tests + bug fix

pepdbagent/db_utils.py

@@ -129,7 +129,7 @@ class Projects(Base):
 
     history_mapping: Mapped[List["HistoryProjects"]] = relationship(
         back_populates="project_mapping", cascade="all, delete-orphan"
-    )  # TODO: check if cascade is correct
+    )
 
     __table_args__ = (UniqueConstraint("namespace", "name", "tag"),)
 
@@ -317,6 +317,9 @@ class Schemas(Base):
         default=deliver_update_date, onupdate=deliver_update_date
     )
 
+    projects_mappings: Mapped[List["Projects"]] = relationship(
+        "Projects", back_populates="schema_mapping"
+    )
     group_relation_mapping: Mapped[List["SchemaGroupRelations"]] = relationship(
         "SchemaGroupRelations", back_populates="schema_mapping"
     )

pepdbagent/models.py

@@ -255,9 +255,10 @@ class SchemaAnnotation(BaseModel):
 
     namespace: str
     name: str
-    last_update_date: Optional[datetime.datetime]
-    submission_date: Optional[datetime.datetime]
-    description: Optional[str]
+    last_update_date: str
+    submission_date: str
+    description: Optional[str] = ""
+    popularity_number: Optional[int] = 0
 
 
 class SchemaSearchResult(BaseModel):

pepdbagent/modules/schema.py

@@ -30,6 +30,7 @@
     Schemas,
     SchemaGroups,
     SchemaGroupRelations,
+    User,
 )
 from pepdbagent.exceptions import (
     SchemaAlreadyExistsError,
@@ -110,9 +111,10 @@ def info(self, namespace: str, name: str) -> SchemaAnnotation:
             return SchemaAnnotation(
                 namespace=schema_obj.namespace,
                 name=schema_obj.name,
-                last_update_date=schema_obj.last_update_date,
-                submission_date=schema_obj.submission_date,
+                last_update_date=str(schema_obj.last_update_date),
+                submission_date=str(schema_obj.submission_date),
                 description=schema_obj.description,
+                popularity_number=len(schema_obj.projects_mappings),
             )
 
     def search(
@@ -143,9 +145,10 @@ def search(
                     SchemaAnnotation(
                         namespace=result.namespace,
                         name=result.name,
-                        last_update_date=result.last_update_date,
-                        submission_date=result.submission_date,
+                        last_update_date=str(result.last_update_date),
+                        submission_date=str(result.submission_date),
                         description=result.description,
+                        # popularity_number=sum(result.projects_mappings),
                     )
                 )
 
@@ -229,6 +232,13 @@ def create(
             )
 
         with Session(self._sa_engine) as session:
+            user = session.scalar(select(User).where(User.namespace == namespace))
+
+            if not user:
+                user = User(namespace=namespace)
+                session.add(user)
+                session.commit()
+
             schema_obj = Schemas(
                 namespace=namespace,
                 name=name,
@@ -366,8 +376,8 @@ def group_get(self, namespace: str, name: str) -> SchemaGroupAnnotation:
                     SchemaAnnotation(
                         namespace=schema_annotation.namespace,
                         name=schema_annotation.name,
-                        last_update_date=schema_annotation.last_update_date,
-                        submission_date=schema_annotation.submission_date,
+                        last_update_date=str(schema_annotation.last_update_date),
+                        submission_date=str(schema_annotation.submission_date),
                         desciription=schema_annotation.description,
                     )
                 )
@@ -458,7 +468,7 @@ def _group_search_count(self, namespace: str = None, search_str: str = ""):
         """
         statement = select(func.count(SchemaGroups.id))
 
-        statement = self._add_condition(statement, namespace, search_str)
+        statement = self._add_group_condition(statement, namespace, search_str)
 
         with Session(self._sa_engine) as session:
             result = session.execute(statement).one()
@@ -475,7 +485,7 @@ def group_delete(self, namespace: str, name: str) -> None:
         :return: None
         """
 
-        if self.group_exist(namespace, name):
+        if not self.group_exist(namespace, name):
             raise SchemaGroupDoesNotExistError(
                 f"Schema group '{name}' does not exist in the database"
             )
@@ -559,30 +569,43 @@ def group_remove_schema(
 
         try:
             with Session(self._sa_engine) as session:
-                session.execute(
-                    delete(SchemaGroupRelations).where(
-                        and_(
-                            SchemaGroupRelations.schema_id
-                            == select(Schemas.id)
-                            .where(
-                                and_(
-                                    Schemas.namespace == schema_namespace,
-                                    Schemas.name == schema_name,
-                                )
+
+                a = session.scalar(
+                    select(Schemas).where(
+                        and_(Schemas.namespace == schema_namespace, Schemas.name == schema_name)
+                    )
+                )
+                b = session.scalar(
+                    select(SchemaGroups).where(
+                        and_(SchemaGroups.namespace == namespace, SchemaGroups.name == name)
+                    )
+                )
+
+                delete_statement = delete(SchemaGroupRelations).where(
+                    and_(
+                        SchemaGroupRelations.schema_id
+                        == select(Schemas.id)
+                        .where(
+                            and_(
+                                Schemas.namespace == schema_namespace,
+                                Schemas.name == schema_name,
                             )
-                            .subquery(),
-                            SchemaGroupRelations.group_id
-                            == select(SchemaGroups.id)
-                            .where(
-                                and_(
-                                    SchemaGroups.namespace == namespace,
-                                    SchemaGroups.name == name,
-                                )
+                        )
+                        .subquery(),
+                        SchemaGroupRelations.group_id
+                        == select(SchemaGroups.id)
+                        .where(
+                            and_(
+                                SchemaGroups.namespace == namespace,
+                                SchemaGroups.name == name,
                             )
-                            .subquery(),
                         )
+                        .subquery(),
                     )
                 )
+
+                session.execute(delete_statement)
+                session.commit()
         except IntegrityError:
             raise SchemaIsNotInGroupError("Schema not found in the group")
 

