200 lines
No EOL
6.5 KiB
C++
200 lines
No EOL
6.5 KiB
C++
#include "OutputProcessor.h"
|
|
|
|
#include <fstream>
|
|
#include <iomanip>
|
|
#include <iostream>
|
|
#include <ostream>
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
OutputProcessor::OutputProcessor() {
|
|
_fileOut = std::ofstream();
|
|
_allWords = std::vector<std::string>();
|
|
_uniqueWords = std::vector<std::string>();
|
|
_letterCounts = std::vector<unsigned int>(26, 0);
|
|
_wordCounts = std::vector<unsigned int>();
|
|
_totalLetterCount = 0;
|
|
_totalWordCount = 0;
|
|
}
|
|
|
|
void OutputProcessor::analyzeWords(std::vector<std::string> allWords,
|
|
std::string punctuation) {
|
|
// Iterate over all words, processing incrementally
|
|
for (size_t wordIdx = 0; wordIdx < allWords.size(); wordIdx++) {
|
|
std::string &word = allWords.at(wordIdx);
|
|
|
|
// Remove punctuation from word
|
|
size_t punctuationIdx = 0;
|
|
while ((punctuationIdx = word.find_first_of(punctuation)) !=
|
|
std::string::npos) {
|
|
word.erase(punctuationIdx, 1);
|
|
}
|
|
|
|
// Save word internally
|
|
_allWords.push_back(word);
|
|
|
|
// Check all unique words for a match, and if so increment the count
|
|
bool foundUnique = false;
|
|
size_t uniqueWordIdx;
|
|
for (uniqueWordIdx = 0; uniqueWordIdx < _uniqueWords.size();
|
|
uniqueWordIdx++) {
|
|
if (_uniqueWords.at(uniqueWordIdx) == word) {
|
|
foundUnique = true;
|
|
break;
|
|
}
|
|
}
|
|
// If no unique word exists, add it to both vectors
|
|
if (!foundUnique) {
|
|
_uniqueWords.push_back(word);
|
|
_wordCounts.push_back(1);
|
|
} else {
|
|
_wordCounts.at(uniqueWordIdx)++;
|
|
}
|
|
|
|
// Add letter count for each letter in the word
|
|
for (size_t letterIdx = 0; letterIdx < word.length(); letterIdx++) {
|
|
char letter = word.at(letterIdx);
|
|
// Normalize to uppercase
|
|
if (letter >= 'a' && letter <= 'z') {
|
|
letter -= 32;
|
|
}
|
|
// Subtracting an uppercase letter by 65 creates its alphabetical
|
|
// index
|
|
letter -= 65;
|
|
_letterCounts.at(letter)++;
|
|
}
|
|
|
|
// Sum total letter count
|
|
_totalLetterCount += word.length();
|
|
|
|
// Increment total word count
|
|
_totalWordCount++;
|
|
}
|
|
}
|
|
|
|
bool OutputProcessor::openStream() {
|
|
std::string file;
|
|
std::cout << "What is the name of the file you would like to write to? ";
|
|
std::cin >> file;
|
|
|
|
if (std::cin.fail()) {
|
|
std::cerr << "Invalid file input" << std::endl;
|
|
return false;
|
|
}
|
|
|
|
_fileOut.open(file);
|
|
if (_fileOut.fail()) {
|
|
std::cerr << "Unable to open file, does it exist?" << std::endl;
|
|
return false;
|
|
}
|
|
|
|
return true;
|
|
}
|
|
|
|
void OutputProcessor::closeStream() { _fileOut.close(); }
|
|
|
|
void OutputProcessor::write() {
|
|
// Calculate longest word length, longest number length, most common word,
|
|
// and least common word for later use in one pass for efficiency
|
|
size_t longestWordLength = 0;
|
|
|
|
std::string *mostCommonWord = &_uniqueWords.at(0);
|
|
unsigned long mostCommonWordOccurrences = _wordCounts.at(0);
|
|
|
|
std::string *leastCommonWord = &_uniqueWords.at(0);
|
|
unsigned long leastCommonWordOccurrences = _wordCounts.at(0);
|
|
|
|
for (size_t uniqueWordIdx = 0; uniqueWordIdx < _uniqueWords.size();
|
|
uniqueWordIdx++) {
|
|
std::string &uniqueWord = _uniqueWords.at(uniqueWordIdx);
|
|
unsigned long wordCount = _wordCounts.at(uniqueWordIdx);
|
|
|
|
if (uniqueWord.length() > longestWordLength) {
|
|
longestWordLength = uniqueWord.length();
|
|
}
|
|
|
|
// Equality can be ignored here because we want the word that was
