Question

Write a method ( C++ )

map occurance_map(const string path);

that reads in an ascii text file and returns an assocation where each key is a word in the text file and each value is the number of occurances of that word. Ignore punctuation and numbers. The method should be case-insensitive and should store the keys as lowercase. A word is definited by an string consisting entirely of alpha-numeric characters or apostrophes (single quote characteris). For example, if the file contained

This is a sentence. Don't think of wier_d strings as words. Really, 123 is a nice number. 

you would include sentence, don't, and 123 but not ., ,, or wier_d. Using single quotes as quotes, as in

'I should use double quotes'

is a user error and will catch the "words"

'I
should
use
double
quotes'

Answer 1

CodeToCopy:

count_occurences.cpp

#include <iostream>     /* cout object */

#include <fstream>      /* for ifstream class */

#include <vector>       /* for vector class */

#include <map>          /* for map class */

#include <algorithm>    /* for using find() function */

#include <iomanip>    /* for using find() function */

/* Macros which define ascii values of characters 0,9,A,Z,a,z,',.,, */

#define ZERO_ASCII 48

#define NINE_ASCII 57

#define UPPERCASE_A_ASCII 65

#define UPPERCASE_Z_ASCII 90

#define LOWERCASE_A_ASCII 97

#define LOWERCASE_Z_ASCII 122

#define APOSTROPHE_ASCII 39

#define PERIOD_ASCII      46

#define COMMA_ASCII      44

#define SPACE_ASCII      32

#define NEWLINE_ASCII    10

using namespace std;

/* This function adds word to the map, if word does not exist.

* If word already exists, then it increases the frequency of

* the word */

void add_word(map<string, int> * occurences_map, string word) {

    /* finding word in the map */

    map<string, int> ::iterator it = occurences_map->find(word);

    /* checking if word is present or not */

    if (it == occurences_map->end()) {

        /* if word is not there, inserting word with frequency 1 */

        occurences_map->insert(make_pair(word, 1));

    }

    else {

        /* if word is there, increasing its frequency by 1 */

        it->second = it->second + 1;

    }

}

map<string, int> occurance_map(const string path) {

   

    /* stores the file name */

    const char * text_file_name = path.c_str();

   

    /* stores the letter */

    char ch;

   

    /* flag variables tells whether parsing a word is in progress or not */

    bool wordstart = false;

   

    /* string variable stores the word */

    string word;   

   

    /* map which stores words and their frequencies as a key-value pair */

    map<string, int> word_occurences;

   

    /* creating ifstream objects to open text file */

    ifstream text_file;

   

    /* opening Teams.txt file in read mode */

    text_file.open(text_file_name, ios::in);

   

    /* checking Teams.txt is opened or not */

    if (text_file.fail()) {

        /* if not, printing error and exiting the program */

        cout << "Error::: Teams.text: No such file exists. ";

        return word_occurences;

    }

   

    /* reading letter by letter from input text file */

    while(text_file >> noskipws >> ch) {

       

        /* condition that enables only parsing alpha numerics and apostrophe */

        if ((ch >= ZERO_ASCII && ch <= NINE_ASCII) ||

            (ch >= UPPERCASE_A_ASCII && ch <= UPPERCASE_Z_ASCII) ||

            (ch >= LOWERCASE_A_ASCII && ch <= LOWERCASE_Z_ASCII) ||

            (ch == APOSTROPHE_ASCII)) {

       

            /* changing word-start flag variable to true */

            wordstart = true;

           

            /* appending each character string variable */

            word.append(1u, ch);

        }

        else {

           

            /* checking for word ending characters such as SPACE, COMA, PERIOD */

            if ((ch == SPACE_ASCII || ch == PERIOD_ASCII || ch == COMMA_ASCII || ch == NEWLINE_ASCII) && wordstart == true) {

                /* if word ending character is found, then adding the parsed word to map */

                add_word(&word_occurences, word);

               

                /* resetting word-start flag to false */

                wordstart = false;

               

                /* resetting letters of string variable */

                word.clear();

            }

            else {

                /* check for unsupported characters when word processing is in progress */

                if (wordstart == true && ch != ' ') {

                   

                    /* parsing rest of the characters in the word and ignoring them */

                    string post_letters;

                    text_file >> post_letters;

                   

                    /* clearing stored characters */

                    word.clear();

                   

                    /* resetting letters of string variable */

                    wordstart = false;

                }

            }

        }

    }

   

    /* if string variable characters are not reset, then adding the stored

     * word in map */

    if (word.size()) {

        add_word(&word_occurences, word);

    }

   

    /* closing the file */

    text_file.close();

   

    /* returing map */

    return word_occurences;

}

/* main function */

int main(int argc, char **argv) {

    /* checking number of command line arguments for user input-file */

    if (argc != 2) {

        cout << "Usage: " << argv[0] << ": <input-text-file>" << endl;

        return 0;

    }

   

    /* calling occurance_map() function with path */

    map<string, int> occurences = occurance_map(argv[1]);   

   

   

    /* iterating map to print key-value pair values */

    map<string, int> ::iterator it = occurences.begin();

   

    /* printing word and frequencies with proper format */

    cout << setw(6) << right << "Word" << setw(20) << right <<"Frequency ";

    cout << setw(15) << left << "-------" << setw(3) << right <<"---------- ";

    for(; it != occurences.end(); ++it) {

        cout << setw(15) << left << it->first << " " << setw(5) << right << it->second << " ";

    }

   

    return 0;

}

OutputScreenshot: