XMLSchemaValidationError when reading xml/h5 dataset
grinic opened this issue · 12 comments
grinic commented
System and Software
- aicsimageio Version: 4.9.2
- Python Version: Python 3.9.15
- Operating System: Windows 10
Description
I am trying to open the xml/h5 dataset here:
xml
h5
using:
image = AICSImage(xmlfile, reader= BioformatsReader)
img = image.data
meta = image.metadata
and I obtain the following error:
---------------------------------------------------------------------------
XMLSchemaValidationError Traceback (most recent call last)
Cell In[2], line 1
----> 1 image.data
File ~\AppData\Roaming\Python\Python39\site-packages\aicsimageio\aics_image.py:529, in AICSImage.data(self)
516 @property
517 def data(self) -> np.ndarray:
518 """
519 Returns
520 -------
(...)
527 Recommended to use `dask_data` for large mosaic images.
528 """
--> 529 return self.xarray_data.data
File ~\AppData\Roaming\Python\Python39\site-packages\aicsimageio\aics_image.py:469, in AICSImage.xarray_data(self)
453 """
454 Returns
455 -------
(...)
462 Recommended to use `xarray_dask_data` for large mosaic images.
463 """
464 if self._xarray_data is None:
465 if (
466 # Does the user want to get stitched mosaic
467 self._reconstruct_mosaic
468 # Does the data have a tile dim
--> 469 and dimensions.DimensionNames.MosaicTile in self.reader.dims.order
470 ):
471 try:
472 self._xarray_data = (
473 self._transform_data_array_to_aics_image_standard(
474 self.reader.mosaic_xarray_data
475 )
476 )
File ~\AppData\Roaming\Python\Python39\site-packages\aicsimageio\readers\reader.py:532, in Reader.dims(self)
525 """
526 Returns
527 -------
528 dims: Dimensions
529 Object with the paired dimension names and their sizes.
530 """
531 if self._dims is None:
--> 532 self._dims = Dimensions(dims=self.xarray_dask_data.dims, shape=self.shape)
534 return self._dims
File ~\AppData\Roaming\Python\Python39\site-packages\aicsimageio\readers\reader.py:359, in Reader.xarray_dask_data(self)
352 """
353 Returns
354 -------
355 xarray_dask_data: xr.DataArray
356 The delayed image and metadata as an annotated data array.
357 """
358 if self._xarray_dask_data is None:
--> 359 self._xarray_dask_data = self._read_delayed()
361 return self._xarray_dask_data
File ~\AppData\Roaming\Python\Python39\site-packages\aicsimageio\readers\bioformats_reader.py:164, in BioformatsReader._read_delayed(self)
163 def _read_delayed(self) -> xr.DataArray:
--> 164 return self._to_xarray(delayed=True)
File ~\AppData\Roaming\Python\Python39\site-packages\aicsimageio\readers\bioformats_reader.py:202, in BioformatsReader._to_xarray(self, delayed)
195 with BioFile(
196 self._path,
197 series=self.current_scene_index,
198 **self._bf_kwargs, # type: ignore
199 ) as rdr:
200 image_data = rdr.to_dask() if delayed else rdr.to_numpy()
201 _, coords = metadata_utils.get_dims_and_coords_from_ome(
--> 202 ome=rdr.ome_metadata,
203 scene_index=self.current_scene_index,
204 )
206 return xr.DataArray(
207 image_data,
208 dims=dimensions.DEFAULT_DIMENSION_ORDER_LIST_WITH_SAMPLES
(...)
215 },
216 )
File ~\AppData\Roaming\Python\Python39\site-packages\aicsimageio\readers\bioformats_reader.py:447, in BioFile.ome_metadata(self)
445 """Return OME object parsed by ome_types."""
446 xml = metadata_utils.clean_ome_xml_for_known_issues(self.ome_xml)
--> 447 return OME.from_xml(xml)
File ~\AppData\Roaming\Python\Python39\site-packages\ome_types\model\ome.py:154, in OME.from_xml(cls, xml)
150 @classmethod
151 def from_xml(cls, xml: Union[Path, str]) -> "OME":
152 from ome_types import from_xml
--> 154 return from_xml(xml)
File ~\AppData\Roaming\Python\Python39\site-packages\ome_types\_convenience.py:105, in from_xml(xml, parser, validate)
79 def from_xml(
80 xml: Union[Path, str, bytes],
81 *,
82 parser: Union[Parser, str, None] = None,
83 validate: Optional[bool] = None,
84 ) -> OME:
85 """Generate OME metadata object from XML string or path.
