breakpilot-lehrer/admin-lehrer/components/ocr-pipeline/usePixelWordPositions.ts

import { useEffect, useState } from 'react'
import type { GridCell } from '@/app/(admin)/ai/ocr-pipeline/types'

export interface WordPosition {
  xPct: number
  wPct: number
  text: string
  fontRatio: number
}

/**
 * Shared hook: analyse dark-pixel clusters on an image to determine
 * the exact horizontal position & auto-font-size of word groups in each cell.
 *
 * Returns a Map<cell_id, WordPosition[]>.
 */
export function usePixelWordPositions(
  imageUrl: string,
  cells: GridCell[],
  active: boolean,
): Map<string, WordPosition[]> {
  const [cellWordPositions, setCellWordPositions] = useState<Map<string, WordPosition[]>>(new Map())

  useEffect(() => {
    if (!active || cells.length === 0 || !imageUrl) return

    const img = new Image()
    img.crossOrigin = 'anonymous'
    img.onload = () => {
      const canvas = document.createElement('canvas')
      canvas.width = img.naturalWidth
      canvas.height = img.naturalHeight
      const ctx = canvas.getContext('2d')
      if (!ctx) return
      ctx.drawImage(img, 0, 0)

      const refFontSize = 40
      const fontFam = "'Liberation Sans', Arial, sans-serif"
      ctx.font = `${refFontSize}px ${fontFam}`

      const positions = new Map<string, WordPosition[]>()

      for (const cell of cells) {
        if (!cell.bbox_pct || !cell.text) continue

        // Split by 3+ whitespace into word-groups
        const groups = cell.text.split(/\s{3,}/).map(s => s.trim()).filter(Boolean)

        // Pixel region for this cell
        const imgW = img.naturalWidth
        const imgH = img.naturalHeight
        const cx = Math.round(cell.bbox_pct.x / 100 * imgW)
        const cy = Math.round(cell.bbox_pct.y / 100 * imgH)
        const cw = Math.round(cell.bbox_pct.w / 100 * imgW)
        const ch = Math.round(cell.bbox_pct.h / 100 * imgH)
        if (cw <= 0 || ch <= 0) continue

        const imageData = ctx.getImageData(cx, cy, cw, ch)

        // Vertical projection: count dark pixels per column
        const proj = new Float32Array(cw)
        for (let y = 0; y < ch; y++) {
          for (let x = 0; x < cw; x++) {
            const idx = (y * cw + x) * 4
            const lum = 0.299 * imageData.data[idx] + 0.587 * imageData.data[idx + 1] + 0.114 * imageData.data[idx + 2]
            if (lum < 128) proj[x]++
          }
        }

        // Find dark-pixel clusters (word groups on the image)
        const threshold = Math.max(1, ch * 0.03)
        const minGap = Math.max(5, Math.round(cw * 0.02))
        const clusters: { start: number; end: number }[] = []
        let inCluster = false
        let clStart = 0
        let gap = 0

        for (let x = 0; x < cw; x++) {
          if (proj[x] >= threshold) {
            if (!inCluster) { clStart = x; inCluster = true }
            gap = 0
          } else if (inCluster) {
            gap++
            if (gap > minGap) {
              clusters.push({ start: clStart, end: x - gap })
              inCluster = false
              gap = 0
            }
          }
        }
        if (inCluster) clusters.push({ start: clStart, end: cw - 1 - gap })

        if (clusters.length === 0) continue

        const wordPos: WordPosition[] = []

        if (groups.length <= 1) {
          // Single group: position at first cluster, merge all clusters for width
          const firstCl = clusters[0]
          const lastCl = clusters[clusters.length - 1]
          const clusterW = lastCl.end - firstCl.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,
            text: cell.text.trim(),
            fontRatio,
          })
        } else if (clusters.length >= groups.length) {
          // Multiple groups: match to clusters left-to-right
          for (let i = 0; i < groups.length; i++) {
            const cl = clusters[i]
            const clusterW = cl.end - cl.start + 1
            const measured = ctx.measureText(groups[i])
            const autoFontPx = refFontSize * (clusterW / measured.width)
            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],
              fontRatio,
            })
          }
        } else {
          continue // fewer clusters than groups — skip
        }

        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 = imageUrl
  }, [active, cells, imageUrl])

  return cellWordPositions
}