Java Code Examples for com.ibm.icu.lang.UCharacter#MAX_VALUE

/**
 * Get a 32 bit data from the table data
 * @param ch  code point for which data is to be retrieved.
 * @param inBlockZero  Output parameter, inBlockZero[0] returns true if the
 *                      char maps into block zero, otherwise false.
 * @return the 32 bit data value.
 */
public int getValue(int ch, boolean [] inBlockZero) 
{
    // valid, uncompacted trie and valid c?
    if (m_isCompacted_ || ch > UCharacter.MAX_VALUE || ch < 0) {
        if (inBlockZero != null) {
            inBlockZero[0] = true;
        }
        return 0;
    }

    int block = m_index_[ch >> SHIFT_];
    if (inBlockZero != null) {
        inBlockZero[0] = (block == 0);
    }
    return m_data_[Math.abs(block) + (ch & MASK_)];
}
 

/**
 * Sets a 32 bit data in the table data
 * @param ch codepoint which data is to be set
 * @param value to set
 * @return true if the set is successful, otherwise 
 *              if the table has been compacted return false
 */
public boolean setValue(int ch, int value) 
{
    // valid, uncompacted trie and valid c? 
    if (m_isCompacted_ || ch > UCharacter.MAX_VALUE || ch < 0) {
        return false;
    }

    int block = getDataBlock(ch);
    if (block < 0) {
        return false;
    }

    m_data_[block + (ch & MASK_)] = value;
    return true;
}
 

/**
* Internal trie getter from a code point.
* Could be faster(?) but longer with
*   if((c32)<=0xd7ff) { (result)=_TRIE_GET_RAW(trie, data, 0, c32); }
* Gets the offset to data which the codepoint points to
* @param ch codepoint
* @return offset to data
*/
protected final int getCodePointOffset(int ch)
{
    // if ((ch >> 16) == 0) slower
    if (ch < 0) {
        return -1;
    } else if (ch < UTF16.LEAD_SURROGATE_MIN_VALUE) {
        // fastpath for the part of the BMP below surrogates (D800) where getRawOffset() works
        return getRawOffset(0, (char)ch);
    } else if (ch < UTF16.SUPPLEMENTARY_MIN_VALUE) {
        // BMP codepoint
        return getBMPOffset((char)ch);
    } else if (ch <= UCharacter.MAX_VALUE) {
        // look at the construction of supplementary characters
        // trail forms the ends of it.
        return getSurrogateOffset(UTF16.getLeadSurrogate(ch),
                                  (char)(ch & SURROGATE_MASK_));
    } else {
        // return -1 if there is an error, in this case we return
        return -1;
    }
}
 

/**
* Retrieve the name of a Unicode code point.
* Depending on <code>choice</code>, the character name written into the
* buffer is the "modern" name or the name that was defined in Unicode
* version 1.0.
* The name contains only "invariant" characters
* like A-Z, 0-9, space, and '-'.
*
* @param ch the code point for which to get the name.
* @param choice Selector for which name to get.
* @return if code point is above 0x1fff, null is returned
*/
public String getName(int ch, int choice)
{
    if (ch < UCharacter.MIN_VALUE || ch > UCharacter.MAX_VALUE ||
        choice > UCharacterNameChoice.CHAR_NAME_CHOICE_COUNT) {
        return null;
    }

    String result = null;

    result = getAlgName(ch, choice);

    // getting normal character name
    if (result == null || result.length() == 0) {
        if (choice == UCharacterNameChoice.EXTENDED_CHAR_NAME) {
            result = getExtendedName(ch);
        } else {
            result = getGroupName(ch, choice);
        }
    }

    return result;
}
 

/**
* Internal trie getter from a code point.
* Could be faster(?) but longer with
*   if((c32)<=0xd7ff) { (result)=_TRIE_GET_RAW(trie, data, 0, c32); }
* Gets the offset to data which the codepoint points to
* @param ch codepoint
* @return offset to data
*/
protected final int getCodePointOffset(int ch)
{
    // if ((ch >> 16) == 0) slower
    if (ch < 0) {
        return -1;
    } else if (ch < UTF16.LEAD_SURROGATE_MIN_VALUE) {
        // fastpath for the part of the BMP below surrogates (D800) where getRawOffset() works
        return getRawOffset(0, (char)ch);
    } else if (ch < UTF16.SUPPLEMENTARY_MIN_VALUE) {
        // BMP codepoint
        return getBMPOffset((char)ch);
    } else if (ch <= UCharacter.MAX_VALUE) {
        // look at the construction of supplementary characters
        // trail forms the ends of it.
        return getSurrogateOffset(UTF16.getLeadSurrogate(ch),
                                  (char)(ch & SURROGATE_MASK_));
    } else {
        // return -1 if there is an error, in this case we return
        return -1;
    }
}
 

