uset.h

linux下开源浏览器WebKit的源码,市面上的很多商用浏览器都是移植自WebKit

 * Removes the given string to the given USet.  After this call,
 * uset_containsString(set, str, strLen) will return FALSE.
 * @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.
 * @stable ICU 2.4
 */
U_STABLE void U_EXPORT2
uset_removeString(USet* set, const UChar* str, int32_t strLen);

/**
 * Removes from this set all of its elements that are contained in the
 * specified set.  This operation effectively modifies this
 * set so that its value is the <i>asymmetric set difference</i> of
 * the two sets.
 * @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
 */
U_DRAFT void U_EXPORT2
uset_removeAll(USet* set, const USet* removeSet);

/**
 * Retain only the elements in this set that are contained in the
 * 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.
 *
 * @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
 */
U_DRAFT void U_EXPORT2
uset_retain(USet* set, UChar32 start, UChar32 end);

/**
 * Retains only the elements in this set that are contained in the
 * specified set.  In other words, removes from this set all of
 * 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.
 *
 * @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
 */
U_DRAFT 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.
 *
 * @param set the object on which to perfrom the compact
 * @draft ICU 3.2
 */
U_DRAFT 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.
 * @param set the set
 * @stable ICU 2.4
 */
U_STABLE void U_EXPORT2
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.
 *
 * @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
 */
U_DRAFT 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.
 * @param set the set
 * @stable ICU 2.4
 */
U_STABLE void U_EXPORT2
uset_clear(USet* set);

/**
 * Returns TRUE if the given USet contains no characters and no
 * strings.
 * @param set the set
 * @return true if set is empty
 * @stable ICU 2.4
 */
U_STABLE UBool U_EXPORT2
uset_isEmpty(const USet* set);

/**
 * Returns TRUE if the given USet contains the given character.
 * @param set the set
 * @param c The codepoint to check for within the set
 * @return true if set contains c
 * @stable ICU 2.4
 */
U_STABLE UBool U_EXPORT2
uset_contains(const USet* set, UChar32 c);

/**
 * Returns TRUE if the given USet contains all characters c
 * where start <= c && c <= end.
 * @param set the set
 * @param start the first character of the range to test, inclusive
 * @param end the last character of the range to test, inclusive
 * @return TRUE if set contains the range
 * @stable ICU 2.2
 */
U_STABLE UBool U_EXPORT2
uset_containsRange(const USet* set, UChar32 start, UChar32 end);

/**
 * Returns TRUE if the given USet contains the given string.
 * @param set the set
 * @param str the string
 * @param strLen the length of the string or -1 if null terminated.
 * @return true if set contains str
 * @stable ICU 2.4
 */
U_STABLE UBool U_EXPORT2
uset_containsString(const USet* set, const UChar* str, int32_t strLen);

/**
 * Returns the index of the given character within this set, where
 * the set is ordered by ascending code point.  If the character
 * is not in this set, return -1.  The inverse of this method is
 * <code>charAt()</code>.
 * @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
 */
U_DRAFT int32_t U_EXPORT2
uset_indexOf(const USet* set, UChar32 c);

/**
 * Returns the character at the given index within this set, where
 * the set is ordered by ascending code point.  If the index is
 * 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
 * @return the character at the given index, or (UChar32)-1.
 * @draft ICU 3.2
 */
U_DRAFT UChar32 U_EXPORT2
uset_charAt(const USet* set, int32_t index);

/**
 * Returns the number of characters and strings contained in the given
 * USet.
 * @param set the set
 * @return a non-negative integer counting the characters and strings
 * contained in set
 * @stable ICU 2.4
 */
U_STABLE int32_t U_EXPORT2
uset_size(const USet* set);

/**
 * Returns the number of items in this set.  An item is either a range
 * of characters or a single multicharacter string.
 * @param set the set
 * @return a non-negative integer counting the character ranges
 * and/or strings contained in set
 * @stable ICU 2.4
 */
U_STABLE int32_t U_EXPORT2
uset_getItemCount(const USet* set);

/**
 * Returns an item of this set.  An item is either a range of
 * characters or a single multicharacter string.
 * @param set the set
 * @param itemIndex a non-negative integer in the range 0..
 * uset_getItemCount(set)-1
 * @param start pointer to variable to receive first character
 * in range, inclusive
 * @param end pointer to variable to receive last character in range,
 * inclusive
 * @param str buffer to receive the string, may be NULL
 * @param strCapacity capacity of str, or 0 if str is NULL
 * @param ec error code
 * @return the length of the string (>= 2), or 0 if the item is a
 * range, in which case it is the range *start..*end, or -1 if
 * itemIndex is out of range
 * @stable ICU 2.4
 */
U_STABLE int32_t U_EXPORT2
uset_getItem(const USet* set, int32_t itemIndex,
             UChar32* start, UChar32* end,
             UChar* str, int32_t strCapacity,
             UErrorCode* ec);

