Merge branch 'FeKozma:main' into main

README.md

@@ -1,3 +1,4 @@
+
 # Code Check #
 
 Do you have a problem with duplicated functions in your java project? Here is the solution on how to find all the duplicate functions, specify the location of your repository in the local-config.properties file (just make a copy of config.properties) and run the code! Then you will get a file in "results" with all the places where functions match.
@@ -66,32 +67,21 @@ The results will be shown in the `/results/` folder. By default, the result nami
 ## Configuration file ##
 You can edit some configuration in `config.properties`.
 
-<details>
-  <summary>
-    Default configuration (click to expand)
-  </summary>
-
-###### *config.properties*
-```shell
-LOGGING_LEVEL=INFO
-  # This is related to TEMP_FILE below.
-TEMP_FILE_ENABLED=false
-  # If enabled, this file will be deleted and replaced every run instead of using the results files.
-TEMP_FILE=debugFile.txt
-  # Directory of where the result files are saved. They range from 0 to 99.
-PATH_TO_RESULTS=results
-  # Set this property to a path that should be excluded. It's regex based, so writing [file1, file2] would exclude any file containing file1 and file2.
-EXCLUDED_PATHS=[]
-  # Prefix for the result files.
-RESULT_NAME_PREFIX=result_{nr}
-  # The LLM located in project root.
-LLM_FILE=models/ggml-model-gpt4all-falcon-q4_0.bin
-  # Run with LLM - needs a model defined and will take more computing power and time to run.
-RUN_WITH_LLM=false
-  # Directory path to where the code is to be scanned.
-PATH_TO_CODE=src/test/resources/
-```
-</details>
+### Properties
+
+| Property             | Default values if not set (if not required) | Type         | Description                                                  |
+|----------------------|---------------------------------------------|--------------|--------------------------------------------------------------|
+| LOGGING_LEVEL        | INFO                                        | String       | Which level to show the logging in.                          |
+| PATH_TO_CODE         | src/test/resources/                         | String       | Required attribute. Where the code is located.               |
+| PATH_TO_RESULTS      | results                                     | String       | Results directory.                                           |
+| RESULT_NAME_PREFIX   | result_{nr}                                 | String       | Result name. {nr} will be replaced by an incremental number. |
+| RESULTS_FILE_LIMIT   | 100                                         | Integer      | Since it's creating a new file each run, there is a limit.   |
+| EXCLUDED_PATHS       | []                                          | List<String> | Separated by commas. Files/Paths to exclude during a run.    |
+| RUN_WITH_LLM         | false                                       | String       | Whether to use LLM during the run or not.                    |
+| LLM_FILE             | models/ggml-model-gpt4all-falcon-q4_0.bin   | String       | If running with LLM, this has to be set linking to a model.  |
+| LLM_THREADS          | 4                                           | Integer      | How many threads the LLM will be using.                      |
+| TEMP_FILE_ENABLED    | false                                       | Boolean      | Whether to use a temporary file.                             |
+| TEMP_FILE            | debugFile.txt                               | String       | Where the temporary file is located.                         |
 
 #### LOGGING_LEVEL
 The different options are the following:

config.properties

@@ -1,17 +1,22 @@
-LOGGING_LEVEL=DEBUG
-  # This is related to TEMP_FILE below.
-TEMP_FILE_ENABLED=false
-  # If enabled, this file will be deleted and replaced every run instead of using the results files.
-TEMP_FILE=debugFile.txt
-  # Directory of where the result files are saved. They range from 0 to 99.
+  # Valid values in order: OFF, ERROR, WARNING, INFO, DEBUG, TRACE.
+LOGGING_LEVEL=INFO
+  # Directory path to where the code will be scanned.
+PATH_TO_CODE=src/test/resources/
+  # Directory of where the result files are saved. By default, it ranges from 0 to 99, and can be changed in `RESULTS_FILE_LIMIT`.
 PATH_TO_RESULTS=results
-  # Set this property to a path that should be excluded. It's regex based, so writing [file1, file2] would exclude any file containing file1 and file2.
-EXCLUDED_PATHS=[]
   # Prefix for the result files.
 RESULT_NAME_PREFIX=result_{nr}
-  # The LLM located in project root.
-LLM_FILE=models/ggml-model-gpt4all-falcon-q4_0.bin
+  # Max amount of results files to create before the limit is reached. Starting from 0. The default value is 100.
+RESULTS_FILE_LIMIT=100
+  # Set this property to a path that should be excluded. It's regex based, so writing [file1, file2] would exclude any file containing file1 and file2.
+EXCLUDED_PATHS=[]
   # Run with LLM - needs a model defined and will take more computing power and time to run.
 RUN_WITH_LLM=false
-  # Directory path to where the code is to be scanned.
-PATH_TO_CODE=src/test/resources/
+  # The LLM located in project root.
+LLM_FILE=models/ggml-model-gpt4all-falcon-q4_0.bin
+  # How many threads the LLM will be using when it's running.
+LLM_THREADS=4
+# This is related to the `TEMP_FILE` option. If the temp file option should be enabled or not.
+TEMP_FILE_ENABLED=false
+# If enabled, this file will be deleted and replaced every run instead of using the result files option.
+TEMP_FILE=debugFile.txt

src/main/java/CodeCheck/CheckDirectory.java

@@ -3,6 +3,7 @@
 import java.io.File;
 import java.io.FileNotFoundException;
 import java.util.Arrays;
+import java.util.Collections;
 import java.util.List;
 import java.util.Scanner;
 import java.util.function.Predicate;
@@ -16,6 +17,7 @@ public class CheckDirectory {
     private final List<Pattern> EXCLUDED_PATHS = ConfigInterface
             .conf
             .getList("EXCLUDED_PATHS")
+            .orElse(Collections.emptyList())
             .stream()
             .filter(Predicate.not(String::isEmpty))
             .map(path -> "((?i)" + path.trim() + "(?-i))")
@@ -26,7 +28,7 @@ public void startModel() {
         llm.initModel();
     }
 
-    public void stopModel() throws Exception {
+    public void stopModel() {
         llm.cleanModel();
     }
 
@@ -81,8 +83,8 @@ public ManyFunctions checkFile(File file) {
                         manyFunctions.commitFile(file.getName());
                         manyFunctions.commitLine(lineNumber);
 
-                        Log.trace("Full path: " + file.getAbsolutePath());
-                        Log.debug("Function: " +
+                        Log.debug("Accessing file at the path: " + file.getAbsolutePath());
+                        Log.trace("Function: " +
                                 manyFunctions.commit.name + " in " +
                                 manyFunctions.commit.file + ":" +
                                 manyFunctions.commit.line + " with " +

src/main/java/CodeCheck/CodeCheck.java

@@ -4,9 +4,11 @@
 import java.util.List;
 
 public interface CodeCheck {
+
     static void execute() throws Exception {
         ConfigInterface.conf.loadConfig();
-        String PATH_TO_CODE = Util.checkIfHomePath(ConfigInterface.conf.getString("PATH_TO_CODE"));
+
+        String PATH_TO_CODE = Util.checkIfHomePath(ConfigInterface.conf.getProperty("PATH_TO_CODE"));
         File baseCodeDir = new File(PATH_TO_CODE);
 
         CheckDirectory checkDirectory = new CheckDirectory();

src/main/java/CodeCheck/ConfigInterface.java

@@ -1,10 +1,7 @@
 package CodeCheck;
 
 import java.io.*;
-import java.util.Arrays;
-import java.util.Collections;
-import java.util.List;
-import java.util.Properties;
+import java.util.*;
 
 public interface ConfigInterface {
     Config conf = new Config();
@@ -54,36 +51,75 @@ public void loadConfig() throws IOException {
             }
         }
 
-        public String getString(String key) {
-            if (appProps == null) return null;
-            return appProps.get(key).toString();
+        public String getProperty(String key) {
+            if (appProps == null) {
+                Log.warning("'%s' not initialized. The key '%s' was not loaded".formatted(appProps.getClass().getSimpleName(), key));
+                throw new RuntimeException("'appProps' is null - cannot continue. Configuration not initialized.");
+            }
+
+            try {
+                return appProps.get(key).toString().strip();
+            } catch (NullPointerException e) {
+                throw new NullPointerException(e.getMessage());
+            }
         }
 
-        public Boolean getBoolean(String key) {
-            return appProps.get(key).toString().equalsIgnoreCase("true");
+        public Optional<String> getString(String key) {
+            try {
+                return Optional.of(getProperty(key));
+            } catch (NullPointerException e) {
+                return Optional.empty();
+            }
         }
 
-        public List<String> getList(String key) {
-            String value = getString(key);
+        public Optional<Boolean> getBoolean(String key) {
+            try {
+                return Optional.of(getProperty(key).equalsIgnoreCase("true"));
+            } catch (NullPointerException e) {
+                return Optional.empty();
+            }
+        }
 
-            if (value == null)
-                return Collections.emptyList();
+        public Optional<Integer> getInteger(String key) {
+            try {
+                return Optional.of(Integer.parseInt(getProperty(key)));
+            } catch (NumberFormatException | NullPointerException e) {
+                return Optional.empty();
+            }
+        }
 
