JCodings 1.0.58 · org.jcodings.Encoding

Modifier and Type	Field and Description
public static final int	CHAR_INVALID
private Charset	charset
private static int	count
private int	hashCode
private int	index
private boolean	isAsciiCompatible
private boolean	isDummy
private final boolean	isFixedWidth
private final boolean	isSingleByte
protected boolean	isUnicode
protected boolean	isUTF8
protected final int	maxLength
protected final int	minLength
private byte[]	name
public static final byte	NEW_LINE
private String	stringName

Access	Constructor and Description
protected	Encoding(String name, int minLength, int maxLength)

Method Summary

Modifier and Type	Method and Description
public abstract void	applyAllCaseFold(int case fold flag flag, ApplyAllCaseFoldFunction case folding functor (look at: `ApplyCaseFold`) fun, Object case folding functor argument (look at: `ApplyCaseFoldArg`) Oniguruma equivalent: `apply_all_case_fold` arg) Expand case folds given a character class (used for case insensitive matching)
public static byte	asciiToLower(int c)
public static byte	asciiToUpper(int c)
public abstract CaseFoldCodeItem[]	caseFoldCodesByString(int flag, byte[] bytes, int p, int end) Expand AST string nodes into their folded alternatives (look at: `Analyser.expandCaseFoldString`) Oniguruma equivalent: `get_case_fold_codes_by_str`
public abstract int	caseMap(IntHolder flagP, byte[] bytes, IntHolder pp, int end, byte[] to, int toP, int toEnd) Oniguruma equivalent: `case_map`
public abstract int	Returns: character length for the given code point Oniguruma equivalent: `code_to_mbc` codeToMbc(int code, byte[] bytes, int p) Extracts code point into it's multibyte representation
public abstract int	codeToMbcLength(int code) Returns character length given a code point Oniguruma equivalent: `code_to_mbclen`
public abstract int[]	ctypeCodeRange(int ctype, IntHolder sbOut) Returns code range for a given character type Oniguruma equivalent: `get_ctype_code_range`
public static int	digitVal(int code)
public final boolean	equals(Object the reference object with which to compare. other) Overrides java.lang.Object.equals. Indicates whether some other object is "equal to" this one.
public Charset	getCharset() If this encoding is capable of being represented by a Java Charset then provide it.
public String	Returns: the name of the equivalent Java Charset for this encoding getCharsetName() The name of the equivalent Java Charset for this encoding.
public final int	getIndex()
public final byte[]	getName()
public final int	hashCode() Overrides java.lang.Object.hashCode. Returns a hash code value for this object.
public final boolean	isAlnum(int code)
public final boolean	isAlpha(int code)
public static boolean	isAscii(int code)
public static boolean	isAscii(byte b)
public final boolean	isAsciiCompatible()
public final boolean	isBlank(int code)
public final boolean	isCntrl(int code)
public abstract boolean	isCodeCType(int a code point of a character code, int a character type to check against Oniguruma equivalent: `is_code_ctype` ctype) Perform a check whether given code is of given character type (e.g. used by isWord(someByte) and similar methods)
public final boolean	isDigit(int code)
public final boolean	isDummy()
public final boolean	isFixedWidth()
public final boolean	isGraph(int code)
public final boolean	isLower(int code)
public static boolean	isMbcAscii(byte b)
public boolean	isMbcCrnl(byte[] bytes, int p, int end)
public final boolean	isMbcHead(byte[] bytes, int p, int end)
public final boolean	isMbcWord(byte[] bytes, int p, int end)
public abstract boolean	isNewLine(byte[] bytes, int p, int end) Returns true if `bytes[p]` is a head of a new line character Oniguruma equivalent: `is_mbc_newline`
public final boolean	isNewLine(int code)
public final boolean	isPrint(int code)
public final boolean	isPunct(int code)
public abstract boolean	isReverseMatchAllowed(byte[] bytes, int p, int end) Returns true if it's safe to use reversal Boyer-Moore search fail fast algorithm Oniguruma equivalent: `is_allowed_reverse_match`
public final boolean	isSbWord(int code)
public final boolean	isSingleByte()
public final boolean	isSpace(int code)
public final boolean	isUnicode()
public final boolean	isUpper(int code)
public final boolean	isUTF8()
public final boolean	isWord(int code)
public static boolean	isWordGraphPrint(int ctype)
public final boolean	isXDigit(int code)
public abstract int	leftAdjustCharHead(byte[] byte stream bytes, int position p, int stop s, int end end) Seeks the previous character head in a stream Oniguruma equivalent: `left_adjust_char_head`
public abstract int	length(byte Character head Oniguruma equivalent: `mbc_enc_len` To be deprecated very soon (use length(byte[]bytes, int p, int end) version) c) Returns character length given character head returns `1` for singlebyte encodings or performs direct length table lookup for multibyte ones.
public abstract int	Returns: 0 Never > 0 Valid character, length returned -1 Illegal/malformed character < -1 (-1 - n) Number of missing bytes for character in p...end range Oniguruma equivalent: `mbc_enc_len` modified for 1.9 purposes, length(byte[] bytes, int p, int end) Returns character length given stream, character position and stream end returns `1` for singlebyte encodings or performs sanity validations for multibyte ones and returns the character length, missing characters in the stream otherwise
public static Encoding	load(String name)
public static Encoding	load(String name, String pkg)
public final int	maxLength() Returns maximum character byte length that can appear in an encoding Oniguruma equivalent: `max_enc_len`
public final int	maxLengthDistance() Deprecated
public abstract int	mbcCaseFold(int case fold flag flag, byte[] bytes, IntHolder an `IntHolder` that points at character head pp, int end, byte[] a buffer where to extract case folded character Oniguruma equivalent: `mbc_case_fold` to) Performs case folding for a character at `bytes[pp.value]`
public final int	mbcodeStartPosition() Deprecated
public abstract int	mbcToCode(byte[] bytes, int p, int end) Returns code point for a character Oniguruma equivalent: `mbc_to_code`
public final int	minLength() Returns minimum character byte length that can appear in an encoding Oniguruma equivalent: `min_enc_len`
public static int	odigitVal(int code)
public final int	prevCharHead(byte[] bytes, int p, int s, int end)
public abstract int	propertyNameToCType(byte[] bytes, int p, int end) Returns character type given character type name (used when e.g. \p{Alpha}) Oniguruma equivalent: `property_name_to_ctype`
pack-priv Encoding	replicate(byte[] name)
public final int	rightAdjustCharHead(byte[] bytes, int p, int s, int end)
public final int	rightAdjustCharHeadWithPrev(byte[] bytes, int p, int s, int end, IntHolder prev)
protected final void	setDummy()
protected final void	setName(String name)
protected final void	setName(byte[] name)
public final int	step(byte[] bytes, int p, int end, int n)
public final int	stepBack(byte[] bytes, int p, int s, int end, int n)
public final int	strByteLengthNull(byte[] bytes, int p, int end)
public abstract int	strCodeAt(byte[] bytes, int p, int end, int index)
public abstract int	strLength(byte[] bytes, int p, int end)
public final int	strLengthNull(byte[] bytes, int p, int end)
public final int	strNCmp(byte[] bytes, int p, int end, byte[] ascii, int asciiP, int n)
public byte[]	Returns: lower case table toLowerCaseTable() Returns lower case table if it's safe to use it directly, otherwise `null` Used for fast case insensitive matching for some singlebyte encodings
public final String	toString() Overrides java.lang.Object.toString. Returns a string representation of the object.
public final int	xdigitVal(int code)

Inherited from java.lang.Object:: clone finalize getClass notify notifyAll wait wait wait

CHAR_INVALID	back to summary
public static final int CHAR_INVALID

charset	back to summary
private Charset charset

count	back to summary
private static int count

hashCode	back to summary
private int hashCode

index	back to summary
private int index

isAsciiCompatible	back to summary
private boolean isAsciiCompatible

isDummy	back to summary
private boolean isDummy

isFixedWidth	back to summary
private final boolean isFixedWidth

isSingleByte	back to summary
private final boolean isSingleByte

isUnicode	back to summary
protected boolean isUnicode

isUTF8	back to summary
protected boolean isUTF8

maxLength	back to summary
protected final int maxLength

minLength	back to summary
protected final int minLength

name	back to summary
private byte[] name

NEW_LINE	back to summary
public static final byte NEW_LINE

stringName	back to summary
private String stringName

Encoding	back to summary
protected Encoding(String name, int minLength, int maxLength)

Method Detail

applyAllCaseFold back to summary

applyAllCaseFold	back to summary
public abstract void applyAllCaseFold(int flag, ApplyAllCaseFoldFunction fun, Object arg) Expand case folds given a character class (used for case insensitive matching) Parameters flag:int case fold flag fun:ApplyAllCaseFoldFunction case folding functor (look at: `ApplyCaseFold`) arg:Object case folding functor argument (look at: `ApplyCaseFoldArg`) Oniguruma equivalent: `apply_all_case_fold`

public abstract void applyAllCaseFold(int flag, ApplyAllCaseFoldFunction fun, Object arg)

Expand case folds given a character class (used for case insensitive matching)

Parameters

flag:int: case fold flag
fun:ApplyAllCaseFoldFunction: case folding functor (look at: ApplyCaseFold)
arg:Object: case folding functor argument (look at: ApplyCaseFoldArg) Oniguruma equivalent: apply_all_case_fold

asciiToLower	back to summary
public static byte asciiToLower(int c)

asciiToUpper	back to summary
public static byte asciiToUpper(int c)

caseFoldCodesByString	back to summary
public abstract CaseFoldCodeItem[] caseFoldCodesByString(int flag, byte[] bytes, int p, int end) Expand AST string nodes into their folded alternatives (look at: `Analyser.expandCaseFoldString`) Oniguruma equivalent: `get_case_fold_codes_by_str`

caseMap	back to summary
public abstract int caseMap(IntHolder flagP, byte[] bytes, IntHolder pp, int end, byte[] to, int toP, int toEnd) Oniguruma equivalent: `case_map`

codeToMbc back to summary

codeToMbc	back to summary
public abstract int codeToMbc(int code, byte[] bytes, int p) Extracts code point into it's multibyte representation Returns:int character length for the given code point Oniguruma equivalent: `code_to_mbc`

public abstract int codeToMbc(int code, byte[] bytes, int p)

Extracts code point into it's multibyte representation

Returns:int: character length for the given code point Oniguruma equivalent: code_to_mbc

codeToMbcLength	back to summary
public abstract int codeToMbcLength(int code) Returns character length given a code point Oniguruma equivalent: `code_to_mbclen`

ctypeCodeRange	back to summary
public abstract int[] ctypeCodeRange(int ctype, IntHolder sbOut) Returns code range for a given character type Oniguruma equivalent: `get_ctype_code_range`

digitVal	back to summary
public static int digitVal(int code)

equals back to summary

equals	back to summary
public final boolean equals(Object other) Overrides java.lang.Object.equals. Doc from java.lang.Object.equals. Indicates whether some other object is "equal to" this one. The `equals` method implements an equivalence relation on non-null object references: It is reflexive: for any non-null reference value `x`, `x.equals(x)` should return `true`. It is symmetric: for any non-null reference values `x` and `y`, `x.equals(y)` should return `true` if and only if `y.equals(x)` returns `true`. It is transitive: for any non-null reference values `x`, `y`, and `z`, if `x.equals(y)` returns `true` and `y.equals(z)` returns `true`, then `x.equals(z)` should return `true`. It is consistent: for any non-null reference values `x` and `y`, multiple invocations of `x.equals(y)` consistently return `true` or consistently return `false`, provided no information used in `equals` comparisons on the objects is modified. For any non-null reference value `x`, `x.equals(null)` should return `false`. An equivalence relation partitions the elements it operates on into equivalence classes; all the members of an equivalence class are equal to each other. Members of an equivalence class are substitutable for each other, at least for some purposes. Parameters other:Object the reference object with which to compare. Returns:boolean `true` if this object is the same as the obj argument; `false` otherwise. Annotations @Override

public final boolean equals(Object other)

Overrides java.lang.Object.equals.

