mirror of
https://github.com/unicode-org/icu.git
synced 2025-04-10 07:39:16 +00:00
ICU-0 security tools
X-SVN-Rev: 18133
This commit is contained in:
Mark Davis
parent
b79aaf70aa
commit
ed99ae9728
2 changed files with 325 additions and 85 deletions
tools/unicodetools/com/ibm/text/UCD
|
|
@ -5,8 +5,8 @@
|
|||
*******************************************************************************
|
||||
*
|
||||
* $Source: /xsrl/Nsvn/icu/unicodetools/com/ibm/text/UCD/GenerateConfusables.java,v $
|
||||
* $Date: 2005/07/01 22:10:00 $
|
||||
* $Revision: 1.4 $
|
||||
* $Date: 2005/07/02 01:42:51 $
|
||||
* $Revision: 1.5 $
|
||||
*
|
||||
*******************************************************************************
|
||||
*/
|
||||
|
|
@ -87,7 +87,34 @@ public class GenerateConfusables {
|
|||
um.put(0x34E4, "2.1");
|
||||
um.put(0x3007, "2.1");
|
||||
_Non_IICore.removeAll(um.getSet("2.1"));
|
||||
|
||||
// add Chinese?
|
||||
UnicodeSet cjk_nic = new UnicodeSet();
|
||||
String line = null;
|
||||
try {
|
||||
BufferedReader br = BagFormatter.openUTF8Reader(indir, "cjk_nic.txt");
|
||||
while (true) {
|
||||
line = Utility.readDataLine(br);
|
||||
if (line == null) break;
|
||||
if (line.length() == 0) continue;
|
||||
String[] pieces = Utility.split(line, ';');
|
||||
// part 0 is range
|
||||
String range = pieces[0].trim();
|
||||
int rangeDivider = range.indexOf("..");
|
||||
int start, end;
|
||||
if (rangeDivider < 0) {
|
||||
start = end = Integer.parseInt(range, 16);
|
||||
} else {
|
||||
start = Integer.parseInt(range.substring(0, rangeDivider), 16);
|
||||
end = Integer.parseInt(range.substring(rangeDivider+2), 16);
|
||||
}
|
||||
cjk_nic.add(start, end);
|
||||
}
|
||||
br.close();
|
||||
} catch (Exception e) {
|
||||
throw (RuntimeException) new RuntimeException("Failure on line " + line).initCause(e);
|
||||
}
|
||||
_Non_IICore.removeAll(cjk_nic);
|
||||
}
|
||||
return _Non_IICore;
|
||||
// for (Iterator it = um.getAvailableValues().iterator(); it.hasNext();) {
|
||||
|
|
@ -401,8 +428,8 @@ public class GenerateConfusables {
|
|||
//reviews.putAll(UNASSIGNED, "");
|
||||
out.print("\uFEFF");
|
||||
out.println("# Review List for IDN");
|
||||
out.println("# $Revision: 1.4 $");
|
||||
out.println("# $Date: 2005/07/01 22:10:00 $");
|
||||
out.println("# $Revision: 1.5 $");
|
||||
out.println("# $Date: 2005/07/02 01:42:51 $");
|
||||
out.println("");
|
||||
|
||||
UnicodeSet fullSet = reviews.getSet("").complement();
|
||||
|
|
@ -457,8 +484,8 @@ public class GenerateConfusables {
|
|||
PrintWriter out = BagFormatter.openUTF8Writer(outdir, "idnchars.txt");
|
||||
|
||||
out.println("# Recommended Identifier Profiles for IDN");
|
||||
out.println("# $Revision: 1.4 $");
|
||||
out.println("# $Date: 2005/07/01 22:10:00 $");
|
||||
out.println("# $Revision: 1.5 $");
|
||||
out.println("# $Date: 2005/07/02 01:42:51 $");
|
||||
|
||||
out.println("");
|
||||
out.println("# Output Characters");
|
||||
|
|
@ -527,8 +554,8 @@ public class GenerateConfusables {
|
|||
"xidmodifications.txt");
|
||||
|
||||
out.println("# Security Profile for General Identifiers");
|
||||
out.println("# $Revision: 1.4 $");
|
||||
out.println("# $Date: 2005/07/01 22:10:00 $");
|
||||
out.println("# $Revision: 1.5 $");
|
||||
