Refactor coordinator/app.py and add new controllers and models

closes #29
add persistence for pitch-books, spacy model and setttings

.gitignore

@@ -2,4 +2,10 @@
 .DS_Store
 
 # Python virtual environments
-.venv/
+**/.venv/
+**/venv
+**/__pycache__
+**/.env
+**/node_modules
+**/build
+**/dist

project/backend/coordinator/app.py

@@ -1,66 +1,28 @@
-from flask import Flask, jsonify
+from flask import Flask
-from flask import request
 import os
+from dotenv import load_dotenv
+from controller import register_routes
+from model.database import init_db
 
 app = Flask(__name__)
 
+load_dotenv()
+DATABASE_URL = os.getenv("DATABASE_URL")
+
+app.config["SQLALCHEMY_DATABASE_URI"] = DATABASE_URL
+app.config["SQLALCHEMY_TRACK_MODIFICATIONS"] = True
+app.config["MAX_CONTENT_LENGTH"] = 100 * 1024 * 1024  # 100 MB
+
+init_db(app)
+
+register_routes(app)
+
 
 @app.route("/health")
 def health_check():
     return "OK"
 
 
-# gibt Beispiel-Konfig der Kennzahlen zurück (für die UI)
-@app.route("/config", methods=["GET"])
-def get_config():
-    config = [
-        {"name": "Fondname", "format": "Text", "required": True},
-        {"name": "IRR", "format": "Prozent", "required": False},
-    ]
-    return jsonify(config)
-
-
-# liefert Beispiel-Ergebnisse der Extraktion
-@app.route("/extraction_results", methods=["GET"])
-def get_extraction_results():
-    results = [
-        {"label": "Fondname", "entity": "ABC Fonds", "page": 1, "status": "validated"},
-        {
-            "label": "IRR",
-            "entity": "6,0%",
-            "page": 3,
-            "status": "single-source",
-            "source": "spaCy",
-        },
-    ]
-    return jsonify(results)
-
-
-# legt Upload-Ordner an, falls nicht vorhanden
-UPLOAD_FOLDER = "uploads"
-os.makedirs(UPLOAD_FOLDER, exist_ok=True)
-
-
-# nimmt eine PDF-Datei per POST entgegen und speichert sie
-@app.route("/upload", methods=["POST"])
-def upload_pdf():
-    if "file" not in request.files:
-        return {"error": "Keine Datei hochgeladen."}, 400
-
-    file = request.files["file"]
-
-    if file.filename == "":
-        return {"error": "Dateiname fehlt."}, 400
-
-    if not file.filename.endswith(".pdf"):
-        return {"error": "Nur PDF-Dateien erlaubt."}, 400
-
-    file_path = os.path.join(UPLOAD_FOLDER, file.filename)
-    file.save(file_path)
-
-    return {"message": f"Datei {file.filename} erfolgreich gespeichert!"}, 200
-
-
 # für Docker wichtig: host='0.0.0.0'
 if __name__ == "__main__":
     app.run(debug=True, host="0.0.0.0")

project/backend/coordinator/controller/__init__.py

@@ -0,0 +1,9 @@
+from controller.spacy_contoller import spacy_controller
+from controller.kpi_setting_controller import kpi_setting_controller
+from controller.pitch_book_controller import pitch_book_controller
+
+
+def register_routes(app):
+    app.register_blueprint(kpi_setting_controller)
+    app.register_blueprint(pitch_book_controller)
+    app.register_blueprint(spacy_controller)

project/backend/coordinator/controller/kpi_setting_controller.py

@@ -0,0 +1,116 @@
+from flask import Blueprint, request, jsonify
+from model.database import db
+from model.kpi_setting_model import KPISettingModel, KPISettingType
+
+
+kpi_setting_controller = Blueprint(
+    "kpi_settings", __name__, url_prefix="/api/kpi_setting"
+)
+
+
+@kpi_setting_controller.route("/", methods=["GET"])
+def get_all_kpi_settings():
+    kpi_settings = KPISettingModel.query.all()
+    return jsonify([kpi_setting.to_dict() for kpi_setting in kpi_settings]), 200
+
+
+@kpi_setting_controller.route("/<int:id>", methods=["GET"])
+def get_kpi_setting(id):
+    kpi_setting = KPISettingModel.query.get_or_404(id)
+    return jsonify(kpi_setting.to_dict()), 200
+
+
+@kpi_setting_controller.route("/", methods=["POST"])
+def create_kpi_setting():
+    data = request.json
+
+    if not data:
+        return jsonify({"error": "No data provided"}), 400
+
+    required_fields = [
+        "name",
+        "description",
+        "mandatory",
+        "type",
+        "translation",
+        "example",
+    ]
+    for field in required_fields:
+        if field not in data:
+            return jsonify({"error": f"Missing required field: {field}"}), 400
+
+    # Check if name already exists
+    existing_kpi = KPISettingModel.query.filter_by(name=data["name"]).first()
+    if existing_kpi:
+        return jsonify({"error": "KPI Setting with this name already exists"}), 409
+
+    # Validate type enum
+    try:
+        kpi_type = KPISettingType(data["type"])
+    except ValueError:
+        valid_types = [t.value for t in KPISettingType]
+        return jsonify({"error": f"Invalid type. Must be one of: {valid_types}"}), 400
+
+    new_kpi_setting = KPISettingModel(
+        name=data["name"],
+        description=data["description"],
+        mandatory=data["mandatory"],
+        type=kpi_type,
+        translation=data["translation"],
+        example=data["example"],
+    )
+
+    db.session.add(new_kpi_setting)
+    db.session.commit()
+
+    return jsonify(new_kpi_setting.to_dict()), 201
+
+
+@kpi_setting_controller.route("/<int:id>", methods=["PUT"])
+def update_kpi_setting(id):
+    kpi_setting = KPISettingModel.query.get_or_404(id)
+    data = request.json
+
+    if not data:
+        return jsonify({"error": "No data provided"}), 400
+
+    if "name" in data and data["name"] != kpi_setting.name:
+        existing_kpi = KPISettingModel.query.filter_by(name=data["name"]).first()
+        if existing_kpi:
+            return jsonify({"error": "KPI Setting with this name already exists"}), 409
+        kpi_setting.name = data["name"]
+
+    if "description" in data:
+        kpi_setting.description = data["description"]
+
+    if "mandatory" in data:
+        kpi_setting.mandatory = data["mandatory"]
+
+    if "type" in data:
+        try:
+            kpi_setting.type = KPISettingType(data["type"])
+        except ValueError:
+            valid_types = [t.value for t in KPISettingType]
+            return (
+                jsonify({"error": f"Invalid type. Must be one of: {valid_types}"}),
+                400,
+            )
+
+    if "translation" in data:
+        kpi_setting.translation = data["translation"]
+
+    if "example" in data:
+        kpi_setting.example = data["example"]
+
+    db.session.commit()
+
+    return jsonify(kpi_setting.to_dict()), 200
+
+
+@kpi_setting_controller.route("/<int:id>", methods=["DELETE"])
+def delete_kpi_setting(id):
+    kpi_setting = KPISettingModel.query.get_or_404(id)
+    db.session.delete(kpi_setting)
+    db.session.commit()
+
+    return jsonify({"message": f"KPI Setting {id} deleted successfully"}), 200

project/backend/coordinator/controller/pitch_book_controller.py

@@ -0,0 +1,97 @@
+from flask import Blueprint, request, jsonify, send_file
+from model.database import db
+from model.pitch_book_model import PitchBookModel
+from io import BytesIO
+from werkzeug.utils import secure_filename
+import puremagic
+
+
+pitch_book_controller = Blueprint("pitch_books", __name__, url_prefix="/api/pitch_book")
+
+
+@pitch_book_controller.route("/", methods=["GET"])
+def get_all_files():
+    files = PitchBookModel.query.all()
+    return jsonify([file.to_dict() for file in files]), 200
+
+
+@pitch_book_controller.route("/<int:id>", methods=["GET"])
+def get_file(id):
+    file = PitchBookModel.query.get_or_404(id)
+    return jsonify(file.to_dict()), 200
+
+
+@pitch_book_controller.route("/<int:id>/download", methods=["GET"])
+def download_file(id):
+    file = PitchBookModel.query.get_or_404(id)
+    return send_file(
+        BytesIO(file.file), download_name=file.filename, as_attachment=True
+    )
+
+
+@pitch_book_controller.route("/", methods=["POST"])
+def upload_file():
+    if "file" not in request.files:
+        return jsonify({"error": "No file part in the request"}), 400
+
+    uploaded_file = request.files["file"]
+    if uploaded_file.filename == "":
+        return jsonify({"error": "No selected file"}), 400
+
+    # Read file data once
+    file_data = uploaded_file.read()
+
+    try:
+        if (
+            uploaded_file
+            and puremagic.from_string(file_data, mime=True) == "application/pdf"
+        ):
+            fileName = uploaded_file.filename or ""
+            new_file = PitchBookModel(
+                filename=secure_filename(fileName), file=file_data
+            )
+
+            db.session.add(new_file)
+            db.session.commit()
+
+            return jsonify(new_file.to_dict()), 201
+    except Exception as e:
+        print(e)
+    return jsonify({"error": "Invalid file format. Only PDF files are accepted"}), 400
+
+
+@pitch_book_controller.route("/<int:id>", methods=["PUT"])
+def update_file(id):
+    file = PitchBookModel.query.get_or_404(id)
+
+    if "file" in request.files:
+        uploaded_file = request.files["file"]
+        if uploaded_file.filename != "":
+            file.filename = uploaded_file.filename
+
+            # Read file data once
+            file_data = uploaded_file.read()
+            try:
+                if (
+                    uploaded_file
+                    and puremagic.from_string(file_data, mime=True) == "application/pdf"
+                ):
+                    file.file = file_data
+            except Exception as e:
+                print(e)
+
+    if "kpi" in request.form:
+        file.kpi = request.form.get("kpi")
+
+    db.session.commit()
+
+    return jsonify(file.to_dict()), 200
+
+
+@pitch_book_controller.route("/<int:id>", methods=["DELETE"])
+def delete_file(id):
+    file = PitchBookModel.query.get_or_404(id)
+    db.session.delete(file)
+    db.session.commit()
+
+    return jsonify({"message": f"File {id} deleted successfully"}), 200

