greenmining 1.2.5__tar.gz → 1.2.6__tar.gz

{greenmining-1.2.5 → greenmining-1.2.6}/CHANGELOG.md

@@ -1,5 +1,21 @@
 # Changelog
 
+## [1.2.5] - 2026-02-02
+
+### Added
+- `shallow_clone` parameter (default: True) to significantly reduce repository download size
+- `clone_depth` parameter for custom clone depth (auto-calculated as `max(50, max_commits * 3)` if None)
+- Manual git shallow cloning before PyDriller analysis for dramatic performance improvement
+
+### Changed
+- Repository cloning now uses `git clone --depth=N` by default, reducing download times by ~90%
+- Clone depth automatically calculated based on max_commits to ensure sufficient history
+
+### Performance
+- Reduced clone size from 528 MB to ~50 MB for typical 10-repo analysis (90% reduction)
+- Example: ant-design repo reduced from 184 MB (full) to 14 MB (depth=50) - 92% smaller
+- Analysis time for small experiments reduced from 6+ minutes to under 1 minute
+
 ## [1.2.4] - 2026-02-01
 
 ### Added
@@ -116,6 +132,7 @@
 - Green awareness analysis
 - Docker containerization
 
+[1.2.5]: https://github.com/adam-bouafia/greenmining/compare/v1.2.4...v1.2.5
 [1.2.4]: https://github.com/adam-bouafia/greenmining/compare/v1.2.3...v1.2.4
 [1.2.3]: https://github.com/adam-bouafia/greenmining/compare/v1.2.1...v1.2.3
 [1.2.1]: https://github.com/adam-bouafia/greenmining/compare/v1.2.0...v1.2.1

{greenmining-1.2.5/greenmining.egg-info → greenmining-1.2.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: greenmining
-Version: 1.2.5
+Version: 1.2.6
 Summary: An empirical Python library for Mining Software Repositories (MSR) in Green IT research
 Author-email: Adam Bouafia <a.bouafia@student.vu.nl>
 License: MIT

{greenmining-1.2.5 → greenmining-1.2.6}/greenmining/__init__.py

@@ -8,7 +8,7 @@ from greenmining.gsf_patterns import (
     is_green_aware,
 )
 
-__version__ = "1.2.5"
+__version__ = "1.2.6"
 
 
 def fetch_repositories(
@@ -75,6 +75,8 @@ def analyze_repositories(
     cleanup_after: bool = True,
     skip_merges: bool = True,
     commit_order: str = "newest_first",
+    shallow_clone: bool = True,
+    clone_depth: int = None,
 ):
     # Analyze multiple repositories from URLs.
     # Args:
@@ -93,6 +95,8 @@ def analyze_repositories(
     #   cleanup_after: Remove cloned repos after analysis (default True)
     #   skip_merges: Skip merge commits (default True)
     #   commit_order: "newest_first" (default) or "oldest_first"
+    #   shallow_clone: Use shallow cloning to reduce download size (default True)
+    #   clone_depth: Git clone depth (auto-calculated from max_commits if None)
     from greenmining.services.local_repo_analyzer import LocalRepoAnalyzer
 
     kwargs = {}
@@ -116,6 +120,8 @@ def analyze_repositories(
         cleanup_after=cleanup_after,
         skip_merges=skip_merges,
         commit_order=commit_order,
+        shallow_clone=shallow_clone,
+        clone_depth=clone_depth,
         **kwargs,
     )
 

{greenmining-1.2.5 → greenmining-1.2.6}/greenmining/services/local_repo_analyzer.py

@@ -205,6 +205,8 @@ class LocalRepoAnalyzer:
         since_date: datetime | None = None,
         to_date: datetime | None = None,
         commit_order: str = "newest_first",
+        shallow_clone: bool = True,
+        clone_depth: int | None = None,
     ):
         # Initialize the local repository analyzer.
         # Args:
@@ -222,6 +224,8 @@ class LocalRepoAnalyzer:
         #   include_source_code: Include source code before/after in results
         #   process_metrics: "standard" or "full" PyDriller process metrics
         #   commit_order: "newest_first" (default) or "oldest_first"
+        #   shallow_clone: Use shallow cloning to reduce download size (default True)
+        #   clone_depth: Git clone depth (auto-calculated from max_commits if None)
         self.clone_path = clone_path or Path.cwd() / "greenmining_repos"
         self.clone_path.mkdir(parents=True, exist_ok=True)
         self.max_commits = max_commits
@@ -232,6 +236,9 @@ class LocalRepoAnalyzer:
         self.compute_process_metrics = compute_process_metrics
         self.cleanup_after = cleanup_after
         self.commit_order = commit_order
+        self.shallow_clone = shallow_clone
+        # Auto-calculate clone depth: max_commits * 3 to account for merges/skipped commits
+        self.clone_depth = clone_depth if clone_depth else max(50, max_commits * 3)
         self.gsf_patterns = GSF_PATTERNS
 
         # Phase 1.3: Private repository support
@@ -472,12 +479,39 @@ class LocalRepoAnalyzer:
         clone_parent.mkdir(parents=True, exist_ok=True)
         local_path = clone_parent / repo_name
 
-        if local_path.exists():
-            shutil.rmtree(local_path)
+        # Perform shallow clone manually before PyDriller (much faster!)
+        if not local_path.exists():
+            import subprocess
 
-        repo_config["clone_repo_to"] = str(clone_parent)
+            clone_cmd = ["git", "clone"]
+            if self.shallow_clone:
+                clone_cmd.extend(["--depth", str(self.clone_depth)])
+            clone_cmd.extend([auth_url, str(local_path)])
 
-        colored_print(f"   Cloning to: {local_path}", "cyan")
+            colored_print(
+                f"   Cloning to: {local_path} (depth={self.clone_depth if self.shallow_clone else 'full'})",
+                "cyan",
+            )
+
+            try:
+                subprocess.run(
+                    clone_cmd,
+                    capture_output=True,
+                    text=True,
+                    check=True,
+                    timeout=180,
+                )
+            except subprocess.TimeoutExpired:
+                colored_print("   Clone timeout after 180s", "yellow")
+                raise
+            except subprocess.CalledProcessError as e:
+                colored_print(f"   Clone failed: {e.stderr}", "red")
+                raise
+        else:
+            colored_print(f"   Using existing clone: {local_path}", "cyan")
+
+        # PyDriller will analyze the already-cloned repo
+        repo_config["path_to_repo"] = str(local_path)
 
         # Phase 2.2: Start energy measurement if enabled (fresh meter per repo)
         energy_result = None

{greenmining-1.2.5 → greenmining-1.2.6}/greenmining/services/reports.py

@@ -76,12 +76,12 @@ class ReportGenerator:
 
         return f"""### Executive Summary
 
-This report presents findings from analyzing **{format_number(summary['total_commits'])} commits** across **{format_number(summary['total_repos'])} microservice-based repositories** to identify green software engineering practices.
+This report presents findings from analyzing **{format_number(summary["total_commits"])} commits** across **{format_number(summary["total_repos"])} microservice-based repositories** to identify green software engineering practices.
 
 **Key Findings:**
 
-- **{format_percentage(summary['green_aware_percentage'])}** of commits ({format_number(summary['green_aware_count'])}) explicitly mention energy efficiency, performance optimization, or sustainability concerns
-- **{format_number(summary['repos_with_green_commits'])}** out of {format_number(summary['total_repos'])} repositories contain at least one green-aware commit
+- **{format_percentage(summary["green_aware_percentage"])}** of commits ({format_number(summary["green_aware_count"])}) explicitly mention energy efficiency, performance optimization, or sustainability concerns
+- **{format_number(summary["repos_with_green_commits"])}** out of {format_number(summary["total_repos"])} repositories contain at least one green-aware commit
 - {pattern_text if pattern_text else "Various green software patterns were detected across the analyzed commits."}
 
 **Implications:**
@@ -106,15 +106,15 @@ Repositories were selected from GitHub based on the following criteria:
 
 - **Keywords:** {search_keywords}
 - **Programming Languages:** {languages}
-- **Minimum Stars:** {metadata.get('min_stars', 100)} (to ensure established projects)
+- **Minimum Stars:** {metadata.get("min_stars", 100)} (to ensure established projects)
 - **Sort Order:** Stars (descending)
-- **Total Repositories:** {metadata.get('total_repos', 0)}
+- **Total Repositories:** {metadata.get("total_repos", 0)}
 
 #### 1.2 Data Extraction Approach
 
 Commit data was extracted using PyDriller library:
 
-- **Commits Analyzed:** {analysis_metadata.get('total_commits_analyzed', 0)}
+- **Commits Analyzed:** {analysis_metadata.get("total_commits_analyzed", 0)}
 - **Time Window:** Last 2 years (730 days)
 - **Merge Commits:** Excluded
 - **Minimum Commit Message Length:** 10 characters
@@ -192,8 +192,8 @@ Commits were analyzed using a keyword and heuristic-based classification framewo
 
         return f"""#### 2.1 Green Awareness in Commits
 
-**Total commits analyzed:** {format_number(summary['total_commits'])}
-**Commits with explicit green mention:** {format_number(summary['green_aware_count'])} ({format_percentage(summary['green_aware_percentage'])})
+**Total commits analyzed:** {format_number(summary["total_commits"])}
+**Commits with explicit green mention:** {format_number(summary["green_aware_count"])} ({format_percentage(summary["green_aware_percentage"])})
 
