SequenceComparator.java

  1. /*
  2.  * Copyright (C) 2010, Google Inc.
  3.  * and other copyright owners as documented in the project's IP log.
  4.  *
  5.  * This program and the accompanying materials are made available
  6.  * under the terms of the Eclipse Distribution License v1.0 which
  7.  * accompanies this distribution, is reproduced below, and is
  8.  * available at http://www.eclipse.org/org/documents/edl-v10.php
  9.  *
  10.  * All rights reserved.
  11.  *
  12.  * Redistribution and use in source and binary forms, with or
  13.  * without modification, are permitted provided that the following
  14.  * conditions are met:
  15.  *
  16.  * - Redistributions of source code must retain the above copyright
  17.  *   notice, this list of conditions and the following disclaimer.
  18.  *
  19.  * - Redistributions in binary form must reproduce the above
  20.  *   copyright notice, this list of conditions and the following
  21.  *   disclaimer in the documentation and/or other materials provided
  22.  *   with the distribution.
  23.  *
  24.  * - Neither the name of the Eclipse Foundation, Inc. nor the
  25.  *   names of its contributors may be used to endorse or promote
  26.  *   products derived from this software without specific prior
  27.  *   written permission.
  28.  *
  29.  * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
  30.  * CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
  31.  * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
  32.  * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  33.  * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
  34.  * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
  35.  * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
  36.  * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
  37.  * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
  38.  * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
  39.  * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
  40.  * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
  41.  * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  42.  */

  43. package org.eclipse.jgit.diff;

  44. /**
  45.  * Equivalence function for a {@link org.eclipse.jgit.diff.Sequence} compared by
  46.  * difference algorithm.
  47.  * <p>
  48.  * Difference algorithms can use a comparator to compare portions of two
  49.  * sequences and discover the minimal edits required to transform from one
  50.  * sequence to the other sequence.
  51.  * <p>
  52.  * Indexes within a sequence are zero-based.
  53.  *
  54.  * @param <S>
  55.  *            type of sequence the comparator supports.
  56.  */
  57. public abstract class SequenceComparator<S extends Sequence> {
  58.     /**
  59.      * Compare two items to determine if they are equivalent.
  60.      *
  61.      * It is permissible to compare sequence {@code a} with itself (by passing
  62.      * {@code a} again in position {@code b}).
  63.      *
  64.      * @param a
  65.      *            the first sequence.
  66.      * @param ai
  67.      *            item of {@code ai} to compare.
  68.      * @param b
  69.      *            the second sequence.
  70.      * @param bi
  71.      *            item of {@code bi} to compare.
  72.      * @return true if the two items are identical according to this function's
  73.      *         equivalence rule.
  74.      */
  75.     public abstract boolean equals(S a, int ai, S b, int bi);

  76.     /**
  77.      * Get a hash value for an item in a sequence.
  78.      *
  79.      * If two items are equal according to this comparator's
  80.      * {@link #equals(Sequence, int, Sequence, int)} method, then this hash
  81.      * method must produce the same integer result for both items.
  82.      *
  83.      * It is not required for two items to have different hash values if they
  84.      * are unequal according to the {@code equals()} method.
  85.      *
  86.      * @param seq
  87.      *            the sequence.
  88.      * @param ptr
  89.      *            the item to obtain the hash for.
  90.      * @return hash the hash value.
  91.      */
  92.     public abstract int hash(S seq, int ptr);

  93.     /**
  94.      * Modify the edit to remove common leading and trailing items.
  95.      *
  96.      * The supplied edit {@code e} is reduced in size by moving the beginning A
  97.      * and B points so the edit does not cover any items that are in common
  98.      * between the two sequences. The ending A and B points are also shifted to
  99.      * remove common items from the end of the region.
  100.      *
  101.      * @param a
  102.      *            the first sequence.
  103.      * @param b
  104.      *            the second sequence.
  105.      * @param e
  106.      *            the edit to start with and update.
  107.      * @return {@code e} if it was updated in-place, otherwise a new edit
  108.      *         containing the reduced region.
  109.      */
  110.     public Edit reduceCommonStartEnd(S a, S b, Edit e) {
  111.         // Skip over items that are common at the start.
  112.         //
  113.         while (e.beginA < e.endA && e.beginB < e.endB
  114.                 && equals(a, e.beginA, b, e.beginB)) {
  115.             e.beginA++;
  116.             e.beginB++;
  117.         }

  118.         // Skip over items that are common at the end.
  119.         //
  120.         while (e.beginA < e.endA && e.beginB < e.endB
  121.                 && equals(a, e.endA - 1, b, e.endB - 1)) {
  122.             e.endA--;
  123.             e.endB--;
  124.         }

  125.         return e;
  126.     }
  127. }