86
87 Parameters
(...)
103 ome_types.OME metadata object
104 """
--> 105 d = to_dict(os.fspath(xml), parser=parser, validate=validate)
106 return OME(**d)
File ~\AppData\Roaming\Python\Python39\site-packages\ome_types\_convenience.py:72, in to_dict(xml, parser, validate)
69 else:
70 raise KeyError("parser string must be one of {'lxml', 'xmlschema'}")
---> 72 d = parser(xml) if validate is None else parser(xml, validate=validate)
73 for key in list(d.keys()):
74 if key.startswith(("xml", "xsi")):
File ~\AppData\Roaming\Python\Python39\site-packages\ome_types\_xmlschema.py:231, in xmlschema2dict(xml, schema, converter, validate, **kwargs)
229 if validate:
230 schema = schema or get_schema(xml)
--> 231 result = xmlschema.to_dict(xml, schema=schema, converter=converter, **kwargs)
232 # xmlschema doesn't provide usable access to mixed XML content, so we'll
233 # fill the XMLAnnotation value attributes ourselves by re-parsing the XML
234 # with ElementTree and using the Element objects as the values.
235 tree = None
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\documents.py:289, in to_dict(xml_document, schema, cls, path, validation, process_namespaces, locations, base_url, defuse, timeout, lazy, **kwargs)
277 """
278 Decodes an XML document to a Python's nested dictionary. Takes the same arguments
279 of the function :meth:`iter_decode`, but *validation* mode defaults to 'strict'.
(...)
284 ``validation='strict'`` is provided.
285 """
286 source, _schema = get_context(
287 xml_document, schema, cls, locations, base_url, defuse, timeout, lazy
288 )
--> 289 return _schema.decode(source, path=path, validation=validation,
290 process_namespaces=process_namespaces, **kwargs)
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\schemas.py:2015, in XMLSchemaBase.decode(self, source, path, schema_path, validation, *args, **kwargs)
2011 """
2012 Decodes XML data. Takes the same arguments of the method :meth:`iter_decode`.
2013 """
2014 data, errors = [], []
-> 2015 for result in self.iter_decode(source, path, schema_path, validation, *args, **kwargs):
2016 if not isinstance(result, XMLSchemaValidationError):
2017 data.append(result)
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\schemas.py:2001, in XMLSchemaBase.iter_decode(self, source, path, schema_path, validation, process_namespaces, namespaces, use_defaults, decimal_type, datetime_types, binary_types, converter, filler, fill_missing, keep_unknown, process_skipped, max_depth, depth_filler, value_hook, **kwargs)
1998 yield schema.validation_error(validation, reason, elem, resource, namespaces)
1999 return
-> 2001 yield from xsd_element.iter_decode(elem, validation, **kwargs)
2003 if 'max_depth' not in kwargs:
2004 yield from self._validate_references(validation=validation, **kwargs)
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\elements.py:733, in XsdElement.iter_decode(self, obj, validation, **kwargs)
730 for error in assertion(obj, **kwargs):
731 yield self.validation_error(validation, error, **kwargs)
--> 733 for result in content_decoder.iter_decode(obj, validation, **kwargs):
734 if isinstance(result, XMLSchemaValidationError):
735 yield self.validation_error(validation, result, obj, **kwargs)
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\groups.py:1073, in XsdGroup.iter_decode(self, obj, validation, **kwargs)
1070 result_list.append((child.tag, func(xsd_element), xsd_element))
1071 continue
-> 1073 for result in xsd_element.iter_decode(child, validation, **kwargs):
1074 if isinstance(result, XMLSchemaValidationError):
1075 yield result
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\elements.py:733, in XsdElement.iter_decode(self, obj, validation, **kwargs)
730 for error in assertion(obj, **kwargs):
731 yield self.validation_error(validation, error, **kwargs)
--> 733 for result in content_decoder.iter_decode(obj, validation, **kwargs):
