greenmining 0.1.7__py3-none-any.whl → 0.1.9__py3-none-any.whl

greenmining/__init__.py

@@ -8,7 +8,7 @@ from greenmining.gsf_patterns import (
     is_green_aware,
 )
 
-__version__ = "0.1.0"
+__version__ = "0.1.9"
 
 __all__ = [
     "Config",

greenmining/services/commit_extractor.py

@@ -6,7 +6,7 @@ from pathlib import Path
 from typing import Any, Optional
 
 import click
-from pydriller import Repository
+from github import Github
 from tqdm import tqdm
 
 from greenmining.config import get_config
@@ -21,20 +21,28 @@ from greenmining.utils import (
 
 
 class CommitExtractor:
-    """Extracts commit data from repositories."""
-
-    def __init__(self, max_commits: int = 50, skip_merges: bool = True, days_back: int = 730):
+    """Extracts commit data from repositories using GitHub API."""
+
+    def __init__(
+        self,
+        max_commits: int = 50,
+        skip_merges: bool = True,
+        days_back: int = 730,
+        github_token: str | None = None,
+    ):
         """Initialize commit extractor.
 
         Args:
             max_commits: Maximum commits per repository
             skip_merges: Skip merge commits
             days_back: Only analyze commits from last N days
+            github_token: GitHub API token (optional)
         """
         self.max_commits = max_commits
         self.skip_merges = skip_merges
         self.days_back = days_back
         self.cutoff_date = datetime.now() - timedelta(days=days_back)
+        self.github = Github(github_token) if github_token else None
 
     def extract_from_repositories(self, repositories: list[dict[str, Any]]) -> list[dict[str, Any]]:
         """Extract commits from list of repositories.
@@ -77,7 +85,7 @@ class CommitExtractor:
 
     @retry_on_exception(max_retries=2, delay=5.0, exceptions=(Exception,))
     def _extract_repo_commits(self, repo: dict[str, Any]) -> list[dict[str, Any]]:
-        """Extract commits from a single repository.
+        """Extract commits from a single repository using GitHub API.
 
         Args:
             repo: Repository metadata dictionary
@@ -86,27 +94,35 @@ class CommitExtractor:
             List of commit dictionaries
         """
         commits = []
-        repo_url = repo["clone_url"]
         repo_name = repo["full_name"]
 
         try:
-            # Use PyDriller to traverse commits
-            commit_count = 0
+            # Get repository from GitHub API
+            if not self.github:
+                config = get_config()
+                self.github = Github(config.GITHUB_TOKEN)
 
-            for commit in Repository(
-                repo_url, only_no_merge=self.skip_merges, since=self.cutoff_date
-            ).traverse_commits():
+            gh_repo = self.github.get_repo(repo_name)
+
+            # Get recent commits (GitHub API returns in reverse chronological order)
+            commit_count = 0
 
+            for commit in gh_repo.get_commits():
                 # Skip if reached max commits
                 if commit_count >= self.max_commits:
                     break
 
+                # Skip merge commits if requested
+                if self.skip_merges and len(commit.parents) > 1:
+                    continue
+
                 # Skip trivial commits
-                if not commit.msg or len(commit.msg.strip()) < 10:
+                commit_msg = commit.commit.message
+                if not commit_msg or len(commit_msg.strip()) < 10:
                     continue
 
                 # Extract commit data
-                commit_data = self._extract_commit_metadata(commit, repo_name)
+                commit_data = self._extract_commit_metadata_from_github(commit, repo_name)
                 commits.append(commit_data)
                 commit_count += 1
 
@@ -158,6 +174,46 @@ class CommitExtractor:
             "in_main_branch": commit.in_main_branch if hasattr(commit, "in_main_branch") else True,
         }
 
+    def _extract_commit_metadata_from_github(self, commit, repo_name: str) -> dict[str, Any]:
+        """Extract metadata from GitHub API commit object.
+
+        Args:
+            commit: GitHub API commit object
+            repo_name: Repository name
+
+        Returns:
+            Dictionary with commit metadata
+        """
+        # Get modified files and stats
+        files_changed = []
+        lines_added = 0
+        lines_deleted = 0
+
+        try:
+            for file in commit.files:
+                files_changed.append(file.filename)
+                lines_added += file.additions
+                lines_deleted += file.deletions
+        except Exception:
+            pass
+
+        return {
+            "commit_id": commit.sha,
+            "repo_name": repo_name,
+            "date": commit.commit.committer.date.isoformat(),
+            "author": commit.commit.author.name,
+            "author_email": commit.commit.author.email,
+            "message": commit.commit.message.strip(),
+            "files_changed": files_changed[:20],  # Limit to 20 files
+            "lines_added": lines_added,
+            "lines_deleted": lines_deleted,
+            "insertions": lines_added,
+            "deletions": lines_deleted,
+            "is_merge": len(commit.parents) > 1,
+            "branches": [],
+            "in_main_branch": True,
+        }
+
     def save_results(self, commits: list[dict[str, Any]], output_file: Path, repos_count: int):
         """Save extracted commits to JSON file.
 

greenmining/services/data_aggregator.py

@@ -72,7 +72,7 @@ class DataAggregator:
         green_aware_count = sum(1 for r in results if r.get("green_aware", False))
 
         # Count repos with at least one green commit
-        repos_with_green = len({r["repo_name"] for r in results if r.get("green_aware", False)})
+        repos_with_green = len({r["repository"] for r in results if r.get("green_aware", False)})
 
         return {
             "total_commits": total_commits,
@@ -91,17 +91,24 @@ class DataAggregator:
         )
 
         for result in results:
-            pattern = result.get("known_pattern")
-            confidence = result.get("pattern_confidence", "NONE")
-
-            if pattern and pattern != "NONE DETECTED":
+            # Handle both gsf_patterns_matched (list) and known_pattern (string)
+            patterns = result.get("gsf_patterns_matched", [])
+            if not patterns:  # Fallback to old format
+                pattern = result.get("known_pattern")
+                if pattern and pattern != "NONE DETECTED":
+                    patterns = [pattern]
+            
+            confidence = result.get("confidence", result.get("pattern_confidence", "low")).upper()
+
+            for pattern in patterns:
                 pattern_data[pattern]["count"] += 1
                 if confidence in ["HIGH", "MEDIUM", "LOW"]:
                     pattern_data[pattern][confidence] += 1
 
                 # Store example commits (max 3)
                 if len(pattern_data[pattern]["example_commits"]) < 3:
-                    pattern_data[pattern]["example_commits"].append(result["commit_id"])
+                    commit_id = result.get("commit_hash", result.get("commit_id", "unknown"))
+                    pattern_data[pattern]["example_commits"].append(commit_id)
 
         # Convert to list format
         patterns_list = []
@@ -153,15 +160,21 @@ class DataAggregator:
 
         # Group commits by repository
         for result in results:
-            repo_commits[result["repo_name"]].append(result)
+            repo_commits[result["repository"]].append(result)
 
         # Calculate stats for each repo
         repo_stats = []
         for repo_name, commits in repo_commits.items():
             green_commits = [c for c in commits if c.get("green_aware", False)]
-            patterns = [
-                c.get("known_pattern") for c in commits if c.get("known_pattern") != "NONE DETECTED"
-            ]
+            # Get all patterns from commits (gsf_patterns_matched is a list)
+            patterns = []
+            for c in commits:
+                patterns_list = c.get("gsf_patterns_matched", [])
+                if not patterns_list:  # Fallback
+                    pattern = c.get("known_pattern")
+                    if pattern and pattern != "NONE DETECTED":
+                        patterns_list = [pattern]
+                patterns.extend(patterns_list)
             unique_patterns = list(set(patterns))
 
             repo_stats.append(
@@ -191,7 +204,7 @@ class DataAggregator:
         # Group commits by language
         language_commits = defaultdict(list)
         for result in results:
-            language = repo_language_map.get(result["repo_name"], "Unknown")
+            language = repo_language_map.get(result["repository"], "Unknown")
             language_commits[language].append(result)
 
         # Calculate stats for each language
@@ -239,18 +252,14 @@ class DataAggregator:
         for result in analysis_results:
             csv_data.append(
                 {
-                    "commit_id": result["commit_id"],
-                    "repo_name": result["repo_name"],
+                    "commit_hash": result.get("commit_hash", result.get("commit_id", "")),
+                    "repo_name": result.get("repository", ""),
                     "date": result.get("date", ""),
-                    "commit_message": result.get("commit_message", "")[:200],  # Truncate
+                    "message": result.get("message", "")[:200],  # Truncate
                     "green_aware": result.get("green_aware", False),
-                    "green_evidence": (
-                        result.get("green_evidence", "")[:200]
-                        if result.get("green_evidence")
-                        else ""
-                    ),
-                    "known_pattern": result.get("known_pattern", ""),
-                    "pattern_confidence": result.get("pattern_confidence", ""),
+                    "gsf_patterns": ", ".join(result.get("gsf_patterns_matched", [])),
+                    "pattern_count": result.get("pattern_count", 0),
+                    "confidence": result.get("confidence", ""),
                     "lines_added": result.get("lines_added", 0),
                     "lines_deleted": result.get("lines_deleted", 0),
                 }

greenmining/services/data_analyzer.py

@@ -114,8 +114,8 @@ class DataAnalyzer:
         return {
             "commit_hash": commit.get("hash", commit.get("commit_id", "unknown")),
             "repository": commit.get("repository", commit.get("repo_name", "unknown")),
-            "author": commit.get("author_name", "unknown"),
-            "date": commit.get("author_date", commit.get("date", "unknown")),
+            "author": commit.get("author", commit.get("author_name", "unknown")),
+            "date": commit.get("date", commit.get("author_date", "unknown")),
             "message": message,
             # Research Question 1: Green awareness
             "green_aware": green_aware,
@@ -125,10 +125,9 @@ class DataAnalyzer:
             "pattern_details": pattern_details,
             "confidence": confidence,
             # Additional metadata
-            "files_modified": commit.get("modified_files", commit.get("files_changed", [])),
-            "insertions": commit.get("insertions", commit.get("lines_added", 0)),
-            "deletions": commit.get("deletions", commit.get("lines_deleted", 0)),
-            "lines_deleted": commit.get("lines_deleted", 0),
+            "files_modified": commit.get("files_changed", commit.get("modified_files", [])),
+            "insertions": commit.get("lines_added", commit.get("insertions", 0)),
+            "deletions": commit.get("lines_deleted", commit.get("deletions", 0)),
         }
 
     def _check_green_awareness(self, message: str, files: list[str]) -> tuple[bool, Optional[str]]:
@@ -205,9 +204,15 @@ class DataAnalyzer:
         """
         # Calculate summary statistics
         green_aware_count = sum(1 for r in results if r["green_aware"])
-        pattern_counts = Counter(
-            r["known_pattern"] for r in results if r["known_pattern"] != "NONE DETECTED"
-        )
+        
+        # Count all matched patterns (results have gsf_patterns_matched which is a list)
+        all_patterns = []
+        for r in results:
+            patterns = r.get("gsf_patterns_matched", [])
+            if patterns:  # If there are matched patterns
+                all_patterns.extend(patterns)
+        
+        pattern_counts = Counter(all_patterns)
 
         data = {
             "metadata": {

{greenmining-0.1.7.dist-info → greenmining-0.1.9.dist-info}/METADATA

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: greenmining
-Version: 0.1.7
-Summary: Green Software Foundation (GSF) patterns mining tool for microservices repositories
+Version: 0.1.9
+Summary: Analyze GitHub repositories to identify green software engineering patterns and energy-efficient practices
 Author-email: Your Name <your.email@example.com>
 Maintainer-email: Your Name <your.email@example.com>
 License: MIT
@@ -63,11 +63,11 @@ Green mining for microservices repositories.
 
 ## Overview
 
-`greenmining` is a Python library and CLI tool for analyzing GitHub repositories to identify green software engineering practices. It detects 76 official Green Software Foundation patterns across cloud, web, AI, database, networking, and general categories.
+`greenmining` is a Python library and CLI tool for analyzing GitHub repositories to identify green software engineering practices and energy-efficient patterns. It detects 76 sustainable software patterns across cloud, web, AI, database, networking, and general categories.
 
 ## Features
 
-- 🔍 **76 GSF Patterns**: Detect official Green Software Foundation patterns
+- 🔍 **76 Sustainability Patterns**: Detect energy-efficient and environmentally conscious coding practices
 - 📊 **Repository Mining**: Analyze 100+ microservices repositories from GitHub
 - 📈 **Green Awareness Detection**: Identify sustainability-focused commits
 - 📄 **Comprehensive Reports**: Generate analysis reports in multiple formats
@@ -128,7 +128,7 @@ greenmining report
 from greenmining import GSF_PATTERNS, is_green_aware, get_pattern_by_keywords
 
 # Check available patterns
-print(f"Total GSF patterns: {len(GSF_PATTERNS)}")  # 76
+print(f"Total patterns: {len(GSF_PATTERNS)}")  # 76
 
 # Detect green awareness in commit messages
 commit_msg = "Optimize Redis caching to reduce energy consumption"
@@ -168,7 +168,7 @@ for commit in commits:
         print(f"  Patterns: {result['known_pattern']}")
 ```
 
-#### Access GSF Patterns Data
+#### Access Sustainability Patterns Data
 
