sapiopycommons 2025.9.3a721__py3-none-any.whl → 2025.9.4a723__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of sapiopycommons might be problematic. Click here for more details.
- sapiopycommons/ai/tool_of_tools.py +917 -0
- sapiopycommons/callbacks/callback_util.py +26 -16
- sapiopycommons/eln/experiment_handler.py +12 -5
- sapiopycommons/files/assay_plate_reader.py +93 -0
- sapiopycommons/files/file_text_converter.py +207 -0
- sapiopycommons/flowcyto/flow_cyto.py +2 -24
- sapiopycommons/general/accession_service.py +2 -28
- sapiopycommons/multimodal/multimodal.py +2 -24
- sapiopycommons/recordmodel/record_handler.py +4 -0
- sapiopycommons/rules/eln_rule_handler.py +3 -0
- sapiopycommons/rules/on_save_rule_handler.py +3 -0
- sapiopycommons/webhook/webservice_handlers.py +1 -1
- {sapiopycommons-2025.9.3a721.dist-info → sapiopycommons-2025.9.4a723.dist-info}/METADATA +2 -2
- {sapiopycommons-2025.9.3a721.dist-info → sapiopycommons-2025.9.4a723.dist-info}/RECORD +16 -48
- sapiopycommons/ai/converter_service_base.py +0 -132
- sapiopycommons/ai/protoapi/fielddefinitions/fields_pb2.py +0 -43
- sapiopycommons/ai/protoapi/fielddefinitions/fields_pb2.pyi +0 -31
- sapiopycommons/ai/protoapi/fielddefinitions/fields_pb2_grpc.py +0 -24
- sapiopycommons/ai/protoapi/fielddefinitions/velox_field_def_pb2.py +0 -123
- sapiopycommons/ai/protoapi/fielddefinitions/velox_field_def_pb2.pyi +0 -598
- sapiopycommons/ai/protoapi/fielddefinitions/velox_field_def_pb2_grpc.py +0 -24
- sapiopycommons/ai/protoapi/plan/converter/converter_pb2.py +0 -51
- sapiopycommons/ai/protoapi/plan/converter/converter_pb2.pyi +0 -63
- sapiopycommons/ai/protoapi/plan/converter/converter_pb2_grpc.py +0 -149
- sapiopycommons/ai/protoapi/plan/item/item_container_pb2.py +0 -55
- sapiopycommons/ai/protoapi/plan/item/item_container_pb2.pyi +0 -90
- sapiopycommons/ai/protoapi/plan/item/item_container_pb2_grpc.py +0 -24
- sapiopycommons/ai/protoapi/plan/script/script_pb2.py +0 -59
- sapiopycommons/ai/protoapi/plan/script/script_pb2.pyi +0 -102
- sapiopycommons/ai/protoapi/plan/script/script_pb2_grpc.py +0 -153
- sapiopycommons/ai/protoapi/plan/step_output_pb2.py +0 -45
- sapiopycommons/ai/protoapi/plan/step_output_pb2.pyi +0 -42
- sapiopycommons/ai/protoapi/plan/step_output_pb2_grpc.py +0 -24
- sapiopycommons/ai/protoapi/plan/step_pb2.py +0 -43
- sapiopycommons/ai/protoapi/plan/step_pb2.pyi +0 -43
- sapiopycommons/ai/protoapi/plan/step_pb2_grpc.py +0 -24
- sapiopycommons/ai/protoapi/plan/tool/entry_pb2.py +0 -41
- sapiopycommons/ai/protoapi/plan/tool/entry_pb2.pyi +0 -35
- sapiopycommons/ai/protoapi/plan/tool/entry_pb2_grpc.py +0 -24
- sapiopycommons/ai/protoapi/plan/tool/tool_pb2.py +0 -75
- sapiopycommons/ai/protoapi/plan/tool/tool_pb2.pyi +0 -237
- sapiopycommons/ai/protoapi/plan/tool/tool_pb2_grpc.py +0 -154
- sapiopycommons/ai/protoapi/session/sapio_conn_info_pb2.py +0 -39
- sapiopycommons/ai/protoapi/session/sapio_conn_info_pb2.pyi +0 -32
- sapiopycommons/ai/protoapi/session/sapio_conn_info_pb2_grpc.py +0 -24
- sapiopycommons/ai/protobuf_utils.py +0 -504
- sapiopycommons/ai/server.py +0 -104
- sapiopycommons/ai/test_client.py +0 -356
- sapiopycommons/ai/tool_service_base.py +0 -951
- {sapiopycommons-2025.9.3a721.dist-info → sapiopycommons-2025.9.4a723.dist-info}/WHEEL +0 -0
- {sapiopycommons-2025.9.3a721.dist-info → sapiopycommons-2025.9.4a723.dist-info}/licenses/LICENSE +0 -0
|
@@ -1765,8 +1765,11 @@ class CallbackUtil:
|
|
|
1765
1765
|
blank_result_handling = BlankResultHandling.REPEAT
|
|
1766
1766
|
def not_blank_func(r: list[DataRecord]) -> bool:
|
|
1767
1767
|
return bool(r)
|
|
1768
|
-
|
|
1769
|
-
|
|
1768
|
+
response: list[DataRecord] = self.__send_dialog_blank_results(request,
|
|
1769
|
+
self.callback.show_input_selection_dialog,
|
|
1770
|
+
not_blank_func, blank_result_handling,
|
|
1771
|
+
repeat_message, cancel_message)
|
|
1772
|
+
return self.rec_handler.wrap_models(response, wrapper_type)