734 if isinstance(result, XMLSchemaValidationError):
735 yield self.validation_error(validation, result, obj, **kwargs)
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\groups.py:1073, in XsdGroup.iter_decode(self, obj, validation, **kwargs)
1070 result_list.append((child.tag, func(xsd_element), xsd_element))
1071 continue
-> 1073 for result in xsd_element.iter_decode(child, validation, **kwargs):
1074 if isinstance(result, XMLSchemaValidationError):
1075 yield result
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\elements.py:689, in XsdElement.iter_decode(self, obj, validation, **kwargs)
687 for result in attribute_group.iter_decode(obj.attrib, validation, **kwargs):
688 if isinstance(result, XMLSchemaValidationError):
--> 689 yield self.validation_error(validation, result, obj, **kwargs)
690 else:
691 attributes = result
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\xsdbase.py:227, in XsdValidator.validation_error(self, validation, error, obj, source, namespaces, **_kwargs)
224 error = XMLSchemaValidationError(self, obj, error, source, namespaces)
226 if validation == 'strict' and error.elem is not None:
--> 227 raise error
228 return error
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\simple_types.py:1388, in XsdAtomicRestriction.iter_decode(self, obj, validation, **kwargs)
1386 if not isinstance(self.primitive_type, XsdUnion):
1387 try:
-> 1388 self.patterns(obj)
1389 except XMLSchemaValidationError as err:
1390 yield err
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\facets.py:726, in XsdPatternFacets.__call__(self, text)
724 if all(pattern.match(text) is None for pattern in self.patterns):
725 reason = _("value doesn't match any pattern of {!r}").format(self.regexps)
--> 726 raise XMLSchemaValidationError(self, text, reason)
727 except TypeError as err:
728 raise XMLSchemaValidationError(self, text, str(err)) from None
XMLSchemaValidationError: failed validating 'XMLAnnotation:0' with XsdPatternFacets(['(urn:lsid:([\\w\\-\\.]+\\.[\\w\\-\\.]+)+:Annotation:\\S+)|(Annotatio...']):
Reason: attribute ID='XMLAnnotation:0': value doesn't match any pattern of ['(urn:lsid:([\\w\\-\\.]+\\.[\\w\\-\\.]+)+:Annotation:\\S+)|(Annotation:\\S+)']
Schema:
<xsd:pattern xmlns:xsd="http://www.w3.org/2001/XMLSchema" value="(urn:lsid:([\w\-\.]+\.[\w\-\.]+)+:Annotation:\S+)|(Annotation:\S+)" />
Instance:
<XMLAnnotation xmlns="http://www.openmicroscopy.org/Schemas/OME/2016-06" ID="XMLAnnotation:0"><Value><SpimData version="0.2">
<BasePath type="relative">.</BasePath>
<SequenceDescription>
<ImageLoader format="bdv.hdf5">
<hdf5 type="relative">xyzct_16bit__mitosis.h5</hdf5>
</ImageLoader>
<ViewSetups>
<ViewSetup>
<id>0</id>
<name>channel 1</name>
<size>171 196 5</size>
<voxelSize>
<unit>µm</unit>
<size>0.08850000022125 0.08850000022125 1.0</size>
</voxelSize>
<attributes>
<channel>1</channel>
</attributes>
</ViewSetup>
<ViewSetup>
...
...
</SpimData></Value></XMLAnnotation>
Path: /OME/StructuredAnnotations/XMLAnnotation
The same error appears when I try to acces image.data and image.metadata.
Expected Behavior
I am not sure if the problem is on the dataset side (XMLAnnotation error is raise), however I am able to open the dataset using python-bioformats directly and with the FIJI Bioformats importer.
I am aware of this previous issue, however I am not sure what should I do to solve my problem. I think I already have the latest version of aicsimageio?
Thank you so much for your help!
Reproduction
After downloading the xml/h5 dataset above, the error can be reproduced with:
from aicsimageio import AICSImage
from aicsimageio.readers import BioformatsReader
xmlfile = 'path-to-xml-file'
image = AICSImage(xmlfile, reader= BioformatsReader)
img = image.data
evamaxfield commented
Sorry to hear you are having an issue! Hopefully we can come up with a fix.
