View Javadoc
1   /*
2    * Licensed to the Apache Software Foundation (ASF) under one or more
3    * contributor license agreements.  See the NOTICE file distributed with
4    * this work for additional information regarding copyright ownership.
5    * The ASF licenses this file to You under the Apache License, Version 2.0
6    * (the "License"); you may not use this file except in compliance with
7    * the License.  You may obtain a copy of the License at
8    *
9    *      https://www.apache.org/licenses/LICENSE-2.0
10   *
11   * Unless required by applicable law or agreed to in writing, software
12   * distributed under the License is distributed on an "AS IS" BASIS,
13   * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14   * See the License for the specific language governing permissions and
15   * limitations under the License.
16   */
17  
18  package org.apache.commons.text.similarity;
19  
20  import java.util.Arrays;
21  
22  /**
23   * An algorithm for measuring the difference between two character sequences.
24   *
25   * <p>
26   * This is the number of changes needed to change one sequence into another, where each change is a single character modification (deletion, insertion or
27   * substitution).
28   * </p>
29   *
30   * @since 1.0
31   */
32  public class LevenshteinDetailedDistance implements EditDistance<LevenshteinResults> {
33  
34      /**
35       * The singleton instance.
36       */
37      private static final LevenshteinDetailedDistance INSTANCE = new LevenshteinDetailedDistance();
38  
39      /**
40       * Finds count for each of the three [insert, delete, substitute] operations needed. This is based on the matrix formed based on the two character sequence.
41       *
42       * @param <E>     The type of similarity score unit.
43       * @param left    character sequence which need to be converted from.
44       * @param right   character sequence which need to be converted to.
45       * @param matrix  two dimensional array containing.
46       * @param swapped tells whether the value for left character sequence and right character sequence were swapped to save memory.
47       * @return result object containing the count of insert, delete and substitute and total count needed.
48       */
49      private static <E> LevenshteinResults findDetailedResults(final SimilarityInput<E> left, final SimilarityInput<E> right, final int[][] matrix,
50              final boolean swapped) {
51          int delCount = 0;
52          int addCount = 0;
53          int subCount = 0;
54          int rowIndex = right.length();
55          int columnIndex = left.length();
56          int dataAtLeft = 0;
57          int dataAtTop = 0;
58          int dataAtDiagonal = 0;
59          int data = 0;
60          boolean deleted = false;
61          boolean added = false;
62          while (rowIndex >= 0 && columnIndex >= 0) {
63              if (columnIndex == 0) {
64                  dataAtLeft = -1;
65              } else {
66                  dataAtLeft = matrix[rowIndex][columnIndex - 1];
67              }
68              if (rowIndex == 0) {
69                  dataAtTop = -1;
70              } else {
71                  dataAtTop = matrix[rowIndex - 1][columnIndex];
72              }
73              if (rowIndex > 0 && columnIndex > 0) {
74                  dataAtDiagonal = matrix[rowIndex - 1][columnIndex - 1];
75              } else {
76                  dataAtDiagonal = -1;
77              }
78              if (dataAtLeft == -1 && dataAtTop == -1 && dataAtDiagonal == -1) {
79                  break;
80              }
81              data = matrix[rowIndex][columnIndex];
82              // case in which the character at left and right are the same,
83              // in this case none of the counters will be incremented.
84              if (columnIndex > 0 && rowIndex > 0 && left.at(columnIndex - 1).equals(right.at(rowIndex - 1))) {
85                  columnIndex--;
86                  rowIndex--;
87                  continue;
88              }
89              // handling insert and delete cases.
90              deleted = false;
91              added = false;
92              if (data - 1 == dataAtLeft && data <= dataAtDiagonal && data <= dataAtTop || dataAtDiagonal == -1 && dataAtTop == -1) { // NOPMD
93                  columnIndex--;
94                  if (swapped) {
95                      addCount++;
96                      added = true;
97                  } else {
98                      delCount++;
99                      deleted = true;
100                 }
101             } else if (data - 1 == dataAtTop && data <= dataAtDiagonal && data <= dataAtLeft || dataAtDiagonal == -1 && dataAtLeft == -1) { // NOPMD
102                 rowIndex--;
103                 if (swapped) {
104                     delCount++;
105                     deleted = true;
106                 } else {
107                     addCount++;
108                     added = true;
109                 }
110             }
111             // substituted case
112             if (!added && !deleted) {
113                 subCount++;
114                 columnIndex--;
115                 rowIndex--;
116             }
117         }
118         return new LevenshteinResults(addCount + delCount + subCount, addCount, delCount, subCount);
119     }
120 
121     /**
122      * Gets the default instance.
123      *
124      * @return The default instace
125      */
126     public static LevenshteinDetailedDistance getDefaultInstance() {
127         return INSTANCE;
128     }
129 
130     /**
131      * Finds the Levenshtein distance between two CharSequences if it's less than or equal to a given threshold.
132      *
133      * <p>
134      * This implementation follows from Algorithms on Strings, Trees and Sequences by Dan Gusfield and Chas Emerick's implementation of the Levenshtein distance
135      * algorithm from <a href="https://www.merriampark.com/ld.htm" >http://www.merriampark.com/ld.htm</a>
136      * </p>
137      *
138      * <pre>
139      * limitedCompare(null, *, *)             = Throws {@link IllegalArgumentException}
140      * limitedCompare(*, null, *)             = Throws {@link IllegalArgumentException}
141      * limitedCompare(*, *, -1)               = Throws {@link IllegalArgumentException}
142      * limitedCompare("","", 0)               = 0
143      * limitedCompare("aaapppp", "", 8)       = 7
144      * limitedCompare("aaapppp", "", 7)       = 7
145      * limitedCompare("aaapppp", "", 6))      = -1
146      * limitedCompare("elephant", "hippo", 7) = 7
147      * limitedCompare("elephant", "hippo", 6) = -1
148      * limitedCompare("hippo", "elephant", 7) = 7
149      * limitedCompare("hippo", "elephant", 6) = -1
150      * </pre>
151      *
152      * @param <E>       The type of similarity score unit.
153      * @param left      the first CharSequence, must not be null.
154      * @param right     the second CharSequence, must not be null.
155      * @param threshold the target threshold, must not be negative.
156      * @return result distance, or -1.
157      */
158     private static <E> LevenshteinResults limitedCompare(SimilarityInput<E> left, SimilarityInput<E> right, final int threshold) { // NOPMD
159         if (left == null || right == null) {
160             throw new IllegalArgumentException("CharSequences must not be null");
161         }
162 
163         /*
164          * This implementation only computes the distance if it's less than or equal to the threshold value, returning -1 if it's greater. The advantage is
165          * performance: unbounded distance is O(nm), but a bound of k allows us to reduce it to O(km) time by only computing a diagonal stripe of width 2k + 1
166          * of the cost table. It is also possible to use this to compute the unbounded Levenshtein distance by starting the threshold at 1 and doubling each
167          * time until the distance is found; this is O(dm), where d is the distance.
168          *
169          * One subtlety comes from needing to ignore entries on the border of our stripe, for example,
170          * p[] = |#|#|#|* d[] = *|#|#|#| We must ignore the entry to the left
171          * of the leftmost member We must ignore the entry above the rightmost member
172          *
173          * Another subtlety comes from our stripe running off the matrix if the strings aren't of the same size. Since string s is always swapped to be the
174          * shorter of the two, the stripe will always run off to the upper right instead of the lower left of the matrix.
175          *
176          * As a concrete example, suppose s is of length 5, t is of length 7, and our threshold is 1. In this case we're going to walk a stripe of length 3. The
177          * matrix would look like so:
178          *
179          * <pre> 1 2 3 4 5 1 |#|#| | | | 2 |#|#|#| | | 3 | |#|#|#| | 4 | | |#|#|#| 5 | | | |#|#| 6 | | | | |#| 7 | | | | | | </pre>
180          *
181          * Note how the stripe leads off the table as there is no possible way to turn a string of length 5 into one of length 7 in edit distance of 1.
182          *
183          * Additionally, this implementation decreases memory usage by using two single-dimensional arrays and swapping them back and forth instead of
184          * allocating an entire n by m matrix. This requires a few minor changes, such as immediately returning when it's detected that the stripe has run off
185          * the matrix and initially filling the arrays with large values so that entries we don't compute are ignored.
186          *
187          * See Algorithms on Strings, Trees and Sequences by Dan Gusfield for some discussion.
188          */
189         int n = left.length(); // length of left
190         int m = right.length(); // length of right
191         // if one string is empty, the edit distance is necessarily the length of the other
192         if (n == 0) {
193             return m <= threshold ? new LevenshteinResults(m, m, 0, 0) : new LevenshteinResults(-1, 0, 0, 0);
194         }
195         if (m == 0) {
196             return n <= threshold ? new LevenshteinResults(n, 0, n, 0) : new LevenshteinResults(-1, 0, 0, 0);
197         }
198         boolean swapped = false;
199         if (n > m) {
200             // swap the two strings to consume less memory
201             final SimilarityInput<E> tmp = left;
202             left = right;
203             right = tmp;
204             n = m;
205             m = right.length();
206             swapped = true;
207         }
208         int[] p = new int[n + 1]; // 'previous' cost array, horizontally
209         int[] d = new int[n + 1]; // cost array, horizontally
210         int[] tempD; // placeholder to assist in swapping p and d
211         final int[][] matrix = new int[m + 1][n + 1];
212         // filling the first row and first column values in the matrix
213         for (int index = 0; index <= n; index++) {
214             matrix[0][index] = index;
215         }
216         for (int index = 0; index <= m; index++) {
217             matrix[index][0] = index;
218         }
219         // fill in starting table values
220         final int boundary = Math.min(n, threshold) + 1;
221         for (int i = 0; i < boundary; i++) {
222             p[i] = i;
223         }
224         // these fills ensure that the value above the rightmost entry of our
225         // stripe will be ignored in following loop iterations
226         Arrays.fill(p, boundary, p.length, Integer.MAX_VALUE);
227         Arrays.fill(d, Integer.MAX_VALUE);
228         // iterates through t
229         for (int j = 1; j <= m; j++) {
230             final E rightJ = right.at(j - 1); // jth character of right
231             d[0] = j;
232             // compute stripe indices, constrain to array size
233             final int min = Math.max(1, j - threshold);
234             final int max = j > Integer.MAX_VALUE - threshold ? n : Math.min(n, j + threshold);
235             // the stripe may lead off of the table if s and t are of different sizes
236             if (min > max) {
237                 return new LevenshteinResults(-1, 0, 0, 0);
238             }
239             // ignore entry left of leftmost
240             if (min > 1) {
241                 d[min - 1] = Integer.MAX_VALUE;
242             }
243             // iterates through [min, max] in s
244             for (int i = min; i <= max; i++) {
245                 if (left.at(i - 1).equals(rightJ)) {
246                     // diagonally left and up
247                     d[i] = p[i - 1];
248                 } else {
249                     // 1 + minimum of cell to the left, to the top, diagonally left and up
250                     d[i] = 1 + Math.min(Math.min(d[i - 1], p[i]), p[i - 1]);
251                 }
252                 matrix[j][i] = d[i];
253             }
254             // copy current distance counts to 'previous row' distance counts
255             tempD = p;
256             p = d;
257             d = tempD;
258         }
259         // if p[n] is greater than the threshold, there's no guarantee on it being the correct distance
260         if (p[n] <= threshold) {
261             return findDetailedResults(left, right, matrix, swapped);
262         }
263         return new LevenshteinResults(-1, 0, 0, 0);
264     }
265 
266     /**
267      * Finds the Levenshtein distance between two Strings.
268      *
269      * <p>
270      * A higher score indicates a greater distance.
271      * </p>
272      *
273      * <p>
274      * The previous implementation of the Levenshtein distance algorithm was from
275      * <a href="https://www.merriampark.com/ld.htm">http://www.merriampark.com/ld.htm</a>
276      * </p>
277      *
278      * <p>
279      * Chas Emerick has written an implementation in Java, which avoids an OutOfMemoryError which can occur when my Java implementation is used with very large
280      * strings.<br>
281      * This implementation of the Levenshtein distance algorithm is from
282      * <a href="https://www.merriampark.com/ldjava.htm">http://www.merriampark.com/ldjava.htm</a>
283      * </p>
284      *
285      * <pre>
286      * unlimitedCompare(null, *)             = Throws {@link IllegalArgumentException}
287      * unlimitedCompare(*, null)             = Throws {@link IllegalArgumentException}
288      * unlimitedCompare("","")               = 0
289      * unlimitedCompare("","a")              = 1
290      * unlimitedCompare("aaapppp", "")       = 7
291      * unlimitedCompare("frog", "fog")       = 1
292      * unlimitedCompare("fly", "ant")        = 3
293      * unlimitedCompare("elephant", "hippo") = 7
294      * unlimitedCompare("hippo", "elephant") = 7
295      * unlimitedCompare("hippo", "zzzzzzzz") = 8
296      * unlimitedCompare("hello", "hallo")    = 1
297      * </pre>
298      *
299      * @param <E>   The type of similarity score unit.
