nci-cidc-api-modules 1.1.34__py3-none-any.whl → 1.1.37__py3-none-any.whl

cidc_api/config/db.py

@@ -4,13 +4,12 @@ from flask import Flask
 from flask_sqlalchemy import SQLAlchemy
 from flask_migrate import Migrate, upgrade
 from sqlalchemy.engine.url import URL
-from sqlalchemy.ext.declarative import declarative_base
-
+from sqlalchemy.orm import declarative_base
 
 from .secrets import get_secrets_manager
 
 db = SQLAlchemy()
-BaseModel = declarative_base(bind=db)
+BaseModel = declarative_base()
 db.Model = BaseModel
 
 
@@ -54,7 +53,7 @@ def get_sqlalchemy_database_uri(testing: bool = False) -> str:
                 "Either POSTGRES_URI or CLOUD_SQL_INSTANCE_NAME must be defined to connect " + "to a database."
             )
 
-        db_uri = str(URL(**config))
+        db_uri = str(URL.create(**config).render_as_string(hide_password=False))
 
     assert db_uri
 

cidc_api/models/files/details.py

@@ -993,4 +993,35 @@ details_dict = {
         "",
         "",
     ),
+    # scrna
+    "/scrnaseq/samples_metadata.csv": FileDetails("source", "", ""),
+    "/scrnaseq/read_1.gz": FileDetails("source", "", ""),
+    "/scrnaseq/read_2.gz": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/samples_metadata.csv": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/config.yaml": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/R_package_versions.csv": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/integration.rds": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/integration_heatmap_plots.zip": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/integration_markers.zip": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/integration_split_percent_plots.zip": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/integration_split_umap_plots.zip": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/integration_umap_plots.zip": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/clustering.rds": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/report.html": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/star_sorted_by_cord.bam": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/star_sorted_by_cord.bam.bai": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/log_final.out": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/log.out": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/log_progress.out": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/sj_out.tab": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/barcodes.stats": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/gene_features.stats": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/gene_summary.csv": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/gene_umi_per_cell_sorted.txt": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/gene_filtered_features.tsv": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/gene_filtered_barcodes.tsv": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/gene_filtered_matrix.mtx": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/gene_raw_features.tsv": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/gene_raw_barcodes.tsv": FileDetails("source", "", ""),
+    "/scrnaseq_analysis/gene_raw_matrix.mtx": FileDetails("source", "", ""),
 }

cidc_api/models/files/facets.py

@@ -346,6 +346,21 @@ assay_facets: Facets = {
             "H and E file from MIBI analysis",
         ),
     },
+    "scRNA": {
+        "Samples Metadata": FacetConfig(["/scrnaseq/samples_metadata.csv"], "Sample metadata for scRNA run"),
+        "Read 1 gz": FacetConfig(["/scrnaseq/read_1.gz"], "Gz file for read 1"),
+        "Read 2 gz": FacetConfig(["/scrnaseq/read_2.gz"], "Gz file for read 2"),
+    },
+    "Visium": {
+        "Samples Metadata": FacetConfig(["/visium/samples_metadata.csv"], "Sample metadata for visium run"),
+        "Read 1 fastq gz": FacetConfig(["/visium/R1_001.fastq.gz"], "Gz file for read 1"),
+        "Read 2 fastq gz": FacetConfig(["/visium/R2_001.fastq.gz"], "Gz file for read 2"),
+        "loupe alignment file": FacetConfig(["/visium/loupe_alignment_file.json"]),
+        "brightfield image": FacetConfig(["/visium/brightfield.tiff"]),
+        "dark image": FacetConfig(["/visium/dark_image.tiff"]),
+        "colorized image": FacetConfig(["/visium/colorized.tiff"]),
+        "cytassist image": FacetConfig(["/visium/cytassist.tiff"]),
+    },
     "mIHC": {
         "Samples Report": FacetConfig(["/mihc/sample_report.csv"], "Samples report for mIHC run"),
         "Multitiffs": FacetConfig(["/mihc/multitiffs.tar.gz"], "Multi Tiffs file from mIHC run"),
@@ -549,6 +564,48 @@ analysis_ready_facets = {
     "WES Analysis": FacetConfig(["/wes/analysis/report.tar.gz"]),
     "TCR": FacetConfig(["/tcr_analysis/report_trial.tar.gz"]),
     "mIF": FacetConfig(["/mif/roi_/cell_seg_data.txt"]),
+    "scRNA": FacetConfig(
+        [
+            "/scrnaseq_analysis/samples_metadata.csv",
+            "/scrnaseq_analysis/config.yaml",
+            "/scrnaseq_analysis/R_package_versions.csv",
+            "/scrnaseq_analysis/integration.rds",
+            "/scrnaseq_analysis/integration_heatmap_plots.zip",
+            "/scrnaseq_analysis/integration_markers.zip",
+            "/scrnaseq_analysis/integration_split_percent_plots.zip",
+            "/scrnaseq_analysis/integration_split_umap_plots.zip",
+            "/scrnaseq_analysis/integration_umap_plots.zip",
+            "/scrnaseq_analysis/clustering.rds",
+            "/scrnaseq_analysis/report.html",
+            "/scrnaseq_analysis/star_sorted_by_cord.bam",
+            "/scrnaseq_analysis/star_sorted_by_cord.bam.bai",
+            "/scrnaseq_analysis/log_final.out",
+            "/scrnaseq_analysis/log.out",
+            "/scrnaseq_analysis/log_progress.out",
+            "/scrnaseq_analysis/sj_out.tab",
+            "/scrnaseq_analysis/barcodes.stats",
+            "/scrnaseq_analysis/gene_features.stats",
+            "/scrnaseq_analysis/gene_summary.csv",
+            "/scrnaseq_analysis/gene_umi_per_cell_sorted.txt",
+            "/scrnaseq_analysis/gene_filtered_features.tsv",
+            "/scrnaseq_analysis/gene_filtered_barcodes.tsv",
+            "/scrnaseq_analysis/gene_filtered_matrix.mtx",
+            "/scrnaseq_analysis/gene_raw_features.tsv",
+            "/scrnaseq_analysis/gene_raw_barcodes.tsv",
+            "/scrnaseq_analysis/gene_raw_matrix.mtx",
+        ]
+    ),
+    "Visium": FacetConfig(
+        [
+            "/visium_analysis/samples_metadata.csv",
+            "/visium_analysis/config.yaml",
+            "/visium_analysis/R_package_versions.csv",
+            "/visium_analysis/merged.rds",
+            "/visium_analysis/spatial_variable_features.rds",
+            "/visium_analysis/report.html",
+            "/visium_analysis/visium_spaceranger_output.zip",
+        ]
+    ),
 }
 
