Skip to content

Centralize and fix age comparison #1043

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
eggrobin merged 5 commits into from
Feb 21, 2025
Merged

Centralize and fix age comparison #1043

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
2804ceb
Centralize and fix age comparison
eggrobin Feb 13, 2025
7d7d448
Use the right props
eggrobin Feb 14, 2025
353713c
sign
eggrobin Feb 17, 2025
60a2c81
Just say no to strings
eggrobin Feb 17, 2025
60379b5
::
eggrobin Feb 18, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
60 changes: 13 additions & 47 deletions UnicodeJsps/src/main/java/org/unicode/jsp/UnicodeSetUtilities.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,14 +7,15 @@
import com.ibm.icu.text.UTF16.StringComparator;
import com.ibm.icu.text.UnicodeSet;
import com.ibm.icu.util.ULocale;
import com.ibm.icu.util.VersionInfo;
import java.text.ParsePosition;
import java.util.Comparator;
import java.util.List;
import java.util.regex.Pattern;
import org.unicode.cldr.util.MultiComparator;
import org.unicode.jsp.UnicodeSetUtilities.ComparisonMatcher.Relation;
import org.unicode.props.UnicodeProperty;
import org.unicode.props.UnicodeProperty.PatternMatcher;
import org.unicode.props.UnicodePropertySymbolTable;

public class UnicodeSetUtilities {

Expand Down Expand Up @@ -292,7 +293,17 @@ private boolean applyPropertyAlias0(
+ prop.getValueAliases());
}
if (isAge) {
set = prop.getSet(new ComparisonMatcher(propertyValue, Relation.geq));
set =
prop.getSet(
new UnicodePropertySymbolTable.ComparisonMatcher<
VersionInfo>(
UnicodePropertySymbolTable.parseVersionInfoOrMax(
propertyValue),
UnicodePropertySymbolTable.Relation.geq,
Comparator.nullsFirst(Comparator.naturalOrder()),
(s) ->
UnicodePropertySymbolTable
.parseVersionInfoOrMax(s)));
} else {
if (prop.getName().equals("General_Category")) {
for (String[] coarseValue : COARSE_GENERAL_CATEGORIES) {
Expand Down Expand Up @@ -344,49 +355,4 @@ private boolean isValid(UnicodeProperty prop, String propertyValue) {
return prop.isValidValue(propertyValue);
}
}
;

public static class ComparisonMatcher implements PatternMatcher {
Relation relation;

enum Relation {
less,
leq,
equal,
geq,
greater
}

static Comparator comparator = new UTF16.StringComparator(true, false, 0);

String pattern;

public ComparisonMatcher(String pattern, Relation comparator) {
this.relation = comparator;
this.pattern = pattern;
}

@Override
public boolean test(String value) {
int comp = comparator.compare(pattern, value);
switch (relation) {
case less:
return comp < 0;
case leq:
return comp <= 0;
default:
return comp == 0;
case geq:
return comp >= 0;
case greater:
return comp > 0;
}
}

@Override
public PatternMatcher set(String pattern) {
this.pattern = pattern;
return this;
}
}
}
79 changes: 33 additions & 46 deletions unicodetools/src/main/java/org/unicode/props/UnicodePropertySymbolTable.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,11 +7,12 @@
package org.unicode.props;

import com.ibm.icu.impl.UnicodeRegex;
import com.ibm.icu.text.UTF16;
import com.ibm.icu.text.UnicodeSet;
import com.ibm.icu.util.VersionInfo;
import java.util.Comparator;
import java.util.HashMap;
import java.util.List;
import java.util.function.Function;
import org.unicode.props.UnicodeProperty.PatternMatcher;

/**
Expand Down Expand Up @@ -201,8 +202,14 @@ public boolean applyPropertyAlias0(
if (isAge) {
set =
prop.getSet(
new ComparisonMatcher(
propertyValue, Relation.geq, DOUBLE_STRING_COMPARATOR));
new ComparisonMatcher<VersionInfo>(
UnicodePropertySymbolTable.parseVersionInfoOrMax(
propertyValue),
Relation.geq,
Comparator.nullsFirst(Comparator.naturalOrder()),
(s) ->
UnicodePropertySymbolTable
.parseVersionInfoOrMax(s)));
} else {
set = prop.getSet(propertyValue);
}
Expand Down Expand Up @@ -242,24 +249,26 @@ public enum Relation {
greater
}

public static class ComparisonMatcher implements PatternMatcher {
public static class ComparisonMatcher<T> implements PatternMatcher {
final Relation relation;
final Comparator<String> comparator;
String pattern;
final Comparator<T> comparator;
final Function<String, T> parser;
T expected;
Comment on lines +250 to +254
Copy link
Member

@markusicu markusicu Feb 18, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

FYI: nice!


public ComparisonMatcher(String pattern, Relation relation) {
this(pattern, relation, new UTF16.StringComparator(true, false, 0));
}

public ComparisonMatcher(String pattern, Relation relation, Comparator<String> comparator) {
public ComparisonMatcher(
T expected,
Relation relation,
Comparator<T> comparator,
Function<String, T> parser) {
this.relation = relation;
this.pattern = pattern;
this.expected = expected;
this.comparator = comparator;
this.parser = parser;
}

@Override
public boolean test(String value) {
int comp = comparator.compare(pattern, value);
int comp = comparator.compare(expected, parser.apply(value));
switch (relation) {
case less:
return comp < 0;
Expand All @@ -276,41 +285,19 @@ public boolean test(String value) {

@Override
public PatternMatcher set(String pattern) {
this.pattern = pattern;
this.expected = parser.apply(pattern);
return this;
}
}

/** Special parser for doubles. Anything not parsable is higher than everything else. */
public static final Comparator<String> DOUBLE_STRING_COMPARATOR =
new Comparator<String>() {

@Override
public int compare(String o1, String o2) {
if (o1 == o2) {
return 0;
} else if (o1 == null) {
return -1;
} else if (o2 == null) {
return 1;
} else {
int f1 = o1.codePointAt(0);
int f2 = o2.codePointAt(0);
boolean n1 = f1 < '0' || f1 > '9';
boolean n2 = f2 < '0' || f2 > '9';
if (n1) {
return n2 ? o1.compareTo(o2) : 1;
} else if (n2) {
return -1;
}
double d1 = Double.parseDouble(o1);
double d2 = Double.parseDouble(o2);
if (Double.isNaN(d1) || Double.isNaN(d2)) {
throw new IllegalArgumentException();
}

return d1 > d2 ? 1 : d1 < d2 ? -1 : 0;
}
}
};
public static VersionInfo parseVersionInfoOrMax(String s) {
if (s == null) {
return null;
}
try {
return VersionInfo.getInstance(s);
} catch (IllegalArgumentException e) {
return VersionInfo.getInstance(255, 255, 255, 255);
}
}
}
46 changes: 35 additions & 11 deletions unicodetools/src/test/java/org/unicode/unittest/TestUnicodeSet.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,23 +2,25 @@

import com.ibm.icu.impl.UnicodeRegex;
import com.ibm.icu.text.UnicodeSet;
import com.ibm.icu.util.VersionInfo;
import java.util.Comparator;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.junit.jupiter.api.Test;
import org.unicode.cldr.util.props.UnicodePropertySymbolTable;
import org.unicode.props.UnicodePropertySymbolTable;
import org.unicode.text.utility.UnicodeSetParser;
import org.unicode.text.utility.Utility;

public class TestUnicodeSet extends TestFmwkMinusMinus {

@Test
public void TestAge() {
checkOrder("3.1", "3.2", -1);
checkOrder("3.2", "3.2", 0);
checkOrder("4.0", "3.2", 1);
checkOrder("10.0", "3.2", 1);
checkOrder("11.0", "3.2", 1);
checkOrder("NA", "11.0", 1);
checkOrder("3.1", "3.2", Comparison.SMALLER);
checkOrder("3.2", "3.2", Comparison.EQUAL);
checkOrder("4.0", "3.2", Comparison.GREATER);
checkOrder("10.0", "3.2", Comparison.GREATER);
checkOrder("11.0", "3.2", Comparison.GREATER);
checkOrder("NA", "11.0", Comparison.GREATER);

final UnicodeSet U32 = new UnicodeSet("[:age=3.2:]").freeze();
if (!U32.contains(0x01F6) || !U32.contains(0x0220)) {
Expand All @@ -29,15 +31,37 @@ public void TestAge() {
}
}

private void checkOrder(String d1, String d2, int expected) {
private static enum Comparison {
EQUAL,
GREATER,
SMALLER;

public Comparison opposite() {
return this == GREATER ? SMALLER : this == SMALLER ? GREATER : this;
}

public static Comparison fromCompareResult(int compareResult) {
return compareResult == 0 ? EQUAL : compareResult > 0 ? GREATER : SMALLER;
}
}

private void checkOrder(String d1, String d2, Comparison expected) {
assertEquals(
d1 + " ?< " + d2,
expected,
UnicodePropertySymbolTable.DOUBLE_STRING_COMPARATOR.compare(d1, d2));
Comparison.fromCompareResult(
Comparator.nullsFirst(Comparator.<VersionInfo>naturalOrder())
.compare(
UnicodePropertySymbolTable.parseVersionInfoOrMax(d1),
UnicodePropertySymbolTable.parseVersionInfoOrMax(d2))));
assertEquals(
d2 + " ?< " + d1,
-expected,
UnicodePropertySymbolTable.DOUBLE_STRING_COMPARATOR.compare(d2, d1));
expected.opposite(),
Comparison.fromCompareResult(
Comparator.nullsFirst(Comparator.<VersionInfo>naturalOrder())
.compare(
UnicodePropertySymbolTable.parseVersionInfoOrMax(d2),
UnicodePropertySymbolTable.parseVersionInfoOrMax(d1))));
}

@Test
Expand Down
Loading