from __future__ import annotations import json import re import uuid from html import escape from pathlib import Path from typing import Any from sqlalchemy.orm import Session from app.core.errors import AppError from app.models import AnalysisRun, Dataset, Export, Project, QualityCheck from app.schemas.export import ExportContentResponse, ExportCreateResponse, ExportListResponse, ExportRead from app.services.dataset_service import DatasetService from app.services.detection_service import DetectionService from app.services.segmentation_service import SegmentationService from app.services.storage_service import StorageService class ExportService: @staticmethod def export_dataset_geojson(db: Session, dataset_id: uuid.UUID, name: str | None = None) -> ExportCreateResponse: dataset = db.get(Dataset, dataset_id) if not dataset: raise AppError(code="DATASET_NOT_FOUND", message="Dataset not found", status_code=404) if dataset.dataset_type not in DatasetService.VECTOR_TYPES: raise AppError( code="INVALID_DATASET_TYPE", message="GeoJSON dataset export requires a vector dataset", details={"dataset_type": dataset.dataset_type}, status_code=400, ) feature_collection = DatasetService.get_dataset_geojson(db, dataset_id) filename = ExportService._filename(name, f"{dataset.id}.geojson", ".geojson") export_path = StorageService.dataset_export_path(str(dataset.project_id), str(dataset.id), filename) metadata = { "source": "dataset", "dataset_id": str(dataset.id), "project_id": str(dataset.project_id), "dataset_type": dataset.dataset_type, "feature_count": len(feature_collection.get("features", [])), } export = ExportService._write_json_export( db, project_id=dataset.project_id, analysis_run_id=None, export_type="dataset_geojson", storage_path=export_path, content=feature_collection, metadata=metadata, ) return ExportService._create_response(export) @staticmethod def export_detection_run_geojson(db: Session, analysis_run_id: uuid.UUID, name: str | None = None) -> ExportCreateResponse: run = db.get(AnalysisRun, analysis_run_id) if not run or run.analysis_type != "detection": raise AppError(code="DETECTION_RUN_NOT_FOUND", message="Detection run not found", status_code=404) feature_collection = DetectionService.detections_to_geojson(db, analysis_run_id=analysis_run_id) filename = ExportService._filename(name, f"{run.id}-detections.geojson", ".geojson") export_path = StorageService.dataset_export_path(str(run.project_id), str(run.dataset_id or run.id), filename) metadata = { "source": "detection_run", "analysis_run_id": str(run.id), "project_id": str(run.project_id), "dataset_id": str(run.dataset_id) if run.dataset_id else None, "feature_count": len(feature_collection.get("features", [])), } export = ExportService._write_json_export( db, project_id=run.project_id, analysis_run_id=run.id, export_type="detection_geojson", storage_path=export_path, content=feature_collection, metadata=metadata, ) return ExportService._create_response(export) @staticmethod def export_segmentation_run_geojson(db: Session, analysis_run_id: uuid.UUID, name: str | None = None) -> ExportCreateResponse: run = db.get(AnalysisRun, analysis_run_id) if not run or run.analysis_type != "segmentation": raise AppError(code="SEGMENTATION_RUN_NOT_FOUND", message="Segmentation run not found", status_code=404) feature_collection = SegmentationService.segmentations_to_geojson(db, analysis_run_id=analysis_run_id) filename = ExportService._filename(name, f"{run.id}-segmentations.geojson", ".geojson") export_path = StorageService.dataset_export_path(str(run.project_id), str(run.dataset_id or run.id), filename) metadata = { "source": "segmentation_run", "analysis_run_id": str(run.id), "project_id": str(run.project_id), "dataset_id": str(run.dataset_id) if run.dataset_id else None, "feature_count": len(feature_collection.get("features", [])), } export = ExportService._write_json_export( db, project_id=run.project_id, analysis_run_id=run.id, export_type="segmentation_geojson", storage_path=export_path, content=feature_collection, metadata=metadata, ) return ExportService._create_response(export) @staticmethod def export_project_metadata(db: Session, project_id: uuid.UUID, name: str | None = None) -> ExportCreateResponse: project = db.get(Project, project_id) if not project: raise AppError(code="PROJECT_NOT_FOUND", message="Project not found", status_code=404) content = ExportService._project_summary(db, project) filename = ExportService._filename(name, f"{project.id}-metadata.json", ".json") export_path = StorageService.dataset_export_path(str(project.id), "project", filename) metadata = { "source": "project_metadata", "project_id": str(project.id), "dataset_count": len(content["datasets"]), "quality_check_count": len(content["quality_checks"]), "export_count": len(content["exports"]), } export = ExportService._write_json_export( db, project_id=project.id, analysis_run_id=None, export_type="project_metadata_json", storage_path=export_path, content=content, metadata=metadata, ) return ExportService._create_response(export) @staticmethod def export_project_report(db: Session, project_id: uuid.UUID, name: str | None = None) -> ExportCreateResponse: project = db.get(Project, project_id) if not project: raise AppError(code="PROJECT_NOT_FOUND", message="Project not found", status_code=404) summary = ExportService._project_summary(db, project) html = ExportService._render_project_report_html(summary) filename = ExportService._filename(name, f"{project.id}-report.html", ".html") export_path = StorageService.dataset_export_path(str(project.id), "project", filename) metadata = { "source": "project_report", "project_id": str(project.id), "dataset_count": len(summary["datasets"]), "quality_check_count": len(summary["quality_checks"]), "export_count": len(summary["exports"]), "format": "html", } export = ExportService._write_text_export( db, project_id=project.id, analysis_run_id=None, export_type="project_report_html", storage_path=export_path, content=html, metadata=metadata, ) return ExportService._create_response(export) @staticmethod def list_project_exports(db: Session, project_id: uuid.UUID, limit: int = 50, offset: int = 0) -> ExportListResponse: if not db.get(Project, project_id): raise AppError(code="PROJECT_NOT_FOUND", message="Project not found", status_code=404) query = db.query(Export).filter(Export.project_id == project_id).order_by(Export.created_at.desc()) rows = query.offset(offset).limit(limit).all() total = query.count() return ExportListResponse( items=[ExportRead.model_validate(row) for row in rows], total=total, limit=limit, offset=offset, ) @staticmethod def get_export(db: Session, export_id: uuid.UUID) -> ExportRead: export = db.get(Export, export_id) if not export: raise AppError(code="EXPORT_NOT_FOUND", message="Export not found", status_code=404) return ExportRead.model_validate(export) @staticmethod def get_export_content(db: Session, export_id: uuid.UUID) -> ExportContentResponse: export = db.get(Export, export_id) if not export: raise AppError(code="EXPORT_NOT_FOUND", message="Export not found", status_code=404) path = ExportService.get_export_download_path(db, export_id) try: content = json.loads(path.read_text(encoding="utf-8")) except json.JSONDecodeError as exc: raise AppError(code="EXPORT_CONTENT_INVALID", message="Export artifact is not valid JSON", status_code=422) from exc return ExportContentResponse(export_id=export.id, export_type=export.export_type, content=content) @staticmethod def get_export_download_path(db: Session, export_id: uuid.UUID) -> Path: export = db.get(Export, export_id) if not export: raise AppError(code="EXPORT_NOT_FOUND", message="Export not found", status_code=404) path = Path(export.storage_path) if not path.exists() or not path.is_file(): raise AppError( code="EXPORT_CONTENT_NOT_FOUND", message="Export artifact is missing from storage", details={"storage_path": export.storage_path}, status_code=404, ) return path @staticmethod def _write_json_export( db: Session, *, project_id: uuid.UUID, analysis_run_id: uuid.UUID | None, export_type: str, storage_path: str, content: dict[str, Any], metadata: dict[str, Any], ) -> Export: path = Path(storage_path) path.parent.mkdir(parents=True, exist_ok=True) path.write_text(json.dumps(content, ensure_ascii=False, indent=2), encoding="utf-8") return ExportService._persist_export( db, project_id=project_id, analysis_run_id=analysis_run_id, export_type=export_type, storage_path=str(path), metadata=metadata, ) @staticmethod def _write_text_export( db: Session, *, project_id: uuid.UUID, analysis_run_id: uuid.UUID | None, export_type: str, storage_path: str, content: str, metadata: dict[str, Any], ) -> Export: path = Path(storage_path) path.parent.mkdir(parents=True, exist_ok=True) path.write_text(content, encoding="utf-8") return