[2ff88f42] einfügen

einfügen
2026-02-20 13:25:21 +00:00
parent 653bd79e1f
commit 101f67936a
5 changed files with 188 additions and 20 deletions
--- a/.dev_session/SESSION_INFO
+++ b/.dev_session/SESSION_INFO
@@ -1 +1 @@
-{"task_id": "2ff88f42-8544-8000-8314-c9013414d1d0", "token": "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", "session_start_time": "2026-02-20T10:56:03.179196"}
+{"task_id": "2ff88f42-8544-8018-883f-e8837c0421af", "token": "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", "session_start_time": "2026-02-20T13:24:58.251700"}
--- a/company-explorer/backend/app.py
+++ b/company-explorer/backend/app.py
@@ -454,6 +454,22 @@ def list_industries(db: Session = Depends(get_db), username: str = Depends(authe
 def list_job_roles(db: Session = Depends(get_db), username: str = Depends(authenticate_user)):
    return db.query(JobRoleMapping).order_by(JobRoleMapping.pattern.asc()).all()

+@app.get("/api/job_roles/raw")
+def list_raw_job_titles(
+    limit: int = 100, 
+    unmapped_only: bool = True,
+    db: Session = Depends(get_db), 
+    username: str = Depends(authenticate_user)
+):
+    """
+    Returns unique raw job titles from CRM imports, prioritized by frequency.
+    """
+    query = db.query(RawJobTitle)
+    if unmapped_only:
+        query = query.filter(RawJobTitle.is_mapped == False)
+    
+    return query.order_by(RawJobTitle.count.desc()).limit(limit).all()
+
@app.get("/api/mistakes")
 def list_reported_mistakes(
    status: Optional[str] = Query(None),
--- a/company-explorer/backend/database.py
+++ b/company-explorer/backend/database.py
@@ -150,7 +150,7 @@ class Industry(Base):
    created_at = Column(DateTime, default=datetime.utcnow)


-class JobRoleMapping(Base):
+class JobRoleMapping(BaseModel):
    """
    Maps job title patterns (regex or simple string) to Roles.
    """
@@ -162,7 +162,25 @@ class JobRoleMapping(Base):
    
    created_at = Column(DateTime, default=datetime.utcnow)

-class Persona(Base):
+class RawJobTitle(BaseModel):
+    """
+    Stores raw unique job titles imported from CRM to assist in pattern mining.
+    Tracks frequency to prioritize high-impact patterns.
+    """
+    __tablename__ = "raw_job_titles"
+
+    id = Column(Integer, primary_key=True, index=True)
+    title = Column(String, unique=True, index=True) # The raw string, e.g. "Senior Sales Mgr."
+    count = Column(Integer, default=1) # How often this title appears in the CRM
+    source = Column(String, default="import")
+    
+    # Status Flags
+    is_mapped = Column(Boolean, default=False) # True if a pattern currently covers this title
+    
+    created_at = Column(DateTime, default=datetime.utcnow)
+    updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
+
+class Persona(BaseModel):
    """
    Represents a generalized persona/role (e.g. 'Geschäftsführer', 'IT-Leiter')
    independent of the specific job title pattern.
--- a/company-explorer/backend/scripts/import_job_titles.py
+++ b/company-explorer/backend/scripts/import_job_titles.py
@@ -0,0 +1,95 @@
+import sys
+import os
+import csv
+import argparse
+from datetime import datetime
+
+# Setup Environment
+sys.path.append(os.path.join(os.path.dirname(__file__), "../../"))
+
+from backend.database import SessionLocal, RawJobTitle, init_db, engine, Base
+
+def import_titles(file_path: str, delimiter: str = ';'):
+    print(f"🚀 Starting Import from {file_path}...")