project/backend/coordinator/controller/spacy_contoller.py

@@ -0,0 +1,93 @@
+from flask import Blueprint, request, jsonify, send_file
+from io import BytesIO
+
+from model.spacy_model import SpacyModel
+import puremagic
+from werkzeug.utils import secure_filename
+from model.database import db
+
+
+spacy_controller = Blueprint("spacy", __name__, url_prefix="/api/spacy")
+
+
+@spacy_controller.route("/", methods=["GET"])
+def get_all_files():
+    files = SpacyModel.query.all()
+    return jsonify([file.to_dict() for file in files]), 200
+
+
+@spacy_controller.route("/<int:id>", methods=["GET"])
+def get_file(id):
+    file = SpacyModel.query.get_or_404(id)
+    return jsonify(file.to_dict()), 200
+
+
+@spacy_controller.route("/<int:id>/download", methods=["GET"])
+def download_file(id):
+    file = SpacyModel.query.get_or_404(id)
+    return send_file(
+        BytesIO(file.file), download_name=file.filename, as_attachment=True
+    )
+
+
+@spacy_controller.route("/", methods=["POST"])
+def upload_file():
+    print(request)
+    if "file" not in request.files:
+        return jsonify({"error": "No file part in the request"}), 400
+
+    uploaded_file = request.files["file"]
+    if uploaded_file.filename == "":
+        return jsonify({"error": "No selected file"}), 400
+
+    # Read file data once
+    file_data = uploaded_file.read()
+    try:
+        if uploaded_file:
+            fileName = uploaded_file.filename or ""
+            new_file = SpacyModel(filename=secure_filename(fileName), file=file_data)
+
+            db.session.add(new_file)
+            db.session.commit()
+
+            return jsonify(new_file.to_dict()), 201
+    except Exception as e:
+        print(e)
+    return jsonify({"error": "Invalid file format. Only PDF files are accepted"}), 400
+
+
+@spacy_controller.route("/<int:id>", methods=["PUT"])
+def update_file(id):
+    file = SpacyModel.query.get_or_404(id)
+
+    if "file" in request.files:
+        uploaded_file = request.files["file"]
+        if uploaded_file.filename != "":
+            file.filename = uploaded_file.filename
+
+            # Read file data once
+            file_data = uploaded_file.read()
+            try:
+                if (
+                    uploaded_file
+                    and puremagic.from_string(file_data, mime=True) == "application/pdf"
+                ):
+                    file.file = file_data
+            except Exception as e:
+                print(e)
+
+    if "kpi" in request.form:
+        file.kpi = request.form.get("kpi")
+
+    db.session.commit()
+
+    return jsonify(file.to_dict()), 200
+
+
+@spacy_controller.route("/<int:id>", methods=["DELETE"])
+def delete_file(id):
+    file = SpacyModel.query.get_or_404(id)
+    db.session.delete(file)
+    db.session.commit()
+
+    return jsonify({"message": f"File {id} deleted successfully"}), 200

project/backend/coordinator/docker-compose.yml

@@ -0,0 +1,9 @@
+
+services:
+  db:
+    image: postgres
+    environment:
+      POSTGRES_PASSWORD: admin
+      POSTGRES_USER: admin
+    ports:
+      - "5432:5432"

