/*
    WordCount.cpp
    Dave Klick
    CIS 250
    2018-02-10

    This program tokenizes a text file into words,
    converts them to lowercase, stores them in a
    binary search tree, and then displays the word
    counts and then goes back through the file
    deleting the words from the tree.
*/

#include "Bintree.h"
#include <algorithm>
#include <functional>
#include <cctype>
#include <iostream>
#include <fstream>
#include <string>
#include <vector>
#include <ios>
#include <cstring>
using std::cout;
using std::endl;
using std::ifstream;
using std::string;
using std::vector;
using std::ios;
using std::ptr_fun;

string convert(string& s);
void tokenize(vector<string>& v, string line);

int main(int argc, char* argv[]) {
    ifstream infile;
    string line;
    // *** Create a Bintree that holds string objects and name the variable "tree"
    vector<string> v;

    for (int argNum=1; argNum<argc; argNum++) {
        cout << "Processing file: " << argv[argNum] << endl;
        infile.open(argv[argNum]);
        if (!infile) {
            cout << "Error: Could not open file\n\n";
        } else {
            // Insert words
            getline(infile, line);
            while (infile) {
                // *** Here you need to convert the line, tokenize it, and
                // *** insert the individual words into the binary search tree.
                getline(infile, line);
            }
            cout << "Tree after insertions:\n";
            // *** Add code here that will display the tree in alphabetical order
            infile.close();
            // Now delete words
            infile.open(argv[argNum]);
            getline(infile, line);
            while (infile) {
                // *** Here you need to convert the line, tokenize it, and
                // *** delete the individual words from the binary search tree.
                getline(infile, line);
            }
            cout << "Tree after deletions:\n";
            // *** Add code here that will display the tree in alphabetical order
            infile.close();
            cout << "\n";
        }
    }

    return 0;
}

string convert(string& s) {
    static char cvrt[] = {
        'A', 'A', 'A', 'A', 'A', 'A', 'A', 'C', 'E', 'E', 'E', 'E', 'I', 'I', 'I', 'I',
        'D', 'N', 'O', 'O', 'O', 'O', 'O',   0,   0, 'U', 'U', 'U', 'U',   0,   0,   0,
        'a', 'a', 'a', 'a', 'a', 'a', 'a', 'c', 'e', 'e', 'e', 'e', 'i', 'i', 'i', 'i',
          0, 'n', 'o', 'o', 'o', 'o', 'o',   0,   0, 'u', 'u', 'u', 'u', 'y',   0, 'y' };

    string word = string(s);
    // Convert string to lowercase
    transform(word.begin(), word.end(), word.begin(), ptr_fun(::tolower));

    // Convert some special characters to rough equivalents or whitespace
    for (unsigned int i=0; i<word.length(); i++) {
        int c = word[i] & 0xff;
        if (c >= 0x80) {
            if (c >= 0xc0 && cvrt[c-0xc0] != 0) word[i] = (char) cvrt[c-0xc0];
            else word[i] = ' ';
        }
    }
    return word;
}


void tokenize(vector<string>& v, string line) {
    static const char* delims = " -\"\'?!,;:.()_`*/[]#%@$&{}<=>\\";
    v.clear();
    char* tempstr = new char[line.length()+1];
    for (unsigned int i=0; i<line.length(); i++) tempstr[i] = line[i];
    tempstr[line.length()] = '\0';
    char* ptr = strtok(tempstr, delims);
    while (ptr != NULL) {
        v.push_back(string(ptr));
        ptr = strtok(NULL, delims);
    }
}