|
|
1770
1773
|
|
|
1771
1774
|
# FR-47690: Deprecated the require_authentication parameter.
|
|
1772
1775
|
# noinspection PyUnusedLocal
|
|
@@ -1812,7 +1815,8 @@ class CallbackUtil:
|
|
|
1812
1815
|
return response
|
|
1813
1816
|
|
|
1814
1817
|
def request_file(self, title: str, exts: Iterable[str] | None = None,
|
|
1815
|
-
show_image_editor: bool = False, show_camera_button: bool = False
|
|
1818
|
+
show_image_editor: bool = False, show_camera_button: bool = False,
|
|
1819
|
+
*, enforce_file_extensions: bool = True) -> tuple[str, bytes]:
|
|
1816
1820
|
"""
|
|
1817
1821
|
Request a single file from the user.
|
|
1818
1822
|
|
|
@@ -1822,6 +1826,8 @@ class CallbackUtil:
|
|
|
1822
1826
|
:param show_image_editor: Whether the user will see an image editor when image is uploaded in this file prompt.
|
|
1823
1827
|
:param show_camera_button: Whether the user will be able to use camera to take a picture as an upload request,
|
|
1824
1828
|
rather than selecting an existing file.
|
|
1829
|
+
:param enforce_file_extensions: If true, then the file extensions provided in the exts parameter will be
|
|
1830
|
+
enforced. If false, then the user may upload any file type.
|
|
1825
1831
|
:return: The file name and bytes of the uploaded file.
|
|
1826
1832
|
"""
|
|
1827
1833
|
# If no extensions were provided, use an empty list for the extensions instead.
|
|
@@ -1841,11 +1847,12 @@ class CallbackUtil:
|
|
|
1841
1847
|
file_path: str = self.__send_dialog(request, self.callback.show_file_dialog, data_sink=do_consume)
|
|
1842
1848
|
|
|
1843
1849
|
# Verify that each of the file given matches the expected extension(s).
|
|
1844
|
-
self.__verify_file(file_path, sink.data, exts)
|
|
1850
|
+
self.__verify_file(file_path, sink.data, exts if enforce_file_extensions else None)
|
|
1845
1851
|
return file_path, sink.data
|
|
1846
1852
|
|
|
1847
1853
|
def request_files(self, title: str, exts: Iterable[str] | None = None,
|
|
1848
|
-
show_image_editor: bool = False, show_camera_button: bool = False
|
|
1854
|
+
show_image_editor: bool = False, show_camera_button: bool = False,
|
|
1855
|
+
*, enforce_file_extensions: bool = True) -> dict[str, bytes]:
|
|
1849
1856
|
"""
|
|
1850
1857
|
Request multiple files from the user.
|
|
1851
1858
|
|
|
@@ -1855,6 +1862,8 @@ class CallbackUtil:
|
|
|
1855
1862
|
:param show_image_editor: Whether the user will see an image editor when image is uploaded in this file prompt.
|
|
1856
1863
|
:param show_camera_button: Whether the user will be able to use camera to take a picture as an upload request,
|
|
1857
1864
|
rather than selecting an existing file.
|
|
1865
|
+
:param enforce_file_extensions: If true, then the file extensions provided in the exts parameter will be
|
|
1866
|
+
enforced. If false, then the user may upload any file type.
|
|
1858
1867
|
:return: A dictionary of file name to file bytes for each file the user uploaded.
|
|
1859
1868
|
"""
|
|
1860
1869
|
# If no extensions were provided, use an empty list for the extensions instead.
|
|
@@ -1870,7 +1879,7 @@ class CallbackUtil:
|
|
|
1870
1879
|
for file_path in file_paths:
|
|
1871
1880
|
sink = InMemoryRecordDataSink(self.user)
|
|
1872
1881
|
sink.consume_client_callback_file_path_data(file_path)
|
|
1873
|
-
self.__verify_file(file_path, sink.data, exts)
|
|
1882
|
+
self.__verify_file(file_path, sink.data, exts if enforce_file_extensions else None)
|
|
1874
1883
|
ret_dict.update({file_path: sink.data})
|
|
1875
1884
|
|
|
1876
1885
|
return ret_dict
|
|
@@ -1887,16 +1896,17 @@ class CallbackUtil:
|
|
|
1887
1896
|
"""
|
|
1888
1897
|
if file_path is None or len(file_path) == 0 or file_bytes is None or len(file_bytes) == 0:
|
|
1889
1898
|
raise SapioUserErrorException("Empty file provided or file unable to be read.")
