Fix the bug that the default language symbols override the symbols.

.gitlab-ci.yml

@@ -0,0 +1,10 @@
+image: clojure:temurin-11-lein-2.10.0-alpine
+
+stages:
+  - test
+
+unit tests:
+  stage: test
+  script:
+    - lein test
+

CHANGELOG.md

@@ -0,0 +1,127 @@
+# Change Log
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [Unreleased]
+
+## [0.5.3] - 2023-10-05
+
+### Added
+- Add the CHANGELOG.
+
+## [0.5.2] - 2023-10-02
+
+### Fixed
+- Fix checking for file existence only when the options are set.
+- Fix writing to a file only when the option is set.
+
+## [0.5.1] - 2023-09-28
+
+### Added
+- Add the output option to save into a file.
+- Add the file errors to prevent using an invalid file path.
+
+## [0.5.0] - 2023-09-22
+
+### Changed
+- Update symbol defaults, factories to have only lower alphabets.
+- Update the Caesar to be case-insensitive and skip unknown symbols.
+- Update Caesar Analyzers to be case-insensitive and testable.
+
+## [0.4.3] - 2023-09-21
+
+### Added
+- Add the language option for symbols.
+
+### Changed
+- Update the CLI to have separated actions and an option initializer.
+
+## [0.4.2] - 2023-09-18
+
+### Added
+- Add tests for the cipher-analyzers module.
+
+### Changed
+- Rename the cipher_analyzer module to cipher-analyzers.
+
+## [0.4.1] - 2023-09-17
+
+### Added
+- Add symbol factories for punctuation, space, defaults symbols.
+- Add the action-type to distinguish the actions.
+- Add the symbol option and its default.
+- Add the cracking option.
+
+### Changed
+- Rename the language_analyzer module to language-analyzer.
+- Update the nonsense for the is-nonsense? test.
+- Rename the symbol_frequences module to symbol-frequences.
+
+## [0.4.0] - 2023-09-15
+
+### Added
+- Add Chi-squared Statistic function to analyze texts.
+- Add the caesar-analyzers to get the plaintext from a ciphertext.
+
+## [0.3.5] - 2023-09-14
+
+### Added
+- Add the frequences of symbols as defaults.
+
+## [0.3.4] - 2023-09-13
+
+### Added
+- Add a simple language analyzers.
+
+## [0.3.3] - 2023-09-12
+
+### Added
+- Add an option to read a message from a file.
+
+## [0.3.2] - 2023-09-11
+
+### Added
+- Add the CI/CD configuration.
+
+## [0.3.1] - 2023-09-11
+
+### Added
+- Add factories for symbols.
+- Add tests for factories.
+
+## [0.3.0] - 2023-09-10
+
+### Added
+- Add a simple cli interface.
+
+## [0.2.0] - 2023-09-09
+
+### Added
+- Add a implementation of Caesar cipher.
+
+## [0.1.0] - 2023-09-09
+
+### Added
+- Project initialization.
+
+[Unreleased]: https://gitlab.com/KKlochko/cipher-analytical-machine/-/compare/0.5.3...main?from_project_id=50218541&straight=false
+[0.5.3]: https://gitlab.com/KKlochko/cipher-analytical-machine/-/compare/0.5.2...0.5.3?from_project_id=50218541&straight=false
+[0.5.2]: https://gitlab.com/KKlochko/cipher-analytical-machine/-/compare/0.5.1...0.5.2?from_project_id=50218541&straight=false
+[0.5.1]: https://gitlab.com/KKlochko/cipher-analytical-machine/-/compare/0.5.0...0.5.1?from_project_id=50218541&straight=false
+[0.5.0]: https://gitlab.com/KKlochko/cipher-analytical-machine/-/compare/0.4.3...0.5.0?from_project_id=50218541&straight=false
+[0.4.3]: https://gitlab.com/KKlochko/cipher-analytical-machine/-/compare/0.4.2...0.4.3?from_project_id=50218541&straight=false
+[0.4.2]: https://gitlab.com/KKlochko/cipher-analytical-machine/-/compare/0.4.1...0.4.2?from_project_id=50218541&straight=false
+[0.4.1]: https://gitlab.com/KKlochko/cipher-analytical-machine/-/compare/0.4.0...0.4.1?from_project_id=50218541&straight=false
+[0.4.0]: https://gitlab.com/KKlochko/cipher-analytical-machine/-/compare/0.3.5...0.4.0?from_project_id=50218541&straight=false
+[0.3.5]: https://gitlab.com/KKlochko/cipher-analytical-machine/-/compare/0.3.4...0.3.5?from_project_id=50218541&straight=false
+[0.3.4]: https://gitlab.com/KKlochko/cipher-analytical-machine/-/compare/0.3.3...0.3.4?from_project_id=50218541&straight=false
+[0.3.3]: https://gitlab.com/KKlochko/cipher-analytical-machine/-/compare/0.3.2...0.3.3?from_project_id=50218541&straight=false
+[0.3.2]: https://gitlab.com/KKlochko/cipher-analytical-machine/-/compare/0.3.1...0.3.2?from_project_id=50218541&straight=false
+[0.3.1]: https://gitlab.com/KKlochko/cipher-analytical-machine/-/compare/0.3.0...0.3.1?from_project_id=50218541&straight=false
+[0.3.0]: https://gitlab.com/KKlochko/cipher-analytical-machine/-/compare/0.2.0...0.3.0?from_project_id=50218541&straight=false
+[0.2.0]: https://gitlab.com/KKlochko/cipher-analytical-machine/-/compare/0.1.0...0.2.0?from_project_id=50218541&straight=false
+[0.1.0]: https://gitlab.com/KKlochko/cipher-analytical-machine/-/commit/a7a715b94276fc8f46fb6a44139636d27b551599
+