Pinging @tlambert03.
From my view this is a problem with the metadata of the dataset itself, but we have made changes to our metadata processing to allow for "common metadata problems" -- exactly like the mircomanager PR you linked. Do you know how this dataset was created?
grinic commented
Thanks @evamaxfield for the reply.
The dataset was created using FIJI: Plugins › BigDataViewer › Export Current Image as XML/HDF5.
I don't know the file format of the original dataset.
Some additional information that might be useful. I tried:
- open the xml/h5 dataset with
FIJI > Plugins > Bio-Formats > Bio-Formats Importer - save image as tif (it then retains all metadata)
- open the tif image and re-save it using
Plugins › BigDataViewer › Export Current Image as XML/HDF5
At this point, using
image = AICSImage(<tif-file>, reader=BioformatsReader)
print(image.data.shape)
print(image.physical_pixel_sizes)
works as expected. However:
image = AICSImage(<new-xml-h5-file>, reader=BioformatsReader)
print(image.data.shape)
print(image.physical_pixel_sizes)
generates the same XMLSchemaValidationError error as before.
I guess this suggests that the problem lies in the way AICSImage reads the output of BigDataViewer xml/h5 export?
tlambert03 commented
Yeah, looks like the issue here is that BigDataViewer is outputting xml that somehow doesn't validate against the OME schema. This is more of a problem with ome-types than aicsimageio. We've discussed having more graceful validation error handling there. I think I can probably get this one loading. Give me a few days and I'll try to release an update to ome-types that works here.
tlambert03 commented
the core problem here is that, somehow/somewhere, the XMLAnnotation is getting written with an ID of <XMLAnnotation ID="XMLAnnotation:0"> .... which does not validate against the AnnotationID regex of ((urn:lsid:([\w\-\.]+\.[\w\-\.]+)+:\S+:\S+)|(\S+:\S+)) & ((urn:lsid:([\w\-\.]+\.[\w\-\.]+)+:Annotation:\S+)|(Annotation:\S+)) (it appears that it should be Annotation:0)
I haven't been able to figure out exactly where in the process this is happening yet (i.e. whether it's in the big dataviewer exporter, or the java bioformats reader that merges the xml file with the hdf5 file). But at least it's clear what the problem is, and we could certainly special case this in clean_ome_xml_for_known_issues
tlambert03 commented
@ctrueden ... if I may bother/summon you :) Maybe you can help me figure this out?
Quick summary: When I load the BigDataViewer h5 file linked in the first post in Fiji with the Bioformats importer, i see this metadata:
note the id of the XMLAnnotation <XMLAnnotation ID="XMLAnnotation:0">, which doesn't validate against the AnnotationID regex in the OME model. The method dumping the xml is loci.formats.ome.OMEPyramidStore.dumpXML, but I haven't been able to determine exactly where in the inheritance chain the faulty id is getting written?
side-note, I will of course fix stuff on my end to fail more gracefully with minor problems like that... just curious if you had run into that ID before
tlambert03 commented
patch for this special case in #455
grinic commented
Thanks a lot for the quick help!
Now I get this new error (only pasting the last XMLSchemaValidationError). Seems like the <XMLAnnotation ID> is completely missing now:
XMLSchemaValidationError: failed validating {} with XsdAttributeGroup(['ID', 'Name', 'SamplesPerPixel', 'IlluminationType', 'PinholeSize', 'PinholeSizeUnit', 'AcquisitionMode', 'ContrastMethod', 'ExcitationWavelength', 'ExcitationWavelengthUnit', 'EmissionWavelength', 'EmissionWavelengthUnit', 'Fluor', 'NDFilter', 'PockelCellSetting', 'Color']):
Reason: missing required attribute 'ID'
Schema:
<xsd:complexType xmlns:xsd="http://www.w3.org/2001/XMLSchema">
<xsd:sequence>
<xsd:element ref="LightSourceSettings" minOccurs="0" maxOccurs="1" />
<xsd:element ref="DetectorSettings" minOccurs="0" maxOccurs="1" />
<xsd:element ref="FilterSetRef" minOccurs="0" maxOccurs="1" />
<xsd:element ref="AnnotationRef" minOccurs="0" maxOccurs="unbounded">
<xsd:annotation>
<xsd:appinfo>
<xsdfu>
<manytomany />
</xsdfu>
</xsd:appinfo>
</xsd:annotation>
</xsd:element>
<xsd:element ref="LightPath" minOccurs="0" maxOccurs="1" />
</xsd:sequence>
<xsd:attribute name="ID" use="required" type="ChannelID" />
<xsd:attribute name="Name" use="optional" type="xsd:string">
<xsd:annotation>
<xsd:documentation>
...
