From ec361df89ade4c33d168f0549e02938c7ba30dd4 Mon Sep 17 00:00:00 2001
From: Rob <rob.tranquillo@gmx.de>
Date: Fri, 27 Mar 2026 13:46:50 +0100
Subject: [PATCH] =?UTF-8?q?Stichproben=20Validierung=20hinzugef=C3=BCgt.?=
 =?UTF-8?q?=20Zeigt=20am=20anfang=20einige=20Werte=20aus=20dem=20PDF=20an?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 src/validators.py | 92 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 92 insertions(+)

diff --git a/src/validators.py b/src/validators.py
index 7843e31..4297bdd 100644
--- a/src/validators.py
+++ b/src/validators.py
@@ -159,6 +159,84 @@ def validate(
     return errors
 
 
+def _extract_samples(
+    file_path: str | Path,
+    sheet_name: str,
+    config: Dict[str, Any],
+) -> List[Dict]:
+    """Extract the first 10 days for persons 1, 5 and 10.
+
+    Returns a list of dicts:
+      {'person': str, 'days': list[str]}   (days[0] = Tag 1 … days[9] = Tag 10)
+
+    Missing persons are silently skipped.
+    """
+    import openpyxl
+
+    result = []
+    target_persons = [1, 5, 10]  # 1-based indices into the data rows
+    num_days = 10
+
+    try:
+        wb = openpyxl.load_workbook(str(file_path), read_only=True, data_only=True)
+        if sheet_name not in wb.sheetnames:
+            wb.close()
+            return result
+
+        ws = wb[sheet_name]
+        rows = list(ws.iter_rows(values_only=True))
+        wb.close()
+
+        name_col: int = config["excel_name_column"]
+        seq_col: int = config["excel_seq_column"]
+        name_header: str = config["excel_name_header"]
+        day_start: int = config["excel_day_start_col"]
+
+        # Find header row
+        header_idx = None
+        for i, row in enumerate(rows):
+            if len(row) > name_col and row[name_col] is not None:
+                if name_header in str(row[name_col]):
+                    header_idx = i
+                    break
+        if header_idx is None:
+            return result
+
+        # Collect data rows (rows after header with a valid seq number)
+        data_rows = []
+        for row in rows[header_idx + 1:]:
+            if len(row) > seq_col and row[seq_col] is not None:
+                try:
+                    int(row[seq_col])
+                    data_rows.append(row)
+                except (TypeError, ValueError):
+                    pass
+
+        def _fmt(val) -> str:
+            if val is None:
+                return "–"
+            if isinstance(val, float) and val == int(val):
+                return str(int(val))
+            return str(val)
+
+        for person_n in target_persons:
+            if person_n > len(data_rows):
+                continue
+            row = data_rows[person_n - 1]
+            name = str(row[name_col]).strip() if len(row) > name_col and row[name_col] else "?"
+            days = []
+            for day_idx in range(num_days):
+                col_idx = day_start + day_idx
+                val = row[col_idx] if col_idx < len(row) else None
+                days.append(_fmt(val))
+            result.append({"person": name, "days": days})
+
+    except Exception:
+        pass  # Preview is best-effort; never block on sample errors
+
+    return result
+
+
 def show_preview_and_confirm(
     file_path: str | Path,
     sheet_name: str,
@@ -191,6 +269,20 @@ def show_preview_and_confirm(
     print(f"Teilnehmer    : {person_count}")
     print(f"Fehler        : {len(errors) if errors else 0}")
 
+    # --- Sample data from the Excel sheet ------------------------------------
+    samples = _extract_samples(file_path, sheet_name, config)
+    if samples:
+        num_days = len(samples[0]["days"])
+        day_headers = "  ".join(f"{d+1:>3}" for d in range(num_days))
+        separator = "  ".join("---" for _ in range(num_days))
+        print()
+        print("--- Stichproben aus dem Excel-Sheet (erste 10 Tage) ---")
+        print(f"  {'Person':<30s}  {day_headers}")
+        print(f"  {'-'*30}  {separator}")
+        for s in samples:
+            day_vals = "  ".join(f"{v:>3}" for v in s["days"])
+            print(f"  {s['person']:<30s}  {day_vals}")
+
     if errors:
         print()
         print("--- Validierungsfehler ---")