mirror of
https://github.com/unicode-org/icu.git
synced 2025-04-14 17:24:01 +00:00
ICU-8874 Modified TestCompareReferenceImpl to do the same tests with ICU4C corresponding test case. Fixed problems in IDNAReference, which was obviously out of date. Restored toUnicode tests in TestErrorCases (but still excluding ASCII only error cases).
X-SVN-Rev: 30805
This commit is contained in:
Yoshito Umaoka
parent
d683b867bf
commit
cd49cad3f7
3 changed files with 128 additions and 144 deletions
|
|
@ -1,6 +1,6 @@
|
|||
/*
|
||||
*******************************************************************************
|
||||
* Copyright (C) 2003-2010, International Business Machines Corporation and *
|
||||
* Copyright (C) 2003-2011, International Business Machines Corporation and *
|
||||
* others. All Rights Reserved. *
|
||||
*******************************************************************************
|
||||
*/
|
||||
|
|
@ -276,96 +276,68 @@ public class IDNAReference {
|
|||
public static StringBuffer convertToUnicode(UCharacterIterator iter, int options)
|
||||
throws StringPrepParseException{
|
||||
|
||||
char[] caseFlags = null;
|
||||
|
||||
//get the options
|
||||
boolean useSTD3ASCIIRules = ((options & USE_STD3_RULES) != 0);
|
||||
|
||||
// the source contains all ascii codepoints
|
||||
boolean srcIsASCII = true;
|
||||
// assume the source contains all LDH codepoints
|
||||
boolean srcIsLDH = true;
|
||||
|
||||
int failPos = -1;
|
||||
boolean srcIsASCII = true;
|
||||
|
||||
int ch;
|
||||
int saveIndex = iter.getIndex();
|
||||
// step 1: find out if all the codepoints in src are ASCII
|
||||
while((ch=iter.next())!= UCharacterIterator.DONE){
|
||||
if(ch>0x7F){
|
||||
// step 1: find out if all the codepoints in src are ASCII
|
||||
while ((ch = iter.next()) != UCharacterIterator.DONE) {
|
||||
if (ch > 0x7F) {
|
||||
srcIsASCII = false;
|
||||
}else if(isLDHChar(ch)==false){
|
||||
failPos = iter.getIndex();
|
||||
srcIsLDH = false;
|
||||
break;
|
||||
}
|
||||
}
|
||||
StringBuffer processOut;
|
||||
|
||||
if(srcIsASCII == false){
|
||||
// step 2: process the string
|
||||
iter.setIndex(saveIndex);
|
||||
processOut = transform.prepare(iter,options);
|
||||
|
||||
}else{
|
||||
//just point to source
|
||||
processOut = new StringBuffer(iter.getText());
|
||||
}
|
||||
// TODO:
|
||||
// The RFC states that
|
||||
// The RFC states that
|
||||
// <quote>
|
||||
// ToUnicode never fails. If any step fails, then the original input
|
||||
// is returned immediately in that step.
|
||||
// </quote>
|
||||
|
||||
//step 3: verify ACE Prefix
|
||||
if(startsWithPrefix(processOut)){
|
||||
|
||||
//step 4: Remove the ACE Prefix
|
||||
String temp = processOut.substring(ACE_PREFIX_LENGTH,processOut.length());
|
||||
|
||||
//step 5: Decode using punycode
|
||||
StringBuffer decodeOut = PunycodeReference.decode(new StringBuffer(temp),caseFlags);
|
||||
|
||||
//step 6:Apply toASCII
|
||||
StringBuffer toASCIIOut = convertToASCII(decodeOut, options);
|
||||
|
||||
//step 7: verify
|
||||
if(compareCaseInsensitiveASCII(processOut, toASCIIOut) !=0){
|
||||
throw new StringPrepParseException("The verification step prescribed by the RFC 3491 failed",
|
||||
StringPrepParseException.VERIFICATION_ERROR);
|
||||
}
|
||||
|
||||
//step 8: return output of step 5
|
||||
return decodeOut;
|
||||
|
||||
}else{
|
||||
// verify that STD3 ASCII rules are satisfied
|
||||
if(useSTD3ASCIIRules == true){
|
||||
if( srcIsLDH == false /* source contains some non-LDH characters */
|
||||
|| processOut.charAt(0) == HYPHEN
|
||||
|| processOut.charAt(processOut.length()-1) == HYPHEN){
|
||||
|
||||
if(srcIsLDH==false){
|
||||
throw new StringPrepParseException("The input does not conform to the STD 3 ASCII rules",