project.clj

@@ -8,6 +8,7 @@
                  [org.apache.tika/tika-core "1.28.5"]
                  [org.apache.tika/tika-langdetect "1.28.5"]]
   :main ^:skip-aot cipher-analytical-machine.core
+  :java-source-paths ["src/main/java"]
   :target-path "target/%s"
   :profiles {:uberjar {:aot :all
                        :jvm-opts ["-Dclojure.compiler.direct-linking=true"]}})

src/cipher_analytical_machine/analyzers/analyzers.clj

@@ -1,4 +1,4 @@
-(ns cipher-analytical-machine.cipher-analyzers
+(ns cipher-analytical-machine.analyzers.analyzers
   (:require [clojure.string :as cs])
   (:gen-class))
 
@@ -21,16 +21,16 @@
 
 (defn chi-squared-statistic
   "To calculate the frequency distribution of a language. More detail about the algorithm here: http://practicalcryptography.com/cryptanalysis/text-characterisation/chi-squared-statistic/"
-  [text letter-frequences]
+  [text letter-frequencies]
   (let [length-text (count text)
         letter-counts (count-characters (cs/lower-case text))]
     ;letter-counts
     (reduce
      (fn [acc [char count]]
        (+ acc
-          (if (contains? letter-frequences char)
+          (if (contains? letter-frequencies char)
             (chi-squared-letter-statistic count
-                                          (get letter-frequences char)
+                                          (get letter-frequencies char)
                                           length-text)
             0)))
             0

src/cipher_analytical_machine/analyzers/caesar.clj

@@ -1,7 +1,9 @@
-(ns cipher-analytical-machine.caesar-analyzers
+(ns cipher-analytical-machine.analyzers.caesar
-  (:require [cipher-analytical-machine.caesar :as caesar]
+  (:require [cipher-analytical-machine.ciphers.caesar :as caesar]
             [clojure.string :as cs]
-            [cipher-analytical-machine.cipher-analyzers :as ca])
+            [cipher-analytical-machine.analyzers.analyzers :as ca])
+  (:import [cipher_analytical_machine.ciphers.caesar Decrypted]
+           [cipher_analytical_machine.analyzers.caesar FrequencyAnalyzer])
   (:gen-class))
 
 (defn get-all-texts
@@ -15,9 +17,9 @@
 
 (defn get-all-scores
   "For pairs (key, plaintext) finds scores and return list of pairs [key, score]."
-  [letter-frequences pairs]
+  [letter-frequencies pairs]
   (map (fn [[key text]]
-         [key (ca/chi-squared-statistic text letter-frequences)])
+         [key (ca/chi-squared-statistic text letter-frequencies)])
        pairs))
 
 (defn get-min-score-pair
@@ -32,17 +34,26 @@
 
 (defn get-key
   "To find the key with frequencies of letters."
-  [ciphertext symbols letter-frequences]
+  [ciphertext symbols letter-frequencies]
   (->> (get-all-texts ciphertext symbols)
-       (get-all-scores letter-frequences)
+       (get-all-scores letter-frequencies)
        (get-min-score-pair)
        (first)))
 
 (defn get-plaintext
   "Return the plaintext from a ciphertext. The function is case-insensitive."
-  [ciphertext symbols letter-frequences]
+  [ciphertext symbols letter-frequencies]
   (let [ciphertext (cs/lower-case ciphertext)]
     (caesar/decrypt-message ciphertext
-                            (get-key ciphertext symbols letter-frequences)
+                            (get-key ciphertext symbols letter-frequencies)
                             symbols)))
 
