Skip to content

Apache Lucene open-source search software

build: generate CaseFolding.java from "gradle regenerate" (#14384)

Robert Muir4f52782a1e2e
diff --git a/gradle/generation/icu.gradle b/gradle/generation/icu.gradle
index fa254d4a1bb..c6c7c71cf7a 100644
--- a/gradle/generation/icu.gradle
+++ b/gradle/generation/icu.gradle
@@ -282,3 +282,37 @@ configure(project(":lucene:analysis:common")) {
mustRunBefore: [ "compileJava" ]
])
}
+
+// Regenerates CaseFolding.java
+configure(project(":lucene:core")) {
+ task generateUnicodePropsInternal() {
+ def icuConfig = rootProject.configurations.icu_current
+ def outputFile = file("src/java/org/apache/lucene/util/automaton/CaseFolding.java")
+
+ description "Regenerate ${outputFile} (with ${icuConfig.name})"
+ group "generation"
+
+ dependsOn icuConfig
+
+ inputs.property "icuConfig", provider { icuVersionFromConfiguration(icuConfig) }
+ outputs.file outputFile
+
+ doFirst {
+ project.javaexec {
+ main "groovy.lang.GroovyShell"
+ classpath icuConfig, rootProject.configurations.groovy
+
+ args = [
+ "--encoding", "UTF-8",
+ file("${resources}/GenerateCaseFolding.groovy"),
+ outputFile
+ ]
+ }
+ }
+ }
+
+ regenerate.dependsOn wrapWithPersistentChecksums(generateUnicodePropsInternal, [
+ andThenTasks: ["spotlessJava", "spotlessJavaApply"],
+ mustRunBefore: [ "compileJava" ]
+ ])
+}
diff --git a/gradle/generation/icu/GenerateCaseFolding.groovy b/gradle/generation/icu/GenerateCaseFolding.groovy
new file mode 100644
index 00000000000..05323d90abc
--- /dev/null
+++ b/gradle/generation/icu/GenerateCaseFolding.groovy
@@ -0,0 +1,89 @@
+import com.ibm.icu.lang.UCharacter
+import com.ibm.icu.text.UnicodeSet
+import com.ibm.icu.text.UnicodeSetIterator
+import com.ibm.icu.util.VersionInfo
+import java.nio.file.Paths
+import java.util.Locale
+import java.util.ArrayList
+
+def icuVersion = VersionInfo.ICU_VERSION.toString()
+def unicodeVersion = UCharacter.getUnicodeVersion().toString()
+
+def outputFile = Paths.get(args[0])
+
+def generateSwitch() {
+ StringBuilder sb = new StringBuilder()
+ sb.append("switch(c) {\n")
+ for (int c = UCharacter.MIN_CODE_POINT; c <= UCharacter.MAX_CODE_POINT; c++) {
+ UnicodeSet set = new UnicodeSet(c, c).closeOver(UnicodeSet.SIMPLE_CASE_INSENSITIVE);
+ ArrayList scf = new ArrayList()
+ for (UnicodeSetIterator it = new UnicodeSetIterator(set); it.next(); ) {
+ if (it.codepoint != c && it.codepoint != UCharacter.toUpperCase(c) && it.codepoint != UCharacter.toLowerCase(c)) {
+ scf.add(it.codepoint)
+ }
+ }
+ if (!scf.isEmpty()) {
+ sb.append(String.format(Locale.ROOT, " case 0x%04X: // %s\n", c, UCharacter.getName(c)))
+ for (int alt : scf) {
+ sb.append(String.format(Locale.ROOT, " fn.accept(0x%04X); // %s\n", alt, UCharacter.getName(alt)))
+ }
+ sb.append(" break;\n")
+ }
+ }
+ sb.append(" }")
+ return sb.toString();
+}
+
+def code = """
+// DO NOT EDIT THIS FILE! Use "gradlew generateUnicodeProps tidy" to recreate.
+
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.lucene.util.automaton;
+
+import java.util.function.IntConsumer;
+
+/**
+ * This file contains unicode properties used by {@code RegExp}.
+ * The data was generated using ICU4J v${icuVersion}, unicode version: ${unicodeVersion}.
+ */
+final class CaseFolding {
+ private CaseFolding() {}
+
+ /**
+ * Calls {@code fn} consumer with {@code c} itself and its {@code scf} mappings.
+ */
+ static void expand(int c, IntConsumer fn) {
+ // add codepoint
+ fn.accept(c);
+ // add uppercase from tables
+ int upper = Character.toUpperCase(c);
+ if (upper != c) {
+ fn.accept(upper);
+ }
+ // add lowercase from tables
+ int lower = Character.toLowerCase(c);
+ if (lower != c) {
+ fn.accept(lower);
+ }
+ // add special casing variants
+ ${generateSwitch()}
+ }
+}
+"""
+outputFile.setText(code, "UTF-8")
diff --git a/lucene/core/src/generated/checksums/generateUnicodeProps.json b/lucene/core/src/generated/checksums/generateUnicodeProps.json
new file mode 100644
index 00000000000..46283f72a5d
--- /dev/null
+++ b/lucene/core/src/generated/checksums/generateUnicodeProps.json
@@ -0,0 +1,4 @@
+{
+ "lucene/core/src/java/org/apache/lucene/util/automaton/CaseFolding.java": "299cbef6383ef2ddb1fe06f4ecda3efab961bed4",
+ "property:icuConfig": "com.ibm.icu:icu4j:74.2"
+}
\ No newline at end of file
diff --git a/lucene/core/src/java/org/apache/lucene/util/automaton/CaseFolding.java b/lucene/core/src/java/org/apache/lucene/util/automaton/CaseFolding.java
index dba1e6438e2..c581c607f8a 100644
--- a/lucene/core/src/java/org/apache/lucene/util/automaton/CaseFolding.java
+++ b/lucene/core/src/java/org/apache/lucene/util/automaton/CaseFolding.java
@@ -1,3 +1,5 @@
+// DO NOT EDIT THIS FILE! Use "gradlew generateUnicodeProps tidy" to recreate.
