Merge pull request #6 from kvedala/document/strings

Documentation of `strings` folder

README.md

@@ -1,7 +1,5 @@
-<!--# DO NOT REMOVE THIS LINE 
+# The Algorithms - C++ # {#mainpage}
-This is for Doxygen to recognize as the index file for the complete documentation
+
-{#mainpage} -->
-# The Algorithms - C++
 [![contributions welcome](https://img.shields.io/static/v1.svg?label=Contributions&message=Welcome&color=0059b3&style=flat-square)](https://github.com/kvedala/C-Plus-Plus/blob/master/CONTRIBUTION.md)&nbsp;
 ![GitHub repo size](https://img.shields.io/github/repo-size/kvedala/C-Plus-Plus?color=red&style=flat-square)
 ![GitHub closed pull requests](https://img.shields.io/github/issues-pr-closed/kvedala/C-Plus-Plus?color=green&style=flat-square)

strings/brute_force_string_searching.cpp

@@ -1,52 +1,53 @@
-#include  <iostream>
+/**
-#include  <string>
+ * @file
-#include  <vector>
+ * @brief          String pattern search - brute force
-
-using std::string;
-
-int brute_force(string text, string pattern);
-std::vector<std::vector<string>> test_set  =   {
-    // {text, pattern, expected output}
-     {"a", "aa", "-1"},
-     {"a", "a", "0"},
-     {"ba", "b", "0"},
-     {"bba", "bb", "0"},
-     {"bbca", "c", "2"},
-     {"ab", "b", "1"}
-};
-
-int main() {
-    for  (size_t i  =  0 ;  i < test_set.size();  i++) {
-        int output  =  brute_force(test_set[i][0],  test_set[i][1]);
-        if (std::to_string(output)  ==  test_set[i][2])
-            std::cout  <<  "success\n";
-        else
-            std::cout  <<  "failure\n";
-    }
-    return 0;
-}
-
-/*
- *@description    Find a pattern in a string by comparing the pattern
- *                to every substring.
- *@param text     Any string that might contain the pattern.
- *@param pattern  String that we are searching for.
- *@return       Index where the pattern starts in the text or
- *                -1 if the pattern was not found.
  */
+#include <iostream>
+#ifdef _MSC_VER
+#include <string>  // use this for MS Visucal C++
+#else
+#include <cstring>
+#endif
+#include <vector>
 
-int brute_force(string text, string pattern) {
+/**
-    size_t pat_l  =  pattern.length();
+ * Find a pattern in a string by comparing the pattern to every substring.
-    size_t txt_l  =  text.length();
+ * @param text     Any string that might contain the pattern.
-    int index  =  -1;
+ * @param pattern  String that we are searching for.
-    if (pat_l  <=  txt_l) {
+ * @return         Index where the pattern starts in the text
-        for  (size_t i = 0;  i < txt_l-pat_l+1; i++) {
+ * @return         -1 if the pattern was not found.
-            string s  =  text.substr(i, pat_l);
+ */
-            if (s  ==  pattern) {
+int brute_force(const std::string &text, const std::string &pattern) {
-                index  =  i;
+    size_t pat_l = pattern.length();
+    size_t txt_l = text.length();
+    int index = -1;
+    if (pat_l <= txt_l) {
+        for (size_t i = 0; i < txt_l - pat_l + 1; i++) {
+            std::string s = text.substr(i, pat_l);
+            if (s == pattern) {
+                index = i;
                 break;
             }
         }
     }
     return index;
 }
+
+/** set of test cases */
+const std::vector<std::vector<std::string>> test_set = {
+    // {text, pattern, expected output}
+    {"a", "aa", "-1"},  {"a", "a", "0"},    {"ba", "b", "0"},
+    {"bba", "bb", "0"}, {"bbca", "c", "2"}, {"ab", "b", "1"}};
+
+/** Main function */
+int main() {
+    for (size_t i = 0; i < test_set.size(); i++) {
+        int output = brute_force(test_set[i][0], test_set[i][1]);
+
+        if (std::to_string(output) == test_set[i][2])
+            std::cout << "success\n";
+        else
+            std::cout << "failure\n";
+    }
+    return 0;
+}

strings/knuth_morris_pratt.cpp

@@ -1,64 +1,88 @@
-/*
+/**
-    The Knuth-Morris-Pratt Algorithm for finding a pattern within a piece of text
+ * \file
-    with complexity O(n + m)
+ * \brief The [Knuth-Morris-Pratt
-    1) Preprocess pattern to identify any suffixes that are identical to prefixes
+ * Algorithm](https://en.wikipedia.org/wiki/Knuth–Morris–Pratt_algorithm) for
-        This tells us where to continue from if we get a mismatch between a character in our pattern
+ * finding a pattern within a piece of text with complexity O(n + m)
-        and the text.
+ *
-    2) Step through the text one character at a time and compare it to a character in the pattern
+ * 1. Preprocess pattern to identify any suffixes that are identical to
-        updating our location within the pattern if necessary
+ * prefixes. This tells us where to continue from if we get a mismatch between a
-*/
+ * character in our pattern and the text.
+ * 2. Step through the text one character at a time and compare it to a
+ * character in the pattern updating our location within the pattern if
+ * necessary
+ */
 
-#include<iostream>
+#include <iostream>
-#include<vector>
+#ifdef _MSC_VER
-#include<string>
+#include <string>  // use this for MS Visucal C++
-using namespace std;
+#else
-vector<int> getFailureArray(string pattern){
+#include <cstring>
-    int pattern_length=pattern.size();
+#endif
-    vector<int>failure(pattern_length+1);
+#include <vector>
-    failure[0]=-1;
+
-    int j=-1;
+/**
-    for(int i=0; i<pattern_length; i++){
+ * Generate the partial match table aka failure function for a pattern to
-        while(j!=-1&&pattern[j]!=pattern[i]){
+ * search.
-            j=failure[j];
+ * \param[in] pattern text for which to create the partial match table
+ * \returns the partial match table as a vector array
+ */
+std::vector<int> getFailureArray(const std::string &pattern) {
+    int pattern_length = pattern.size();
+    std::vector<int> failure(pattern_length + 1);
+    failure[0] = -1;
+    int j = -1;
+
+    for (int i = 0; i < pattern_length; i++) {
+        while (j != -1 && pattern[j] != pattern[i]) {
+            j = failure[j];
         }
         j++;
-        failure[i+1]=j;
+        failure[i + 1] = j;
     }
     return failure;
 }
-bool kmp(string pattern,string text){
+
-    int text_length=text.size(),pattern_length=pattern.size();
+/**
-    vector<int>failure=getFailureArray(pattern);
+ * KMP algorithm to find a pattern in a text
-    int k=0;
+ * \param[in] pattern string pattern to search
-    for(int  j=0; j<text_length; j++){
+ * \param[in] text text in which to search
-        while(k!=-1&&pattern[k]!=text[j]){
+ * \returns `true` if pattern was found
-            k=failure[k];
+ * \returns `false` if pattern was not found
+ */
+bool kmp(const std::string &pattern, const std::string &text) {
+    int text_length = text.size(), pattern_length = pattern.size();
+    std::vector<int> failure = getFailureArray(pattern);
+
+    int k = 0;
+    for (int j = 0; j < text_length; j++) {
+        while (k != -1 && pattern[k] != text[j]) {
+            k = failure[k];
         }
         k++;
-        if(k==pattern_length)return true;
+        if (k == pattern_length)
+            return true;
     }
     return false;
 }
 
-int main()
+/** Main function */
-{   
+int main() {
-   
+    std::string text = "alskfjaldsabc1abc1abc12k23adsfabcabc";
-    string text="alskfjaldsabc1abc1abc12k23adsfabcabc";
+    std::string pattern = "abc1abc12l";
-    string pattern="abc1abc12l";
+
-    if(kmp(pattern,text)==true){
+    if (kmp(pattern, text) == true) {
-        cout<<"Found"<<endl;
+        std::cout << "Found" << std::endl;
+    } else {
+        std::cout << "Not Found" << std::endl;
     }
-    else{
+
-        cout<<"Not Found"<<endl;
+    text = "abcabc";
-    }
+    pattern = "bca";
-    text="abcabc";
+    if (kmp(pattern, text) == true) {
-    pattern="bca";
+        std::cout << "Found" << std::endl;
-    if(kmp(pattern,text)==true){
+    } else {
-        cout<<"Found"<<endl;
+        std::cout << "Not Found" << std::endl;
-    }
-    else{
-        cout<<"Not Found"<<endl;
     }
+
     return 0;
 }
-

strings/rabin_karp.cpp

@@ -1,39 +1,64 @@
-/*
+/**
- * file name : rabin_karp.cpp
+ * \file
- * author    : Amit Kumar 
+ * \brief The [Rabin-Karp
- * Copyright : 2020 , Amit Kumar 
+ * Algorithm](https://en.wikipedia.org/wiki/Rabin–Karp_algorithm) for finding a
- * version   : 1.0
+ * pattern within a piece of text with complexity O(n + m)
  */
-#include<cassert>
+#include <cassert>
-#include<cmath>
+#include <cmath>
-#include<iostream>
+#include <iostream>
-#include<string>
+#ifdef _MSC_VER
+#include <string>  // use this for MS Visucal C++
+#else
+#include <cstring>
+#endif
 