tests/schemas/namespace1/2.0.0.yaml

@@ -0,0 +1,69 @@
+description: "Schema for a minimal PEP"
+version: "2.0.0"
+properties:
+  config:
+    properties:
+      name: 
+        type: string
+        pattern: "^\\S*$"
+        description: "Project name with no whitespace"
+      pep_version:
+        description: "Version of the PEP Schema this PEP follows"
+        type: string
+      sample_table:
+        type: string
+        description: "Path to the sample annotation table with one row per sample"
+      subsample_table:
+        type: string
+        description: "Path to the subsample annotation table with one row per subsample and sample_name attribute matching an entry in the sample table"
+      sample_modifiers:
+        type: object
+        properties:
+          append:
+            type: object
+          duplicate:
+            type: object
+          imply:
+            type: array
+            items:
+              type: object
+              properties:
+                if:
+                  type: object
+                then:
+                  type: object
+          derive:
+            type: object
+            properties:
+              attributes:
+                type: array
+                items:
+                  type: string
+              sources:
+                type: object
+        project_modifiers:
+          type: object
+          properties:
+            amend:
+              description: "Object overwriting original project attributes"
+              type: object
+            import:
+              description: "List of external PEP project config files to import"
+              type: array
+              items:
+                type: string
+    required:
+      - pep_version
+  samples:
+    type: array
+    items:
+      type: object
+      properties:
+        sample_name: 
+          type: string
+          pattern: "^\\S*$"
+          description: "Unique name of the sample with no whitespace"
+      required:
+        - sample_name
+required:
+  - samples

tests/schemas/namespace1/2.1.0.yaml

@@ -0,0 +1,77 @@
+description: "Schema for a minimal PEP"
+version: "2.1.0"
+properties:
+  config:
+    properties:
+      name: 
+        type: string
+        pattern: "^\\S*$"
+        description: "Project name with no whitespace"
+      pep_version:
+        description: "Version of the PEP Schema this PEP follows"
+        type: string
+      sample_table:
+        type: string
+        description: "Path to the sample annotation table"
+      subsample_table:
+        type: string
+        description: "Path to the subsample annotation table with one row per subsample and sample_name attribute matching an entry in the sample table"
+      sample_table_index: 
+        type: string
+        pattern: "^\\S*$"
+        description: "Name of the column in sample table to use as an index. It's 'sample_name' by default"
+      subsample_table_index: 
+        type: array
+        items:
+          type: string
+          pattern: "^\\S*$"
+        description: "Names of the columns in subsample table to use as an index. It's ['sample_name', 'subsample_name'] by default"
+      sample_modifiers:
+        type: object
+        properties:
+          append:
+            type: object
+          duplicate:
+            type: object
+          imply:
+            type: array
+            items:
+              type: object
+              properties:
+                if:
+                  type: object
+                then:
+                  type: object
+          derive:
+            type: object
+            properties:
+              attributes:
+                type: array
+                items:
+                  type: string
+              sources:
+                type: object
+        project_modifiers:
+          type: object
+          properties:
+            amend:
+              description: "Object overwriting original project attributes"
+              type: object
+            import:
+              description: "List of external PEP project config files to import"
+              type: array
+              items:
+                type: string
+    required:
+      - pep_version
+  samples:
+    type: array
+    items:
+      type: object
+      properties:
+        sample_name: 
+          type: string
+          pattern: "^\\S*$"
+          description: "Unique name of the sample with no whitespace"
+required:
+  - samples

tests/schemas/namespace2/bedboss.yaml

@@ -0,0 +1,47 @@
+description: bedboss run-all pep schema
+
+properties:
+  samples:
+    type: array
+    items:
+      type: object
+      properties:
+        sample_name: 
+          type: string
+          description: "Name of the sample"
+        input_file:
+          type: string
+          description: "Absolute path to the input file"
+        input_type:
+          type: string
+          description: "file format"
+          enum: [ "bigWig", "bigBed", "bed", "wig", "bedGraph" ]
+        genome:
+          type: string
+          description: "organism genome code"
+        format_type:
+          type: string
+          description: "whether the regions are narrow (transcription factor implies narrow, histone mark implies broad peaks)"
+          enum: [ "narrowPeak", "broadPeak" ]
+        description:
+          type: string
+          description: "freeform description of the sample"
+        open_signal_matrix:
+          type: string
+          description: "A full path to the openSignalMatrix required for the tissue"
+        chrom_sizes:
+          type: string
+          description: "A full path to the chrom.sizes required for the bedtobigbed conversion"
+        treatment:
+          type: string
+          description: "freeform description of the sample treatment"
+        cell_type:
+          type: string
+          description: "cell type code"
+      required:
+        - sample_name
+        - input_file
+        - input_type
+        - genome
+required:
+  - samples

tests/schemas/namespace2/bedbuncher.yaml

@@ -0,0 +1,25 @@
+description: bedbuncher PEP schema
+imports: 
+  - http://schema.databio.org/pep/2.0.0.yaml
+
+properties:
+  samples:
+    type: array
+    items:
+      type: object
+      properties:
+        JSONquery_path: 
+          type: string
+          description: "path to the JSON file with the Elasticsearch query"
+        bedset_name:
+          type: string
+          pattern: "^\\S*$"
+          description: "name of the bedset that will be created"
+        bbconfig_path:
+          type: string
+          description: "path to bedbase config file"
+      required:
+        - JSONquery_path
+        - bedset_name
+required:
+  - samples