project/backend/coordinator/model/database.py

@@ -0,0 +1,15 @@
+from flask_sqlalchemy import SQLAlchemy
+from sqlalchemy.orm import DeclarativeBase
+
+
+class Base(DeclarativeBase):
+    pass
+
+
+db = SQLAlchemy(model_class=Base)
+
+
+def init_db(app):
+    db.init_app(app)
+    with app.app_context():
+        db.create_all()

project/backend/coordinator/model/kpi_setting_model.py

@@ -0,0 +1,43 @@
+from model.database import db
+from sqlalchemy.orm import Mapped, mapped_column
+from sqlalchemy import Enum as SQLAlchemyEnum
+from enum import Enum
+
+
+class KPISettingType(Enum):
+    NUMBER = "number"
+    STRING = "string"
+    RANGE = "range"
+    BOOLEAN = "boolean"
+    ARRAY = "array"
+
+
+class KPISettingModel(db.Model):
+    id: Mapped[int] = mapped_column(primary_key=True)
+    name: Mapped[str] = mapped_column(unique=True)
+    description: Mapped[str]
+    mandatory: Mapped[bool]
+    type: Mapped[KPISettingType] = mapped_column(
+        SQLAlchemyEnum(KPISettingType, native_enum=True)
+    )
+    translation: Mapped[str]
+    example: Mapped[str]
+
+    def to_dict(self):
+        return {
+            "id": self.id,
+            "name": self.name,
+            "description": self.description,
+            "mandatory": self.mandatory,
+            "type": self.type.value,
+            "translation": self.translation,
+            "example": self.example,
+        }
+
+    def __init__(self, name, description, mandatory, type, translation, example):
+        self.name = name
+        self.description = description
+        self.mandatory = mandatory
+        self.type = type
+        self.translation = translation
+        self.example = example

project/backend/coordinator/model/pitch_book_model.py

@@ -0,0 +1,17 @@
+from model.database import db
+from sqlalchemy.orm import Mapped, mapped_column
+from sqlalchemy import LargeBinary
+
+
+class PitchBookModel(db.Model):
+    id: Mapped[int] = mapped_column(primary_key=True)
+    filename: Mapped[str] = mapped_column()
+    file: Mapped[bytes] = mapped_column(LargeBinary)
+    kpi: Mapped[str | None]
+
+    def to_dict(self):
+        return {"id": self.id, "filename": self.filename, "kpi": self.kpi}
+
+    def __init__(self, filename, file):
+        self.filename = filename
+        self.file = file

project/backend/coordinator/model/spacy_model.py

@@ -0,0 +1,22 @@
+from model.database import db
+from sqlalchemy.orm import Mapped, mapped_column
+from sqlalchemy import LargeBinary
+from datetime import datetime
+
+
+class SpacyModel(db.Model):
+    id: Mapped[int] = mapped_column(primary_key=True)
+    filename: Mapped[str] = mapped_column()
+    file: Mapped[bytes] = mapped_column(LargeBinary)
+    created_at: Mapped[datetime] = mapped_column(default=datetime.utcnow)
+
+    def to_dict(self):
+        return {
+            "id": self.id,
+            "filename": self.filename,
+            "created_at": self.created_at.isoformat(),
+        }
+
+    def __init__(self, filename, file):
+        self.filename = filename
+        self.file = file

project/backend/coordinator/requirements.txt

@@ -1,4 +1,31 @@
-Flask
+black==25.1.0
-black
+blinker==1.9.0
-flake8
+cfgv==3.4.0
-pre-commit
+click==8.2.1
+distlib==0.3.9
+filelock==3.18.0
+flake8==7.2.0
+Flask==3.1.1
+Flask-SQLAlchemy==3.1.1
+greenlet==3.2.2
+identify==2.6.12
+itsdangerous==2.2.0
+Jinja2==3.1.6
+MarkupSafe==3.0.2
+mccabe==0.7.0
+mypy_extensions==1.1.0
+nodeenv==1.9.1
+packaging==25.0
+pathspec==0.12.1
+platformdirs==4.3.8
+pre_commit==4.2.0
+psycopg2-binary==2.9.10
+puremagic==1.29
+pycodestyle==2.13.0
+pyflakes==3.3.2
+python-dotenv==1.1.0
+PyYAML==6.0.2
+SQLAlchemy==2.0.41
+typing_extensions==4.13.2
+virtualenv==20.31.2
+Werkzeug==3.1.3