Value Members

1.  final def !=(arg0: Any): Boolean

   Definition Classes

   AnyRef → Any

2.  final def ##: Int

   Definition Classes

   AnyRef → Any

3.  final def ==(arg0: Any): Boolean

   Definition Classes

   AnyRef → Any

4.  final def asInstanceOf[T0]: T0

   Definition Classes

   Any

5.  def clone(): UTF8String

   Definition Classes

   UTF8String → AnyRef

   Annotations

   @Override()

6.  def compare(other: UTF8String): Int
7.  def compareTo(other: UTF8String): Int

   Definition Classes

   UTF8String → Comparable

   Annotations

   @Override()

8.  def contains(substring: UTF8String): Boolean

   Returns whether this contains substring or not.

9.  def copy(): UTF8String
10.  def endsWith(suffix: UTF8String): Boolean
11.  final def eq(arg0: AnyRef): Boolean

    Definition Classes

    AnyRef

12.  def equals(other: AnyRef): Boolean

    Definition Classes

    UTF8String → AnyRef → Any

    Annotations

    @Override()

13.  def finalize(): Unit

    Attributes

    protected[lang]

    Definition Classes

    AnyRef

    Annotations

    @throws(classOf[java.lang.Throwable])

14.  def findInSet(match: UTF8String): Int
15.  def getBaseObject(): AnyRef
16.  def getBaseOffset(): Long
17.  def getByteBuffer(): ByteBuffer

    Returns a ByteBuffer wrapping the base object if it is a byte array or a copy of the data if the base object is not a byte array.

    Returns a ByteBuffer wrapping the base object if it is a byte array or a copy of the data if the base object is not a byte array.

    Unlike getBytes this will not create a copy the array if this is a slice.

    Annotations

    @Nonnull()

18.  def getBytes(): Array[Byte]

    Returns the underline bytes, will be a copy of it if it's part of another array.

19.  final def getClass(): Class[_ <: AnyRef]

    Definition Classes

    AnyRef → Any

    Annotations

    @native()

20.  def getPrefix(): Long

    Returns a 64-bit integer that can be used as the prefix used in sorting.

21.  def hashCode(): Int

    Definition Classes

    UTF8String → AnyRef → Any

    Annotations

    @Override()

22.  def indexOf(v: UTF8String, start: Int): Int

    Returns the position of the first occurrence of substr in current string from the specified position (0-based index).

    Returns the position of the first occurrence of substr in current string from the specified position (0-based index).

    v

    the string to be searched

    start

    the start position of the current string for searching

    returns

    the position of the first occurrence of substr, if not found, -1 returned.

23.  final def isInstanceOf[T0]: Boolean

    Definition Classes

    Any

24.  def levenshteinDistance(other: UTF8String): Int

    Levenshtein distance is a metric for measuring the distance of two strings.

    Levenshtein distance is a metric for measuring the distance of two strings. The distance is defined by the minimum number of single-character edits (i.e. insertions, deletions or substitutions) that are required to change one of the strings into the other.

25.  def lpad(len: Int, pad: UTF8String): UTF8String

    Returns str, left-padded with pad to a length of len.

    Returns str, left-padded with pad to a length of len. For example: ('hi', 5, '??') => '???hi' ('hi', 1, '??') => 'h'

26.  def matchAt(s: UTF8String, pos: Int): Boolean
27.  final def ne(arg0: AnyRef): Boolean

    Definition Classes

    AnyRef

28.  final def notify(): Unit

    Definition Classes

    AnyRef

    Annotations

    @native()

29.  final def notifyAll(): Unit

    Definition Classes

    AnyRef

    Annotations

    @native()

30.  def numBytes(): Int

    Returns the number of bytes

31.  def numChars(): Int

    Returns the number of code points in it.

32.  def read(kryo: Kryo, in: Input): Unit

    Definition Classes

    UTF8String → KryoSerializable

    Annotations

    @Override()

33.  def readExternal(in: ObjectInput): Unit

    Definition Classes

    UTF8String → Externalizable

    Annotations

    @Override()

34.  def repeat(times: Int): UTF8String
35.  def replace(search: UTF8String, replace: UTF8String): UTF8String
36.  def reverse(): UTF8String
37.  def rpad(len: Int, pad: UTF8String): UTF8String

    Returns str, right-padded with pad to a length of len For example: ('hi', 5, '??') => 'hi???' ('hi', 1, '??') => 'h'

38.  def soundex(): UTF8String

    Encodes a string into a Soundex value.

    Encodes a string into a Soundex value. Soundex is an encoding used to relate similar names, but can also be used as a general purpose scheme to find word with similar phonemes. https://en.wikipedia.org/wiki/Soundex

39.  def split(pattern: UTF8String, limit: Int): Array[UTF8String]
40.  def splitSQL(delimiter: UTF8String, limit: Int): Array[UTF8String]
41.  def startsWith(prefix: UTF8String): Boolean
42.  def subStringIndex(delim: UTF8String, count: Int): UTF8String

    Returns the substring from string str before count occurrences of the delimiter delim.

    Returns the substring from string str before count occurrences of the delimiter delim. If count is positive, everything the left of the final delimiter (counting from left) is returned. If count is negative, every to the right of the final delimiter (counting from the right) is returned. subStringIndex performs a case-sensitive match when searching for delim.

43.  def substring(start: Int, until: Int): UTF8String

    Returns a substring of this.

    Returns a substring of this.

    start

    the position of first code point

    until

    the position after last code point, exclusive.

44.  def substringSQL(pos: Int, length: Int): UTF8String
45.  final def synchronized[T0](arg0: => T0): T0

    Definition Classes

    AnyRef

46.  def toByte(intWrapper: IntWrapper): Boolean
47.  def toByteExact(): Byte
48.  def toInt(intWrapper: IntWrapper): Boolean

    Parses this UTF8String(trimmed if needed) to int.

