X-Git-Url: https://git.saurik.com/apple/icu.git/blobdiff_plain/374ca955a76ecab1204ca8bfa63ff9238d998416..2ca993e82fb37b597a3c73ecd1586a139a6579c5:/icuSources/common/unicode/uset.h

diff --git a/icuSources/common/unicode/uset.h b/icuSources/common/unicode/uset.h
index b82ceb8f..eb3c9e6a 100644
--- a/icuSources/common/unicode/uset.h
+++ b/icuSources/common/unicode/uset.h
@@ -1,7 +1,7 @@
 /*
 *******************************************************************************
 *
-*   Copyright (C) 2002-2004, International Business Machines
+*   Copyright (C) 2002-2014, International Business Machines
 *   Corporation and others.  All Rights Reserved.
 *
 *******************************************************************************
@@ -29,6 +29,7 @@
 
 #include "unicode/utypes.h"
 #include "unicode/uchar.h"
+#include "unicode/localpointer.h"
 
 #ifndef UCNV_H
 struct USet;
@@ -57,30 +58,157 @@ enum {
      * will match 'a', 'A', 'b', and 'B'.  "[^ab]" with this flag will
      * match all except 'a', 'A', 'b', and 'B'. This performs a full
      * closure over case mappings, e.g. U+017F for s.
+     *
+     * The resulting set is a superset of the input for the code points but
+     * not for the strings.
+     * It performs a case mapping closure of the code points and adds
+     * full case folding strings for the code points, and reduces strings of
+     * the original set to their full case folding equivalents.
+     *
+     * This is designed for case-insensitive matches, for example
+     * in regular expressions. The full code point case closure allows checking of
+     * an input character directly against the closure set.
+     * Strings are matched by comparing the case-folded form from the closure
+     * set with an incremental case folding of the string in question.
+     *
+     * The closure set will also contain single code points if the original
+     * set contained case-equivalent strings (like U+00DF for "ss" or "Ss" etc.).
+     * This is not necessary (that is, redundant) for the above matching method
+     * but results in the same closure sets regardless of whether the original
+     * set contained the code point or a string.
+     *
      * @stable ICU 2.4
      */
     USET_CASE_INSENSITIVE = 2,  
 
