Add knuth.

trekhleb · trekhleb · commit 4afc8c759a4e · 2018-04-24T17:53:29.000+03:00
diff --git a/README.md b/README.md
@@ -41,10 +41,10 @@
 * **String**
   * [Levenshtein Distance](https://github.com/trekhleb/javascript-algorithms/tree/master/src/algorithms/string/levenshtein-distance) - minimum edit distance between two sequences
   * [Hamming Distance](https://github.com/trekhleb/javascript-algorithms/tree/master/src/algorithms/string/hamming-distance) - number of positions at which the symbols are different
-  * Knuth Morris Pratt
+  * [Knuth–Morris–Pratt algorithm](https://github.com/trekhleb/javascript-algorithms/tree/master/src/algorithms/string/knuth-morris-pratt) - substring search
+  * Rabin Karp
   * Longest common subsequence
   * longest common substring
-  * Rabin Karp
 * **Search**
   * [Binary Search](https://github.com/trekhleb/javascript-algorithms/tree/master/src/algorithms/search/binary-search)
 * **Sorting**
diff --git a/src/algorithms/string/knuth-morris-pratt/README.md b/src/algorithms/string/knuth-morris-pratt/README.md
@@ -0,0 +1,19 @@
+# Knuth–Morris–Pratt Algorithm
+
+The Knuth–Morris–Pratt string searching algorithm (or 
+KMP algorithm) searches for occurrences of a "word" `W` 
+within a main "text string" `T` by employing the 
+observation that when a mismatch occurs, the word itself 
+embodies sufficient information to determine where the 
+next match could begin, thus bypassing re-examination 
+of previously matched characters.
+
+## Complexity
+
+- **Time:** `O(|W| + |T|)` (much faster comparing to trivial `O(|W| * |T|)`)
+- **Space:** `O(|W|)`
+
+## References
+
+- [Wikipedia](https://en.wikipedia.org/wiki/Knuth%E2%80%93Morris%E2%80%93Pratt_algorithm)
+- [YouTube](https://www.youtube.com/watch?v=GTJr8OvyEVQ)
diff --git a/src/algorithms/string/knuth-morris-pratt/__test__/knuthMorrisPratt.test.js b/src/algorithms/string/knuth-morris-pratt/__test__/knuthMorrisPratt.test.js
@@ -0,0 +1,12 @@
+import knuthMorrisPratt from '../knuthMorrisPratt';
+
+describe('knuthMorrisPratt', () => {
+  it('should find word position in given text', () => {
+    expect(knuthMorrisPratt('abcbcglx', 'abca')).toBe(-1);
+    expect(knuthMorrisPratt('abcbcglx', 'bcgl')).toBe(3);
+    expect(knuthMorrisPratt('abcxabcdabxabcdabcdabcy', 'abcdabcy')).toBe(15);
+    expect(knuthMorrisPratt('abcxabcdabxabcdabcdabcy', 'abcdabca')).toBe(-1);
+    expect(knuthMorrisPratt('abcxabcdabxaabcdabcabcdabcdabcy', 'abcdabca')).toBe(12);
+    expect(knuthMorrisPratt('abcxabcdabxaabaabaaaabcdabcdabcy', 'aabaabaaa')).toBe(11);
+  });
+});
diff --git a/src/algorithms/string/knuth-morris-pratt/knuthMorrisPratt.js b/src/algorithms/string/knuth-morris-pratt/knuthMorrisPratt.js
@@ -0,0 +1,55 @@
+/**
+ * @see https://www.youtube.com/watch?v=GTJr8OvyEVQ
+ * @param {string} word
+ * @return {number[]}
+ */
+function buildPatternTable(word) {
+  const patternTable = [0];
+  let prefixIndex = 0;
+  let suffixIndex = 1;
+
+  while (suffixIndex < word.length) {
+    if (word[prefixIndex] === word[suffixIndex]) {
+      patternTable[suffixIndex] = prefixIndex + 1;
+      suffixIndex += 1;
+      prefixIndex += 1;
+    } else if (prefixIndex === 0) {
+      patternTable[suffixIndex] = 0;
+      suffixIndex += 1;
+    } else {
+      prefixIndex = patternTable[prefixIndex - 1];
+    }
+  }
+
+  return patternTable;
+}
+
+/**
+ * @param {string} text
+ * @param {string} word
+ * @return {number}
+ */
+export default function knuthMorrisPratt(text, word) {
+  let textIndex = 0;
+  let wordIndex = 0;
+
+  const patternTable = buildPatternTable(word);
+
+  while (textIndex < text.length) {
+    if (text[textIndex] === word[wordIndex]) {
+      // We've found a match.
+      if (wordIndex === word.length - 1) {
+        return (textIndex - word.length) + 1;
+      }
+      wordIndex += 1;
+      textIndex += 1;
+    } else if (wordIndex > 0) {
+      wordIndex = patternTable[wordIndex - 1];
+    } else {
+      wordIndex = 0;
+      textIndex += 1;
+    }
+  }
+
+  return -1;
+}
