org.apache.abdera.i18n.text
Class CharUtils

java.lang.Object
  org.apache.abdera.i18n.text.CharUtils

public final class CharUtils
extends Object

General utilities for dealing with Unicode characters

Nested Class Summary

static class

CharUtils.Profile

Field Summary

static char	LRE
static char	LRM
static char	LRO
static char	PDF
static char	RLE
static char	RLM
static char	RLO

Method Summary

static void	append(Appendable buf, Codepoint c) Append the specified codepoint to the buffer, automatically handling surrogate pairs
static void	append(Appendable buf, int c) Append the specified codepoint to the buffer, automatically handling surrogate pairs
static Codepoint	codepointAt(CharSequence s, int i) Return the codepoint at the given location, automatically dealing with surrogate pairs
static Codepoint	codepointAt(String s, int i) Return the codepoint at the given location, automatically dealing with surrogate pairs
static int	get_index(int[] set, int value)
static char	getHighSurrogate(int c) Get the high surrogate for a particular unicode codepoint
static char	getLowSurrogate(int c) Get the low surrogate for a particular unicode codepoint
static boolean	inRange(char[] chars, char low, char high) True if all the characters in chars are within the set [low,high]
static boolean	inRange(char[] chars, int low, int high) True if all the characters in chars are within the set [low,high]
static boolean	inRange(int codepoint, int low, int high) True if the codepoint is within the set [low,high]
static void	insert(CharSequence s, int i, Codepoint c) Insert a codepoint into the buffer, automatically dealing with surrogate pairs
static void	insert(CharSequence s, int i, int c) Insert a codepoint into the buffer, automatically dealing with surrogate pairs
static boolean	invset_contains(int[] set, int value) Treats the specified int array as an Inversion Set and returns true if the value is located within the set.
static boolean	is_ifragment(int codepoint)
static boolean	is_ipath(int codepoint)
static boolean	is_ipathnodelims(int codepoint)
static boolean	is_ipchar(int codepoint)
static boolean	is_iprivate(int codepoint)
static boolean	is_iquery(int codepoint)
static boolean	is_iregname(int codepoint)
static boolean	is_iserver(int codepoint)
static boolean	is_iunreserved(int codepoint)
static boolean	is_iuserinfo(int codepoint)
static boolean	is_regname(int codepoint)
static boolean	is_ucschar(int codepoint)
static boolean	isAlpha(Codepoint codepoint) True if the codepoint is part of the ASCII alphabet (a-z, A-Z)
static boolean	isAlpha(int codepoint) True if the codepoint is part of the ASCII alphabet (a-z, A-Z)
static boolean	isAlphaDigit(Codepoint codepoint) True if isAlpha and isDigit both return true
static boolean	isAlphaDigit(int codepoint) True if isAlpha and isDigit both return true
static boolean	isBidi(Codepoint codepoint) True if the codepoint is a bidi control character
static boolean	isBidi(int codepoint) True if the codepoint is a bidi control character
static boolean	isDigit(Codepoint codepoint) True if the codepoint is a digit
static boolean	isDigit(int codepoint) True if the codepoint is a digit
static boolean	isFragment(int codepoint)
static boolean	isGenDelim(int codepoint)
static boolean	isHighSurrogate(char c) True if the specified char is a high surrogate
static boolean	isLowSurrogate(char c) True if the specified char is a low surrogate
static boolean	isMark(int codepoint)
static boolean	isPath(int codepoint)
static boolean	isPathNoDelims(int codepoint)
static boolean	isPchar(int codepoint)
static boolean	isPctEnc(int codepoint)
static boolean	isQuery(int codepoint)
static boolean	isReserved(int codepoint)
static boolean	isScheme(int codepoint)
static boolean	isSubDelim(int codepoint)
static boolean	isSupplementary(int c) True if the specified character is supplemental
static boolean	isSurrogatePair(char high, char low) True if the two chars represent a surrogate pair
static boolean	isUnreserved(int codepoint)
static boolean	isUserInfo(int codepoint)
static boolean	isValid(Codepoint c) True if the character is a valid unicode codepoint
static boolean	isValid(int c) True if the character is a valid unicode codepoint
static int	length(char[] c) Return the total number of codepoints in the buffer.
static int	length(CharSequence c) Return the total number of codepoints in the buffer.
static int	length(Codepoint c) Return the number of characters used to represent the codepoint (will return 1 or 2)
static int	length(int c) Return the number of characters used to represent the codepoint (will return 1 or 2)
static void	setChar(CharSequence s, int i, Codepoint c) Set the character at a given location, automatically dealing with surrogate pairs
static void	setChar(CharSequence s, int i, int c) Set the character at a given location, automatically dealing with surrogate pairs
static String	stripBidi(String s) Removes leading and trailing bidi controls from the string
static String	stripBidiInternal(String s) Removes bidi controls from within a string
static String	toString(int c) Return the String representation of the codepoint, automatically dealing with surrogate pairs
static Codepoint	toSupplementary(char high, char low) Converts the high and low surrogate into a supplementary codepoint
static void	verify(char[] s, CharUtils.Profile profile) Verifies a sequence of codepoints using the specified profile
static void	verify(CodepointIterator ci, CharUtils.Profile profile) Verifies a sequence of codepoints using the specified filter
static void	verify(CodepointIterator ci, Filter filter) Verifies a sequence of codepoints using the specified filter
static void	verify(String s, CharUtils.Profile profile) Verifies a sequence of codepoints using the specified profile
static void	verifyNot(char[] array, CharUtils.Profile profile) Verifies a sequence of codepoints using the specified profile
static void	verifyNot(CodepointIterator ci, CharUtils.Profile profile) Verifies a sequence of codepoints using the specified profile
static void	verifyNot(CodepointIterator ci, Filter filter) Verifies a sequence of codepoints using the specified filter
static String	wrapBidi(String s, char c) Wrap the string with the specified bidi control

