Now using java8 for older builds

src/hadoop_analysis/build_manager.py

@@ -8,6 +8,29 @@ import json
 from java_version_manager import switch_java_version
 
 
+def create_maven_settings(repo_path):
+    """Create or modify Maven settings to enforce HTTPS."""
+    settings_path = os.path.join(repo_path, "settings.xml")
+    settings_content = f"""
+    <settings xmlns="http://maven.apache.org/SETTINGS/1.0.0"
+              xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+              xsi:schemaLocation="http://maven.apache.org/SETTINGS/1.0.0
+                                  https://maven.apache.org/xsd/settings-1.0.0.xsd">
+        <mirrors>
+            <mirror>
+                <id>central-https</id>
+                <mirrorOf>central</mirrorOf>
+                <name>Maven Central mirror over HTTPS</name>
+                <url>https://repo.maven.apache.org/maven2</url>
+            </mirror>
+        </mirrors>
+    </settings>
+    """
+    with open(settings_path, "w") as file:
+        file.write(settings_content)
+    return settings_path
+
+
 def parse_pom_xml(file_path):
     tree = ET.parse(file_path)
     root = tree.getroot()
@@ -69,7 +92,8 @@ def version_is_compatible(required_version_range, installed_version):
         try:
             normalized_installed_version = normalize_version(installed_version)
             if "," in required_version_range:
-                lower_bound = required_version_range.strip("[]()").split(",")[0].strip()
+                lower_bound = required_version_range.strip("[]()").split(",")[
+                    0].strip()
                 if version.parse(normalized_installed_version) >= version.parse(
                     lower_bound
                 ):
@@ -110,11 +134,13 @@ def process_commit_hashes(commit_hashes, repo_path, output_dir):
     for hash in commit_hashes:
         hash = hash.strip()
         try:
-            subprocess.run(["git", "reset", "--hard"], cwd=repo_path, check=True)
+            subprocess.run(["git", "reset", "--hard"],
+                           cwd=repo_path, check=True)
             subprocess.run(["git", "clean", "-fdx"], cwd=repo_path, check=True)
 
             # Checkout the specified hash
-            subprocess.run(["git", "checkout", hash], cwd=repo_path, check=True)
+            subprocess.run(["git", "checkout", hash],
+                           cwd=repo_path, check=True)
             print(f"Checked out {hash}")
 
             # Get repo requirements
@@ -162,16 +188,21 @@ def process_commit_hashes(commit_hashes, repo_path, output_dir):
             )
             print("=" * 10)
 
-            is_version_compatible = version_is_compatible(java_required, java_installed)
+            is_version_compatible = version_is_compatible(
+                java_required, java_installed)
             java_versions[hash]["compatible"] = is_version_compatible
+            is_version_compatible = True # Temporarily skipping checking compatible versions
 
             # Proceed if versions are compatible
             if (
                 is_version_compatible
             ):  # and version_is_compatible(maven_required, maven_installed):
                 # Run Maven to build the project
+
+                settings_path = create_maven_settings(repo_path)
                 subprocess.run(
-                    f"cd {repo_path} && mvn clean package --projects :hadoop-common --also-make -DskipTests",
+                    f"cd {repo_path} && mvn --settings {settings_path} clean package -Dhttps.protocols=TLSv1.2 --projects :hadoop-common --also-make -DskipTests \
+                        -Dmaven.wagon.http.ssl.insecure=true -Dmaven.wagon.http.ssl.allowall=true",
                     shell=True,
                     check=True,
                 )

src/hadoop_analysis/java_version_manager.py

@@ -20,15 +20,15 @@ def switch_java_version(java_version):
         java_version (str): The name of the Java version to switch to, as listed by 'update-java-alternatives --list'.
     """
     version_map = {
-        "1.6": "jdk1.6.0_45",
-        "1.7": "java-se-7u75-ri",
+        "1.6": "temurin-8-jdk-amd64",
+        "1.7": "temurin-8-jdk-amd64",
         "1.8": "temurin-8-jdk-amd64",
         "11": "temurin-11-jdk-amd64",
         "21": "temurin-21-jdk-amd64"
     }
 
     maven_map = {
-        "1.6": "/opt/maven/apache-maven-3.0.5",
+        "1.6": "/opt/maven/apache-maven-3.6.3",
         "1.7": "/opt/maven/apache-maven-3.6.3",
         "1.8": "/opt/maven/apache-maven-3.6.3",
         "11": "/opt/maven/apache-maven-3.6.3",

src/hadoop_analysis/main.py

@@ -10,7 +10,7 @@ from visualization import create_charts
 
 from java_version_manager import switch_java_version
 from dependency_analyzer import analyze_dependencies, get_rsf_file_paths
-from clustering import run_pkg, run_acdc, run_clusterer
+from clustering import RepoClusterer
 from clustering_result_analyzer import analyze_clustering_results
 
 # Define default paths for input and output directories
@@ -57,9 +57,10 @@ def main():
     analyze_dependencies(output_dir)
 
     # Clustering
-    run_pkg(output_dir)
-    run_acdc(output_dir)
-    run_clusterer(output_dir)
+    clusterer =  RepoClusterer(output_dir)
+    clusterer.run_pkg()
+    clusterer.run_acdc()
+    clusterer.run_clusterer()
 
     # Analyzing the clustering results
     analyze_clustering_results(output_dir)

src/hadoop_analysis/statistical_analysis.py

@@ -40,7 +40,7 @@ def perform_statistical_analysis(commit_info_file_path, output_dir):
     for decision_type in decision_types:
         for attribute in attributes:
             decision_df = df[df[f"is{decision_type}Decision"]]
-            output_file = os.path.join(output_dir, f"{decision_type.lower()}_decision_{attribute}_vs_a2a.pdf")
+            output_file = os.path.join(output_dir, '_statistical_analysis', f"{decision_type.lower()}_decision_{attribute}_vs_a2a.pdf")
             plot_scatterplot_and_correlation(
                 decision_df, 
                 attribute,