ask for text to edit, text formatting

Question

I would like to make a program that asks for text (a paragraph with several words) that would be separated by commas. To transform the text and add a tag between the two, like to format the text to html text

Example: word1, word2, word3 to <a> word1 </a>, <a> word2 </a>, <a> word3 </a>

So I started doing this code but I do not know how to continue. How can I test the text to find the front of the word? I imagine with ASCII tests? Maybe with a table that will test every case ?

I do not necessarily ask the complete answer but maybe a direction to follow could help.

#include <iostream>
#include <iomanip>
#include <string> //For getline()

using namespace std;

// Creating class
class GetText
{
public:
    string text;
    string line; //Using this as a buffer

    void userText()
    {
        cout << "Please type a message: ";

        do
        {
            getline(cin, line);
            text += line;
        }
        while(line != "");
    }

    void to_string()
    {
        cout << "\n" << "User's Text: " << "\n" << text << endl;
    }
};


int main() {
    GetText test;
    test.userText();
    test.to_string();
    system("pause");

    return 0;
}

Answer 1

The next thing you would need to do is to split your input by a deltimeter (in your case ',') into a vector and later combine everything with pre and posfixes. C++ does not support splitting by default, you would have to be creative or search for a solution like here.

Answer 2

If you want to keep it really simple, you can detect word boundaries by checking two characters at a time. Here's a working example.

using namespace std;

#include <iostream>
#include <string>

#include <cctype>

typedef enum boundary_type_e {
    E_BOUNDARY_TYPE_ERROR = -1,
    E_BOUNDARY_TYPE_NONE,
    E_BOUNDARY_TYPE_LEFT,
    E_BOUNDARY_TYPE_RIGHT,
} boundary_type_t;

typedef struct boundary_s {
    boundary_type_t type;
    int pos;
} boundary_t;

bool is_word_char(int c) {
    return ' ' <= c && c <= '~' && !isspace(c) && c != ',';
}

boundary_t maybe_word_boundary(string str, int pos) {
    int len = str.length();
    if (pos < 0 || pos >= len) {
        return (boundary_t){.type = E_BOUNDARY_TYPE_ERROR};
    } else {
        if (pos == 0 && is_word_char(str[pos])) {
            // if the first character is word-y, we have a left boundary at the beginning
            return (boundary_t){.type = E_BOUNDARY_TYPE_LEFT, .pos = pos};
        } else if (pos == len - 1 && is_word_char(str[pos])) {
            // if the last character is word-y, we have a right boundary left of the null terminator
            return (boundary_t){.type = E_BOUNDARY_TYPE_RIGHT, .pos = pos + 1};
        } else if (!is_word_char(str[pos]) && is_word_char(str[pos + 1])) {
            // if we have a delimiter followed by a word char, we have a left boundary left of the word char
            return (boundary_t){.type = E_BOUNDARY_TYPE_LEFT, .pos = pos + 1};
        } else if (is_word_char(str[pos]) && !is_word_char(str[pos + 1])) {
            // if we have a word char followed by a delimiter, we have a right boundary right of the word char
            return (boundary_t){.type = E_BOUNDARY_TYPE_RIGHT, .pos = pos + 1};
        }
        return (boundary_t){.type = E_BOUNDARY_TYPE_NONE};
    }
}

int main() {
    string str;
    string ins_left("<tag>");
    string ins_right("</tag>");
    getline(cin, str);

    // can't use length for the loop condition without recalculating it all the time
    for (int i = 0; str[i] != '\0'; i++) {
        boundary_t boundary = maybe_word_boundary(str, i);
        if (boundary.type == E_BOUNDARY_TYPE_LEFT) {
            str.insert(boundary.pos, ins_left);
            i += ins_left.length();
        } else if (boundary.type == E_BOUNDARY_TYPE_RIGHT) {
            str.insert(boundary.pos, ins_right);
            i += ins_right.length();
        }
    }
}

It would be better to use enum class but I forgot the notation. You can also copy to a buffer instead of generating the new string in-place, I was just trying to keep it simple. Feel free to expand it to a class based C++ style. To get your exact desired output, strip the spaces first and add spaces to ins_left and ins_right.