+    
+    # Ensure Table Exists
+    RawJobTitle.__table__.create(bind=engine, checkfirst=True)
+    
+    db = SessionLocal()
+    total_rows = 0
+    new_titles = 0
+    updated_titles = 0
+    
+    try:
+        with open(file_path, 'r', encoding='utf-8-sig') as f: # utf-8-sig handles BOM from Excel
+            # Try to detect header
+            sample = f.read(1024)
+            has_header = csv.Sniffer().has_header(sample)
+            f.seek(0)
+            
+            reader = csv.reader(f, delimiter=delimiter)
+            
+            if has_header:
+                headers = next(reader)
+                print(f"ℹ️ Header detected: {headers}")
+                # Try to find the right column index
+                col_idx = 0
+                for i, h in enumerate(headers):
+                    if h.lower() in ['funktion', 'jobtitle', 'title', 'position', 'rolle']:
+                        col_idx = i
+                        print(f"  -> Using column '{h}' (Index {i})")
+                        break
+            else:
+                col_idx = 0
+                print("ℹ️ No header detected, using first column.")
+
+            # Process Rows
+            for row in reader:
+                if not row: continue
+                if len(row) <= col_idx: continue
+                
+                raw_title = row[col_idx].strip()
+                if not raw_title: continue # Skip empty
+                
+                total_rows += 1
+                
+                # Check existance
+                existing = db.query(RawJobTitle).filter(RawJobTitle.title == raw_title).first()
+                
+                if existing:
+                    existing.count += 1
+                    existing.updated_at = datetime.utcnow()
+                    updated_titles += 1
+                else:
+                    db.add(RawJobTitle(title=raw_title, count=1))
+                    new_titles += 1
+                
+                if total_rows % 100 == 0:
+                    db.commit()
+                    print(f"  Processed {total_rows} rows...", end='\r')
+
+            db.commit()
+            
+    except Exception as e:
+        print(f"\n❌ Error: {e}")
+        db.rollback()
+    finally:
+        db.close()
+
+    print(f"\n✅ Import Complete.")
+    print(f"   Total Processed: {total_rows}")
+    print(f"   New Unique Titles: {new_titles}")
+    print(f"   Updated Frequencies: {updated_titles}")
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Import Job Titles from CSV")
+    parser.add_argument("file", help="Path to CSV file")
+    parser.add_argument("--delimiter", default=";", help="CSV Delimiter (default: ';')")
+    
+    args = parser.parse_args()
+    
+    if not os.path.exists(args.file):
+        print(f"❌ File not found: {args.file}")
+        sys.exit(1)
+        
+    import_titles(args.file, args.delimiter)
--- a/company-explorer/frontend/src/components/RoboticsSettings.tsx
+++ b/company-explorer/frontend/src/components/RoboticsSettings.tsx
@@ -32,6 +32,7 @@ export function RoboticsSettings({ isOpen, onClose, apiBase }: RoboticsSettingsP
  const [roboticsCategories, setRoboticsCategories] = useState<any[]>([])
  const [industries, setIndustries] = useState<any[]>([])
  const [jobRoles, setJobRoles] = useState<any[]>([])
+  const [rawJobTitles, setRawJobTitles] = useState<any[]>([])
  const [reportedMistakes, setReportedMistakes] = useState<ReportedMistake[]>([])
  const [currentMistakeStatusFilter, setCurrentMistakeStatusFilter] = useState<string>("PENDING");
  const [isLoading, setIsLoading] = useState(false);
@@ -39,15 +40,17 @@ export function RoboticsSettings({ isOpen, onClose, apiBase }: RoboticsSettingsP
  const fetchAllData = async () => {
    setIsLoading(true);
    try {
-      const [resRobotics, resIndustries, resJobRoles, resMistakes] = await Promise.all([
+      const [resRobotics, resIndustries, resJobRoles, resRawTitles, resMistakes] = await Promise.all([
        axios.get(`${apiBase}/robotics/categories`),
        axios.get(`${apiBase}/industries`),
        axios.get(`${apiBase}/job_roles`),
+        axios.get(`${apiBase}/job_roles/raw`),
        axios.get(`${apiBase}/mistakes?status=${currentMistakeStatusFilter}`),
      ]);