out.println("# $Date: 2005/07/02 01:42:51 $");
|
||||
out.println("");
|
||||
|
||||
out.println("# Characters restricted");
|
||||
|
|
@ -584,8 +611,8 @@ public class GenerateConfusables {
|
|||
//someRemovals = removals;
|
||||
out = BagFormatter.openUTF8Writer(outdir, "draft-restrictions.txt");
|
||||
out.println("# Characters restricted in domain names");
|
||||
out.println("# $Revision: 1.4 $");
|
||||
out.println("# $Date: 2005/07/01 22:10:00 $");
|
||||
out.println("# $Revision: 1.5 $");
|
||||
out.println("# $Date: 2005/07/02 01:42:51 $");
|
||||
out.println("#");
|
||||
out.println("# This file contains a draft list of characters for use in");
|
||||
out.println("# UTR #36: Unicode Security Considerations");
|
||||
|
|
@ -763,7 +790,7 @@ public class GenerateConfusables {
|
|||
/*
|
||||
* Returns UScript.INVALID_CODE if mixed script, otherwise the script
|
||||
*/
|
||||
private static int getSingleScript(String source) {
|
||||
public static int getSingleScript(String source) {
|
||||
int lastScript = UScript.INVALID_CODE;
|
||||
int cp;
|
||||
for (int i = 0; i < source.length(); i += UTF16.getCharCount(cp)) {
|
||||
|
|
@ -1119,8 +1146,8 @@ public class GenerateConfusables {
|
|||
public void writeSource(String directory, String filename) throws IOException {
|
||||
PrintWriter out = BagFormatter.openUTF8Writer(directory, filename);
|
||||
out.println("# Source File for IDN Confusables");
|
||||
out.println("# $Revision: 1.4 $");
|
||||
out.println("# $Date: 2005/07/01 22:10:00 $");
|
||||
out.println("# $Revision: 1.5 $");
|
||||
out.println("# $Date: 2005/07/02 01:42:51 $");
|
||||
out.println("");
|
||||
dataMixedAnycase.writeSource(out);
|
||||
out.close();
|
||||
|
|
@ -1130,8 +1157,8 @@ public class GenerateConfusables {
|
|||
PrintWriter out = BagFormatter.openUTF8Writer(directory, filename);
|
||||
out.print('\uFEFF');
|
||||
out.println("# Recommended confusable mapping for IDN");
|
||||
out.println("# $Revision: 1.4 $");
|
||||
out.println("# $Date: 2005/07/01 22:10:00 $");
|
||||
out.println("# $Revision: 1.5 $");
|
||||
out.println("# $Date: 2005/07/02 01:42:51 $");
|
||||
out.println("");
|
||||
|
||||
if (appendFile) {
|
||||
|
|
@ -1339,8 +1366,8 @@ public class GenerateConfusables {
|
|||
UnicodeSet representable = new UnicodeSet();
|
||||
out.print('\uFEFF');
|
||||
out.println("# Summary: Recommended confusable mapping for IDN");
|
||||
out.println("# $Revision: 1.4 $");
|
||||
out.println("# $Date: 2005/07/01 22:10:00 $");
|
||||
out.println("# $Revision: 1.5 $");
|
||||
out.println("# $Date: 2005/07/02 01:42:51 $");
|
||||
out.println("");
|
||||
MyEquivalenceClass data = dataMixedAnycase;
|
||||
Set items = data.getOrderedExplicitItems();
|
||||
|
|
@ -1446,8 +1473,8 @@ public class GenerateConfusables {
|
|||
PrintWriter out = BagFormatter.openUTF8Writer(outdir, filename);
|
||||
out.print('\uFEFF');
|
||||
out.println("# Summary: Whole-Script Confusables");
|
||||
out.println("# $Revision: 1.4 $");
|
||||
out.println("# $Date: 2005/07/01 22:10:00 $");
|
||||
out.println("# $Revision: 1.5 $");
|
||||
out.println("# $Date: 2005/07/02 01:42:51 $");
|
||||
out.println("");
|
||||
out.println("# Lowercase Only");
|
||||
out.println("");
|
||||
|
|
@ -1516,7 +1543,7 @@ public class GenerateConfusables {