|
||||
StringPrepParseException.STD3_ASCII_RULES_ERROR,processOut.toString(),
|
||||
(failPos>0) ? (failPos-1) : failPos);
|
||||
}else if(processOut.charAt(0) == HYPHEN){
|
||||
throw new StringPrepParseException("The input does not conform to the STD 3 ASCII rules",
|
||||
StringPrepParseException.STD3_ASCII_RULES_ERROR,
|
||||
processOut.toString(),0);
|
||||
|
||||
}else{
|
||||
throw new StringPrepParseException("The input does not conform to the STD 3 ASCII rules",
|
||||
StringPrepParseException.STD3_ASCII_RULES_ERROR,
|
||||
processOut.toString(),
|
||||
processOut.length());
|
||||
|
||||
}
|
||||
}
|
||||
do {
|
||||
StringBuffer processOut;
|
||||
if (srcIsASCII == false) {
|
||||
// step 2: process the string
|
||||
iter.setIndex(saveIndex);
|
||||
try {
|
||||
processOut = transform.prepare(iter, options);
|
||||
} catch (StringPrepParseException e) {
|
||||
break;
|
||||
}
|
||||
} else {
|
||||
// just point to source
|
||||
processOut = new StringBuffer(iter.getText());
|
||||
}
|
||||
// just return the source
|
||||
return new StringBuffer(iter.getText());
|
||||
}
|
||||
|
||||
// step 3: verify ACE Prefix
|
||||
if (startsWithPrefix(processOut)) {
|
||||
|
||||
// step 4: Remove the ACE Prefix
|
||||
String temp = processOut.substring(ACE_PREFIX_LENGTH, processOut.length());
|
||||
|
||||
// step 5: Decode using punycode
|
||||
StringBuffer decodeOut = null;
|
||||
try {
|
||||
decodeOut = PunycodeReference.decode(new StringBuffer(temp), null);
|
||||
} catch (StringPrepParseException e) {
|
||||
break;
|
||||
}
|
||||
|
||||
// step 6:Apply toASCII
|
||||
StringBuffer toASCIIOut = convertToASCII(decodeOut, options);
|
||||
|
||||
// step 7: verify
|
||||
if (compareCaseInsensitiveASCII(processOut, toASCIIOut) != 0) {
|
||||
break;
|
||||
}
|
||||
// step 8: return output of step 5
|
||||
return decodeOut;
|
||||
}
|
||||
} while (false);
|
||||
|
||||
return new StringBuffer(iter.getText());
|
||||
}
|
||||
|
||||
public static StringBuffer convertIDNToUnicode(UCharacterIterator iter, int options)
|
||||
throws StringPrepParseException{
|
||||
return convertIDNToUnicode(iter.getText(), options);
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
/*
|
||||
*******************************************************************************
|
||||
* Copyright (C) 2003-2006, International Business Machines Corporation and *
|
||||
* Copyright (C) 2003-2011, International Business Machines Corporation and *
|
||||
* others. All Rights Reserved. *
|
||||
*******************************************************************************
|
||||
*/
|
||||
|
|
@ -380,7 +380,7 @@ public class TestData {
|
|||
},
|
||||
"www.-abcde.com",
|
||||
new StringPrepParseException("",StringPrepParseException.STD3_ASCII_RULES_ERROR),
|
||||
true, true, false
|
||||
true, false /* ToUnicode preserves casing for this case */, false
|
||||
),
|
||||
new ErrorCase( new char[] {
|
||||
0x0077, 0x0077, 0x0077, 0x002e, // www.
|
||||
|
|
@ -390,7 +390,7 @@ public class TestData {
|
|||
},
|
||||
"www.abcde-.com",
|
||||
new StringPrepParseException("",StringPrepParseException.STD3_ASCII_RULES_ERROR),
|
||||
true, true, false
|
||||
true, false /* ToUnicode preserves casing for this case */, false
|
||||
),
|
||||
new ErrorCase( new char[]{
|
||||
0x0077, 0x0077, 0x0077, 0x002e, // www.
|
||||
|
|
@ -400,7 +400,7 @@ public class TestData {
|
|||
},
|
||||
"www.abcde@.com",
|
||||
new StringPrepParseException("",StringPrepParseException.STD3_ASCII_RULES_ERROR),
|
||||
true, true, false
|
||||
true, false /* ToUnicode preserves casing for this case */, false
|
||||
),
|
||||
new ErrorCase( new char[]{
|
||||
0x0077, 0x0077, 0x0077, 0x002e, // www.