|
|
1890
|
-
if allowed_extensions:
|
|
1891
|
-
|
|
1892
|
-
|
|
1893
|
-
|
|
1894
|
-
|
|
1895
|
-
|
|
1896
|
-
|
|
1897
|
-
|
|
1898
|
-
|
|
1899
|
-
|
|
1899
|
+
if not allowed_extensions:
|
|
1900
|
+
return
|
|
1901
|
+
matches: bool = False
|
|
1902
|
+
for ext in allowed_extensions:
|
|
1903
|
+
# FR-47690: Changed to a case-insensitive match.
|
|
1904
|
+
if file_path.casefold().endswith("." + ext.lstrip(".").casefold()):
|
|
1905
|
+
matches = True
|
|
1906
|
+
break
|
|
1907
|
+
if not matches:
|
|
1908
|
+
raise SapioUserErrorException("Unsupported file type. Expecting the following extension(s): "
|
|
1909
|
+
+ (",".join(allowed_extensions)))
|
|
1900
1910
|
|
|
1901
1911
|
def write_file(self, file_name: str, file_data: str | bytes) -> None:
|
|
1902
1912
|
"""
|
|
@@ -206,12 +206,11 @@ class ExperimentHandler:
|
|
|
206
206
|
else:
|
|
207
207
|
user = context
|
|
208
208
|
context = None
|
|
209
|
-
if context is not None and context.eln_experiment is not None and experiment is None:
|
|
210
|
-
experiment = context.eln_experiment
|
|
211
209
|
# FR-46495 - Allow the init function of ExperimentHandler to take in an ElnExperiment that is separate from the
|
|
212
210
|
# context.
|
|
213
211
|
# CR-37038 - Allow other experiment object types to be provided. Convert them all down to ElnExperiment.
|
|
214
|
-
|
|
212
|
+
# PR-47793 - Fix cases where both a SapioWebhookContext and an experiment parameter are provided.
|
|
213
|
+
if experiment is not None:
|
|
215
214
|
eln_manager = DataMgmtServer.get_eln_manager(user)
|
|
216
215
|
# If this object is already an ElnExperiment, do nothing.
|
|
217
216
|
if isinstance(experiment, ElnExperiment):
|
|
@@ -227,13 +226,19 @@ class ExperimentHandler:
|
|
|
227
226
|
raise SapioException(f"No experiment with notebook ID {notebook_id} located in the system.")
|
|
228
227
|
# If this object is a record, assume it is an experiment record that we can query the system with.
|
|
229
228
|
else:
|
|
230
|
-
record_id: int = AliasUtil.
|
|
229
|
+
record_id: int = AliasUtil.to_record_id(experiment)
|
|
231
230
|
experiment: ElnExperiment = eln_manager.get_eln_experiment_by_record_id(record_id)
|
|
232
231
|
if not experiment:
|
|
233
232
|
raise SapioException(f"No experiment with record ID {record_id} located in the system.")
|
|
233
|
+
elif context is not None and context.eln_experiment is not None:
|
|
234
|
+
experiment = context.eln_experiment
|
|
235
|
+
|
|
234
236
|
if experiment is None:
|
|
235
237
|
raise SapioException("Cannot initialize ExperimentHandler. No ELN Experiment found in the provided "
|
|
236
238
|
"parameters.")
|
|
239
|
+
elif not isinstance(experiment, ElnExperiment):
|
|
240
|
+
raise SapioException("Cannot initialize ExperimentHandler. The experiment variable is not an "
|
|
241
|
+
"ElnExperiment!")
|
|
237
242
|
|
|
238
243
|
return user, context, experiment
|
|
239
244
|
|
|
@@ -1425,7 +1430,9 @@ class ExperimentHandler:
|
|
|
1425
1430
|
:return: The map of options for the input step.
|
|
1426
1431
|
"""
|
|
1427
1432
|
step: ElnEntryStep = self.get_step(step)
|
|
1428
|
-
|
|
1433
|
+
# PR-47796: Fix the get_step_options function making a webservice query every time it is called instead of
|
|
1434
|
+
# properly checking its cache of entry options.
|
|
1435
|
+
if step.get_id() not in self._step_options:
|
|
1429
1436
|
self._step_options.update(ExperimentReportUtil.get_experiment_entry_options(self.user,
|
|
1430
1437
|
self.get_all_steps()))
|
|
1431
1438
|
return self._step_options[step.get_id()]
|
|
@@ -0,0 +1,93 @@
|
|
|
1
|
+
import base64
|
|
2
|
+
import dataclasses
|
|
3
|
+
from typing import Any
|
|
4
|
+
|
|
5
|
+
from databind.core.dataclasses import dataclass
|
|
6
|
+
from databind.json import loads
|
|
7
|
+
from sapiopylib.rest.utils.singletons import SapioContextManager
|
|
8
|
+
|
|
9
|
+
|
|
10
|
+
@dataclasses.dataclass
|
|
11
|
+
class ProcessAssayPlateRequest:
|
|
12
|
+
"""
|
|
13
|
+
A request to process the results of assay plate reader with a configuration set in Sapio.
|
|
14
|
+
|
|
15
|
+
Attributes:
|
|
16
|
+
num_rows (int): The number of rows in the plate.
|
|
17
|
+
num_columns (int): The number of columns in the plate.
|
|
18
|
+
plate_ids_in_context (list[str]): List of plate IDs that are in context for this request.
|
|
19
|
+
filename (str): The name of the file containing the assay data.
|
|
20
|
+
file_data (bytes): The binary content of the file.
|
|
21
|
+
plate_reader_config_name (str): The name of the plate reader configuration to use.
