Java Count Characters In Text File

Java program to count characters in text file.

Output

Total characters: 671751
 : 111015 16.526212837792574%
!: 499 0.07428347706218524%
': 741 0.11030873046709272%
(: 18 0.0026795643028443574%
): 18 0.0026795643028443574%
*: 30 0.0044659405047405955%
,: 9132 1.3594322896430373%
-: 1118 0.16643071614333288%
.: 6180 0.9199837439765627%
0: 6 8.931881009481192E-4%
1: 19 0.0028284289863357106%
2: 18 0.0026795643028443574%
3: 16 0.002381834935861651%
4: 16 0.002381834935861651%
5: 17 0.002530699619353004%
6: 10 0.0014886468349135321%
7: 6 8.931881009481192E-4%
8: 7 0.0010420527844394725%
9: 6 8.931881009481192E-4%
:: 132 0.019650138220858624%
;: 1538 0.22895388320970123%
?: 462 0.06877548377300517%
A: 460 0.06847775440602247%
B: 1078 0.16047612880367876%
C: 629 0.09363588591606116%
D: 548 0.08157784655326154%
E: 731 0.10882008363217918%
F: 146 0.021734243789737567%
G: 173 0.0257535902440041%
H: 676 0.10063252604015475%
I: 2576 0.38347542467372586%
J: 322 0.04793442808421573%
K: 95 0.014142144931678554%
L: 735 0.1094155423661446%
M: 1702 0.25336769130228315%
N: 238 0.03542979467094206%
O: 184 0.02739110176240899%
P: 178 0.026497913661460867%
R: 105 0.015630791766592086%
S: 512 0.07621871794757283%
T: 778 0.11581672375627278%
U: 23 0.003423887720301124%
V: 19 0.0028284289863357106%
W: 637 0.09482680338399198%
Y: 351 0.05225150390546497%
Z: 5 7.443234174567661E-4%
_: 808 0.12028266426101339%
a: 41225 6.136946576931035%
b: 8010 1.1924061147657392%
c: 12833 1.9103804832445355%
d: 21754 3.238402324670897%
e: 68641 10.218220739529976%
f: 11854 1.764641958106501%
g: 9857 1.4673591851742684%
h: 33391 4.970740646459775%
i: 35256 5.248373281171148%
j: 551 0.08202444060373561%
k: 3113 0.4634157597085825%
l: 20857 3.1048707035791536%
m: 13062 1.9444704957640553%
n: 37452 5.575280126118161%
o: 39855 5.933001960547882%
p: 8049 1.198211837421902%
q: 627 0.09333815654907845%
r: 32193 4.792400755637134%
s: 32598 4.852690952451131%
t: 45865 6.8276787083309145%
u: 14964 2.2276111237646092%
v: 5707 0.8495707486851526%
w: 11668 1.7369531269771092%
x: 839 0.12489746944924533%
y: 12355 1.8392231645356687%
z: 931 0.13859302033044982%
?: 1791 0.26661664813301356%
?: 1740 0.25902454927495455%

It was generated for “Pride And Prejudice” without header and license.

Main.java

import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.stream.Stream;

// ? 2018 TheFlyingKeyboard and released under MIT License
// theflyingkeyboard.net
public class Main {
    public static void main(String[] args) {
        Statistics statistics = new Statistics();

        try (Stream<String> stream = Files.lines(Paths.get("PRIDE AND PREJUDICE.txt"))) {
            stream.forEach(statistics::process);
        } catch (IOException e) {
            e.printStackTrace();
        }

        statistics.printStatistics();
    }
}

Statistics.java

import java.util.ArrayList;
import java.util.List;
import java.util.Map;
import java.util.TreeMap;

// ? 2018 TheFlyingKeyboard and released under MIT License
// theflyingkeyboard.net
public class Statistics {
    private Map<Character, Integer> charactersOccurrences = new TreeMap<>();
    private long characterCount;

    public void process(String text) {
        char charAt;

        for (int i = 0; i < text.length(); ++i) {
            charAt = text.charAt(i);

            if (charactersOccurrences.containsKey(charAt)) {
                charactersOccurrences.merge(charAt, 1, (oldValue, one) -> oldValue + one);
            } else {
                charactersOccurrences.put(charAt, 1);
            }

            ++characterCount;
        }
    }

    public void printStatistics() {
        List<Character> keys = new ArrayList<>(charactersOccurrences.keySet());
        int value;

        System.out.println("Total characters: " + characterCount);

        for (int i = 0; i < keys.size(); ++i) {
            value = charactersOccurrences.get(keys.get(i));
            System.out.println(keys.get(i) + ": " + value + " " + ((double) value / characterCount) * 100.0d + "%");
        }
    }
}