|
|||
}
|
||||
}
|
||||
|
||||
static class UnicodeSetToScript {
|
||||
public static class UnicodeSetToScript {
|
||||
public int getScript() {
|
||||
return script;
|
||||
}
|
||||
|
|
@ -1535,8 +1562,8 @@ public class GenerateConfusables {
|
|||
private int script;
|
||||
}
|
||||
|
||||
UnicodeSetToScript[][] scriptToUnicodeSetToScript;
|
||||
UnicodeSet[] fastReject;
|
||||
UnicodeSetToScript[][] scriptToUnicodeSetToScript = new UnicodeSetToScript[UScript.CODE_LIMIT][];
|
||||
UnicodeSet[] fastReject = new UnicodeSet[UScript.CODE_LIMIT];
|
||||
boolean finished = false;
|
||||
|
||||
void finish() {
|
||||
|
|
@ -1562,15 +1589,13 @@ public class GenerateConfusables {
|
|||
}
|
||||
|
||||
void write(PrintWriter out) throws IOException {
|
||||
finish();
|
||||
for (int j = 0; j < UScript.CODE_LIMIT; ++j) {
|
||||
if (j == UScript.COMMON || j == UScript.INHERITED) continue;
|
||||
if (script_representables[j].size() == 0) continue;
|
||||
for (int k = 0; k < UScript.CODE_LIMIT; ++k) {
|
||||
if (k == UScript.COMMON || k == UScript.INHERITED) continue;
|
||||
if (script_representables[k].size() == 0) continue;
|
||||
|
||||
if (script_set[j].containsNone(script_representables[k])) continue;
|
||||
UnicodeSet items = new UnicodeSet(script_set[j]).retainAll(script_representables[k]);
|
||||
if (scriptToUnicodeSetToScript[j] == null) continue;
|
||||
for (int q = 0; q < scriptToUnicodeSetToScript[j].length; ++q) {
|
||||
UnicodeSetToScript uss = scriptToUnicodeSetToScript[j][q];
|
||||
int k = uss.getScript();
|
||||
UnicodeSet items = uss.getSet();
|
||||
String sname = UScript.getShortName(j) + "; " + UScript.getShortName(k) + "; " + label;
|
||||
String name = UScript.getName(j) + "; " + UScript.getName(k);
|
||||
out.println("# " + name + ": " + items.toPattern(false));
|
||||
|
|
@ -1581,61 +1606,6 @@ public class GenerateConfusables {
|
|||
}
|
||||
}
|
||||
}
|
||||
/*
|
||||
* for this routine, we don't care what the targetScripts are,
|
||||
* just whether there is at least one whole-script confusable.
|
||||
*/
|
||||
boolean hasWholeScriptConfusable(String givenString, BitSet resultingScripts) {
|
||||
int givenScript = getSingleScript(givenString);
|
||||
if (givenScript == UScript.INVALID_CODE) {
|
||||
throw new IllegalArgumentException("Not single script string");
|
||||
}
|
||||
UnicodeSet givenSet = new UnicodeSet()
|
||||
.addAll(givenString)
|
||||
.removeAll(commonAndInherited);
|
||||
return hasWholeScriptConfusable(givenScript, givenSet, resultingScripts);
|
||||
}
|
||||
|
||||
/**
|
||||
*
|
||||
*/
|
||||
private boolean hasWholeScriptConfusable(int givenScript, UnicodeSet givenSet, BitSet resultingScripts) {
|
||||
resultingScripts.clear();
|
||||
if (fastReject[givenScript].containsSome(givenSet)) return false;
|
||||
UnicodeSetToScript[] possibles = scriptToUnicodeSetToScript[givenScript];
|
||||
for (int i = 0; i < possibles.length; ++i) {
|
||||
if (possibles[i].set.containsAll(givenSet)) {
|
||||
resultingScripts.set(possibles[i].script);
|
||||
}
|
||||
}
|
||||
return resultingScripts.isEmpty();
|
||||
}
|
||||
/*
|
||||
* for this routine, we don't care what the targetScripts are,
|
||||
* just whether there is at least one whole-script confusable.
