Add HfFileSystem.url method (#2027)

* Add url method

* Apply suggestions from code review

Co-authored-by: Lucain <lucainp@gmail.com>

* Apply suggestions from code review

Co-authored-by: Lucain <lucainp@gmail.com>

* Fix

---------

Co-authored-by: Lucain <lucainp@gmail.com>

src/huggingface_hub/hf_file_system.py

@@ -577,6 +577,20 @@ def isfile(self, path):
         except:  # noqa: E722
             return False
 
+    def url(self, path: str) -> str:
+        """Get the HTTP URL of the given path"""
+        resolved_path = self.resolve_path(path)
+        url = hf_hub_url(
+            resolved_path.repo_id,
+            resolved_path.path_in_repo,
+            repo_type=resolved_path.repo_type,
+            revision=resolved_path.revision,
+            endpoint=self.endpoint,
+        )
+        if self.isdir(path):
+            url = url.replace("/resolve/", "/tree/", 1)
+        return url
+
     @property
     def transaction(self):
         """A context within which files are committed together upon exit
@@ -653,6 +667,9 @@ def _upload_chunk(self, final: bool = False) -> None:
                 path=self.resolved_path.unresolve(),
             )
 
+    def url(self) -> str:
+        return self.fs.url(self.path)
+
 
 class HfFileSystemStreamFile(fsspec.spec.AbstractBufferedFile):
     def __init__(
@@ -740,6 +757,9 @@ def read(self, length: int = -1):
         self.loc += len(out)
         return out
 
+    def url(self) -> str:
+        return self.fs.url(self.path)
+
     def __del__(self):
         if not hasattr(self, "resolved_path"):
             # Means that the constructor failed. Nothing to do.

tests/test_hf_file_system.py

@@ -131,6 +131,16 @@ def test_glob(self):
         )
         self.assertIsNotNone(files[keys[0]]["last_commit"])
 
+    def test_url(self):
+        self.assertEqual(
+            self.hffs.url(self.hf_path + "/data/text_data.txt"),
+            f"{ENDPOINT_STAGING}/datasets/{self.repo_id}/resolve/main/data/text_data.txt",
+        )
+        self.assertEqual(
+            self.hffs.url(self.hf_path + "/data"),
+            f"{ENDPOINT_STAGING}/datasets/{self.repo_id}/tree/main/data",
+        )
+
     def test_file_type(self):
         self.assertTrue(
             self.hffs.isdir(self.hf_path + "/data") and not self.hffs.isdir(self.hf_path + "/.gitattributes")