lucene/analysis/common/src/tools/groovy/generate-unicode-data.groovy

/*
 * 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.
 */

import com.ibm.icu.lang.UCharacter;
import com.ibm.icu.util.VersionInfo;

def linesep = properties['line.separator'];

def appendChar = { StringBuilder sb, int c ->
  int len = sb.length();
  if (len != 0) {
    sb.append(', ');
  }
  if (len == 0 || len - sb.lastIndexOf(linesep) > 100) {
    sb.append(linesep).append('    ');
  }
  sb.append(String.format(Locale.ROOT, "0x%04X", c));
}

def whitespace = new StringBuilder();
for (int c = UCharacter.MIN_CODE_POINT; c <= UCharacter.MAX_CODE_POINT; c++) {
  if (UCharacter.isUWhiteSpace(c)) {
    appendChar(whitespace, c);
  }
}

def icuVersion = VersionInfo.ICU_VERSION.toString();
def unicodeVersion = UCharacter.getUnicodeVersion().toString();

def code = """
// DO NOT EDIT THIS FILE! Use "ant unicode-data" 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.analysis.util;

import org.apache.lucene.util.Bits;
import org.apache.lucene.util.SparseFixedBitSet;

/**
 * This file contains unicode properties used by various {@link CharTokenizer}s.
 * The data was created using ICU4J v${icuVersion}
 * <p>
 * Unicode version: ${unicodeVersion}
 */
public final class UnicodeProps {
  private UnicodeProps() {}
  
  /** Unicode version that was used to generate this file: {@value} */
  public static final String UNICODE_VERSION = "${unicodeVersion}";
  
  /** Bitset with Unicode WHITESPACE code points. */
  public static final Bits WHITESPACE = createBits(${whitespace});
  
  private static Bits createBits(final int... codepoints) {
    final int len = codepoints[codepoints.length - 1] + 1;
    final SparseFixedBitSet bitset = new SparseFixedBitSet(len);
    for (int i : codepoints) bitset.set(i);
    return new Bits() {
      @Override
      public boolean get(int index) {
        return index < len && bitset.get(index);
      }
      
      @Override
      public int length() {
        return ${String.format(Locale.ROOT, "0x%X", UCharacter.MAX_CODE_POINT)} + 1;
      }
    };
  }
}
""";

File f = new File(properties['unicode-props-file']);
f.write(code.trim(), 'UTF-8');

task.log("Unicode data written to: " + f);