archive/jdk
1
0
Fork 0
mirror of https://github.com/openjdk/jdk.git synced 2025-08-28 07:14:30 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

8187443: Forest Consolidation: Move files to unified layout

Browse source 
Reviewed-by: darcy, ihse
This commit is contained in:
Erik Joelsson 2017-09-12 19:03:39 +02:00
parent 270fe13182
commit 3789983e89
56923 changed files with 3 additions and 15727 deletions
Download patch file Download diff file Expand all files Collapse all files

511
src/java.base/share/classes/sun/net/idn/Punycode.java Normal file
View file

@ -0,0 +1,511 @@
/*
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This code is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 only, as
* published by the Free Software Foundation. Oracle designates this
* particular file as subject to the "Classpath" exception as provided
* by Oracle in the LICENSE file that accompanied this code.
*
* This code is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
* version 2 for more details (a copy is included in the LICENSE file that
* accompanied this code).
*
* You should have received a copy of the GNU General Public License version
* 2 along with this work; if not, write to the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
* or visit www.oracle.com if you need additional information or have any
* questions.
*/
/*
*******************************************************************************
* Copyright (C) 2003-2004, International Business Machines Corporation and *
* others. All Rights Reserved. *
*******************************************************************************
*/
//
// CHANGELOG
// 2005-05-19 Edward Wang
// - copy this file from icu4jsrc_3_2/src/com/ibm/icu/text/Punycode.java
// - move from package com.ibm.icu.text to package sun.net.idn
// - use ParseException instead of StringPrepParseException
// 2007-08-14 Martin Buchholz
// - remove redundant casts
//
package sun.net.idn;
import java.text.ParseException;
import sun.text.normalizer.UCharacter;
import sun.text.normalizer.UTF16;
/**
* Ported code from ICU punycode.c
* @author ram
*/
/* Package Private class */
public final class Punycode {
/* Punycode parameters for Bootstring */
private static final int BASE = 36;
private static final int TMIN = 1;
private static final int TMAX = 26;
private static final int SKEW = 38;
private static final int DAMP = 700;
private static final int INITIAL_BIAS = 72;
private static final int INITIAL_N = 0x80;
/* "Basic" Unicode/ASCII code points */
private static final int HYPHEN = 0x2d;
private static final int DELIMITER = HYPHEN;
private static final int ZERO = 0x30;
private static final int NINE = 0x39;
private static final int SMALL_A = 0x61;
private static final int SMALL_Z = 0x7a;
private static final int CAPITAL_A = 0x41;
private static final int CAPITAL_Z = 0x5a;
// TODO: eliminate the 256 limitation
private static final int MAX_CP_COUNT = 256;
private static final int UINT_MAGIC = 0x80000000;
private static final long ULONG_MAGIC = 0x8000000000000000L;
private static int adaptBias(int delta, int length, boolean firstTime){
if(firstTime){
delta /=DAMP;
}else{
delta /= 2;
}
delta += delta/length;
int count=0;
for(; delta>((BASE-TMIN)*TMAX)/2; count+=BASE) {
delta/=(BASE-TMIN);
}
return count+(((BASE-TMIN+1)*delta)/(delta+SKEW));
}
/**
* basicToDigit[] contains the numeric value of a basic code
* point (for use in representing integers) in the range 0 to
* BASE-1, or -1 if b is does not represent a value.
*/
static final int[] basicToDigit= new int[]{
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
26, 27, 28, 29, 30, 31, 32, 33, 34, 35, -1, -1, -1, -1, -1, -1,
-1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14,
15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, -1, -1, -1, -1, -1,
-1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14,
15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1
};
private static char asciiCaseMap(char b, boolean uppercase) {
if(uppercase) {
if(SMALL_A<=b && b<=SMALL_Z) {
b-=(SMALL_A-CAPITAL_A);
}
} else {
if(CAPITAL_A<=b && b<=CAPITAL_Z) {
b+=(SMALL_A-CAPITAL_A);
}
}
return b;
}
/**
* digitToBasic() returns the basic code point whose value
* (when used for representing integers) is d, which must be in the
* range 0 to BASE-1. The lowercase form is used unless the uppercase flag is
* nonzero, in which case the uppercase form is used.
*/
private static char digitToBasic(int digit, boolean uppercase) {
/* 0..25 map to ASCII a..z or A..Z */
/* 26..35 map to ASCII 0..9 */
if(digit<26) {
if(uppercase) {
return (char)(CAPITAL_A+digit);
} else {
return (char)(SMALL_A+digit);
}
} else {
return (char)((ZERO-26)+digit);
}
}
/**
* Converts Unicode to Punycode.
* The input string must not contain single, unpaired surrogates.
* The output will be represented as an array of ASCII code points.
*
* @param src
* @param caseFlags
* @return
* @throws ParseException
*/
public static StringBuffer encode(StringBuffer src, boolean[] caseFlags) throws ParseException{
int[] cpBuffer = new int[MAX_CP_COUNT];
int n, delta, handledCPCount, basicLength, destLength, bias, j, m, q, k, t, srcCPCount;
char c, c2;
int srcLength = src.length();
int destCapacity = MAX_CP_COUNT;
char[] dest = new char[destCapacity];
StringBuffer result = new StringBuffer();
/*
* Handle the basic code points and
* convert extended ones to UTF-32 in cpBuffer (caseFlag in sign bit):
*/
srcCPCount=destLength=0;
for(j=0; j<srcLength; ++j) {
if(srcCPCount==MAX_CP_COUNT) {
/* too many input code points */
throw new IndexOutOfBoundsException();
}
c=src.charAt(j);
if(isBasic(c)) {
if(destLength<destCapacity) {
cpBuffer[srcCPCount++]=0;
dest[destLength]=
caseFlags!=null ?
asciiCaseMap(c, caseFlags[j]) :
c;
}
++destLength;
} else {
n=((caseFlags!=null && caseFlags[j])? 1 : 0)<<31L;
if(!UTF16.isSurrogate(c)) {
n|=c;
} else if(UTF16.isLeadSurrogate(c) && (j+1)<srcLength && UTF16.isTrailSurrogate(c2=src.charAt(j+1))) {
++j;
n|=UCharacter.getCodePoint(c, c2);
} else {
/* error: unmatched surrogate */
throw new ParseException("Illegal char found", -1);
}
cpBuffer[srcCPCount++]=n;
}
}
/* Finish the basic string - if it is not empty - with a delimiter. */
basicLength=destLength;
if(basicLength>0) {
if(destLength<destCapacity) {
dest[destLength]=DELIMITER;
}
++destLength;
}
/*
* handledCPCount is the number of code points that have been handled
* basicLength is the number of basic code points
* destLength is the number of chars that have been output
*/
/* Initialize the state: */
n=INITIAL_N;
delta=0;
bias=INITIAL_BIAS;
/* Main encoding loop: */
for(handledCPCount=basicLength; handledCPCount<srcCPCount; /* no op */) {
/*
* All non-basic code points < n have been handled already.