...
</xsd:complexType>
Instance:
<Channel xmlns="http://www.openmicroscopy.org/Schemas/OME/2016-06">
<id>1</id>
<name>1</name>
</Channel>
Path: /OME/StructuredAnnotations/XMLAnnotation/Value/SpimData/SequenceDescription/ViewSetups/Attributes/Channel[1]
Maybe I am doing something wrong? I installed following patch #455 using the fix-xmlannotation-id branch via:
pip install git+https://github.com/tlambert03/aicsimageio.git@fix-xmlannotation-id
tlambert03 commented
can you show me the exact code that precedes the error?
grinic commented
Sure, here it is:
---------------------------------------------------------------------------
XMLSchemaValidationError Traceback (most recent call last)
Cell In[3], line 1
----> 1 print(image2.data.shape)
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\aicsimageio\aics_image.py:529, in AICSImage.data(self)
516 @property
517 def data(self) -> np.ndarray:
518 """
519 Returns
520 -------
(...)
527 Recommended to use `dask_data` for large mosaic images.
528 """
--> 529 return self.xarray_data.data
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\aicsimageio\aics_image.py:469, in AICSImage.xarray_data(self)
453 """
454 Returns
455 -------
(...)
462 Recommended to use `xarray_dask_data` for large mosaic images.
463 """
464 if self._xarray_data is None:
465 if (
466 # Does the user want to get stitched mosaic
467 self._reconstruct_mosaic
468 # Does the data have a tile dim
--> 469 and dimensions.DimensionNames.MosaicTile in self.reader.dims.order
470 ):
471 try:
472 self._xarray_data = (
473 self._transform_data_array_to_aics_image_standard(
474 self.reader.mosaic_xarray_data
475 )
476 )
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\aicsimageio\readers\reader.py:532, in Reader.dims(self)
525 """
526 Returns
527 -------
528 dims: Dimensions
529 Object with the paired dimension names and their sizes.
530 """
531 if self._dims is None:
--> 532 self._dims = Dimensions(dims=self.xarray_dask_data.dims, shape=self.shape)
534 return self._dims
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\aicsimageio\readers\reader.py:359, in Reader.xarray_dask_data(self)
352 """
353 Returns
354 -------
355 xarray_dask_data: xr.DataArray
356 The delayed image and metadata as an annotated data array.
357 """
358 if self._xarray_dask_data is None:
--> 359 self._xarray_dask_data = self._read_delayed()
361 return self._xarray_dask_data
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\aicsimageio\readers\bioformats_reader.py:164, in BioformatsReader._read_delayed(self)
163 def _read_delayed(self) -> xr.DataArray:
--> 164 return self._to_xarray(delayed=True)
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\aicsimageio\readers\bioformats_reader.py:202, in BioformatsReader._to_xarray(self, delayed)
195 with BioFile(
196 self._path,
197 series=self.current_scene_index,
198 **self._bf_kwargs, # type: ignore
199 ) as rdr:
200 image_data = rdr.to_dask() if delayed else rdr.to_numpy()
201 _, coords = metadata_utils.get_dims_and_coords_from_ome(
--> 202 ome=rdr.ome_metadata,
203 scene_index=self.current_scene_index,
204 )
206 return xr.DataArray(
207 image_data,
208 dims=dimensions.DEFAULT_DIMENSION_ORDER_LIST_WITH_SAMPLES
(...)
215 },
216 )
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\aicsimageio\readers\bioformats_reader.py:447, in BioFile.ome_metadata(self)
445 """Return OME object parsed by ome_types."""