+
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
@@ -14,733 +16,307 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
-package org.apache.lucene.util.automaton;
-class CaseFolding {
+package org.apache.lucene.util.automaton;
- /**
- * Generates the set of codepoints which represent the given codepoint that are case-insensitive
- * matches within the Unicode table, which may not always be intuitive for instance Σ, σ, ς do all
- * fold to one another and so would match one another
- *
- * <p>Known special cases derived from generating mappings using a combination of the Unicode
- * 16.0.0 spec: https://www.unicode.org/Public/16.0.0/ucd/CaseFolding.txt and
- * https://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt these are only the alternate
- * mappings for each codepoint that are not supported by a transform using Character.toUpperCase
- * or Character.toLowerCase
- *
- * @param codepoint the codepoint for the character to case fold
- * @return an array of characters as codepoints that should match the given codepoint in a
- * case-insensitive context or null if no alternates exist this does not include the given
- * codepoint itself
- */
- static int[] lookupAlternates(int codepoint) {
+import java.util.function.IntConsumer;
- int[] alts =
- switch (codepoint) {
- case 0x00049 -> // I [LATIN CAPITAL LETTER I]
- new int[] {
- 0x00130, // İ [LATIN CAPITAL LETTER I WITH DOT ABOVE]
- 0x00131, // ı [LATIN SMALL LETTER DOTLESS I]
- 0x00069, // i [LATIN SMALL LETTER I]
- };
- case 0x0004B -> // K [LATIN CAPITAL LETTER K]
- new int[] {
- 0x0212A, // K [KELVIN SIGN]
- 0x0006B, // k [LATIN SMALL LETTER K]
- };
- case 0x00053 -> // S [LATIN CAPITAL LETTER S]
- new int[] {
- 0x00073, // s [LATIN SMALL LETTER S]
- 0x0017F, // ſ [LATIN SMALL LETTER LONG S]
- };
- case 0x00069 -> // i [LATIN SMALL LETTER I]
- new int[] {
- 0x00130, // İ [LATIN CAPITAL LETTER I WITH DOT ABOVE]
- 0x00131, // ı [LATIN SMALL LETTER DOTLESS I]
- 0x00049, // I [LATIN CAPITAL LETTER I]
- };
- case 0x0006B -> // k [LATIN SMALL LETTER K]
- new int[] {
- 0x0212A, // K [KELVIN SIGN]
- 0x0004B, // K [LATIN CAPITAL LETTER K]
- };
- case 0x00073 -> // s [LATIN SMALL LETTER S]
- new int[] {
- 0x00053, // S [LATIN CAPITAL LETTER S]
- 0x0017F, // ſ [LATIN SMALL LETTER LONG S]
- };
- case 0x000B5 -> // µ [MICRO SIGN]
- new int[] {
- 0x0039C, // Μ [GREEK CAPITAL LETTER MU]
- 0x003BC, // μ [GREEK SMALL LETTER MU]
- };
- case 0x000C5 -> // Å [LATIN CAPITAL LETTER A WITH RING ABOVE]
- new int[] {
- 0x000E5, // å [LATIN SMALL LETTER A WITH RING ABOVE]
- 0x0212B, // Å [ANGSTROM SIGN]
- };
- case 0x000DF -> // ß [LATIN SMALL LETTER SHARP S]
- new int[] {
- 0x01E9E, // ẞ [LATIN CAPITAL LETTER SHARP S]
- };
- case 0x000E5 -> // å [LATIN SMALL LETTER A WITH RING ABOVE]
- new int[] {
- 0x000C5, // Å [LATIN CAPITAL LETTER A WITH RING ABOVE]
- 0x0212B, // Å [ANGSTROM SIGN]
- };
- case 0x02126 -> // Ω [OHM SIGN]
- new int[] {
- 0x003A9, // Ω [GREEK CAPITAL LETTER OMEGA]
- 0x003C9, // ω [GREEK SMALL LETTER OMEGA]
- };
- case 0x0212A -> // K [KELVIN SIGN]
- new int[] {
- 0x0004B, // K [LATIN CAPITAL LETTER K]
- 0x0006B, // k [LATIN SMALL LETTER K]
- };
- case 0x0212B -> // Å [ANGSTROM SIGN]
- new int[] {
- 0x000C5, // Å [LATIN CAPITAL LETTER A WITH RING ABOVE]
- 0x000E5, // å [LATIN SMALL LETTER A WITH RING ABOVE]
- };
- case 0x00130 -> // İ [LATIN CAPITAL LETTER I WITH DOT ABOVE]
- new int[] {
- 0x00131, // ı [LATIN SMALL LETTER DOTLESS I]
- 0x00049, // I [LATIN CAPITAL LETTER I]
- 0x00069, // i [LATIN SMALL LETTER I]
- };
- case 0x00131 -> // ı [LATIN SMALL LETTER DOTLESS I]
- new int[] {
- 0x00130, // İ [LATIN CAPITAL LETTER I WITH DOT ABOVE]
- 0x00069, // i [LATIN SMALL LETTER I]
- 0x00049, // I [LATIN CAPITAL LETTER I]
- };
- case 0x0017F -> // ſ [LATIN SMALL LETTER LONG S]
- new int[] {
- 0x00053, // S [LATIN CAPITAL LETTER S]
- 0x00073, // s [LATIN SMALL LETTER S]
- };
- case 0x0019B -> // ƛ [LATIN SMALL LETTER LAMBDA WITH STROKE]
- new int[] {
- 0x0A7DC, // Ƛ [LATIN CAPITAL LETTER LAMBDA WITH STROKE]
- };
- case 0x001C4 -> // DŽ [LATIN CAPITAL LETTER DZ WITH CARON]
- new int[] {
- 0x001C5, // Dž [LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON]
- 0x001C6, // dž [LATIN SMALL LETTER DZ WITH CARON]
- };
- case 0x001C5 -> // Dž [LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON]
- new int[] {
- 0x001C4, // DŽ [LATIN CAPITAL LETTER DZ WITH CARON]
- 0x001C6, // dž [LATIN SMALL LETTER DZ WITH CARON]
- };
- case 0x001C6 -> // dž [LATIN SMALL LETTER DZ WITH CARON]
- new int[] {
- 0x001C4, // DŽ [LATIN CAPITAL LETTER DZ WITH CARON]
- 0x001C5, // Dž [LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON]
- };
- case 0x001C7 -> // LJ [LATIN CAPITAL LETTER LJ]
- new int[] {
- 0x001C8, // Lj [LATIN CAPITAL LETTER L WITH SMALL LETTER J]
- 0x001C9, // lj [LATIN SMALL LETTER LJ]
- };
- case 0x001C8 -> // Lj [LATIN CAPITAL LETTER L WITH SMALL LETTER J]
- new int[] {
- 0x001C7, // LJ [LATIN CAPITAL LETTER LJ]
- 0x001C9, // lj [LATIN SMALL LETTER LJ]
- };
- case 0x001C9 -> // lj [LATIN SMALL LETTER LJ]
- new int[] {
- 0x001C7, // LJ [LATIN CAPITAL LETTER LJ]
- 0x001C8, // Lj [LATIN CAPITAL LETTER L WITH SMALL LETTER J]
- };
- case 0x001CA -> // NJ [LATIN CAPITAL LETTER NJ]
- new int[] {
- 0x001CB, // Nj [LATIN CAPITAL LETTER N WITH SMALL LETTER J]
- 0x001CC, // nj [LATIN SMALL LETTER NJ]
- };
- case 0x001CB -> // Nj [LATIN CAPITAL LETTER N WITH SMALL LETTER J]
- new int[] {
- 0x001CA, // NJ [LATIN CAPITAL LETTER NJ]
- 0x001CC, // nj [LATIN SMALL LETTER NJ]
- };
- case 0x001CC -> // nj [LATIN SMALL LETTER NJ]
- new int[] {
- 0x001CA, // NJ [LATIN CAPITAL LETTER NJ]
- 0x001CB, // Nj [LATIN CAPITAL LETTER N WITH SMALL LETTER J]
- };
- case 0x001F1 -> // DZ [LATIN CAPITAL LETTER DZ]
- new int[] {
- 0x001F2, // Dz [LATIN CAPITAL LETTER D WITH SMALL LETTER Z]
- 0x001F3, // dz [LATIN SMALL LETTER DZ]
- };
