/*
Copyright (c) 2008 Health Market Science, Inc.

Licensed 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 com.healthmarketscience.jackcess.impl;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.Arrays;
import java.util.HashMap;
import java.util.Map;

import static com.healthmarketscience.jackcess.impl.ByteUtil.ByteStream;

/**
 * Various constants used for creating "general legacy" (access 2000-2007)
 * sort order text index entries.
 *
 * @author James Ahlborn
 */
public class GeneralLegacyIndexCodes {

  static final int MAX_TEXT_INDEX_CHAR_LENGTH =
    (JetFormat.TEXT_FIELD_MAX_LENGTH / JetFormat.TEXT_FIELD_UNIT_SIZE);

  static final byte END_TEXT = (byte)0x01;
  static final byte END_EXTRA_TEXT = (byte)0x00;

  // unprintable char is removed from normal text.
  // pattern for unprintable chars in the extra bytes:
  // 01 01 01 <pos> 06  <code> )
  // <pos> = 7 + (4 * char_pos) | 0x8000 (as short)
  // <code> = char code
  static final int UNPRINTABLE_COUNT_START = 7;
  static final int UNPRINTABLE_COUNT_MULTIPLIER = 4;
  static final int UNPRINTABLE_OFFSET_FLAGS = 0x8000;
  static final byte UNPRINTABLE_MIDFIX = (byte)0x06;

  // international char is replaced with ascii char.
  // pattern for international chars in the extra bytes:
  // [ 02 (for each normal char) ] [ <symbol_code> (for each inat char) ]
  static final byte INTERNATIONAL_EXTRA_PLACEHOLDER = (byte)0x02;

  // see Index.writeCrazyCodes for details on writing crazy codes
  static final byte CRAZY_CODE_START = (byte)0x80;
  static final byte CRAZY_CODE_1 = (byte)0x02;
  static final byte CRAZY_CODE_2 = (byte)0x03;
  static final byte[] CRAZY_CODES_SUFFIX =
    new byte[]{(byte)0xFF, (byte)0x02, (byte)0x80, (byte)0xFF, (byte)0x80};
  static final byte CRAZY_CODES_UNPRINT_SUFFIX = (byte)0xFF;

  // stash the codes in some resource files
  private static final String CODES_FILE =
    DatabaseImpl.RESOURCE_PATH + "index_codes_genleg.txt";
  private static final String EXT_CODES_FILE =
    DatabaseImpl.RESOURCE_PATH + "index_codes_ext_genleg.txt";

  /**
   * Enum which classifies the types of char encoding strategies used when
   * creating text index entries.
   */
  enum Type {
    SIMPLE("S") {
      @Override public CharHandler parseCodes(String[] codeStrings) {
        return parseSimpleCodes(codeStrings);
      }
    },
    INTERNATIONAL("I") {
      @Override public CharHandler parseCodes(String[] codeStrings) {
        return parseInternationalCodes(codeStrings);
      }
    },
    UNPRINTABLE("U") {
      @Override public CharHandler parseCodes(String[] codeStrings) {
        return parseUnprintableCodes(codeStrings);
      }
    },
    UNPRINTABLE_EXT("P") {
      @Override public CharHandler parseCodes(String[] codeStrings) {
        return parseUnprintableExtCodes(codeStrings);
      }
    },
    INTERNATIONAL_EXT("Z") {
      @Override public CharHandler parseCodes(String[] codeStrings) {
        return parseInternationalExtCodes(codeStrings);
      }
    },
    SIGNIFICANT("G") {
      @Override public CharHandler parseCodes(String[] codeStrings) {
        return parseSignificantCodes(codeStrings);
      }
    },
    IGNORED("X") {
      @Override public CharHandler parseCodes(String[] codeStrings) {
        return IGNORED_CHAR_HANDLER;
      }
    };

    private final String _prefixCode;

    private Type(String prefixCode) {
      _prefixCode = prefixCode;
    }

    public String getPrefixCode() {
      return _prefixCode;
    }

    public abstract CharHandler parseCodes(String[] codeStrings);
  }

  /**
   * Base class for the handlers which hold the text index character encoding
   * information.
   */
  abstract static class CharHandler {
    public abstract Type getType();
    public byte[] getInlineBytes() {
      return null;
    }
    public byte[] getExtraBytes() {
      return null;
    }
    public byte[] getUnprintableBytes() {
      return null;
    }
    public byte getExtraByteModifier() {
      return 0;
    }
    public byte getCrazyFlag() {
      return 0;
    }
    public boolean isSignificantChar() {
      return false;
    }
  }

  /**
   * CharHandler for Type.SIMPLE
   */
  private static final class SimpleCharHandler extends CharHandler {
    private final byte[] _bytes;
    private SimpleCharHandler(byte[] bytes) {
      _bytes = bytes;
    }
    @Override public Type getType() {
      return Type.SIMPLE;
    }
    @Override public byte[] getInlineBytes() {