Doc from java.lang.Object.equals.

Indicates whether some other object is "equal to" this one.

The equals method implements an equivalence relation on non-null object references:

It is reflexive: for any non-null reference value x, x.equals(x) should return true.
It is symmetric: for any non-null reference values x and y, x.equals(y) should return true if and only if y.equals(x) returns true.
It is transitive: for any non-null reference values x, y, and z, if x.equals(y) returns true and y.equals(z) returns true, then x.equals(z) should return true.
It is consistent: for any non-null reference values x and y, multiple invocations of x.equals(y) consistently return true or consistently return false, provided no information used in equals comparisons on the objects is modified.
For any non-null reference value x, x.equals(null) should return false.

An equivalence relation partitions the elements it operates on into equivalence classes; all the members of an equivalence class are equal to each other. Members of an equivalence class are substitutable for each other, at least for some purposes.

Parameters

other:Object: the reference object with which to compare.

Returns:boolean

true if this object is the same as the obj argument; false otherwise.

Annotations

@Override

getCharset	back to summary
public Charset getCharset() If this encoding is capable of being represented by a Java Charset then provide it. Otherwise this will raise a CharsetNotFound error via the JDK APIs. To reduce cases like jruby/jruby#4716, we always attempt to find a charset here, and default to using the encoding name which is never null. Either the encoding will exist in the JDK or it will fail hard, rather than propagating a null Charset. Encodings with names different than those found in the JDK can override this getCharsetName to provide that name or getCharset to return the right Charset.

getCharset

back to summary

public Charset getCharset()

If this encoding is capable of being represented by a Java Charset then provide it. Otherwise this will raise a CharsetNotFound error via the JDK APIs. To reduce cases like jruby/jruby#4716, we always attempt to find a charset here, and default to using the encoding name which is never null. Either the encoding will exist in the JDK or it will fail hard, rather than propagating a null Charset. Encodings with names different than those found in the JDK can override this getCharsetName to provide that name or getCharset to return the right Charset.

getCharsetName	back to summary
public String getCharsetName() The name of the equivalent Java Charset for this encoding. Defaults to the name of the encoding. Subclasses can override this to provide a different name. Returns:String the name of the equivalent Java Charset for this encoding

getCharsetName

back to summary

public String getCharsetName()

The name of the equivalent Java Charset for this encoding. Defaults to the name of the encoding. Subclasses can override this to provide a different name.

Returns:String: the name of the equivalent Java Charset for this encoding

getIndex	back to summary
public final int getIndex()

getName	back to summary
public final byte[] getName()

hashCode back to summary

hashCode	back to summary
public final int hashCode() Overrides java.lang.Object.hashCode. Doc from java.lang.Object.hashCode. Returns a hash code value for this object. This method is supported for the benefit of hash tables such as those provided by `java.util.HashMap`. The general contract of `hashCode` is: Whenever it is invoked on the same object more than once during an execution of a Java application, the `hashCode` method must consistently return the same integer, provided no information used in `equals` comparisons on the object is modified. This integer need not remain consistent from one execution of an application to another execution of the same application. If two objects are equal according to the `equals` method, then calling the `hashCode` method on each of the two objects must produce the same integer result. It is not required that if two objects are unequal according to the `equals` method, then calling the `hashCode` method on each of the two objects must produce distinct integer results. However, the programmer should be aware that producing distinct integer results for unequal objects may improve the performance of hash tables. Returns:int a hash code value for this object Annotations @Override

public final int hashCode()

Overrides java.lang.Object.hashCode.

Doc from java.lang.Object.hashCode.

Returns a hash code value for this object. This method is supported for the benefit of hash tables such as those provided by java.util.HashMap.

