From 8a5f2aa188d0d594d0474cba172a11f926d6df8f Mon Sep 17 00:00:00 2001
From: Benjamin Admin <benjaminadmin@MacBook-Pro.fritz.box>
Date: Wed, 11 Mar 2026 15:39:54 +0100
Subject: [PATCH] fix: Cluster-Zuordnung per Breiten-Proportionalitaet statt
 Position

Zwei wesentliche Verbesserungen:

1. Multi-group: Gruppen werden per Best-Fit-Breite den Clustern
   zugeordnet statt naiv links-nach-rechts. Damit wird z.B.
   "Kokosnuss" dem DE-Spalten-Cluster zugeordnet statt dem
   breiteren Box-Cluster.

2. Single-group Fallback: verwendet den BREITESTEN Cluster statt
   first-to-last Span. Verhindert dass Streupixel von benachbarten
   Seitenbereichen den Text nach links ziehen.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 .../ocr-overlay/usePixelWordPositions.ts      | 71 +++++++++++++------
 1 file changed, 48 insertions(+), 23 deletions(-)

diff --git a/admin-lehrer/components/ocr-overlay/usePixelWordPositions.ts b/admin-lehrer/components/ocr-overlay/usePixelWordPositions.ts
index b4872b9..6568a35 100644
--- a/admin-lehrer/components/ocr-overlay/usePixelWordPositions.ts
+++ b/admin-lehrer/components/ocr-overlay/usePixelWordPositions.ts
@@ -147,43 +147,68 @@ export function usePixelWordPositions(
 
         const wordPos: WordPosition[] = []
 
-        // When more clusters than groups, pick the N widest clusters
-        // (text clusters are wider than box-border clusters)
-        let matchClusters = clusters
-        if (groups.length > 1 && clusters.length > groups.length) {
-          matchClusters = [...clusters]
-            .sort((a, b) => (b.end - b.start) - (a.end - a.start))
-            .slice(0, groups.length)
-            .sort((a, b) => a.start - b.start)
-        }
+        // Match groups to clusters using width-proportional assignment.
+        // Each group is assigned to the cluster whose width best matches
+        // the group's expected pixel width (text measurement).
+        if (groups.length > 1 && clusters.length >= groups.length) {
+          // Measure each group's expected width
+          const groupWidths = groups.map(g => ctx.measureText(g).width)
 
-        if (groups.length > 1 && matchClusters.length >= groups.length) {
-          // Multiple text groups with matching clusters
-          for (let i = 0; i < groups.length; i++) {
-            const cl = matchClusters[i]
+          // Greedy assignment: for each group (in order), find the best
+          // unassigned cluster by width ratio consistency
+          const totalMeasured = groupWidths.reduce((a, b) => a + b, 0)
+          const totalClusterW = clusters.reduce((a, c) => a + (c.end - c.start + 1), 0)
+          const refScale = totalClusterW / totalMeasured
+          const used = new Set<number>()
+
+          const assignments: number[] = []
+          for (let gi = 0; gi < groups.length; gi++) {
+            const expectedW = groupWidths[gi] * refScale
+            let bestIdx = -1
+            let bestDiff = Infinity
+            for (let ci = 0; ci < clusters.length; ci++) {
+              if (used.has(ci)) continue
+              const clW = clusters[ci].end - clusters[ci].start + 1
+              const diff = Math.abs(clW - expectedW)
+              if (diff < bestDiff) {
+                bestDiff = diff
+                bestIdx = ci
+              }
+            }
+            used.add(bestIdx)
+            assignments.push(bestIdx)
+          }
+
+          // Sort assignments to maintain left-to-right order
+          const sortedPairs = assignments
+            .map((ci, gi) => ({ ci, gi }))
+            .sort((a, b) => clusters[a.ci].start - clusters[b.ci].start)
+
+          for (const { ci, gi } of sortedPairs) {
+            const cl = clusters[ci]
             const clusterW = cl.end - cl.start + 1
-            const measured = ctx.measureText(groups[i])
-            const autoFontPx = refFontSize * (clusterW / measured.width)
+            const autoFontPx = refFontSize * (clusterW / groupWidths[gi])
             const fontRatio = Math.min(autoFontPx / ch, 1.0)
             wordPos.push({
               xPct: cell.bbox_pct.x + (cl.start / cw) * cell.bbox_pct.w,
               wPct: ((cl.end - cl.start + 1) / cw) * cell.bbox_pct.w,
-              text: groups[i],
+              text: groups[gi],
               fontRatio,
             })
           }
         } else {
-          // Single group OR clusters don't match groups:
-          // position entire text as one span from first to last cluster
-          const firstCl = clusters[0]
-          const lastCl = clusters[clusters.length - 1]
-          const clusterW = lastCl.end - firstCl.start + 1
+          // Single group OR not enough clusters:
+          // use the WIDEST cluster (not first-to-last span which pulls in
+          // stray pixels from adjacent page areas like box borders)
+          const widest = clusters.reduce((best, c) =>
+            (c.end - c.start) > (best.end - best.start) ? c : best, clusters[0])
+          const clusterW = widest.end - widest.start + 1
           const measured = ctx.measureText(cell.text.trim())
           const autoFontPx = refFontSize * (clusterW / measured.width)
           const fontRatio = Math.min(autoFontPx / ch, 1.0)
           wordPos.push({
-            xPct: cell.bbox_pct.x + (firstCl.start / cw) * cell.bbox_pct.w,
-            wPct: ((lastCl.end - firstCl.start + 1) / cw) * cell.bbox_pct.w,
+            xPct: cell.bbox_pct.x + (widest.start / cw) * cell.bbox_pct.w,
+            wPct: ((widest.end - widest.start + 1) / cw) * cell.bbox_pct.w,
             text: cell.text.trim(),
             fontRatio,
           })