greenmining 1.0.4__py3-none-any.whl → 1.0.5__py3-none-any.whl

greenmining/__init__.py

@@ -9,7 +9,7 @@ from greenmining.gsf_patterns import (
     is_green_aware,
 )
 
-__version__ = "1.0.4"
+__version__ = "1.0.5"
 
 
 def fetch_repositories(

greenmining/__version__.py

@@ -1,3 +1,3 @@
 # Version information for greenmining.
 
-__version__ = "1.0.4"
+__version__ = "1.0.5"

greenmining/services/github_fetcher.py

@@ -1,21 +1,19 @@
-"""
-================================================================================
-DEADCODE - OLD REST API IMPLEMENTATION
-================================================================================
-
-This file contains the OLD GitHub REST API implementation.
-It has been REPLACED by GitHubGraphQLFetcher for better performance.
-
-Performance comparison:
-  REST API:    10+ requests for 100 repos, ~2 minutes
-  GraphQL API: 1-2 requests for 100 repos, ~15 seconds (10x faster!)
-
-USE INSTEAD: greenmining.services.github_graphql_fetcher.GitHubGraphQLFetcher
-
-This file is kept for reference only. Do not use in production.
-
-================================================================================
-"""
+# ================================================================================
+# DEADCODE - OLD REST API IMPLEMENTATION
+# ================================================================================
+#
+# This file contains the OLD GitHub REST API implementation.
+# It has been REPLACED by GitHubGraphQLFetcher for better performance.
+#
+# Performance comparison:
+#   REST API:    10+ requests for 100 repos, ~2 minutes
+#   GraphQL API: 1-2 requests for 100 repos, ~15 seconds (10x faster!)
+#
+# USE INSTEAD: greenmining.services.github_graphql_fetcher.GitHubGraphQLFetcher
+#
+# This file is kept for reference only. Do not use in production.
+#
+# ================================================================================
 
 # GitHub repository fetcher for green microservices mining.
 

greenmining/services/github_graphql_fetcher.py

@@ -1,9 +1,7 @@
-"""
-GitHub GraphQL API fetcher for faster and more efficient repository fetching.
-
-GraphQL allows fetching exactly the data you need in a single request,
-reducing API calls and improving rate limit efficiency.
-"""
+# GitHub GraphQL API fetcher for faster and more efficient repository fetching.
+#
+# GraphQL allows fetching exactly the data you need in a single request,
+# reducing API calls and improving rate limit efficiency.
 
 import json
 import time
@@ -15,25 +13,21 @@ from greenmining.models.repository import Repository
 
 
 class GitHubGraphQLFetcher:
-    """
-    Fetch GitHub repositories using GraphQL API v4.
-
-    Benefits over REST API:
-    - Fetch repos + commits in 1 request instead of 100+ REST calls
-    - Get exactly the fields you need (no over-fetching)
-    - Better rate limit efficiency (5000 points/hour vs 5000 requests/hour)
-    - More powerful search capabilities
-    """
+    # Fetch GitHub repositories using GraphQL API v4.
+    #
+    # Benefits over REST API:
+    # - Fetch repos + commits in 1 request instead of 100+ REST calls
+    # - Get exactly the fields you need (no over-fetching)
+    # - Better rate limit efficiency (5000 points/hour vs 5000 requests/hour)
+    # - More powerful search capabilities
 
     GRAPHQL_ENDPOINT = "https://api.github.com/graphql"
 