 facets_dict: Dict[str, Facets] = {

cidc_api/models/models.py

@@ -23,6 +23,14 @@ __all__ = [
     "ValidationMultiError",
     "with_default_session",
     "PreprocessedFiles",
+    "IngestionJobs",
+    "JobFileCategories",
+    "TRIAL_APPENDIX_A",
+    "REQUEST_LETTER",
+    "ADMIN_FILE_CATEGORIES",
+    "FINAL_JOB_STATUS",
+    "INGESTION_JOB_STATUSES",
+    "INGESTION_JOB_COLORS",
 ]
 
 import hashlib
@@ -36,6 +44,7 @@ from functools import wraps
 from typing import (
     Any,
     BinaryIO,
+    ClassVar,
     Dict,
     Optional,
     List,
@@ -54,32 +63,33 @@ from google.cloud.storage import Blob
 from jsonschema.exceptions import ValidationError
 from sqlalchemy import (
     and_,
-    Column,
+    asc,
+    case,
+    desc,
+    func,
+    literal,
+    literal_column,
+    not_,
+    or_,
+    select,
+    text,
+    true,
+    tuple_,
+    update,
+    BigInteger,
     Boolean,
+    CheckConstraint,
+    Column,
     DateTime,
-    Integer,
-    BigInteger,
-    String,
     Enum,
-    Index,
-    func,
-    CheckConstraint,
     ForeignKey,
     ForeignKeyConstraint,
+    Index,
+    Integer,
+    MetaData,
     PrimaryKeyConstraint,
-    tuple_,
-    asc,
-    desc,
-    update,
-    case,
-    select,
-    literal_column,
-    not_,
-    literal,
-    or_,
+    String,
     Table,
-    MetaData,
-    true,
 )
 from sqlalchemy.dialects.postgresql import JSONB, UUID
 from sqlalchemy.engine import ResultProxy
@@ -96,8 +106,6 @@ from sqlalchemy.sql import (
     # break up this giant file.
     and_ as sql_and,
     or_ as sql_or,
-    # select, # ALREADY IMPORTED
-    text,
 )
 from sqlalchemy.sql.elements import BooleanClauseList
 from sqlalchemy.sql.functions import coalesce
@@ -119,6 +127,7 @@ from ..config.settings import (
     MAX_PAGINATION_PAGE_SIZE,
     TESTING,
     INACTIVE_USER_DAYS,
+    GOOGLE_CLINICAL_DATA_BUCKET,
 )
 from ..shared import emails
 from ..shared.gcloud_client import (
@@ -132,6 +141,7 @@ from ..shared.gcloud_client import (
     revoke_intake_access,
     revoke_lister_access,
     revoke_bigquery_access,
+    gcs_xlsx_or_csv_file_to_pandas_dataframe,
 )
 
 os.environ["TZ"] = "UTC"
@@ -309,7 +319,7 @@ class CommonColumns(BaseModel):  # type: ignore
     @with_default_session
     def find_by_id(cls, id: int, session: Session):
         """Find the record with this id"""
-        return session.query(cls).get(id)
+        return session.get(cls, id)
 
     @classmethod
     @with_default_session
@@ -1207,9 +1217,10 @@ class TrialMetadata(CommonColumns):
             raise NoResultFound(f"No trial found with id {trial_id}")
         return unprism.unprism_samples(trial.metadata_json)
 
-    file_bundle: Optional[FileBundle]
-    num_participants: Optional[int]
-    num_samples: Optional[int]
+    file_bundle: ClassVar[Optional[FileBundle]]
+    num_participants: ClassVar[Optional[int]]
+    num_samples: ClassVar[Optional[int]]
+    ready_for_submission: ClassVar[Optional[Boolean]]
 