    Parses this UTF8String(trimmed if needed) to int.

    Note that, in this method we accumulate the result in negative format, and convert it to positive format at the end, if this string is not started with '-'. This is because min value is bigger than max value in digits, e.g. Integer.MAX_VALUE is '2147483647' and Integer.MIN_VALUE is '-2147483648'.

    This code is mostly copied from LazyInt.parseInt in Hive.

    Note that, this method is almost same as toLong, but we leave it duplicated for performance reasons, like Hive does.

    intWrapper

    If a valid int was parsed from this UTF8String, then its value would be set in intWrapper

    returns

    true if the parsing was successful else false

49.  def toIntExact(): Int

    Parses UTF8String(trimmed if needed) to int.

    Parses UTF8String(trimmed if needed) to int. This method is used when ANSI is enabled.

    returns

    If string contains valid numeric value then it returns the int value otherwise a NumberFormatException is thrown.

50.  def toLong(toLongResult: LongWrapper): Boolean

    Parses this UTF8String(trimmed if needed) to long.

    Parses this UTF8String(trimmed if needed) to long.

    Note that, in this method we accumulate the result in negative format, and convert it to positive format at the end, if this string is not started with '-'. This is because min value is bigger than max value in digits, e.g. Long.MAX_VALUE is '9223372036854775807' and Long.MIN_VALUE is '-9223372036854775808'.

    This code is mostly copied from LazyLong.parseLong in Hive.

    toLongResult

    If a valid long was parsed from this UTF8String, then its value would be set in toLongResult

    returns

    true if the parsing was successful else false

51.  def toLongExact(): Long

    Parses UTF8String(trimmed if needed) to long.

    Parses UTF8String(trimmed if needed) to long. This method is used when ANSI is enabled.

    returns

    If string contains valid numeric value then it returns the long value otherwise a NumberFormatException is thrown.

52.  def toLowerCase(): UTF8String

    Returns the lower case of this string

53.  def toShort(intWrapper: IntWrapper): Boolean
54.  def toShortExact(): Short
55.  def toString(): String

    Definition Classes

    UTF8String → AnyRef → Any

    Annotations

    @Override()

56.  def toTitleCase(): UTF8String

    Returns the title case of this string, that could be used as title.

57.  def toUpperCase(): UTF8String

    Returns the upper case of this string

58.  def translate(dict: Map[String, String]): UTF8String
59.  def trim(trimString: UTF8String): UTF8String

    Trims instances of the given trim string from both ends of this string.

    Trims instances of the given trim string from both ends of this string.

    trimString

    the trim character string

    returns

    this string with no occurrences of the trim string at the start or end, or null if trimString is null

60.  def trim(): UTF8String

    Trims space characters (ASCII 32) from both ends of this string.

    Trims space characters (ASCII 32) from both ends of this string.

    returns

    this string with no spaces at the start or end

61.  def trimAll(): UTF8String

    Trims whitespace ASCII characters from both ends of this string.

    Trims whitespace ASCII characters from both ends of this string.

    Note that, this method is different from UTF8String#trim() which removes only spaces(= ASCII 32) from both ends.

    returns

    A UTF8String whose value is this UTF8String, with any leading and trailing white space removed, or this UTF8String if it has no leading or trailing whitespace.

62.  def trimLeft(trimString: UTF8String): UTF8String

    Trims instances of the given trim string from the start of this string.

    Trims instances of the given trim string from the start of this string.

    trimString

    the trim character string

    returns

    this string with no occurrences of the trim string at the start, or null if trimString is null

63.  def trimLeft(): UTF8String

    Trims space characters (ASCII 32) from the start of this string.

    Trims space characters (ASCII 32) from the start of this string.

    returns

    this string with no spaces at the start

64.  def trimRight(trimString: UTF8String): UTF8String

    Trims instances of the given trim string from the end of this string.

    Trims instances of the given trim string from the end of this string.

    trimString

    the trim character string

    returns

    this string with no occurrences of the trim string at the end, or null if trimString is null

65.  def trimRight(): UTF8String

    Trims space characters (ASCII 32) from the end of this string.

    Trims space characters (ASCII 32) from the end of this string.

    returns

    this string with no spaces at the end

66.  def trimTrailingSpaces(numSpaces: Int): UTF8String

    Trims at most numSpaces space characters (ASCII 32) from the end of this string.

67.  final def wait(): Unit

    Definition Classes

    AnyRef

    Annotations

    @throws(classOf[java.lang.InterruptedException])

68.  final def wait(arg0: Long, arg1: Int): Unit

    Definition Classes

    AnyRef

    Annotations

    @throws(classOf[java.lang.InterruptedException])

69.  final def wait(arg0: Long): Unit

    Definition Classes

    AnyRef

    Annotations

    @throws(classOf[java.lang.InterruptedException]) @native()

70.  def write(kryo: Kryo, out: Output): Unit

    Definition Classes

    UTF8String → KryoSerializable

    Annotations

    @Override()

71.  def writeExternal(out: ObjectOutput): Unit

    Definition Classes

    UTF8String → Externalizable

    Annotations

    @Override()

72.  def writeTo(out: OutputStream): Unit
73.  def writeTo(buffer: ByteBuffer): Unit
74.  def writeToMemory(target: AnyRef, targetOffset: Long): Unit

    Writes the content of this string into a memory address, identified by an object and an offset.

    Writes the content of this string into a memory address, identified by an object and an offset. The target memory address must already been allocated, and have enough space to hold all the bytes in this string.