* Find the next larger one:
*/
for(m=0x7fffffff, j=0; j<srcCPCount; ++j) {
q=cpBuffer[j]&0x7fffffff; /* remove case flag from the sign bit */
if(n<=q && q<m) {
m=q;
}
}
/*
* Increase delta enough to advance the decoder's
* <n,i> state to <m,0>, but guard against overflow:
*/
if(m-n>(0x7fffffff-MAX_CP_COUNT-delta)/(handledCPCount+1)) {
throw new RuntimeException("Internal program error");
}
delta+=(m-n)*(handledCPCount+1);
n=m;
/* Encode a sequence of same code points n */
for(j=0; j<srcCPCount; ++j) {
q=cpBuffer[j]&0x7fffffff; /* remove case flag from the sign bit */
if(q<n) {
++delta;
} else if(q==n) {
/* Represent delta as a generalized variable-length integer: */
for(q=delta, k=BASE; /* no condition */; k+=BASE) {
/** RAM: comment out the old code for conformance with draft-ietf-idn-punycode-03.txt
t=k-bias;
if(t<TMIN) {
t=TMIN;
} else if(t>TMAX) {
t=TMAX;
}
*/
t=k-bias;
if(t<TMIN) {
t=TMIN;
} else if(k>=(bias+TMAX)) {
t=TMAX;
}
if(q<t) {
break;
}
if(destLength<destCapacity) {
dest[destLength++]=digitToBasic(t+(q-t)%(BASE-t), false);
}
q=(q-t)/(BASE-t);
}
if(destLength<destCapacity) {
dest[destLength++]=digitToBasic(q, (cpBuffer[j]<0));
}
bias=adaptBias(delta, handledCPCount+1,(handledCPCount==basicLength));
delta=0;
++handledCPCount;
}
}
++delta;
++n;
}
return result.append(dest, 0, destLength);
}
private static boolean isBasic(int ch){
return (ch < INITIAL_N);
}
private static boolean isBasicUpperCase(int ch){
return( CAPITAL_A <= ch && ch <= CAPITAL_Z);
}
private static boolean isSurrogate(int ch){
return (((ch)&0xfffff800)==0xd800);
}
/**
* Converts Punycode to Unicode.
* The Unicode string will be at most as long as the Punycode string.
*
* @param src
* @param caseFlags
* @return
* @throws ParseException
*/
public static StringBuffer decode(StringBuffer src, boolean[] caseFlags)
throws ParseException{
int srcLength = src.length();
StringBuffer result = new StringBuffer();
int n, destLength, i, bias, basicLength, j, in, oldi, w, k, digit, t,
destCPCount, firstSupplementaryIndex, cpLength;
char b;
int destCapacity = MAX_CP_COUNT;
char[] dest = new char[destCapacity];
/*
* Handle the basic code points:
* Let basicLength be the number of input code points
* before the last delimiter, or 0 if there is none,
* then copy the first basicLength code points to the output.
*
* The two following loops iterate backward.
*/
for(j=srcLength; j>0;) {
if(src.charAt(--j)==DELIMITER) {
break;
}
}
destLength=basicLength=destCPCount=j;
while(j>0) {
b=src.charAt(--j);
if(!isBasic(b)) {
throw new ParseException("Illegal char found", -1);
}
if(j<destCapacity) {
dest[j]= b;
if(caseFlags!=null) {
caseFlags[j]=isBasicUpperCase(b);
}
}
}
/* Initialize the state: */
n=INITIAL_N;
i=0;
bias=INITIAL_BIAS;
firstSupplementaryIndex=1000000000;
/*
* Main decoding loop:
* Start just after the last delimiter if any
* basic code points were copied; start at the beginning otherwise.
*/
for(in=basicLength>0 ? basicLength+1 : 0; in<srcLength; /* no op */) {
/*
* in is the index of the next character to be consumed, and
* destCPCount is the number of code points in the output array.
*
* Decode a generalized variable-length integer into delta,
* which gets added to i. The overflow checking is easier
* if we increase i as we go, then subtract off its starting
* value at the end to obtain delta.
*/
for(oldi=i, w=1, k=BASE; /* no condition */; k+=BASE) {
if(in>=srcLength) {
throw new ParseException("Illegal char found", -1);
}
digit=basicToDigit[(byte)src.charAt(in++)];
if(digit<0) {
throw new ParseException("Invalid char found", -1);
}
if(digit>(0x7fffffff-i)/w) {
/* integer overflow */
throw new ParseException("Illegal char found", -1);
}
i+=digit*w;
t=k-bias;
if(t<TMIN) {
t=TMIN;
} else if(k>=(bias+TMAX)) {
t=TMAX;
}
if(digit<t) {
break;
}
if(w>0x7fffffff/(BASE-t)) {
/* integer overflow */
throw new ParseException("Illegal char found", -1);
}
w*=BASE-t;
}
/*
* Modification from sample code:
* Increments destCPCount here,
* where needed instead of in for() loop tail.
*/
++destCPCount;
bias=adaptBias(i-oldi, destCPCount, (oldi==0));
/*
* i was supposed to wrap around from (incremented) destCPCount to 0,
* incrementing n each time, so we'll fix that now:
*/
if(i/destCPCount>(0x7fffffff-n)) {
/* integer overflow */
throw new ParseException("Illegal char found", -1);
}
n+=i/destCPCount;
i%=destCPCount;
/* not needed for Punycode: */
/* if (decode_digit(n) <= BASE) return punycode_invalid_input; */
if(n>0x10ffff || isSurrogate(n)) {
/* Unicode code point overflow */
throw new ParseException("Illegal char found", -1);
}
/* Insert n at position i of the output: */
cpLength=UTF16.getCharCount(n);
if((destLength+cpLength)<destCapacity) {
int codeUnitIndex;
/*
* Handle indexes when supplementary code points are present.
*
* In almost all cases, there will be only BMP code points before i
* and even in the entire string.
* This is handled with the same efficiency as with UTF-32.
