From dea0d523c69fb2d0d81ece394b4ec36bf06806a4 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Wed, 29 May 2024 10:09:26 +0200
Subject: [PATCH] Transparently open compressed files in DatasetDataProvider

Fixes https://sentry.galaxyproject.org/share/issue/026b0ea1f8aa478daea1cdb0b18df78a/:
```
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x8b in position 1: invalid start byte
  File "starlette/applications.py", line 123, in __call__
    await self.middleware_stack(scope, receive, send)
  File "starlette/middleware/errors.py", line 186, in __call__
    raise exc
  File "starlette/middleware/errors.py", line 164, in __call__
    await self.app(scope, receive, _send)
  File "starlette_context/middleware/raw_middleware.py", line 92, in __call__
    await self.app(scope, receive, send_wrapper)
  File "starlette/middleware/base.py", line 189, in __call__
    with collapse_excgroups():
  File "contextlib.py", line 155, in __exit__
    self.gen.throw(typ, value, traceback)
  File "starlette/_utils.py", line 93, in collapse_excgroups
    raise exc
  File "starlette/middleware/base.py", line 191, in __call__
    response = await self.dispatch_func(request, call_next)
  File "galaxy/webapps/galaxy/fast_app.py", line 109, in add_x_frame_options
    response = await call_next(request)
  File "starlette/middleware/base.py", line 165, in call_next
    raise app_exc
  File "starlette/middleware/base.py", line 151, in coro
    await self.app(scope, receive_or_disconnect, send_no_error)
  File "starlette/middleware/exceptions.py", line 62, in __call__
    await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
  File "starlette/_exception_handler.py", line 64, in wrapped_app
    raise exc
  File "starlette/_exception_handler.py", line 53, in wrapped_app
    await app(scope, receive, sender)
  File "starlette/routing.py", line 758, in __call__
    await self.middleware_stack(scope, receive, send)
  File "starlette/routing.py", line 778, in app
    await route.handle(scope, receive, send)
  File "starlette/routing.py", line 299, in handle
    await self.app(scope, receive, send)
  File "starlette/routing.py", line 79, in app
    await wrap_app_handling_exceptions(app, request)(scope, receive, send)
  File "starlette/_exception_handler.py", line 64, in wrapped_app
    raise exc
  File "starlette/_exception_handler.py", line 53, in wrapped_app
    await app(scope, receive, sender)
  File "starlette/routing.py", line 74, in app
    response = await func(request)
  File "fastapi/routing.py", line 278, in app
    raw_response = await run_endpoint_function(
  File "fastapi/routing.py", line 193, in run_endpoint_function
    return await run_in_threadpool(dependant.call, **values)
  File "starlette/concurrency.py", line 42, in run_in_threadpool
    return await anyio.to_thread.run_sync(func, *args)
  File "anyio/to_thread.py", line 56, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
  File "anyio/_backends/_asyncio.py", line 2144, in run_sync_in_worker_thread
    return await future
  File "anyio/_backends/_asyncio.py", line 851, in run
    result = context.run(func, *args)
  File "galaxy/webapps/galaxy/api/datasets.py", line 446, in show
    return self.service.show(trans, dataset_id, hda_ldda, serialization_params, data_type, **extra_params)
  File "galaxy/webapps/galaxy/services/datasets.py", line 395, in show
    rval = self._raw_data(trans, dataset, **extra_params)
  File "galaxy/webapps/galaxy/services/datasets.py", line 1009, in _raw_data
    return DataResult(data=list(dataset.datatype.dataprovider(dataset, provider, **kwargs)))
  File "galaxy/datatypes/dataproviders/base.py", line 262, in __iter__
    for datum in parent_gen:
  File "galaxy/datatypes/dataproviders/base.py", line 199, in __iter__
    for datum in parent_gen:
  File "galaxy/datatypes/dataproviders/base.py", line 137, in __iter__
    yield from self.source
  File "galaxy/datatypes/dataproviders/base.py", line 137, in __iter__
    yield from self.source
  File "<frozen codecs>", line 322, in decode
```
---
 lib/galaxy/datatypes/dataproviders/dataset.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/dataproviders/dataset.py b/lib/galaxy/datatypes/dataproviders/dataset.py
index dfce2edef527..60b5f6295f3e 100644
--- a/lib/galaxy/datatypes/dataproviders/dataset.py
+++ b/lib/galaxy/datatypes/dataproviders/dataset.py
@@ -15,6 +15,7 @@
 )
 
 from galaxy.util import sqlite
+from galaxy.util.compression_utils import get_fileobj
 from . import (
     base,
     column,
@@ -54,7 +55,7 @@ def __init__(self, dataset, **kwargs):
         # this dataset file is obviously the source
         # TODO: this might be a good place to interface with the object_store...
         mode = "rb" if dataset.datatype.is_binary else "r"
-        super().__init__(open(dataset.get_file_name(), mode))
+        super().__init__(get_fileobj(dataset.get_file_name(), mode))
 
     # TODO: this is a bit of a mess
     @classmethod