|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Objectorg.jcodings.Encoding
org.jcodings.MultiByteEncoding
org.jcodings.unicode.UnicodeEncoding
org.jcodings.unicode.FixedWidthUnicodeEncoding
public abstract class FixedWidthUnicodeEncoding
Field Summary | |
---|---|
protected static CaseFoldCodeItem[] |
EMPTY_FOLD_CODES
|
protected int |
shift
|
Fields inherited from class org.jcodings.MultiByteEncoding |
---|
A, EncLen, F, Trans, TransZero |
Fields inherited from class org.jcodings.Encoding |
---|
CHAR_INVALID, hashCode, isAsciiCompatible, isDummy, isFixedWidth, isSingleByte, maxLength, minLength, name, NEW_LINE |
Constructor Summary | |
---|---|
protected |
FixedWidthUnicodeEncoding(String name,
int width)
|
Method Summary | |
---|---|
protected void |
asciiApplyAllCaseFold(int flag,
ApplyAllCaseFoldFunction fun,
Object arg)
|
protected CaseFoldCodeItem[] |
asciiCaseFoldCodesByString(int flag,
byte[] bytes,
int p,
int end)
|
protected int |
asciiMbcCaseFold(int flag,
byte[] bytes,
IntHolder pp,
int end,
byte[] lower)
|
int |
codeToMbcLength(int code)
Returns character length given a code point Oniguruma equivalent: code_to_mbclen |
int[] |
ctypeCodeRange(int ctype,
IntHolder sbOut)
onigenc_utf16_32_get_ctype_code_range |
protected boolean |
isCodeCTypeInternal(int code,
int ctype)
ONIGENC_IS_XXXXXX_CODE_CTYPE |
boolean |
isNewLine(byte[] bytes,
int p,
int end)
onigenc_is_mbc_newline_0x0a / used also by multibyte encodings |
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 |
int |
leftAdjustCharHead(byte[] bytes,
int p,
int s,
int end)
Seeks the previous character head in a stream Oniguruma equivalent: left_adjust_char_head |
int |
length(byte c)
Returns character length given character head returns 1 for singlebyte encodings or performs direct length table lookup for multibyte ones. |
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 |
int |
strCodeAt(byte[] bytes,
int p,
int end,
int index)
|
int |
strLength(byte[] bytes,
int p,
int end)
|
Methods inherited from class org.jcodings.unicode.UnicodeEncoding |
---|
applyAllCaseFold, caseFoldCodesByString, ctypeCodeRange, isCodeCType, mbcCaseFold, propertyNameToCType |
Methods inherited from class org.jcodings.MultiByteEncoding |
---|
mb2CodeToMbc, mb2CodeToMbcLength, mb2IsCodeCType, mb4CodeToMbc, mb4CodeToMbcLength, mb4IsCodeCType, mbnMbcCaseFold, mbnMbcToCode, missing, missing, safeLengthForUptoFour, safeLengthForUptoThree, safeLengthForUptoTwo |
Methods inherited from class org.jcodings.Encoding |
---|
asciiToLower, asciiToUpper, codeToMbc, digitVal, equals, getIndex, getName, hashCode, isAlnum, isAlpha, isAscii, isAscii, isAsciiCompatible, isBlank, isCntrl, isDigit, isDummy, isFixedWidth, isGraph, isLower, isMbcAscii, isMbcCrnl, isMbcHead, isMbcWord, isNewLine, isPrint, isPunct, isSbWord, isSingleByte, isSpace, isUpper, isWord, isWordGraphPrint, isXDigit, load, maxLength, maxLengthDistance, mbcodeStartPosition, mbcToCode, minLength, odigitVal, prevCharHead, replicate, rightAdjustCharHead, rightAdjustCharHeadWithPrev, setName, setName, step, stepBack, strByteLengthNull, strLengthNull, strNCmp, toLowerCaseTable, toString, xdigitVal |
Methods inherited from class java.lang.Object |
---|
clone, finalize, getClass, notify, notifyAll, wait, wait, wait |
Field Detail |
---|
protected final int shift
protected static final CaseFoldCodeItem[] EMPTY_FOLD_CODES
Constructor Detail |
---|
protected FixedWidthUnicodeEncoding(String name, int width)
Method Detail |
---|
public final int length(byte c)
Encoding
1
for singlebyte encodings or performs direct length table lookup for multibyte ones.
length
in class MultiByteEncoding
c
- Character head
Oniguruma equivalent: mbc_enc_len
To be deprecated very soon (use length(byte[]bytes, int p, int end) version)public final int length(byte[] bytes, int p, int end)
Encoding
1
for singlebyte encodings or performs sanity validations for multibyte ones
and returns the character length, missing characters in the stream otherwise
length
in class Encoding
mbc_enc_len
modified for 1.9 purposes,public final int strLength(byte[] bytes, int p, int end)
strLength
in class MultiByteEncoding
public final int strCodeAt(byte[] bytes, int p, int end, int index)
strCodeAt
in class MultiByteEncoding
public final int codeToMbcLength(int code)
Encoding
code_to_mbclen
codeToMbcLength
in class Encoding
public final int[] ctypeCodeRange(int ctype, IntHolder sbOut)
ctypeCodeRange
in class Encoding
public final int leftAdjustCharHead(byte[] bytes, int p, int s, int end)
Encoding
left_adjust_char_head
leftAdjustCharHead
in class Encoding
bytes
- byte streamp
- positions
- stopend
- endpublic final boolean isReverseMatchAllowed(byte[] bytes, int p, int end)
Encoding
is_allowed_reverse_match
isReverseMatchAllowed
in class Encoding
protected final boolean isCodeCTypeInternal(int code, int ctype)
public boolean isNewLine(byte[] bytes, int p, int end)
isNewLine
in class Encoding
protected final int asciiMbcCaseFold(int flag, byte[] bytes, IntHolder pp, int end, byte[] lower)
protected final void asciiApplyAllCaseFold(int flag, ApplyAllCaseFoldFunction fun, Object arg)
protected final CaseFoldCodeItem[] asciiCaseFoldCodesByString(int flag, byte[] bytes, int p, int end)
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |