic, and discouraged from use in [Uniocde] 7.0.
+ *  They were thus removed from version 8.0"
+ *
+ *  In light of this, the default mapping data included with ICU 55 uses the
+ *  Unicode 7 MA (Multi script Any case) table data for the other type options
+ *  (Single Script, Any Case), (Single Script, Lower Case) and (Multi Script, Lower Case).
  */
 
 struct USpoofChecker;
 typedef struct USpoofChecker USpoofChecker; /**< typedef for C of USpoofChecker */
 
 /**
  * Enum for the kinds of checks that USpoofChecker can perform.
  * These enum values are used both to select the set of checks that
  * will be performed, and to report results from the check function.
  *
@@ skipping 111 matching lines @@
      * for returned identifier restriction levels in check results.
      * @stable ICU 51
      */
     typedef enum URestrictionLevel {
         /**
          * Only ASCII characters: U+0000..U+007F
          * 
          * @stable ICU 51
          */
         USPOOF_ASCII = 0x10000000,
-#ifndef U_HIDE_DRAFT_API
         /**
           * All characters in each identifier must be from a single script.
           *
-          * @draft ICU 53
+          * @stable ICU 53
           */
         USPOOF_SINGLE_SCRIPT_RESTRICTIVE = 0x20000000,
-#endif /* U_HIDE_DRAFT_API */
         /**
          * All characters in each identifier must be from a single script, or from the combinations: Latin + Han +
          * Hiragana + Katakana; Latin + Han + Bopomofo; or Latin + Han + Hangul. Note that this level will satisfy the
          * vast majority of Latin-script users; also that TR36 has ASCII instead of Latin.
          * 
          * @stable ICU 51
          */
         USPOOF_HIGHLY_RESTRICTIVE = 0x30000000,
         /**
          * Allow Latin with other scripts except Cyrillic, Greek, Cherokee Otherwise, the same as Highly Restrictive
          * 
          * @stable ICU 51
          */
         USPOOF_MODERATELY_RESTRICTIVE = 0x40000000,
         /**
          * Allow arbitrary mixtures of scripts. Otherwise, the same as Moderately Restrictive.
          * 
          * @stable ICU 51
          */
         USPOOF_MINIMALLY_RESTRICTIVE = 0x50000000,
         /**
          * Any valid identifiers, including characters outside of the Identifier Profile.
          * 
          * @stable ICU 51
          */
         USPOOF_UNRESTRICTIVE = 0x60000000,
-#ifndef U_HIDE_DRAFT_API
         /**
           * Mask for selecting the Restriction Level bits from the return value of uspoof_check().
           * 
-          * @draft ICU 53
+          * @stable ICU 53
           */
          USPOOF_RESTRICTION_LEVEL_MASK = 0x7F000000 
-#endif /* U_HIDE_DRAFT_API */
     } URestrictionLevel;
 
 /**
  *  Create a Unicode Spoof Checker, configured to perform all 
  *  checks except for USPOOF_LOCALE_LIMIT and USPOOF_CHAR_LIMIT.
  *  Note that additional checks may be added in the future,
  *  resulting in the changes to the default checking behavior.
  *
  *  @param status  The error code, set if this function encounters a problem.
  *  @return        the newly created Spoof Checker
@@ skipping 540 matching lines @@
   *  Using skeletons directly makes it possible to quickly check
   *  whether an identifier is confusable with any of some large
   *  set of existing identifiers, by creating an efficiently
   *  searchable collection of the skeletons.
   *
   * @param sc      The USpoofChecker
   * @param type    The type of skeleton, corresponding to which
   *                of the Unicode confusable data tables to use.
   *                The default is Mixed-Script, Lowercase.
   *                Allowed options are USPOOF_SINGLE_SCRIPT_CONFUSABLE and
-  *                USPOOF_ANY_CASE_CONFUSABLE.  The two flags may be ORed.
+  *                USPOOF_ANY_CASE.  The two flags may be ORed.
   * @param id      The input identifier whose skeleton will be computed.
   * @param length  The length of the input identifier, expressed in 16 bit
   *                UTF-16 code units, or -1 if the string is zero terminated.
   * @param dest    The output buffer, to receive the skeleton string.
   * @param destCapacity  The length of the output buffer, in 16 bit units.
   *                The destCapacity may be zero, in which case the function will
   *                return the actual length of the skeleton.
   * @param status  The error code, set if an error occurred while attempting to
   *                perform the check.
   * @return        The length of the skeleton string.  The returned length
@@ skipping 61 matching lines @@
   *  Using skeletons directly makes it possible to quickly check
   *  whether an identifier is confusable with any of some large
   *  set of existing identifiers, by creating an efficiently
   *  searchable collection of the skeletons.
   *
   * @param sc      The USpoofChecker.
   * @param type    The type of skeleton, corresponding to which
   *                of the Unicode confusable data tables to use.
   *                The default is Mixed-Script, Lowercase.
   *                Allowed options are USPOOF_SINGLE_SCRIPT_CONFUSABLE and
-  *                USPOOF_ANY_CASE_CONFUSABLE.  The two flags may be ORed.
+  *                USPOOF_ANY_CASE.  The two flags may be ORed.
   * @param id      The input identifier whose skeleton will be computed.
   * @param dest    The output identifier, to receive the skeleton string.
   * @param status  The error code, set if an error occurred while attempting to
   *                perform the check.
   * @return        A reference to the destination (skeleton) string.
   *                
   * @stable ICU 4.2
   */   
 U_I18N_API icu::UnicodeString & U_EXPORT2
 uspoof_getSkeletonUnicodeString(const USpoofChecker *sc,
@@ skipping 87 matching lines @@
  */
 U_STABLE int32_t U_EXPORT2
 uspoof_serialize(USpoofChecker *sc,
                  void *data, int32_t capacity,
                  UErrorCode *status);
 
 
 #endif
 
 #endif   /* USPOOF_H */