Replace file_name property with get_file_name function

doc/source/admin/jobs.md

@@ -254,7 +254,7 @@ def ncbi_blastn_wrapper(job):
     # Allocate extra time
     inp_data = dict( [ ( da.name, da.dataset ) for da in job.input_datasets ] )
     inp_data.update( [ ( da.name, da.dataset ) for da in job.input_library_datasets ] )
-    query_file = inp_data[ "query" ].file_name
+    query_file = inp_data[ "query" ].get_file_name()
     query_size = os.path.getsize( query_file )
     if query_size > 1024 * 1024:
         walltime_str = "walltime=24:00:00/"

doc/source/dev/data_types.md

@@ -282,7 +282,7 @@ we're setting metadata about the file.
 
 ```python
     def set_meta(self, dataset, **kwd):
-        dataset.metadata.number_of_sequences = self._count_genbank_sequences(dataset.file_name)
+        dataset.metadata.number_of_sequences = self._count_genbank_sequences(dataset.get_file_name())
 ```
 
 Now we'll need to make use of this in our `set_peek`
@@ -297,7 +297,7 @@ override:
             else:
                 dataset.blurb = "%s sequences" % dataset.metadata.number_of_sequences
             # Get standard text peek from dataset
-            dataset.peek = data.get_file_peek(dataset.file_name, is_multi_byte=is_multi_byte)
+            dataset.peek = data.get_file_peek(dataset.get_file_name(), is_multi_byte=is_multi_byte)
         else:
             dataset.peek = 'file does not exist'
             dataset.blurb = 'file purged from disk'
@@ -332,7 +332,7 @@ class Genbank(data.Text):
             else:
                 dataset.blurb = "%s sequences" % dataset.metadata.number_of_sequences
             # Get
-            dataset.peek = data.get_file_peek(dataset.file_name, is_multi_byte=is_multi_byte)
+            dataset.peek = data.get_file_peek(dataset.get_file_name(), is_multi_byte=is_multi_byte)
         else:
             dataset.peek = 'file does not exist'
             dataset.blurb = 'file purged from disk'
@@ -348,7 +348,7 @@ class Genbank(data.Text):
         """
         Set the number of sequences in dataset.
         """
-        dataset.metadata.number_of_sequences = self._count_genbank_sequences(dataset.file_name)
+        dataset.metadata.number_of_sequences = self._count_genbank_sequences(dataset.get_file_name())
 
     def _count_genbank_sequences(self, filename):
         """

lib/galaxy/celery/tasks.py

@@ -152,7 +152,7 @@ def change_datatype(
         log.info(f"Changing datatype is not allowed for {model_class} {dataset_instance.id}")
         return
     if datatype == "auto":
-        path = dataset_instance.dataset.file_name
+        path = dataset_instance.dataset.get_file_name()
         datatype = sniff.guess_ext(path, datatypes_registry.sniff_order)
     datatypes_registry.change_datatype(dataset_instance, datatype)
     with transaction(sa_session):

lib/galaxy/datatypes/annotation.py

@@ -23,7 +23,7 @@ class SnapHmm(Text):
 
     def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
-            dataset.peek = get_file_peek(dataset.file_name)
+            dataset.peek = get_file_peek(dataset.get_file_name())
             dataset.blurb = "SNAP HMM model"
         else:
             dataset.peek = "file does not exist"

lib/galaxy/datatypes/assembly.py

@@ -238,7 +238,7 @@ def regenerate_primary_file(self, dataset: DatasetProtocol) -> None:
                 else:
                     rval.append(f'<li><a href="{fn}" type="text/plain">{fn}</a>{opt_text}</li>')
         rval.append("</ul></div></html>")
-        with open(dataset.file_name, "w") as f:
+        with open(dataset.get_file_name(), "w") as f:
             f.write("\n".join(rval))
             f.write("\n")
 

lib/galaxy/datatypes/blast.py

@@ -70,7 +70,7 @@ class BlastXml(GenericXml):
     def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
-            dataset.peek = get_file_peek(dataset.file_name)
+            dataset.peek = get_file_peek(dataset.get_file_name())
             dataset.blurb = "NCBI Blast XML data"
         else:
             dataset.peek = "file does not exist"
@@ -246,7 +246,7 @@ def display_data(
         msg = ""
         try:
             # Try to use any text recorded in the dummy index file:
-            with open(dataset.file_name, encoding="utf-8") as handle:
+            with open(dataset.get_file_name(), encoding="utf-8") as handle:
                 msg = handle.read().strip()
         except Exception:
             pass