- case 0x001F2 -> // Dz [LATIN CAPITAL LETTER D WITH SMALL LETTER Z]
- new int[] {
- 0x001F1, // DZ [LATIN CAPITAL LETTER DZ]
- 0x001F3, // dz [LATIN SMALL LETTER DZ]
- };
- case 0x001F3 -> // dz [LATIN SMALL LETTER DZ]
- new int[] {
- 0x001F1, // DZ [LATIN CAPITAL LETTER DZ]
- 0x001F2, // Dz [LATIN CAPITAL LETTER D WITH SMALL LETTER Z]
- };
- case 0x00264 -> // ɤ [LATIN SMALL LETTER RAMS HORN]
- new int[] {
- 0x0A7CB, // Ɤ [LATIN CAPITAL LETTER RAMS HORN]
- };
- case 0x00345 -> // ͅ [COMBINING GREEK YPOGEGRAMMENI]
- new int[] {
- 0x00399, // Ι [GREEK CAPITAL LETTER IOTA]
- 0x003B9, // ι [GREEK SMALL LETTER IOTA]
- 0x01FBE, // ι [GREEK PROSGEGRAMMENI]
- };
- case 0x00390 -> // ΐ [GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS]
- new int[] {
- 0x01FD3, // ΐ [GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA]
- };
- case 0x00392 -> // Β [GREEK CAPITAL LETTER BETA]
- new int[] {
- 0x003D0, // ϐ [GREEK BETA SYMBOL]
- 0x003B2, // β [GREEK SMALL LETTER BETA]
- };
- case 0x00395 -> // Ε [GREEK CAPITAL LETTER EPSILON]
- new int[] {
- 0x003F5, // ϵ [GREEK LUNATE EPSILON SYMBOL]
- 0x003B5, // ε [GREEK SMALL LETTER EPSILON]
- };
- case 0x00398 -> // Θ [GREEK CAPITAL LETTER THETA]
- new int[] {
- 0x003D1, // ϑ [GREEK THETA SYMBOL]
- 0x003F4, // ϴ [GREEK CAPITAL THETA SYMBOL]
- 0x003B8, // θ [GREEK SMALL LETTER THETA]
- };
- case 0x00399 -> // Ι [GREEK CAPITAL LETTER IOTA]
- new int[] {
- 0x00345, // ͅ [COMBINING GREEK YPOGEGRAMMENI]
- 0x003B9, // ι [GREEK SMALL LETTER IOTA]
- 0x01FBE, // ι [GREEK PROSGEGRAMMENI]
- };
- case 0x0039A -> // Κ [GREEK CAPITAL LETTER KAPPA]
- new int[] {
- 0x003F0, // ϰ [GREEK KAPPA SYMBOL]
- 0x003BA, // κ [GREEK SMALL LETTER KAPPA]
- };
- case 0x0039C -> // Μ [GREEK CAPITAL LETTER MU]
- new int[] {
- 0x000B5, // µ [MICRO SIGN]
- 0x003BC, // μ [GREEK SMALL LETTER MU]
- };
- case 0x003A0 -> // Π [GREEK CAPITAL LETTER PI]
- new int[] {
- 0x003C0, // π [GREEK SMALL LETTER PI]
- 0x003D6, // ϖ [GREEK PI SYMBOL]
- };
- case 0x003A1 -> // Ρ [GREEK CAPITAL LETTER RHO]
- new int[] {
- 0x003F1, // ϱ [GREEK RHO SYMBOL]
- 0x003C1, // ρ [GREEK SMALL LETTER RHO]
- };
- case 0x003A3 -> // Σ [GREEK CAPITAL LETTER SIGMA]
- new int[] {
- 0x003C2, // ς [GREEK SMALL LETTER FINAL SIGMA]
- 0x003C3, // σ [GREEK SMALL LETTER SIGMA]
- };
- case 0x003A6 -> // Φ [GREEK CAPITAL LETTER PHI]
- new int[] {
- 0x003D5, // ϕ [GREEK PHI SYMBOL]
- 0x003C6, // φ [GREEK SMALL LETTER PHI]
- };
- case 0x003A9 -> // Ω [GREEK CAPITAL LETTER OMEGA]
- new int[] {
- 0x02126, // Ω [OHM SIGN]
- 0x003C9, // ω [GREEK SMALL LETTER OMEGA]
- };
- case 0x003B0 -> // ΰ [GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS]
- new int[] {
- 0x01FE3, // ΰ [GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA]
- };
- case 0x003B2 -> // β [GREEK SMALL LETTER BETA]
- new int[] {
- 0x003D0, // ϐ [GREEK BETA SYMBOL]
- 0x00392, // Β [GREEK CAPITAL LETTER BETA]
- };
- case 0x003B5 -> // ε [GREEK SMALL LETTER EPSILON]
- new int[] {
- 0x00395, // Ε [GREEK CAPITAL LETTER EPSILON]
- 0x003F5, // ϵ [GREEK LUNATE EPSILON SYMBOL]
- };
- case 0x003B8 -> // θ [GREEK SMALL LETTER THETA]
- new int[] {
- 0x003D1, // ϑ [GREEK THETA SYMBOL]
- 0x003F4, // ϴ [GREEK CAPITAL THETA SYMBOL]
- 0x00398, // Θ [GREEK CAPITAL LETTER THETA]
- };
- case 0x003B9 -> // ι [GREEK SMALL LETTER IOTA]
- new int[] {
- 0x00345, // ͅ [COMBINING GREEK YPOGEGRAMMENI]
- 0x00399, // Ι [GREEK CAPITAL LETTER IOTA]
- 0x01FBE, // ι [GREEK PROSGEGRAMMENI]
- };
- case 0x003BA -> // κ [GREEK SMALL LETTER KAPPA]
- new int[] {
- 0x003F0, // ϰ [GREEK KAPPA SYMBOL]
- 0x0039A, // Κ [GREEK CAPITAL LETTER KAPPA]
- };
- case 0x003BC -> // μ [GREEK SMALL LETTER MU]
- new int[] {
- 0x000B5, // µ [MICRO SIGN]
- 0x0039C, // Μ [GREEK CAPITAL LETTER MU]
- };
- case 0x003C0 -> // π [GREEK SMALL LETTER PI]
- new int[] {
- 0x003A0, // Π [GREEK CAPITAL LETTER PI]
- 0x003D6, // ϖ [GREEK PI SYMBOL]
- };
- case 0x003C1 -> // ρ [GREEK SMALL LETTER RHO]
- new int[] {
- 0x003A1, // Ρ [GREEK CAPITAL LETTER RHO]
- 0x003F1, // ϱ [GREEK RHO SYMBOL]
- };
- case 0x003C2 -> // ς [GREEK SMALL LETTER FINAL SIGMA]
- new int[] {
- 0x003A3, // Σ [GREEK CAPITAL LETTER SIGMA]
- 0x003C3, // σ [GREEK SMALL LETTER SIGMA]
- };
- case 0x003C3 -> // σ [GREEK SMALL LETTER SIGMA]
- new int[] {
- 0x003C2, // ς [GREEK SMALL LETTER FINAL SIGMA]
- 0x003A3, // Σ [GREEK CAPITAL LETTER SIGMA]
- };
- case 0x003C6 -> // φ [GREEK SMALL LETTER PHI]
- new int[] {
- 0x003D5, // ϕ [GREEK PHI SYMBOL]
- 0x003A6, // Φ [GREEK CAPITAL LETTER PHI]
- };
- case 0x003C9 -> // ω [GREEK SMALL LETTER OMEGA]
- new int[] {
- 0x02126, // Ω [OHM SIGN]
- 0x003A9, // Ω [GREEK CAPITAL LETTER OMEGA]
- };
- case 0x003D0 -> // ϐ [GREEK BETA SYMBOL]
- new int[] {
- 0x00392, // Β [GREEK CAPITAL LETTER BETA]
- 0x003B2, // β [GREEK SMALL LETTER BETA]
- };
- case 0x003D1 -> // ϑ [GREEK THETA SYMBOL]
- new int[] {
- 0x003F4, // ϴ [GREEK CAPITAL THETA SYMBOL]
- 0x00398, // Θ [GREEK CAPITAL LETTER THETA]
- 0x003B8, // θ [GREEK SMALL LETTER THETA]
- };
- case 0x003D5 -> // ϕ [GREEK PHI SYMBOL]
- new int[] {
- 0x003A6, // Φ [GREEK CAPITAL LETTER PHI]
- 0x003C6, // φ [GREEK SMALL LETTER PHI]
- };
- case 0x003D6 -> // ϖ [GREEK PI SYMBOL]
- new int[] {
- 0x003A0, // Π [GREEK CAPITAL LETTER PI]
- 0x003C0, // π [GREEK SMALL LETTER PI]
- };
- case 0x003F0 -> // ϰ [GREEK KAPPA SYMBOL]
- new int[] {
- 0x0039A, // Κ [GREEK CAPITAL LETTER KAPPA]
- 0x003BA, // κ [GREEK SMALL LETTER KAPPA]
- };
- case 0x003F1 -> // ϱ [GREEK RHO SYMBOL]
- new int[] {
- 0x003A1, // Ρ [GREEK CAPITAL LETTER RHO]
- 0x003C1, // ρ [GREEK SMALL LETTER RHO]
- };
- case 0x003F4 -> // ϴ [GREEK CAPITAL THETA SYMBOL]
- new int[] {
- 0x003D1, // ϑ [GREEK THETA SYMBOL]
- 0x00398, // Θ [GREEK CAPITAL LETTER THETA]
- 0x003B8, // θ [GREEK SMALL LETTER THETA]
- };
- case 0x003F5 -> // ϵ [GREEK LUNATE EPSILON SYMBOL]
- new int[] {
- 0x00395, // Ε [GREEK CAPITAL LETTER EPSILON]
- 0x003B5, // ε [GREEK SMALL LETTER EPSILON]
- };