ExportService._persist_export( db, project_id=project_id, analysis_run_id=analysis_run_id, export_type=export_type, storage_path=str(path), metadata=metadata, ) @staticmethod def _persist_export( db: Session, *, project_id: uuid.UUID, analysis_run_id: uuid.UUID | None, export_type: str, storage_path: str, metadata: dict[str, Any], ) -> Export: export = Export( id=uuid.uuid4(), project_id=project_id, analysis_run_id=analysis_run_id, export_type=export_type, storage_path=storage_path, metadata_json=metadata, ) db.add(export) db.commit() db.refresh(export) return export @staticmethod def _project_summary(db: Session, project: Project) -> dict[str, Any]: datasets = db.query(Dataset).filter(Dataset.project_id == project.id).order_by(Dataset.created_at.desc()).all() quality_checks = ( db.query(QualityCheck) .filter(QualityCheck.project_id == project.id) .order_by(QualityCheck.created_at.desc()) .all() ) exports = db.query(Export).filter(Export.project_id == project.id).order_by(Export.created_at.desc()).all() return { "project": { "id": str(project.id), "name": project.name, "description": project.description, "region": project.region, "status": project.status, }, "datasets": [ { "id": str(dataset.id), "name": dataset.name, "dataset_type": dataset.dataset_type, "dataset_role": dataset.dataset_role, "source_name": dataset.source_name, "reference_layer_name": dataset.reference_layer_name, "status": dataset.status, "crs": dataset.crs, "bounds_json": dataset.bounds_json, "feature_count": (dataset.metadata_json or {}).get("feature_count"), } for dataset in datasets ], "quality_checks": [ { "id": str(check.id), "analysis_run_id": str(check.analysis_run_id) if check.analysis_run_id else None, "candidate_dataset_id": str(check.candidate_dataset_id) if check.candidate_dataset_id else None, "reference_dataset_id": str(check.reference_dataset_id), "check_type": check.check_type, "status": check.status, "score": check.score, } for check in quality_checks ], "exports": [ { "id": str(export.id), "analysis_run_id": str(export.analysis_run_id) if export.analysis_run_id else None, "export_type": export.export_type, "storage_path": export.storage_path, "metadata_json": export.metadata_json, "created_at": export.created_at.isoformat() if export.created_at else None, } for export in exports ], } @staticmethod def _render_project_report_html(summary: dict[str, Any]) -> str: project = summary["project"] datasets = summary["datasets"] quality_checks = summary["quality_checks"] exports = summary["exports"] dataset_rows = "\n".join( "" f"{escape(str(item['name']))}" f"{escape(str(item['dataset_type']))}" f"{escape(str(item['dataset_role']))}" f"{escape(str(item['status']))}" f"{escape(str(item['feature_count'] if item['feature_count'] is not None else 'n/a'))}" "" for item in datasets ) quality_rows = "\n".join( "" f"{escape(str(item['check_type']))}" f"{escape(str(item['status']))}" f"{escape(str(item['score'] if item['score'] is not None else 'n/a'))}" f"{escape(str(item['reference_dataset_id']))}" "" for item in quality_checks ) export_rows = "\n".join( "" f"{escape(str(item['export_type']))}" f"{escape(str(item['storage_path']))}" f"{escape(str(item['created_at'] or 'n/a'))}" "" for item in exports ) return f""" GeoIntel Project Report - {escape(str(project["name"]))}

{escape(str(project["name"]))}

GeoIntel project report artifact

Region: {escape(str(project["region"]))}

Status: {escape(str(project["status"]))}

Description: {escape(str(project["description"] or "n/a"))}

Datasets ({len(datasets)})

{dataset_rows or ''}
NameTypeRoleStatusFeatures
No datasets

QA/QC Results ({len(quality_checks)})

{quality_rows or ''}
CheckStatusScoreReference dataset
No QA/QC results

Export History ({len(exports)})

{export_rows or ''}
TypeStorage pathCreated
No exports
""" @staticmethod def _create_response(export: Export) -> ExportCreateResponse: return ExportCreateResponse( export_id=export.id, path=export.storage_path, status="ready", export_type=export.export_type, metadata_json=export.metadata_json, ) @staticmethod def _filename(name: str | None, fallback: str, suffix: str) -> str: raw_name = name or fallback cleaned = re.sub(r"[^A-Za-z0-9_.-]+", "_", raw_name).strip("._") if not cleaned: cleaned = fallback if not cleaned.lower().endswith(suffix): cleaned = f"{cleaned}{suffix}" return cleaned