lib/galaxy/datatypes/chain.py

@@ -39,7 +39,7 @@ def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> N
         """
         data_lines = 0
         chains = 0
-        with compression_utils.get_fileobj(dataset.file_name) as fh:
+        with compression_utils.get_fileobj(dataset.get_file_name()) as fh:
             for line in fh:
                 line = line.strip()
                 if line and line.startswith("#"):
@@ -55,7 +55,7 @@ def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> N
 
     def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
-            dataset.peek = data.get_file_peek(dataset.file_name)
+            dataset.peek = data.get_file_peek(dataset.get_file_name())
             if dataset.metadata.chains:
                 dataset.blurb = f"{commaify(str(dataset.metadata.chains))} chains"
             else:

lib/galaxy/datatypes/constructive_solid_geometry.py

@@ -106,7 +106,7 @@ def _is_ply_header(self, fh: "TextIOBase", subtype: str) -> bool:
 
     def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
-            with open(dataset.file_name, errors="ignore") as fh:
+            with open(dataset.get_file_name(), errors="ignore") as fh:
                 for line in fh:
                     line = line.strip()
                     if not line:
@@ -129,7 +129,7 @@ def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> N
 
     def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
-            dataset.peek = get_file_peek(dataset.file_name)
+            dataset.peek = get_file_peek(dataset.get_file_name())
             dataset.blurb = f"Faces: {str(dataset.metadata.face)}, Vertices: {str(dataset.metadata.vertex)}"
         else:
             dataset.peek = "File does not exist"
@@ -292,7 +292,7 @@ def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> N
             field_components = {}
             dataset_structure_complete = False
             processing_field_section = False
-            with open(dataset.file_name, errors="ignore") as fh:
+            with open(dataset.get_file_name(), errors="ignore") as fh:
                 for i, line in enumerate(fh):
                     line = line.strip()
                     if not line:
@@ -463,7 +463,7 @@ def get_blurb(self, dataset: HasMetadata) -> str:
 
     def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
-            dataset.peek = get_file_peek(dataset.file_name)
+            dataset.peek = get_file_peek(dataset.get_file_name())
             dataset.blurb = self.get_blurb(dataset)
         else:
             dataset.peek = "File does not exist"
@@ -556,7 +556,7 @@ def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
 
     def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
-            with open(dataset.file_name, errors="ignore") as fh:
+            with open(dataset.get_file_name(), errors="ignore") as fh:
                 for i, line in enumerate(fh):
                     line = line.strip()
                     if not line or i > 6:
@@ -572,7 +572,7 @@ def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> N
 
     def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
-            dataset.peek = get_file_peek(dataset.file_name, line_count=7)
+            dataset.peek = get_file_peek(dataset.get_file_name(), line_count=7)
             dataset.blurb = f"format: {str(dataset.metadata.format)} dim: {str(dataset.metadata.dimension)} cells: {str(dataset.metadata.cells)}"
         else:
             dataset.peek = "File does not exist"
@@ -627,7 +627,7 @@ def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
 
     def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
-            with open(dataset.file_name, errors="ignore") as fh:
+            with open(dataset.get_file_name(), errors="ignore") as fh:
                 field = ""
                 for i, line in enumerate(fh):
                     line = line.strip()
@@ -659,7 +659,7 @@ def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> N
 
     def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
-            dataset.peek = get_file_peek(dataset.file_name, line_count=9)
+            dataset.peek = get_file_peek(dataset.get_file_name(), line_count=9)
             dataset.blurb = f"format: {str(dataset.metadata.format)} dim: {str(dataset.metadata.dimension)} cells: {str(dataset.metadata.cells)}"
         else:
             dataset.peek = "File does not exist"
@@ -681,7 +681,7 @@ def __init__(self, **kwd):
     def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         data.Text.set_meta(self, dataset, overwrite=overwrite, **kwd)
         if dataset.has_data():
-            with open(dataset.file_name, errors="ignore") as fh:
+            with open(dataset.get_file_name(), errors="ignore") as fh:
                 dataset.metadata.dimension = self._get_dimension(fh)
 
     def _get_dimension(self, fh: "TextIOBase", maxlines: int = 100, sep: Optional[str] = None) -> Optional[float]:
@@ -723,7 +723,7 @@ def __init__(self, **kwd):
     def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         Tabular.set_meta(self, dataset, overwrite=overwrite, **kwd)
         if dataset.has_data():
-            with open(dataset.file_name, errors="ignore") as fh:
+            with open(dataset.get_file_name(), errors="ignore") as fh:
                 dataset.metadata.dimension = self._get_dimension(fh)
 