 ```python
 from greenmining import GSF_PATTERNS

{greenmining-0.1.7.dist-info → greenmining-0.1.9.dist-info}/RECORD

@@ -1,4 +1,4 @@
-greenmining/__init__.py,sha256=ITaqGeXxagpd_NwAF68-WFLmWVP4iNeP6t4hici3ktA,395
+greenmining/__init__.py,sha256=-pLhkoePJtUXVyzBfTmT1iW56AvFgmNwf54hQckdYI8,395
 greenmining/__main__.py,sha256=1RwcSXcwdza6xJX5fRT8-HhZjlnKbkmGY_uxTm-NYZ4,138
 greenmining/__version__.py,sha256=Hry6u6QztktMYf7nqf0jPXFaA0b7lmr6pjdAaVRXDaE,66
 greenmining/cli.py,sha256=11DEE9bwKDIzj8CbR4-B8re_1cmywPo1CyLGWVGzF9U,13254
@@ -16,14 +16,14 @@ greenmining/models/repository.py,sha256=lpe9Pte6KPCcRvx0aOH16v2PiH3NwjPeQRJYxriK
 greenmining/presenters/__init__.py,sha256=-ukAvhNuTvy1Xpknps0faDZ78HKdPHPySzFpQHABzKM,203
 greenmining/presenters/console_presenter.py,sha256=jK_8agdEz-_2mqoyMNht-mNA9hXWe9EA8VlAUT_XFxA,5299
 greenmining/services/__init__.py,sha256=7CJDjHMTrY0bBoqzx22AUzIwEvby0FbAUUKYbjSlNPQ,460
-greenmining/services/commit_extractor.py,sha256=IxON_s6p9Rp4JJN8Q8T0bMLxBtatN4W7bCtk72snBSI,9900
-greenmining/services/data_aggregator.py,sha256=8yb70_lwT85Cn8jVDLUrEZXcGr44UKy8UEFTHbAebZg,16250
-greenmining/services/data_analyzer.py,sha256=ejvfKoG19D1U-b_RBne3e66h2yF4k05gyv3BLnZB9_k,11856
+greenmining/services/commit_extractor.py,sha256=XB7Y1HKeQ4OpgEz0yAjKDPdiQcq07QCQ5Xrx9AxGfrM,11814
+greenmining/services/data_aggregator.py,sha256=eXAHrzpafLJ14HRSFy70TCuamQpi43C6KcP2cG5IBGU,16877
+greenmining/services/data_analyzer.py,sha256=RHHxw2y-thjCtVEL_GmvPJPWdWNa-C6jMzjy5QZk4eI,12051
 greenmining/services/github_fetcher.py,sha256=9aHSbZoA8BWL1Cp0cCv2NltXf0Jr7W_mO5d_-7TuOvY,9294
 greenmining/services/reports.py,sha256=cE7XvB2ihD5KwrO4W1Uj_I1h5pELBPF85MjgGFzkgOQ,21829
-greenmining-0.1.7.dist-info/licenses/LICENSE,sha256=M7ma3JHGeiIZIs3ea0HTcFl_wLFPX2NZElUliYs4bCA,1083
-greenmining-0.1.7.dist-info/METADATA,sha256=OeDR3EVi-N2aIzjXSdpPeD6bsWJZxZGHZnsTGpjw4F4,9892
-greenmining-0.1.7.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-greenmining-0.1.7.dist-info/entry_points.txt,sha256=oHvTWMzNFGf2W3CFEKVVPsG4exeMv0MaQu9YsUoQ9lw,53
-greenmining-0.1.7.dist-info/top_level.txt,sha256=nreXgXxZIWI-42yQknQ0HXtUrFnzZ8N1ra4Mdy2KcsI,12
-greenmining-0.1.7.dist-info/RECORD,,
+greenmining-0.1.9.dist-info/licenses/LICENSE,sha256=M7ma3JHGeiIZIs3ea0HTcFl_wLFPX2NZElUliYs4bCA,1083
+greenmining-0.1.9.dist-info/METADATA,sha256=momgAH0mimUN2PjbgixNXXlraeP8unuIx2sgbyQT2ks,9969
+greenmining-0.1.9.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+greenmining-0.1.9.dist-info/entry_points.txt,sha256=oHvTWMzNFGf2W3CFEKVVPsG4exeMv0MaQu9YsUoQ9lw,53
+greenmining-0.1.9.dist-info/top_level.txt,sha256=nreXgXxZIWI-42yQknQ0HXtUrFnzZ8N1ra4Mdy2KcsI,12
+greenmining-0.1.9.dist-info/RECORD,,