com.helger.commons.text.codepoint

Class CodepointHelper

java.lang.Object

com.helger.commons.text.codepoint.CodepointHelper

@Immutable
public final class CodepointHelper
extends Object

General utilities for dealing with Unicode characters

Author:

Apache Abdera

Field Summary

Fields

Modifier and Type	Field and Description
static char	LRE
static char	LRM
static char	LRO
static char	PDF
static char	RLE
static char	RLM
static char	RLO

Method Summary

Modifier and Type	Method and Description
static Codepoint	codepointAt(CharSequence aSeq, int nIndex)
static String	getAsString(int nCodepoint)
static char	getHighSurrogate(int nCodepoint)
static int	getIndex(int[] aCodepointSet, int nValue)
static char	getLowSurrogate(int nCodepoint)
static boolean	inRange(char[] aChars, char cLow, char cHigh)
static boolean	inRange(char[] aChars, int nLow, int nHigh)
static boolean	inRange(int nCodepoint, int nLow, int nHigh)
static void	insert(CharSequence aSeq, int nIndex, Codepoint aCodepoint) Insert a codepoint into the buffer, automatically dealing with surrogate pairs
static void	insert(CharSequence aSeq, int nIndex, int nCodepoint) Insert a codepoint into the buffer, automatically dealing with surrogate pairs
static boolean	inverseSetContains(int[] aCodepointSet, 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_ihost(int codepoint)
static boolean	is_ipath(int codepoint)
static boolean	is_ipathnodelims(int codepoint)
static boolean	is_ipchar(int codepoint)
static boolean	is_ipliteral(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	isBidi(int nCodepoint)
static boolean	isFragment(int codepoint)
static boolean	isGenDelim(int codepoint)
static boolean	isHex(int nCodepoint)
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	isUnreserved(int codepoint)
static boolean	isUserInfo(int codepoint)
static int	length(AbstractCodepointIterator aIter)
static int	length(char[] aArray)
static int	length(CharSequence aSeq)
static void	setChar(CharSequence aSeq, int nIndex, Codepoint aCodepoint) Set the character at a given location, automatically dealing with surrogate pairs
static void	setChar(CharSequence aSeq, int nIndex, int nCodepoint) Set the character at a given location, automatically dealing with surrogate pairs
static String	stripBidi(String sStr) Removes leading and trailing bidi controls from the string
static String	stripBidiInternal(String sStr) Removes bidi controls from within a string
static void	verify(AbstractCodepointIterator aIter, ECodepointProfile eProfile) Verifies a sequence of codepoints using the specified filter
static void	verify(AbstractCodepointIterator aIter, IntPredicate aFilter) Verifies a sequence of codepoints using the specified filter
static void	verify(char[] aArray, ECodepointProfile eProfile) Verifies a sequence of codepoints using the specified profile
static void	verify(String sStr, ECodepointProfile eProfile) Verifies a sequence of codepoints using the specified profile
static void	verifyNot(char[] aArray, ECodepointProfile eProfile) Verifies a sequence of codepoints using the specified profile
static void	verifyNot(ICodepointIterator aIter, ECodepointProfile eProfile) Verifies a sequence of codepoints using the specified profile
static void	verifyNot(ICodepointIterator aIter, IntPredicate aFilter) Verifies a sequence of codepoints using the specified filter
static String	wrapBidi(String sStr, char cChar) 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

inRange

public static boolean inRange(@Nonnull
                              char[] aChars,
                              char cLow,
                              char cHigh)

Parameters:

aChars - char array

cLow - Low index

cHigh - high index

Returns:

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

inRange

public static boolean inRange(char[] aChars,
                              int nLow,
                              int nHigh)

Parameters:

aChars - char array

nLow - Low index

nHigh - high index

Returns:

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

inRange

public static boolean inRange(int nCodepoint,
                              int nLow,
                              int nHigh)

Parameters:

nCodepoint - codepoint

nLow - Low index

nHigh - high index

Returns:

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

getHighSurrogate

public static char getHighSurrogate(int nCodepoint)

Parameters:

nCodepoint - Codepoint

Returns:

Get the high surrogate for a particular unicode codepoint

getLowSurrogate

public static char getLowSurrogate(int nCodepoint)

Parameters:

nCodepoint - Codepoint

Returns:

Get the low surrogate for a particular unicode codepoint

codepointAt

@Nonnull
public static Codepoint codepointAt(@Nonnull
                                              CharSequence aSeq,
                                              int nIndex)

