add extract text button to doom scroll mode

Show an extract-text button (document icon) in the bottom bar when the
current image has no extracted text yet. Clicking it calls the extract-text
API, shows a spinner while in progress, and on success replaces itself with
the text-lines display button and auto-opens the overlay. Error state briefly
turns the button red. Resets on every item navigation alongside the other
text state. Hidden for videos and items without an itemKey.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Garret Patti
2026-04-13 09:19:32 -04:00
parent cd9a83ea90
commit b0fc275a52

View File

@@ -46,6 +46,8 @@ export default function DoomScrollView({ items, videoContext = 'mixed', onClose,
const [translatedText, setTranslatedText] = useState<string | null>(null) const [translatedText, setTranslatedText] = useState<string | null>(null)
const [showTextOverlay, setShowTextOverlay] = useState(false) const [showTextOverlay, setShowTextOverlay] = useState(false)
const [showOriginal, setShowOriginal] = useState(false) const [showOriginal, setShowOriginal] = useState(false)
const [extracting, setExtracting] = useState(false)
const [extractError, setExtractError] = useState<string | null>(null)
const videoRef = useRef<HTMLVideoElement>(null) const videoRef = useRef<HTMLVideoElement>(null)
const cooldownRef = useRef(false) const cooldownRef = useRef(false)
@@ -130,6 +132,8 @@ export default function DoomScrollView({ items, videoContext = 'mixed', onClose,
setTranslatedText(null) setTranslatedText(null)
setShowTextOverlay(false) setShowTextOverlay(false)
setShowOriginal(false) setShowOriginal(false)
setExtracting(false)
setExtractError(null)
if (!current?.itemKey) return if (!current?.itemKey) return
fetch(`/api/ai-tagging/fields?itemKey=${encodeURIComponent(current.itemKey)}`) fetch(`/api/ai-tagging/fields?itemKey=${encodeURIComponent(current.itemKey)}`)
.then((r) => r.json()) .then((r) => r.json())
@@ -178,6 +182,32 @@ export default function DoomScrollView({ items, videoContext = 'mixed', onClose,
} }
}, [navigate, onClose, extractedText]) }, [navigate, onClose, extractedText])
const handleExtractText = async () => {
if (!current?.itemKey) return
setExtracting(true)
setExtractError(null)
try {
const res = await fetch('/api/ai-tagging/extract-text', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ itemKey: current.itemKey }),
})
if (!res.ok) {
const data = await res.json().catch(() => ({}))
throw new Error((data as { error?: string }).error ?? 'Extraction failed')
}
const result = await res.json()
setExtractedText(result.extractedText || null)
setTranslatedText(result.translatedText || null)
if (result.extractedText) setShowTextOverlay(true)
} catch (err) {
setExtractError(err instanceof Error ? err.message : 'Extraction failed')
setTimeout(() => setExtractError(null), 4000)
} finally {
setExtracting(false)
}
}
return ( return (
<div className="fixed inset-0 z-50 flex flex-col" style={{ backgroundColor: '#000' }}> <div className="fixed inset-0 z-50 flex flex-col" style={{ backgroundColor: '#000' }}>
{/* Keyframe for auto-play progress bar */} {/* Keyframe for auto-play progress bar */}
@@ -317,7 +347,7 @@ export default function DoomScrollView({ items, videoContext = 'mixed', onClose,
{current?.name} {current?.name}
</span> </span>
<div className="flex-shrink-0 flex items-center gap-1"> <div className="flex-shrink-0 flex items-center gap-1">
{extractedText && ( {extractedText ? (
<button <button
onClick={() => setShowTextOverlay((v) => !v)} onClick={() => setShowTextOverlay((v) => !v)}
className="w-9 h-9 rounded-full flex items-center justify-center transition-opacity hover:opacity-100 opacity-70" className="w-9 h-9 rounded-full flex items-center justify-center transition-opacity hover:opacity-100 opacity-70"
@@ -333,7 +363,30 @@ export default function DoomScrollView({ items, videoContext = 'mixed', onClose,
<line x1="3" y1="18" x2="18" y2="18"/> <line x1="3" y1="18" x2="18" y2="18"/>
</svg> </svg>
</button> </button>
) : current?.itemKey && current?.mediaType === 'image' ? (
<button
onClick={handleExtractText}
disabled={extracting}
className="w-9 h-9 rounded-full flex items-center justify-center transition-opacity hover:opacity-100 opacity-70 disabled:opacity-40"
style={{
backgroundColor: extractError ? 'rgba(127,29,29,0.8)' : 'rgba(0,0,0,0.5)',
color: extractError ? '#fca5a5' : '#fff',
}}
aria-label="Extract text"
>
{extracting ? (
<span className="animate-spin" style={{ display: 'inline-block', fontSize: '0.75rem' }}></span>
) : (
<svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2" strokeLinecap="round" strokeLinejoin="round">
<path d="M14 2H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h12a2 2 0 0 0 2-2V8z"/>
<polyline points="14 2 14 8 20 8"/>
<line x1="16" y1="13" x2="8" y2="13"/>
<line x1="16" y1="17" x2="8" y2="17"/>
<polyline points="10 9 9 9 8 9"/>
</svg>
)} )}
</button>
) : null}
{onViewInLibrary && current?.itemKey && ( {onViewInLibrary && current?.itemKey && (
<button <button
onClick={(e) => { e.stopPropagation(); onViewInLibrary(current) }} onClick={(e) => { e.stopPropagation(); onViewInLibrary(current) }}