The general contract of hashCode is:

Whenever it is invoked on the same object more than once during an execution of a Java application, the hashCode method must consistently return the same integer, provided no information used in equals comparisons on the object is modified. This integer need not remain consistent from one execution of an application to another execution of the same application.
If two objects are equal according to the equals method, then calling the hashCode method on each of the two objects must produce the same integer result.
It is not required that if two objects are unequal according to the equals method, then calling the hashCode method on each of the two objects must produce distinct integer results. However, the programmer should be aware that producing distinct integer results for unequal objects may improve the performance of hash tables.

Returns:int

a hash code value for this object

Annotations

@Override

isAlnum	back to summary
public final boolean isAlnum(int code)

isAlpha	back to summary
public final boolean isAlpha(int code)

isAscii	back to summary
public static boolean isAscii(int code)

isAscii	back to summary
public static boolean isAscii(byte b)

isAsciiCompatible	back to summary
public final boolean isAsciiCompatible()

isBlank	back to summary
public final boolean isBlank(int code)

isCntrl	back to summary
public final boolean isCntrl(int code)

isCodeCType back to summary

isCodeCType	back to summary
public abstract boolean isCodeCType(int code, int ctype) Perform a check whether given code is of given character type (e.g. used by isWord(someByte) and similar methods) Parameters code:int a code point of a character ctype:int a character type to check against Oniguruma equivalent: `is_code_ctype`

public abstract boolean isCodeCType(int code, int ctype)

Perform a check whether given code is of given character type (e.g. used by isWord(someByte) and similar methods)

Parameters

code:int: a code point of a character
ctype:int: a character type to check against Oniguruma equivalent: is_code_ctype

isDigit	back to summary
public final boolean isDigit(int code)

isDummy	back to summary
public final boolean isDummy()

isFixedWidth	back to summary
public final boolean isFixedWidth()

isGraph	back to summary
public final boolean isGraph(int code)

isLower	back to summary
public final boolean isLower(int code)

isMbcAscii	back to summary
public static boolean isMbcAscii(byte b)

isMbcCrnl	back to summary
public boolean isMbcCrnl(byte[] bytes, int p, int end)

isMbcHead	back to summary
public final boolean isMbcHead(byte[] bytes, int p, int end)

isMbcWord	back to summary
public final boolean isMbcWord(byte[] bytes, int p, int end)

isNewLine	back to summary
public abstract boolean isNewLine(byte[] bytes, int p, int end) Returns true if `bytes[p]` is a head of a new line character Oniguruma equivalent: `is_mbc_newline`

isNewLine	back to summary
public final boolean isNewLine(int code)

isPrint	back to summary
public final boolean isPrint(int code)

isPunct	back to summary
public final boolean isPunct(int code)

isReverseMatchAllowed	back to summary
public abstract boolean isReverseMatchAllowed(byte[] bytes, int p, int end) Returns true if it's safe to use reversal Boyer-Moore search fail fast algorithm Oniguruma equivalent: `is_allowed_reverse_match`

isSbWord	back to summary
public final boolean isSbWord(int code)

isSingleByte	back to summary
public final boolean isSingleByte()

isSpace	back to summary
public final boolean isSpace(int code)

isUnicode	back to summary
public final boolean isUnicode()

isUpper	back to summary
public final boolean isUpper(int code)

isUTF8	back to summary
public final boolean isUTF8()

isWord	back to summary
public final boolean isWord(int code)

isWordGraphPrint	back to summary
public static boolean isWordGraphPrint(int ctype)

isXDigit	back to summary
public final boolean isXDigit(int code)

leftAdjustCharHead back to summary

public abstract int leftAdjustCharHead(byte[] bytes, int p, int s, int end)

Seeks the previous character head in a stream Oniguruma equivalent: left_adjust_char_head

Parameters

bytes:byte[]: byte stream
p:int: position
s:int: stop
end:int: end

length back to summary

public abstract int length(byte c)

Returns character length given character head returns 1 for singlebyte encodings or performs direct length table lookup for multibyte ones.