-using std::string;
+#define PRIME 5  ///< Prime modulus for hash functions
-using std::pow;
 
-#define PRIME 5
+/**
-
+ * convert a string to an intger - called as hashing function
-int64_t create_hash(string s , int n) {
+ * \param[in] s source of string to hash
+ * \param[in] n length of substring to hash
+ * \returns hash integer
+ */
+int64_t create_hash(const std::string& s, int n) {
     int64_t result = 0;
-    for ( int i = 0; i < n; ++i ) {
+    for (int i = 0; i < n; ++i) {
-        result += (int64_t)(s[i] * (int64_t)pow(PRIME , i));
+        result += (int64_t)(s[i] * (int64_t)pow(PRIME, i));
     }
     return result;
 }
 
-int64_t recalculate_hash(string s , int old_index ,
+/**
-        int new_index , int64_t old_hash , int patLength) {
+ * re-hash a string using known existing hash
+ * \param[in] s source of string to hash
+ * \param[in] old_index previous index of string
+ * \param[in] new_index new index of string
+ * \param[in] old_hash previous hash of substring
+ * \param[in] patLength length of substring to hash
+ * \returns new hash integer
+ */
+int64_t recalculate_hash(const std::string& s, int old_index, int new_index,
+                         int64_t old_hash, int patLength) {
     int64_t new_hash = old_hash - s[old_index];
     new_hash /= PRIME;
-    new_hash += (int64_t)(s[new_index]*(int64_t)pow(PRIME, patLength-1));
+    new_hash += (int64_t)(s[new_index] * (int64_t)pow(PRIME, patLength - 1));
     return new_hash;
 }
 
-bool check_if_equal(string str1 , string str2 ,
+/**
-                    int start1 , int end1 ,
+ * compare if two sub-strings are equal
-                    int start2 , int end2) {
+ * \param[in] str1 string pattern to search
-    if (end1-start1 != end2-start2) {
+ * \param[in] str2 text in which to search
+ * \param[in] start1,end1 start and end indices for substring in str1
+ * \param[in] start2,end2 start and end indices for substring in str2
+ * \returns `true` if pattern was found
+ * \returns `false` if pattern was not found
+ * @note can this be replaced by std::string::compare?
+ */
+bool check_if_equal(const std::string& str1, const std::string& str2,
+                    int start1, int end1, int start2, int end2) {
+    if (end1 - start1 != end2 - start2) {
         return false;
     }
     while (start1 <= end1 && start2 <= end2) {
@@ -46,33 +71,36 @@ bool check_if_equal(string str1 , string str2 ,
     return true;
 }
 
-/*
+/**
- *  @description : search pattern in the given text 
+ *  Perform string pattern search using Rabin-Karp algorithm
- *  @param : string str
+ *  @param[in] str string to search in
- *  @param : string pat
+ *  @param[in] pat pattern to search for
- *  @return index of first occurrence of pattern or -1 if pattern not found
+ *  @return index of first occurrence of pattern
+ *  @return -1 if pattern not found
  */
 
-int rabin_karp(const string &str , const string& pat) {
+int rabin_karp(const std::string& str, const std::string& pat) {
-    int64_t pat_hash = create_hash(pat , pat.size());
+    int64_t pat_hash = create_hash(pat, pat.size());
-    int64_t str_hash = create_hash(str , pat.size());
+    int64_t str_hash = create_hash(str, pat.size());
-    for (int i=0;  i <= str.size()-pat.size(); ++i) {
+    for (int i = 0; i <= str.size() - pat.size(); ++i) {
         if (pat_hash == str_hash &&
-            check_if_equal(str , pat , i , i+pat.size()-1 , 0 , pat.size()-1)) {
+            check_if_equal(str, pat, i, i + pat.size() - 1, 0,
-                return i;
+                           pat.size() - 1)) {
+            return i;
         }
-        if (i < str.size()-pat.size()) {
+        if (i < str.size() - pat.size()) {
             str_hash =
-                recalculate_hash(str, i, i+pat.size(), str_hash, pat.size());
+                recalculate_hash(str, i, i + pat.size(), str_hash, pat.size());
         }
     }
     return -1;  // return -1 if given pattern not found
 }
 
+/** Main function */
 int main(void) {
-    assert(rabin_karp("helloWorld", "world")    == -1);
+    assert(rabin_karp("helloWorld", "world") == -1);
-    assert(rabin_karp("helloWorld", "World")    ==  5);
+    assert(rabin_karp("helloWorld", "World") == 5);
-    assert(rabin_karp("this_is_c++" , "c++")   ==  8);
+    assert(rabin_karp("this_is_c++", "c++") == 8);
-    assert(rabin_karp("happy_coding", "happy") ==  0);
+    assert(rabin_karp("happy_coding", "happy") == 0);
     return 0;
 }