Merge pull request #240 from hatrg/enhance-get-repo-name-by-url-method

enhance method _get_repo_name_from_url to handle case when .git is part of the repo name

pydriller/repository.py

@@ -272,13 +272,18 @@ def _split_in_chunks(full_list: List[Commit], num_workers: int) -> List[List[Com
     @staticmethod
     def _get_repo_name_from_url(url: str) -> str:
         last_slash_index = url.rfind("/")
-        last_suffix_index = url.rfind(".git")
-        if last_suffix_index < 0:
-            last_suffix_index = len(url)
+        len_url = len(url)
 
-        if last_slash_index < 0 or last_suffix_index <= last_slash_index:
+        if last_slash_index < 0 or last_slash_index >= len_url - 1:
             raise MalformedUrl(f"Badly formatted url {url}")
 
+        last_dot_index = url.rfind(".")
+
+        if url[last_dot_index:] == ".git":
+            last_suffix_index = last_dot_index
+        else:
+            last_suffix_index = len_url
+
         return url[last_slash_index + 1:last_suffix_index]
 
 

tests/test_repository_mining.py

@@ -269,6 +269,25 @@ def test_projectname_multiple_repos_remote():
         assert commit.project_name == 'pydriller'
 
 
+def test_get_repo_name_from_url():
+    # with .git in the middle of the name
+    url_set_a = [
+        "https://github.com/academicpages/academicpages.github.io",
+        "https://github.com/academicpages/academicpages.github.io.git",
+    ]
+
+    url_set_b = [
+        "https://github.com/ishepard/pydriller",
+        "https://github.com/ishepard/pydriller.git",
+    ]
+
+    for url in url_set_a:
+        assert Repository._get_repo_name_from_url(url) == "academicpages.github.io"
+
+    for url in url_set_b:
+        assert Repository._get_repo_name_from_url(url) == "pydriller"
+
+
 @pytest.mark.skipif(sys.version_info < (3, 8) and sys.platform == "win32", reason="requires Python3.8 or greater on Windows")
 def test_deletion_remotes():
     repos = [