|
||||
*/
|
||||
boolean hasMixedScriptConfusable(String givenString) {
|
||||
// UnicodeSet givenSet = new UnicodeSet()
|
||||
// .addAll(givenString)
|
||||
// .removeAll(commonAndInherited);
|
||||
// BitSet givenScripts = getScriptsIn(givenString);
|
||||
// for (int i = 0; i < givenScripts.length(); ++i) {
|
||||
// ;
|
||||
// }
|
||||
// UnicodeSet givenSet = new UnicodeSet()
|
||||
// .addAll(givenString)
|
||||
// .removeAll(commonAndInherited);
|
||||
// resultingScripts.clear();
|
||||
// if (fastReject[givenScript].containsSome(givenSet)) return false;
|
||||
// UnicodeSetToScript[] possibles = scriptToUnicodeSets[givenScript];
|
||||
// for (int i = 0; i < possibles.length; ++i) {
|
||||
// if (possibles[i].set.containsAll(givenSet)) {
|
||||
// resultingScripts.set(possibles[i].script);
|
||||
// }
|
||||
// }
|
||||
// return resultingScripts.isEmpty();
|
||||
return true;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
|
|
|||
270
tools/unicodetools/com/ibm/text/UCD/TestIdentifiers.java
Normal file
270
tools/unicodetools/com/ibm/text/UCD/TestIdentifiers.java
Normal file
|
|
@ -0,0 +1,270 @@
|
|||
package com.ibm.text.UCD;
|
||||
|
||||
import java.io.BufferedReader;
|
||||
import java.io.IOException;
|
||||
import java.util.ArrayList;
|
||||
import java.util.BitSet;
|
||||
import java.util.List;
|
||||
|
||||
import com.ibm.icu.dev.test.util.BagFormatter;
|
||||
import com.ibm.icu.lang.UScript;
|
||||
import com.ibm.icu.text.UTF16;
|
||||
import com.ibm.icu.text.UnicodeSet;
|
||||
import com.ibm.icu.text.UnicodeSetIterator;
|
||||
import com.ibm.text.utility.Utility;
|
||||
import com.ibm.icu.lang.UCharacter;
|
||||
|
||||
public class TestIdentifiers {
|
||||
|
||||
public static void main(String[] args) throws IOException {
|
||||
String[] tests = { "MOPE", "VOP", "scope", "ibm", "vop", "toys-я-us", "1iνе", "back" };
|
||||
TestIdentifiers ti = new TestIdentifiers("L");
|
||||
TestIdentifiers tiany = new TestIdentifiers("A");
|
||||
for (int i = 0; i < tests.length; ++i) {
|
||||
System.out.print(tests[i]);
|
||||
ti.testItem(tests[i]);
|
||||
String folded = UCharacter.foldCase(tests[i], true);
|
||||
if (!folded.equals(tests[i])) {
|
||||
System.out.print("\t");
|
||||
tiany.testItem(tests[i]);
|
||||
System.out.print(folded);
|
||||
ti.testItem(folded);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
void testItem(String test) {
|
||||
BitSet scripts = new BitSet();
|
||||
System.out.print("\t" + caseType + "\t");
|
||||
boolean foundProblem = false;
|
||||
if (hasWholeScriptConfusable(test, scripts)) {
|
||||
System.out.print("whole-script confusables: ");
|
||||
for (int j = 0; j < scripts.length(); ++j) {
|
||||
if (scripts.get(j))
|
||||
System.out.print(UScript.getName(j) + " ");
|
||||
}
|
||||
System.out.println();
|
||||
foundProblem = true;
|
||||
}
|
||||
if (hasMixedScriptConfusable(test)) {
|
||||
System.out.println("mixed-script confusable");
|
||||
foundProblem = true;
|
||||
}
|
||||
if (!foundProblem) {
|
||||
System.out.println("no confusable");
|
||||
}
|
||||
}
|
||||
|
||||
private static final String indir = "C:\\Unicode-CVS2\\draft\\reports\\tr36\\data\\";
|
||||
|
||||
private static UnicodeSet commonAndInherited = new UnicodeSet(
|
||||
"[[:script=common:][:script=inherited:]]");
|
||||
|
||||
private static UnicodeSet XIDContinueSet = new UnicodeSet("[:xidcontinue:]")
|
||||
.add('-');
|
||||
|
||||
private static final boolean DEBUG = false;
|
||||
private String caseType;
|
||||
|
||||
TestIdentifiers(String caseType) throws IOException {