300      * @param left  the first CharSequence, must not be null.
301      * @param right the second CharSequence, must not be null.
302      * @return result distance, or -1.
303      * @throws IllegalArgumentException if either CharSequence input is {@code null}.
304      */
305     private static <E> LevenshteinResults unlimitedCompare(SimilarityInput<E> left, SimilarityInput<E> right) {
306         if (left == null || right == null) {
307             throw new IllegalArgumentException("CharSequences must not be null");
308         }
309         /*
310          * The difference between this impl. and the previous is that, rather than creating and retaining a matrix of size s.length() + 1 by t.length() + 1, we
311          * maintain two single-dimensional arrays of length s.length() + 1. The first, d, is the 'current working' distance array that maintains the newest
312          * distance cost counts as we iterate through the characters of String s. Each time we increment the index of String t we are comparing, d is copied to
313          * p, the second int[]. Doing so allows us to retain the previous cost counts as required by the algorithm (taking the minimum of the cost count to the
314          * left, up one, and diagonally up and to the left of the current cost count being calculated). (Note that the arrays aren't really copied anymore, just
315          * switched...this is clearly much better than cloning an array or doing a System.arraycopy() each time through the outer loop.)
316          *
317          * Effectively, the difference between the two implementations is this one does not cause an out of memory condition when calculating the LD over two
318          * very large strings.
319          */
320         int n = left.length(); // length of left
321         int m = right.length(); // length of right
322         if (n == 0) {
323             return new LevenshteinResults(m, m, 0, 0);
324         }
325         if (m == 0) {
326             return new LevenshteinResults(n, 0, n, 0);
327         }
328         boolean swapped = false;
329         if (n > m) {
330             // swap the input strings to consume less memory
331             final SimilarityInput<E> tmp = left;
332             left = right;
333             right = tmp;
334             n = m;
335             m = right.length();
336             swapped = true;
337         }
338         int[] p = new int[n + 1]; // 'previous' cost array, horizontally
339         int[] d = new int[n + 1]; // cost array, horizontally
340         int[] tempD; // placeholder to assist in swapping p and d
341         final int[][] matrix = new int[m + 1][n + 1];
342         // filling the first row and first column values in the matrix
343         for (int index = 0; index <= n; index++) {
344             matrix[0][index] = index;
345         }
346         for (int index = 0; index <= m; index++) {
347             matrix[index][0] = index;
348         }
349         // indexes into strings left and right
350         int i; // iterates through left
351         int j; // iterates through right
352         E rightJ; // jth character of right
353         int cost; // cost
354         for (i = 0; i <= n; i++) {
355             p[i] = i;
356         }
357         for (j = 1; j <= m; j++) {
358             rightJ = right.at(j - 1);
359             d[0] = j;
360             for (i = 1; i <= n; i++) {
361                 cost = left.at(i - 1).equals(rightJ) ? 0 : 1;
362                 // minimum of cell to the left+1, to the top+1, diagonally left and up +cost
363                 d[i] = Math.min(Math.min(d[i - 1] + 1, p[i] + 1), p[i - 1] + cost);
364                 // filling the matrix
365                 matrix[j][i] = d[i];
366             }
367             // copy current distance counts to 'previous row' distance counts
368             tempD = p;
369             p = d;
370             d = tempD;
371         }
372         return findDetailedResults(left, right, matrix, swapped);
373     }
374 
375     /**
376      * Threshold.
377      */
378     private final Integer threshold;
379 
380     /**
381      * Constructs a new instance that uses a version of the algorithm that does not use a threshold parameter.
382      *
383      * @see LevenshteinDetailedDistance#getDefaultInstance()
384      * @deprecated Use {@link #getDefaultInstance()}.
385      */
386     @Deprecated
387     public LevenshteinDetailedDistance() {
388         this(null);
389     }
390 
391     /**
392      * Constructs a new instance for a threshold.
393      * <p>
394      * If the threshold is not null, distance calculations will be limited to a maximum length.
395      * </p>
396      * <p>
397      * If the threshold is null, the unlimited version of the algorithm will be used.