     def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
@@ -768,7 +768,7 @@ def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
 
     def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
-            with open(dataset.file_name, errors="ignore") as fh:
+            with open(dataset.get_file_name(), errors="ignore") as fh:
                 for i, line in enumerate(fh):
                     line = line.strip()
                     if not line or i > 1:
@@ -784,7 +784,7 @@ def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> N
 
     def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
-            dataset.peek = get_file_peek(dataset.file_name, line_count=3)
+            dataset.peek = get_file_peek(dataset.get_file_name(), line_count=3)
             dataset.blurb = f"Gmsh verion: {str(dataset.metadata.version)} {str(dataset.metadata.format)}"
         else:
             dataset.peek = "File does not exist"

lib/galaxy/datatypes/data.py

@@ -183,7 +183,7 @@ def _get_file_size(data):
         if data.dataset.object_store:
             file_size = data.dataset.object_store.size(data.dataset)
         else:
-            file_size = os.stat(data.file_name).st_size
+            file_size = os.stat(data.get_file_name()).st_size
     return file_size
 
 
@@ -389,7 +389,7 @@ def _archive_composite_dataset(
         error = False
         msg = ""
         ext = data.extension
-        path = data.file_name
+        path = data.get_file_name()
         efp = data.extra_files_path
         # Add any central file to the archive,
 
@@ -424,7 +424,7 @@ def __archive_extra_files_path(self, extra_files_path: str) -> Generator[Tuple[s
     def _serve_raw(
         self, dataset: DatasetHasHidProtocol, to_ext: Optional[str], headers: Headers, **kwd
     ) -> Tuple[IO, Headers]:
-        headers["Content-Length"] = str(os.stat(dataset.file_name).st_size)
+        headers["Content-Length"] = str(os.stat(dataset.get_file_name()).st_size)
         headers[
             "content-type"
         ] = "application/octet-stream"  # force octet-stream so Safari doesn't append mime extensions to filename
@@ -436,7 +436,7 @@ def _serve_raw(
             filename_pattern=kwd.get("filename_pattern"),
         )
         headers["Content-Disposition"] = f'attachment; filename="{filename}"'
-        return open(dataset.file_name, mode="rb"), headers
+        return open(dataset.get_file_name(), mode="rb"), headers
 
     def to_archive(self, dataset: DatasetProtocol, name: str = "") -> Iterable:
         """
@@ -451,13 +451,13 @@ def to_archive(self, dataset: DatasetProtocol, name: str = "") -> Iterable:
         if dataset.datatype.composite_type or dataset.extension.endswith("html"):
             main_file = f"{name}.html"
             rel_paths.append(main_file)
-            file_paths.append(dataset.file_name)
+            file_paths.append(dataset.get_file_name())
             for fpath, rpath in self.__archive_extra_files_path(dataset.extra_files_path):
                 rel_paths.append(os.path.join(name, rpath))
                 file_paths.append(fpath)
         else:
-            rel_paths.append(f"{name or dataset.file_name}.{dataset.extension}")
-            file_paths.append(dataset.file_name)
+            rel_paths.append(f"{name or dataset.get_file_name()}.{dataset.extension}")
+            file_paths.append(dataset.get_file_name())
         return zip(file_paths, rel_paths)
 
     def _serve_file_download(self, headers, data, trans, to_ext, file_size, **kwd):
@@ -480,15 +480,15 @@ def _serve_file_download(self, headers, data, trans, to_ext, file_size, **kwd):
                 "content-type"
             ] = "application/octet-stream"  # force octet-stream so Safari doesn't append mime extensions to filename
             headers["Content-Disposition"] = f'attachment; filename="{filename}"'
-            return open(data.file_name, "rb"), headers
+            return open(data.get_file_name(), "rb"), headers
 
     def _serve_binary_file_contents_as_text(self, trans, data, headers, file_size, max_peek_size):
         headers["content-type"] = "text/html"
         return (
             trans.fill_template_mako(
                 "/dataset/binary_file.mako",
                 data=data,
-                file_contents=open(data.file_name, "rb").read(max_peek_size),
+                file_contents=open(data.get_file_name(), "rb").read(max_peek_size),
                 file_size=util.nice_size(file_size),
                 truncated=file_size > max_peek_size,
             ),
@@ -500,13 +500,15 @@ def _serve_file_contents(self, trans, data, headers, preview, file_size, max_pee
 
         preview = util.string_as_bool(preview)
         if not preview or isinstance(data.datatype, images.Image) or file_size < max_peek_size:
-            return self._yield_user_file_content(trans, data, data.file_name, headers), headers
+            return self._yield_user_file_content(trans, data, data.get_file_name(), headers), headers
 