+(defn frequency-analizer-get-plaintext
+  "Return the plaintext from a ciphertext using simple analizer. The function is case-insensitive."
+  [ciphertext symbols letter-frequencies-string]
+  (let [decrypt (reify Decrypted
+                  (decrypt [this message key symbols]
+                    (caesar/decrypt-message message key symbols)))]
+    (-> (new FrequencyAnalyzer ciphertext symbols letter-frequencies-string decrypt)
+        .crack)))
+

src/cipher_analytical_machine/analyzers/language.clj

@@ -1,4 +1,4 @@
-(ns cipher-analytical-machine.language-analyzer
+(ns cipher-analytical-machine.analyzers.language
   (:import [org.apache.tika.language LanguageIdentifier])
   (:gen-class))
 

src/cipher_analytical_machine/ciphers/caesar.clj

@@ -1,4 +1,4 @@
-(ns cipher-analytical-machine.caesar
+(ns cipher-analytical-machine.ciphers.caesar
   (:require [clojure.string :as cs])
   (:gen-class))
 

src/cipher_analytical_machine/cli/cli.clj

@@ -1,10 +1,10 @@
-(ns cipher-analytical-machine.cli
+(ns cipher-analytical-machine.cli.cli
   (:require
-   [cipher-analytical-machine.file :as file]
+   [cipher-analytical-machine.cli.file :as file]
-   [cipher-analytical-machine.caesar :as caesar]
+   [cipher-analytical-machine.ciphers.caesar :as caesar]
-   [cipher-analytical-machine.caesar-analyzers :as caesar-analyzers]
+   [cipher-analytical-machine.analyzers.caesar :as caesar-analyzers]
-   [cipher-analytical-machine.symbol-factories :as sf]
+   [cipher-analytical-machine.symbols.factories :as sf]
-   [cipher-analytical-machine.symbol-frequences :as symbol-frequences]
+   [cipher-analytical-machine.symbols.frequencies :as symbol-frequencies]
    [clojure.string :as cs]
    [clojure.tools.cli :refer [parse-opts]])
   (:gen-class))
@@ -122,8 +122,10 @@
 (defn set-symbols
   "Set defaults symbols for a language."
   [options]
-  (set-option options :symbols
+  (if (contains? options :language)
-              (sf/default-symbol-factory (:language options))))
+    (set-option options :symbols
+                (sf/default-symbol-factory (:language options)))
+    options))
 
 (defn load-and-set-option
   "Load the option and set it."
@@ -155,7 +157,7 @@
   [options arguments action-type]
   (let [message (:message options)
         symbols (:symbols options)
-        frequencies symbol-frequences/english-letter-frequences]
+        frequencies symbol-frequencies/english-letter-frequencies]
     (cond
       (= action-type :cracking)
       (caesar-analyzers/get-plaintext message symbols frequencies)

src/cipher_analytical_machine/cli/file.clj

@@ -1,4 +1,4 @@
-(ns cipher-analytical-machine.file
+(ns cipher-analytical-machine.cli.file
   (:require [clojure.java.io :as io])
   (:gen-class))
 

src/cipher_analytical_machine/core.clj

@@ -1,6 +1,6 @@
 (ns cipher-analytical-machine.core
   (:require
-   [cipher-analytical-machine.cli :as cli])
+   [cipher-analytical-machine.cli.cli :as cli])
   (:gen-class))
 
 (defn -main

src/cipher_analytical_machine/symbols/factories.clj

@@ -1,4 +1,4 @@
-(ns cipher-analytical-machine.symbol-factories
+(ns cipher-analytical-machine.symbols.factories
   (:require [clojure.string :as cs])
   (:gen-class))
 

src/cipher_analytical_machine/symbols/frequencies.clj

@@ -1,7 +1,17 @@
-(ns cipher-analytical-machine.symbol-frequences
+(ns cipher-analytical-machine.symbols.frequencies
   (:gen-class))
 
-(def english-letter-frequences {
+(defn map-to-string
+  "Convert the map of frequencies to the frequency string. Letters are sorted by frequency in descending order."
+  [frequency-map]
+  (->> frequency-map
+       (reduce (fn [acc el] (conj acc el)) [])
+       (sort-by last)
+       (map first)
+       (reverse)
+       (apply str)))
+
+(def english-letter-frequencies {
    \a 0.0804
    \b 0.0154
    \c 0.0306
@@ -30,7 +40,7 @@
    \z 0.0009
 })
 