- case 0x00412 -> // В [CYRILLIC CAPITAL LETTER VE]
- new int[] {
- 0x01C80, // ᲀ [CYRILLIC SMALL LETTER ROUNDED VE]
- 0x00432, // в [CYRILLIC SMALL LETTER VE]
- };
- case 0x00414 -> // Д [CYRILLIC CAPITAL LETTER DE]
- new int[] {
- 0x01C81, // ᲁ [CYRILLIC SMALL LETTER LONG-LEGGED DE]
- 0x00434, // д [CYRILLIC SMALL LETTER DE]
- };
- case 0x0041E -> // О [CYRILLIC CAPITAL LETTER O]
- new int[] {
- 0x01C82, // ᲂ [CYRILLIC SMALL LETTER NARROW O]
- 0x0043E, // о [CYRILLIC SMALL LETTER O]
- };
- case 0x00421 -> // С [CYRILLIC CAPITAL LETTER ES]
- new int[] {
- 0x00441, // с [CYRILLIC SMALL LETTER ES]
- 0x01C83, // ᲃ [CYRILLIC SMALL LETTER WIDE ES]
- };
- case 0x00422 -> // Т [CYRILLIC CAPITAL LETTER TE]
- new int[] {
- 0x00442, // т [CYRILLIC SMALL LETTER TE]
- 0x01C84, // ᲄ [CYRILLIC SMALL LETTER TALL TE]
- 0x01C85, // ᲅ [CYRILLIC SMALL LETTER THREE-LEGGED TE]
- };
- case 0x0042A -> // Ъ [CYRILLIC CAPITAL LETTER HARD SIGN]
- new int[] {
- 0x01C86, // ᲆ [CYRILLIC SMALL LETTER TALL HARD SIGN]
- 0x0044A, // ъ [CYRILLIC SMALL LETTER HARD SIGN]
- };
- case 0x00432 -> // в [CYRILLIC SMALL LETTER VE]
- new int[] {
- 0x01C80, // ᲀ [CYRILLIC SMALL LETTER ROUNDED VE]
- 0x00412, // В [CYRILLIC CAPITAL LETTER VE]
- };
- case 0x00434 -> // д [CYRILLIC SMALL LETTER DE]
- new int[] {
- 0x01C81, // ᲁ [CYRILLIC SMALL LETTER LONG-LEGGED DE]
- 0x00414, // Д [CYRILLIC CAPITAL LETTER DE]
- };
- case 0x0043E -> // о [CYRILLIC SMALL LETTER O]
- new int[] {
- 0x01C82, // ᲂ [CYRILLIC SMALL LETTER NARROW O]
- 0x0041E, // О [CYRILLIC CAPITAL LETTER O]
- };
- case 0x00441 -> // с [CYRILLIC SMALL LETTER ES]
- new int[] {
- 0x00421, // С [CYRILLIC CAPITAL LETTER ES]
- 0x01C83, // ᲃ [CYRILLIC SMALL LETTER WIDE ES]
- };
- case 0x00442 -> // т [CYRILLIC SMALL LETTER TE]
- new int[] {
- 0x00422, // Т [CYRILLIC CAPITAL LETTER TE]
- 0x01C84, // ᲄ [CYRILLIC SMALL LETTER TALL TE]
- 0x01C85, // ᲅ [CYRILLIC SMALL LETTER THREE-LEGGED TE]
- };
- case 0x0044A -> // ъ [CYRILLIC SMALL LETTER HARD SIGN]
- new int[] {
- 0x01C86, // ᲆ [CYRILLIC SMALL LETTER TALL HARD SIGN]
- 0x0042A, // Ъ [CYRILLIC CAPITAL LETTER HARD SIGN]
- };
- case 0x00462 -> // Ѣ [CYRILLIC CAPITAL LETTER YAT]
- new int[] {
- 0x00463, // ѣ [CYRILLIC SMALL LETTER YAT]
- 0x01C87, // ᲇ [CYRILLIC SMALL LETTER TALL YAT]
- };
- case 0x00463 -> // ѣ [CYRILLIC SMALL LETTER YAT]
- new int[] {
- 0x00462, // Ѣ [CYRILLIC CAPITAL LETTER YAT]
- 0x01C87, // ᲇ [CYRILLIC SMALL LETTER TALL YAT]
- };
- case 0x0A64A -> // Ꙋ [CYRILLIC CAPITAL LETTER MONOGRAPH UK]
- new int[] {
- 0x01C88, // ᲈ [CYRILLIC SMALL LETTER UNBLENDED UK]
- 0x0A64B, // ꙋ [CYRILLIC SMALL LETTER MONOGRAPH UK]
- };
- case 0x0A64B -> // ꙋ [CYRILLIC SMALL LETTER MONOGRAPH UK]
- new int[] {
- 0x01C88, // ᲈ [CYRILLIC SMALL LETTER UNBLENDED UK]
- 0x0A64A, // Ꙋ [CYRILLIC CAPITAL LETTER MONOGRAPH UK]
- };
- case 0x0A7CB -> // Ɤ [LATIN CAPITAL LETTER RAMS HORN]
- new int[] {
- 0x00264, // ɤ [LATIN SMALL LETTER RAMS HORN]
- };
- case 0x0A7CC -> // Ꟍ [LATIN CAPITAL LETTER S WITH DIAGONAL STROKE]
- new int[] {
- 0x0A7CD, // ꟍ [LATIN SMALL LETTER S WITH DIAGONAL STROKE]
- };
- case 0x0A7CD -> // ꟍ [LATIN SMALL LETTER S WITH DIAGONAL STROKE]
- new int[] {
- 0x0A7CC, // Ꟍ [LATIN CAPITAL LETTER S WITH DIAGONAL STROKE]
- };
- case 0x0A7DA -> // Ꟛ [LATIN CAPITAL LETTER LAMBDA]
- new int[] {
- 0x0A7DB, // ꟛ [LATIN SMALL LETTER LAMBDA]
- };
- case 0x0A7DB -> // ꟛ [LATIN SMALL LETTER LAMBDA]
- new int[] {
- 0x0A7DA, // Ꟛ [LATIN CAPITAL LETTER LAMBDA]
- };
- case 0x0A7DC -> // Ƛ [LATIN CAPITAL LETTER LAMBDA WITH STROKE]
- new int[] {
- 0x0019B, // ƛ [LATIN SMALL LETTER LAMBDA WITH STROKE]
- };
- case 0x0FB05 -> // ſt [LATIN SMALL LIGATURE LONG S T]
- new int[] {
- 0x0FB06, // st [LATIN SMALL LIGATURE ST]
- };
- case 0x0FB06 -> // st [LATIN SMALL LIGATURE ST]
- new int[] {
- 0x0FB05, // ſt [LATIN SMALL LIGATURE LONG S T]
- };
- case 0x01C80 -> // ᲀ [CYRILLIC SMALL LETTER ROUNDED VE]
- new int[] {
- 0x00412, // В [CYRILLIC CAPITAL LETTER VE]
- 0x00432, // в [CYRILLIC SMALL LETTER VE]
- };
- case 0x01C81 -> // ᲁ [CYRILLIC SMALL LETTER LONG-LEGGED DE]
- new int[] {
- 0x00414, // Д [CYRILLIC CAPITAL LETTER DE]
- 0x00434, // д [CYRILLIC SMALL LETTER DE]
- };
- case 0x01C82 -> // ᲂ [CYRILLIC SMALL LETTER NARROW O]
- new int[] {
- 0x0041E, // О [CYRILLIC CAPITAL LETTER O]
- 0x0043E, // о [CYRILLIC SMALL LETTER O]
- };
- case 0x01C83 -> // ᲃ [CYRILLIC SMALL LETTER WIDE ES]
- new int[] {
- 0x00421, // С [CYRILLIC CAPITAL LETTER ES]
- 0x00441, // с [CYRILLIC SMALL LETTER ES]
- };
- case 0x01C84 -> // ᲄ [CYRILLIC SMALL LETTER TALL TE]
- new int[] {
- 0x00422, // Т [CYRILLIC CAPITAL LETTER TE]
- 0x00442, // т [CYRILLIC SMALL LETTER TE]
- 0x01C85, // ᲅ [CYRILLIC SMALL LETTER THREE-LEGGED TE]
- };
- case 0x01C85 -> // ᲅ [CYRILLIC SMALL LETTER THREE-LEGGED TE]
- new int[] {
- 0x00422, // Т [CYRILLIC CAPITAL LETTER TE]
- 0x00442, // т [CYRILLIC SMALL LETTER TE]
- 0x01C84, // ᲄ [CYRILLIC SMALL LETTER TALL TE]
- };
- case 0x01C86 -> // ᲆ [CYRILLIC SMALL LETTER TALL HARD SIGN]
- new int[] {
- 0x0042A, // Ъ [CYRILLIC CAPITAL LETTER HARD SIGN]
- 0x0044A, // ъ [CYRILLIC SMALL LETTER HARD SIGN]
- };
- case 0x01C87 -> // ᲇ [CYRILLIC SMALL LETTER TALL YAT]
- new int[] {
- 0x00462, // Ѣ [CYRILLIC CAPITAL LETTER YAT]
- 0x00463, // ѣ [CYRILLIC SMALL LETTER YAT]
- };
- case 0x01C88 -> // ᲈ [CYRILLIC SMALL LETTER UNBLENDED UK]
- new int[] {
- 0x0A64A, // Ꙋ [CYRILLIC CAPITAL LETTER MONOGRAPH UK]
- 0x0A64B, // ꙋ [CYRILLIC SMALL LETTER MONOGRAPH UK]
- };
- case 0x01C89 -> // Ᲊ [CYRILLIC CAPITAL LETTER TJE]
- new int[] {
- 0x01C8A, // ᲊ [CYRILLIC SMALL LETTER TJE]
- };
- case 0x01C8A -> // ᲊ [CYRILLIC SMALL LETTER TJE]
- new int[] {
- 0x01C89, // Ᲊ [CYRILLIC CAPITAL LETTER TJE]
- };
- case 0x10D51 -> // 𐵑 [GARAY CAPITAL LETTER CA]
- new int[] {
- 0x10D71, // 𐵱 [GARAY SMALL LETTER CA]
- };
- case 0x10D50 -> // 𐵐 [GARAY CAPITAL LETTER A]
- new int[] {
- 0x10D70, // 𐵰 [GARAY SMALL LETTER A]