*
* Only the rare cases with supplementary code points are handled
* more slowly - but not too bad since this is an insertion anyway.
*/
if(i<=firstSupplementaryIndex) {
codeUnitIndex=i;
if(cpLength>1) {
firstSupplementaryIndex=codeUnitIndex;
} else {
++firstSupplementaryIndex;
}
} else {
codeUnitIndex=firstSupplementaryIndex;
codeUnitIndex=UTF16.moveCodePointOffset(dest, 0, destLength, codeUnitIndex, i-codeUnitIndex);
}
/* use the UChar index codeUnitIndex instead of the code point index i */
if(codeUnitIndex<destLength) {
System.arraycopy(dest, codeUnitIndex,
dest, codeUnitIndex+cpLength,
(destLength-codeUnitIndex));
if(caseFlags!=null) {
System.arraycopy(caseFlags, codeUnitIndex,
caseFlags, codeUnitIndex+cpLength,
destLength-codeUnitIndex);
}
}
if(cpLength==1) {
/* BMP, insert one code unit */
dest[codeUnitIndex]=(char)n;
} else {
/* supplementary character, insert two code units */
dest[codeUnitIndex]=UTF16.getLeadSurrogate(n);
dest[codeUnitIndex+1]=UTF16.getTrailSurrogate(n);
}
if(caseFlags!=null) {
/* Case of last character determines uppercase flag: */
caseFlags[codeUnitIndex]=isBasicUpperCase(src.charAt(in-1));
if(cpLength==2) {
caseFlags[codeUnitIndex+1]=false;
}
}
}
destLength+=cpLength;
++i;
}
result.append(dest, 0, destLength);
return result;
}
}

486
src/java.base/share/classes/sun/net/idn/StringPrep.java Normal file
View file

@ -0,0 +1,486 @@
/*
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This code is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 only, as
* published by the Free Software Foundation. Oracle designates this
* particular file as subject to the "Classpath" exception as provided
* by Oracle in the LICENSE file that accompanied this code.
*
* This code is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
* version 2 for more details (a copy is included in the LICENSE file that
* accompanied this code).
*
* You should have received a copy of the GNU General Public License version
* 2 along with this work; if not, write to the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
* or visit www.oracle.com if you need additional information or have any
* questions.
*/
/*
/*
*******************************************************************************
* Copyright (C) 2003-2004, International Business Machines Corporation and *
* others. All Rights Reserved. *
*******************************************************************************
*/
//
// CHANGELOG
// 2005-05-19 Edward Wang
// - copy this file from icu4jsrc_3_2/src/com/ibm/icu/text/StringPrep.java
// - move from package com.ibm.icu.text to package sun.net.idn
// - use ParseException instead of StringPrepParseException
// - change 'Normalizer.getUnicodeVersion()' to 'NormalizerImpl.getUnicodeVersion()'
// - remove all @deprecated tag to make compiler happy
// 2007-08-14 Martin Buchholz
// - remove redundant casts
//
package sun.net.idn;
import java.io.BufferedInputStream;
import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.text.ParseException;
import sun.text.Normalizer;
import sun.text.normalizer.CharTrie;
import sun.text.normalizer.Trie;
import sun.text.normalizer.VersionInfo;
import sun.text.normalizer.UCharacter;
import sun.text.normalizer.UCharacterIterator;
import sun.text.normalizer.UTF16;
import sun.net.idn.UCharacterDirection;
import sun.net.idn.StringPrepDataReader;
/**
* StringPrep API implements the StingPrep framework as described by
* <a href="http://www.ietf.org/rfc/rfc3454.txt">RFC 3454</a>.
* StringPrep prepares Unicode strings for use in network protocols.
* Profiles of StingPrep are set of rules and data according to which the
* Unicode Strings are prepared. Each profiles contains tables which describe
* how a code point should be treated. The tables are broadly classied into
* <ul>
* <li> Unassigned Table: Contains code points that are unassigned
* in the Unicode Version supported by StringPrep. Currently
* RFC 3454 supports Unicode 3.2. </li>
* <li> Prohibited Table: Contains code points that are prohibted from
* the output of the StringPrep processing function. </li>
* <li> Mapping Table: Contains code ponts that are deleted from the output or case mapped. </li>
* </ul>
*
* The procedure for preparing Unicode strings:
* <ol>
* <li> Map: For each character in the input, check if it has a mapping
* and, if so, replace it with its mapping. </li>
* <li> Normalize: Possibly normalize the result of step 1 using Unicode
* normalization. </li>
* <li> Prohibit: Check for any characters that are not allowed in the
* output. If any are found, return an error.</li>
* <li> Check bidi: Possibly check for right-to-left characters, and if
* any are found, make sure that the whole string satisfies the
* requirements for bidirectional strings. If the string does not
* satisfy the requirements for bidirectional strings, return an
* error. </li>
* </ol>
* @author Ram Viswanadha
* @draft ICU 2.8
*/
public final class StringPrep {
/**
* Option to prohibit processing of unassigned code points in the input
*
* @see #prepare
* @draft ICU 2.8
*/
public static final int DEFAULT = 0x0000;
/**
* Option to allow processing of unassigned code points in the input
*
* @see #prepare
* @draft ICU 2.8
*/
public static final int ALLOW_UNASSIGNED = 0x0001;
private static final int UNASSIGNED = 0x0000;
private static final int MAP = 0x0001;
private static final int PROHIBITED = 0x0002;
private static final int DELETE = 0x0003;
private static final int TYPE_LIMIT = 0x0004;
private static final int NORMALIZATION_ON = 0x0001;
private static final int CHECK_BIDI_ON = 0x0002;
private static final int TYPE_THRESHOLD = 0xFFF0;
private static final int MAX_INDEX_VALUE = 0x3FBF; /*16139*/
private static final int MAX_INDEX_TOP_LENGTH = 0x0003;
/* indexes[] value names */
private static final int INDEX_TRIE_SIZE = 0; /* number of bytes in normalization trie */
private static final int INDEX_MAPPING_DATA_SIZE = 1; /* The array that contains the mapping */
private static final int NORM_CORRECTNS_LAST_UNI_VERSION = 2; /* The index of Unicode version of last entry in NormalizationCorrections.txt */
private static final int ONE_UCHAR_MAPPING_INDEX_START = 3; /* The starting index of 1 UChar mapping index in the mapping data array */
private static final int TWO_UCHARS_MAPPING_INDEX_START = 4; /* The starting index of 2 UChars mapping index in the mapping data array */
private static final int THREE_UCHARS_MAPPING_INDEX_START = 5;
private static final int FOUR_UCHARS_MAPPING_INDEX_START = 6;
private static final int OPTIONS = 7; /* Bit set of options to turn on in the profile */
private static final int INDEX_TOP = 16; /* changing this requires a new formatVersion */
/**
* Default buffer size of datafile
*/
private static final int DATA_BUFFER_SIZE = 25000;
/* Wrappers for Trie implementations */
private static final class StringPrepTrieImpl implements Trie.DataManipulate{
private CharTrie sprepTrie = null;
/**
* Called by com.ibm.icu.util.Trie to extract from a lead surrogate's
* data the index array offset of the indexes for that lead surrogate.