|
|
22
|
+
"""
|
|
23
|
+
num_rows: int
|
|
24
|
+
num_columns: int
|
|
25
|
+
plate_ids_in_context: list[str] | None
|
|
26
|
+
filename: str
|
|
27
|
+
file_data: bytes
|
|
28
|
+
plate_reader_config_name: str
|
|
29
|
+
|
|
30
|
+
def to_json(self) -> dict[str, Any]:
|
|
31
|
+
return {
|
|
32
|
+
"numRows": self.num_rows,
|
|
33
|
+
"numCols": self.num_columns,
|
|
34
|
+
"plateIdsInContext": self.plate_ids_in_context,
|
|
35
|
+
"fileName": self.filename,
|
|
36
|
+
"fileDataBase64": base64.b64encode(self.file_data).decode('utf-8'),
|
|
37
|
+
"plateReaderName": self.plate_reader_config_name
|
|
38
|
+
}
|
|
39
|
+
|
|
40
|
+
|
|
41
|
+
@dataclass
|
|
42
|
+
class AssayPlateResultIdent:
|
|
43
|
+
plateId: str
|
|
44
|
+
channelIdOrBlock: str
|
|
45
|
+
kineticAssaySeconds: float | None
|
|
46
|
+
|
|
47
|
+
|
|
48
|
+
@dataclass
|
|
49
|
+
class AssayResultDatum:
|
|
50
|
+
"""
|
|
51
|
+
Describes the data received from an assay plate reader.
|
|
52
|
+
Most of the time, the data is a single value, but sometimes it can be multiple values, especially for kinetic data.
|
|
53
|
+
"""
|
|
54
|
+
DEFAULT_PROPERTY_NAME: str = "read"
|
|
55
|
+
rowPosition: str
|
|
56
|
+
columnPosition: str
|
|
57
|
+
valueByPropertyName: dict[str, float]
|
|
58
|
+
textValueByPropertyName: dict[str, str]
|
|
59
|
+
|
|
60
|
+
|
|
61
|
+
@dataclass
|
|
62
|
+
class AssayPlateResult:
|
|
63
|
+
"""
|
|
64
|
+
Assay plate load result for a single plate in a file. A file can have more than one of this result if it has multiple plate of data in a single file.
|
|
65
|
+
"""
|
|
66
|
+
resultIdent: AssayPlateResultIdent
|
|
67
|
+
numRows: int
|
|
68
|
+
numColumns: int
|
|
69
|
+
resultDatum: list[AssayResultDatum]
|
|
70
|
+
|
|
71
|
+
|
|
72
|
+
@dataclass
|
|
73
|
+
class AssayFileLoadResult:
|
|
74
|
+
"""
|
|
75
|
+
The entire top-level file loading result for an assay plate reader file.
|
|
76
|
+
"""
|
|
77
|
+
filename: str
|
|
78
|
+
plateResultList: list[AssayPlateResult]
|
|
79
|
+
|
|
80
|
+
|
|
81
|
+
class AssayPlateReader(SapioContextManager):
|
|
82
|
+
"""
|
|
83
|
+
This class contains services for Sapio Assay Plate Reader.
|
|
84
|
+
"""
|
|
85
|
+
|
|
86
|
+
def process_plate_reader_data(self, request: ProcessAssayPlateRequest) -> AssayFileLoadResult:
|
|
87
|
+
"""
|
|
88
|
+
Processes the assay plate reader data using provided request into a structured result using configuration defined in Sapio.
|
|
89
|
+
"""
|
|
90
|
+
payload = request.to_json()
|
|
91
|
+
response = self.user.plugin_post("assayplatereader/process", payload=payload)
|
|
92
|
+
self.user.raise_for_status(response)
|
|
93
|
+
return loads(response.text, AssayFileLoadResult)
|
|
@@ -0,0 +1,207 @@
|
|
|
1
|
+
import io
|
|
2
|
+
import os
|
|
3
|
+
import tempfile
|
|
4
|
+
from enum import Enum, auto
|
|
5
|
+
|
|
6
|
+
class FileType(Enum):
|
|
7
|
+
"""Supported file types for conversion."""
|
|
8
|
+
TXT = auto()
|
|
9
|
+
MD = auto()
|
|
10
|
+
CSV = auto()
|
|
11
|
+
DOC = auto()
|
|
12
|
+
DOCX = auto()
|
|
13
|
+
XLS = auto()
|
|
14
|
+
XLSX = auto()
|
|
15
|
+
PPT = auto()
|
|
16
|
+
PPTX = auto()
|
|
17
|
+
PDF = auto()
|
|
18
|
+
UNKNOWN = auto()
|
|
19
|
+
|
|
20
|
+
|
|
21
|
+
class FileToTextConverter:
|
|
22
|
+
"""
|
|
23
|
+
A class for converting various file types to raw text.
|
|
24
|
+
"""
|
|
25
|
+
@staticmethod
|
|
26
|
+
def mime_type_to_enum(mime_type: str) -> FileType:
|
|
27
|
+
"""
|
|
28
|
+
Converts a MIME type to a FileType enum.
|
|
29
|
+
|
|
30
|
+
:param mime_type: The MIME type string to convert.
|
|
31
|
+
:return: The corresponding FileType enum, or UNKNOWN if not recognized.