     # List of metadata JSON fields that should not be sent to clients
     # in queries that list trial metadata, because they may contain a lot
@@ -1330,11 +1341,26 @@ class TrialMetadata(CommonColumns):
                             del trial.file_bundle[assay][purpose]
                     if not trial.file_bundle[assay]:
                         del trial.file_bundle[assay]
+            # Check if trial is ready for submission
+            setattr(trial, "ready_for_submission", trial.ready_for_submission())
 
             trials.append(trial)
 
         return trials
 
+    @with_default_session
+    def ready_for_submission(self, session: Session) -> Boolean:
+        open_job = IngestionJobs.get_open_job_by_trial(self.trial_id)
+        if not open_job:
+            return False
+        appendix_a_files = PreprocessedFiles.get_files_by_category_and_status(
+            "trial_appendix_a", "current", job_id=open_job.id
+        )
+        trial_letters = PreprocessedFiles.get_files_by_category_and_status(
+            "request_letter", "current", job_id=open_job.id
+        )
+        return appendix_a_files and trial_letters and open_job.status == "DRAFT"
+
     @with_default_session
     def insert(
         self,
@@ -1711,6 +1737,30 @@ class TrialMetadata(CommonColumns):
                         jsonb_array_elements(batch->'records') record
                 """
 
+        # Find all samples associated with scrnaseq analysis uploads.
+        scrnaseq_analysis_subquery = """
+                    select
+                        trial_id,
+                        'scrnaseq_analysis' as key,
+                        record->>'cimac_id' as cimac_id
+                    from
+                        trial_metadata,
+                        jsonb_array_elements(metadata_json#>'{analysis,scrnaseq_analysis}') batch,
+                        jsonb_array_elements(batch->'records') record
+                """
+
+        # Find all samples associated with visium analysis uploads.
+        visium_analysis_subquery = """
+                    select
+                        trial_id,
+                        'visium_analysis' as key,
+                        record->>'cimac_id' as cimac_id
+                    from
+                        trial_metadata,
+                        jsonb_array_elements(metadata_json#>'{analysis,visium_analysis}') batch,
+                        jsonb_array_elements(batch->'records') record
+                """
+
         # Build up a JSON object mapping analysis types to arrays of excluded samples.
         # The resulting object will have structure like:
         # {
@@ -1866,6 +1916,10 @@ class TrialMetadata(CommonColumns):
                                 {cytof_analysis_subquery}
                                 union all
                                 {atacseq_analysis_subquery}
+                                union all
+                                {scrnaseq_analysis_subquery}
+                                union all
+                                {visium_analysis_subquery}
                             ) assays_and_analysis
                             group by
                                 trial_id, key
@@ -1924,7 +1978,7 @@ class TrialMetadata(CommonColumns):
             - `"wes_tumor_only_analysis"` counts (tumor) samples with tumor-only analysis
         For `"total_[participants/samples]"`, ALL (ie tumor AND normal) WES assay samples are included.
         """
-        summaries_query = "SELECT result FROM trial_summaries_mv"
+        summaries_query = text("SELECT result FROM trial_summaries_mv")
         # Retrieve trial-level summary results from data cached in trial_summaries_mv materialized view.
         # The source of the SQL query used in trial_summaries_mv is get_summaries_query()
         summaries = [summary for (summary,) in session.execute(summaries_query) if summary]
@@ -2256,6 +2310,7 @@ class DownloadableFiles(CommonColumns):
         "FileGroups",
         secondary="files_to_file_groups",
         back_populates="downloadable_files",
+        cascade="save-update",
     )
 
     FILE_EXT_REGEX = r"\.([^./]*(\.gz)?)$"
@@ -2751,7 +2806,7 @@ class DownloadableFiles(CommonColumns):
         """
 
         where_clause = DownloadableFiles._generate_where_clause_with_permissions(user)
-        statement = select([DownloadableFiles.id]).where(sql_and(DownloadableFiles.id.in_(ids), where_clause))
+        statement = select(DownloadableFiles.id).where(sql_and(DownloadableFiles.id.in_(ids), where_clause))
 
         return [row[0] for row in session.execute(statement).fetchall()]
 
@@ -2783,7 +2838,7 @@ class DownloadableFiles(CommonColumns):
 
         for file in files_to_delete:
             file.delete(commit=True)
-        session.execute("REFRESH MATERIALIZED VIEW CONCURRENTLY trial_summaries_mv")
+        session.execute(text("REFRESH MATERIALIZED VIEW CONCURRENTLY trial_summaries_mv"))
 
