WIP: Fehler F401 behoben, cleanup vor Branchwechsel

project/backend/coordinator/app.py

@@ -7,6 +7,7 @@ from model.database import init_db
 from controller.socketIO import socketio
 from controller.kennzahlen import kennzahlen_bp
 
+
 app = Flask(__name__)
 CORS(app)
 socketio.init_app(app)
@@ -25,6 +26,7 @@ register_routes(app)
 # Register blueprints
 app.register_blueprint(kennzahlen_bp)
 
+
 @app.route("/health")
 def health_check():
     return "OK"

project/backend/coordinator/controller/__init__.py

@@ -1,4 +1,4 @@
-from controller.spacy_contoller import spacy_controller
+from controller.spacy_controller import spacy_controller
 from controller.kpi_setting_controller import kpi_setting_controller
 from controller.pitch_book_controller import pitch_book_controller
 from controller.progress_controller import progress_controller

project/backend/coordinator/controller/spacy_controller.py

@@ -1,10 +1,11 @@
 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
+import os
+import json
 
 
 spacy_controller = Blueprint("spacy", __name__, url_prefix="/api/spacy")
@@ -91,3 +92,39 @@ def delete_file(id):
     db.session.commit()
 
     return jsonify({"message": f"File {id} deleted successfully"}), 200
+
+
+@spacy_controller.route("/append-training-entry", methods=["POST"])
+def append_training_entry():
+    entry = request.get_json()
+
+    if not entry or "text" not in entry or "entities" not in entry:
+        return (
+            jsonify(
+                {"error": "Ungültiges Format – 'text' und 'entities' erforderlich."}
+            ),
+            400,
+        )
+
+    path = os.path.join("spacy_training", "annotation_data.json")
+
+    try:
+        os.makedirs(os.path.dirname(path), exist_ok=True)
+
+        if os.path.exists(path):
+            with open(path, "r", encoding="utf-8") as f:
+                data = json.load(f)
+        else:
+            data = []
+
+        if entry in data:
+            return jsonify({"message": "Eintrag existiert bereits."}), 200
+
+        data.append(entry)
+        with open(path, "w", encoding="utf-8") as f:
+            json.dump(data, f, indent=2, ensure_ascii=False)
+
+        return jsonify({"message": "Eintrag erfolgreich gespeichert."}), 200
+    except Exception as e:
+        print(f"[ERROR] Fehler beim Schreiben: {e}")
+        return jsonify({"error": "Interner Fehler beim Schreiben."}), 500

project/backend/spacy-service/app.py

@@ -3,12 +3,19 @@ from extractSpacy import extract
 import requests
 import os
 import json
+from flask_cors import CORS
+
 
 app = Flask(__name__)
+CORS(app)
 
-VALIDATE_SERVICE_URL = os.getenv("VALIDATE_SERVICE_URL", "http://localhost:5054/validate")
 
-@app.route('/extract', methods=['POST'])
+VALIDATE_SERVICE_URL = os.getenv(
+    "VALIDATE_SERVICE_URL", "http://localhost:5054/validate"
+)
+
+
+@app.route("/extract", methods=["POST"])
 def extract_pdf():
     json_data = request.get_json()
 
@@ -16,19 +23,19 @@ def extract_pdf():
     pages_data = json_data["extracted_text_per_page"]
 
     entities_json = extract(pages_data)
-    entities = json.loads(entities_json) if isinstance(entities_json, str) else entities_json
+    entities = (
+        json.loads(entities_json) if isinstance(entities_json, str) else entities_json
+    )
 
-    validate_payload = {
+    validate_payload = {"id": pitchbook_id, "service": "spacy", "entities": entities}
-        "id": pitchbook_id,
-        "service": "spacy",
-        "entities": entities
-    }
 
     print(f"[SPACY] Sending to validate service: {VALIDATE_SERVICE_URL}")
     print(f"[SPACY] Payload: {validate_payload} entities for pitchbook {pitchbook_id}")
 
     try:
-        response = requests.post(VALIDATE_SERVICE_URL, json=validate_payload, timeout=600)
+        response = requests.post(
+            VALIDATE_SERVICE_URL, json=validate_payload, timeout=600
+        )
         print(f"[SPACY] Validate service response: {response.status_code}")
         if response.status_code != 200:
             print(f"[SPACY] Validate service error: {response.text}")
@@ -38,5 +45,40 @@ def extract_pdf():
     return jsonify("Sent to validate-service"), 200
 
 
+@app.route("/append-training-entry", methods=["POST"])
+def append_training_entry():
+    entry = request.get_json()
+
+    if not entry or "text" not in entry or "entities" not in entry:
+        return (
+            jsonify(
+                {"error": "Ungültiges Format – 'text' und 'entities' erforderlich."}
+            ),
+            400,
+        )
+
+    path = os.path.join("spacy_training", "annotation_data.json")
+
+    try:
+        if os.path.exists(path):
+            with open(path, "r", encoding="utf-8") as f:
+                data = json.load(f)
+        else:
+            data = []
+
+        # Optional: Duplikate prüfen
+        if entry in data:
+            return jsonify({"message": "Eintrag existiert bereits."}), 200
+
+        data.append(entry)
+        with open(path, "w", encoding="utf-8") as f:
+            json.dump(data, f, indent=2, ensure_ascii=False)
+
+        return jsonify({"message": "Eintrag erfolgreich gespeichert."}), 200
+    except Exception as e:
+        print(f"[ERROR] Fehler beim Schreiben der Datei: {e}")
+        return jsonify({"error": "Interner Fehler beim Schreiben."}), 500
+
+
 if __name__ == "__main__":
-    app.run(host="0.0.0.0", port=5052, debug=True)
+    app.run(host="0.0.0.0", port=5052, debug=True)

project/backend/spacy-service/save_training_entry.py

@@ -0,0 +1,35 @@
+from flask import Flask, request, jsonify
+import os
+import json
+
+app = Flask(__name__)
+
+ANNOTATION_FILE = (
+    "spacy_training/annotation_data.json"  # relativer Pfad im Container/Projekt
+)
+
+
+@app.route("/api/spacy-training-entry", methods=["POST"])
+def append_training_entry():
+    new_entry = request.get_json()
+
+    if not new_entry or "text" not in new_entry or "entities" not in new_entry:
+        return jsonify({"error": "Ungültiges Format"}), 400
+
+    # Bestehende Datei laden
+    if os.path.exists(ANNOTATION_FILE):
+        with open(ANNOTATION_FILE, "r", encoding="utf-8") as f:
+            data = json.load(f)
+    else:
+        data = []
+
+    # Optional: Duplikat vermeiden
+    if new_entry in data:
+        return jsonify({"message": "Eintrag bereits vorhanden."}), 200
+
+    # Anfügen
+    data.append(new_entry)
+    with open(ANNOTATION_FILE, "w", encoding="utf-8") as f:
+        json.dump(data, f, indent=2, ensure_ascii=False)
+
+    return jsonify({"message": "Eintrag erfolgreich gespeichert."}), 200

project/docker-compose.yml

@@ -37,6 +37,8 @@ services:
       retries: 10
     ports:
       - 5050:5000
+    volumes:
+      - ./backend/spacy-service/spacy_training:/app/spacy_training
 
   ocr:
     build:

project/frontend/Dockerfile

@@ -4,7 +4,9 @@ WORKDIR /usr/src/app
 # install dependencies into temp directory
 # this will cache them and speed up future builds
 COPY package.json bun.lockb ./
-RUN bun install --frozen-lockfile
+#RUN bun install --frozen-lockfile
+RUN bun install
+
 
 COPY . .
 

project/frontend/package.json

@@ -23,6 +23,7 @@
 		"@tanstack/react-router": "^1.114.3",
 		"@tanstack/react-router-devtools": "^1.114.3",
 		"@tanstack/router-plugin": "^1.114.3",
+		"file-saver": "^2.0.5",
 		"react": "^19.0.0",
 		"react-dom": "^19.0.0",
 		"react-material-file-upload": "^0.0.4",
@@ -33,6 +34,7 @@
 		"@biomejs/biome": "1.9.4",
 		"@testing-library/dom": "^10.4.0",
 		"@testing-library/react": "^16.2.0",
+		"@types/file-saver": "^2.0.7",
 		"@types/react": "^19.0.8",
 		"@types/react-dom": "^19.0.3",
 		"@vitejs/plugin-react": "^4.3.4",

project/frontend/src/components/KPIForm.tsx

@@ -3,6 +3,7 @@ import { Box, Typography, Button, Paper, TextField, FormControlLabel,
 import { useState, useEffect } from "react";
 import type { Kennzahl } from "../types/kpi";
 import { typeDisplayMapping } from "../types/kpi";
+// import { saveAs } from "file-saver";
 
 interface KPIFormProps {
     mode: 'add' | 'edit';
@@ -19,7 +20,9 @@ const emptyKPI: Partial<Kennzahl> = {
     type: 'string',
     translation: '',
     example: '',
-    active: true
+    active: true,
+    exampleText: '',
+    markedValue: '',
 };
 
 export function KPIForm({ mode, initialData, onSave, onCancel, loading = false }: KPIFormProps) {
@@ -40,16 +43,60 @@ export function KPIForm({ mode, initialData, onSave, onCancel, loading = false }
             return;
         }
 
+        if (!formData.exampleText?.trim()) {
+            alert('Beispielsatz ist erforderlich');
+            return;
+        }
+
+        if (!formData.markedValue?.trim()) {
+            alert('Bezeichneter Wert im Satz ist erforderlich');
+            return;
+        }
+
         setIsSaving(true);
         try {
+            const spacyEntry = generateSpacyEntry(formData);
+
+            //in localStorage merken
+            const stored = localStorage.getItem("spacyData");
+            const existingData = stored ? JSON.parse(stored) : [];
+            const updated = [...existingData, spacyEntry];
+            localStorage.setItem("spacyData", JSON.stringify(updated));
+
+            // an Flask senden
+            const response = await fetch("http://localhost:5050/api/spacy/append-training-entry", {
+            method: "POST",
+            headers: {
+                "Content-Type": "application/json"
+            },
+            body: JSON.stringify(spacyEntry)
+            });
+
+
+            const data = await response.json();
+            console.log("Response von /append-training-entry:", data);
+
+            if (!response.ok) {
+                throw new Error(data.error || "Fehler beim Aufruf von append-training-entry");
+            }
+
+            if (!response.ok) {
+                throw new Error("Fehler vom Backend: " + response.status);
+            }
+
+            // anschließend in der Datenbank speichern
             await onSave(formData);
-        } catch (error) {
+
-            console.error('Error saving KPI:', error);
+            alert("SpaCy-Eintrag erfolgreich gespeichert!");
+        } catch (e: any) {
+            alert(e.message || "Fehler beim Erzeugen des Trainingsbeispiels.");
+            console.error(e);
         } finally {
             setIsSaving(false);
         }
     };
 
+
     const handleCancel = () => {
         onCancel();
     };
@@ -106,18 +153,40 @@ export function KPIForm({ mode, initialData, onSave, onCancel, loading = false }
 
             <Box mb={4}>
                 <Typography variant="h6" fontWeight="bold" mb={2}>
-                    Beschreibung
+                    Beispielsatz
                 </Typography>
                 <TextField
                     fullWidth
                     multiline
                     rows={3}
-                    label="Beschreibung"
+                    label="Beispielsatz"
-                    value={formData.description || ''}
+                    required
-                    onChange={(e) => updateField('description', e.target.value)}
+                    value={formData.exampleText || ''}
-                    helperText="Beschreibung der Kennzahl"
+                    onChange={(e) => updateField('exampleText', e.target.value)}
+                    error={!formData.exampleText?.trim()}
+                    helperText={
+                        !formData.exampleText?.trim()
+                        ? "Beispielsatz ist erforderlich"
+                        : "Ein vollständiger Satz, in dem der markierte Begriff vorkommt"
+                    }
                 />
 
+                <TextField
+                    fullWidth
+                    required
+                    sx={{ mt: 2 }}
+                    label="Bezeichneter Wert im Satz *"
+                    value={formData.markedValue || ''}
+                    onChange={(e) => updateField('markedValue', e.target.value)}
+                    error={!formData.markedValue?.trim()}
+                    helperText={
+                        !formData.markedValue?.trim()
+                        ? "Markierter Begriff ist erforderlich"
+                        : "Nur der Begriff, der im Satz markiert werden soll (z. B. Core/Core+)"
+                    }
+                />
+
+
                 <Box mt={3}>
                     <FormControlLabel
                         control={
@@ -244,4 +313,28 @@ export function KPIForm({ mode, initialData, onSave, onCancel, loading = false }
             </Box>
         </Paper>
     );
-}
+}
+
+function generateSpacyEntry(formData: Partial<Kennzahl>) {
+  const text = formData.exampleText?.trim() || "";
+  const value = formData.markedValue?.trim() || "";
+  const label = formData.name?.trim().toUpperCase() || "";
+
+  const start = text.indexOf(value);
+  if (start === -1) {
+    throw new Error("Bezeichneter Begriff wurde im Satz nicht gefunden.");
+  }
+
+  return {
+    text,
+    entities: [[start, start + value.length, label]],
+  };
+}
+
+// function appendAndDownload(newEntry: any, existing: any[] = []) {
+//   const updated = [...existing, newEntry];
+//   const blob = new Blob([JSON.stringify(updated, null, 2)], {
+//     type: "application/json",
+//   });
+//   saveAs(blob, "..\project\backend\spacy-service\spacy_training\annotation_data.json");
+// }

project/frontend/src/types/kpi.ts

@@ -8,6 +8,8 @@ export interface Kennzahl {
     example: string;
     position: number;
     active: boolean;
+    exampleText?: string;
+    markedValue?: string;
 }
 
 export const typeDisplayMapping: Record<string, string> = {