|
|
// encountered first, so any subsequent extremes can be ignored
|
|
if (wordCount < leastCommonWordOccurrences) {
|
|
leastCommonWordOccurrences = wordCount;
|
|
leastCommonWord = &uniqueWord;
|
|
} else {
|
|
if (wordCount > mostCommonWordOccurrences) {
|
|
mostCommonWordOccurrences = wordCount;
|
|
mostCommonWord = &uniqueWord;
|
|
}
|
|
}
|
|
}
|
|
size_t longestWordLengthDigits = std::to_string(longestWordLength).length();
|
|
|
|
_fileOut << "Read in " << _totalWordCount << " words" << std::endl;
|
|
_fileOut << "Encountered " << _uniqueWords.size() << " unique words"
|
|
<< std::endl;
|
|
|
|
// Print out each unique word and how often it happened
|
|
for (size_t uniqueWordIdx = 0; uniqueWordIdx < _uniqueWords.size();
|
|
uniqueWordIdx++) {
|
|
_fileOut << std::setw(longestWordLength) << std::left
|
|
<< _uniqueWords.at(uniqueWordIdx) << std::right << " : "
|
|
<< std::setw(longestWordLengthDigits + 1)
|
|
<< _wordCounts.at(uniqueWordIdx) << std::endl;
|
|
}
|
|
|
|
// Print the most and least common word
|
|
size_t longerFrequentWordLength =
|
|
mostCommonWord->length() > leastCommonWord->length()
|
|
? mostCommonWord->length()
|
|
: leastCommonWord->length();
|
|
size_t mostCommonWordOccurrencesDigits =
|
|
std::to_string(mostCommonWordOccurrences).length();
|
|
|
|
_fileOut << " Most Frequent Word: " << std::setw(longerFrequentWordLength)
|
|
<< std::left << *mostCommonWord << " "
|
|
<< std::setw(mostCommonWordOccurrencesDigits) << std::right
|
|
<< mostCommonWordOccurrences << std::endl;
|
|
|
|
// Calculate the most and least common letters to display, along with their
|
|
// occurrences for formatting purposes
|
|
char mostCommonLetter = 'A';
|
|
unsigned long mostCommonLetterOccurrences = _letterCounts.at(0);
|
|
char leastCommonLetter = 'A';
|
|
unsigned long leastCommonLetterOccurrences = _letterCounts.at(0);
|
|
|
|
for (size_t letterIdx = 0; letterIdx < 26; letterIdx++) {
|
|
// Here not using "or equals" means the letters later alphabetically get
|
|
// ignored if they occur the same amount
|
|
if (_letterCounts.at(letterIdx) <
|
|
_letterCounts.at(leastCommonLetter - 65)) {
|
|
leastCommonLetter = letterIdx + 65;
|
|
leastCommonLetterOccurrences = _letterCounts.at(letterIdx);
|
|
} else {
|
|
if (_letterCounts.at(letterIdx) >
|
|
_letterCounts.at(mostCommonLetter - 65)) {
|
|
mostCommonLetter = letterIdx + 65;
|
|
mostCommonLetterOccurrences = _letterCounts.at(letterIdx);
|
|
}
|
|
}
|
|
}
|
|
|
|
// Print out each letter along with the amount of times it occurs
|
|
size_t mostCommonLetterOccurrencesDigits =
|
|
std::to_string(mostCommonLetterOccurrences).length();
|
|
for (size_t letterIdx = 0; letterIdx < 26; letterIdx++) {
|
|
_fileOut << (char)(letterIdx + 65) << ": "
|
|
<< std::setw(mostCommonLetterOccurrencesDigits) << std::right
|
|
<< _letterCounts.at(letterIdx) << std::endl;
|
|
}
|
|
|
|
// Print out the most and least common letters in total
|
|
_fileOut << " Most Frequent Letter: " << mostCommonLetter << " "
|
|
<< mostCommonLetterOccurrences << " (" << std::setw(7)
|
|
<< std::fixed << std::setprecision(3)
|
|
<< ((float)mostCommonLetterOccurrences / _totalLetterCount * 100)
|
|
<< "%)" << std::endl;
|
|
_fileOut << "Least Frequent Letter: " << leastCommonLetter << " "
|
|
<< std::setw(mostCommonLetterOccurrencesDigits) << std::right
|
|
<< leastCommonLetterOccurrences << " (" << std::setw(7)
|
|
<< std::fixed << std::setprecision(3)
|
|
<< ((float)leastCommonLetterOccurrences / _totalLetterCount * 100)
|
|
<< "%)" << std::endl;
|
|
} |