Parameters:

aSeq - source sequence

nIndex - index

Returns:

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

insert

public static void insert(CharSequence aSeq,
                          int nIndex,
                          @Nonnull
                          Codepoint aCodepoint)

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

Parameters:

aSeq - source sequence

nIndex - index

aCodepoint - codepoint to be inserted

insert

public static void insert(@Nonnull
                          CharSequence aSeq,
                          int nIndex,
                          int nCodepoint)

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

Parameters:

aSeq - source sequence

nIndex - index

nCodepoint - codepoint to be inserted

setChar

public static void setChar(@Nonnull
                           CharSequence aSeq,
                           int nIndex,
                           @Nonnull
                           Codepoint aCodepoint)

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

Parameters:

aSeq - source sequence

nIndex - index

aCodepoint - codepoint to be set

setChar

public static void setChar(@Nonnull
                           CharSequence aSeq,
                           int nIndex,
                           int nCodepoint)

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

Parameters:

aSeq - source sequence

nIndex - index

nCodepoint - codepoint to be set

length

@Nonnegative
public static int length(@Nonnull
                                       CharSequence aSeq)

Parameters:

aSeq - source sequence

Returns:

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

length

@Nonnegative
public static int length(@Nonnull
                                       char[] aArray)

Parameters:

aArray - source array

Returns:

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

length

@Nonnegative
public static int length(@Nonnull
                                       AbstractCodepointIterator aIter)

getAsString

@Nonnull
 @Nonempty
public static String getAsString(int nCodepoint)

Parameters:

nCodepoint - codepoint

Returns:

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

stripBidi

@Nullable
public static String stripBidi(@Nullable
                                          String sStr)

Removes leading and trailing bidi controls from the string

Parameters:

sStr - Source string

Returns:

the modified string

stripBidiInternal

@Nonnull
public static String stripBidiInternal(@Nonnull
                                                 String sStr)

Removes bidi controls from within a string

Parameters:

sStr - Source string

Returns:

the modified string

wrapBidi

@Nullable
public static String wrapBidi(@Nullable
                                         String sStr,
                                         char cChar)

Wrap the string with the specified bidi control

Parameters:

sStr - source string

cChar - source char

Returns:

The wrapped string

isHex

public static boolean isHex(int nCodepoint)

isBidi

public static boolean isBidi(int nCodepoint)

Parameters:

nCodepoint - codepoint

Returns:

true if the codepoint is a bidi control character

getIndex

@CheckForSigned
public static int getIndex(@Nonnull
                                            int[] aCodepointSet,
                                            int nValue)

inverseSetContains

public static boolean inverseSetContains(@Nonnull
                                         int[] aCodepointSet,
                                         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

Parameters:

aCodepointSet - Source set

value - Value to check

Returns:

true if the value is located within the set

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_ipliteral

public static boolean is_ipliteral(int codepoint)

is_ihost

public static boolean is_ihost(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(AbstractCodepointIterator aIter,
                          IntPredicate aFilter)

Verifies a sequence of codepoints using the specified filter

Parameters:

aIter - Codepointer iterator

aFilter - filter

verify

public static void verify(AbstractCodepointIterator aIter,
                          @Nonnull
                          ECodepointProfile eProfile)

Verifies a sequence of codepoints using the specified filter

Parameters:

aIter - codepoint iterator

eProfile - profile to use

verify

public static void verify(@Nullable
                          char[] aArray,
                          @Nonnull
                          ECodepointProfile eProfile)

Verifies a sequence of codepoints using the specified profile

Parameters:

aArray - char array

eProfile - profile to use

verify

public static void verify(@Nullable
                          String sStr,
                          @Nonnull
                          ECodepointProfile eProfile)

Verifies a sequence of codepoints using the specified profile

Parameters:

sStr - String

eProfile - profile to use

verifyNot

public static void verifyNot(ICodepointIterator aIter,
                             IntPredicate aFilter)

Verifies a sequence of codepoints using the specified filter

Parameters:

aIter - Codepoint iterator

aFilter - Filter to use

verifyNot

public static void verifyNot(ICodepointIterator aIter,
                             @Nonnull
                             ECodepointProfile eProfile)

Verifies a sequence of codepoints using the specified profile

Parameters:

aIter - Codepoint iterator

eProfile - profile to use

verifyNot

public static void verifyNot(char[] aArray,
                             @Nonnull
                             ECodepointProfile eProfile)

Verifies a sequence of codepoints using the specified profile

Parameters:

aArray - char array

eProfile - profile to use