* @param property data value for a surrogate from the trie, including
* the folding offset
* @return data offset or 0 if there is no data for the lead surrogate
*/
public int getFoldingOffset(int value){
return value;
}
}
// CharTrie implementation for reading the trie data
private StringPrepTrieImpl sprepTrieImpl;
// Indexes read from the data file
private int[] indexes;
// mapping data read from the data file
private char[] mappingData;
// format version of the data file
private byte[] formatVersion;
// the version of Unicode supported by the data file
private VersionInfo sprepUniVer;
// the Unicode version of last entry in the
// NormalizationCorrections.txt file if normalization
// is turned on
private VersionInfo normCorrVer;
// Option to turn on Normalization
private boolean doNFKC;
// Option to turn on checking for BiDi rules
private boolean checkBiDi;
private char getCodePointValue(int ch){
return sprepTrieImpl.sprepTrie.getCodePointValue(ch);
}
private static VersionInfo getVersionInfo(int comp){
int micro = comp & 0xFF;
int milli =(comp >> 8) & 0xFF;
int minor =(comp >> 16) & 0xFF;
int major =(comp >> 24) & 0xFF;
return VersionInfo.getInstance(major,minor,milli,micro);
}
private static VersionInfo getVersionInfo(byte[] version){
if(version.length != 4){
return null;
}
return VersionInfo.getInstance((int)version[0],(int) version[1],(int) version[2],(int) version[3]);
}
/**
* Creates an StringPrep object after reading the input stream.
* The object does not hold a reference to the input steam, so the stream can be
* closed after the method returns.
*
* @param inputStream The stream for reading the StringPrep profile binarySun
* @throws IOException
* @draft ICU 2.8
*/
public StringPrep(InputStream inputStream) throws IOException{
BufferedInputStream b = new BufferedInputStream(inputStream,DATA_BUFFER_SIZE);
StringPrepDataReader reader = new StringPrepDataReader(b);
// read the indexes
indexes = reader.readIndexes(INDEX_TOP);
byte[] sprepBytes = new byte[indexes[INDEX_TRIE_SIZE]];
//indexes[INDEX_MAPPING_DATA_SIZE] store the size of mappingData in bytes
mappingData = new char[indexes[INDEX_MAPPING_DATA_SIZE]/2];
// load the rest of the data data and initialize the data members
reader.read(sprepBytes,mappingData);
sprepTrieImpl = new StringPrepTrieImpl();
sprepTrieImpl.sprepTrie = new CharTrie( new ByteArrayInputStream(sprepBytes),sprepTrieImpl );
// get the data format version
formatVersion = reader.getDataFormatVersion();
// get the options
doNFKC = ((indexes[OPTIONS] & NORMALIZATION_ON) > 0);
checkBiDi = ((indexes[OPTIONS] & CHECK_BIDI_ON) > 0);
sprepUniVer = getVersionInfo(reader.getUnicodeVersion());
normCorrVer = getVersionInfo(indexes[NORM_CORRECTNS_LAST_UNI_VERSION]);
VersionInfo normUniVer = UCharacter.getUnicodeVersion();
if(normUniVer.compareTo(sprepUniVer) < 0 && /* the Unicode version of SPREP file must be less than the Unicode Vesion of the normalization data */
normUniVer.compareTo(normCorrVer) < 0 && /* the Unicode version of the NormalizationCorrections.txt file should be less than the Unicode Vesion of the normalization data */
((indexes[OPTIONS] & NORMALIZATION_ON) > 0) /* normalization turned on*/
){
throw new IOException("Normalization Correction version not supported");
}
b.close();
}
private static final class Values{
boolean isIndex;
int value;
int type;
public void reset(){
isIndex = false;
value = 0;
type = -1;
}
}
private static final void getValues(char trieWord,Values values){
values.reset();
if(trieWord == 0){
/*
* Initial value stored in the mapping table
* just return TYPE_LIMIT .. so that
* the source codepoint is copied to the destination
*/
values.type = TYPE_LIMIT;
}else if(trieWord >= TYPE_THRESHOLD){
values.type = (trieWord - TYPE_THRESHOLD);
}else{
/* get the type */
values.type = MAP;
/* ascertain if the value is index or delta */
if((trieWord & 0x02)>0){
values.isIndex = true;
values.value = trieWord >> 2; //mask off the lower 2 bits and shift
}else{
values.isIndex = false;
values.value = (trieWord<<16)>>16;
values.value = (values.value >> 2);
}
if((trieWord>>2) == MAX_INDEX_VALUE){
values.type = DELETE;
values.isIndex = false;
values.value = 0;
}
}
}
private StringBuffer map( UCharacterIterator iter, int options)
throws ParseException {
Values val = new Values();
char result = 0;
int ch = UCharacterIterator.DONE;
StringBuffer dest = new StringBuffer();
boolean allowUnassigned = ((options & ALLOW_UNASSIGNED)>0);
while((ch=iter.nextCodePoint())!= UCharacterIterator.DONE){
result = getCodePointValue(ch);
getValues(result,val);
// check if the source codepoint is unassigned
if(val.type == UNASSIGNED && allowUnassigned == false){
throw new ParseException("An unassigned code point was found in the input " +
iter.getText(), iter.getIndex());
}else if((val.type == MAP)){
int index, length;
if(val.isIndex){
index = val.value;
if(index >= indexes[ONE_UCHAR_MAPPING_INDEX_START] &&
index < indexes[TWO_UCHARS_MAPPING_INDEX_START]){
length = 1;
}else if(index >= indexes[TWO_UCHARS_MAPPING_INDEX_START] &&
index < indexes[THREE_UCHARS_MAPPING_INDEX_START]){
length = 2;
}else if(index >= indexes[THREE_UCHARS_MAPPING_INDEX_START] &&
index < indexes[FOUR_UCHARS_MAPPING_INDEX_START]){
length = 3;
}else{
length = mappingData[index++];
}
/* copy mapping to destination */
dest.append(mappingData,index,length);
continue;
}else{
ch -= val.value;
}
}else if(val.type == DELETE){
// just consume the codepoint and contine
continue;
}
//copy the source into destination
UTF16.append(dest,ch);
}
return dest;
}
private StringBuffer normalize(StringBuffer src){
/*
* Option UNORM_BEFORE_PRI_29:
*
* IDNA as interpreted by IETF members (see unicode mailing list 2004H1)
* requires strict adherence to Unicode 3.2 normalization,
* including buggy composition from before fixing Public Review Issue #29.