     @classmethod
     @with_default_session
@@ -3054,23 +3109,19 @@ class DownloadableFiles(CommonColumns):
 
         id_bundles = (
             select(
-                [
-                    cls.trial_id,
-                    cls.data_category_prefix.label(type_col.key),
-                    cls.file_purpose.label(purp_col.key),
-                    func.json_agg(cls.id).label(ids_col.key),
-                ]
+                cls.trial_id,
+                cls.data_category_prefix.label(type_col.key),
+                cls.file_purpose.label(purp_col.key),
+                func.json_agg(cls.id).label(ids_col.key),
             )
             .group_by(cls.trial_id, cls.data_category_prefix, cls.file_purpose)
             .alias("id_bundles")
         )
         purpose_bundles = (
             select(
-                [
-                    tid_col,
-                    type_col,
-                    func.json_object_agg(func.coalesce(purp_col, "miscellaneous"), ids_col).label(purps_col.key),
-                ]
+                tid_col,
+                type_col,
+                func.json_object_agg(func.coalesce(purp_col, "miscellaneous"), ids_col).label(purps_col.key),
             )
             .select_from(id_bundles)
             .group_by(tid_col, type_col)
@@ -3078,10 +3129,8 @@ class DownloadableFiles(CommonColumns):
         )
         file_bundles = (
             select(
-                [
-                    tid_col.label(tid_col.key),
-                    func.json_object_agg(func.coalesce(type_col, "other"), purps_col).label("file_bundle"),
-                ]
+                tid_col.label(tid_col.key),
+                func.json_object_agg(func.coalesce(type_col, "other"), purps_col).label("file_bundle"),
             )
             .select_from(purpose_bundles)
             .group_by(tid_col)
@@ -3131,13 +3180,13 @@ class DownloadableFiles(CommonColumns):
 # Query clause for computing a downloadable file's data category.
 # Used above in the DownloadableFiles.data_category computed property.
 DATA_CATEGORY_CASE_CLAUSE = case(
-    [(DownloadableFiles.facet_group == k, v) for k, v in facet_groups_to_categories.items()]
+    *[(DownloadableFiles.facet_group == k, v) for k, v in facet_groups_to_categories.items()]
 )
 
 # Query clause for computing a downloadable file's file purpose.
 # Used above in the DownloadableFiles.file_purpose computed property.
 FILE_PURPOSE_CASE_CLAUSE = case(
-    [
+    *[
         (DownloadableFiles.facet_group == facet_group, file_details.file_purpose)
         for facet_group, file_details in details_dict.items()
     ]
@@ -3146,7 +3195,7 @@ FILE_PURPOSE_CASE_CLAUSE = case(
 
 def result_proxy_to_models(result_proxy: ResultProxy, model: BaseModel) -> List[BaseModel]:
     """Materialize a sqlalchemy `result_proxy` iterable as a list of `model` instances"""
-    return [model(**dict(row_proxy)) for row_proxy in result_proxy.all()]
+    return [model(**dict(row_proxy._mapping)) for row_proxy in result_proxy.all()]
 
 
 @with_default_session
@@ -3187,12 +3236,24 @@ def upload_manifest_json(
     return manifest_upload.id
 
 
+TRIAL_APPENDIX_A = "trial_appendix_a"
+REQUEST_LETTER = "request_letter"
+ADMIN_FILE_CATEGORIES = [TRIAL_APPENDIX_A, REQUEST_LETTER]
+
+
 class PreprocessedFiles(CommonColumns):
     __tablename__ = "preprocessed_files"
+    __table_args__ = (
+        ForeignKeyConstraint(
+            ["job_id"],
+            ["ingestion_jobs.id"],
+            name="preprocessed_files_job_id_fkey",
+        ),
+    )
 
     file_name = Column(String)
     object_url = Column(String)
-    trial_id = Column(String)
+    job_id = Column(Integer)
     file_category = Column(String)
     uploader_email = Column(String)
     status = Column(String)
@@ -3207,7 +3268,7 @@ class PreprocessedFiles(CommonColumns):
         file_category: str,
         uploader_email: str,
         status: str = "pending",
-        trial_id: str = None,
+        job_id: int = None,
         version: int = None,
         released_version: str = None,
         session: Session = None,
@@ -3219,7 +3280,7 @@ class PreprocessedFiles(CommonColumns):
             file_category=file_category,
             uploader_email=uploader_email,
             status=status,
-            trial_id=trial_id,
+            job_id=job_id,
             version=version,
             released_version=released_version,
         )
@@ -3228,10 +3289,10 @@ class PreprocessedFiles(CommonColumns):
 
     @classmethod
     @with_default_session
-    def archive_current_files(cls, file_category: str, session: Session = None):
+    def archive_current_files(cls, file_category: str, job_id: int = None, session: Session = None):
         """Update any 'current' files in the given category to 'archived'. Returns latest existing version number."""
         current_version = 0
-        current_files = cls.get_files_by_category_and_status(file_category, "current", session=session)
+        current_files = cls.get_files_by_category_and_status(file_category, "current", job_id=job_id, session=session)
         for file in current_files:
             file.status = "archived"
             file._updated = datetime.now()
@@ -3241,22 +3302,35 @@ class PreprocessedFiles(CommonColumns):
 