|
|
32
|
+
"""
|
|
33
|
+
if not mime_type or not mime_type.strip():
|
|
34
|
+
return FileType.UNKNOWN
|
|
35
|
+
|
|
36
|
+
mime_map = {
|
|
37
|
+
"text/plain": FileType.TXT,
|
|
38
|
+
"text/markdown": FileType.MD,
|
|
39
|
+
"text/csv": FileType.CSV,
|
|
40
|
+
"application/msword": FileType.DOC,
|
|
41
|
+
"application/vnd.openxmlformats-officedocument.wordprocessingml.document": FileType.DOCX,
|
|
42
|
+
"application/vnd.ms-excel": FileType.XLS,
|
|
43
|
+
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet": FileType.XLSX,
|
|
44
|
+
"application/vnd.ms-powerpoint": FileType.PPT,
|
|
45
|
+
"application/vnd.openxmlformats-officedocument.presentationml.presentation": FileType.PPTX,
|
|
46
|
+
"application/pdf": FileType.PDF,
|
|
47
|
+
}
|
|
48
|
+
return mime_map.get(mime_type, FileType.UNKNOWN)
|
|
49
|
+
|
|
50
|
+
@staticmethod
|
|
51
|
+
def file_extension_to_enum(file_path: str) -> FileType:
|
|
52
|
+
"""
|
|
53
|
+
Converts a file path or extension to a FileType enum.
|
|
54
|
+
|
|
55
|
+
:param file_path: The file path or extension to convert.
|
|
56
|
+
:return: The corresponding FileType enum, or UNKNOWN if not recognized.
|
|
57
|
+
"""
|
|
58
|
+
if not file_path or not file_path.strip():
|
|
59
|
+
return FileType.UNKNOWN
|
|
60
|
+
|
|
61
|
+
# Extract the file extension, removing the leading dot and making it lowercase
|
|
62
|
+
file_extension = os.path.splitext(file_path)[1].lstrip('.').lower()
|
|
63
|
+
|
|
64
|
+
ext_map = {
|
|
65
|
+
"txt": FileType.TXT,
|
|
66
|
+
"md": FileType.MD,
|
|
67
|
+
"csv": FileType.CSV,
|
|
68
|
+
"doc": FileType.DOC,
|
|
69
|
+
"docx": FileType.DOCX,
|
|
70
|
+
"xls": FileType.XLS,
|
|
71
|
+
"xlsx": FileType.XLSX,
|
|
72
|
+
"ppt": FileType.PPT,
|
|
73
|
+
"pptx": FileType.PPTX,
|
|
74
|
+
"pdf": FileType.PDF,
|
|
75
|
+
}
|
|
76
|
+
return ext_map.get(file_extension, FileType.UNKNOWN)
|
|
77
|
+
|
|
78
|
+
@classmethod
|
|
79
|
+
def parse_file(cls, file_type: FileType, file_bytes: bytes) -> str | None:
|
|
80
|
+
"""
|
|
81
|
+
Parses file bytes based on the FileType and returns the text content.
|
|
82
|
+
|
|
83
|
+
:param file_type: The type of the file to parse.
|
|
84
|
+
:param file_bytes: The raw bytes of the file to parse.
|
|
85
|
+
:return: The text content of the file, or None if the file type is not supported or parsing fails.
|
|
86
|
+
"""
|
|
87
|
+
if file_type is None or file_bytes is None:
|
|
88
|
+
return None
|
|
89
|
+
if not file_bytes:
|
|
90
|
+
return ""
|
|
91
|
+
|
|
92
|
+
# Dispatch to the correct parser method
|
|
93
|
+
parser_map = {
|
|
94
|
+
FileType.TXT: cls._parse_plain_text,
|
|
95
|
+
FileType.MD: cls._parse_plain_text,
|
|
96
|
+
FileType.CSV: cls._parse_plain_text,
|
|
97
|
+
FileType.DOC: cls._parse_doc,
|
|
98
|
+
FileType.DOCX: cls._parse_docx,
|
|
99
|
+
FileType.XLS: cls._parse_xls,
|
|
100
|
+
FileType.XLSX: cls._parse_xlsx,
|
|
101
|
+
FileType.PPT: cls._parse_ppt,
|
|
102
|
+
FileType.PPTX: cls._parse_pptx,
|
|
103
|
+
FileType.PDF: cls._parse_pdf,
|
|
104
|
+
}
|
|
105
|
+
|
|
106
|
+
parser_func = parser_map.get(file_type)
|
|
107
|
+
|
|
108
|
+
if parser_func:
|
|
109
|
+
return parser_func(file_bytes)
|
|
110
|
+
|
|
111
|
+
return None
|
|
112
|
+
|
|
113
|
+
@staticmethod
|
|
114
|
+
def _parse_plain_text(file_bytes: bytes) -> str:
|
|
115
|
+
return file_bytes.decode('utf-8')
|
|
116
|
+
|
|
117
|
+
@staticmethod
|
|
118
|
+
def _run_textract(file_bytes: bytes, extension: str) -> str:
|
|
119
|
+
"""
|
|
120
|
+
Helper to run textract on in-memory bytes by writing to a temp file.
|
|
121
|
+
Note: textract may require external system dependencies.
