Skip to content

Fix versioned GC groupings in the JSPs #1058

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 7 commits into from
Mar 12, 2025
Merged

Fix versioned GC groupings in the JSPs #1058

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
d4214b3
A failing test, though I don’t think it could run in CI
eggrobin Mar 12, 2025
dfcd1f5
Fix the bug
eggrobin Mar 12, 2025
202b65f
Combining_Mark
eggrobin Mar 12, 2025
bbb7f5a
Gate it behind a flag until I figure out something smarter
eggrobin Mar 12, 2025
2b4b35d
Merge remote-tracking branch 'la-vache/main' into versioned-gc-groupings
eggrobin Mar 12, 2025
66acf97
Remove unused and wrong SUPER_CATEGORIES
eggrobin Mar 12, 2025
038e6d3
Aliases from PVA
eggrobin Mar 12, 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
35 changes: 19 additions & 16 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 @@ -9,6 +9,7 @@
import com.ibm.icu.util.ULocale;
import com.ibm.icu.util.VersionInfo;
import java.text.ParsePosition;
import java.util.Arrays;
import java.util.Comparator;
import java.util.List;
import java.util.regex.Pattern;
Expand Down Expand Up @@ -221,15 +222,15 @@ public boolean applyPropertyAlias(
return status;
}

private static String[][] COARSE_GENERAL_CATEGORIES = {
{"Other", "C", "Cc", "Cf", "Cn", "Co", "Cs"},
{"Letter", "L", "Ll", "Lm", "Lo", "Lt", "Lu"},
{"Cased_Letter", "LC", "Ll", "Lt", "Lu"},
{"Mark", "M", "Mc", "Me", "Mn"},
{"Number", "N", "Nd", "Nl", "No"},
{"Punctuation", "P", "Pc", "Pd", "Pe", "Pf", "Pi", "Po", "Ps"},
{"Symbol", "S", "Sc", "Sk", "Sm", "So"},
{"Separator", "Z", "Zl", "Zp", "Zs"},
private static String[][][] COARSE_GENERAL_CATEGORIES = {
{{"Other", "C"}, {"Cc", "Cf", "Cn", "Co", "Cs"}},
{{"Letter", "L"}, {"Ll", "Lm", "Lo", "Lt", "Lu"}},
{{"Cased_Letter", "LC"}, {"Ll", "Lt", "Lu"}},
{{"Mark", "M", "Combining_Mark"}, {"Mc", "Me", "Mn"}},
{{"Number", "N"}, {"Nd", "Nl", "No"}},
{{"Punctuation", "P"}, {"Pc", "Pd", "Pe", "Pf", "Pi", "Po", "Ps"}},
{{"Symbol", "S"}, {"Sc", "Sk", "Sm", "So"}},
{{"Separator", "Z"}, {"Zl", "Zp", "Zs"}},
};

// TODO(eggrobin): I think this function only ever returns true; might as well make it void.
Expand Down Expand Up @@ -304,13 +305,15 @@ private boolean applyPropertyAlias0(
UnicodePropertySymbolTable::parseVersionInfoOrMax));
} else {
if (prop.getName().equals("General_Category")) {
for (String[] coarseValue : COARSE_GENERAL_CATEGORIES) {
final String longName = coarseValue[0];
final String shortName = coarseValue[1];
if (UnicodeProperty.equalNames(propertyValue, longName)
|| UnicodeProperty.equalNames(propertyValue, shortName)) {
for (int i = 2; i < coarseValue.length; ++i) {
prop.getSet(coarseValue[i], result);
for (String[][] coarseValue : COARSE_GENERAL_CATEGORIES) {
final String[] aliases = coarseValue[0];
if (Arrays.stream(aliases)
.anyMatch(
a ->
UnicodeProperty.equalNames(
propertyValue, a))) {
for (var value : coarseValue[1]) {
prop.getSet(value, result);
}
return true;
}
Expand Down
8 changes: 7 additions & 1 deletion UnicodeJsps/src/test/java/org/unicode/jsptest/TestUnicodeSet.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -145,13 +145,19 @@ public void TestPretty() {
}

@Test
public void TestGeneralCategoryGroupings() {
public void TestGeneralCategoryGroupingsWithIncrementalProperties() {
IndexUnicodeProperties.useIncrementalProperties();
UcdLoader.setOldestLoadedUcd(VersionInfo.UNICODE_10_0);
checkSetsEqual("[\\p{U10:Lu}\\p{U10:Ll}\\p{U10:Lm}\\p{U10:Lt}\\p{U10:Lo}]", "\\p{U10:L}");
UcdLoader.setOldestLoadedUcd(Settings.LAST_VERSION_INFO);
}

@Test
public void TestGeneralCategoryGroupings() {
checkSetsEqual("[\\p{Lu}\\p{Ll}\\p{Lm}\\p{Lt}\\p{Lo}]", "\\p{L}");
checkSetsEqual("[\\p{Mc}\\p{Me}\\p{Mn}]", "\\p{gc=Combining_Mark}");
}

// public void TestAExemplars() {
// checkProperties("[:exemplars_en:]", "[a]", "[\u0350]");
// }
Expand Down
Loading