446 xml = metadata_utils.clean_ome_xml_for_known_issues(self.ome_xml)
--> 447 return OME.from_xml(xml)
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\ome_types\model\ome.py:154, in OME.from_xml(cls, xml)
150 @classmethod
151 def from_xml(cls, xml: Union[Path, str]) -> "OME":
152 from ome_types import from_xml
--> 154 return from_xml(xml)
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\ome_types\_convenience.py:105, in from_xml(xml, parser, validate)
79 def from_xml(
80 xml: Union[Path, str, bytes],
81 *,
82 parser: Union[Parser, str, None] = None,
83 validate: Optional[bool] = None,
84 ) -> OME:
85 """Generate OME metadata object from XML string or path.
86
87 Parameters
(...)
103 ome_types.OME metadata object
104 """
--> 105 d = to_dict(os.fspath(xml), parser=parser, validate=validate)
106 return OME(**d)
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\ome_types\_convenience.py:72, in to_dict(xml, parser, validate)
69 else:
70 raise KeyError("parser string must be one of {'lxml', 'xmlschema'}")
---> 72 d = parser(xml) if validate is None else parser(xml, validate=validate)
73 for key in list(d.keys()):
74 if key.startswith(("xml", "xsi")):
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\ome_types\_xmlschema.py:238, in xmlschema2dict(xml, schema, converter, validate, **kwargs)
235 if _XMLSCHEMA_VERSION >= (2,):
236 kwargs["validation"] = "strict" if validate else "lax"
--> 238 result = xmlschema.to_dict(xml, schema=schema, converter=converter, **kwargs)
240 if _XMLSCHEMA_VERSION >= (2,) and not validate:
241 result, _ = result
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\documents.py:289, in to_dict(xml_document, schema, cls, path, validation, process_namespaces, locations, base_url, defuse, timeout, lazy, **kwargs)
277 """
278 Decodes an XML document to a Python's nested dictionary. Takes the same arguments
279 of the function :meth:`iter_decode`, but *validation* mode defaults to 'strict'.
(...)
284 ``validation='strict'`` is provided.
285 """
286 source, _schema = get_context(
287 xml_document, schema, cls, locations, base_url, defuse, timeout, lazy
288 )
--> 289 return _schema.decode(source, path=path, validation=validation,
290 process_namespaces=process_namespaces, **kwargs)
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\schemas.py:2015, in XMLSchemaBase.decode(self, source, path, schema_path, validation, *args, **kwargs)
2011 """
2012 Decodes XML data. Takes the same arguments of the method :meth:`iter_decode`.
2013 """
2014 data, errors = [], []
-> 2015 for result in self.iter_decode(source, path, schema_path, validation, *args, **kwargs):
2016 if not isinstance(result, XMLSchemaValidationError):
2017 data.append(result)
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\schemas.py:2001, in XMLSchemaBase.iter_decode(self, source, path, schema_path, validation, process_namespaces, namespaces, use_defaults, decimal_type, datetime_types, binary_types, converter, filler, fill_missing, keep_unknown, process_skipped, max_depth, depth_filler, value_hook, **kwargs)
1998 yield schema.validation_error(validation, reason, elem, resource, namespaces)
1999 return
-> 2001 yield from xsd_element.iter_decode(elem, validation, **kwargs)
2003 if 'max_depth' not in kwargs:
2004 yield from self._validate_references(validation=validation, **kwargs)
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\elements.py:733, in XsdElement.iter_decode(self, obj, validation, **kwargs)
730 for error in assertion(obj, **kwargs):
731 yield self.validation_error(validation, error, **kwargs)
--> 733 for result in content_decoder.iter_decode(obj, validation, **kwargs):
734 if isinstance(result, XMLSchemaValidationError):
735 yield self.validation_error(validation, result, obj, **kwargs)
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\groups.py:1073, in XsdGroup.iter_decode(self, obj, validation, **kwargs)
1070 result_list.append((child.tag, func(xsd_element), xsd_element))
1071 continue
-> 1073 for result in xsd_element.iter_decode(child, validation, **kwargs):
