fix: Pixel-Analyse nicht mehr ueberspringen wenn Cluster < Gruppen
Some checks failed
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-school (push) Successful in 31s
CI / test-go-edu-search (push) Successful in 31s
CI / test-python-klausur (push) Failing after 2m1s
CI / test-python-agent-core (push) Successful in 18s
CI / test-nodejs-website (push) Successful in 20s
Some checks failed
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-school (push) Successful in 31s
CI / test-go-edu-search (push) Successful in 31s
CI / test-python-klausur (push) Failing after 2m1s
CI / test-python-agent-core (push) Successful in 18s
CI / test-nodejs-website (push) Successful in 20s
Vorher: wenn Text mehr Wort-Gruppen hatte als Pixel-Cluster gefunden wurden (z.B. bei Box-Rahmen die Cluster zusammenmergen), wurde die Zelle komplett uebersprungen → Fallback bei x=0%. Jetzt: Fallback auf Single-Span Positionierung (first→last Cluster) statt Skip. Damit wird der Text immer korrekt horizontal platziert. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -126,20 +126,8 @@ export function usePixelWordPositions(
|
||||
|
||||
const wordPos: WordPosition[] = []
|
||||
|
||||
if (groups.length <= 1) {
|
||||
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) {
|
||||
if (groups.length > 1 && clusters.length >= groups.length) {
|
||||
// Multiple text groups with enough clusters: map each group to a cluster
|
||||
for (let i = 0; i < groups.length; i++) {
|
||||
const cl = clusters[i]
|
||||
const clusterW = cl.end - cl.start + 1
|
||||
@@ -154,7 +142,20 @@ export function usePixelWordPositions(
|
||||
})
|
||||
}
|
||||
} else {
|
||||
continue
|
||||
// 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
|
||||
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,
|
||||
})
|
||||
}
|
||||
|
||||
positions.set(cell.cell_id, wordPos)
|
||||
|
||||
Reference in New Issue
Block a user