Fix non-compliant Git URL matching

RFC 3986 § 2.3 permits more characters in a URL than were matched. This corrects that, though there may be other deficiencies. This was a regression from v1.0.2, where at least “.” was matched without error.
python-poetry · Feb 11, 2020 · 7348893 · 7348893
1 parent ed44342
commit 7348893
Show file tree

Hide file tree

Showing 2 changed files with 18 additions and 2 deletions.
diff --git a/poetry/vcs/git.py b/poetry/vcs/git.py
@@ -12,8 +12,8 @@
     "user": r"[a-zA-Z0-9_.-]+",
     "resource": r"[a-zA-Z0-9_.-]+",
     "port": r"\d+",
-    "path": r"[\w\-/\\]+",
-    "name": r"[\w\-]+",
+    "path": r"[\w~.\-/\\]+",
+    "name": r"[\w~.\-]+",
     "rev": r"[^@#]+",
 }
 

diff --git a/tests/vcs/test_git.py b/tests/vcs/test_git.py
@@ -20,6 +20,10 @@
             "git+https://user@hostname/project/blah.git",
             GitUrl("https://user@hostname/project/blah.git", None),
         ),
+        (
+            "git+https://user@hostname/project~_-.foo/blah~_-.bar.git",
+            GitUrl("https://user@hostname/project~_-.foo/blah~_-.bar.git", None),
+        ),
         (
             "git+https://user@hostname:project/blah.git",
             GitUrl("https://user@hostname/project/blah.git", None),
@@ -98,6 +102,18 @@ def test_normalize_url(url, normalized):
                 "https", "hostname", "/project/blah.git", "user", None, "blah", None
             ),
         ),
+        (
+            "git+https://user@hostname/project~_-.foo/blah~_-.bar.git",
+            ParsedUrl(
+                "https",
+                "hostname",
+                "/project~_-.foo/blah~_-.bar.git",
+                "user",
+                None,
+                "blah~_-.bar",
+                None,
+            ),
+        ),
         (
             "git+https://user@hostname:project/blah.git",
             ParsedUrl(