* Note that this results in some valid but nonsensical text to be
* either corrupted or rejected, depending on the text.
* See http://www.unicode.org/review/resolved-pri.html#pri29
* See unorm.cpp and cnormtst.c
*/
return new StringBuffer(
Normalizer.normalize(
src.toString(),
java.text.Normalizer.Form.NFKC,
Normalizer.UNICODE_3_2));
}
/*
boolean isLabelSeparator(int ch){
int result = getCodePointValue(ch);
if( (result & 0x07) == LABEL_SEPARATOR){
return true;
}
return false;
}
*/
/*
1) Map -- For each character in the input, check if it has a mapping
and, if so, replace it with its mapping.
2) Normalize -- Possibly normalize the result of step 1 using Unicode
normalization.
3) Prohibit -- Check for any characters that are not allowed in the
output. If any are found, return an error.
4) Check bidi -- Possibly check for right-to-left characters, and if
any are found, make sure that the whole string satisfies the
requirements for bidirectional strings. If the string does not
satisfy the requirements for bidirectional strings, return an
error.
[Unicode3.2] defines several bidirectional categories; each character
has one bidirectional category assigned to it. For the purposes of
the requirements below, an "RandALCat character" is a character that
has Unicode bidirectional categories "R" or "AL"; an "LCat character"
is a character that has Unicode bidirectional category "L". Note
that there are many characters which fall in neither of the above
definitions; Latin digits (<U+0030> through <U+0039>) are examples of
this because they have bidirectional category "EN".
In any profile that specifies bidirectional character handling, all
three of the following requirements MUST be met:
1) The characters in section 5.8 MUST be prohibited.
2) If a string contains any RandALCat character, the string MUST NOT
contain any LCat character.
3) If a string contains any RandALCat character, a RandALCat
character MUST be the first character of the string, and a
RandALCat character MUST be the last character of the string.
*/
/**
* Prepare the input buffer for use in applications with the given profile. This operation maps, normalizes(NFKC),
* checks for prohited and BiDi characters in the order defined by RFC 3454
* depending on the options specified in the profile.
*
* @param src A UCharacterIterator object containing the source string
* @param options A bit set of options:
*
* - StringPrep.NONE Prohibit processing of unassigned code points in the input
*
* - StringPrep.ALLOW_UNASSIGNED Treat the unassigned code points are in the input
* as normal Unicode code points.
*
* @return StringBuffer A StringBuffer containing the output
* @throws ParseException
* @draft ICU 2.8
*/
public StringBuffer prepare(UCharacterIterator src, int options)
throws ParseException{
// map
StringBuffer mapOut = map(src,options);
StringBuffer normOut = mapOut;// initialize
if(doNFKC){
// normalize
normOut = normalize(mapOut);
}
int ch;
char result;
UCharacterIterator iter = UCharacterIterator.getInstance(normOut);
Values val = new Values();
int direction=UCharacterDirection.CHAR_DIRECTION_COUNT,
firstCharDir=UCharacterDirection.CHAR_DIRECTION_COUNT;
int rtlPos=-1, ltrPos=-1;
boolean rightToLeft=false, leftToRight=false;
while((ch=iter.nextCodePoint())!= UCharacterIterator.DONE){
result = getCodePointValue(ch);
getValues(result,val);
if(val.type == PROHIBITED ){
throw new ParseException("A prohibited code point was found in the input" +
iter.getText(), val.value);
}
direction = UCharacter.getDirection(ch);
if(firstCharDir == UCharacterDirection.CHAR_DIRECTION_COUNT){
firstCharDir = direction;
}
if(direction == UCharacterDirection.LEFT_TO_RIGHT){
leftToRight = true;
ltrPos = iter.getIndex()-1;
}
if(direction == UCharacterDirection.RIGHT_TO_LEFT || direction == UCharacterDirection.RIGHT_TO_LEFT_ARABIC){
rightToLeft = true;
rtlPos = iter.getIndex()-1;
}
}
if(checkBiDi == true){
// satisfy 2
if( leftToRight == true && rightToLeft == true){
throw new ParseException("The input does not conform to the rules for BiDi code points." +
iter.getText(),
(rtlPos>ltrPos) ? rtlPos : ltrPos);
}
//satisfy 3
if( rightToLeft == true &&
!((firstCharDir == UCharacterDirection.RIGHT_TO_LEFT || firstCharDir == UCharacterDirection.RIGHT_TO_LEFT_ARABIC) &&
(direction == UCharacterDirection.RIGHT_TO_LEFT || direction == UCharacterDirection.RIGHT_TO_LEFT_ARABIC))
){
throw new ParseException("The input does not conform to the rules for BiDi code points." +
iter.getText(),
(rtlPos>ltrPos) ? rtlPos : ltrPos);
}
}
return normOut;
}
}

127
src/java.base/share/classes/sun/net/idn/StringPrepDataReader.java Normal file
View file

@ -0,0 +1,127 @@
/*
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This code is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 only, as
* published by the Free Software Foundation. Oracle designates this
* particular file as subject to the "Classpath" exception as provided
* by Oracle in the LICENSE file that accompanied this code.
*
* This code is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
* version 2 for more details (a copy is included in the LICENSE file that
* accompanied this code).
*
* You should have received a copy of the GNU General Public License version
* 2 along with this work; if not, write to the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
* or visit www.oracle.com if you need additional information or have any
* questions.