     def __init__(self, token: str):
-        """
-        Initialize GraphQL fetcher.
-
-        Args:
-            token: GitHub personal access token
-        """
+        # Initialize GraphQL fetcher.
+        #
+        # Args:
+        #     token: GitHub personal access token
         self.token = token
         self.headers = {
             "Authorization": f"Bearer {token}",
@@ -51,22 +45,20 @@ class GitHubGraphQLFetcher:
         pushed_after: Optional[str] = None,
         pushed_before: Optional[str] = None,
     ) -> List[Repository]:
-        """
-        Search GitHub repositories using GraphQL.
-
-        Args:
-            keywords: Search keywords
-            max_repos: Maximum number of repositories to fetch
-            min_stars: Minimum star count
-            languages: Programming languages to filter
-            created_after: Created after date (YYYY-MM-DD)
-            created_before: Created before date (YYYY-MM-DD)
-            pushed_after: Pushed after date (YYYY-MM-DD)
-            pushed_before: Pushed before date (YYYY-MM-DD)
-
-        Returns:
-            List of Repository objects
-        """
+        # Search GitHub repositories using GraphQL.
+        #
+        # Args:
+        #     keywords: Search keywords
+        #     max_repos: Maximum number of repositories to fetch
+        #     min_stars: Minimum star count
+        #     languages: Programming languages to filter
+        #     created_after: Created after date (YYYY-MM-DD)
+        #     created_before: Created before date (YYYY-MM-DD)
+        #     pushed_after: Pushed after date (YYYY-MM-DD)
+        #     pushed_before: Pushed before date (YYYY-MM-DD)
+        #
+        # Returns:
+        #     List of Repository objects
         # Build search query
         search_query = self._build_search_query(
             keywords,
@@ -195,7 +187,7 @@ class GitHubGraphQLFetcher:
         pushed_after: Optional[str],
         pushed_before: Optional[str],
     ) -> str:
-        """Build GitHub search query string."""
+        # Build GitHub search query string.
         query_parts = [keywords]
 
         # Star count
@@ -219,7 +211,7 @@ class GitHubGraphQLFetcher:
         return " ".join(query_parts)
 
     def _execute_query(self, query: str, variables: Dict[str, Any]) -> Dict[str, Any]:
-        """Execute GraphQL query."""
+        # Execute GraphQL query.
         payload = {"query": query, "variables": variables}
 
         response = requests.post(
@@ -230,7 +222,7 @@ class GitHubGraphQLFetcher:
         return response.json()
 
     def _parse_repository(self, node: Dict[str, Any]) -> Repository:
-        """Parse GraphQL repository node to Repository object."""
+        # Parse GraphQL repository node to Repository object.
         # Extract languages
         languages = []
         if node.get("languages") and node["languages"].get("nodes"):
@@ -265,20 +257,18 @@ class GitHubGraphQLFetcher:
     def get_repository_commits(
         self, owner: str, name: str, max_commits: int = 100
     ) -> List[Dict[str, Any]]:
-        """
-        Fetch commits for a specific repository using GraphQL.
-
-        This is much faster than REST API as it gets all commits in 1-2 requests
-        instead of paginating through 100 individual REST calls.
-
-        Args:
-            owner: Repository owner
-            name: Repository name
-            max_commits: Maximum commits to fetch
-
-        Returns:
-            List of commit dictionaries
-        """
+        # Fetch commits for a specific repository using GraphQL.
+        #
+        # This is much faster than REST API as it gets all commits in 1-2 requests
+        # instead of paginating through 100 individual REST calls.
+        #
+        # Args:
+        #     owner: Repository owner
+        #     name: Repository name
+        #     max_commits: Maximum commits to fetch
+        #
+        # Returns:
+        #     List of commit dictionaries
         query = """
         query($owner: String!, $name: String!, $first: Int!) {
           repository(owner: $owner, name: $name) {
@@ -359,7 +349,7 @@ class GitHubGraphQLFetcher:
         return commits
 
     def save_results(self, repositories: List[Repository], output_file: str):
-        """Save repositories to JSON file."""
+        # Save repositories to JSON file.
         data = {
             "total_repositories": len(repositories),
             "repositories": [repo.to_dict() for repo in repositories],

{greenmining-1.0.4.dist-info → greenmining-1.0.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: greenmining
-Version: 1.0.4
+Version: 1.0.5
 Summary: Analyze GitHub repositories to identify green software engineering patterns and energy-efficient practices
 Author-email: Adam Bouafia <a.bouafia@student.vu.nl>
 License: MIT
@@ -43,7 +43,7 @@ Requires-Dist: pytest-mock>=3.12.0; extra == "dev"
 Requires-Dist: black>=23.12.0; extra == "dev"
 Requires-Dist: ruff>=0.1.9; extra == "dev"
 Requires-Dist: mypy>=1.8.0; extra == "dev"
-Requires-Dist: build>=1.0.4; extra == "dev"
+Requires-Dist: build>=1.0.5; extra == "dev"
 Requires-Dist: twine>=4.0.2; extra == "dev"
 Provides-Extra: docs
 Requires-Dist: sphinx>=7.2.0; extra == "docs"
@@ -61,7 +61,7 @@ Green mining for microservices repositories.
 