-    /**
-     * Bitmask for UnicodeSet::closeOver() indicating letter case.
-     * This may be ORed together with other selectors.
-     * @internal
-     */
-    USET_CASE = 2,
-
     /**
      * Enable case insensitive matching.  E.g., "[ab]" with this flag
      * will match 'a', 'A', 'b', and 'B'.  "[^ab]" with this flag will
      * match all except 'a', 'A', 'b', and 'B'. This adds the lower-,
      * title-, and uppercase mappings as well as the case folding
      * of each existing element in the set.
-     * @draft ICU 3.2
+     * @stable ICU 3.2
+     */
+    USET_ADD_CASE_MAPPINGS = 4
+};
+
+/**
+ * Argument values for whether span() and similar functions continue while
+ * the current character is contained vs. not contained in the set.
+ *
+ * The functionality is straightforward for sets with only single code points,
+ * without strings (which is the common case):
+ * - USET_SPAN_CONTAINED and USET_SPAN_SIMPLE work the same.
+ * - USET_SPAN_CONTAINED and USET_SPAN_SIMPLE are inverses of USET_SPAN_NOT_CONTAINED.
+ * - span() and spanBack() partition any string the same way when
+ *   alternating between span(USET_SPAN_NOT_CONTAINED) and
+ *   span(either "contained" condition).
+ * - Using a complemented (inverted) set and the opposite span conditions
+ *   yields the same results.
+ *
+ * When a set contains multi-code point strings, then these statements may not
+ * be true, depending on the strings in the set (for example, whether they
+ * overlap with each other) and the string that is processed.
+ * For a set with strings:
+ * - The complement of the set contains the opposite set of code points,
+ *   but the same set of strings.
+ *   Therefore, complementing both the set and the span conditions
+ *   may yield different results.
+ * - When starting spans at different positions in a string
+ *   (span(s, ...) vs. span(s+1, ...)) the ends of the spans may be different
+ *   because a set string may start before the later position.
+ * - span(USET_SPAN_SIMPLE) may be shorter than
+ *   span(USET_SPAN_CONTAINED) because it will not recursively try
+ *   all possible paths.
+ *   For example, with a set which contains the three strings "xy", "xya" and "ax",
+ *   span("xyax", USET_SPAN_CONTAINED) will return 4 but
+ *   span("xyax", USET_SPAN_SIMPLE) will return 3.
+ *   span(USET_SPAN_SIMPLE) will never be longer than
+ *   span(USET_SPAN_CONTAINED).
+ * - With either "contained" condition, span() and spanBack() may partition
+ *   a string in different ways.
+ *   For example, with a set which contains the two strings "ab" and "ba",
+ *   and when processing the string "aba",
+ *   span() will yield contained/not-contained boundaries of { 0, 2, 3 }
+ *   while spanBack() will yield boundaries of { 0, 1, 3 }.
+ *
+ * Note: If it is important to get the same boundaries whether iterating forward
+ * or backward through a string, then either only span() should be used and
+ * the boundaries cached for backward operation, or an ICU BreakIterator
+ * could be used.
+ *
+ * Note: Unpaired surrogates are treated like surrogate code points.
+ * Similarly, set strings match only on code point boundaries,
+ * never in the middle of a surrogate pair.
+ * Illegal UTF-8 sequences are treated like U+FFFD.
+ * When processing UTF-8 strings, malformed set strings
+ * (strings with unpaired surrogates which cannot be converted to UTF-8)
+ * are ignored.
+ *
+ * @stable ICU 3.8
+ */
+typedef enum USetSpanCondition {
+    /**
+     * Continues a span() while there is no set element at the current position.
+     * Increments by one code point at a time.
+     * Stops before the first set element (character or string).
+     * (For code points only, this is like while contains(current)==FALSE).
+     *
+     * When span() returns, the substring between where it started and the position
+     * it returned consists only of characters that are not in the set,
+     * and none of its strings overlap with the span.
+     *
+     * @stable ICU 3.8
+     */
+    USET_SPAN_NOT_CONTAINED = 0,
+    /**
+     * Spans the longest substring that is a concatenation of set elements (characters or strings).
+     * (For characters only, this is like while contains(current)==TRUE).
+     *
+     * When span() returns, the substring between where it started and the position
+     * it returned consists only of set elements (characters or strings) that are in the set.
+     *
+     * If a set contains strings, then the span will be the longest substring for which there
+     * exists at least one non-overlapping concatenation of set elements (characters or strings).
+     * This is equivalent to a POSIX regular expression for <code>(OR of each set element)*</code>.
+     * (Java/ICU/Perl regex stops at the first match of an OR.)
+     *
+     * @stable ICU 3.8
+     */
+    USET_SPAN_CONTAINED = 1,
+    /**
+     * Continues a span() while there is a set element at the current position.
+     * Increments by the longest matching element at each position.
+     * (For characters only, this is like while contains(current)==TRUE).
+     *
+     * When span() returns, the substring between where it started and the position
+     * it returned consists only of set elements (characters or strings) that are in the set.
+     *
+     * If a set only contains single characters, then this is the same
+     * as USET_SPAN_CONTAINED.
+     *
+     * If a set contains strings, then the span will be the longest substring
+     * with a match at each position with the longest single set element (character or string).
+     *
+     * Use this span condition together with other longest-match algorithms,
+     * such as ICU converters (ucnv_getUnicodeSet()).
+     *
+     * @stable ICU 3.8
+     */
+    USET_SPAN_SIMPLE = 2,
+    /**
+     * One more than the last span condition.
+     * @stable ICU 3.8
      */
-    USET_ADD_CASE_MAPPINGS = 4,
+    USET_SPAN_CONDITION_COUNT
+} USetSpanCondition;
 