*/
/*
/*
******************************************************************************
* Copyright (C) 2003, International Business Machines Corporation and *
* others. All Rights Reserved. *
******************************************************************************
*
* Created on May 2, 2003
*
* To change the template for this generated file go to
* Window>Preferences>Java>Code Generation>Code and Comments
*/
// CHANGELOG
// 2005-05-19 Edward Wang
// - copy this file from icu4jsrc_3_2/src/com/ibm/icu/impl/StringPrepDataReader.java
// - move from package com.ibm.icu.impl to package sun.net.idn
//
package sun.net.idn;
import java.io.DataInputStream;
import java.io.IOException;
import java.io.InputStream;
import sun.text.normalizer.ICUBinary;
/**
* @author ram
*
* To change the template for this generated type comment go to
* Window>Preferences>Java>Code Generation>Code and Comments
*/
final class StringPrepDataReader implements ICUBinary.Authenticate {
/**
* <p>private constructor.</p>
* @param inputStream ICU uprop.dat file input stream
* @exception IOException throw if data file fails authentication
* @draft 2.1
*/
public StringPrepDataReader(InputStream inputStream)
throws IOException{
unicodeVersion = ICUBinary.readHeader(inputStream, DATA_FORMAT_ID, this);
dataInputStream = new DataInputStream(inputStream);
}
public void read(byte[] idnaBytes,
char[] mappingTable)
throws IOException{
//Read the bytes that make up the idnaTrie
dataInputStream.read(idnaBytes);
//Read the extra data
for(int i=0;i<mappingTable.length;i++){
mappingTable[i]=dataInputStream.readChar();
}
}
public byte[] getDataFormatVersion(){
return DATA_FORMAT_VERSION;
}
public boolean isDataVersionAcceptable(byte version[]){
return version[0] == DATA_FORMAT_VERSION[0]
&& version[2] == DATA_FORMAT_VERSION[2]
&& version[3] == DATA_FORMAT_VERSION[3];
}
public int[] readIndexes(int length)throws IOException{
int[] indexes = new int[length];
//Read the indexes
for (int i = 0; i <length ; i++) {
indexes[i] = dataInputStream.readInt();
}
return indexes;
}
public byte[] getUnicodeVersion(){
return unicodeVersion;
}
// private data members -------------------------------------------------
/**
* ICU data file input stream
*/
private DataInputStream dataInputStream;
private byte[] unicodeVersion;
/**
* File format version that this class understands.
* No guarantees are made if a older version is used
* see store.c of gennorm for more information and values
*/
///* dataFormat="SPRP" 0x53, 0x50, 0x52, 0x50 */
private static final byte DATA_FORMAT_ID[] = {(byte)0x53, (byte)0x50,
(byte)0x52, (byte)0x50};
private static final byte DATA_FORMAT_VERSION[] = {(byte)0x3, (byte)0x2,
(byte)0x5, (byte)0x2};
}

112
src/java.base/share/classes/sun/net/idn/UCharacterDirection.java Normal file
View file

@ -0,0 +1,112 @@
/*
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This code is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 only, as
* published by the Free Software Foundation. Oracle designates this
* particular file as subject to the "Classpath" exception as provided
* by Oracle in the LICENSE file that accompanied this code.
*
* This code is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
* version 2 for more details (a copy is included in the LICENSE file that
* accompanied this code).
*
* You should have received a copy of the GNU General Public License version
* 2 along with this work; if not, write to the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
* or visit www.oracle.com if you need additional information or have any
* questions.
*/
/*
/**
*******************************************************************************
* Copyright (C) 1996-2004, International Business Machines Corporation and *
* others. All Rights Reserved. *
*******************************************************************************
*/
// CHANGELOG
// 2005-05-19 Edward Wang
// - copy this file from icu4jsrc_3_2/src/com/ibm/icu/lang/UCharacterDirection.java
// - move from package com.ibm.icu.lang to package sun.net.idn
//
package sun.net.idn;
/**
* Enumerated Unicode character linguistic direction constants.
* Used as return results from <a href=UCharacter.html>UCharacter</a>
* <p>
* This class is not subclassable
* </p>
* @author Syn Wee Quek
* @stable ICU 2.1
*/
@SuppressWarnings("deprecation")
final class UCharacterDirection implements UCharacterEnums.ECharacterDirection {
// private constructor =========================================
///CLOVER:OFF
/**
* Private constructor to prevent initialisation
*/
private UCharacterDirection()
{
}
///CLOVER:ON
/**
* Gets the name of the argument direction
* @param dir direction type to retrieve name
* @return directional name
* @stable ICU 2.1
*/
public static String toString(int dir) {
switch(dir)
{
case LEFT_TO_RIGHT :
return "Left-to-Right";
case RIGHT_TO_LEFT :
return "Right-to-Left";
case EUROPEAN_NUMBER :
return "European Number";
case EUROPEAN_NUMBER_SEPARATOR :
return "European Number Separator";
case EUROPEAN_NUMBER_TERMINATOR :
return "European Number Terminator";
case ARABIC_NUMBER :
return "Arabic Number";
case COMMON_NUMBER_SEPARATOR :
return "Common Number Separator";
case BLOCK_SEPARATOR :
return "Paragraph Separator";
case SEGMENT_SEPARATOR :
return "Segment Separator";
case WHITE_SPACE_NEUTRAL :
return "Whitespace";
case OTHER_NEUTRAL :
return "Other Neutrals";
case LEFT_TO_RIGHT_EMBEDDING :
return "Left-to-Right Embedding";
case LEFT_TO_RIGHT_OVERRIDE :
return "Left-to-Right Override";
case RIGHT_TO_LEFT_ARABIC :
return "Right-to-Left Arabic";
case RIGHT_TO_LEFT_EMBEDDING :
return "Right-to-Left Embedding";
case RIGHT_TO_LEFT_OVERRIDE :
return "Right-to-Left Override";
case POP_DIRECTIONAL_FORMAT :
return "Pop Directional Format";
case DIR_NON_SPACING_MARK :
return "Non-Spacing Mark";
case BOUNDARY_NEUTRAL :
return "Boundary Neutral";
}
return "Unassigned";
}
}

587
src/java.base/share/classes/sun/net/idn/UCharacterEnums.java Normal file
View file

@ -0,0 +1,587 @@
/*
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This code is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 only, as
* published by the Free Software Foundation. Oracle designates this
* particular file as subject to the "Classpath" exception as provided
* by Oracle in the LICENSE file that accompanied this code.
*
* This code is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
* version 2 for more details (a copy is included in the LICENSE file that
* accompanied this code).
*
* You should have received a copy of the GNU General Public License version
* 2 along with this work; if not, write to the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
* or visit www.oracle.com if you need additional information or have any
* questions.