-(def ukrainian-letter-frequences {
+(def ukrainian-letter-frequencies {
    \а 0.064
    \б 0.013
    \в 0.046

src/main/java/cipher_analytical_machine/analyzers/caesar/FrequencyAnalyzer.java

@@ -0,0 +1,25 @@
+package cipher_analytical_machine.analyzers.caesar;
+
+import cipher_analytical_machine.ciphers.caesar.Decrypted;
+import java.util.Map;
+
+public class FrequencyAnalyzer {
+    private String ciphertext;
+    private int key;
+    private String symbols;
+    private String symbol_frequences;
+    private Decrypted decryptor;
+
+    public FrequencyAnalyzer(String ciphertext, String symbols, String symbol_frequences, Decrypted decryptor) {
+	this.ciphertext = ciphertext;
+	this.key = 1;
+	this.symbols = symbols;
+	this.symbol_frequences = symbol_frequences;
+	this.decryptor = decryptor;
+    }
+
+    public String crack() {
+	return decryptor.decrypt(ciphertext, key, symbols);
+    }
+}
+

src/main/java/cipher_analytical_machine/ciphers/caesar/Decrypted.java

@@ -0,0 +1,6 @@
+package cipher_analytical_machine.ciphers.caesar;
+
+public interface Decrypted {
+    String decrypt(String message, int key, String symbols);
+}
+

test/cipher_analytical_machine/analyzers/caesar_test.clj

@@ -1,9 +1,9 @@
-(ns cipher-analytical-machine.caesar-analyzers-test
+(ns cipher-analytical-machine.analyzers.caesar-test
   (:require
    [clojure.test :refer :all]
-   [cipher-analytical-machine.caesar-analyzers :refer :all]
+   [cipher-analytical-machine.analyzers.caesar :refer :all]
-   [cipher-analytical-machine.symbol-frequences :as sf]
+   [cipher-analytical-machine.symbols.frequencies :as sf]
-   [cipher-analytical-machine.cipher-analyzers :as ca]
+   [cipher-analytical-machine.analyzers.analyzers :as ca]
    [clojure.string :as cs]))
 
 (deftest get-all-texts-test
@@ -25,9 +25,9 @@
   (testing "There're 27 combinations for a 'Hello World'."
     (let [ciphertext "khoorczruog"
           symbols "abcdefghijklmnopqrstuvwxyz "
-          frequences sf/english-letter-frequences
+          frequencies sf/english-letter-frequencies
           text-pairs (get-all-texts ciphertext symbols)]
-      (is (= 27 (count (get-all-scores frequences text-pairs)))))))
+      (is (= 27 (count (get-all-scores frequencies text-pairs)))))))
 
 (deftest get-min-score-pair-test
   (testing "If a key is one, then the min score pair is 15."
@@ -40,37 +40,47 @@
         ciphertext "khoorczruog"
         key 3
         symbols "abcdefghijklmnopqrstuvwxyz "
-        frequences sf/english-letter-frequences]
+        frequencies sf/english-letter-frequencies]
     (testing "The plaintext is encrypted with 3 as the key."
-      (is (= key (get-key ciphertext symbols frequences)))))
+      (is (= key (get-key ciphertext symbols frequencies)))))
 
   (let [; З поеми "Кавказ" Тараса Григоровича Шевченка:
         plaintext "Борітеся – поборете, Вам Бог помагає! За вас правда, за вас слава. І воля святая!"
         ciphertext "жхчощйшде–ецхжхчйщй,езєуежхиецхуєиєк!емєезєшецчєзїє,емєезєшештєзє.еоезхтдешздщєд!"
         key 7
         symbols "абвгґдеєжзиіїйклмнопрстуфхцчшщьюя "
-        frequences sf/ukrainian-letter-frequences]
+        frequencies sf/ukrainian-letter-frequencies]
     (testing "The plaintext is encrypted with 3 as the key."
-      (is (= key (get-key ciphertext symbols frequences))))))
+      (is (= key (get-key ciphertext symbols frequencies))))))
 
 (deftest get-plaintext-test
   (let [plaintext "hello world"
         ciphertext "khoorczruog"
         symbols "abcdefghijklmnopqrstuvwxyz "
-        frequences sf/english-letter-frequences]
+        frequencies sf/english-letter-frequencies]
     (testing "The plaintext is encrypted with 3 as the key."
-      (is (= plaintext (get-plaintext ciphertext symbols frequences))))
+      (is (= plaintext (get-plaintext ciphertext symbols frequencies))))
 
     (testing "The ciphertext is case-insensitive."
-      (is (= plaintext (get-plaintext "KhoorcZruog" symbols frequences)))))
+      (is (= plaintext (get-plaintext "KhoorcZruog" symbols frequencies)))))
 