1074 if isinstance(result, XMLSchemaValidationError):
1075 yield result
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\elements.py:733, in XsdElement.iter_decode(self, obj, validation, **kwargs)
730 for error in assertion(obj, **kwargs):
731 yield self.validation_error(validation, error, **kwargs)
--> 733 for result in content_decoder.iter_decode(obj, validation, **kwargs):
734 if isinstance(result, XMLSchemaValidationError):
735 yield self.validation_error(validation, result, obj, **kwargs)
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\groups.py:1073, in XsdGroup.iter_decode(self, obj, validation, **kwargs)
1070 result_list.append((child.tag, func(xsd_element), xsd_element))
1071 continue
-> 1073 for result in xsd_element.iter_decode(child, validation, **kwargs):
1074 if isinstance(result, XMLSchemaValidationError):
1075 yield result
[... skipping similar frames: XsdElement.iter_decode at line 733 (2 times), XsdGroup.iter_decode at line 1073 (2 times)]
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\wildcards.py:507, in XsdAnyElement.iter_decode(self, obj, validation, **kwargs)
505 if validation != 'skip' and self.process_contents == 'strict':
506 yield self.validation_error(validation, reason, obj, **kwargs)
--> 507 yield from self.any_type.iter_decode(obj, validation, **kwargs)
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\complex_types.py:740, in XsdComplexType.iter_decode(self, obj, validation, **kwargs)
738 xsd_element = self.schema.create_element(obj.tag, parent=self, form='unqualified')
739 xsd_element.type = self
--> 740 yield from xsd_element.iter_decode(obj, validation, **kwargs)
741 elif isinstance(self.content, XsdSimpleType):
742 yield from self.content.iter_decode(obj, validation, **kwargs)
[... skipping similar frames: XsdElement.iter_decode at line 733 (1 times), XsdGroup.iter_decode at line 1073 (1 times)]
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\wildcards.py:507, in XsdAnyElement.iter_decode(self, obj, validation, **kwargs)
505 if validation != 'skip' and self.process_contents == 'strict':
506 yield self.validation_error(validation, reason, obj, **kwargs)
--> 507 yield from self.any_type.iter_decode(obj, validation, **kwargs)
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\complex_types.py:740, in XsdComplexType.iter_decode(self, obj, validation, **kwargs)
738 xsd_element = self.schema.create_element(obj.tag, parent=self, form='unqualified')
739 xsd_element.type = self
--> 740 yield from xsd_element.iter_decode(obj, validation, **kwargs)
741 elif isinstance(self.content, XsdSimpleType):
742 yield from self.content.iter_decode(obj, validation, **kwargs)
[... skipping similar frames: XsdElement.iter_decode at line 733 (2 times), XsdGroup.iter_decode at line 1073 (2 times), XsdAnyElement.iter_decode at line 507 (1 times), XsdComplexType.iter_decode at line 740 (1 times)]
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\wildcards.py:507, in XsdAnyElement.iter_decode(self, obj, validation, **kwargs)
505 if validation != 'skip' and self.process_contents == 'strict':
506 yield self.validation_error(validation, reason, obj, **kwargs)
--> 507 yield from self.any_type.iter_decode(obj, validation, **kwargs)
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\complex_types.py:740, in XsdComplexType.iter_decode(self, obj, validation, **kwargs)
738 xsd_element = self.schema.create_element(obj.tag, parent=self, form='unqualified')
739 xsd_element.type = self
--> 740 yield from xsd_element.iter_decode(obj, validation, **kwargs)
741 elif isinstance(self.content, XsdSimpleType):
742 yield from self.content.iter_decode(obj, validation, **kwargs)
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\elements.py:733, in XsdElement.iter_decode(self, obj, validation, **kwargs)
730 for error in assertion(obj, **kwargs):
731 yield self.validation_error(validation, error, **kwargs)
--> 733 for result in content_decoder.iter_decode(obj, validation, **kwargs):
