fix open file method for tar files (#412)

iterative · Sep 9, 2024 · ca36654 · ca36654
1 parent 823f9f8
commit ca36654
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 9 deletions.
diff --git a/examples/multimodal/wds.py b/examples/multimodal/wds.py
@@ -16,7 +16,7 @@
 )
 
 wds_images = (
-    DataChain.from_storage(IMAGE_TARS)
+    DataChain.from_storage(IMAGE_TARS, type="image")
     .settings(cache=True)
     .gen(laion=process_webdataset(spec=WDSLaion), params="file")
 )

diff --git a/src/datachain/lib/file.py b/src/datachain/lib/file.py
@@ -195,14 +195,15 @@ def open(self, mode: Literal["rb", "r"] = "rb"):
             with VFileRegistry.resolve(self, self.location) as f:  # type: ignore[arg-type]
                 yield f
 
-        uid = self.get_uid()
-        client = self._catalog.get_client(self.source)
-        if self._caching_enabled:
-            client.download(uid, callback=self._download_cb)
-        with client.open_object(
-            uid, use_cache=self._caching_enabled, cb=self._download_cb
-        ) as f:
-            yield io.TextIOWrapper(f) if mode == "r" else f
+        else:
+            uid = self.get_uid()
+            client = self._catalog.get_client(self.source)
+            if self._caching_enabled:
+                client.download(uid, callback=self._download_cb)
+            with client.open_object(
+                uid, use_cache=self._caching_enabled, cb=self._download_cb
+            ) as f:
+                yield io.TextIOWrapper(f) if mode == "r" else f
 
     def read(self, length: int = -1):
         """Returns file contents."""