 **Table: Top 10 Repositories with Highest Green Awareness**
 
@@ -224,10 +224,10 @@ Commits were analyzed using a keyword and heuristic-based classification framewo
         # Pattern descriptions
         pattern_details = []
         for i, pattern in enumerate(patterns[:10], 1):
-            pattern_details.append(f"""**{i}. {pattern['pattern_name']}**
-- Frequency: {format_number(pattern['count'])} commits ({format_percentage(pattern['percentage'])})
-- Confidence Distribution: HIGH={conf['HIGH']}, MEDIUM={conf['MEDIUM']}, LOW={conf['LOW']}
-- Example Commits: {', '.join([c[:8] for c in pattern['example_commits'][:3]])}""")
+            pattern_details.append(f"""**{i}. {pattern["pattern_name"]}**
+- Frequency: {format_number(pattern["count"])} commits ({format_percentage(pattern["percentage"])})
+- Confidence Distribution: HIGH={conf["HIGH"]}, MEDIUM={conf["MEDIUM"]}, LOW={conf["LOW"]}
+- Example Commits: {", ".join([c[:8] for c in pattern["example_commits"][:3]])}""")
 
         return f"""#### 2.2 Known Green Patterns & Tactics Applied
 
@@ -252,10 +252,10 @@ No novel microservice-specific green practices were automatically detected. Manu
 
         pattern_list = []
         for pattern in emergent:
-            pattern_list.append(f"""**Pattern:** {pattern['pattern_name']}
-- Occurrences: {pattern['count']}
-- Description: {pattern['description']}
-- Example Commits: {', '.join([c[:8] for c in pattern['example_commits'][:3]])}""")
+            pattern_list.append(f"""**Pattern:** {pattern["pattern_name"]}
+- Occurrences: {pattern["count"]}
+- Description: {pattern["description"]}
+- Example Commits: {", ".join([c[:8] for c in pattern["example_commits"][:3]])}""")
 
         return f"""#### 2.3 Emerging Practices Discovered
 
@@ -299,7 +299,7 @@ No novel microservice-specific green practices were automatically detected. Manu
         if "error" in stats:
             return f"""#### 2.5 Statistical Analysis
 
-**Note:** Statistical analysis encountered an error: {stats['error']}
+**Note:** Statistical analysis encountered an error: {stats["error"]}
 """
 
         sections = []
@@ -495,16 +495,16 @@ Based on the detected patterns, microservice developers primarily focus on:
 
 #### 5.1 Summary of Key Findings
 
-This study analyzed {format_number(summary['total_commits'])} commits from {format_number(summary['total_repos'])} microservice repositories and found:
+This study analyzed {format_number(summary["total_commits"])} commits from {format_number(summary["total_repos"])} microservice repositories and found:
 
-1. **{format_percentage(summary['green_aware_percentage'])}** of commits explicitly address energy/sustainability concerns
-2. **{format_number(summary['repos_with_green_commits'])}** repositories demonstrate some level of green awareness
+1. **{format_percentage(summary["green_aware_percentage"])}** of commits explicitly address energy/sustainability concerns
+2. **{format_number(summary["repos_with_green_commits"])}** repositories demonstrate some level of green awareness
 3. Common green patterns include: {patterns_text}
 
 #### 5.2 Answers to Research Questions
 
 **RQ1: What percentage of microservice commits explicitly mention energy efficiency?**
-Answer: {format_percentage(summary['green_aware_percentage'])} of analyzed commits contain explicit mentions.
+Answer: {format_percentage(summary["green_aware_percentage"])} of analyzed commits contain explicit mentions.
 
 **RQ2: Which green software tactics are developers applying in practice?**
 Answer: Developers primarily apply caching strategies, resource pooling, database optimization, and asynchronous processing patterns.

{greenmining-1.2.5 → greenmining-1.2.6/greenmining.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: greenmining
-Version: 1.2.5
+Version: 1.2.6
 Summary: An empirical Python library for Mining Software Repositories (MSR) in Green IT research
 Author-email: Adam Bouafia <a.bouafia@student.vu.nl>
 License: MIT

{greenmining-1.2.5 → greenmining-1.2.6}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "greenmining"
-version = "1.2.5"
+version = "1.2.6"
 description = "An empirical Python library for Mining Software Repositories (MSR) in Green IT research"
 readme = "README.md"
 requires-python = ">=3.9"