   (let [; З поеми "Кавказ" Тараса Григоровича Шевченка:
         plaintext "Борітеся – поборете, Вам Бог помагає! За вас правда, за вас слава. І воля святая!"
         ciphertext "жхчощйшде–ецхжхчйщй,езєуежхиецхуєиєк!емєезєшецчєзїє,емєезєшештєзє.еоезхтдешздщєд!"
         key 7
         symbols "абвгґдеєжзиіїйклмнопрстуфхцчшщьюя "
-        frequences sf/ukrainian-letter-frequences]
+        frequencies sf/ukrainian-letter-frequencies]
     (testing "The ciphertext is case-insensitive."
       (is (= (cs/lower-case plaintext)
-             (get-plaintext ciphertext symbols frequences))))))
+             (get-plaintext ciphertext symbols frequencies))))))
+
+(deftest frequency-analizer-get-plaintext-test
+  (let [plaintext "abc"
+        ciphertext "bca"
+        key 1
+        symbols "abc"
+        frequencies "etaoinsrhldcumfpgwybvkxjqz"]
+    (testing "The ciphertext is 'bca' and key is 1."
+      (is (= plaintext
+             (frequency-analizer-get-plaintext ciphertext symbols frequencies))))))
 

test/cipher_analytical_machine/analyzers/language_test.clj

@@ -1,7 +1,7 @@
-(ns cipher-analytical-machine.language-analyzer-test
+(ns cipher-analytical-machine.analyzers.language-test
   (:require
    [clojure.test :refer :all]
-   [cipher-analytical-machine.language-analyzer :refer :all]
+   [cipher-analytical-machine.analyzers.language :refer :all]
   ))
 
 (deftest detect-language-test

test/cipher_analytical_machine/cipher_analyzers_test.clj

@@ -1,25 +0,0 @@
-(ns cipher-analytical-machine.cipher-analyzers-test
-  (:require
-   [clojure.test :refer :all]
-   [cipher-analytical-machine.cipher-analyzers :refer :all]))
-
-(deftest count-characters-test
-  (testing "Count two dublicates and one uniq character from a string."
-    (is (= {\a 2 \b 1}
-           (count-characters "aba")))))
-
-(deftest chi-squared-letter-statistic-test
-  (testing "If the frequence of A is 0.1, the text length is 100 and contains 20 times, then the chi-squared is 10."
-    (is (= 10.0
-           (chi-squared-letter-statistic 20 0.1 100))))
-
-  (testing "If the frequence of A is 0.1, the text length is 10 and contains 5 times, then the chi-squared is 16.0."
-    (is (= 16.0
-           (chi-squared-letter-statistic 5 0.1 10)))))
-
-(deftest chi-squared-statistic-test
-  (let [text "aaaaabbbbb"]
-  (testing "If the frequences of a and b is 0.1, the text length is 10 and contains them 5 times, then score is 32."
-    (is (= 32.0
-           (chi-squared-statistic text {\a 0.1 \b 0.1}))))))
-

test/cipher_analytical_machine/ciphers/caesar_test.clj

@@ -1,7 +1,7 @@
-(ns cipher-analytical-machine.caesar-test
+(ns cipher-analytical-machine.ciphers.caesar-test
   (:require
    [clojure.test :refer :all]
-   [cipher-analytical-machine.caesar :refer :all]
+   [cipher-analytical-machine.ciphers.caesar :refer :all]
   ))
 
 (deftest calculate-char-index-test

test/cipher_analytical_machine/symbols/factories_test.clj

@@ -1,7 +1,7 @@
-(ns cipher-analytical-machine.symbol-factories-test
+(ns cipher-analytical-machine.symbols.factories-test
   (:require
    [clojure.test :refer :all]
-   [cipher-analytical-machine.symbol-factories :refer :all]
+   [cipher-analytical-machine.symbols.factories :refer :all]
   ))
 
 (deftest english-alphabet-factory-test

test/cipher_analytical_machine/symbols/frequencies_test.clj

@@ -0,0 +1,11 @@
+(ns cipher-analytical-machine.symbols.frequencies-test
+  (:require
+   [clojure.test :refer :all]
+   [cipher-analytical-machine.symbols.frequencies :refer :all]))
+
+(deftest calculate-char-index-test
+  (let [symbol-map english-letter-frequencies]
+    (testing "The map must be converted to 'etaoinsrhldcumfpgwybvkxjqz'"
+      (is (= "etaoinsrhldcumfpgwybvkxjqz"
+             (map-to-string symbol-map))))))
+