*/
/*
/**
*******************************************************************************
* Copyright (C) 2004, International Business Machines Corporation and *
* others. All Rights Reserved. *
*******************************************************************************
*/
// CHANGELOG
// 2005-05-19 Edward Wang
// - copy this file from icu4jsrc_3_2/src/com/ibm/icu/lang/UCharacterEnums.java
// - move from package com.ibm.icu.lang to package sun.net.idn
//
// 2011-09-06 Kurchi Subhra Hazra
// - Added @Deprecated tag to the following:
// - class UCharacterEnums
// - interfaces ECharacterCategory, ECharacterDirection
// - fields INITIAL_QUOTE_PUNCTUATION, FINAL_QUOTE_PUNCTUATION,
// DIRECTIONALITY_LEFT_TO_RIGHT, DIRECTIONALITY_RIGHT_TO_LEFT,
// DIRECTIONALITY_EUROPEAN_NUMBER, DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR
// DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR, DIRECTIONALITY_ARABIC_NUMBER,
// DIRECTIONALITY_COMMON_NUMBER_SEPARATOR, DIRECTIONALITY_PARAGRAPH_SEPARATOR,
// DIRECTIONALITY_SEGMENT_SEPARATOR, DIRECTIONALITY_WHITESPACE,
// DIRECTIONALITY_OTHER_NEUTRALS, DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING,
// DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE, DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC,
// DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING, DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE,
// DIRECTIONALITY_POP_DIRECTIONAL_FORMAT, DIRECTIONALITY_NON_SPACING_MARK,
// DIRECTIONALITY_BOUNDARY_NEUTRAL, DIRECTIONALITY_UNDEFINED
//
package sun.net.idn;
/**
* A container for the different 'enumerated types' used by UCharacter.
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
class UCharacterEnums {
/** This is just a namespace, it is not instantiatable. */
private UCharacterEnums() {};
/**
* 'Enum' for the CharacterCategory constants. These constants are
* compatible in name <b>but not in value</b> with those defined in
* <code>java.lang.Character</code>.
* @see UCharacterCategory
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static interface ECharacterCategory {
/**
* Unassigned character type
* @stable ICU 2.1
*/
public static final int UNASSIGNED = 0;
/**
* Character type Cn
* Not Assigned (no characters in [UnicodeData.txt] have this property)
* @stable ICU 2.6
*/
public static final int GENERAL_OTHER_TYPES = 0;
/**
* Character type Lu
* @stable ICU 2.1
*/
public static final int UPPERCASE_LETTER = 1;
/**
* Character type Ll
* @stable ICU 2.1
*/
public static final int LOWERCASE_LETTER = 2;
/**
* Character type Lt
* @stable ICU 2.1
*/
public static final int TITLECASE_LETTER = 3;
/**
* Character type Lm
* @stable ICU 2.1
*/
public static final int MODIFIER_LETTER = 4;
/**
* Character type Lo
* @stable ICU 2.1
*/
public static final int OTHER_LETTER = 5;
/**
* Character type Mn
* @stable ICU 2.1
*/
public static final int NON_SPACING_MARK = 6;
/**
* Character type Me
* @stable ICU 2.1
*/
public static final int ENCLOSING_MARK = 7;
/**
* Character type Mc
* @stable ICU 2.1
*/
public static final int COMBINING_SPACING_MARK = 8;
/**
* Character type Nd
* @stable ICU 2.1
*/
public static final int DECIMAL_DIGIT_NUMBER = 9;
/**
* Character type Nl
* @stable ICU 2.1
*/
public static final int LETTER_NUMBER = 10;
/**
* Character type No
* @stable ICU 2.1
*/
public static final int OTHER_NUMBER = 11;
/**
* Character type Zs
* @stable ICU 2.1
*/
public static final int SPACE_SEPARATOR = 12;
/**
* Character type Zl
* @stable ICU 2.1
*/
public static final int LINE_SEPARATOR = 13;
/**
* Character type Zp
* @stable ICU 2.1
*/
public static final int PARAGRAPH_SEPARATOR = 14;
/**
* Character type Cc
* @stable ICU 2.1
*/
public static final int CONTROL = 15;
/**
* Character type Cf
* @stable ICU 2.1
*/
public static final int FORMAT = 16;
/**
* Character type Co
* @stable ICU 2.1
*/
public static final int PRIVATE_USE = 17;
/**
* Character type Cs
* @stable ICU 2.1
*/
public static final int SURROGATE = 18;
/**
* Character type Pd
* @stable ICU 2.1
*/
public static final int DASH_PUNCTUATION = 19;
/**
* Character type Ps
* @stable ICU 2.1
*/
public static final int START_PUNCTUATION = 20;
/**
* Character type Pe
* @stable ICU 2.1
*/
public static final int END_PUNCTUATION = 21;
/**
* Character type Pc
* @stable ICU 2.1
*/
public static final int CONNECTOR_PUNCTUATION = 22;
/**
* Character type Po
* @stable ICU 2.1
*/
public static final int OTHER_PUNCTUATION = 23;
/**
* Character type Sm
* @stable ICU 2.1
*/
public static final int MATH_SYMBOL = 24;
/**
* Character type Sc
* @stable ICU 2.1
*/
public static final int CURRENCY_SYMBOL = 25;
/**
* Character type Sk
* @stable ICU 2.1
*/
public static final int MODIFIER_SYMBOL = 26;
/**
* Character type So
* @stable ICU 2.1
*/
public static final int OTHER_SYMBOL = 27;
/**
* Character type Pi
* @see #INITIAL_QUOTE_PUNCTUATION
* @stable ICU 2.1
*/
public static final int INITIAL_PUNCTUATION = 28;
/**
* Character type Pi
* This name is compatible with java.lang.Character's name for this type.
* @see #INITIAL_PUNCTUATION
* @draft ICU 2.8
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final int INITIAL_QUOTE_PUNCTUATION = 28;
/**
* Character type Pf
* @see #FINAL_QUOTE_PUNCTUATION
* @stable ICU 2.1
*/
public static final int FINAL_PUNCTUATION = 29;
/**
* Character type Pf
* This name is compatible with java.lang.Character's name for this type.
* @see #FINAL_PUNCTUATION
* @draft ICU 2.8
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final int FINAL_QUOTE_PUNCTUATION = 29;
/**
* Character type count
* @stable ICU 2.1
*/
public static final int CHAR_CATEGORY_COUNT = 30;
}
/**
* 'Enum' for the CharacterDirection constants. There are two sets
* of names, those used in ICU, and those used in the JDK. The
* JDK constants are compatible in name <b>but not in value</b>
* with those defined in <code>java.lang.Character</code>.