|
|
122
|
+
"""
|
|
123
|
+
import textract
|
|
124
|
+
with tempfile.NamedTemporaryFile(suffix=f".{extension}", delete=True) as temp_file:
|
|
125
|
+
temp_file.write(file_bytes)
|
|
126
|
+
temp_file.flush() # Ensure all bytes are written to disk
|
|
127
|
+
text = textract.process(temp_file.name).decode('utf-8')
|
|
128
|
+
return text
|
|
129
|
+
|
|
130
|
+
@classmethod
|
|
131
|
+
def _parse_doc(cls, file_bytes: bytes) -> str:
|
|
132
|
+
return cls._run_textract(file_bytes, 'doc')
|
|
133
|
+
|
|
134
|
+
@staticmethod
|
|
135
|
+
def _parse_docx(file_bytes: bytes) -> str:
|
|
136
|
+
import docx
|
|
137
|
+
with io.BytesIO(file_bytes) as stream:
|
|
138
|
+
document = docx.Document(stream)
|
|
139
|
+
return "\n".join(para.text for para in document.paragraphs if para.text.strip())
|
|
140
|
+
|
|
141
|
+
@staticmethod
|
|
142
|
+
def _parse_xls(file_bytes: bytes) -> str:
|
|
143
|
+
import xlrd
|
|
144
|
+
workbook = xlrd.open_workbook(file_contents=file_bytes)
|
|
145
|
+
text_parts = []
|
|
146
|
+
for sheet in workbook.sheets():
|
|
147
|
+
text_parts.append(f"Sheet: {sheet.name}\n")
|
|
148
|
+
for row_idx in range(sheet.nrows):
|
|
149
|
+
row_cells = []
|
|
150
|
+
for col_idx in range(sheet.ncols):
|
|
151
|
+
cell_text = str(sheet.cell_value(row_idx, col_idx))
|
|
152
|
+
if cell_text.strip():
|
|
153
|
+
row_cells.append(cell_text + "\t")
|
|
154
|
+
if row_cells:
|
|
155
|
+
text_parts.append("".join(row_cells))
|
|
156
|
+
text_parts.append("\n")
|
|
157
|
+
text_parts.append("\n")
|
|
158
|
+
return "".join(text_parts)
|
|
159
|
+
|
|
160
|
+
@staticmethod
|
|
161
|
+
def _parse_xlsx(file_bytes: bytes) -> str:
|
|
162
|
+
import openpyxl
|
|
163
|
+
with io.BytesIO(file_bytes) as stream:
|
|
164
|
+
workbook = openpyxl.load_workbook(stream, read_only=True)
|
|
165
|
+
text_parts = []
|
|
166
|
+
for sheet in workbook.worksheets:
|
|
167
|
+
text_parts.append(f"Sheet: {sheet.title}\n")
|
|
168
|
+
for row in sheet.iter_rows():
|
|
169
|
+
row_cells = []
|
|
170
|
+
for cell in row:
|
|
171
|
+
cell_text = str(cell.value) if cell.value is not None else ""
|
|
172
|
+
if cell_text.strip():
|
|
173
|
+
row_cells.append(cell_text + "\t")
|
|
174
|
+
if row_cells:
|
|
175
|
+
text_parts.append("".join(row_cells))
|
|
176
|
+
text_parts.append("\n")
|
|
177
|
+
text_parts.append("\n")
|
|
178
|
+
return "".join(text_parts)
|
|
179
|
+
|
|
180
|
+
@classmethod
|
|
181
|
+
def _parse_ppt(cls, file_bytes: bytes) -> str:
|
|
182
|
+
return cls._run_textract(file_bytes, 'ppt')
|
|
183
|
+
|
|
184
|
+
@staticmethod
|
|
185
|
+
def _parse_pptx(file_bytes: bytes) -> str:
|
|
186
|
+
import pptx
|
|
187
|
+
with io.BytesIO(file_bytes) as stream:
|
|
188
|
+
presentation = pptx.Presentation(stream)
|
|
189
|
+
text_parts = []
|
|
190
|
+
for slide in presentation.slides:
|
|
191
|
+
for shape in slide.shapes:
|
|
192
|
+
if shape.has_text_frame:
|
|
193
|
+
text = shape.text_frame.text
|
|
194
|
+
if text and text.strip():
|
|
195
|
+
text_parts.append(text)
|
|
196
|
+
return "\n".join(text_parts)
|
|
197
|
+
|
|
198
|
+
@staticmethod
|
|
199
|
+
def _parse_pdf(file_bytes: bytes) -> str:
|
|
200
|
+
"""Parses a PDF file's bytes and extracts text using PyMuPDF."""
|
|
201
|
+
import pymupdf
|
|
202
|
+
text_parts = []
|
|
203
|
+
with io.BytesIO(file_bytes) as stream:
|
|
204
|
+
with pymupdf.open(stream=stream) as doc:
|
|
205
|
+
for page in doc:
|
|
206
|
+
text_parts.append(page.get_text())
|
|
207
|
+
return "\n".join(text_parts)
|
|
@@ -4,38 +4,16 @@ from weakref import WeakValueDictionary
|
|
|
4
4
|
|
|
5
5
|
from databind.json import dumps
|
|
6
6
|
from sapiopylib.rest.User import SapioUser
|
|
7
|
+
from sapiopylib.rest.utils.singletons import SapioContextManager
|
|
7
8
|
|
|
8
9
|
from sapiopycommons.flowcyto.flowcyto_data import FlowJoWorkspaceInputJson, UploadFCSInputJson, \
|
|
9
10
|
ComputeFlowStatisticsInputJson
|
|
10
11
|
|
|
11
12
|
|
|
12
|
-
class FlowCytoManager:
|
|
13
|
+
class FlowCytoManager(SapioContextManager):
|
|
13
14
|
"""
|
|
14
15
|
This manager includes flow cytometry analysis tools that would require FlowCyto license to use.
|
|
15
16
|
"""
|
|
16
|
-
_user: SapioUser
|
|
17
|
-
|
|
18
|
-
__instances: WeakValueDictionary[SapioUser, FlowCytoManager] = WeakValueDictionary()
|
|
19
|
-
__initialized: bool
|
|
20
|
-
|
|
21
|
-
def __new__(cls, user: SapioUser):
|
|
22
|
-
"""
|
|
23
|
-
Observes singleton pattern per record model manager object.
|
|
24
|
-
|
|
25
|
-
:param user: The user that will make the webservice request to the application.
|
|
26
|
-
"""
|
|
27
|
-
obj = cls.__instances.get(user)
|
|
28
|
-
if not obj:
|
|
29
|
-
obj = object.__new__(cls)
|
|
30
|
-
obj.__initialized = False
|
|
31
|
-
cls.__instances[user] = obj
|
|
32
|
-
return obj
|
|
33
|
-
|
|
34
|
-
def __init__(self, user: SapioUser):
|
|
35
|
-
if self.__initialized:
|
|
36
|
-
return
|
|
37
|
-
self._user = user
|
|
38
|
-
self.__initialized = True
|
|
39
17
|
|
|
40
18
|
def create_flowjo_workspace(self, workspace_input: FlowJoWorkspaceInputJson) -> int:
|
|
41
19
|
"""
|
|
@@ -5,6 +5,7 @@ from typing import Any
|
|
|
5
5
|
from weakref import WeakValueDictionary
|
|
6
6
|
|
|
7
7
|
from sapiopylib.rest.User import SapioUser
|
|
8
|
+
from sapiopylib.rest.utils.singletons import SapioContextManager
|
|
8
9
|
|
|
9
10
|
_STR_JAVA_TYPE = "java.lang.String"
|
|
10
11
|
_INT_JAVA_TYPE = "java.lang.Integer"
|
|
@@ -274,37 +275,10 @@ class AccessionServiceDescriptor:
|
|
|
274
275
|
}
|
|
275
276
|
|
|
276
277
|
|
|
277
|
-
class AccessionService:
|
|
278
|
+
class AccessionService(SapioContextManager):
|
|
278
279
|
"""
|
|
279
280
|
Provides Sapio Foundations Accession Service functionalities.
|
|
280
281
|
"""
|
|
281
|
-
_user: SapioUser
|
|
282
|
-
|
|
283
|
-
__instances: WeakValueDictionary[SapioUser, AccessionService] = WeakValueDictionary()
|
|
284
|
-
__initialized: bool
|
|
285
|
-
|
|
286
|
-
@property
|
|
287
|
-
def user(self) -> SapioUser:
|
|
288
|
-
return self._user
|
|
289
|
-
|
|
290
|
-
def __new__(cls, user: SapioUser):
|
|
291
|
-
"""
|
|
292
|
-
Observes singleton pattern per record model manager object.
|
|
293
|
-
|
|
294
|
-
:param user: The user that will make the webservice request to the application.
|
|
295
|
-
"""
|
|
296
|
-
obj = cls.__instances.get(user)
|
|
297
|
-
if not obj:
|
|
298
|
-
obj = object.__new__(cls)
|
|
299
|
-
obj.__initialized = False
|
|
300
|
-
cls.__instances[user] = obj
|
|
301
|
-
return obj
|
|
302
|
-
|
|
303
|
-
def __init__(self, user: SapioUser):
|
|
304
|
-
if self.__initialized:
|
|
305
|
-
return
|
|
306
|
-
self._user = user
|
|
307
|
-
self.__initialized = True
|
|
308
282
|
|
|
309
283
|
def accession_with_config(self, data_type_name: str, data_field_name: str, num_ids: int) -> list[str]:
|
|
310
284
|
"""
|
|
@@ -7,35 +7,13 @@ from weakref import WeakValueDictionary
|
|
|
7
7
|
from databind.json import dumps, loads
|
|
8
8
|
from sapiopylib.rest.User import SapioUser
|
|
9
9
|
from sapiopylib.rest.pojo.DataRecord import DataRecord
|
|
10
|
+
from sapiopylib.rest.utils.singletons import SapioContextManager
|
|
10
11
|
|
|
11
12
|
from sapiopycommons.general.exceptions import SapioException
|
|
12
13
|
from sapiopycommons.multimodal.multimodal_data import *
|
|
13
14
|
|
|
14
15
|
|
|
15
|
-
class MultiModalManager:
|
|
16
|
-
_user: SapioUser
|
|
17
|
-
|
|
18
|
-
__instances: WeakValueDictionary[SapioUser, MultiModalManager] = WeakValueDictionary()
|
|
19
|
-
__initialized: bool
|
|
20
|
-
|
|
21
|
-
def __new__(cls, user: SapioUser):
|
|
22
|
-
"""
|
|
23
|
-
Observes singleton pattern per record model manager object.