     @classmethod
     @with_default_session
-    def delete_pending_files_by_category(cls, file_category: str, trial_id: str = None, session: Session = None):
-        """Delete all pending files matching given file_category and optional trial_id."""
-        records = cls.get_files_by_category_and_status(file_category, "pending", trial_id=trial_id, session=session)
+    def delete_pending_files_by_category(cls, file_category: str, job_id: int = None, session: Session = None):
+        """Delete all pending files matching given file_category and optional job_id."""
+        records = cls.get_files_by_category_and_status(file_category, "pending", job_id=job_id, session=session)
+        for record in records:
+            session.delete(record)
+        session.commit()
+
+    @classmethod
+    @with_default_session
+    def delete_files_by_category(cls, file_category: str, job_id: int = None, session: Session = None):
+        """Delete all files matching a given file_category and job_id (or system files if job_id is None)."""
+        query = session.query(cls).filter_by(file_category=file_category)
+        query = cls.add_job_filter(query, job_id)
+        records = query.all()
+        if not records:
+            return False
         for record in records:
             session.delete(record)
         session.commit()
+        return True
 
     @classmethod
     @with_default_session
     def get_files_by_category_and_status(
-        cls, file_category: str, status: str, trial_id: str = None, session: Session = None
+        cls, file_category: str, status: str, job_id: int = None, session: Session = None
     ) -> list["PreprocessedFiles"]:
-        """Return all files matching given file_category and status, optionally filtered by trial_id."""
+        """Return all files matching file_category and status, with job_id filter (job_id is NULL if not provided)."""
         query = session.query(cls).filter_by(file_category=file_category, status=status)
-        if trial_id:
-            query = query.filter_by(trial_id=trial_id)
+        query = cls.add_job_filter(query, job_id)
         return query.all()
 
     @classmethod
@@ -3266,3 +3340,171 @@ class PreprocessedFiles(CommonColumns):
     ) -> Optional["PreprocessedFiles"]:
         """Return the file matching the given category and version number."""
         return session.query(cls).filter_by(file_category=file_category, version=version).one_or_none()
+
+    @classmethod
+    @with_default_session
+    def get_system_reference_files(cls, status: str = "current", session: Session = None) -> list["PreprocessedFiles"]:
+        """Return static reference files that are not linked to any job and not Master Appendix A."""
+        return (
+            session.query(cls)
+            .filter(cls.job_id.is_(None))
+            .filter(cls.file_category != "master_appendix_a")
+            .filter_by(status=status)
+            .all()
+        )
+
+    # TODO: logic for pending vs current files after high level validation
+    @classmethod
+    @with_default_session
+    def get_pending_non_admin_files(cls, job_id: int, session: Session) -> list["PreprocessedFiles"]:
+        return (
+            session.query(cls)
+            .filter(cls.job_id == job_id)
+            .filter(cls.status == "pending", cls.file_category.notin_(ADMIN_FILE_CATEGORIES))
+            .all()
+        )
+
+    @classmethod
+    def add_job_filter(cls, query, job_id):
+        """
+        Add a job_id filter to the SQLAlchemy query:
+        - If job_id is provided, filters for exact match.
+        - If not, filters for system-wide files (where job_id IS NULL).
+        """
+        if job_id is not None:
+            return query.filter_by(job_id=job_id)
+        else:
+            return query.filter(cls.job_id.is_(None))
+
+
+INGESTION_JOB_STATUSES = [
+    "DRAFT",
+    "INITIAL SUBMISSION",
+    "VALIDATION REVIEW",
+    "REVISION SUBMISSION",
+    "INGESTION",
+    "PUBLISHED",
+]
+
+# Business decision to pass hex codes from the backend though that should be done by the front end...
+INGESTION_JOB_COLORS = {
+    "DRAFT": "",
+    "INITIAL SUBMISSION": "#ACCAD7",
+    "VALIDATION REVIEW": "#DABE90",
+    "REVISION SUBMISSION": "#C8BAE5",
+    "INGESTION": "#8FCEC7",
+    "PUBLISHED": "#90D9E6",
+}
+# TODO If have "CANCELLED" concept or other final status, add here
+FINAL_JOB_STATUS = ["PUBLISHED"]
+
+
+class IngestionJobs(CommonColumns):
+    __tablename__ = "ingestion_jobs"
+    __table_args__ = (
+        ForeignKeyConstraint(
+            ["trial_id"],
+            ["trial_metadata.trial_id"],
+            name="ingestion_jobs_trial_id_fkey",
+        ),
+    )
+
+    status = Column("status", Enum(*INGESTION_JOB_STATUSES, name="status"), nullable=False)
+    trial_id = Column(String, nullable=False)
+    version = Column(Integer, nullable=False)
+
+    @staticmethod
+    @with_default_session
+    def create(trial_id: str, status: str, version: int, session: Session = None):
+        new_job = IngestionJobs(trial_id=trial_id, status=status, version=version)
+        new_job.insert(session=session)
+        return new_job
+
+    @with_default_session
+    def transition_status(self, status: str, session: Session):
+        # create required categories after opening job for submission
+        if self.status == "DRAFT" and status == "INITIAL SUBMISSION":
+            for category in self.derive_required_categories_from_appendix_a():
+                JobFileCategories.create(category=category, job_id=self.id, type="required")
+        self.status = status
+        self.update(session=session)
+
+    def derive_required_categories_from_appendix_a(self) -> List:
+        appendix_a = PreprocessedFiles.get_files_by_category_and_status(TRIAL_APPENDIX_A, "current", job_id=self.id)[0]
+        df = gcs_xlsx_or_csv_file_to_pandas_dataframe(GOOGLE_CLINICAL_DATA_BUCKET, appendix_a.object_url)
+        categories = []
+        headers_ended = False
+        for index, row in df.iterrows():
+            cell = str(row.iloc[0])
+            if headers_ended:
+                if not cell == "nan" and cell not in categories and cell != "Specialized_Data":
+                    categories.append(cell)
+            elif cell == "PATIENT-LEVEL DATA":
+                headers_ended = True
+        return categories
+
+    @classmethod
+    @with_default_session
+    def get_jobs_by_trial(cls, trial_id: str, session: Session = None) -> list["IngestionJobs"]:
+        return session.query(cls).filter(cls.trial_id == trial_id).order_by(cls.version.desc()).all()
+
+    @classmethod
+    @with_default_session
+    def get_open_job_by_trial(cls, trial_id: str, session: Session = None) -> Optional["IngestionJobs"]:
+        """Return the open job for a given trial if it exists."""
+        return (
+            session.query(cls)
+            .filter(
+                cls.trial_id == trial_id,
+                cls.status.notin_(FINAL_JOB_STATUS),
+            )
+            .order_by(cls._created.desc())
+            .first()
+        )
+
+    # TODO: figure out which users have access to which jobs
+    @classmethod
+    @with_default_session
+    def get_open_jobs_for_user(cls, user: Users, session: Session = None) -> list["IngestionJobs"]:
+        return session.query(cls).filter(cls.status.notin_(["DRAFT"])).order_by(cls._created.desc()).all()
+
+
+class JobFileCategories(CommonColumns):
+    __tablename__ = "job_file_categories"
+    __table_args__ = (
+        ForeignKeyConstraint(
+            ["job_id"],
+            ["ingestion_jobs.id"],
+        ),
+        Index(
+            "idx_categories_job_id" "job_id",
+            "category",
+            unique=True,
+        ),
+    )
+
+    category = Column(String)
+    job_id = Column(Integer)
+    type = Column(Enum("required", "optional", name="type"))
+
+    @staticmethod
+    @with_default_session
+    def create(
+        category: str,
+        job_id: int,
+        type: str,
+        session: Session = None,
+    ):
+        new_category = JobFileCategories(
+            category=category,
+            job_id=job_id,
+            type=type,
+        )
+        new_category.insert(session=session)
+        return new_category
+
+    @classmethod
+    @with_default_session
+    def categories_for_job(cls, job_id: int, type: str, session: Session = None):
+        categories = session.query(cls).filter(cls.job_id == job_id, cls.type == type).all()
+        return [c.category for c in categories]

