Formatted with Google Java Formatter

strings/HorspoolSearch.java

@@ -3,30 +3,38 @@ package strings;
 import java.util.HashMap;
 
 /**
- * This class is not thread safe<br><br>
+ * This class is not thread safe<br>
- * (From wikipedia)
+ * <br>
- * In computer science, the Boyer–Moore–Horspool algorithm or Horspool's algorithm is an algorithm for finding
+ * (From wikipedia) In computer science, the Boyer–Moore–Horspool algorithm or Horspool's algorithm
- * substrings in strings. It was published by Nigel Horspool in 1980. <br>
+ * is an algorithm for finding substrings in strings. It was published by Nigel Horspool in 1980.
- * <a href=https://en.wikipedia.org/wiki/Boyer%E2%80%93Moore%E2%80%93Horspool_algorithm>Wikipedia page</a><br><br>
+ * <br>
- * <p>
+ * <a href=https://en.wikipedia.org/wiki/Boyer%E2%80%93Moore%E2%80%93Horspool_algorithm>Wikipedia
- * An explanation:<br>
+ * page</a><br>
- * <p>
+ * <br>
- * The Horspool algorithm is a simplification of the Boyer-Moore algorithm in that it uses only one of the two heuristic
+ *
- * methods for increasing the number of characters shifted when finding a bad match in the text. This method is usually
+ * <p>An explanation:<br>
- * called the "bad symbol" or "bad character" shift. The bad symbol shift method is classified as an input enhancement
+ *
- * method in the theory of algorithms. Input enhancement is (from wikipedia) the principle that processing a given input
+ * <p>The Horspool algorithm is a simplification of the Boyer-Moore algorithm in that it uses only
- * to a problem and altering it in a specific way will increase runtime efficiency or space efficiency, or both. Both
+ * one of the two heuristic methods for increasing the number of characters shifted when finding a
- * algorithms try to match the pattern and text comparing the pattern symbols to the text's from right to left.<br><br>
+ * bad match in the text. This method is usually called the "bad symbol" or "bad character" shift.
- * <p>
+ * The bad symbol shift method is classified as an input enhancement method in the theory of
- * In the bad symbol shift method, a table is created prior to the search, called the "bad symbol table". The bad symbol
+ * algorithms. Input enhancement is (from wikipedia) the principle that processing a given input to
- * table contains the shift values for any symbol in the text and pattern. For these symbols, the value is the length of
+ * a problem and altering it in a specific way will increase runtime efficiency or space efficiency,
- * the pattern, if the symbol is not in the first (length - 1) of the pattern. Else it is the distance from its
+ * or both. Both algorithms try to match the pattern and text comparing the pattern symbols to the
- * rightmost occurrence in the pattern to the last symbol of the pattern. In practice, we only calculate the values for
+ * text's from right to left.<br>
- * the ones that exist in the first (length - 1) of the pattern.<br><br>
+ * <br>
- * <p>
+ *
- * For more details on the algorithm and the more advanced Boyer-Moore I recommend checking out the wikipedia page and
+ * <p>In the bad symbol shift method, a table is created prior to the search, called the "bad symbol
- * professor Anany Levitin's book: Introduction To The Design And Analysis Of Algorithms.
+ * table". The bad symbol table contains the shift values for any symbol in the text and pattern.
- * </p>
+ * For these symbols, the value is the length of the pattern, if the symbol is not in the first
+ * (length - 1) of the pattern. Else it is the distance from its rightmost occurrence in the pattern
+ * to the last symbol of the pattern. In practice, we only calculate the values for the ones that
+ * exist in the first (length - 1) of the pattern.<br>
+ * <br>
+ *
+ * <p>For more details on the algorithm and the more advanced Boyer-Moore I recommend checking out
+ * the wikipedia page and professor Anany Levitin's book: Introduction To The Design And Analysis Of
+ * Algorithms.
  */
 public class HorspoolSearch {
 
@@ -66,9 +74,9 @@ public class HorspoolSearch {
   }
 
   /**
-     * Fairly standard implementation of the Horspool algorithm. Only the index of the last character of the pattern on the
+   * Fairly standard implementation of the Horspool algorithm. Only the index of the last character
-     * text is saved and shifted by the appropriate amount when a mismatch is found. The algorithm stops at the first
+   * of the pattern on the text is saved and shifted by the appropriate amount when a mismatch is
-     * match or when the entire text has been exhausted.
+   * found. The algorithm stops at the first match or when the entire text has been exhausted.
    *
    * @param pattern String to be matched in the text
    * @param text text String
@@ -78,7 +86,8 @@ public class HorspoolSearch {
     shiftValues = calcShiftValues(pattern); // build the bad symbol table
     comparisons = 0; // reset comparisons
 
-        int textIndex = pattern.length() - 1; // align pattern with text start and get index of the last character
+    int textIndex =
+        pattern.length() - 1; // align pattern with text start and get index of the last character
 
     // while pattern is not out of text bounds
     while (textIndex < text.length()) {
@@ -88,9 +97,7 @@ public class HorspoolSearch {
       while (i >= 0) {
         comparisons++;
         char patternChar = pattern.charAt(i);
-                char textChar = text.charAt(
+        char textChar = text.charAt((textIndex + i) - (pattern.length() - 1));
-                        (textIndex + i) - (pattern.length() - 1)
-                );
         if (!charEquals(patternChar, textChar, caseSensitive)) { // bad character, shift pattern
           textIndex += getShiftValue(text.charAt(textIndex));
           break;
@@ -124,10 +131,11 @@ public class HorspoolSearch {
   }
 
   /**
-     * Builds the bad symbol table required to run the algorithm. The method starts from the second to last character
+   * Builds the bad symbol table required to run the algorithm. The method starts from the second to
-     * of the pattern and moves to the left. When it meets a new character, it is by definition its rightmost occurrence
+   * last character of the pattern and moves to the left. When it meets a new character, it is by
-     * and therefore puts the distance from the current index to the index of the last character into the table. If the
+   * definition its rightmost occurrence and therefore puts the distance from the current index to
-     * character is already in the table, then it is not a rightmost occurrence, so it continues.
+   * the index of the last character into the table. If the character is already in the table, then
+   * it is not a rightmost occurrence, so it continues.
    *
    * @param pattern basis for the bad symbol table
    * @return the bad symbol table
@@ -136,7 +144,9 @@ public class HorspoolSearch {
     patternLength = pattern.length();
     HashMap<Character, Integer> table = new HashMap<>();
 
-        for (int i = pattern.length() - 2; i >= 0; i--) { // length - 2 is the index of the second to last character
+    for (int i = pattern.length() - 2;
+        i >= 0;
+        i--) { // length - 2 is the index of the second to last character
       char c = pattern.charAt(i);
       int finalI = i;
       table.computeIfAbsent(c, k -> pattern.length() - 1 - finalI);
@@ -146,7 +156,8 @@ public class HorspoolSearch {
   }
 
   /**
-     * Helper function that uses the bad symbol shift table to return the appropriate shift value for a given character
+   * Helper function that uses the bad symbol shift table to return the appropriate shift value for
+   * a given character
    *
    * @param c character
    * @return shift value that corresponds to the character argument
@@ -158,5 +169,4 @@ public class HorspoolSearch {
       return patternLength;
     }
   }
-
 }