Parameters

c:byte: Character head Oniguruma equivalent: mbc_enc_len To be deprecated very soon (use length(byte[]bytes, int p, int end) version)

length back to summary

public abstract int length(byte[] bytes, int p, int end)

Returns character length given stream, character position and stream end returns 1 for singlebyte encodings or performs sanity validations for multibyte ones and returns the character length, missing characters in the stream otherwise

Returns:int: 0 Never > 0 Valid character, length returned -1 Illegal/malformed character < -1 (-1 - n) Number of missing bytes for character in p...end range Oniguruma equivalent: mbc_enc_len modified for 1.9 purposes,

load	back to summary
public static Encoding load(String name)

load	back to summary
public static Encoding load(String name, String pkg)

maxLength	back to summary
public final int maxLength() Returns maximum character byte length that can appear in an encoding Oniguruma equivalent: `max_enc_len`

maxLengthDistance	back to summary
public final int maxLengthDistance() Deprecated Annotations @Deprecated

mbcCaseFold back to summary

public abstract int mbcCaseFold(int flag, byte[] bytes, IntHolder pp, int end, byte[] to)

Performs case folding for a character at bytes[pp.value]

Parameters

flag:int: case fold flag
pp:IntHolder: an IntHolder that points at character head
to:byte[]: a buffer where to extract case folded character Oniguruma equivalent: mbc_case_fold

mbcodeStartPosition	back to summary
public final int mbcodeStartPosition() Deprecated Annotations @Deprecated

mbcToCode	back to summary
public abstract int mbcToCode(byte[] bytes, int p, int end) Returns code point for a character Oniguruma equivalent: `mbc_to_code`

minLength	back to summary
public final int minLength() Returns minimum character byte length that can appear in an encoding Oniguruma equivalent: `min_enc_len`

odigitVal	back to summary
public static int odigitVal(int code)

prevCharHead	back to summary
public final int prevCharHead(byte[] bytes, int p, int s, int end)

propertyNameToCType	back to summary
public abstract int propertyNameToCType(byte[] bytes, int p, int end) Returns character type given character type name (used when e.g. \p{Alpha}) Oniguruma equivalent: `property_name_to_ctype`

replicate	back to summary
pack-priv Encoding replicate(byte[] name)

rightAdjustCharHead	back to summary
public final int rightAdjustCharHead(byte[] bytes, int p, int s, int end)

rightAdjustCharHeadWithPrev	back to summary
public final int rightAdjustCharHeadWithPrev(byte[] bytes, int p, int s, int end, IntHolder prev)

setDummy	back to summary
protected final void setDummy()

setName	back to summary
protected final void setName(String name)

setName	back to summary
protected final void setName(byte[] name)

step	back to summary
public final int step(byte[] bytes, int p, int end, int n)

stepBack	back to summary
public final int stepBack(byte[] bytes, int p, int s, int end, int n)

strByteLengthNull	back to summary
public final int strByteLengthNull(byte[] bytes, int p, int end)

strCodeAt	back to summary
public abstract int strCodeAt(byte[] bytes, int p, int end, int index)

strLength	back to summary
public abstract int strLength(byte[] bytes, int p, int end)

strLengthNull	back to summary
public final int strLengthNull(byte[] bytes, int p, int end)

strNCmp	back to summary
public final int strNCmp(byte[] bytes, int p, int end, byte[] ascii, int asciiP, int n)

toLowerCaseTable back to summary

public byte[] toLowerCaseTable()

Returns lower case table if it's safe to use it directly, otherwise null Used for fast case insensitive matching for some singlebyte encodings

Returns:byte[]: lower case table

toString

back to summary

public final String toString()

Overrides java.lang.Object.toString.

Doc from java.lang.Object.toString.

Returns a string representation of the object.

Returns:String

a string representation of the object

Annotations

@Override

xdigitVal	back to summary
public final int xdigitVal(int code)

public abstract Class Encoding

Field Summary

Constructor Summary

Method Summary

Field Detail

Constructor Detail

Method Detail