Version up to 1.4.5 (#243)

* Version up to 1.4.5 and template fix

* Update whatthepath requirement version to avoid huge diffs check.

* Added test for huge patches parsing

.github/pull-request-template.md

@@ -1,6 +1,6 @@
 ## Description
 
-Please include a summary of the change and which is is fixed.
+Please include a summary of the change and which is fixed.
 
 - Add A
 - Fix B

credsweeper/__init__.py

@@ -25,4 +25,4 @@
 
 CREDSWEEPER_DIR = Path(__file__).resolve().parent
 
-__version__ = "1.4.4"
+__version__ = "1.4.5"

requirements.txt

@@ -9,7 +9,7 @@ PyYAML~=6.0
 regex~=2022.8.17
 requests~=2.28.0
 typing_extensions~=4.2.0
-whatthepatch~=1.0.2
+whatthepatch~=1.0.3
 
 # ML requirements
 numpy<=1.23.0

tests/test_app.py

@@ -52,6 +52,32 @@ def test_it_works_p(self) -> None:
 
     # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
 
+    def test_huge_diff_p(self) -> None:
+        # verifies issue when huge patch is parsed very slow
+        # https://github.com/Samsung/CredSweeper/issues/242
+        text = """diff --git a/huge.file b/huge.file
+                index 0000000..1111111 100644
+                --- a/huge.file
+                +++ a/huge.file
+                @@ -3,13 +3,1000007 @@
+                 00000000
+                 11111111
+                 22222222
+                -33333333
+                -44444444
+                +55555555
+                +66666666
+                """
+        for n in range(0, 1000000):
+            text += "+" + hex(n) + "\n"
+        with tempfile.TemporaryDirectory() as tmp_dir:
+            target_path = os.path.join(tmp_dir, f"{__name__}.diff")
+            start_time = time.time()
+            _stdout, _stderr = self._m_credsweeper(["--path", target_path, "--ml_threshold", "0", "--log", "silence"])
+            self.assertGreater(100, time.time() - start_time)
+
+    # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
+
     def test_it_works_without_ml_p(self) -> None:
         target_path = str(SAMPLES_DIR / "password")
         _stdout, _stderr = self._m_credsweeper(["--path", target_path, "--ml_threshold", "0", "--log", "silence"])