398      * </p>
399      *
400      * @param threshold If this is null then distances calculations will not be limited. This may not be negative.
401      */
402     public LevenshteinDetailedDistance(final Integer threshold) {
403         if (threshold != null && threshold < 0) {
404             throw new IllegalArgumentException("Threshold must not be negative");
405         }
406         this.threshold = threshold;
407     }
408 
409     /**
410      * Computes the Levenshtein distance between two Strings.
411      *
412      * <p>
413      * A higher score indicates a greater distance.
414      * </p>
415      *
416      * <p>
417      * The previous implementation of the Levenshtein distance algorithm was from
418      * <a href="https://www.merriampark.com/ld.htm">http://www.merriampark.com/ld.htm</a>
419      * </p>
420      *
421      * <p>
422      * Chas Emerick has written an implementation in Java, which avoids an OutOfMemoryError which can occur when my Java implementation is used with very large
423      * strings.<br>
424      * This implementation of the Levenshtein distance algorithm is from
425      * <a href="https://www.merriampark.com/ldjava.htm">http://www.merriampark.com/ldjava.htm</a>
426      * </p>
427      *
428      * <pre>
429      * distance.apply(null, *)             = Throws {@link IllegalArgumentException}
430      * distance.apply(*, null)             = Throws {@link IllegalArgumentException}
431      * distance.apply("","")               = 0
432      * distance.apply("","a")              = 1
433      * distance.apply("aaapppp", "")       = 7
434      * distance.apply("frog", "fog")       = 1
435      * distance.apply("fly", "ant")        = 3
436      * distance.apply("elephant", "hippo") = 7
437      * distance.apply("hippo", "elephant") = 7
438      * distance.apply("hippo", "zzzzzzzz") = 8
439      * distance.apply("hello", "hallo")    = 1
440      * </pre>
441      *
442      * @param left  the first input, must not be null.
443      * @param right the second input, must not be null.
444      * @return result distance, or -1.
445      * @throws IllegalArgumentException if either String input {@code null}.
446      */
447     @Override
448     public LevenshteinResults apply(final CharSequence left, final CharSequence right) {
449         return apply(SimilarityInput.input(left), SimilarityInput.input(right));
450     }
451 
452     /**
453      * Computes the Levenshtein distance between two Strings.
454      *
455      * <p>
456      * A higher score indicates a greater distance.
457      * </p>
458      *
459      * <p>
460      * The previous implementation of the Levenshtein distance algorithm was from
461      * <a href="https://www.merriampark.com/ld.htm">http://www.merriampark.com/ld.htm</a>
462      * </p>
463      *
464      * <p>
465      * Chas Emerick has written an implementation in Java, which avoids an OutOfMemoryError which can occur when my Java implementation is used with very large
466      * strings.<br>
467      * This implementation of the Levenshtein distance algorithm is from
468      * <a href="https://www.merriampark.com/ldjava.htm">http://www.merriampark.com/ldjava.htm</a>
469      * </p>
470      *
471      * <pre>
472      * distance.apply(null, *)             = Throws {@link IllegalArgumentException}
473      * distance.apply(*, null)             = Throws {@link IllegalArgumentException}
474      * distance.apply("","")               = 0
475      * distance.apply("","a")              = 1
476      * distance.apply("aaapppp", "")       = 7
477      * distance.apply("frog", "fog")       = 1
478      * distance.apply("fly", "ant")        = 3
479      * distance.apply("elephant", "hippo") = 7
480      * distance.apply("hippo", "elephant") = 7
481      * distance.apply("hippo", "zzzzzzzz") = 8
482      * distance.apply("hello", "hallo")    = 1
483      * </pre>
484      *
485      * @param <E>   The type of similarity score unit.
486      * @param left  the first input, must not be null.
487      * @param right the second input, must not be null.
488      * @return result distance, or -1.
489      * @throws IllegalArgumentException if either String input {@code null}.
490      * @since 1.13.0
491      */
492     public <E> LevenshteinResults apply(final SimilarityInput<E> left, final SimilarityInput<E> right) {
493         if (threshold != null) {
494             return limitedCompare(left, right, threshold);
495         }
496         return unlimitedCompare(left, right);
497     }
498 
499     /**
500      * Gets the distance threshold.
501      *
502      * @return The distance threshold.
503      */
504     public Integer getThreshold() {
505         return threshold;
506     }
507 }