From 7f8615b8c1dd08ce0a2e4405951420ec0b8b0293 Mon Sep 17 00:00:00 2001
From: Benjamin Admin <benjaminadmin@MacBookPro.fritz.box>
Date: Tue, 10 Mar 2026 14:28:23 +0100
Subject: [PATCH] fix: Schriftgroesse auf haeufigsten Wert (Mode) normalisieren

Alle Wortgruppen bekommen die gleiche fontRatio (gerundet auf 0.02),
basierend auf der haeufigsten berechneten Groesse. Ueberschriften
und Fliesstext haben damit einheitliche Schriftgroesse.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 .../components/ocr-pipeline/StepLlmReview.tsx | 23 +++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/admin-lehrer/components/ocr-pipeline/StepLlmReview.tsx b/admin-lehrer/components/ocr-pipeline/StepLlmReview.tsx
index 9f9161c..45ee16e 100644
--- a/admin-lehrer/components/ocr-pipeline/StepLlmReview.tsx
+++ b/admin-lehrer/components/ocr-pipeline/StepLlmReview.tsx
@@ -221,6 +221,29 @@ export function StepLlmReview({ sessionId, onNext }: StepLlmReviewProps) {
         positions.set(cell.cell_id, wordPos)
       }
 
+      // Normalise: find the most common fontRatio (mode) and apply it to all
+      const allRatios: number[] = []
+      for (const wps of positions.values()) {
+        for (const wp of wps) allRatios.push(wp.fontRatio)
+      }
+      if (allRatios.length > 0) {
+        // Bucket ratios to 2 decimal places, find mode
+        const buckets = new Map<number, number>()
+        for (const r of allRatios) {
+          const key = Math.round(r * 50) / 50 // round to nearest 0.02
+          buckets.set(key, (buckets.get(key) || 0) + 1)
+        }
+        let modeRatio = allRatios[0]
+        let modeCount = 0
+        for (const [ratio, count] of buckets) {
+          if (count > modeCount) { modeRatio = ratio; modeCount = count }
+        }
+        // Apply mode to all word positions
+        for (const wps of positions.values()) {
+          for (const wp of wps) wp.fontRatio = modeRatio
+        }
+      }
+
       setCellWordPositions(positions)
     }
     img.src = imgUrl