[speedfix] Ignore all files and folders .gitignore while copying

src/analyze_libraries.py

@@ -11,10 +11,36 @@
 from language.detect_language import supported_languages
 from datetime import datetime
 import logging
+import fnmatch
 import time
 
 module_logger = logging.getLogger("main.analyze_libraries")
 
+def ignore_gitignore(basedir):
+    """
+    Function that can be used as copytree() ignore parameter using a glob style parameter.
+    Reads the .gitignore (if exists) and adding it to an ignore array.
+    """
+    if os.path.isfile(basedir+'/.gitignore'):
+        with open(basedir+'/.gitignore') as f:
+            gitignores = f.readlines()
+    else:
+        gitignores = []
+
+    gitignores = [x.strip() for x in gitignores]
+    filtered = []
+    for pattern in gitignores:
+        if (pattern != "" and pattern[0] != "#"): # Strip comments and linebreaks
+            filtered.append(pattern.rstrip('/').lstrip('/')) # Remove first and last char slashes to comply w/ glob
+    gitignores = filtered
+
+    def _ignore_gitignore(path, names):
+        ignored_names = []
+        for pattern in gitignores:
+            ignored_names.extend(fnmatch.filter(names, pattern))
+        return set(ignored_names)
+    return _ignore_gitignore
+
 
 class AnalyzeLibraries:
     def __init__(self, commit_list, author_emails, basedir, skip, commit_size_limit, file_size_limit):
@@ -38,7 +64,7 @@ def get_libraries(self):
 
         _log_info("Copying the repository to a temporary location, this can take a while...")
         try:
-            shutil.copytree(self.basedir, tmp_repo_path, symlinks=True)
+            shutil.copytree(self.basedir, tmp_repo_path, symlinks=True, ignore=ignore_gitignore(self.basedir))
         except shutil.Error as e:
             module_logger.debug("Shutil error messages: {}.".format(str(e)))
         _log_info("Finished copying the repository to", tmp_repo_path)