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
/*
|
||||
*******************************************************************************
|
||||
* Copyright (C) 2003-2010, International Business Machines Corporation and *
|
||||
* Copyright (C) 2003-2011, International Business Machines Corporation and *
|
||||
* others. All Rights Reserved. *
|
||||
*******************************************************************************
|
||||
*/
|
||||
|
|
@ -343,9 +343,8 @@ public class TestIDNA extends TestFmwk {
|
|||
}else{
|
||||
doTestIDNToASCII(new String(errCase.unicode),errCase.ascii,IDNA.USE_STD3_RULES,errCase.expected);
|
||||
}
|
||||
|
||||
//TestToUnicode
|
||||
if(false && errCase.testToUnicode==true){
|
||||
if(errCase.testToUnicode==true){
|
||||
if(errCase.useSTD3ASCIIRules!=true){
|
||||
// Test IDNToUnicode
|
||||
doTestIDNToUnicode(errCase.ascii,new String(errCase.unicode),IDNA.DEFAULT,errCase.expected);
|
||||
|
|
@ -635,76 +634,89 @@ public class TestIDNA extends TestFmwk {
|
|||
doTestCompareReferenceImpl(source);
|
||||
doTestToASCII(source.toString(),expected.toString(), IDNA.DEFAULT, null);
|
||||
}
|
||||
private void doTestCompareReferenceImpl(StringBuffer src) throws Exception{
|
||||
|
||||
StringBuffer label = src;
|
||||
|
||||
StringPrepParseException expected = null;
|
||||
StringBuffer ascii = null;
|
||||
int options = IDNA.DEFAULT;
|
||||
logln("Comparing idnaref_toASCII with uidna_toASCII for input: " + prettify(label));
|
||||
try{
|
||||
ascii = IDNAReference.convertToASCII(label, options);
|
||||
}catch( StringPrepParseException e){
|
||||
expected = e;
|
||||
if(e.equals(unassignedException)){
|
||||
options = IDNA.ALLOW_UNASSIGNED;
|
||||
expected = null;
|
||||
try{
|
||||
ascii = IDNAReference.convertToASCII(label, options);
|
||||
}catch( StringPrepParseException ex){
|
||||
expected = ex;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
doTestToASCII(label.toString(),
|
||||
(ascii == null) ? null : ascii.toString(),
|
||||
options,
|
||||
expected);
|
||||
private StringBuffer _doTestCompareReferenceImpl(StringBuffer src, boolean toASCII, int options) {
|
||||
String refIDNAName = toASCII ? "IDNAReference.convertToASCII" : "IDNAReference.convertToUnicode";
|
||||
String uIDNAName = toASCII ? "IDNA.convertToASCII" : "IDNA.convertToUnicode";
|
||||
|
||||
logln("Comparing idnaref_toUnicode with uidna_toUnicode for input: " + prettify(label));
|
||||
StringBuffer uni =null;
|
||||
|
||||
if(expected == null){
|
||||
options = IDNA.DEFAULT;
|
||||
try{
|
||||
uni = IDNAReference.convertToUnicode(ascii, options);
|
||||
}catch( StringPrepParseException e ){
|
||||
expected = e;
|
||||
if(expected.equals(unassignedException)){
|
||||
options = IDNA.ALLOW_UNASSIGNED;
|
||||
expected = null;
|
||||
try{
|
||||
uni = IDNAReference.convertToUnicode(ascii, options);
|
||||
}catch(StringPrepParseException ex){
|
||||
expected = ex;
|
||||
}
|
||||
}
|
||||
}
|
||||
doTestToUnicode(ascii.toString(),
|
||||
(uni==null)? null : uni.toString(),
|
||||
options,
|
||||
expected);
|
||||
logln("Comparing " + refIDNAName + " with " + uIDNAName + " for input: "
|
||||
+ prettify(src) + " with options: " + options);
|
||||
|
||||