|
|
24
|
-
|
|
25
|
-
:param user: The user that will make the webservice request to the application.
|
|
26
|
-
"""
|
|
27
|
-
obj = cls.__instances.get(user)
|
|
28
|
-
if not obj:
|
|
29
|
-
obj = object.__new__(cls)
|
|
30
|
-
obj.__initialized = False
|
|
31
|
-
cls.__instances[user] = obj
|
|
32
|
-
return obj
|
|
33
|
-
|
|
34
|
-
def __init__(self, user:SapioUser):
|
|
35
|
-
if self.__initialized:
|
|
36
|
-
return
|
|
37
|
-
self._user = user
|
|
38
|
-
self.__initialized = True
|
|
16
|
+
class MultiModalManager(SapioContextManager):
|
|
39
17
|
|
|
40
18
|
def load_image_data(self, request: ImageDataRequestPojo) -> list[str]:
|
|
41
19
|
"""
|
|
@@ -100,6 +100,10 @@ class RecordHandler:
|
|
|
100
100
|
PyRecordModel instead of a WrappedRecordModel.
|
|
101
101
|
:return: The record model for the input.
|
|
102
102
|
"""
|
|
103
|
+
# PR-47792: Set the wrapper_type to None if a str was provided instead of a type[WrappedType]. The type hints
|
|
104
|
+
# say this shouldn't be done anyway, but using this as a safeguard against user error.
|
|
105
|
+
if isinstance(wrapper_type, str):
|
|
106
|
+
wrapper_type = None
|
|
103
107
|
if wrapper_type is not None:
|
|
104
108
|
self.__verify_data_type(record, wrapper_type)
|
|
105
109
|
if isinstance(record, PyRecordModel):
|
|
@@ -184,4 +184,7 @@ class ElnRuleHandler:
|
|
|
184
184
|
instead of a model wrapper, then the returned records will be PyRecordModels instead of WrappedRecordModels.
|
|
185
185
|
"""
|
|
186
186
|
dt: str = AliasUtil.to_data_type_name(wrapper_type)
|
|
187
|
+
# PR-47792: Set the wrapper_type to None if a str was provided instead of a type[WrappedType].
|
|
188
|
+
if isinstance(wrapper_type, str):
|
|
189
|
+
wrapper_type = None
|
|
187
190
|
return self._rec_handler.wrap_models(self.get_records(dt, entry), wrapper_type)
|
|
@@ -180,4 +180,7 @@ class OnSaveRuleHandler:
|
|
|
180
180
|
instead of a model wrapper, then the returned records will be PyRecordModels instead of WrappedRecordModels.
|
|
181
181
|
"""
|
|
182
182
|
dt: str = AliasUtil.to_data_type_name(wrapper_type)
|
|
183
|
+
# PR-47792: Set the wrapper_type to None if a str was provided instead of a type[WrappedType].
|
|
184
|
+
if isinstance(wrapper_type, str):
|
|
185
|
+
wrapper_type = None
|
|
183
186
|
return self._rec_handler.wrap_models(self.get_records(dt, record_id), wrapper_type)
|
|
@@ -140,7 +140,7 @@ class AbstractWebserviceHandler(AbstractWebhookHandler):
|
|
|
140
140
|
# Get the login credentials from the headers.
|
|
141
141
|
auth: str = headers.get("Authorization")
|
|
142
142
|
if auth and auth.startswith("Basic "):
|
|
143
|
-
credentials: list[str] = b64decode(auth.split("Basic ")[1]).decode().split(":"
|
|
143
|
+
credentials: list[str] = b64decode(auth.split("Basic ")[1]).decode().split(":")
|
|
144
144
|
user = self.basic_auth(url, credentials[0], credentials[1])
|
|
145
145
|
elif auth and auth.startswith("Bearer "):
|
|
146
146
|
user = self.bearer_token_auth(url, auth.split("Bearer ")[1])
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.3
|
|
2
2
|
Name: sapiopycommons
|
|
3
|
-
Version: 2025.9.
|
|
3
|
+
Version: 2025.9.4a723
|
|
4
4
|
Summary: Official Sapio Python API Utilities Package
|
|
5
5
|
Project-URL: Homepage, https://github.com/sapiosciences
|
|
6
6
|
Author-email: Jonathan Steck <jsteck@sapiosciences.com>, Yechen Qiao <yqiao@sapiosciences.com>
|
|
@@ -17,7 +17,7 @@ Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
|
|
|
17
17
|
Classifier: Topic :: Software Development :: Libraries :: Python Modules
|
|
18
18
|
Requires-Python: >=3.10
|
|
19
19
|
Requires-Dist: databind>=4.5
|
|
20
|
-
Requires-Dist: sapiopylib>=2025.
|
|
20
|
+
Requires-Dist: sapiopylib>=2025.7.31a279
|
|
21
21
|
Description-Content-Type: text/markdown
|
|
22
22
|
|
|
23
23
|
|