-            return Arrays
-                    .stream(value.substring(1, value.length() - 1).split(","))
-                    .map(String::strip)
-                    .toList();
+        public Optional<List<String>> getList(String key) {
+            try {
+                String value = getProperty(key);
+
+                if (value == null)
+                    return Optional.of(Collections.emptyList());
+
+                return Optional.of(
+                        Arrays
+                        .stream(value.substring(1, value.length() - 1).split(","))
+                        .map(String::strip)
+                        .toList());
+            } catch (NullPointerException e) {
+                return Optional.empty();
+            }
         }
 
         public LoggingLevel getLogLvl() {
-            String loggingLevel = getString("LOGGING_LEVEL");
-            if (loggingLevel == null) loggingLevel = "DEBUG";
-            return LoggingLevel.valueOf(loggingLevel);
+            String loggingLevel = getString("LOGGING_LEVEL")
+                    .orElse("INFO");
+
+            try {
+                return LoggingLevel.valueOf(loggingLevel.toUpperCase());
+            } catch (IllegalArgumentException e) {
+                Log.error(getLogLvl().name() + "::LoggingLevel got an error. %s.".formatted(e.getMessage()));
+                return LoggingLevel.INFO;
+            }
         }
 
         private int countLines(File file) throws IOException {
-            BufferedReader reader = new BufferedReader(new FileReader(file));
             int lines = 0;
+            BufferedReader reader = new BufferedReader(new FileReader(file));
             while (reader.readLine() != null) lines++;
             reader.close();
             return lines;

src/main/java/CodeCheck/LLM.java

@@ -21,8 +21,8 @@ public void initModel() {
         startTime = System.currentTimeMillis();
 
         runIfConfig(() -> {
-            Path modelPath = Path.of(Util.checkIfHomePath(
-                    ConfigInterface.conf.getString("LLM_FILE")));
+            Path modelPath = ConfigInterface.conf.getBoolean("RUN_WITH_LLM")
+                            .orElse(false) ? Path.of(Util.checkIfHomePath(ConfigInterface.conf.getProperty("LLM_FILE"))) : null;
 
             if (Files.isDirectory(modelPath)) {
                 Log.error("LLM_FILE not configured correctly - it is a directory, but was expecting a model file. Please change it into a correct model filepath.");
@@ -33,7 +33,8 @@ public void initModel() {
             }
 
             model = new LLModel(modelPath);
-            model.setThreadCount(6);
+            model.setThreadCount(ConfigInterface.conf.getInteger("LLM_THREADS")
+                    .orElse(4));
 
             Log.debug("Thread Count: " + model.threadCount());
 
@@ -51,26 +52,24 @@ public void cleanModel() {
             try {
                 model.close();
             } catch (Exception e) {
-                String errorMessage = "LLM is not closing...";
-                Log.error(errorMessage);
-                throw new RuntimeException(errorMessage, e);
+                throw new RuntimeException("LLM is not closing...", e);
             }
             return true;
         });
 
-        int[] formattedTime = Util.getFormattedDurationTime(startTime);
-        Log.log(String.format("LLM run completed in %02d hours, %02d minutes, %02d seconds and %02d milliseconds.",
+        int[] formattedTime = Util.getPreparedDurationTime(startTime);
+        Log.log(String.format("Run completed in %02d hours, %02d minutes, %02d seconds and %02d milliseconds.",
                 formattedTime[0], formattedTime[1], formattedTime[2], formattedTime[3]));
     }
 
     public String getAnswer(String question) {
 
-        Log.debug("Question: " + question);
+        Log.trace("Question: " + question);
 
         return runIfConfig(() -> {
             String answer = model.chatCompletion(createMessage(question), config).choices.toString();
 
-            Log.debug("Answer: " + answer);
+            Log.trace("Answer: " + answer);
 
             return answer;
         }).orElse("LLM has not been configured.");
@@ -81,7 +80,8 @@ private List<Map<String, String>> createMessage(String content) {
     }
 
     private <T> Optional<T> runIfConfig(Supplier<T> supplier) {
-        if (ConfigInterface.conf.getBoolean("RUN_WITH_LLM")) {
+        if (ConfigInterface.conf.getBoolean("RUN_WITH_LLM")
+                .orElse(false)) {
             return Optional.of(supplier.get());
         }
         return Optional.empty();

src/main/java/CodeCheck/Main.java

@@ -1,12 +1,18 @@
 package CodeCheck;
 
+import java.time.LocalDateTime;
+import java.time.format.DateTimeFormatter;
+
 public class Main {
+
     public static void main(String[] args) throws Exception {
-        Log.log("Starting up...");
+        long startTime = System.currentTimeMillis();
+        Log.log("Starting up at: %s.".formatted(LocalDateTime.now().format(DateTimeFormatter.ofPattern("yyyy-MM-dd HH:mm:ss.SSS"))));
         Log.log("Running on %s.".formatted(System.getProperty("os.name")));
 
         CodeCheck.execute();
 
-        Log.log("Shutting down...");
+        Log.log("Shutting down at: %s.".formatted(LocalDateTime.now().format(DateTimeFormatter.ofPattern("yyyy-MM-dd HH:mm:ss.SSS"))));
+        Log.log("Total duration: %s".formatted(Util.getFormattedDurationTime(startTime)));
     }
 }