 ## Overview
 
-`greenmining` is a Python library and CLI tool for analyzing GitHub repositories to identify green software engineering practices and energy-efficient patterns. It detects sustainable software patterns across cloud, web, AI, database, networking, and general categories.
+`greenmining` is a Python library for analyzing GitHub repositories to identify green software engineering practices and energy-efficient patterns. It detects sustainable software patterns across cloud, web, AI, database, networking, and general categories.
 
 ## Installation
 
@@ -105,7 +105,7 @@ if is_green_aware(commit_msg):
     # Output: ['Cache Static Data', 'Use Efficient Cache Strategies']
 ```
 
-#### Fetch Repositories with Custom Keywords (NEW)
+#### Fetch Repositories with Custom Keywords
 
 ```python
 from greenmining import fetch_repositories
@@ -144,8 +144,6 @@ for repo in repos[:5]:
 ```python
 from greenmining.services.commit_extractor import CommitExtractor
 from greenmining.services.data_analyzer import DataAnalyzer
-from greenmining.analyzers.nlp_analyzer import NLPAnalyzer
-from greenmining.analyzers.ml_feature_extractor import MLFeatureExtractor
 from greenmining import fetch_repositories
 
 # Fetch repositories with custom keywords
@@ -195,18 +193,6 @@ for commit in commits:
         results.append(result)
         print(f"Green commit found: {commit.message[:50]}...")
         print(f"  Patterns: {result['known_pattern']}")
-        
-        # Access NLP analysis results (NEW)
-        if 'nlp_analysis' in result:
-            nlp = result['nlp_analysis']
-            print(f"  NLP: {nlp['morphological_count']} morphological matches, "
-                  f"{nlp['semantic_count']} semantic matches")
-        
-        # Access ML features (NEW)
-        if 'ml_features' in result:
-            ml = result['ml_features']['text']
-            print(f"  ML Features: {ml['word_count']} words, "
-                  f"keyword density: {ml['keyword_density']:.2f}")
 ```
 
 #### Access Sustainability Patterns Data
@@ -242,7 +228,7 @@ print(f"Available categories: {sorted(categories)}")
 #          'monitoring', 'network', 'networking', 'resource', 'web']
 ```
 
-#### Advanced Analysis: Temporal Trends (NEW)
+#### Advanced Analysis: Temporal Trends
 
 ```python
 from greenmining.services.data_aggregator import DataAggregator
@@ -374,7 +360,7 @@ repositories = fetch_repositories(
     min_stars=10,
     keywords="software engineering",
 )
-print(f"✓ Fetched {len(repositories)} repositories")
+print(f"Fetched {len(repositories)} repositories")
 
 # STAGE 2: Extract Commits
 print("\nExtracting commits...")
@@ -386,7 +372,7 @@ extractor = CommitExtractor(
     timeout=120,
 )
 all_commits = extractor.extract_from_repositories(repositories)
-print(f"✓ Extracted {len(all_commits)} commits")
+print(f"Extracted {len(all_commits)} commits")
 
 # Save commits
 extractor.save_results(
@@ -405,8 +391,8 @@ analyzed_commits = analyzer.analyze_commits(all_commits)
 # Count green-aware commits
 green_count = sum(1 for c in analyzed_commits if c.get("green_aware", False))
 green_percentage = (green_count / len(analyzed_commits) * 100) if analyzed_commits else 0
-print(f"✓ Analyzed {len(analyzed_commits)} commits")
-print(f"✓ Green-aware: {green_count} ({green_percentage:.1f}%)")
+print(f"Analyzed {len(analyzed_commits)} commits")
+print(f"Green-aware: {green_count} ({green_percentage:.1f}%)")
 