- };
- case 0x10D53 -> // 𐵓 [GARAY CAPITAL LETTER KA]
- new int[] {
- 0x10D73, // 𐵳 [GARAY SMALL LETTER KA]
- };
- case 0x10D52 -> // 𐵒 [GARAY CAPITAL LETTER MA]
- new int[] {
- 0x10D72, // 𐵲 [GARAY SMALL LETTER MA]
- };
- case 0x10D55 -> // 𐵕 [GARAY CAPITAL LETTER JA]
- new int[] {
- 0x10D75, // 𐵵 [GARAY SMALL LETTER JA]
- };
- case 0x10D54 -> // 𐵔 [GARAY CAPITAL LETTER BA]
- new int[] {
- 0x10D74, // 𐵴 [GARAY SMALL LETTER BA]
- };
- case 0x10D57 -> // 𐵗 [GARAY CAPITAL LETTER WA]
- new int[] {
- 0x10D77, // 𐵷 [GARAY SMALL LETTER WA]
- };
- case 0x10D56 -> // 𐵖 [GARAY CAPITAL LETTER SA]
- new int[] {
- 0x10D76, // 𐵶 [GARAY SMALL LETTER SA]
- };
- case 0x10D59 -> // 𐵙 [GARAY CAPITAL LETTER GA]
- new int[] {
- 0x10D79, // 𐵹 [GARAY SMALL LETTER GA]
- };
- case 0x10D58 -> // 𐵘 [GARAY CAPITAL LETTER LA]
- new int[] {
- 0x10D78, // 𐵸 [GARAY SMALL LETTER LA]
- };
- case 0x10D5B -> // 𐵛 [GARAY CAPITAL LETTER XA]
- new int[] {
- 0x10D7B, // 𐵻 [GARAY SMALL LETTER XA]
- };
- case 0x10D5A -> // 𐵚 [GARAY CAPITAL LETTER DA]
- new int[] {
- 0x10D7A, // 𐵺 [GARAY SMALL LETTER DA]
- };
- case 0x10D5D -> // 𐵝 [GARAY CAPITAL LETTER TA]
- new int[] {
- 0x10D7D, // 𐵽 [GARAY SMALL LETTER TA]
- };
- case 0x10D5C -> // 𐵜 [GARAY CAPITAL LETTER YA]
- new int[] {
- 0x10D7C, // 𐵼 [GARAY SMALL LETTER YA]
- };
- case 0x10D5F -> // 𐵟 [GARAY CAPITAL LETTER NYA]
- new int[] {
- 0x10D7F, // 𐵿 [GARAY SMALL LETTER NYA]
- };
- case 0x10D5E -> // 𐵞 [GARAY CAPITAL LETTER RA]
- new int[] {
- 0x10D7E, // 𐵾 [GARAY SMALL LETTER RA]
- };
- case 0x10D61 -> // 𐵡 [GARAY CAPITAL LETTER NA]
- new int[] {
- 0x10D81, // 𐶁 [GARAY SMALL LETTER NA]
- };
- case 0x10D60 -> // 𐵠 [GARAY CAPITAL LETTER FA]
- new int[] {
- 0x10D80, // 𐶀 [GARAY SMALL LETTER FA]
- };
- case 0x10D63 -> // 𐵣 [GARAY CAPITAL LETTER HA]
- new int[] {
- 0x10D83, // 𐶃 [GARAY SMALL LETTER HA]
- };
- case 0x10D62 -> // 𐵢 [GARAY CAPITAL LETTER PA]
- new int[] {
- 0x10D82, // 𐶂 [GARAY SMALL LETTER PA]
- };
- case 0x10D65 -> // 𐵥 [GARAY CAPITAL LETTER OLD NA]
- new int[] {
- 0x10D85, // 𐶅 [GARAY SMALL LETTER OLD NA]
- };
- case 0x10D64 -> // 𐵤 [GARAY CAPITAL LETTER OLD KA]
- new int[] {
- 0x10D84, // 𐶄 [GARAY SMALL LETTER OLD KA]
- };
- case 0x10D71 -> // 𐵱 [GARAY SMALL LETTER CA]
- new int[] {
- 0x10D51, // 𐵑 [GARAY CAPITAL LETTER CA]
- };
- case 0x10D70 -> // 𐵰 [GARAY SMALL LETTER A]
- new int[] {
- 0x10D50, // 𐵐 [GARAY CAPITAL LETTER A]
- };
- case 0x10D73 -> // 𐵳 [GARAY SMALL LETTER KA]
- new int[] {
- 0x10D53, // 𐵓 [GARAY CAPITAL LETTER KA]
- };
- case 0x10D72 -> // 𐵲 [GARAY SMALL LETTER MA]
- new int[] {
- 0x10D52, // 𐵒 [GARAY CAPITAL LETTER MA]
- };
- case 0x10D75 -> // 𐵵 [GARAY SMALL LETTER JA]
- new int[] {
- 0x10D55, // 𐵕 [GARAY CAPITAL LETTER JA]
- };
- case 0x10D74 -> // 𐵴 [GARAY SMALL LETTER BA]
- new int[] {
- 0x10D54, // 𐵔 [GARAY CAPITAL LETTER BA]
- };
- case 0x10D77 -> // 𐵷 [GARAY SMALL LETTER WA]
- new int[] {
- 0x10D57, // 𐵗 [GARAY CAPITAL LETTER WA]
- };
- case 0x10D76 -> // 𐵶 [GARAY SMALL LETTER SA]
- new int[] {
- 0x10D56, // 𐵖 [GARAY CAPITAL LETTER SA]
- };
- case 0x10D79 -> // 𐵹 [GARAY SMALL LETTER GA]
- new int[] {
- 0x10D59, // 𐵙 [GARAY CAPITAL LETTER GA]
- };
- case 0x10D78 -> // 𐵸 [GARAY SMALL LETTER LA]
- new int[] {
- 0x10D58, // 𐵘 [GARAY CAPITAL LETTER LA]
- };
- case 0x10D7B -> // 𐵻 [GARAY SMALL LETTER XA]
- new int[] {
- 0x10D5B, // 𐵛 [GARAY CAPITAL LETTER XA]
- };
- case 0x10D7A -> // 𐵺 [GARAY SMALL LETTER DA]
- new int[] {
- 0x10D5A, // 𐵚 [GARAY CAPITAL LETTER DA]
- };
- case 0x10D7D -> // 𐵽 [GARAY SMALL LETTER TA]
- new int[] {
- 0x10D5D, // 𐵝 [GARAY CAPITAL LETTER TA]
- };
- case 0x10D7C -> // 𐵼 [GARAY SMALL LETTER YA]
- new int[] {
- 0x10D5C, // 𐵜 [GARAY CAPITAL LETTER YA]
- };
- case 0x10D7F -> // 𐵿 [GARAY SMALL LETTER NYA]
- new int[] {
- 0x10D5F, // 𐵟 [GARAY CAPITAL LETTER NYA]
- };
- case 0x10D7E -> // 𐵾 [GARAY SMALL LETTER RA]
- new int[] {
- 0x10D5E, // 𐵞 [GARAY CAPITAL LETTER RA]
- };
- case 0x10D81 -> // 𐶁 [GARAY SMALL LETTER NA]
- new int[] {
- 0x10D61, // 𐵡 [GARAY CAPITAL LETTER NA]
- };
- case 0x10D80 -> // 𐶀 [GARAY SMALL LETTER FA]
- new int[] {
- 0x10D60, // 𐵠 [GARAY CAPITAL LETTER FA]
- };
- case 0x10D83 -> // 𐶃 [GARAY SMALL LETTER HA]
- new int[] {
- 0x10D63, // 𐵣 [GARAY CAPITAL LETTER HA]
- };
- case 0x10D82 -> // 𐶂 [GARAY SMALL LETTER PA]
- new int[] {
- 0x10D62, // 𐵢 [GARAY CAPITAL LETTER PA]
- };
- case 0x10D85 -> // 𐶅 [GARAY SMALL LETTER OLD NA]
- new int[] {
- 0x10D65, // 𐵥 [GARAY CAPITAL LETTER OLD NA]
- };
- case 0x10D84 -> // 𐶄 [GARAY SMALL LETTER OLD KA]
- new int[] {
- 0x10D64, // 𐵤 [GARAY CAPITAL LETTER OLD KA]
- };
- case 0x01E60 -> // Ṡ [LATIN CAPITAL LETTER S WITH DOT ABOVE]
- new int[] {
- 0x01E61, // ṡ [LATIN SMALL LETTER S WITH DOT ABOVE]
- 0x01E9B, // ẛ [LATIN SMALL LETTER LONG S WITH DOT ABOVE]
- };
- case 0x01E61 -> // ṡ [LATIN SMALL LETTER S WITH DOT ABOVE]
- new int[] {
- 0x01E60, // Ṡ [LATIN CAPITAL LETTER S WITH DOT ABOVE]
- 0x01E9B, // ẛ [LATIN SMALL LETTER LONG S WITH DOT ABOVE]
- };
- case 0x01E9B -> // ẛ [LATIN SMALL LETTER LONG S WITH DOT ABOVE]
- new int[] {
- 0x01E60, // Ṡ [LATIN CAPITAL LETTER S WITH DOT ABOVE]
- 0x01E61, // ṡ [LATIN SMALL LETTER S WITH DOT ABOVE]
- };
- case 0x01FBE -> // ι [GREEK PROSGEGRAMMENI]
- new int[] {
- 0x00345, // ͅ [COMBINING GREEK YPOGEGRAMMENI]
- 0x00399, // Ι [GREEK CAPITAL LETTER IOTA]
- 0x003B9, // ι [GREEK SMALL LETTER IOTA]
- };
- case 0x01FD3 -> // ΐ [GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA]
- new int[] {
- 0x00390, // ΐ [GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS]
- };
- case 0x01FE3 -> // ΰ [GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA]
- new int[] {
- 0x003B0, // ΰ [GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS]
- };
- default -> null;
- };
+/**
+ * This file contains unicode properties used by {@code RegExp}. The data was generated using ICU4J
+ * v74.2.0.0, unicode version: 15.1.0.0.