* @see UCharacterDirection
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static interface ECharacterDirection {
/**
* Directional type L
* @stable ICU 2.1
*/
public static final int LEFT_TO_RIGHT = 0;
/**
* JDK-compatible synonum for LEFT_TO_RIGHT.
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = (byte)LEFT_TO_RIGHT;
/**
* Directional type R
* @stable ICU 2.1
*/
public static final int RIGHT_TO_LEFT = 1;
/**
* JDK-compatible synonum for RIGHT_TO_LEFT.
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final byte DIRECTIONALITY_RIGHT_TO_LEFT = (byte)RIGHT_TO_LEFT;
/**
* Directional type EN
* @stable ICU 2.1
*/
public static final int EUROPEAN_NUMBER = 2;
/**
* JDK-compatible synonum for EUROPEAN_NUMBER.
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final byte DIRECTIONALITY_EUROPEAN_NUMBER = (byte)EUROPEAN_NUMBER;
/**
* Directional type ES
* @stable ICU 2.1
*/
public static final int EUROPEAN_NUMBER_SEPARATOR = 3;
/**
* JDK-compatible synonum for EUROPEAN_NUMBER_SEPARATOR.
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR = (byte)EUROPEAN_NUMBER_SEPARATOR;
/**
* Directional type ET
* @stable ICU 2.1
*/
public static final int EUROPEAN_NUMBER_TERMINATOR = 4;
/**
* JDK-compatible synonum for EUROPEAN_NUMBER_TERMINATOR.
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR = (byte)EUROPEAN_NUMBER_TERMINATOR;
/**
* Directional type AN
* @stable ICU 2.1
*/
public static final int ARABIC_NUMBER = 5;
/**
* JDK-compatible synonum for ARABIC_NUMBER.
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final byte DIRECTIONALITY_ARABIC_NUMBER = (byte)ARABIC_NUMBER;
/**
* Directional type CS
* @stable ICU 2.1
*/
public static final int COMMON_NUMBER_SEPARATOR = 6;
/**
* JDK-compatible synonum for COMMON_NUMBER_SEPARATOR.
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final byte DIRECTIONALITY_COMMON_NUMBER_SEPARATOR = (byte)COMMON_NUMBER_SEPARATOR;
/**
* Directional type B
* @stable ICU 2.1
*/
public static final int BLOCK_SEPARATOR = 7;
/**
* JDK-compatible synonum for BLOCK_SEPARATOR.
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final byte DIRECTIONALITY_PARAGRAPH_SEPARATOR = (byte)BLOCK_SEPARATOR;
/**
* Directional type S
* @stable ICU 2.1
*/
public static final int SEGMENT_SEPARATOR = 8;
/**
* JDK-compatible synonum for SEGMENT_SEPARATOR.
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final byte DIRECTIONALITY_SEGMENT_SEPARATOR = (byte)SEGMENT_SEPARATOR;
/**
* Directional type WS
* @stable ICU 2.1
*/
public static final int WHITE_SPACE_NEUTRAL = 9;
/**
* JDK-compatible synonum for WHITE_SPACE_NEUTRAL.
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final byte DIRECTIONALITY_WHITESPACE = (byte)WHITE_SPACE_NEUTRAL;
/**
* Directional type ON
* @stable ICU 2.1
*/
public static final int OTHER_NEUTRAL = 10;
/**
* JDK-compatible synonum for OTHER_NEUTRAL.
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final byte DIRECTIONALITY_OTHER_NEUTRALS = (byte)OTHER_NEUTRAL;
/**
* Directional type LRE
* @stable ICU 2.1
*/
public static final int LEFT_TO_RIGHT_EMBEDDING = 11;
/**
* JDK-compatible synonum for LEFT_TO_RIGHT_EMBEDDING.
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING = (byte)LEFT_TO_RIGHT_EMBEDDING;
/**
* Directional type LRO
* @stable ICU 2.1
*/
public static final int LEFT_TO_RIGHT_OVERRIDE = 12;
/**
* JDK-compatible synonum for LEFT_TO_RIGHT_OVERRIDE.
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE = (byte)LEFT_TO_RIGHT_OVERRIDE;
/**
* Directional type AL
* @stable ICU 2.1
*/
public static final int RIGHT_TO_LEFT_ARABIC = 13;
/**
* JDK-compatible synonum for RIGHT_TO_LEFT_ARABIC.
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC = (byte)RIGHT_TO_LEFT_ARABIC;
/**
* Directional type RLE
* @stable ICU 2.1
*/
public static final int RIGHT_TO_LEFT_EMBEDDING = 14;
/**
* JDK-compatible synonum for RIGHT_TO_LEFT_EMBEDDING.
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = (byte)RIGHT_TO_LEFT_EMBEDDING;
/**
* Directional type RLO
* @stable ICU 2.1
*/
public static final int RIGHT_TO_LEFT_OVERRIDE = 15;
/**
* JDK-compatible synonum for RIGHT_TO_LEFT_OVERRIDE.
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = (byte)RIGHT_TO_LEFT_OVERRIDE;
/**
* Directional type PDF
* @stable ICU 2.1
*/
public static final int POP_DIRECTIONAL_FORMAT = 16;
/**
* JDK-compatible synonum for POP_DIRECTIONAL_FORMAT.
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = (byte)POP_DIRECTIONAL_FORMAT;
/**
* Directional type NSM
* @stable ICU 2.1
*/
public static final int DIR_NON_SPACING_MARK = 17;
/**
* JDK-compatible synonum for DIR_NON_SPACING_MARK.
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final byte DIRECTIONALITY_NON_SPACING_MARK = (byte)DIR_NON_SPACING_MARK;
/**
* Directional type BN
* @stable ICU 2.1
*/
public static final int BOUNDARY_NEUTRAL = 18;
/**
* JDK-compatible synonum for BOUNDARY_NEUTRAL.
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final byte DIRECTIONALITY_BOUNDARY_NEUTRAL = (byte)BOUNDARY_NEUTRAL;
/**
* Number of directional types
* @stable ICU 2.1
*/
public static final int CHAR_DIRECTION_COUNT = 19;
/**
* Undefined bidirectional character type. Undefined <code>char</code>
* values have undefined directionality in the Unicode specification.
* @draft ICU 3.0
* @deprecated This is a draft API and might change in a future release of ICU.
*/
@Deprecated
public static final byte DIRECTIONALITY_UNDEFINED = -1;
}
}

BIN
src/java.base/share/classes/sun/net/idn/uidna.spp Normal file
View file

Binary file not shown.