001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *      http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017package org.apache.commons.text.translate;
018
019import java.io.IOException;
020import java.io.StringWriter;
021import java.io.UncheckedIOException;
022import java.io.Writer;
023import java.util.Locale;
024
025import org.apache.commons.lang3.Validate;
026
027/**
028 * An API for translating text.
029 * Its core use is to escape and unescape text. Because escaping and unescaping
030 * is completely contextual, the API does not present two separate signatures.
031 *
032 * @since 1.0
033 */
034public abstract class CharSequenceTranslator {
035
036    /**
037     * Array containing the hexadecimal alphabet.
038     */
039    static final char[] HEX_DIGITS = { '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C', 'D', 'E', 'F' };
040
041    /**
042     * Returns an upper case hexadecimal {@code String} for the given
043     * character.
044     *
045     * @param codePoint The code point to convert.
046     * @return An upper case hexadecimal {@code String}
047     */
048    public static String hex(final int codePoint) {
049        return Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH);
050    }
051
052    /**
053     * Helper for non-Writer usage.
054     * @param input CharSequence to be translated
055     * @return String output of translation
056     */
057    public final String translate(final CharSequence input) {
058        if (input == null) {
059            return null;
060        }
061        try {
062            final StringWriter writer = new StringWriter(input.length() * 2);
063            translate(input, writer);
064            return writer.toString();
065        } catch (final IOException ioe) {
066            // this should never ever happen while writing to a StringWriter
067            throw new UncheckedIOException(ioe);
068        }
069    }
070
071    /**
072     * Translate a set of code points, represented by an int index into a CharSequence,
073     * into another set of code points. The number of code points consumed must be returned,
074     * and the only IOExceptions thrown must be from interacting with the Writer so that
075     * the top level API may reliably ignore StringWriter IOExceptions.
076     *
077     * @param input CharSequence that is being translated
078     * @param index int representing the current point of translation
079     * @param writer Writer to translate the text to
080     * @return int count of code points consumed
081     * @throws IOException if and only if the Writer produces an IOException
082     */
083    public abstract int translate(CharSequence input, int index, Writer writer) throws IOException;
084
085    /**
086     * Translate an input onto a Writer. This is intentionally final as its algorithm is
087     * tightly coupled with the abstract method of this class.
088     *
089     * @param input CharSequence that is being translated
090     * @param writer Writer to translate the text to
091     * @throws IOException if and only if the Writer produces an IOException
092     */
093    public final void translate(final CharSequence input, final Writer writer) throws IOException {
094        Validate.isTrue(writer != null, "The Writer must not be null");
095        if (input == null) {
096            return;
097        }
098        int pos = 0;
099        final int len = input.length();
100        while (pos < len) {
101            final int consumed = translate(input, pos, writer);
102            if (consumed == 0) {
103                // inlined implementation of Character.toChars(Character.codePointAt(input, pos))
104                // avoids allocating temp char arrays and duplicate checks
105                final char c1 = input.charAt(pos);
106                writer.write(c1);
107                pos++;
108                if (Character.isHighSurrogate(c1) && pos < len) {
109                    final char c2 = input.charAt(pos);
110                    if (Character.isLowSurrogate(c2)) {
111                      writer.write(c2);
112                      pos++;
113                    }
114                }
115                continue;
116            }
117            // contract with translators is that they have to understand code points
118            // and they just took care of a surrogate pair
119            for (int pt = 0; pt < consumed; pt++) {
120                pos += Character.charCount(Character.codePointAt(input, pos));
121            }
122        }
123    }
124
125    /**
126     * Helper method to create a merger of this translator with another set of
127     * translators. Useful in customizing the standard functionality.
128     *
129     * @param translators CharSequenceTranslator array of translators to merge with this one
130     * @return CharSequenceTranslator merging this translator with the others
131     */
132    public final CharSequenceTranslator with(final CharSequenceTranslator... translators) {
133        final CharSequenceTranslator[] newArray = new CharSequenceTranslator[translators.length + 1];
134        newArray[0] = this;
135        System.arraycopy(translators, 0, newArray, 1, translators.length);
136        return new AggregateTranslator(newArray);
137    }
138
139}