greenmining 1.2.6__py3-none-any.whl → 1.2.8__py3-none-any.whl

greenmining/__init__.py

@@ -8,7 +8,7 @@ from greenmining.gsf_patterns import (
     is_green_aware,
 )
 
-__version__ = "1.2.6"
+__version__ = "1.2.8"
 
 
 def fetch_repositories(

greenmining/services/local_repo_analyzer.py

@@ -237,8 +237,9 @@ class LocalRepoAnalyzer:
         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)
+        # Auto-calculate clone depth: max_commits * 5 to account for merges/skipped commits
+        # and avoid boundary errors where parent commits fall outside the shallow window
+        self.clone_depth = clone_depth if clone_depth else max(100, max_commits * 5)
         self.gsf_patterns = GSF_PATTERNS
 
         # Phase 1.3: Private repository support
@@ -479,7 +480,7 @@ class LocalRepoAnalyzer:
         clone_parent.mkdir(parents=True, exist_ok=True)
         local_path = clone_parent / repo_name
 
-        # Perform shallow clone manually before PyDriller (much faster!)
+        # Perform shallow clone manually, then unshallow for full history
         if not local_path.exists():
             import subprocess
 
@@ -499,14 +500,36 @@ class LocalRepoAnalyzer:
                     capture_output=True,
                     text=True,
                     check=True,
-                    timeout=180,
+                    timeout=300,
                 )
             except subprocess.TimeoutExpired:
-                colored_print("   Clone timeout after 180s", "yellow")
+                colored_print("   Clone timeout after 300s", "yellow")
                 raise
             except subprocess.CalledProcessError as e:
                 colored_print(f"   Clone failed: {e.stderr}", "red")
                 raise
+
+            # Immediately unshallow to get full history for accurate analysis
+            # This is still faster than a full clone: shallow clone negotiates
+            # objects quickly, then unshallow fetches the remainder incrementally
+            if self.shallow_clone:
+                colored_print("   Fetching full history...", "cyan")
+                try:
+                    subprocess.run(
+                        ["git", "fetch", "--unshallow"],
+                        cwd=str(local_path),
+                        capture_output=True,
+                        text=True,
+                        check=True,
+                        timeout=300,
+                    )
+                except subprocess.CalledProcessError:
+                    pass  # Already unshallowed or not shallow
+                except subprocess.TimeoutExpired:
+                    colored_print(
+                        "   Warning: Full history fetch timed out, some metrics may be incomplete",
+                        "yellow",
+                    )
         else:
             colored_print(f"   Using existing clone: {local_path}", "cyan")
 
@@ -556,7 +579,8 @@ class LocalRepoAnalyzer:
                 except Exception:
                     pass
 
-            # Compute process metrics if enabled
+            # Compute process metrics if enabled (full history already available
+            # from the unshallow step that runs right after cloning)
             process_metrics = {}
             if self.compute_process_metrics and local_path.exists():
                 colored_print("   Computing process metrics...", "cyan")

{greenmining-1.2.6.dist-info → greenmining-1.2.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: greenmining
-Version: 1.2.6
+Version: 1.2.8
 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-1.2.6.dist-info → greenmining-1.2.8.dist-info}/RECORD

@@ -1,4 +1,4 @@
-greenmining/__init__.py,sha256=FvURFMzA2M-JtfP92RiAaCOVvJjN2qNUuEAQr0SPD4o,4789
+greenmining/__init__.py,sha256=949lyKXLFKgFLvz0T3o6UuVuGO1kvwdOwPmF1FA65d0,4789
 greenmining/__main__.py,sha256=NYOVS7D4w2XDLn6SyXHXPKE5GrNGOeoWSTb_KazgK5c,590
 greenmining/gsf_patterns.py,sha256=UvNJPY3HlAx1SicwUqci40TlLg8lCL0tszSOH4haxQs,55921
 greenmining/utils.py,sha256=-dnLUw9taCzvQ2dk6uc66GAohOFiXJFKs9TLSEPk5kM,2893
@@ -25,10 +25,10 @@ greenmining/services/commit_extractor.py,sha256=qBM9QpGzPZRmGMFufJ6gP8eWIuufTowL
 greenmining/services/data_aggregator.py,sha256=BU_HUb-8c0n0sa_7VZRB8jIVnaVhRLf-E6KA4ASh-08,19427
 greenmining/services/data_analyzer.py,sha256=0XqW-slrnt7RotrHDweOqKtoN8XIA7y6p7s2Jau6cMg,7431
 greenmining/services/github_graphql_fetcher.py,sha256=WhSbQGMdkb0D4uLcMKW6xZK77c5AkW-nZf718issap4,11527
-greenmining/services/local_repo_analyzer.py,sha256=Ju3UA9LQc2LpIatvpDiKg9aLhQp5HsldsrdWJDU5Rwo,27406
+greenmining/services/local_repo_analyzer.py,sha256=n-znklcb0MeN6nGha7pD6PCt7Z8SpN1rcIKthTFrt70,28634
 greenmining/services/reports.py,sha256=QCJZhET3hRkH83htxLkbEP58dE3-7jIZh82Pp60hQcc,23218
-greenmining-1.2.6.dist-info/licenses/LICENSE,sha256=M7ma3JHGeiIZIs3ea0HTcFl_wLFPX2NZElUliYs4bCA,1083
-greenmining-1.2.6.dist-info/METADATA,sha256=M7yBMY3OIVcZnq3JxIvRe6ncQnnK78_U90ezvN1WyVA,10522
-greenmining-1.2.6.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-greenmining-1.2.6.dist-info/top_level.txt,sha256=nreXgXxZIWI-42yQknQ0HXtUrFnzZ8N1ra4Mdy2KcsI,12
-greenmining-1.2.6.dist-info/RECORD,,
+greenmining-1.2.8.dist-info/licenses/LICENSE,sha256=M7ma3JHGeiIZIs3ea0HTcFl_wLFPX2NZElUliYs4bCA,1083
+greenmining-1.2.8.dist-info/METADATA,sha256=h-psius6PqVGZdP4_83a2KvLr2SQkT-0t5fDeWduwJc,10522
+greenmining-1.2.8.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+greenmining-1.2.8.dist-info/top_level.txt,sha256=nreXgXxZIWI-42yQknQ0HXtUrFnzZ8N1ra4Mdy2KcsI,12
+greenmining-1.2.8.dist-info/RECORD,,