/**
 * Returns true if set1 contains all the characters and strings
 * of set2. It answers the question, 'Is set1 a subset 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
 */
U_DRAFT UBool U_EXPORT2
uset_containsAll(const USet* set1, const USet* set2);

/**
 * 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
 */
U_DRAFT UBool U_EXPORT2
uset_containsNone(const USet* set1, const USet* set2);

/**
 * Returns true if set1 contains some of the characters and strings
 * of set2. It answers the question, 'Does set1 and set2 have an intersection?'
 * @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
 */
U_DRAFT UBool U_EXPORT2
uset_containsSome(const USet* set1, const USet* set2);

/**
 * 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
 */
U_DRAFT UBool U_EXPORT2
uset_equals(const USet* set1, const USet* set2);

/*********************************************************************
 * Serialized set API
 *********************************************************************/

/**
 * Serializes this set into an array of 16-bit integers.  Serialization
 * (currently) only records the characters in the set; multicharacter
 * strings are ignored.
 *
 * The array
 * has following format (each line is one 16-bit integer):
 *
 *  length     = (n+2*m) | (m!=0?0x8000:0)
 *  bmpLength  = n; present if m!=0
 *  bmp[0]
 *  bmp[1]
 *  ...
 *  bmp[n-1]
 *  supp-high[0]
 *  supp-low[0]
 *  supp-high[1]
 *  supp-low[1]
 *  ...
 *  supp-high[m-1]
 *  supp-low[m-1]
 *
 * The array starts with a header.  After the header are n bmp
 * code points, then m supplementary code points.  Either n or m
 * or both may be zero.  n+2*m is always <= 0x7FFF.
 *
 * If there are no supplementary characters (if m==0) then the
 * header is one 16-bit integer, 'length', with value n.
 *
 * If there are supplementary characters (if m!=0) then the header
 * is two 16-bit integers.  The first, 'length', has value
 * (n+2*m)|0x8000.  The second, 'bmpLength', has value n.
 *
 * After the header the code points are stored in ascending order.
 * Supplementary code points are stored as most significant 16
 * bits followed by least significant 16 bits.
 *
 * @param set the set
 * @param dest pointer to buffer of destCapacity 16-bit integers.
 * May be NULL only if destCapacity is zero.
 * @param destCapacity size of dest, or zero.  Must not be negative.
 * @param pErrorCode pointer to the error code.  Will be set to
 * U_INDEX_OUTOFBOUNDS_ERROR if n+2*m > 0x7FFF.  Will be set to
 * U_BUFFER_OVERFLOW_ERROR if n+2*m+(m!=0?2:1) > destCapacity.
 * @return the total length of the serialized format, including
 * the header, that is, n+2*m+(m!=0?2:1), or 0 on error other
 * than U_BUFFER_OVERFLOW_ERROR.
 * @stable ICU 2.4
 */
U_STABLE int32_t U_EXPORT2
uset_serialize(const USet* set, uint16_t* dest, int32_t destCapacity, UErrorCode* pErrorCode);

/**
 * Given a serialized array, fill in the given serialized set object.
 * @param fillSet pointer to result
 * @param src pointer to start of array
 * @param srcLength length of array
 * @return true if the given array is valid, otherwise false
 * @stable ICU 2.4
 */
U_STABLE UBool U_EXPORT2
uset_getSerializedSet(USerializedSet* fillSet, const uint16_t* src, int32_t srcLength);

/**
 * Set the USerializedSet to contain the given character (and nothing
 * else).
 * @param fillSet pointer to result
 * @param c The codepoint to set
 * @stable ICU 2.4
 */
U_STABLE void U_EXPORT2
uset_setSerializedToOne(USerializedSet* fillSet, UChar32 c);

/**
 * Returns TRUE if the given USerializedSet contains the given
 * character.
 * @param set the serialized set
 * @param c The codepoint to check for within the set
 * @return true if set contains c
 * @stable ICU 2.4
 */
U_STABLE UBool U_EXPORT2
uset_serializedContains(const USerializedSet* set, UChar32 c);

/**
 * Returns the number of disjoint ranges of characters contained in
 * the given serialized set.  Ignores any strings contained in the
 * set.
 * @param set the serialized set
 * @return a non-negative integer counting the character ranges
 * contained in set
 * @stable ICU 2.4
 */
U_STABLE int32_t U_EXPORT2
uset_getSerializedRangeCount(const USerializedSet* set);

/**
 * Returns a range of characters contained in the given serialized
 * set.
 * @param set the serialized set
 * @param rangeIndex a non-negative integer in the range 0..
 * uset_getSerializedRangeCount(set)-1
 * @param pStart pointer to variable to receive first character
 * in range, inclusive
 * @param pEnd pointer to variable to receive last character in range,
 * inclusive
 * @return true if rangeIndex is valid, otherwise false
 * @stable ICU 2.4
 */
U_STABLE UBool U_EXPORT2
uset_getSerializedRange(const USerializedSet* set, int32_t rangeIndex,
                        UChar32* pStart, UChar32* pEnd);

#endif