+enum {
     /**
-     * Enough for any single-code point set
-     * @internal
+     * Capacity of USerializedSet::staticArray.
+     * Enough for any single-code point set.
+     * Also provides padding for nice sizeof(USerializedSet).
+     * @stable ICU 2.4
      */
     USET_SERIALIZED_STATIC_ARRAY_CAPACITY=8
 };
@@ -117,9 +245,20 @@ typedef struct USerializedSet {
  * USet API
  *********************************************************************/
 
+/**
+ * Create an empty USet object.
+ * Equivalent to uset_open(1, 0).
+ * @return a newly created USet.  The caller must call uset_close() on
+ * it when done.
+ * @stable ICU 4.2
+ */
+U_STABLE USet* U_EXPORT2
+uset_openEmpty(void);
+
 /**
  * Creates a USet object that contains the range of characters
- * start..end, inclusive.
+ * start..end, inclusive.  If <code>start > end</code> 
+ * then an empty set is created (same as using uset_openEmpty()).
  * @param start first character of the range, inclusive
  * @param end last character of the range, inclusive
  * @return a newly created USet.  The caller must call uset_close() on
@@ -167,15 +306,89 @@ uset_openPatternOptions(const UChar* pattern, int32_t patternLength,
 U_STABLE void U_EXPORT2
 uset_close(USet* set);
 
+#if U_SHOW_CPLUSPLUS_API
+
+U_NAMESPACE_BEGIN
+
+/**
+ * \class LocalUSetPointer
+ * "Smart pointer" class, closes a USet via uset_close().
+ * For most methods see the LocalPointerBase base class.
+ *
+ * @see LocalPointerBase
+ * @see LocalPointer
+ * @stable ICU 4.4
+ */
+U_DEFINE_LOCAL_OPEN_POINTER(LocalUSetPointer, USet, uset_close);
+
+U_NAMESPACE_END
+
+#endif
+
+/**
+ * Returns a copy of this object.
+ * If this set is frozen, then the clone will be frozen as well.
+ * Use uset_cloneAsThawed() for a mutable clone of a frozen set.
+ * @param set the original set
+ * @return the newly allocated copy of the set
+ * @see uset_cloneAsThawed
+ * @stable ICU 3.8
+ */
+U_STABLE USet * U_EXPORT2
+uset_clone(const USet *set);
+
+/**
+ * Determines whether the set has been frozen (made immutable) or not.
+ * See the ICU4J Freezable interface for details.
+ * @param set the set
+ * @return TRUE/FALSE for whether the set has been frozen
+ * @see uset_freeze
+ * @see uset_cloneAsThawed
+ * @stable ICU 3.8
+ */
+U_STABLE UBool U_EXPORT2
+uset_isFrozen(const USet *set);
+
+/**
+ * Freeze the set (make it immutable).
+ * Once frozen, it cannot be unfrozen and is therefore thread-safe
+ * until it is deleted.
+ * See the ICU4J Freezable interface for details.
+ * Freezing the set may also make some operations faster, for example
+ * uset_contains() and uset_span().
+ * A frozen set will not be modified. (It remains frozen.)
+ * @param set the set
+ * @return the same set, now frozen
+ * @see uset_isFrozen
+ * @see uset_cloneAsThawed
+ * @stable ICU 3.8
+ */
+U_STABLE void U_EXPORT2
+uset_freeze(USet *set);
+
+/**
+ * Clone the set and make the clone mutable.
+ * See the ICU4J Freezable interface for details.
+ * @param set the set
+ * @return the mutable clone
+ * @see uset_freeze
+ * @see uset_isFrozen
+ * @see uset_clone
+ * @stable ICU 3.8
+ */
+U_STABLE USet * U_EXPORT2
+uset_cloneAsThawed(const USet *set);
+
 /**
  * Causes the USet object to represent the range <code>start - end</code>.
  * If <code>start > end</code> then this USet is set to an empty range.
+ * A frozen set will not be modified.
  * @param set the object to set to the given range
  * @param start first character in the set, inclusive
  * @param end last character in the set, inclusive
- * @draft ICU 3.2
+ * @stable ICU 3.2
  */
-U_DRAFT void U_EXPORT2
+U_STABLE void U_EXPORT2
 uset_set(USet* set,
          UChar32 start, UChar32 end);
 