|
||||
this.caseType = caseType;
|
||||
loadFile(caseType);
|
||||
}
|
||||
|
||||
private static class UnicodeSetToScript {
|
||||
public int getScript() {
|
||||
return script;
|
||||
}
|
||||
|
||||
public UnicodeSetToScript setScript(int script) {
|
||||
this.script = script;
|
||||
return this;
|
||||
}
|
||||
|
||||
public UnicodeSet getSet() {
|
||||
return set;
|
||||
}
|
||||
|
||||
public UnicodeSetToScript setSet(UnicodeSet set) {
|
||||
this.set = set;
|
||||
return this;
|
||||
}
|
||||
|
||||
private UnicodeSet set;
|
||||
|
||||
private int script;
|
||||
}
|
||||
|
||||
UnicodeSetToScript[][] scriptToUnicodeSetToScript = new UnicodeSetToScript[UScript.CODE_LIMIT][];
|
||||
UnicodeSet[] fastReject = new UnicodeSet[UScript.CODE_LIMIT];
|
||||
|
||||
void loadFile(String filterType) throws IOException {
|
||||
UnicodeSet[][] script_script_set = new UnicodeSet[UScript.CODE_LIMIT][UScript.CODE_LIMIT];
|
||||
for (int i = 0; i < UScript.CODE_LIMIT; ++i) {
|
||||
script_script_set[i] = new UnicodeSet[UScript.CODE_LIMIT];
|
||||
}
|
||||
BufferedReader br = BagFormatter.openUTF8Reader(indir,
|
||||
"confusablesWholeScript.txt");
|
||||
String line = null;
|
||||
try {
|
||||
while (true) {
|
||||
line = Utility.readDataLine(br);
|
||||
if (line == null)
|
||||
break;
|
||||
if (line.length() == 0)
|
||||
continue;
|
||||
String[] pieces = Utility.split(line, ';');
|
||||
// part 0 is range
|
||||
String range = pieces[0].trim();
|
||||
int rangeDivider = range.indexOf("..");
|
||||
int start, end;
|
||||
if (rangeDivider < 0) {
|
||||
start = end = Integer.parseInt(range, 16);
|
||||
} else {
|
||||
start = Integer.parseInt(range.substring(0, rangeDivider),
|
||||
16);
|
||||
end = Integer.parseInt(range.substring(rangeDivider + 2),
|
||||
16);
|
||||
}
|
||||
// part 1 is script1
|
||||
int script1 = UScript.getCodeFromName(pieces[1].trim());
|
||||
// part 2 is script2
|
||||
int script2 = UScript.getCodeFromName(pieces[2].trim());
|
||||
String type = pieces[3].trim();
|
||||
if (!type.equals(filterType))
|
||||
continue;
|
||||
if (script_script_set[script1][script2] == null) {
|
||||
script_script_set[script1][script2] = new UnicodeSet();
|
||||
}
|
||||
script_script_set[script1][script2].add(start, end);
|
||||
}
|
||||
for (int i = 0; i < script_script_set.length; ++i) {
|
||||
UnicodeSet accept = new UnicodeSet();
|
||||
List curr = new ArrayList();
|
||||
for (int j = 0; j < script_script_set[i].length; ++j) {
|
||||
if (script_script_set[i][j] == null)
|
||||
continue;
|
||||
accept.addAll(script_script_set[i][j]);
|
||||
curr.add(new UnicodeSetToScript().setScript(j).setSet(
|
||||
script_script_set[i][j]));
|
||||
if (DEBUG && i == UScript.LATIN)
|
||||
System.out.println(UScript.getName(i) + "; "
|
||||
+ UScript.getName(j) + "; "
|
||||
+ script_script_set[i][j]);
|
||||
}
|
||||
if (curr.size() == 0)
|
||||
continue;
|
||||
scriptToUnicodeSetToScript[i] = (UnicodeSetToScript[]) curr
|
||||
.toArray(new UnicodeSetToScript[curr.size()]);
|
||||
fastReject[i] = accept.complement();
|
||||
if (DEBUG && i == UScript.LATIN)
|
||||
System.out.println(UScript.getName(i) + "; "
|
||||
+ fastReject[i]);
|
||||
}
|
||||
} catch (Exception e) {
|
||||
throw (RuntimeException) new RuntimeException("Failure on line "
|
||||
+ line).initCause(e);
|
||||
}
|
||||
br.close();
|
||||
}
|
||||
|
||||
/*
|
||||
* for this routine, we don't care what the targetScripts are, just whether
|
||||
* there is at least one whole-script confusable.