734 if isinstance(result, XMLSchemaValidationError):
735 yield self.validation_error(validation, result, obj, **kwargs)
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\groups.py:1073, in XsdGroup.iter_decode(self, obj, validation, **kwargs)
1070 result_list.append((child.tag, func(xsd_element), xsd_element))
1071 continue
-> 1073 for result in xsd_element.iter_decode(child, validation, **kwargs):
1074 if isinstance(result, XMLSchemaValidationError):
1075 yield result
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\wildcards.py:489, in XsdAnyElement.iter_decode(self, obj, validation, **kwargs)
487 reason = f"element {obj.tag!r} not found"
488 else:
--> 489 yield from xsd_element.iter_decode(obj, validation, **kwargs)
490 return
492 if XSI_TYPE in obj.attrib:
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\elements.py:689, in XsdElement.iter_decode(self, obj, validation, **kwargs)
687 for result in attribute_group.iter_decode(obj.attrib, validation, **kwargs):
688 if isinstance(result, XMLSchemaValidationError):
--> 689 yield self.validation_error(validation, result, obj, **kwargs)
690 else:
691 attributes = result
File ~\Anaconda3\envs\sk-nap-tut\lib\site-packages\xmlschema\validators\xsdbase.py:227, in XsdValidator.validation_error(self, validation, error, obj, source, namespaces, **_kwargs)
224 error = XMLSchemaValidationError(self, obj, error, source, namespaces)
226 if validation == 'strict' and error.elem is not None:
--> 227 raise error
228 return error
XMLSchemaValidationError: failed validating {} with XsdAttributeGroup(['ID', 'Name', 'SamplesPerPixel', 'IlluminationType', 'PinholeSize', 'PinholeSizeUnit', 'AcquisitionMode', 'ContrastMethod', 'ExcitationWavelength', 'ExcitationWavelengthUnit', 'EmissionWavelength', 'EmissionWavelengthUnit', 'Fluor', 'NDFilter', 'PockelCellSetting', 'Color']):
Reason: missing required attribute 'ID'
Schema:
<xsd:complexType xmlns:xsd="http://www.w3.org/2001/XMLSchema">
<xsd:sequence>
<xsd:element ref="LightSourceSettings" minOccurs="0" maxOccurs="1" />
<xsd:element ref="DetectorSettings" minOccurs="0" maxOccurs="1" />
<xsd:element ref="FilterSetRef" minOccurs="0" maxOccurs="1" />
<xsd:element ref="AnnotationRef" minOccurs="0" maxOccurs="unbounded">
<xsd:annotation>
<xsd:appinfo>
<xsdfu>
<manytomany />
</xsdfu>
</xsd:appinfo>
</xsd:annotation>
</xsd:element>
<xsd:element ref="LightPath" minOccurs="0" maxOccurs="1" />
</xsd:sequence>
<xsd:attribute name="ID" use="required" type="ChannelID" />
<xsd:attribute name="Name" use="optional" type="xsd:string">
<xsd:annotation>
<xsd:documentation>
...
...
</xsd:complexType>
Instance:
<Channel xmlns="http://www.openmicroscopy.org/Schemas/OME/2016-06">
<id>1</id>
<name>1</name>
</Channel>
Path: /OME/StructuredAnnotations/XMLAnnotation/Value/SpimData/SequenceDescription/ViewSetups/Attributes/Channel[1]
tlambert03 commented
sorry... I'm looking more for what image2 was. Like, which file did you open, (xml or h5), how did you open (bioformats reader vs aicsimage), etc... also can you give me the output of:
from aicsimageio.readers import BioformatsReader
BioformatsReader.bioformats_version()grinic commented
Ah, sorry I didn't get it.
I am opening the xml file that I posted in the first post, both xml and h5 files are in the same folder, with AICSImage:
from aicsimageio import AICSImage
from aicsimageio.readers import BioformatsReader
fname1 = 'test_dataset\\xyzct_16bit__mitosis.tif'
image1 = AICSImage(fname1, reader=BioformatsReader)
fname2 = 'test_dataset\\xyzct_16bit__mitosis.xml'
image2 = AICSImage(fname2, reader=BioformatsReader)
In this case, the tif file was generated opening the xml/h5 dataset with Bioformats Importer in FIJI and saving the dataset as tif.
print(image1.metadata) gives the expected result, while print(image2.metadata) gives the above error.
The output of the code:
from aicsimageio.readers import BioformatsReader
BioformatsReader.bioformats_version()
is:
'6.12.0-SNAPSHOT'
tlambert03 commented
huh... bummer, I can't reproduce. will need to try windows and python 3.9