@@ -184,6 +397,7 @@ uset_set(USet* set,
  * pattern. See the UnicodeSet class description for the syntax of 
  * the pattern language. See also the User Guide chapter about UnicodeSet.
  * <em>Empties the set passed before applying the pattern.</em>
+ * A frozen set will not be modified.
  * @param set               The set to which the pattern is to be applied. 
  * @param pattern           A pointer to UChar string specifying what characters are in the set.
  *                          The character at pattern[0] must be a '['.
@@ -196,10 +410,10 @@ uset_set(USet* set,
  *                          of the parsed pattern.
  *                          If the status code indicates failure, then the return value 
  *                          is the index of the error in the source.
- *                                  
- * @draft ICU 2.8
+ *
+ * @stable ICU 2.8
  */
-U_DRAFT int32_t U_EXPORT2 
+U_STABLE int32_t U_EXPORT2 
 uset_applyPattern(USet *set,
                   const UChar *pattern, int32_t patternLength,
                   uint32_t options,
@@ -209,6 +423,7 @@ uset_applyPattern(USet *set,
  * Modifies the set to contain those code points which have the given value
  * for the given binary or enumerated property, as returned by
  * u_getIntPropertyValue.  Prior contents of this set are lost.
+ * A frozen set will not be modified.
  *
  * @param set the object to contain the code points defined by the property
  *
@@ -224,9 +439,9 @@ uset_applyPattern(USet *set,
  *
  * @param ec error code input/output parameter
  *
- * @draft ICU 3.2
+ * @stable ICU 3.2
  */
-U_DRAFT void U_EXPORT2
+U_STABLE void U_EXPORT2
 uset_applyIntPropertyValue(USet* set,
                            UProperty prop, int32_t value, UErrorCode* ec);
 
@@ -234,6 +449,7 @@ uset_applyIntPropertyValue(USet* set,
  * Modifies the set to contain those code points which have the
  * given value for the given property.  Prior contents of this
  * set are lost.
+ * A frozen set will not be modified.
  *
  * @param set the object to contain the code points defined by the given
  * property and value alias
@@ -246,7 +462,8 @@ uset_applyIntPropertyValue(USet* set,
  * matched loosely and correspond to the following sets:
  *
  * "ANY" = [\\u0000-\\U0010FFFF],
- * "ASCII" = [\\u0000-\\u007F].
+ * "ASCII" = [\\u0000-\\u007F],
+ * "Assigned" = [:^Cn:].
  *
  * @param propLength the length of the prop, or -1 if NULL
  *
@@ -261,9 +478,9 @@ uset_applyIntPropertyValue(USet* set,
  *
  * @param ec error code input/output parameter
  *
- * @draft ICU 3.2
+ * @stable ICU 3.2
  */
-U_DRAFT void U_EXPORT2
+U_STABLE void U_EXPORT2
 uset_applyPropertyAlias(USet* set,
                         const UChar *prop, int32_t propLength,
                         const UChar *value, int32_t valueLength,
@@ -276,9 +493,9 @@ uset_applyPropertyAlias(USet* set,
  * @param pattern a string specifying the pattern
  * @param patternLength the length of the pattern, or -1 if NULL
  * @param pos the given position
- * @draft ICU 3.2
+ * @stable ICU 3.2
  */
-U_DRAFT UBool U_EXPORT2
+U_STABLE UBool U_EXPORT2
 uset_resemblesPattern(const UChar *pattern, int32_t patternLength,
                       int32_t pos);
 