+ */
+final class CaseFolding {
+ private CaseFolding() {}
- return alts;
+ /** Calls {@code fn} consumer with {@code c} itself and its {@code scf} mappings. */
+ static void expand(int c, IntConsumer fn) {
+ // add codepoint
+ fn.accept(c);
+ // add uppercase from tables
+ int upper = Character.toUpperCase(c);
+ if (upper != c) {
+ fn.accept(upper);
+ }
+ // add lowercase from tables
+ int lower = Character.toLowerCase(c);
+ if (lower != c) {
+ fn.accept(lower);
+ }
+ // add special casing variants
+ switch (c) {
+ case 0x004B: // LATIN CAPITAL LETTER K
+ fn.accept(0x212A); // KELVIN SIGN
+ break;
+ case 0x0053: // LATIN CAPITAL LETTER S
+ fn.accept(0x017F); // LATIN SMALL LETTER LONG S
+ break;
+ case 0x006B: // LATIN SMALL LETTER K
+ fn.accept(0x212A); // KELVIN SIGN
+ break;
+ case 0x0073: // LATIN SMALL LETTER S
+ fn.accept(0x017F); // LATIN SMALL LETTER LONG S
+ break;
+ case 0x00B5: // MICRO SIGN
+ fn.accept(0x03BC); // GREEK SMALL LETTER MU
+ break;
+ case 0x00C5: // LATIN CAPITAL LETTER A WITH RING ABOVE
+ fn.accept(0x212B); // ANGSTROM SIGN
+ break;
+ case 0x00DF: // LATIN SMALL LETTER SHARP S
+ fn.accept(0x1E9E); // LATIN CAPITAL LETTER SHARP S
+ break;
+ case 0x00E5: // LATIN SMALL LETTER A WITH RING ABOVE
+ fn.accept(0x212B); // ANGSTROM SIGN
+ break;
+ case 0x017F: // LATIN SMALL LETTER LONG S
+ fn.accept(0x0073); // LATIN SMALL LETTER S
+ break;
+ case 0x01C4: // LATIN CAPITAL LETTER DZ WITH CARON
+ fn.accept(0x01C5); // LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON
+ break;
+ case 0x01C6: // LATIN SMALL LETTER DZ WITH CARON
+ fn.accept(0x01C5); // LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON
+ break;
+ case 0x01C7: // LATIN CAPITAL LETTER LJ
+ fn.accept(0x01C8); // LATIN CAPITAL LETTER L WITH SMALL LETTER J
+ break;
+ case 0x01C9: // LATIN SMALL LETTER LJ
+ fn.accept(0x01C8); // LATIN CAPITAL LETTER L WITH SMALL LETTER J
+ break;
+ case 0x01CA: // LATIN CAPITAL LETTER NJ
+ fn.accept(0x01CB); // LATIN CAPITAL LETTER N WITH SMALL LETTER J
+ break;
+ case 0x01CC: // LATIN SMALL LETTER NJ
+ fn.accept(0x01CB); // LATIN CAPITAL LETTER N WITH SMALL LETTER J
+ break;
+ case 0x01F1: // LATIN CAPITAL LETTER DZ
+ fn.accept(0x01F2); // LATIN CAPITAL LETTER D WITH SMALL LETTER Z
+ break;
+ case 0x01F3: // LATIN SMALL LETTER DZ
+ fn.accept(0x01F2); // LATIN CAPITAL LETTER D WITH SMALL LETTER Z
+ break;
+ case 0x0345: // COMBINING GREEK YPOGEGRAMMENI
+ fn.accept(0x03B9); // GREEK SMALL LETTER IOTA
+ fn.accept(0x1FBE); // GREEK PROSGEGRAMMENI
+ break;
+ case 0x0390: // GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
+ fn.accept(0x1FD3); // GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
+ break;
+ case 0x0392: // GREEK CAPITAL LETTER BETA
+ fn.accept(0x03D0); // GREEK BETA SYMBOL
+ break;
+ case 0x0395: // GREEK CAPITAL LETTER EPSILON
+ fn.accept(0x03F5); // GREEK LUNATE EPSILON SYMBOL
+ break;
+ case 0x0398: // GREEK CAPITAL LETTER THETA
+ fn.accept(0x03D1); // GREEK THETA SYMBOL
+ fn.accept(0x03F4); // GREEK CAPITAL THETA SYMBOL
+ break;
+ case 0x0399: // GREEK CAPITAL LETTER IOTA
+ fn.accept(0x0345); // COMBINING GREEK YPOGEGRAMMENI
+ fn.accept(0x1FBE); // GREEK PROSGEGRAMMENI
+ break;
+ case 0x039A: // GREEK CAPITAL LETTER KAPPA
+ fn.accept(0x03F0); // GREEK KAPPA SYMBOL
+ break;
+ case 0x039C: // GREEK CAPITAL LETTER MU
+ fn.accept(0x00B5); // MICRO SIGN
+ break;
+ case 0x03A0: // GREEK CAPITAL LETTER PI
+ fn.accept(0x03D6); // GREEK PI SYMBOL
+ break;
+ case 0x03A1: // GREEK CAPITAL LETTER RHO
+ fn.accept(0x03F1); // GREEK RHO SYMBOL
+ break;
+ case 0x03A3: // GREEK CAPITAL LETTER SIGMA
+ fn.accept(0x03C2); // GREEK SMALL LETTER FINAL SIGMA
+ break;
+ case 0x03A6: // GREEK CAPITAL LETTER PHI
+ fn.accept(0x03D5); // GREEK PHI SYMBOL
+ break;
+ case 0x03A9: // GREEK CAPITAL LETTER OMEGA
+ fn.accept(0x2126); // OHM SIGN
+ break;
+ case 0x03B0: // GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
+ fn.accept(0x1FE3); // GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
+ break;
+ case 0x03B2: // GREEK SMALL LETTER BETA
+ fn.accept(0x03D0); // GREEK BETA SYMBOL
+ break;
+ case 0x03B5: // GREEK SMALL LETTER EPSILON
+ fn.accept(0x03F5); // GREEK LUNATE EPSILON SYMBOL
+ break;
+ case 0x03B8: // GREEK SMALL LETTER THETA
+ fn.accept(0x03D1); // GREEK THETA SYMBOL
+ fn.accept(0x03F4); // GREEK CAPITAL THETA SYMBOL
+ break;
+ case 0x03B9: // GREEK SMALL LETTER IOTA
+ fn.accept(0x0345); // COMBINING GREEK YPOGEGRAMMENI
+ fn.accept(0x1FBE); // GREEK PROSGEGRAMMENI
+ break;
+ case 0x03BA: // GREEK SMALL LETTER KAPPA
+ fn.accept(0x03F0); // GREEK KAPPA SYMBOL
+ break;
+ case 0x03BC: // GREEK SMALL LETTER MU
+ fn.accept(0x00B5); // MICRO SIGN
+ break;
+ case 0x03C0: // GREEK SMALL LETTER PI
+ fn.accept(0x03D6); // GREEK PI SYMBOL
+ break;
+ case 0x03C1: // GREEK SMALL LETTER RHO
+ fn.accept(0x03F1); // GREEK RHO SYMBOL
+ break;
+ case 0x03C2: // GREEK SMALL LETTER FINAL SIGMA
+ fn.accept(0x03C3); // GREEK SMALL LETTER SIGMA
+ break;
+ case 0x03C3: // GREEK SMALL LETTER SIGMA
+ fn.accept(0x03C2); // GREEK SMALL LETTER FINAL SIGMA
+ break;
+ case 0x03C6: // GREEK SMALL LETTER PHI
+ fn.accept(0x03D5); // GREEK PHI SYMBOL
+ break;
+ case 0x03C9: // GREEK SMALL LETTER OMEGA
+ fn.accept(0x2126); // OHM SIGN
+ break;
+ case 0x03D0: // GREEK BETA SYMBOL
+ fn.accept(0x03B2); // GREEK SMALL LETTER BETA
+ break;
+ case 0x03D1: // GREEK THETA SYMBOL
+ fn.accept(0x03B8); // GREEK SMALL LETTER THETA
+ fn.accept(0x03F4); // GREEK CAPITAL THETA SYMBOL
+ break;
+ case 0x03D5: // GREEK PHI SYMBOL
+ fn.accept(0x03C6); // GREEK SMALL LETTER PHI
+ break;
+ case 0x03D6: // GREEK PI SYMBOL
+ fn.accept(0x03C0); // GREEK SMALL LETTER PI
+ break;
+ case 0x03F0: // GREEK KAPPA SYMBOL
+ fn.accept(0x03BA); // GREEK SMALL LETTER KAPPA
+ break;
+ case 0x03F1: // GREEK RHO SYMBOL
+ fn.accept(0x03C1); // GREEK SMALL LETTER RHO
+ break;
+ case 0x03F4: // GREEK CAPITAL THETA SYMBOL