/**
* Retrieve the name of a Unicode code point.
* Depending on <code>choice</code>, the character name written into the
* buffer is the "modern" name or the name that was defined in Unicode
* version 1.0.
* The name contains only "invariant" characters
* like A-Z, 0-9, space, and '-'.
*
* @param ch the code point for which to get the name.
* @param choice Selector for which name to get.
* @return if code point is above 0x1fff, null is returned
*/
public String getName(int ch, int choice)
{
    if (ch < UCharacter.MIN_VALUE || ch > UCharacter.MAX_VALUE ||
        choice > UCharacterNameChoice.CHAR_NAME_CHOICE_COUNT) {
        return null;
    }

    String result = null;

    result = getAlgName(ch, choice);

    // getting normal character name
    if (result == null || result.length() == 0) {
        if (choice == UCharacterNameChoice.EXTENDED_CHAR_NAME) {
            result = getExtendedName(ch);
        } else {
            result = getGroupName(ch, choice);
        }
    }

    return result;
}
 

/**
 * Checks if the character belongs to a zero block in the trie
 * @param ch codepoint which data is to be retrieved
 * @return true if ch is in the zero block
 */
public boolean isInZeroBlock(int ch) 
{
    // valid, uncompacted trie and valid c?
    if (m_isCompacted_ || ch > UCharacter.MAX_VALUE 
        || ch < UCharacter.MIN_VALUE) {
        return true;
    }

    return m_index_[ch >> SHIFT_] == 0;
}
 

/**
 * Gets a 32 bit data from the table data
 * @param ch codepoint which data is to be retrieved
 * @return the 32 bit data
 */
public int getValue(int ch) 
{
    // valid, uncompacted trie and valid c?
    if (m_isCompacted_ || ch > UCharacter.MAX_VALUE || ch < 0) {
        return 0;
    }

    int block = m_index_[ch >> SHIFT_];
    return m_data_[Math.abs(block) + (ch & MASK_)];
}
 

/**
* <p>Returns true if we are not at the end of the iteration, false
* otherwise.</p>
* <p>The next set of codepoints with the same value type will be
* calculated during this call and returned in the arguement element.</p>
* @param element return result
* @return true if we are not at the end of the iteration, false otherwise.
* @exception NoSuchElementException - if no more elements exist.
* @see com.ibm.icu.util.RangeValueIterator.Element
*/
@Override
public final boolean next(Element element)
{
    if (m_nextCodepoint_ > UCharacter.MAX_VALUE) {
        return false;
    }
    if (m_nextCodepoint_ < UCharacter.SUPPLEMENTARY_MIN_VALUE &&
        calculateNextBMPElement(element)) {
        return true;
    }
    calculateNextSupplementaryElement(element);
    return true;
}
 

/**
* Sets the information for accessing the algorithmic names
* @param rangestart starting code point that lies within this name group
* @param rangeend end code point that lies within this name group
* @param type algorithm type. There's 2 kinds of algorithmic type. First
*        which uses code point as part of its name and the other uses
*        variant postfix strings
* @param variant algorithmic variant
* @return true if values are valid
*/
boolean setInfo(int rangestart, int rangeend, byte type, byte variant)
{
    if (rangestart >= UCharacter.MIN_VALUE && rangestart <= rangeend
        && rangeend <= UCharacter.MAX_VALUE &&
        (type == TYPE_0_ || type == TYPE_1_)) {
        m_rangestart_ = rangestart;
        m_rangeend_ = rangeend;
        m_type_ = type;
        m_variant_ = variant;
        return true;
    }
    return false;
}
 

/**
* <p>Returns true if we are not at the end of the iteration, false
* otherwise.</p>
* <p>The next set of codepoints with the same value type will be
* calculated during this call and returned in the arguement element.</p>
* @param element return result
* @return true if we are not at the end of the iteration, false otherwise.
* @exception NoSuchElementException - if no more elements exist.
* @see com.ibm.icu.util.RangeValueIterator.Element
*/
@Override
public final boolean next(Element element)
{
    if (m_nextCodepoint_ > UCharacter.MAX_VALUE) {
        return false;
    }
    if (m_nextCodepoint_ < UCharacter.SUPPLEMENTARY_MIN_VALUE &&
        calculateNextBMPElement(element)) {
        return true;
    }
    calculateNextSupplementaryElement(element);
    return true;
}
 

/**
* Sets the information for accessing the algorithmic names
* @param rangestart starting code point that lies within this name group
* @param rangeend end code point that lies within this name group
* @param type algorithm type. There's 2 kinds of algorithmic type. First
*        which uses code point as part of its name and the other uses
*        variant postfix strings
* @param variant algorithmic variant
* @return true if values are valid
*/
boolean setInfo(int rangestart, int rangeend, byte type, byte variant)
{
    if (rangestart >= UCharacter.MIN_VALUE && rangestart <= rangeend
        && rangeend <= UCharacter.MAX_VALUE &&
        (type == TYPE_0_ || type == TYPE_1_)) {
        m_rangestart_ = rangestart;
        m_rangeend_ = rangeend;
        m_type_ = type;
        m_variant_ = variant;
        return true;
    }
    return false;
}