@@ -306,6 +523,7 @@ uset_toPattern(const USet* set,
 /**
  * Adds the given character to the given USet.  After this call,
  * uset_contains(set, c) will return TRUE.
+ * A frozen set will not be modified.
  * @param set the object to which to add the character
  * @param c the character to add
  * @stable ICU 2.4
@@ -319,6 +537,7 @@ uset_add(USet* set, UChar32 c);
  * modifies this set so that its value is the <i>union</i> of the two
  * sets.  The behavior of this operation is unspecified if the specified
  * collection is modified while the operation is in progress.
+ * A frozen set will not be modified.
  *
  * @param set the object to which to add the set
  * @param additionalSet the source set whose elements are to be added to this set.
@@ -330,6 +549,7 @@ uset_addAll(USet* set, const USet *additionalSet);
 /**
  * Adds the given range of characters to the given USet.  After this call,
  * uset_contains(set, start, end) will return TRUE.
+ * A frozen set will not be modified.
  * @param set the object to which to add the character
  * @param start the first character of the range to add, inclusive
  * @param end the last character of the range to add, inclusive
@@ -341,6 +561,7 @@ uset_addRange(USet* set, UChar32 start, UChar32 end);
 /**
  * Adds the given string to the given USet.  After this call,
  * uset_containsString(set, str, strLen) will return TRUE.
+ * A frozen set will not be modified.
  * @param set the object to which to add the character
  * @param str the string to add
  * @param strLen the length of the string or -1 if null terminated.
@@ -349,9 +570,22 @@ uset_addRange(USet* set, UChar32 start, UChar32 end);
 U_STABLE void U_EXPORT2
 uset_addString(USet* set, const UChar* str, int32_t strLen);
 
+/**
+ * Adds each of the characters in this string to the set. Thus "ch" => {"c", "h"}
+ * If this set already any particular character, it has no effect on that character.
+ * A frozen set will not be modified.
+ * @param set the object to which to add the character
+ * @param str the source string
+ * @param strLen the length of the string or -1 if null terminated.
+ * @stable ICU 3.4
+ */
+U_STABLE void U_EXPORT2
+uset_addAllCodePoints(USet* set, const UChar *str, int32_t strLen);
+
 /**
  * Removes the given character from the given USet.  After this call,
  * uset_contains(set, c) will return FALSE.
+ * A frozen set will not be modified.
  * @param set the object from which to remove the character
  * @param c the character to remove
  * @stable ICU 2.4
@@ -362,6 +596,7 @@ uset_remove(USet* set, UChar32 c);
 /**
  * Removes the given range of characters from the given USet.  After this call,
  * uset_contains(set, start, end) will return FALSE.
+ * A frozen set will not be modified.
  * @param set the object to which to add the character
  * @param start the first character of the range to remove, inclusive
  * @param end the last character of the range to remove, inclusive
@@ -373,6 +608,7 @@ uset_removeRange(USet* set, UChar32 start, UChar32 end);
 /**
  * Removes the given string to the given USet.  After this call,
  * uset_containsString(set, str, strLen) will return FALSE.
+ * A frozen set will not be modified.
  * @param set the object to which to add the character
  * @param str the string to remove
  * @param strLen the length of the string or -1 if null terminated.
@@ -386,12 +622,13 @@ uset_removeString(USet* set, const UChar* str, int32_t strLen);
  * specified set.  This operation effectively modifies this
  * set so that its value is the <i>asymmetric set difference</i> of
  * the two sets.
+ * A frozen set will not be modified.
  * @param set the object from which the elements are to be removed
  * @param removeSet the object that defines which elements will be
  * removed from this set
- * @draft ICU 3.2
+ * @stable ICU 3.2
  */
-U_DRAFT void U_EXPORT2
+U_STABLE void U_EXPORT2
 uset_removeAll(USet* set, const USet* removeSet);
 
 /**
@@ -399,15 +636,16 @@ uset_removeAll(USet* set, const USet* removeSet);
  * specified range.  If <code>start > end</code> then an empty range is
  * retained, leaving the set empty.  This is equivalent to
  * a boolean logic AND, or a set INTERSECTION.
+ * A frozen set will not be modified.
  *
  * @param set the object for which to retain only the specified range
  * @param start first character, inclusive, of range to be retained
  * to this set.
  * @param end last character, inclusive, of range to be retained
  * to this set.
- * @draft ICU 3.2
+ * @stable ICU 3.2
  */
-U_DRAFT void U_EXPORT2
+U_STABLE void U_EXPORT2
 uset_retain(USet* set, UChar32 start, UChar32 end);
 
 /**
@@ -416,28 +654,31 @@ uset_retain(USet* set, UChar32 start, UChar32 end);
  * its elements that are not contained in the specified set.  This
  * operation effectively modifies this set so that its value is
  * the <i>intersection</i> of the two sets.
+ * A frozen set will not be modified.
  *
  * @param set the object on which to perform the retain
  * @param retain set that defines which elements this set will retain
- * @draft ICU 3.2
+ * @stable ICU 3.2
  */
-U_DRAFT void U_EXPORT2
+U_STABLE void U_EXPORT2
 uset_retainAll(USet* set, const USet* retain);
 
 /**
  * Reallocate this objects internal structures to take up the least
  * possible space, without changing this object's value.
+ * A frozen set will not be modified.
  *
  * @param set the object on which to perfrom the compact
- * @draft ICU 3.2
+ * @stable ICU 3.2
  */
-U_DRAFT void U_EXPORT2
+U_STABLE void U_EXPORT2
 uset_compact(USet* set);
 
 /**
  * Inverts this set.  This operation modifies this set so that
  * its value is its complement.  This operation does not affect
  * the multicharacter strings, if any.
+ * A frozen set will not be modified.
  * @param set the set
  * @stable ICU 2.4
  */
@@ -448,24 +689,64 @@ uset_complement(USet* set);
  * Complements in this set all elements contained in the specified
  * set.  Any character in the other set will be removed if it is
  * in this set, or will be added if it is not in this set.
+ * A frozen set will not be modified.
  *
  * @param set the set with which to complement
  * @param complement set that defines which elements will be xor'ed
  * from this set.
- * @draft ICU 3.2
+ * @stable ICU 3.2
  */
-U_DRAFT void U_EXPORT2
+U_STABLE void U_EXPORT2
 uset_complementAll(USet* set, const USet* complement);
 
 /**
  * Removes all of the elements from this set.  This set will be
  * empty after this call returns.
+ * A frozen set will not be modified.
  * @param set the set
  * @stable ICU 2.4
  */
 U_STABLE void U_EXPORT2
 uset_clear(USet* set);
 
+/**
+ * Close this set over the given attribute.  For the attribute
+ * USET_CASE, the result is to modify this set so that:
+ *
+ * 1. For each character or string 'a' in this set, all strings or
+ * characters 'b' such that foldCase(a) == foldCase(b) are added
+ * to this set.
+ *
+ * 2. For each string 'e' in the resulting set, if e !=
+ * foldCase(e), 'e' will be removed.
+ *
+ * Example: [aq\\u00DF{Bc}{bC}{Fi}] => [aAqQ\\u00DF\\uFB01{ss}{bc}{fi}]
+ *
+ * (Here foldCase(x) refers to the operation u_strFoldCase, and a
+ * == b denotes that the contents are the same, not pointer
+ * comparison.)
+ *
+ * A frozen set will not be modified.
+ *
+ * @param set the set
+ *
+ * @param attributes bitmask for attributes to close over.
+ * Currently only the USET_CASE bit is supported.  Any undefined bits
+ * are ignored.
+ * @stable ICU 4.2
+ */
+U_STABLE void U_EXPORT2
+uset_closeOver(USet* set, int32_t attributes);
+
+/**
+ * Remove all strings from this set.
+ *
+ * @param set the set
+ * @stable ICU 4.2
+ */
+U_STABLE void U_EXPORT2
+uset_removeAllStrings(USet* set);
+
 /**
  * Returns TRUE if the given USet contains no characters and no
  * strings.
@@ -478,6 +759,7 @@ uset_isEmpty(const USet* set);
 
 /**
  * Returns TRUE if the given USet contains the given character.
+ * This function works faster with a frozen set.
  * @param set the set
  * @param c The codepoint to check for within the set
  * @return true if set contains c
@@ -517,9 +799,9 @@ uset_containsString(const USet* set, const UChar* str, int32_t strLen);
  * @param set the set
  * @param c the character to obtain the index for
  * @return an index from 0..size()-1, or -1
- * @draft ICU 3.2
+ * @stable ICU 3.2
  */
-U_DRAFT int32_t U_EXPORT2
+U_STABLE int32_t U_EXPORT2
 uset_indexOf(const USet* set, UChar32 c);
 
 /**
@@ -528,12 +810,12 @@ uset_indexOf(const USet* set, UChar32 c);
  * out of range, return (UChar32)-1.  The inverse of this method is
  * <code>indexOf()</code>.
  * @param set the set
- * @param index an index from 0..size()-1 to obtain the char for
+ * @param charIndex an index from 0..size()-1 to obtain the char for
  * @return the character at the given index, or (UChar32)-1.
- * @draft ICU 3.2
+ * @stable ICU 3.2
  */
-U_DRAFT UChar32 U_EXPORT2
-uset_charAt(const USet* set, int32_t index);
+U_STABLE UChar32 U_EXPORT2
+uset_charAt(const USet* set, int32_t charIndex);
 
 /**
  * Returns the number of characters and strings contained in the given
@@ -583,24 +865,37 @@ uset_getItem(const USet* set, int32_t itemIndex,
 
 /**
  * Returns true if set1 contains all the characters and strings
- * of set2. It answers the question, 'Is set1 a subset of set2?'
+ * of set2. It answers the question, 'Is set1 a superset of set2?'
  * @param set1 set to be checked for containment
  * @param set2 set to be checked for containment
  * @return true if the test condition is met
- * @draft ICU 3.2
+ * @stable ICU 3.2
  */
-U_DRAFT UBool U_EXPORT2
+U_STABLE UBool U_EXPORT2
 uset_containsAll(const USet* set1, const USet* set2);
 
+/**
+ * Returns true if this set contains all the characters
+ * of the given string. This is does not check containment of grapheme
+ * clusters, like uset_containsString.
+ * @param set set of characters to be checked for containment
+ * @param str string containing codepoints to be checked for containment
+ * @param strLen the length of the string or -1 if null terminated.
+ * @return true if the test condition is met
+ * @stable ICU 3.4
+ */
+U_STABLE UBool U_EXPORT2
+uset_containsAllCodePoints(const USet* set, const UChar *str, int32_t strLen);
+
 /**
  * Returns true if set1 contains none of the characters and strings
  * of set2. It answers the question, 'Is set1 a disjoint set of set2?'
  * @param set1 set to be checked for containment
  * @param set2 set to be checked for containment
  * @return true if the test condition is met
- * @draft ICU 3.2
+ * @stable ICU 3.2
  */
-U_DRAFT UBool U_EXPORT2
+U_STABLE UBool U_EXPORT2
 uset_containsNone(const USet* set1, const USet* set2);
 
 /**
@@ -609,20 +904,106 @@ uset_containsNone(const USet* set1, const USet* set2);
  * @param set1 set to be checked for containment
  * @param set2 set to be checked for containment
  * @return true if the test condition is met
- * @draft ICU 3.2
+ * @stable ICU 3.2
  */
-U_DRAFT UBool U_EXPORT2
+U_STABLE UBool U_EXPORT2
 uset_containsSome(const USet* set1, const USet* set2);
 
