[Feature] Package Pathway Export to CSV (#439)

Co-authored-by: Tim Lorsbach <tim@lorsba.ch>
Reviewed-on: enviPath/enviPy#439

epdb/legacy_api.py

@@ -46,6 +46,10 @@ from .models import (
 Package = s.GET_PACKAGE_MODEL()
 
 
+def get_package_for_read(user, package_uuid):
+    return PackageManager.get_package_by_id(user, package_uuid)
+
+
 def get_package_for_write(user, package_uuid):
     p = PackageManager.get_package_by_id(user, package_uuid)
     if not PackageManager.writable(user, p):
@@ -2291,3 +2295,38 @@ def predict(request, np: Form[NonPersistent]):
         return 403, {
             "message": f"Getting Setting with id {np.setting_url} failed due to insufficient rights!"
         }
+
+
+##########
+# Export #
+##########
+class PackageExportInSchema(Schema):
+    package_uuid: str
+    additional_information_types: List[str] | None = None
+
+
+@router.get("/export", response={200: Any, 403: Error})
+def export(request, q: Query[PackageExportInSchema]):
+    try:
+        p = get_package_for_read(request.user, q.package_uuid)
+
+        from envipy_additional_information import registry
+        from utilities.misc import PathwayExporter
+
+        ai_types = []
+        if q.additional_information_types is not None:
+            for ai_type in q.additional_information_types:
+                if registry.get_model(ai_type) is None:
+                    return 400, {
+                        "message": f"Exporting Package with id {q.package_uuid} failed as {ai_type} is not a valid additional information type!"
+                    }
+                ai_types.append(ai_type)
+
+        exporter = PathwayExporter(p, add_infs_to_export=ai_types)
+        res = exporter.do_export()
+
+        return res
+    except ValueError:
+        return 403, {
+            "message": f"Exporting Package with id {q.package_uuid} failed due to insufficient rights!"
+        }

templates/objects/node.html

@@ -139,7 +139,7 @@
                           </tr>
                           <tr>
                             <td>Model</td>
-                            <td>{{ half_lifes.0.model }}</td>
+                            <td>{{ half_lifes.0.model.value }}</td>
                           </tr>
                         </tbody>
                       </table>

utilities/misc.py

@@ -4,11 +4,13 @@ import hmac
 import json
 import logging
 import uuid
+from abc import ABC, abstractmethod
 from collections import defaultdict
 from datetime import datetime
-from typing import Any, Dict, List, Optional, TYPE_CHECKING
+from typing import Any, Dict, List, Optional, TYPE_CHECKING, Type
 
 from django.conf import settings as s
+from envipy_additional_information import EnviPyModel, UIConfig
 from ninja import Schema
 from pydantic import HttpUrl, ValidationError
 
@@ -277,15 +279,20 @@ class PackageExportSchema(Schema):
         return AdditionalInformation.objects.filter(package=obj)
 
 
-class PackageExporter:
+class Exporter(ABC):
     def __init__(self, package: Package):
         self._raw_package = package
 
     def do_export(self):
-        return PackageExporter._export_package_as_json(self._raw_package)
+        return self._export()
 
-    @staticmethod
-    def _export_package_as_json(package: Package) -> Dict[str, Any]:
+    @abstractmethod
+    def _export(self):
+        pass
+
+
+class PackageExporter(Exporter):
+    def _export(self) -> Dict[str, Any]:
         """
         Dumps a Package and all its related objects as JSON.
 