|
||||
*/
|
||||
boolean hasWholeScriptConfusable(String givenString, BitSet resultingScripts) {
|
||||
int givenScript = getSingleScript(givenString);
|
||||
if (givenScript == UScript.INVALID_CODE)
|
||||
return false;
|
||||
UnicodeSet givenSet = new UnicodeSet().addAll(givenString).removeAll(
|
||||
commonAndInherited);
|
||||
return hasWholeScriptConfusable(givenScript, givenSet, resultingScripts);
|
||||
}
|
||||
|
||||
/**
|
||||
*
|
||||
*/
|
||||
private boolean hasWholeScriptConfusable(int givenScript,
|
||||
UnicodeSet givenSet, BitSet resultingScripts) {
|
||||
resultingScripts.clear();
|
||||
if (fastReject[givenScript] == null)
|
||||
return false;
|
||||
if (fastReject[givenScript].containsSome(givenSet))
|
||||
return false;
|
||||
UnicodeSetToScript[] possibles = scriptToUnicodeSetToScript[givenScript];
|
||||
for (int i = 0; i < possibles.length; ++i) {
|
||||
if (possibles[i].set.containsAll(givenSet)) {
|
||||
resultingScripts.set(possibles[i].script);
|
||||
}
|
||||
}
|
||||
return !resultingScripts.isEmpty();
|
||||
}
|
||||
|
||||
/*
|
||||
* for this routine, we don't care what the targetScripts are, just
|
||||
* whether there is at least one whole-script confusable.
|
||||
*/
|
||||
boolean hasMixedScriptConfusable(String givenString) {
|
||||
UnicodeSet givenSet = new UnicodeSet().addAll(givenString).removeAll(
|
||||
commonAndInherited);
|
||||
UnicodeSet[] byScript = getScripts(givenSet);
|
||||
BitSet wholeScripts = new BitSet();
|
||||
boolean result = false;
|
||||
main: for (int i = 0; i < byScript.length; ++i) {
|
||||
if (byScript[i] == null)
|
||||
continue;
|
||||
// see if the other characters have whole script confusables in
|
||||
// my script
|
||||
for (int j = 0; j < byScript.length; ++j) {
|
||||
if (j == i || byScript[j] == null)
|
||||
continue;
|
||||
if (!hasWholeScriptConfusable(j, byScript[j], wholeScripts))
|
||||
continue main;
|
||||
if (!wholeScripts.get(i))
|
||||
continue main; // doesn't have the
|
||||
// one we want
|
||||
result = true;
|
||||
}
|
||||
return result; // passed the guantlet
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
/*
|
||||
* Returns UScript.INVALID_CODE if mixed script, otherwise the script
|
||||
*/
|
||||
public static int getSingleScript(String source) {
|
||||
int lastScript = UScript.INVALID_CODE;
|
||||
int cp;
|
||||
for (int i = 0; i < source.length(); i += UTF16.getCharCount(cp)) {
|
||||
cp = UTF16.charAt(source, i);
|
||||
int script = UScript.getScript(cp);
|
||||
if (script == UScript.COMMON || script == UScript.INHERITED) {
|
||||
if (XIDContinueSet.contains(cp)) {
|
||||
if (lastScript == UScript.INVALID_CODE)
|
||||
lastScript = script;
|
||||
continue; // skip if not identifier
|
||||
}
|
||||
script = UScript.COMMON;
|
||||
}
|
||||
if (lastScript == UScript.INVALID_CODE)
|
||||
lastScript = script;
|
||||
else if (script != lastScript)
|
||||
return UScript.INVALID_CODE;
|
||||
}
|
||||
return lastScript;
|
||||
}
|
||||
|
||||
public static UnicodeSet[] getScripts(UnicodeSet sourceSet) {
|
||||
UnicodeSet[] byScript = new UnicodeSet[UScript.CODE_LIMIT];
|
||||
for (UnicodeSetIterator usi = new UnicodeSetIterator(sourceSet); usi
|
||||
.next();) {
|
||||
int script = UScript.getScript(usi.codepoint);
|
||||
if (byScript[script] == null)
|
||||
byScript[script] = new UnicodeSet();
|
||||
byScript[script].add(usi.codepoint);
|
||||
}
|
||||
return byScript;
|
||||
}
|
||||
|
||||
}
|
||||
Loading…
Add table
Reference in a new issue