 # Save analysis
 analyzer.save_results(analyzed_commits, output_dir / "analyzed.json")
@@ -434,7 +420,7 @@ print("\n" + "="*80)
 print("ANALYSIS COMPLETE")
 print("="*80)
 aggregator.print_summary(results)
-print(f"\n📁 Results saved in: {output_dir.absolute()}")
+print(f"\nResults saved in: {output_dir.absolute()}")
 ```
 
 **What this example does:**

{greenmining-1.0.4.dist-info → greenmining-1.0.5.dist-info}/RECORD

@@ -1,6 +1,6 @@
-greenmining/__init__.py,sha256=m1foz4CUfEgBsgyWHEjehsT3qt1vogyer1fjhIVFqjg,992
+greenmining/__init__.py,sha256=wlLxbv7hzKNy1yWAEZckcSpYkC1rYDIHU9bjQZHs9es,992
 greenmining/__main__.py,sha256=NYOVS7D4w2XDLn6SyXHXPKE5GrNGOeoWSTb_KazgK5c,590
-greenmining/__version__.py,sha256=QpL6VzwpRtOZiXqutOetZBUCoiJKYFeTosucueZ4gpQ,62
+greenmining/__version__.py,sha256=xZc02a8bS3vUJlzh8k9RoxemB1irQmq_SpVVj6Cg5M0,62
 greenmining/config.py,sha256=00v1Ln8eZE0RxMrLxvonf8XOWqeRYaIme_iC1yDLR90,8228
 greenmining/gsf_patterns.py,sha256=hnd9GuWB8GEflrusEib5hjvl8CD5TSbGcBtb0gfxFp4,54193
 greenmining/utils.py,sha256=dSFwQzQwbS8rYZSgwLIxM_geLqbldwqVOIXMqEg08Qs,5609
@@ -26,12 +26,12 @@ greenmining/services/__init__.py,sha256=UhjS2X9x2v5iH991UDPazP3dTPuSgylMq4kQJaue
 greenmining/services/commit_extractor.py,sha256=3EfUVBwd8hGSbl7pS-_jAL8gX8RxIASXTX5EZBbKQPI,8387
 greenmining/services/data_aggregator.py,sha256=TsFT0oGOnnHk0QGZ1tT6ZhKGc5X1H1D1u7-7OpiPo7Y,19566
 greenmining/services/data_analyzer.py,sha256=f0nlJkPAclHHCzzTyQW5bjhYrgE0XXiR1x7_o3fJaDs,9732
-greenmining/services/github_fetcher.py,sha256=WFyowC0tROKAhP3bA4QXH7QIYf42yaZf2ePpUEvOZ6s,8266
-greenmining/services/github_graphql_fetcher.py,sha256=mQOUZZEltYWusA7TR6Q7BZrHZ-N1Ijt0Wg2kV5T7lFM,11958
+greenmining/services/github_fetcher.py,sha256=mUcmQevhdDRYX72O-M7Vi-s3y4ZwNyKewleti838cqU,8285
+greenmining/services/github_graphql_fetcher.py,sha256=p76vp5EgStzkmTcws__jb90za8m61toW0CBrwrm5Ew4,11972
 greenmining/services/local_repo_analyzer.py,sha256=IrfqY1L6peGO78zufEj4uAU1N7nskc0edAYVzE0Ew_w,14785
 greenmining/services/reports.py,sha256=7Smc7a4KtpmkAJ8UoMlzH5BZerC_iO_jMyQw3_42n1s,23387
-greenmining-1.0.4.dist-info/licenses/LICENSE,sha256=M7ma3JHGeiIZIs3ea0HTcFl_wLFPX2NZElUliYs4bCA,1083
-greenmining-1.0.4.dist-info/METADATA,sha256=rP_4u0fkgp_Bmq2txIpBTLa7ZMj3By2ylTjoej7RSEw,25610
-greenmining-1.0.4.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-greenmining-1.0.4.dist-info/top_level.txt,sha256=nreXgXxZIWI-42yQknQ0HXtUrFnzZ8N1ra4Mdy2KcsI,12
-greenmining-1.0.4.dist-info/RECORD,,
+greenmining-1.0.5.dist-info/licenses/LICENSE,sha256=M7ma3JHGeiIZIs3ea0HTcFl_wLFPX2NZElUliYs4bCA,1083
+greenmining-1.0.5.dist-info/METADATA,sha256=UIp-sji0KZ4GOtLaZOsPjaT9Qb0uDfuzFSIpw-UEcjQ,24899
+greenmining-1.0.5.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+greenmining-1.0.5.dist-info/top_level.txt,sha256=nreXgXxZIWI-42yQknQ0HXtUrFnzZ8N1ra4Mdy2KcsI,12
+greenmining-1.0.5.dist-info/RECORD,,