greenmining 1.0.2__py3-none-any.whl → 1.0.4__py3-none-any.whl

greenmining/cli.py

@@ -1,471 +0,0 @@
-"""Green Microservices Mining CLI"""
-
-import click
-
-from greenmining.config import Config
-from greenmining.controllers.repository_controller import RepositoryController
-from greenmining.presenters.console_presenter import ConsolePresenter
-from greenmining.utils import colored_print, load_json_file
-
-# Initialize configuration
-config = Config()
-
-# Initialize presenter
-presenter = ConsolePresenter()
-
-
-@click.group()
-@click.option("--config-file", default=".env", help="Path to configuration file")
-@click.option("--verbose", is_flag=True, help="Enable verbose output")
-def cli(config_file, verbose):
-    """Green Microservices Mining"""
-    if verbose:
-        config.VERBOSE = True
-
-
-@cli.command()
-@click.option("--max-repos", default=100, type=int, help="Maximum repositories to fetch")
-@click.option("--min-stars", default=100, type=int, help="Minimum stars required")
-@click.option(
-    "--languages", default="Python,Java,Go,JavaScript,TypeScript", help="Comma-separated languages"
-)
-@click.option(
-    "--keywords",
-    default="microservices",
-    type=str,
-    help="Search keywords (e.g., 'kubernetes', 'docker', 'cloud-native')",
-)
-@click.option("--created-after", type=str, help="Repository created after (YYYY-MM-DD)")
-@click.option("--created-before", type=str, help="Repository created before (YYYY-MM-DD)")
-@click.option("--pushed-after", type=str, help="Repository pushed after (YYYY-MM-DD)")
-@click.option("--pushed-before", type=str, help="Repository pushed before (YYYY-MM-DD)")
-def fetch(
-    max_repos,
-    min_stars,
-    languages,
-    keywords,
-    created_after,
-    created_before,
-    pushed_after,
-    pushed_before,
-):
-    """Fetch repositories from GitHub based on custom search keywords."""
-    presenter.show_banner()
-    colored_print(f"\n🎯 Target: {max_repos} repositories\n", "cyan")
-
-    controller = RepositoryController(config)
-    lang_list = [lang.strip() for lang in languages.split(",")]
-
-    try:
-        repositories = controller.fetch_repositories(
-            max_repos=max_repos,
-            min_stars=min_stars,
-            languages=lang_list,
-            keywords=keywords,
-            created_after=created_after,
-            created_before=created_before,
-            pushed_after=pushed_after,
-            pushed_before=pushed_before,
-        )
-
-        # Show results
-        repo_dicts = [r.to_dict() for r in repositories]
-        presenter.show_repositories(repo_dicts, limit=10)
-
-        stats = controller.get_repository_stats(repositories)
-        colored_print(f"\n📊 Total Stars: {stats.get('total_stars', 0):,}", "green")
-        colored_print(f"📈 Average Stars: {stats.get('avg_stars', 0):.0f}", "green")
-
-        presenter.show_success(f"Fetched {len(repositories)} repositories successfully!")
-
-    except Exception as e:
-        presenter.show_error(str(e))
-        raise click.Abort() from e
-
-
-@cli.command()
-@click.option("--max-commits", default=50, type=int, help="Max commits per repository")
-@click.option("--skip-merges", is_flag=True, default=True, help="Skip merge commits")
-@click.option("--days-back", default=730, type=int, help="Days to look back (default: 2 years)")
-@click.option("--timeout", default=60, type=int, help="Timeout per repo in seconds (default: 60)")
-def extract(max_commits, skip_merges, days_back, timeout):
-    """Extract commits from fetched repositories."""
-    presenter.show_banner()
-
-    from greenmining.services.commit_extractor import CommitExtractor
-
-    try:
-        # Load repositories
-        controller = RepositoryController(config)
-        repositories = controller.load_repositories()
-
-        colored_print(f"\n📝 Extracting commits from {len(repositories)} repositories...\n", "cyan")
-        colored_print(
-            f"   Settings: max={max_commits}/repo, skip_merges={skip_merges}, days_back={days_back}\n",
-            "cyan",
-        )
-
-        # Extract commits
-        extractor = CommitExtractor(
-            max_commits=max_commits, skip_merges=skip_merges, days_back=days_back, timeout=timeout
-        )
-        commits = extractor.extract_from_repositories(
-            repositories=[r.to_dict() for r in repositories]
-        )
-
-        # Save commits
-        from greenmining.utils import save_json_file
-
-        save_json_file(commits, config.COMMITS_FILE)
-        colored_print(f"   Saved to: {config.COMMITS_FILE}", "cyan")
-
-        # Show stats
-        stats = {
-            "total_commits": len(commits),
-            "total_repos": len(repositories),
-            "avg_per_repo": len(commits) / len(repositories) if repositories else 0,
-        }
-
-        presenter.show_commit_stats(stats)
-        presenter.show_success(f"Extracted {len(commits)} commits successfully!")
-
-    except FileNotFoundError as e:
-        presenter.show_error(str(e))
-        colored_print("💡 Run 'fetch' command first to get repositories", "yellow")
-        raise click.Abort() from e
-    except Exception as e:
-        presenter.show_error(str(e))
-        raise click.Abort() from e
-
-
-@cli.command()
-@click.option("--batch-size", default=10, type=int, help="Batch size for processing")
-@click.option("--enable-diff-analysis", is_flag=True, help="Enable code diff analysis (slower)")
-@click.option("--enable-nlp", is_flag=True, help="Enable NLP-enhanced pattern detection")
-@click.option("--enable-ml-features", is_flag=True, help="Enable ML feature extraction")
-def analyze(batch_size, enable_diff_analysis, enable_nlp, enable_ml_features):
-    """Analyze commits for green software patterns."""
-    presenter.show_banner()
-
-    from greenmining.services.data_analyzer import DataAnalyzer
-    from greenmining.utils import save_json_file
-
-    try:
-        # Load commits
-        if not config.COMMITS_FILE.exists():
-            raise FileNotFoundError("No commits file found. Run 'extract' first.")
-
-        commits = load_json_file(config.COMMITS_FILE)
-        colored_print(f"\n🔬 Analyzing {len(commits)} commits for green patterns...\n", "cyan")
-
-        # Show enabled methods
-        methods = ["Keyword"]
-        if enable_diff_analysis:
-            methods.append("Code Diff")
-        if enable_nlp:
-            methods.append("NLP")
-        if enable_ml_features:
-            methods.append("ML Features")
-
-        colored_print(f"   Methods: {' + '.join(methods)}\n", "cyan")
-        colored_print(f"   Batch size: {batch_size}\n", "cyan")
-
-        # Analyze
-        analyzer = DataAnalyzer(
-            batch_size=batch_size,
-            enable_diff_analysis=enable_diff_analysis,
-            enable_nlp=enable_nlp,
-            enable_ml_features=enable_ml_features,
-        )
-        results = analyzer.analyze_commits(commits)
-
-        # Save results
-        save_json_file(results, config.ANALYSIS_FILE)
-
-        # Show results
-        green_count = sum(1 for r in results if r.get("green_aware", False))
-        green_rate = (green_count / len(results)) if results else 0
-
-        results_dict = {
-            "summary": {
-                "total_commits": len(results),
-                "green_commits": green_count,
-                "green_commit_rate": green_rate,
-            },
-            "known_patterns": {},
-        }
-
-        presenter.show_analysis_results(results_dict)
-        presenter.show_success(f"Analysis complete! Results saved to {config.ANALYSIS_FILE}")
-
-    except Exception as e:
-        presenter.show_error(str(e))
-        raise click.Abort() from e
-
-
-@cli.command()
-@click.option("--enable-enhanced-stats", is_flag=True, help="Enable enhanced statistical analysis")
-@click.option("--enable-temporal", is_flag=True, help="Enable temporal trend analysis")
-@click.option(
-    "--temporal-granularity",
-    default="quarter",
-    type=click.Choice(["day", "week", "month", "quarter", "year"]),
-    help="Temporal analysis granularity",
-)
-def aggregate(enable_enhanced_stats, enable_temporal, temporal_granularity):
-    """Aggregate analysis results and generate statistics."""
-    presenter.show_banner()
-
-    from greenmining.services.data_aggregator import DataAggregator
-    from greenmining.utils import save_json_file
-
-    try:
-        # Load data
-        if not config.ANALYSIS_FILE.exists():
-            raise FileNotFoundError("No analysis file found. Run 'analyze' first.")
-
-        results = load_json_file(config.ANALYSIS_FILE)
-        repos = load_json_file(config.REPOS_FILE) if config.REPOS_FILE.exists() else []
-
-        colored_print(f"\n📊 Aggregating results from {len(results)} commits...\n", "cyan")
-
-        # Show enabled features
-        if enable_enhanced_stats:
-            colored_print("   Enhanced statistics: Enabled\n", "cyan")
-        if enable_temporal:
-            colored_print(
-                f"   Temporal analysis: Enabled (granularity: {temporal_granularity})\n", "cyan"
-            )
-
-        # Aggregate
-        aggregator = DataAggregator(
-            enable_enhanced_stats=enable_enhanced_stats,
-            enable_temporal=enable_temporal,
-            temporal_granularity=temporal_granularity,
-        )
-        aggregated = aggregator.aggregate(results, repos)
-
-        # Save
-        save_json_file(aggregated, config.AGGREGATED_FILE)
-
-        # Show results
-        presenter.show_analysis_results(aggregated)
-
-        if aggregated.get("known_patterns"):
-            # Convert list format to dict format expected by presenter
-            patterns_dict = {}
-            for pattern in aggregated["known_patterns"]:
-                patterns_dict[pattern["pattern_name"]] = {
-                    "count": pattern["count"],
-                    "percentage": pattern["percentage"],
-                    "confidence_distribution": pattern.get("confidence_breakdown", {}),
-                }
-            presenter.show_pattern_distribution(patterns_dict, limit=10)
-
-        presenter.show_success(f"Aggregation complete! Results saved to {config.AGGREGATED_FILE}")
-
-    except Exception as e:
-        presenter.show_error(str(e))
-        raise click.Abort() from e
-
-
-@cli.command()
-@click.option("--output", default="green_microservices_analysis.md", help="Output filename")
-def report(output):
-    """Generate comprehensive markdown report."""
-    presenter.show_banner()
-
-    from greenmining.services.reports import ReportGenerator
-
-    try:
-        # Load aggregated data
-        if not config.AGGREGATED_FILE.exists():
-            raise FileNotFoundError("No aggregated data found. Run 'aggregate' first.")
-
-        # Load analysis results
-        if not config.ANALYSIS_FILE.exists():
-            raise FileNotFoundError("No analysis results found. Run 'analyze' first.")
-
-        # Load repository data
-        if not config.REPOS_FILE.exists():
-            raise FileNotFoundError("No repository data found. Run 'fetch' first.")
-
-        aggregated = load_json_file(config.AGGREGATED_FILE)
-        analysis_results = load_json_file(config.ANALYSIS_FILE)
-        repos_data = load_json_file(config.REPOS_FILE)
-
-        # Wrap analysis results if it's a list
-        if isinstance(analysis_results, list):
-            analysis = {"results": analysis_results, "total": len(analysis_results)}
-        else:
-            analysis = analysis_results
-
-        # Wrap repos data if it's a list
-        if isinstance(repos_data, list):
-            repos = {"repositories": repos_data, "total": len(repos_data)}
-        else:
-            repos = repos_data
-
-        colored_print("\n📄 Generating comprehensive report...\n", "cyan")
-
-        # Generate report
-        generator = ReportGenerator()
-        report_content = generator.generate_report(aggregated, analysis, repos)
-
-        # Save report
-        from pathlib import Path
-
-        report_path = Path(output)
-        report_path.write_text(report_content)
-
-        presenter.show_success(f"Report generated: {report_path}")
-        colored_print("\n📖 The report includes:", "cyan")
-        colored_print("   • Executive Summary", "white")
-        colored_print("   • Methodology", "white")
-        colored_print("   • Results & Statistics", "white")
-        colored_print("   • Pattern Analysis", "white")
-        colored_print("   • Per-Repository Breakdown", "white")
-        colored_print("   • Discussion & Conclusions", "white")
-
-    except Exception as e:
-        presenter.show_error(str(e))
-        raise click.Abort() from e
-
-
-@cli.command()
-def status():
-    """Show current pipeline status."""
-    presenter.show_banner()
-
-    phases = {
-        "1. Fetch Repositories": {
-            "file": str(config.REPOS_FILE),
-            "completed": config.REPOS_FILE.exists(),
-            "size": (
-                f"{config.REPOS_FILE.stat().st_size / 1024:.1f} KB"
-                if config.REPOS_FILE.exists()
-                else "N/A"
-            ),
-        },
-        "2. Extract Commits": {
-            "file": str(config.COMMITS_FILE),
-            "completed": config.COMMITS_FILE.exists(),
-            "size": (
-                f"{config.COMMITS_FILE.stat().st_size / 1024:.1f} KB"
-                if config.COMMITS_FILE.exists()
-                else "N/A"
-            ),
-        },
-        "3. Analyze Commits": {
-            "file": str(config.ANALYSIS_FILE),
-            "completed": config.ANALYSIS_FILE.exists(),
-            "size": (
-                f"{config.ANALYSIS_FILE.stat().st_size / 1024:.1f} KB"
-                if config.ANALYSIS_FILE.exists()
-                else "N/A"
-            ),
-        },
-        "4. Aggregate Results": {
-            "file": str(config.AGGREGATED_FILE),
-            "completed": config.AGGREGATED_FILE.exists(),
-            "size": (
-                f"{config.AGGREGATED_FILE.stat().st_size / 1024:.1f} KB"
-                if config.AGGREGATED_FILE.exists()
-                else "N/A"
-            ),
-        },
-        "5. Generate Report": {
-            "file": str(config.REPORT_FILE),
-            "completed": config.REPORT_FILE.exists(),
-            "size": (
-                f"{config.REPORT_FILE.stat().st_size / 1024:.1f} KB"
-                if config.REPORT_FILE.exists()
-                else "N/A"
-            ),
-        },
-    }
-
-    presenter.show_pipeline_status(phases)
-
-    # Show next step
-    for phase_name, info in phases.items():
-        if not info["completed"]:
-            colored_print(f"\n💡 Next step: {phase_name}", "yellow")
-            break
-    else:
-        colored_print("\n✅ All phases complete!", "green")
-
-
-@cli.command()
-@click.option("--max-repos", default=100, type=int, help="Maximum repositories to analyze")
-@click.option("--skip-fetch", is_flag=True, help="Skip fetch phase if data exists")
-def pipeline(max_repos, skip_fetch):
-    """Run full pipeline: fetch → extract → analyze → aggregate → report."""
-    presenter.show_banner()
-
-    colored_print("\n🚀 Starting Full Pipeline...\n", "green")
-    colored_print(f"   Target: {max_repos} repositories", "cyan")
-    colored_print("   Phases: fetch → extract → analyze → aggregate → report\n", "cyan")
-
-    try:
-        # Phase 1: Fetch
-        if not skip_fetch or not config.REPOS_FILE.exists():
-            colored_print("\n[1/5] 🔍 Fetching repositories...", "cyan")
-            controller = RepositoryController(config)
-            controller.fetch_repositories(max_repos=max_repos)
-        else:
-            colored_print("\n[1/5] ⏭️  Skipping fetch (using existing data)", "yellow")
-
-        # Phase 2: Extract
-        colored_print("\n[2/5] 📝 Extracting commits...", "cyan")
-        from greenmining.services.commit_extractor import CommitExtractor
-        from greenmining.utils import save_json_file
-
-        controller = RepositoryController(config)
-        repos = controller.load_repositories()
-        extractor = CommitExtractor()
-        commits = extractor.extract_from_repositories([r.to_dict() for r in repos])
-        save_json_file(commits, config.COMMITS_FILE)
-        colored_print(f"   Saved {len(commits)} commits to: {config.COMMITS_FILE}", "green")
-
-        # Phase 3: Analyze
-        colored_print("\n[3/5] 🔬 Analyzing commits...", "cyan")
-        from greenmining.services.data_analyzer import DataAnalyzer
-
-        commits = load_json_file(config.COMMITS_FILE)
-        analyzer = DataAnalyzer()
-        results = analyzer.analyze_commits_batch(commits)
-        save_json_file(results, config.ANALYSIS_FILE)
-        colored_print(
-            f"   Analyzed {len(results)} commits, saved to: {config.ANALYSIS_FILE}", "green"
-        )
-
-        # Phase 4: Aggregate
-        colored_print("\n[4/5] 📊 Aggregating results...", "cyan")
-        from greenmining.services.data_aggregator import DataAggregator
-
-        aggregator = DataAggregator()
-        aggregated = aggregator.aggregate(results, [r.to_dict() for r in repos])
-        save_json_file(aggregated, config.AGGREGATED_FILE)
-
-        # Phase 5: Report
-        colored_print("\n[5/5] 📄 Generating report...", "cyan")
-        from greenmining.services.reports import ReportGenerator
-
-        generator = ReportGenerator()
-        generator.generate_report(aggregated)
-
-        colored_print("\n" + "=" * 60, "green")
-        colored_print("✅ Pipeline Complete!", "green")
-        colored_print("=" * 60, "green")
-
-        presenter.show_success(f"All results saved to {config.OUTPUT_DIR}")
-        colored_print(f"\n📖 View report: {config.REPORT_FILE}", "cyan")
-
-    except Exception as e:
-        presenter.show_error(str(e))
-        raise click.Abort() from e
-
-
-if __name__ == "__main__":
-    cli()

greenmining/main.py

@@ -1,37 +0,0 @@
-"""Main entry point for Green Microservices Mining CLI."""
-
-import sys
-
-from cli import cli
-
-from greenmining.utils import colored_print, print_banner
-
-
-def main():
-    """Main entry point with error handling."""
-    try:
-        print_banner("🌱 Green Microservices Mining Tool")
-        colored_print("Analyze GitHub repositories for sustainability practices\n", "cyan")
-
-        cli(obj={})
-
-    except KeyboardInterrupt:
-        colored_print("\n\n⚠️  Operation cancelled by user", "yellow")
-        sys.exit(130)
-
-    except Exception as e:
-        colored_print(f"\n❌ Unexpected error: {e}", "red")
-
-        if "--verbose" in sys.argv or "-v" in sys.argv:
-            import traceback
-
-            colored_print("\nFull traceback:", "red")
-            traceback.print_exc()
-        else:
-            colored_print("Run with --verbose for detailed error information", "yellow")
-
-        sys.exit(1)
-
-
-if __name__ == "__main__":
-    main()

greenmining-1.0.2.dist-info/RECORD

@@ -1,36 +0,0 @@
-greenmining/__init__.py,sha256=c_Vaq_WW6-SkI_es4cQKXpdEtXdfVEnGjIDxACF6bzk,1764
-greenmining/__main__.py,sha256=1RwcSXcwdza6xJX5fRT8-HhZjlnKbkmGY_uxTm-NYZ4,138
-greenmining/__version__.py,sha256=3OgUZ5K2OXa9_-2kjlgye1N6G_QeQDeex2uw33Ja6Cs,66
-greenmining/cli.py,sha256=40eKDEZHNeDVb91xKBG70VfPk45mwb4YjuVCC2efVPA,17458
-greenmining/config.py,sha256=1_puT52zNS589hTxEZ3UCqRC_Qw5Jw2UupUPNbNz_hs,5195
-greenmining/gsf_patterns.py,sha256=Prsk_stnQrfOsk0x0zn-zdevbueAnPfGDM4XNA9PbdA,54664
-greenmining/main.py,sha256=h8J9OcwyGpVJ-gjSFUS2SZExQQlHV0eDMMjAoI_sgAo,952
-greenmining/utils.py,sha256=-pL8yznf1jSazBMk1ugjPQbtFOQI1E9wRI1NJbHl2xs,7941
-greenmining/analyzers/__init__.py,sha256=6emAyka8ifjNjEpqhWOGkWkTJU1SgJy8Xuva-b9XSNY,518
-greenmining/analyzers/code_diff_analyzer.py,sha256=mL8sCpnVo_m8vsgabe2t3gF0b_gNp3MIM-D4v31-zNQ,7682
-greenmining/analyzers/ml_feature_extractor.py,sha256=rbCPA12hD1Xda7CGkLA7vGZgDjZK0r4ev5crDcbg3Jc,17727
-greenmining/analyzers/nlp_analyzer.py,sha256=fBwkHqV0e4rnI-dz2DH2zmrnLZYpcRTkMrAY-zmMBTo,12616
-greenmining/analyzers/qualitative_analyzer.py,sha256=6HU_Rn-mAOBXiwroj7UjV13nmagSboz5rB4eYuiYs6U,17256
-greenmining/analyzers/statistical_analyzer.py,sha256=g_suZ6AAJzTft2kZH5dwSUZ8S06JyuaBy4MPSZidavY,8755
-greenmining/analyzers/temporal_analyzer.py,sha256=-1fmZdkGsNqmukoy8xxEG1v4AdJ5P6Y1C1Q8e-aI1cs,15976
-greenmining/controllers/__init__.py,sha256=y-W1Xnnhm4JnrY2QEo5osK8jQs7hpxXovVbHlE334F0,279
-greenmining/controllers/repository_controller.py,sha256=_DtX0OAm5VUEOPY8SxrvVWNujjQmkoyt-2PpL-R2sQ0,6453
-greenmining/models/__init__.py,sha256=K8udzQW2V5LqPowIm5aCiK07LxJZxCt_oW3gz5Qi-mc,397
-greenmining/models/aggregated_stats.py,sha256=eYyEcKfL8oqqE_hN0tzM7eyXFzc54by20N3-72vcJ7Y,1032
-greenmining/models/analysis_result.py,sha256=-6hwmickqncRXDGWM3aXBEaOGlddM5G6hnmRTyHFcMs,1525
-greenmining/models/commit.py,sha256=OT95QqVzU-0xbXB5l7m7V6J4FXSPIO80M2zYJHJdyOU,2459
-greenmining/models/repository.py,sha256=k1X9UYZYLl0RznohOHx_Y5wur-ZBvLcNyc9vPVArb7E,2876
-greenmining/presenters/__init__.py,sha256=-ukAvhNuTvy1Xpknps0faDZ78HKdPHPySzFpQHABzKM,203
-greenmining/presenters/console_presenter.py,sha256=ykJ9Hgors2dRTqQNaqCTxH4fd49F0AslQTgUOr_csI0,5347
-greenmining/services/__init__.py,sha256=7CJDjHMTrY0bBoqzx22AUzIwEvby0FbAUUKYbjSlNPQ,460
-greenmining/services/commit_extractor.py,sha256=FSgoHpMvoqjZ6b1UQYtwfUaLVX_GDfiR0BVd51y-gYk,13126
-greenmining/services/data_aggregator.py,sha256=OqJvQZp9xaZaSmbwWoiHAHECAghd8agbhVmStDvebOU,24054
-greenmining/services/data_analyzer.py,sha256=HZDQLFZDCwCUGIzRjypyXC09Fl_-zaxhly74n3siwQc,16325
-greenmining/services/github_fetcher.py,sha256=J47-plM_NKXwHDSWNBuSUZMnZnGP6wXiJyrVfeWT9ug,11360
-greenmining/services/reports.py,sha256=NCNI9SCTnSLeAO8WmkNIdkB0hr-XyVpuzV0sovOoUOM,27107
-greenmining-1.0.2.dist-info/licenses/LICENSE,sha256=M7ma3JHGeiIZIs3ea0HTcFl_wLFPX2NZElUliYs4bCA,1083
-greenmining-1.0.2.dist-info/METADATA,sha256=vTygz3S30HRdkpHdMIiD-jau6Lx60VcPsf3OSSBeL0w,25694
-greenmining-1.0.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-greenmining-1.0.2.dist-info/entry_points.txt,sha256=oHvTWMzNFGf2W3CFEKVVPsG4exeMv0MaQu9YsUoQ9lw,53
-greenmining-1.0.2.dist-info/top_level.txt,sha256=nreXgXxZIWI-42yQknQ0HXtUrFnzZ8N1ra4Mdy2KcsI,12
-greenmining-1.0.2.dist-info/RECORD,,

greenmining-1.0.2.dist-info/entry_points.txt

@@ -1,2 +0,0 @@
-[console_scripts]
-greenmining = greenmining.cli:main