StringBuffer exp = null;
|
||||
int expStatus = -1;
|
||||
try {
|
||||
exp = toASCII ? IDNAReference.convertToASCII(src, options) : IDNAReference.convertToUnicode(src, options);
|
||||
} catch (StringPrepParseException e) {
|
||||
expStatus = e.getError();
|
||||
}
|
||||
|
||||
StringBuffer got = null;
|
||||
int gotStatus = -1;
|
||||
try {
|
||||
got = toASCII ? IDNA.convertToASCII(src, options) : IDNA.convertToUnicode(src, options);
|
||||
} catch (StringPrepParseException e) {
|
||||
gotStatus = e.getError();
|
||||
}
|
||||
|
||||
if (expStatus != gotStatus) {
|
||||
errln("Did not get the expected status while comparing " + refIDNAName + " with " + uIDNAName
|
||||
+ " Expected: " + expStatus
|
||||
+ " Got: " + gotStatus
|
||||
+ " for Source: "+ prettify(src)
|
||||
+ " Options: " + options);
|
||||
} else {
|
||||
// now we know that both implementation yielded same status
|
||||
if (gotStatus == -1) {
|
||||
// compare the outputs
|
||||
if (!got.toString().equals(exp.toString())) {
|
||||
errln("Did not get the expected output while comparing " + refIDNAName + " with " + uIDNAName
|
||||
+ " Expected: " + exp
|
||||
+ " Got: " + got
|
||||
+ " for Source: "+ prettify(src)
|
||||
+ " Options: " + options);
|
||||
}
|
||||
} else {
|
||||
logln("Got the same error while comparing " + refIDNAName + " with " + uIDNAName
|
||||
+" for input: " + prettify(src) + " with options: " + options);
|
||||
}
|
||||
}
|
||||
|
||||
return exp;
|
||||
}
|
||||
public void TestCompareRefImpl() throws Exception{
|
||||
|
||||
for(int i = 0x40000 ; i< 0x10ffff; i++){
|
||||
|
||||
private void doTestCompareReferenceImpl(StringBuffer src) throws Exception{
|
||||
// test toASCII
|
||||
src.setLength(0);
|
||||
src.append("[");
|
||||
StringBuffer asciiLabel = _doTestCompareReferenceImpl(src, true, IDNA.ALLOW_UNASSIGNED);
|
||||
_doTestCompareReferenceImpl(src, true, IDNA.DEFAULT);
|
||||
_doTestCompareReferenceImpl(src, true, IDNA.USE_STD3_RULES);
|
||||
_doTestCompareReferenceImpl(src, true, IDNA.USE_STD3_RULES | IDNA.ALLOW_UNASSIGNED);
|
||||
|
||||
if (asciiLabel != null) {
|
||||
// test toUnicode
|
||||
_doTestCompareReferenceImpl(src, false, IDNA.ALLOW_UNASSIGNED);
|
||||
_doTestCompareReferenceImpl(src, false, IDNA.DEFAULT);
|
||||
_doTestCompareReferenceImpl(src, false, IDNA.USE_STD3_RULES);
|
||||
_doTestCompareReferenceImpl(src, false, IDNA.USE_STD3_RULES | IDNA.ALLOW_UNASSIGNED);
|
||||
}
|
||||
}
|
||||
|
||||
public void TestCompareRefImpl() throws Exception {
|
||||
for (int i = 65; i < 0x10FFFF; i++) {
|
||||
StringBuffer src = new StringBuffer();
|
||||
|
||||
if(isQuick()==true && i> 0x1FFFF){
|
||||
if (isQuick() == true && i > 0x0FFF) {
|
||||
return;
|
||||
}
|
||||
if(i >= 0x30000 && i<=0xf0000){
|
||||
i+=0xB0000;
|
||||
if (i == 0x30000) {
|
||||
// jump to E0000, no characters assigned in plain 3 to plain 13 as of Unicode 6.0
|
||||
i = 0xE0000;
|
||||
}
|
||||
UTF16.append(src,i);
|
||||
UTF16.append(src, i);
|
||||
doTestCompareReferenceImpl(src);
|
||||
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
public void TestJB4490(){
|
||||
String[] in = new String[]{
|
||||
"\u00F5\u00dE\u00dF\u00dD",
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue