From ed7e01a39578226b912e1dc49acfdb6a278026f0 Mon Sep 17 00:00:00 2001
From: Abdulraahman Dabbagh <1924466@stud.hs-mannheim.de>
Date: Sun, 25 May 2025 10:43:44 +0200
Subject: [PATCH] Backend Flask aufsetzen (Ticket #4)

---
 .flake8                                       |  3 +
 .pre-commit-config.yaml                       | 11 +++
 docker-compose.yml                            | 14 +++
 project/backend/Dockerfile                    | 15 ++++
 project/backend/README.md                     | 85 +++++++++++++++++++
 project/backend/app.py                        | 67 +++++++++++++++
 project/backend/requirements.txt              |  4 +
 .../fine_tuning_spaCy/annotated_data.json     |  2 +
 prototypes/fine_tuning_spaCy/neue_kennzahl.py | 17 ++++
 9 files changed, 218 insertions(+)
 create mode 100644 .flake8
 create mode 100644 .pre-commit-config.yaml
 create mode 100644 docker-compose.yml
 create mode 100644 project/backend/Dockerfile
 create mode 100644 project/backend/README.md
 create mode 100644 project/backend/app.py
 create mode 100644 project/backend/requirements.txt
 create mode 100644 prototypes/fine_tuning_spaCy/annotated_data.json
 create mode 100644 prototypes/fine_tuning_spaCy/neue_kennzahl.py

diff --git a/.flake8 b/.flake8
new file mode 100644
index 0000000..e2f249a
--- /dev/null
+++ b/.flake8
@@ -0,0 +1,3 @@
+# .flake8
+[flake8]
+max-line-length = 88
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
new file mode 100644
index 0000000..9fcd752
--- /dev/null
+++ b/.pre-commit-config.yaml
@@ -0,0 +1,11 @@
+repos:
+  - repo: https://github.com/psf/black
+    rev: 23.3.0
+    hooks:
+      - id: black
+        language_version: python3
+
+  - repo: https://github.com/pycqa/flake8
+    rev: 6.1.0
+    hooks:
+      - id: flake8
diff --git a/docker-compose.yml b/docker-compose.yml
new file mode 100644
index 0000000..ae56aab
--- /dev/null
+++ b/docker-compose.yml
@@ -0,0 +1,14 @@
+services:
+  backend:
+    build: ./project/backend
+    container_name: fundfuechse-backend
+    ports:
+      - "5000:5000"
+    restart: always
+
+  # frontend:
+  #   build: ./project/frontend
+  #   container_name: fundfuechse-frontend
+  #   ports:
+  #     - "3000:80"
+  #   restart: always
diff --git a/project/backend/Dockerfile b/project/backend/Dockerfile
new file mode 100644
index 0000000..196f4bc
--- /dev/null
+++ b/project/backend/Dockerfile
@@ -0,0 +1,15 @@
+# 1. Python-Image verwenden
+FROM python:3.11-slim
+
+# 2. Arbeitsverzeichnis im Container setzen
+WORKDIR /app
+
+# 3. requirements.txt kopieren und Pakete installieren
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# 4. Quellcode kopieren (z. B. app.py)
+COPY . .
+
+# 5. Flask-App starten
+CMD ["python", "app.py"]
diff --git a/project/backend/README.md b/project/backend/README.md
new file mode 100644
index 0000000..67e6f69
--- /dev/null
+++ b/project/backend/README.md
@@ -0,0 +1,85 @@
+##  Setup
+
+### Voraussetzungen
+
+- Python 3.11+
+- pip
+- Docker (Desktop)
+- Optional: `pre-commit`
+
+### Abhängigkeiten installieren
+
+```bash
+pip install -r requirements.txt
+
+# Codequalität (lokal prüfen)
+black app.py
+flake8 app.py
+
+
+## Anwendung starten
+
+### Lokal 
+
+1. Abhängigkeiten installieren:
+
+```bash
+pip install -r requirements.txt
+```
+
+2. Flask-App starten:
+
+```bash
+python app.py
+```
+
+3. Aufrufen im Browser:
+
+```
+http://localhost:5000/
+```
+
+---
+
+###  Option 2: Mit Docker
+
+1. Image bauen:
+
+```bash
+docker build -t fundfuechse-backend .
+```
+
+2. Container starten:
+
+```bash
+docker run -p 5000:5000 fundfuechse-backend
+```
+
+Die API läuft dann unter:
+
+```
+http://localhost:5000/
+```
+
+---
+
+###  Option 3: Mit docker-compose
+
+```bash
+docker-compose up --build
+```
+
+Danach ist der Service erreichbar unter:
+
+```
+http://localhost:5000/
+```
+
+---
+
+### Testaufruf per curl (PDF hochladen)
+
+```bash
+curl.exe -X POST -F "file=@Pitchbook 1.pdf" http://localhost:5000/upload
+```
+
diff --git a/project/backend/app.py b/project/backend/app.py
new file mode 100644
index 0000000..ecb21ef
--- /dev/null
+++ b/project/backend/app.py
@@ -0,0 +1,67 @@
+from flask import Flask, jsonify
+from flask import request
+import os
+
+app = Flask(__name__)
+
+
+# Startseite
+@app.route("/")
+def hello():
+    return "Startseite"
+
+
+# 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("/dummy_results", methods=["GET"])
+def get_dummy_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")
diff --git a/project/backend/requirements.txt b/project/backend/requirements.txt
new file mode 100644
index 0000000..8822904
--- /dev/null
+++ b/project/backend/requirements.txt
@@ -0,0 +1,4 @@
+Flask
+black
+flake8
+pre-commit
diff --git a/prototypes/fine_tuning_spaCy/annotated_data.json b/prototypes/fine_tuning_spaCy/annotated_data.json
new file mode 100644
index 0000000..728d74a
--- /dev/null
+++ b/prototypes/fine_tuning_spaCy/annotated_data.json
@@ -0,0 +1,2 @@
+{"text": "Das geplante Projektvolumen beträgt 120 Mio. €.", "entities": [[28, 44, "KENNZAHL"]]}
+{"text": "Das geplante Projektvolumen beträgt 120 Mio. €.", "entities": [[28, 44, "KENNZAHL"]]}
diff --git a/prototypes/fine_tuning_spaCy/neue_kennzahl.py b/prototypes/fine_tuning_spaCy/neue_kennzahl.py
new file mode 100644
index 0000000..696b851
--- /dev/null
+++ b/prototypes/fine_tuning_spaCy/neue_kennzahl.py
@@ -0,0 +1,17 @@
+import streamlit as st
+import json
+
+st.title("Neue Kennzahl annotieren")
+
+text = st.text_area("Text", "Das geplante Projektvolumen beträgt 120 Mio. €.")
+start = st.number_input("Start-Position", min_value=0, max_value=len(text), value=28)
+end = st.number_input("End-Position", min_value=0, max_value=len(text), value=44)
+label = st.text_input("Label (z. B. KENNZAHL)", "KENNZAHL")
+
+if st.button("Speichern"):
+    example = {"text": text, "entities": [[start, end, label]]}
+
+    with open("annotated_data.json", "a", encoding="utf-8") as f:
+        f.write(json.dumps(example, ensure_ascii=False) + "\n")
+
+    st.success("✅ Annotation gespeichert!")