+ fn.accept(0x0398); // GREEK CAPITAL LETTER THETA
+ fn.accept(0x03D1); // GREEK THETA SYMBOL
+ break;
+ case 0x03F5: // GREEK LUNATE EPSILON SYMBOL
+ fn.accept(0x03B5); // GREEK SMALL LETTER EPSILON
+ break;
+ case 0x0412: // CYRILLIC CAPITAL LETTER VE
+ fn.accept(0x1C80); // CYRILLIC SMALL LETTER ROUNDED VE
+ break;
+ case 0x0414: // CYRILLIC CAPITAL LETTER DE
+ fn.accept(0x1C81); // CYRILLIC SMALL LETTER LONG-LEGGED DE
+ break;
+ case 0x041E: // CYRILLIC CAPITAL LETTER O
+ fn.accept(0x1C82); // CYRILLIC SMALL LETTER NARROW O
+ break;
+ case 0x0421: // CYRILLIC CAPITAL LETTER ES
+ fn.accept(0x1C83); // CYRILLIC SMALL LETTER WIDE ES
+ break;
+ case 0x0422: // CYRILLIC CAPITAL LETTER TE
+ fn.accept(0x1C84); // CYRILLIC SMALL LETTER TALL TE
+ fn.accept(0x1C85); // CYRILLIC SMALL LETTER THREE-LEGGED TE
+ break;
+ case 0x042A: // CYRILLIC CAPITAL LETTER HARD SIGN
+ fn.accept(0x1C86); // CYRILLIC SMALL LETTER TALL HARD SIGN
+ break;
+ case 0x0432: // CYRILLIC SMALL LETTER VE
+ fn.accept(0x1C80); // CYRILLIC SMALL LETTER ROUNDED VE
+ break;
+ case 0x0434: // CYRILLIC SMALL LETTER DE
+ fn.accept(0x1C81); // CYRILLIC SMALL LETTER LONG-LEGGED DE
+ break;
+ case 0x043E: // CYRILLIC SMALL LETTER O
+ fn.accept(0x1C82); // CYRILLIC SMALL LETTER NARROW O
+ break;
+ case 0x0441: // CYRILLIC SMALL LETTER ES
+ fn.accept(0x1C83); // CYRILLIC SMALL LETTER WIDE ES
+ break;
+ case 0x0442: // CYRILLIC SMALL LETTER TE
+ fn.accept(0x1C84); // CYRILLIC SMALL LETTER TALL TE
+ fn.accept(0x1C85); // CYRILLIC SMALL LETTER THREE-LEGGED TE
+ break;
+ case 0x044A: // CYRILLIC SMALL LETTER HARD SIGN
+ fn.accept(0x1C86); // CYRILLIC SMALL LETTER TALL HARD SIGN
+ break;
+ case 0x0462: // CYRILLIC CAPITAL LETTER YAT
+ fn.accept(0x1C87); // CYRILLIC SMALL LETTER TALL YAT
+ break;
+ case 0x0463: // CYRILLIC SMALL LETTER YAT
+ fn.accept(0x1C87); // CYRILLIC SMALL LETTER TALL YAT
+ break;
+ case 0x1C80: // CYRILLIC SMALL LETTER ROUNDED VE
+ fn.accept(0x0432); // CYRILLIC SMALL LETTER VE
+ break;
+ case 0x1C81: // CYRILLIC SMALL LETTER LONG-LEGGED DE
+ fn.accept(0x0434); // CYRILLIC SMALL LETTER DE
+ break;
+ case 0x1C82: // CYRILLIC SMALL LETTER NARROW O
+ fn.accept(0x043E); // CYRILLIC SMALL LETTER O
+ break;
+ case 0x1C83: // CYRILLIC SMALL LETTER WIDE ES
+ fn.accept(0x0441); // CYRILLIC SMALL LETTER ES
+ break;
+ case 0x1C84: // CYRILLIC SMALL LETTER TALL TE
+ fn.accept(0x0442); // CYRILLIC SMALL LETTER TE
+ fn.accept(0x1C85); // CYRILLIC SMALL LETTER THREE-LEGGED TE
+ break;
+ case 0x1C85: // CYRILLIC SMALL LETTER THREE-LEGGED TE
+ fn.accept(0x0442); // CYRILLIC SMALL LETTER TE
+ fn.accept(0x1C84); // CYRILLIC SMALL LETTER TALL TE
+ break;
+ case 0x1C86: // CYRILLIC SMALL LETTER TALL HARD SIGN
+ fn.accept(0x044A); // CYRILLIC SMALL LETTER HARD SIGN
+ break;
+ case 0x1C87: // CYRILLIC SMALL LETTER TALL YAT
+ fn.accept(0x0463); // CYRILLIC SMALL LETTER YAT
+ break;
+ case 0x1C88: // CYRILLIC SMALL LETTER UNBLENDED UK
+ fn.accept(0xA64B); // CYRILLIC SMALL LETTER MONOGRAPH UK
+ break;
+ case 0x1E60: // LATIN CAPITAL LETTER S WITH DOT ABOVE
+ fn.accept(0x1E9B); // LATIN SMALL LETTER LONG S WITH DOT ABOVE
+ break;
+ case 0x1E61: // LATIN SMALL LETTER S WITH DOT ABOVE
+ fn.accept(0x1E9B); // LATIN SMALL LETTER LONG S WITH DOT ABOVE
+ break;
+ case 0x1E9B: // LATIN SMALL LETTER LONG S WITH DOT ABOVE
+ fn.accept(0x1E61); // LATIN SMALL LETTER S WITH DOT ABOVE
+ break;
+ case 0x1FBE: // GREEK PROSGEGRAMMENI
+ fn.accept(0x0345); // COMBINING GREEK YPOGEGRAMMENI
+ fn.accept(0x03B9); // GREEK SMALL LETTER IOTA
+ break;
+ case 0x1FD3: // GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
+ fn.accept(0x0390); // GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
+ break;
+ case 0x1FE3: // GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
+ fn.accept(0x03B0); // GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
+ break;
+ case 0x2126: // OHM SIGN
+ fn.accept(0x03A9); // GREEK CAPITAL LETTER OMEGA
+ break;
+ case 0x212A: // KELVIN SIGN
+ fn.accept(0x004B); // LATIN CAPITAL LETTER K
+ break;
+ case 0x212B: // ANGSTROM SIGN
+ fn.accept(0x00C5); // LATIN CAPITAL LETTER A WITH RING ABOVE
+ break;
+ case 0xA64A: // CYRILLIC CAPITAL LETTER MONOGRAPH UK
+ fn.accept(0x1C88); // CYRILLIC SMALL LETTER UNBLENDED UK
+ break;
+ case 0xA64B: // CYRILLIC SMALL LETTER MONOGRAPH UK
+ fn.accept(0x1C88); // CYRILLIC SMALL LETTER UNBLENDED UK
+ break;
+ case 0xFB05: // LATIN SMALL LIGATURE LONG S T
+ fn.accept(0xFB06); // LATIN SMALL LIGATURE ST
+ break;
+ case 0xFB06: // LATIN SMALL LIGATURE ST
+ fn.accept(0xFB05); // LATIN SMALL LIGATURE LONG S T
+ break;
+ }
}
}
diff --git a/lucene/core/src/java/org/apache/lucene/util/automaton/RegExp.java b/lucene/core/src/java/org/apache/lucene/util/automaton/RegExp.java
index 342efe05978..b10ed8ec30c 100644
--- a/lucene/core/src/java/org/apache/lucene/util/automaton/RegExp.java
+++ b/lucene/core/src/java/org/apache/lucene/util/automaton/RegExp.java
@@ -31,6 +31,7 @@ package org.apache.lucene.util.automaton;
import java.io.IOException;
import java.util.ArrayList;
+import java.util.Collections;
import java.util.HashSet;
import java.util.Iterator;
import java.util.List;
@@ -436,12 +437,11 @@ public class RegExp {
*
* <p>In general the attempt is to reach parity with {@link java.util.regex.Pattern}
* Pattern.CASE_INSENSITIVE and Pattern.UNICODE_CASE flags when doing a case-insensitive match. We
- * support common case folding in addition to simple case folding as defined by the common (C),
- * simple (S) and special (T) mappings in
- * https://www.unicode.org/Public/16.0.0/ucd/CaseFolding.txt. This is in line with {@link
- * java.util.regex.Pattern} and means characters like those representing the Greek symbol sigma
- * (Σ, σ, ς) will all match one another despite σ and ς both being lowercase characters as
- * detailed here: https://www.unicode.org/Public/UCD/latest/ucd/SpecialCasing.txt.