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

LRE

public static final char LRE

See Also:

Constant Field Values

RLE

public static final char RLE

See Also:

Constant Field Values

LRO

public static final char LRO

See Also:

Constant Field Values

RLO

public static final char RLO

See Also:

Constant Field Values

LRM

public static final char LRM

See Also:

Constant Field Values

RLM

public static final char RLM

See Also:

Constant Field Values

PDF

public static final char PDF

See Also:

Constant Field Values

Method Detail

isValid

public static boolean isValid(int c)

True if the character is a valid unicode codepoint

isValid

public static boolean isValid(Codepoint c)

True if the character is a valid unicode codepoint

inRange

public static boolean inRange(char[] chars,
                              char low,
                              char high)

True if all the characters in chars are within the set [low,high]

inRange

public static boolean inRange(char[] chars,
                              int low,
                              int high)

True if all the characters in chars are within the set [low,high]

inRange

public static boolean inRange(int codepoint,
                              int low,
                              int high)

True if the codepoint is within the set [low,high]

append

public static void append(Appendable buf,
                          Codepoint c)

Append the specified codepoint to the buffer, automatically handling surrogate pairs

append

public static void append(Appendable buf,
                          int c)

Append the specified codepoint to the buffer, automatically handling surrogate pairs

getHighSurrogate

public static char getHighSurrogate(int c)

Get the high surrogate for a particular unicode codepoint

getLowSurrogate

public static char getLowSurrogate(int c)

Get the low surrogate for a particular unicode codepoint

isHighSurrogate

public static boolean isHighSurrogate(char c)

True if the specified char is a high surrogate

isLowSurrogate

public static boolean isLowSurrogate(char c)

True if the specified char is a low surrogate

isSupplementary

public static boolean isSupplementary(int c)

True if the specified character is supplemental

isSurrogatePair

public static boolean isSurrogatePair(char high,
                                      char low)

True if the two chars represent a surrogate pair

toSupplementary

public static Codepoint toSupplementary(char high,
                                        char low)

Converts the high and low surrogate into a supplementary codepoint

codepointAt

public static Codepoint codepointAt(String s,
                                    int i)

Return the codepoint at the given location, automatically dealing with surrogate pairs

codepointAt

public static Codepoint codepointAt(CharSequence s,
                                    int i)

Return the codepoint at the given location, automatically dealing with surrogate pairs

insert

public static void insert(CharSequence s,
                          int i,
                          Codepoint c)

Insert a codepoint into the buffer, automatically dealing with surrogate pairs

insert

public static void insert(CharSequence s,
                          int i,
                          int c)

Insert a codepoint into the buffer, automatically dealing with surrogate pairs

setChar

public static void setChar(CharSequence s,
                           int i,
                           Codepoint c)

Set the character at a given location, automatically dealing with surrogate pairs

setChar

public static void setChar(CharSequence s,
                           int i,
                           int c)

Set the character at a given location, automatically dealing with surrogate pairs

length

public static int length(Codepoint c)

Return the number of characters used to represent the codepoint (will return 1 or 2)

length

public static int length(int c)

Return the number of characters used to represent the codepoint (will return 1 or 2)

length

public static int length(CharSequence c)

Return the total number of codepoints in the buffer. Each surrogate pair counts as a single codepoint

length

public static int length(char[] c)