      setRoboticsCategories(resRobotics.data);
      setIndustries(resIndustries.data);
      setJobRoles(resJobRoles.data);
+      setRawJobTitles(resRawTitles.data);
      setReportedMistakes(resMistakes.data.items);
    } catch (e) {
      console.error("Failed to fetch settings data:", e);
@@ -251,22 +254,58 @@ export function RoboticsSettings({ isOpen, onClose, apiBase }: RoboticsSettingsP
              </div>
          </div>

-          <div key="roles-content" className={clsx("space-y-4", { 'hidden': isLoading || activeTab !== 'roles' })}>
-              <div className="flex justify-between items-center"><h3 className="text-sm font-bold text-slate-700 dark:text-slate-300">Job Title Mapping Patterns</h3><button onClick={handleAddJobRole} className="flex items-center gap-1 px-3 py-1.5 bg-blue-600 hover:bg-blue-500 text-white text-xs font-bold rounded"><Plus className="h-3 w-3" /> ADD PATTERN</button></div>
-              <div className="bg-slate-50 dark:bg-slate-950 border border-slate-200 dark:border-slate-800 rounded-lg overflow-hidden">
-                  <table className="w-full text-left text-xs">
-                      <thead className="bg-slate-100 dark:bg-slate-900 border-b border-slate-200 dark:border-slate-800 text-slate-500 font-bold uppercase"><tr><th className="p-3">Job Title Pattern (Regex/Text)</th><th className="p-3">Mapped Role</th><th className="p-3 w-10"></th></tr></thead>
-                      <tbody className="divide-y divide-slate-200 dark:divide-slate-800">
-                          {jobRoles.map(role => (
-                              <tr key={role.id} className="group">
-                                  <td className="p-2"><input className="w-full bg-transparent border border-transparent hover:border-slate-300 dark:hover:border-slate-700 rounded px-2 py-1 text-slate-900 dark:text-slate-200 outline-none focus:border-blue-500" defaultValue={role.pattern} /></td>
-                                  <td className="p-2"><select className="w-full bg-transparent border border-transparent hover:border-slate-300 dark:hover:border-slate-700 rounded px-2 py-1 text-slate-900 dark:text-slate-200 outline-none focus:border-blue-500" defaultValue={role.role}><option>Operativer Entscheider</option><option>Infrastruktur-Verantwortlicher</option><option>Wirtschaftlicher Entscheider</option><option>Innovations-Treiber</option><option>Influencer</option></select></td>
-                                  <td className="p-2 text-center"><button onClick={() => handleDeleteJobRole(role.id)} className="text-slate-400 hover:text-red-500 opacity-0 group-hover:opacity-100 transition-opacity"><Trash2 className="h-4 w-4" /></button></td>
-                              </tr>
-                          ))}
-                          {jobRoles.length === 0 && (<tr><td colSpan={3} className="p-8 text-center text-slate-500 italic">No patterns defined yet.</td></tr>)}
-                      </tbody>
-                  </table>
+          <div key="roles-content" className={clsx("space-y-8", { 'hidden': isLoading || activeTab !== 'roles' })}>
+              {/* Existing Patterns */}
+              <div className="space-y-4">
+                  <div className="flex justify-between items-center">
+                    <div>
+                        <h3 className="text-sm font-bold text-slate-700 dark:text-slate-300">Active Mapping Patterns</h3>
+                        <p className="text-[10px] text-slate-500 uppercase font-semibold">Deterministic Regex/Text rules</p>
+                    </div>
+                    <button onClick={handleAddJobRole} className="flex items-center gap-1 px-3 py-1.5 bg-blue-600 hover:bg-blue-500 text-white text-xs font-bold rounded shadow-lg shadow-blue-500/20"><Plus className="h-3 w-3" /> ADD PATTERN</button>
+                  </div>
+                  <div className="bg-white dark:bg-slate-950 border border-slate-200 dark:border-slate-800 rounded-xl overflow-hidden shadow-sm">
+                      <table className="w-full text-left text-xs">
+                          <thead className="bg-slate-50 dark:bg-slate-900/50 border-b border-slate-200 dark:border-slate-800 text-slate-500 font-bold uppercase tracking-wider"><tr><th className="p-3">Pattern (% for wildcard)</th><th className="p-3">Target Persona Role</th><th className="p-3 w-10"></th></tr></thead>
+                          <tbody className="divide-y divide-slate-100 dark:divide-slate-800/50">
+                              {jobRoles.map(role => (
+                                  <tr key={role.id} className="group hover:bg-slate-50/50 dark:hover:bg-slate-800/30 transition-colors">
+                                      <td className="p-2"><input className="w-full bg-transparent border border-transparent hover:border-slate-300 dark:hover:border-slate-700 rounded px-2 py-1 text-slate-900 dark:text-slate-200 outline-none focus:border-blue-500 font-mono" defaultValue={role.pattern} /></td>
+                                      <td className="p-2"><select className="w-full bg-transparent border border-transparent hover:border-slate-300 dark:hover:border-slate-700 rounded px-2 py-1 text-slate-900 dark:text-slate-200 outline-none focus:border-blue-500" defaultValue={role.role}><option>Operativer Entscheider</option><option>Infrastruktur-Verantwortlicher</option><option>Wirtschaftlicher Entscheider</option><option>Innovations-Treiber</option><option>Influencer</option></select></td>
+                                      <td className="p-2 text-center"><button onClick={() => handleDeleteJobRole(role.id)} className="text-slate-400 hover:text-red-500 opacity-0 group-hover:opacity-100 transition-all transform hover:scale-110"><Trash2 className="h-4 w-4" /></button></td>
+                                  </tr>
+                              ))}
+                          </tbody>
+                      </table>
+                  </div>
+              </div>
+
+              {/* Discovery Inbox */}
+              <div className="space-y-4 pt-4 border-t border-slate-200 dark:border-slate-800">
+                  <div className="flex justify-between items-center">
+                    <div>
+                        <h3 className="text-sm font-bold text-slate-700 dark:text-slate-300">Discovery Inbox</h3>
+                        <p className="text-[10px] text-slate-500 uppercase font-semibold">Unmapped job titles from CRM, prioritized by frequency</p>
+                    </div>
+                  </div>
+                  <div className="bg-slate-50/50 dark:bg-slate-900/20 border border-dashed border-slate-300 dark:border-slate-700 rounded-xl overflow-hidden">
+                      <table className="w-full text-left text-xs">
+                          <thead className="bg-slate-100/50 dark:bg-slate-900/80 border-b border-slate-200 dark:border-slate-800 text-slate-400 font-bold uppercase tracking-wider"><tr><th className="p-3">Job Title from CRM</th><th className="p-3 w-20 text-center">Frequency</th><th className="p-3 w-10"></th></tr></thead>
+                          <tbody className="divide-y divide-slate-100 dark:divide-slate-800/50">
+                              {rawJobTitles.map(raw => (
+                                  <tr key={raw.id} className="group hover:bg-white dark:hover:bg-slate-800 transition-colors">
+                                      <td className="p-3 font-medium text-slate-600 dark:text-slate-400 italic">{raw.title}</td>
+                                      <td className="p-3 text-center"><span className="px-2 py-1 bg-slate-200 dark:bg-slate-800 rounded-full font-bold text-[10px] text-slate-500">{raw.count}x</span></td>
+                                      <td className="p-3 text-center"><button onClick={async () => {
+                                          await axios.post(`${apiBase}/job_roles`, { pattern: `%${raw.title.toLowerCase()}%`, role: "Influencer" });
+                                          fetchAllData();
+                                      }} className="p-1 text-blue-500 hover:bg-blue-100 dark:hover:bg-blue-900/30 rounded transition-all"><Plus className="h-4 w-4" /></button></td>
+                                  </tr>
+                              ))}
+                              {rawJobTitles.length === 0 && (<tr><td colSpan={3} className="p-12 text-center text-slate-400 italic">Discovery inbox is empty. Import raw job titles to see data here.</td></tr>)}
+                          </tbody>
+                      </table>
+                  </div>
              </div>
          </div>