find all blob in a repo

.isort.cfg

@@ -1,4 +1,4 @@
 [settings]
 line_length = 79
 multi_line_output = 3
-known_third_party =
+known_third_party =dulwich

loadBlob.py

@@ -0,0 +1,29 @@
+from dulwich.repo import Repo
+
+
+def loadBlobObjects(dir):
+    """
+    function: Find all blob objects in a given repo and make a list
+    input: the directory of a repo
+    output: a list of blob object
+    """
+    repo = Repo(dir)
+    objectlist = list(repo.object_store)
+    bloblist = []
+    for object in objectlist:
+        if (
+            repo.object_store[object].type == 3
+        ):  # type == 1 -> commit; type == 2 -> tree ;type == 3 -> blob.
+            bloblist.append(repo.object_store[object].data)
+    repo.close()
+    return bloblist
+
+
+def changeToSourceCode(list):
+    # TODO:转换成源代码文件或者是其他的能被克隆检测工具检测的形式，不知道该做成啥样就先放着
+    return 0
+
+
+# a test for local repo
+# list = loadBlobObjects("C:/Users/Administrator/redis")
+# print(list)

requirements.txt

@@ -1 +1,2 @@
 pre-commit==2.20.0
+dulwich==0.20.45