         # preview large text file
         headers["content-type"] = "text/html"
         return (
             trans.fill_template_mako(
-                "/dataset/large_file.mako", truncated_data=open(data.file_name, "rb").read(max_peek_size), data=data
+                "/dataset/large_file.mako",
+                truncated_data=open(data.get_file_name(), "rb").read(max_peek_size),
+                data=data,
             ),
             headers,
         )
@@ -581,8 +583,8 @@ def display_data(
         downloading = to_ext is not None
         file_size = _get_file_size(dataset)
 
-        if not os.path.exists(dataset.file_name):
-            raise ObjectNotFound(f"File Not Found ({dataset.file_name}).")
+        if not os.path.exists(dataset.get_file_name()):
+            raise ObjectNotFound(f"File Not Found ({dataset.get_file_name()}).")
 
         if downloading:
             trans.log_event(f"Download dataset id: {str(dataset.id)}")
@@ -618,7 +620,7 @@ def display_as_markdown(self, dataset_instance: DatasetProtocol) -> str:
         if self.is_binary:
             result = "*cannot display binary content*\n"
         else:
-            with open(dataset_instance.file_name) as f:
+            with open(dataset_instance.get_file_name()) as f:
                 contents = f.read(DEFAULT_MAX_PEEK_SIZE)
             result = literal_via_fence(contents)
             if len(contents) == DEFAULT_MAX_PEEK_SIZE:
@@ -1038,12 +1040,12 @@ def estimate_file_lines(self, dataset: DatasetProtocol) -> Optional[int]:
         """
         sample_size = 1048576
         try:
-            with compression_utils.get_fileobj(dataset.file_name) as dataset_fh:
+            with compression_utils.get_fileobj(dataset.get_file_name()) as dataset_fh:
                 dataset_read = dataset_fh.read(sample_size)
             sample_lines = dataset_read.count("\n")
             return int(sample_lines * (float(dataset.get_size()) / float(sample_size)))
         except UnicodeDecodeError:
-            log.error(f"Unable to estimate lines in file {dataset.file_name}")
+            log.error(f"Unable to estimate lines in file {dataset.get_file_name()}")
             return None
 
     def count_data_lines(self, dataset: HasFileName) -> Optional[int]:
@@ -1053,7 +1055,7 @@ def count_data_lines(self, dataset: HasFileName) -> Optional[int]:
         """
         CHUNK_SIZE = 2**15  # 32Kb
         data_lines = 0
-        with compression_utils.get_fileobj(dataset.file_name) as in_file:
+        with compression_utils.get_fileobj(dataset.get_file_name()) as in_file:
             # FIXME: Potential encoding issue can prevent the ability to iterate over lines
             # causing set_meta process to fail otherwise OK jobs. A better solution than
             # a silent try/except is desirable.
@@ -1063,7 +1065,7 @@ def count_data_lines(self, dataset: HasFileName) -> Optional[int]:
                     if line and not line.startswith("#"):
                         data_lines += 1
             except UnicodeDecodeError:
-                log.error(f"Unable to count lines in file {dataset.file_name}")
+                log.error(f"Unable to count lines in file {dataset.get_file_name()}")
                 return None
         return data_lines
 
@@ -1078,7 +1080,7 @@ def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
 
         if not dataset.dataset.purged:
             # The file must exist on disk for the get_file_peek() method
-            dataset.peek = get_file_peek(dataset.file_name, width=width, skipchars=skipchars, line_wrap=line_wrap)
+            dataset.peek = get_file_peek(dataset.get_file_name(), width=width, skipchars=skipchars, line_wrap=line_wrap)
             if line_count is None:
                 # See if line_count is stored in the metadata
                 if dataset.metadata.data_lines:
@@ -1117,7 +1119,7 @@ def split(cls, input_datasets: List, subdir_generator_function: Callable, split_
 
         if len(input_datasets) > 1:
             raise Exception("Text file splitting does not support multiple files")
-        input_files = [ds.file_name for ds in input_datasets]
+        input_files = [ds.get_file_name() for ds in input_datasets]
 
         lines_per_file = None
         chunk_size = None