+ * support common case folding in addition to simple case folding as defined by the common (C) and
+ * simple (S) mappings in https://www.unicode.org/Public/16.0.0/ucd/CaseFolding.txt. This is in
+ * line with {@link java.util.regex.Pattern} and means characters like those representing the
+ * Greek symbol sigma (Σ, σ, ς) will all match one another despite σ and ς both being lowercase
+ * characters as detailed here: https://www.unicode.org/Public/UCD/latest/ucd/SpecialCasing.txt.
*
* <p>Some Unicode characters are difficult to correctly decode casing. In some cases Java's
* String class correctly handles decoding these but Java's {@link java.util.regex.Pattern} class
@@ -759,23 +759,14 @@ public class RegExp {
* @return the original codepoint and the set of alternates
*/
private int[] toCaseInsensitiveChar(int codepoint) {
- int[] altCodepoints = CaseFolding.lookupAlternates(codepoint);
- if (altCodepoints != null) {
- int[] concat = new int[altCodepoints.length + 1];
- System.arraycopy(altCodepoints, 0, concat, 0, altCodepoints.length);
- concat[altCodepoints.length] = codepoint;
- return concat;
- } else {
- int altCase =
- Character.isLowerCase(codepoint)
- ? Character.toUpperCase(codepoint)
- : Character.toLowerCase(codepoint);
- if (altCase != codepoint) {
- return new int[] {altCase, codepoint};
- } else {
- return new int[] {codepoint};
- }
- }
+ List<Integer> list = new ArrayList<>();
+ CaseFolding.expand(
+ codepoint,
+ (int variant) -> {
+ list.add(variant);
+ });
+ Collections.sort(list);
+ return list.stream().mapToInt(Integer::intValue).toArray();
}
private Automaton toCaseInsensitiveString() {
diff --git a/lucene/core/src/test/org/apache/lucene/util/automaton/TestRegExp.java b/lucene/core/src/test/org/apache/lucene/util/automaton/TestRegExp.java
index 234aa1525c7..37cb5ddfc6b 100644
--- a/lucene/core/src/test/org/apache/lucene/util/automaton/TestRegExp.java
+++ b/lucene/core/src/test/org/apache/lucene/util/automaton/TestRegExp.java
@@ -16,11 +16,7 @@
*/
package org.apache.lucene.util.automaton;
-import java.io.IOException;
-import java.util.HexFormat;
-import java.util.List;
import java.util.Locale;
-import java.util.Set;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.apache.lucene.tests.util.LuceneTestCase;
@@ -95,76 +91,6 @@ public class TestRegExp extends LuceneTestCase {
// class 3 Unicode characters behaves appropriately with different flags
r = new RegExp("ﬗ", RegExp.ALL, RegExp.CASE_INSENSITIVE);
assertFalse(new CharacterRunAutomaton(r.toAutomaton()).run("ﬗ".toUpperCase(Locale.ROOT)));
-
- r = new RegExp(new String(Character.toChars(0x1C8A)), RegExp.ALL, RegExp.CASE_INSENSITIVE);
- assertTrue(
- new CharacterRunAutomaton(r.toAutomaton()).run(new String(Character.toChars(0x1C89))));
- }
-
- public void testRandomUnicodeInsensitiveMatchPatternParity() {
- HexFormat hexFormat = HexFormat.of().withUpperCase();
- int maxIters = 1000;
- List<Integer> reservedCharacters =
- Set.of(
- '.', '^', '$', '*', '+', '?', '(', ')', '[', '{', '\\', '|', '-', '"', '<', '>',
- '#', '@', '&', '~')
- .stream()
- .map(c -> (int) c)
- .toList();
- for (int i = 0; i < maxIters; i++) {
- int nextCode1 = random().nextInt(0, Character.MAX_CODE_POINT + 1);
- int nextCode2 = random().nextInt(0, Character.MAX_CODE_POINT + 1);
-
- // skip if we select a reserved character that blows up .^$*+?()[{\|-]"<
- if (reservedCharacters.contains(nextCode1)) {
- continue;
- }
-
- String pattern = new String(Character.toChars(nextCode1));
- String altString = new String(Character.toChars(nextCode2));
-
- Pattern javaRegex = Pattern.compile(pattern, Pattern.CASE_INSENSITIVE | Pattern.UNICODE_CASE);
- RegExp r = new RegExp(pattern, RegExp.ALL, RegExp.CASE_INSENSITIVE);
- CharacterRunAutomaton cra = new CharacterRunAutomaton(r.toAutomaton());
-
- // Pattern doesn't respect the Unicode spec so some things will not match
- if (javaRegex.matcher(altString).matches()) {
- // ... but if they do match then we must agree
- assertTrue(
- "Pattern and RegExp disagree on pattern: "
- + hexFormat.toHexDigits(nextCode1, 4)
- + " :text: "
- + hexFormat.toHexDigits(nextCode2, 4),
- cra.run(altString));
- }
- }
- }
-
- public void testUnicodeInsensitiveMatchPatternParity() throws IOException {
- // this ensures that if the Pattern class behavior were to change with a change to the Unicode
- // spec then we would pick it up. It may help indicate in the future if we don't notice
- // that the spec has changed and Pattern picks up the change first
- for (int codepoint = 0; codepoint < Character.MAX_CODE_POINT + 1; codepoint++) {
- int[] caseInsensitiveAlternatives = CaseFolding.lookupAlternates(codepoint);
- if (caseInsensitiveAlternatives != null) {
- String pattern = new String(Character.toChars(codepoint));
- Pattern javaRegex =
- Pattern.compile(pattern, Pattern.CASE_INSENSITIVE | Pattern.UNICODE_CASE);
- RegExp r = new RegExp(pattern, RegExp.ALL, RegExp.CASE_INSENSITIVE);
- CharacterRunAutomaton cra = new CharacterRunAutomaton(r.toAutomaton());
- for (int i = 0; i < caseInsensitiveAlternatives.length; i++) {
-
- int alt = caseInsensitiveAlternatives[i];
- String altString = new String(Character.toChars(alt));
-
- // Pattern doesn't respect the Unicode spec so some things will not match
- if (javaRegex.matcher(altString).matches()) {
- // ... but if they do match then we must agree
- assertTrue(cra.run(altString));
- }
- }
- }
- }
}
// LUCENE-6046