+/**
+ * Returns the length of the initial substring of the input string which
+ * consists only of characters and strings that are contained in this set
+ * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
+ * or only of characters and strings that are not contained
+ * in this set (USET_SPAN_NOT_CONTAINED).
+ * See USetSpanCondition for details.
+ * Similar to the strspn() C library function.
+ * Unpaired surrogates are treated according to contains() of their surrogate code points.
+ * This function works faster with a frozen set and with a non-negative string length argument.
+ * @param set the set
+ * @param s start of the string
+ * @param length of the string; can be -1 for NUL-terminated
+ * @param spanCondition specifies the containment condition
+ * @return the length of the initial substring according to the spanCondition;
+ *         0 if the start of the string does not fit the spanCondition
+ * @stable ICU 3.8
+ * @see USetSpanCondition
+ */
+U_STABLE int32_t U_EXPORT2
+uset_span(const USet *set, const UChar *s, int32_t length, USetSpanCondition spanCondition);
+
+/**
+ * Returns the start of the trailing substring of the input string which
+ * consists only of characters and strings that are contained in this set
+ * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
+ * or only of characters and strings that are not contained
+ * in this set (USET_SPAN_NOT_CONTAINED).
+ * See USetSpanCondition for details.
+ * Unpaired surrogates are treated according to contains() of their surrogate code points.
+ * This function works faster with a frozen set and with a non-negative string length argument.
+ * @param set the set
+ * @param s start of the string
+ * @param length of the string; can be -1 for NUL-terminated
+ * @param spanCondition specifies the containment condition
+ * @return the start of the trailing substring according to the spanCondition;
+ *         the string length if the end of the string does not fit the spanCondition
+ * @stable ICU 3.8
+ * @see USetSpanCondition
+ */
+U_STABLE int32_t U_EXPORT2
+uset_spanBack(const USet *set, const UChar *s, int32_t length, USetSpanCondition spanCondition);
+
+/**
+ * Returns the length of the initial substring of the input string which
+ * consists only of characters and strings that are contained in this set
+ * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
+ * or only of characters and strings that are not contained
+ * in this set (USET_SPAN_NOT_CONTAINED).
+ * See USetSpanCondition for details.
+ * Similar to the strspn() C library function.
+ * Malformed byte sequences are treated according to contains(0xfffd).
+ * This function works faster with a frozen set and with a non-negative string length argument.
+ * @param set the set
+ * @param s start of the string (UTF-8)
+ * @param length of the string; can be -1 for NUL-terminated
+ * @param spanCondition specifies the containment condition
+ * @return the length of the initial substring according to the spanCondition;
+ *         0 if the start of the string does not fit the spanCondition
+ * @stable ICU 3.8
+ * @see USetSpanCondition
+ */
+U_STABLE int32_t U_EXPORT2
+uset_spanUTF8(const USet *set, const char *s, int32_t length, USetSpanCondition spanCondition);
+
+/**
+ * Returns the start of the trailing substring of the input string which
+ * consists only of characters and strings that are contained in this set
+ * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
+ * or only of characters and strings that are not contained
+ * in this set (USET_SPAN_NOT_CONTAINED).
+ * See USetSpanCondition for details.
+ * Malformed byte sequences are treated according to contains(0xfffd).
+ * This function works faster with a frozen set and with a non-negative string length argument.
+ * @param set the set
+ * @param s start of the string (UTF-8)
+ * @param length of the string; can be -1 for NUL-terminated
+ * @param spanCondition specifies the containment condition
+ * @return the start of the trailing substring according to the spanCondition;
+ *         the string length if the end of the string does not fit the spanCondition
+ * @stable ICU 3.8
+ * @see USetSpanCondition
+ */
+U_STABLE int32_t U_EXPORT2
+uset_spanBackUTF8(const USet *set, const char *s, int32_t length, USetSpanCondition spanCondition);
+
 /**
  * Returns true if set1 contains all of the characters and strings
  * of set2, and vis versa. It answers the question, 'Is set1 equal to set2?'
  * @param set1 set to be checked for containment
  * @param set2 set to be checked for containment
  * @return true if the test condition is met
- * @draft ICU 3.2
+ * @stable ICU 3.2
  */
-U_DRAFT UBool U_EXPORT2
+U_STABLE UBool U_EXPORT2
 uset_equals(const USet* set1, const USet* set2);
 
 /*********************************************************************