cidc_api/models/schemas.py

@@ -104,6 +104,7 @@ class TrialMetadataSchema(BaseSchema):
     file_bundle = fields.Dict(dump_only=True)
     num_participants = fields.Int(dump_only=True)
     num_samples = fields.Int(dump_only=True)
+    ready_for_submission = fields.Bool(dump_only=True)
 
 
 TrialMetadataListSchema = _make_list_schema(TrialMetadataSchema())

cidc_api/shared/emails.py

@@ -16,7 +16,7 @@ from ..config.settings import ENV
 # - errors from CSMS in update_cidc_from_csms,
 # - errors from kicking off permissions in grant_download_permissions, and
 # - errors from implementing permissions in worker > permissions_worker
-CIDC_MAILING_LIST = ["essex-alert@cimac-network.org", "mustafa.kucukkal@nih.gov"]
+CIDC_MAILING_LIST = ["essex-alert@cimac-network.org"]
 
 
 def sendable(email_template):

cidc_api/shared/file_handling.py

@@ -0,0 +1,56 @@
+from werkzeug.datastructures import FileStorage
+from werkzeug.exceptions import BadRequest
+
+from ..config.settings import GOOGLE_CLINICAL_DATA_BUCKET
+from ..models import PreprocessedFiles
+from ..shared.auth import get_current_user
+from ..shared.gcloud_client import upload_file_to_gcs
+
+
+def set_current_file(file: FileStorage, file_category: str, gcs_folder: str, job_id: int = None) -> PreprocessedFiles:
+    """
+    Archives any existing 'current' files for the given category and job,
+    then uploads the new file as the latest 'current' version.
+    """
+    latest_version = PreprocessedFiles.archive_current_files(file_category, job_id=job_id)
+    latest_file = create_file(file, gcs_folder, file_category, job_id, latest_version + 1)
+    return latest_file
+
+
+def create_file(
+    file: FileStorage, gcs_folder: str, file_category: str, job_id: int = None, version: int = None
+) -> PreprocessedFiles:
+    """Upload file to GCS and create corresponding metadata record in the database."""
+    status = "pending" if gcs_folder.endswith("pending/") else "current"
+    # only need timestamp for current/approved files
+    append_timestamp = status == "current"
+    # create file in GCS
+    gcs_file_path = upload_file_to_gcs(file, GOOGLE_CLINICAL_DATA_BUCKET, gcs_folder, append_timestamp=append_timestamp)
+    # create corresponding record in db
+    file = PreprocessedFiles.create(
+        file_name=file.filename,
+        object_url=gcs_file_path,
+        file_category=file_category,
+        uploader_email=get_current_user().email,
+        status=status,
+        job_id=job_id,
+        version=version,
+    )
+    return file
+
+
+def validate_file_extension(filename: str, allowed_extensions: list[str]):
+    if not filename or not any(filename.lower().endswith(ext) for ext in allowed_extensions):
+        raise BadRequest(f"Invalid file type. Must be one of: {allowed_extensions}")
+
+
+def format_common_preprocessed_file_response(file: PreprocessedFiles):
+    """Format a common response for a single PreprocessedFiles record."""
+    return {
+        "file_name": file.file_name,
+        "gcs_uri": f"gs://{GOOGLE_CLINICAL_DATA_BUCKET}/{file.object_url}",
+        "status": file.status,
+        "file_category": file.file_category,
+        "uploader_email": file.uploader_email,
+        "date": file._created.isoformat(),
+    }

cidc_api/shared/gcloud_client.py

@@ -26,6 +26,7 @@ from typing import (
 
 import googleapiclient.discovery
 import requests
+import pandas as pd
 from cidc_schemas.prism.constants import ASSAY_TO_FILEPATH
 from google.api_core.client_options import ClientOptions
 from google.api_core.iam import Policy
@@ -217,10 +218,12 @@ def upload_xlsx_to_gcs(
     return final_object
 
 
-def upload_file_to_gcs(file: FileStorage, bucket_name: str, gcs_folder: str) -> str:
+def upload_file_to_gcs(file: FileStorage, bucket_name: str, gcs_folder: str, append_timestamp: bool = False) -> str:
     """Upload a file to the specified GCS folder and return the GCS path from the bucket."""
     # Secure the filename and prepare file
     filename = secure_filename(file.filename)
+    if append_timestamp:
+        filename = _append_iso_timestamp_to_filename(filename)
     gcs_file_path = os.path.join(gcs_folder, filename)
     binary_file = io.BytesIO(file.read())
 
@@ -416,6 +419,20 @@ def upload_xlsx_to_intake_bucket(user_email: str, trial_id: str, upload_type: st
     return f"https://console.cloud.google.com/storage/browser/_details/{bucket_name}/{blob_name}"
 
 
+def gcs_xlsx_or_csv_file_to_pandas_dataframe(bucket_name: str, blob_name: str):
+    """Reads an XLSX file from Google Cloud Storage into a Pandas DataFrame."""
+    sheet_data = storage.Client().bucket(bucket_name).blob(blob_name).download_as_bytes()
+    temp_file = io.BytesIO(sheet_data)
+
+    # TODO: specify sheet in xlsx file and/or accept tsv and xls files
+    if blob_name[-3:] == "csv":
+        return pd.read_csv(temp_file)
+    elif blob_name[-4:] == "xlsx":
+        return pd.read_excel(temp_file)
+    else:
+        raise Exception("Can only read csv or xlsx files")
+
+
 def _execute_multiblob_acl_change(
     user_email_list: List[str],
     blob_list: List[storage.Blob],

{nci_cidc_api_modules-1.1.34.dist-info → nci_cidc_api_modules-1.1.37.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nci_cidc_api_modules
-Version: 1.1.34
+Version: 1.1.37
 Summary: SQLAlchemy data models and configuration tools used in the NCI CIDC API
 Home-page: https://github.com/NCI-CIDC/cidc-api-gae
 License: MIT license
@@ -10,10 +10,10 @@ License-File: LICENSE
 Requires-Dist: werkzeug==3.0.6
 Requires-Dist: flask==3.0.3
 Requires-Dist: flask-migrate==3.1.0
-Requires-Dist: flask-sqlalchemy==3.0.2
-Requires-Dist: sqlalchemy==1.4.54
+Requires-Dist: flask-sqlalchemy==3.1.1
+Requires-Dist: sqlalchemy==2.0.41
 Requires-Dist: marshmallow==3.19.0
-Requires-Dist: marshmallow-sqlalchemy==0.22.3
+Requires-Dist: marshmallow-sqlalchemy==1.4.2
 Requires-Dist: google-cloud-storage==2.18.0
 Requires-Dist: google-cloud-secret-manager==2.20.1
 Requires-Dist: google-cloud-pubsub==2.22.0
@@ -28,7 +28,7 @@ Requires-Dist: python-dotenv==0.10.3
 Requires-Dist: requests==2.32.4
 Requires-Dist: jinja2==3.1.6
 Requires-Dist: certifi==2024.7.4
-Requires-Dist: nci-cidc-schemas==0.27.25
+Requires-Dist: nci-cidc-schemas==0.27.27
 Dynamic: description
 Dynamic: description-content-type
 Dynamic: home-page

{nci_cidc_api_modules-1.1.34.dist-info → nci_cidc_api_modules-1.1.37.dist-info}/RECORD