Return the total number of codepoints in the buffer. Each surrogate pair counts as a single codepoint

toString

public static String toString(int c)

Return the String representation of the codepoint, automatically dealing with surrogate pairs

stripBidi

public static String stripBidi(String s)

Removes leading and trailing bidi controls from the string

stripBidiInternal

public static String stripBidiInternal(String s)

Removes bidi controls from within a string

wrapBidi

public static String wrapBidi(String s,
                              char c)

Wrap the string with the specified bidi control

isDigit

public static boolean isDigit(Codepoint codepoint)

True if the codepoint is a digit

isDigit

public static boolean isDigit(int codepoint)

True if the codepoint is a digit

isAlpha

public static boolean isAlpha(Codepoint codepoint)

True if the codepoint is part of the ASCII alphabet (a-z, A-Z)

isAlpha

public static boolean isAlpha(int codepoint)

True if the codepoint is part of the ASCII alphabet (a-z, A-Z)

isAlphaDigit

public static boolean isAlphaDigit(Codepoint codepoint)

True if isAlpha and isDigit both return true

isAlphaDigit

public static boolean isAlphaDigit(int codepoint)

True if isAlpha and isDigit both return true

isBidi

public static boolean isBidi(Codepoint codepoint)

True if the codepoint is a bidi control character

isBidi

public static boolean isBidi(int codepoint)

True if the codepoint is a bidi control character

get_index

public static int get_index(int[] set,
                            int value)

invset_contains

public static boolean invset_contains(int[] set,
                                      int value)

Treats the specified int array as an Inversion Set and returns true if the value is located within the set. This will only work correctly if the values in the int array are monotonically increasing

isPctEnc

public static boolean isPctEnc(int codepoint)

isMark

public static boolean isMark(int codepoint)

isUnreserved

public static boolean isUnreserved(int codepoint)

isReserved

public static boolean isReserved(int codepoint)

isGenDelim

public static boolean isGenDelim(int codepoint)

isSubDelim

public static boolean isSubDelim(int codepoint)

isPchar

public static boolean isPchar(int codepoint)

isPath

public static boolean isPath(int codepoint)

isPathNoDelims

public static boolean isPathNoDelims(int codepoint)

isScheme

public static boolean isScheme(int codepoint)

isUserInfo

public static boolean isUserInfo(int codepoint)

isQuery

public static boolean isQuery(int codepoint)

isFragment

public static boolean isFragment(int codepoint)

is_ucschar

public static boolean is_ucschar(int codepoint)

is_iprivate

public static boolean is_iprivate(int codepoint)

is_iunreserved

public static boolean is_iunreserved(int codepoint)

is_ipchar

public static boolean is_ipchar(int codepoint)

is_ipath

public static boolean is_ipath(int codepoint)

is_ipathnodelims

public static boolean is_ipathnodelims(int codepoint)

is_iquery

public static boolean is_iquery(int codepoint)

is_ifragment

public static boolean is_ifragment(int codepoint)

is_iregname

public static boolean is_iregname(int codepoint)

is_regname

public static boolean is_regname(int codepoint)

is_iuserinfo

public static boolean is_iuserinfo(int codepoint)

is_iserver

public static boolean is_iserver(int codepoint)

verify

public static void verify(CodepointIterator ci,
                          Filter filter)
                   throws InvalidCharacterException

Verifies a sequence of codepoints using the specified filter

Throws:

InvalidCharacterException

verify

public static void verify(CodepointIterator ci,
                          CharUtils.Profile profile)
                   throws InvalidCharacterException

Verifies a sequence of codepoints using the specified filter

Throws:

InvalidCharacterException

verify

public static void verify(char[] s,
                          CharUtils.Profile profile)
                   throws InvalidCharacterException

Verifies a sequence of codepoints using the specified profile

Throws:

InvalidCharacterException

verify

public static void verify(String s,
                          CharUtils.Profile profile)
                   throws InvalidCharacterException

Verifies a sequence of codepoints using the specified profile

Throws:

InvalidCharacterException

verifyNot

public static void verifyNot(CodepointIterator ci,
                             Filter filter)
                      throws InvalidCharacterException

Verifies a sequence of codepoints using the specified filter

Throws:

InvalidCharacterException

verifyNot

public static void verifyNot(CodepointIterator ci,
                             CharUtils.Profile profile)
                      throws InvalidCharacterException

Verifies a sequence of codepoints using the specified profile

Throws:

InvalidCharacterException

verifyNot

public static void verifyNot(char[] array,
                             CharUtils.Profile profile)
                      throws InvalidCharacterException

Verifies a sequence of codepoints using the specified profile

Throws:

InvalidCharacterException