Qortal/qortal
1
0
Fork 1
mirror of https://github.com/Qortal/qortal.git synced 2025-07-26 19:51:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

Unicode / NAME updates.

Browse Source 
Fix UPDATE_NAME not processing empty 'newName' transactions correctly.
Fix some emoji code-points not being processed correctly.
Updated tests.
Now included ICU4J v70.1 - WARNING: this could add around 10MB to JAR size!
Bumped homoglyph to v1.2.1.
This commit is contained in:
catbref
2022-03-14 08:45:32 +00:00
parent e63e39fe9a
commit e604a19bce
6 changed files with 120 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/main/java/org/qortal/data/transaction/UpdateNameTransactionData.java
View File

@@ -48,6 +48,7 @@ public class UpdateNameTransactionData extends TransactionData {
public void afterUnmarshal(Unmarshaller u, Object parent) {
this.creatorPublicKey = this.ownerPublicKey;
this.reducedNewName = this.newName != null ? Unicode.sanitize(this.newName) : null;
}
/** From repository */
@@ -62,7 +63,7 @@ public class UpdateNameTransactionData extends TransactionData {
this.nameReference = nameReference;
}
/** From network/API */
/** From network */
public UpdateNameTransactionData(BaseTransactionData baseTransactionData, String name, String newName, String newData) {
this(baseTransactionData, name, newName, newData, Unicode.sanitize(newName), null);
}

11
src/main/java/org/qortal/transaction/UpdateNameTransaction.java
View File

@@ -118,10 +118,13 @@ public class UpdateNameTransaction extends Transaction {
if (!owner.getAddress().equals(nameData.getOwner()))
return ValidationResult.INVALID_NAME_OWNER;
// Check new name isn't already taken, unless it is the same name (this allows for case-adjusting renames)
NameData newNameData = this.repository.getNameRepository().fromReducedName(this.updateNameTransactionData.getReducedNewName());
if (newNameData != null && !newNameData.getName().equals(nameData.getName()))
return ValidationResult.NAME_ALREADY_REGISTERED;
// Additional checks if transaction intends to change name
if (!this.updateNameTransactionData.getNewName().isEmpty()) {
// Check new name isn't already taken, unless it is the same name (this allows for case-adjusting renames)
NameData newNameData = this.repository.getNameRepository().fromReducedName(this.updateNameTransactionData.getReducedNewName());
if (newNameData != null && !newNameData.getName().equals(nameData.getName()))
return ValidationResult.NAME_ALREADY_REGISTERED;
}
return ValidationResult.OK;
}

17
src/main/java/org/qortal/utils/Unicode.java
View File

@@ -18,6 +18,9 @@ import java.util.TreeMap;
import com.google.common.base.CharMatcher;
import com.ibm.icu.text.CaseMap;
import com.ibm.icu.text.Normalizer2;
import com.ibm.icu.text.UnicodeSet;
import net.codebox.homoglyph.HomoglyphBuilder;
public abstract class Unicode {
@@ -31,6 +34,8 @@ public abstract class Unicode {
public static final String ZERO_WIDTH_NO_BREAK_SPACE = "\ufeff";
public static final CharMatcher ZERO_WIDTH_CHAR_MATCHER = CharMatcher.anyOf(ZERO_WIDTH_SPACE + ZERO_WIDTH_NON_JOINER + ZERO_WIDTH_JOINER + WORD_JOINER + ZERO_WIDTH_NO_BREAK_SPACE);
private static final UnicodeSet removableUniset = new UnicodeSet("[[:Mark:][:Other:]]").freeze();
private static int[] homoglyphCodePoints;
private static int[] reducedCodePoints;
@@ -59,7 +64,7 @@ public abstract class Unicode {
public static String normalize(String input) {
String output;
// Normalize
// Normalize using NFKC to recompose in canonical form
output = Normalizer.normalize(input, Form.NFKC);
// Remove zero-width code-points, used for rendering
@@ -91,8 +96,8 @@ public abstract class Unicode {
public static String sanitize(String input) {
String output;
// Normalize
output = Normalizer.normalize(input, Form.NFKD);
// Normalize using NFKD to decompose into individual combining code points
output = Normalizer2.getNFKDInstance().normalize(input);
// Remove zero-width code-points, used for rendering
output = removeZeroWidth(output);
@@ -100,11 +105,11 @@ public abstract class Unicode {
// Normalize whitespace
output = CharMatcher.whitespace().trimAndCollapseFrom(output, ' ');
// Remove accents, combining marks
output = output.replaceAll("[\\p{M}\\p{C}]", "");
// Remove accents, combining marks - see https://www.unicode.org/reports/tr44/#GC_Values_Table
output = removableUniset.stripFrom(output, true);
// Convert to lowercase
output = output.toLowerCase(Locale.ROOT);
output = CaseMap.toLower().apply(Locale.ROOT, output);
// Reduce homoglyphs
output = reduceHomoglyphs(output);