@@ -1,23 +1,24 @@
 cidc_api/config/__init__.py,sha256=5mX8GAPxUKV84iS-aGOoE-4m68LsOCGCDptXNdlgvj0,148
-cidc_api/config/db.py,sha256=cyWhWtmXha4OsrwUf6ez8aKSfm7tPSmPDE9JVSBx3Fk,1935
+cidc_api/config/db.py,sha256=5rf7kIowkiJIqJj2_JtO1cY9L55IjJBonJ-vThA4cGo,1960
 cidc_api/config/logging.py,sha256=abhVYtn8lfhIt0tyV2WHFgSmp_s2eeJh7kodB6LH4J0,1149
 cidc_api/config/secrets.py,sha256=jRFj7W43pWuPf9DZQLCKF7WPXf5cUv-BAaS3ASqhV_Q,1481
 cidc_api/config/settings.py,sha256=mA-4r7oB60uFepYtl5abbPigjwX8aBz__qCJXdcWWbs,4272
 cidc_api/models/__init__.py,sha256=bl445G8Zic9YbhZ8ZBni07wtBMhLJRMBA-JqjLxx2bw,66
 cidc_api/models/migrations.py,sha256=gp9vtkYbA9FFy2s-7woelAmsvQbJ41LO2_DY-YkFIrQ,11464
-cidc_api/models/models.py,sha256=JceOfSBetV6ifhYIPL4Qp0T3YpG55M016YvEajLUQ8o,132587
-cidc_api/models/schemas.py,sha256=7tDYtmULuzTt2kg7RorWhte06ffalgpQKrFiDRGcPEQ,2711
+cidc_api/models/models.py,sha256=u2SA3R0xaVgdoU8nnnl2dptt_hMtkdgQcmZhdEQbLv4,141631
+cidc_api/models/schemas.py,sha256=6IE2dJoEMcMbi0Vr1V3cYKnPKU0hv9vRKBixOZHe88s,2766
 cidc_api/models/files/__init__.py,sha256=8BMTnUSHzUbz0lBeEQY6NvApxDD3GMWMduoVMos2g4Y,213
-cidc_api/models/files/details.py,sha256=WrWPxJqlsteinoNbGTaQ3fcxgvChqLGJ9vY7H829jtk,62842
-cidc_api/models/files/facets.py,sha256=JqCmwcjYYSz7XK4bAokSE9i71C8t9EQ4Jtbv7npth7M,29391
+cidc_api/models/files/details.py,sha256=sZkGM7iEV4-J6IDQCdiMV6KBDLbPxCOqUMaU3aY9rX8,65153
+cidc_api/models/files/facets.py,sha256=WqjfqtYJgY2tBnZ598Yc0eJdQUo2slFNLyTDaqPx_DE,32318
 cidc_api/shared/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 cidc_api/shared/auth.py,sha256=PHqmVGkqDjbmUofytVFwD_9ssgUomESl3fFtFHPwZYQ,9062
-cidc_api/shared/emails.py,sha256=GY-l0EkoVU_3hjV0g-xo7N9d1iyCdluyq_arftEPPe0,4989
-cidc_api/shared/gcloud_client.py,sha256=oD7Y3Glp1ZrPYkonv7DvX1koGtF30lgm3ENXYQ7G5cI,35634
+cidc_api/shared/emails.py,sha256=HQIixEUsR8yyu7Iv8S81RjtvEQeGuzQHzBfGsWIfP7k,4961
+cidc_api/shared/file_handling.py,sha256=z9Fza4PNTQ2U2VgMEiwx-Xpsp1AKgJuBugEl8loglec,2334
+cidc_api/shared/gcloud_client.py,sha256=tgi6Ja31EUQcJueAIYHc3VyrMchoMZCdui1eruakCLg,36351
 cidc_api/shared/jose.py,sha256=-qzGzEDAlokEp9E7WtBtQkXyyfPWTYXlwYpCqVJWmqM,1830
 cidc_api/shared/rest_utils.py,sha256=RwR30WOUAYCxL7V-i2totEyeriG30GbBDvBcpLXhM9w,6594
-nci_cidc_api_modules-1.1.34.dist-info/licenses/LICENSE,sha256=pNYWVTHaYonnmJyplmeAp7tQAjosmDpAWjb34jjv7Xs,1102
-nci_cidc_api_modules-1.1.34.dist-info/METADATA,sha256=RLRMhMdB-8zd-vX3O77F8VEdQf4cHISKnBF7fy-aEMc,41285
-nci_cidc_api_modules-1.1.34.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-nci_cidc_api_modules-1.1.34.dist-info/top_level.txt,sha256=rNiRzL0lJGi5Q9tY9uSoMdTbJ-7u5c_D2E86KA94yRA,9
-nci_cidc_api_modules-1.1.34.dist-info/RECORD,,
+nci_cidc_api_modules-1.1.37.dist-info/licenses/LICENSE,sha256=pNYWVTHaYonnmJyplmeAp7tQAjosmDpAWjb34jjv7Xs,1102
+nci_cidc_api_modules-1.1.37.dist-info/METADATA,sha256=lkOyyerechLmU60nEzlIxONbexRRnvVbB1T1qApjjtM,41284
+nci_cidc_api_modules-1.1.37.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+nci_cidc_api_modules-1.1.37.dist-info/top_level.txt,sha256=rNiRzL0lJGi5Q9tY9uSoMdTbJ-7u5c_D2E86KA94yRA,9
+nci_cidc_api_modules-1.1.37.dist-info/RECORD,,