@@ -296,11 +303,126 @@ class PackageExporter:
             Dict containing the complete package data as JSON-serializable structure
         """
 
-        data = PackageExportSchema.from_orm(package)
+        data = PackageExportSchema.from_orm(self._raw_package)
 
         return data.model_dump(mode="json")
 
 
+class PathwayExporter(Exporter):
+    def __init__(self, package: Package, add_infs_to_export: List[str] = []):
+        super().__init__(package)
+        self._add_infs_to_export = add_infs_to_export
+
+    def _flatten_additional_information(self, ai: AdditionalInformation) -> dict[str, Any]:
+        model_cls: Type[EnviPyModel] = type(ai.get())
+
+        def _flatten(d: dict, parent_key: str = "") -> dict[str, Any]:
+            items: dict[str, Any] = {}
+            for key, value in d.items():
+                new_key = f"{parent_key}__{key.lower()}" if parent_key else key.lower()
+                if isinstance(value, dict):
+                    items.update(_flatten(value, new_key))
+                else:
+                    items[new_key] = value
+            return items
+
+        flat = _flatten(ai.data, ai.type)
+
+        ui_class = getattr(model_cls, "UI", None)
+        if ui_class is None:
+            return flat
+
+        for f in model_cls.model_fields:
+            ui_info = getattr(ui_class, f, None)
+
+            if not isinstance(ui_info, UIConfig) or ui_info.unit is None:
+                continue
+
+            flat[f"{model_cls.__name__}__{f}__unit"] = ui_info.unit
+
+        return flat
+
+    def _export(self):
+        from io import StringIO
+        from csv import DictWriter
+
+        rows = []
+
+        for pw in self._raw_package.pathways.all():
+            for n in pw.nodes:
+                for scen in pw.scenarios.all():
+                    row = {
+                        "pathway_name": pw.name,
+                        "pathway_id": str(pw.url),
+                        "node_depth": n.depth,
+                        "compound_id": str(n.default_node_label.compound.url),
+                        "pubchem_ID": n.default_node_label.pubchem_compound_id,
+                        "compound_name": n.default_node_label.compound.name,
+                        "compound_smiles": n.default_node_label.smiles,
+                        "scenario_id": str(scen.url),
+                        "scenario_name": scen.name,
+                        "scenario_type": scen.scenario_type,
+                        "scenario_description": scen.description,
+                    }
+
+                    if self._add_infs_to_export:
+                        ai_qs = AdditionalInformation.objects.filter(
+                            scenario=scen, type__in=self._add_infs_to_export
+                        )
+                    else:
+                        ai_qs = AdditionalInformation.objects.filter(scenario=scen)
+
+                    for ai in ai_qs:
+                        if ai.type == "ProposedIntermediate" and ai.content_object == n:
+                            row.update({"proposed_intermediate": True})
+                        elif ai.type == "SpikeCompound":
+                            spike = {"SpikeCompound__url": ai.get().url}
+
+                            try:
+                                struc = CompoundStructure.objects.get(
+                                    compound__package=self._raw_package, url=ai.get().url
+                                )
+                                spike["SpikeCompound__smiles"] = struc.smiles
+                            except Exception:
+                                spike["SpikeCompound__smiles"] = None
+
+                            row.update(**spike)
+                        else:
+                            row.update(self._flatten_additional_information(ai))
+                    rows.append(row)
+
+        # Get all header fields
+        all_header_fields = set()
+        for row in rows:
+            all_header_fields.update(row.keys())
+
+        # Per request the CSV should start with these fields
+        header = [
+            "pathway_name",
+            "pathway_id",
+            "node_depth",
+            "compound_id",
+            "pubchem_ID",
+            "compound_name",
+            "compound_smiles",
+            "scenario_id",
+            "scenario_name",
+            "scenario_type",
+            "scenario_description",
+        ]
+
+        # User remaining fields and place them after the predefined values in a sorted manner
+        remainder = sorted(list(all_header_fields.difference(set(header))))
+        header.extend(remainder)
+
+        buffer = StringIO()
+        writer = DictWriter(buffer, fieldnames=header, delimiter="\t")
+        writer.writeheader()
+        writer.writerows(rows)
+        buffer.seek(0)
+        return buffer.getvalue()
+
+
 class PackageImporter:
     def __init__(self, package: Dict[str, Any], preserve_uuids: bool = False):
         self.preserve_uuids = preserve_uuids