Akiba So
d346cc2670
All checks were successful
CI / Windows build (push) Successful in 14m22s
Make Surface remote debugging and classroom workflows viable: always-on structured logs with one-click zip export, a single AppShell chrome, OOXML PPTX/DOCX annotation without LibreOffice, and a first-class sticky board. Also drop spike/legacy ink widgets and tighten pen feel (predictor, PenInfoHistory, page-tile layer). Co-authored-by: Cursor <cursoragent@cursor.com>
82 lines
2.9 KiB
Dart
82 lines
2.9 KiB
Dart
import 'dart:io';
|
|
|
|
import '../diagnostics/badnote_log.dart';
|
|
import '../editor/persistence/sidecar_repository.dart';
|
|
import '../models/note.dart';
|
|
import '../models/pen_tool.dart';
|
|
import 'database_service.dart';
|
|
import 'ocr_engine.dart';
|
|
import 'stroke_rasterizer.dart';
|
|
|
|
/// Runs OCR locally: typed text from strokes + handwriting via platform OCR.
|
|
class OcrService {
|
|
/// Extract searchable text from [note] and persist it for search. The text is
|
|
/// written to the note's `*.badnote.json` sidecar `ocrText` field — the
|
|
/// vault-scan source of truth the Phase 6 search index reads — and also
|
|
/// appended to the (rebuildable) SQLite FTS cache so legacy callers keep
|
|
/// working. [note.id] is the synthetic note path, which is exactly the
|
|
/// `sourceFilePath` the editor opened its [SidecarRepository] with.
|
|
Future<void> processNote(Note note) async {
|
|
BadNoteLog.instance.info(LogSubsystem.diag, 'ocr_start', fields: {
|
|
'note': note.id,
|
|
'strokes': note.strokes.length,
|
|
});
|
|
final parts = <String>[];
|
|
|
|
for (final stroke in note.strokes) {
|
|
if (stroke.tool == PenTool.text &&
|
|
stroke.textContent != null &&
|
|
stroke.textContent!.trim().isNotEmpty) {
|
|
parts.add(stroke.textContent!.trim());
|
|
}
|
|
}
|
|
|
|
final handwritingStrokes = note.strokes
|
|
.where(
|
|
(s) =>
|
|
s.tool != PenTool.eraser &&
|
|
s.tool != PenTool.text &&
|
|
s.points.isNotEmpty,
|
|
)
|
|
.toList();
|
|
|
|
if (handwritingStrokes.isNotEmpty) {
|
|
final png = await StrokeRasterizer.render(handwritingStrokes);
|
|
if (png != null) {
|
|
final recognized = await OcrEngine.recognizeImage(png);
|
|
if (recognized != null && recognized.isNotEmpty) {
|
|
parts.add(recognized);
|
|
BadNoteLog.instance.info(LogSubsystem.diag, 'ocr_handwriting', fields: {
|
|
'chars': recognized.length,
|
|
});
|
|
}
|
|
}
|
|
}
|
|
|
|
final combined = parts.join(' ').trim();
|
|
if (combined.isEmpty) {
|
|
BadNoteLog.instance.debug(LogSubsystem.diag, 'ocr_empty');
|
|
return;
|
|
}
|
|
|
|
// Persist into the note's sidecar so the vault-scan search index finds it.
|
|
// Prefer the editor's already-open repo (same in-memory sidecar — no race);
|
|
// if the note is closed, open/flush/dispose a transient handle.
|
|
final open = SidecarRepositoryRegistry.forPath(note.id);
|
|
if (open != null) {
|
|
open.scheduleOcrTextSave(combined);
|
|
await open.flush();
|
|
} else if (await File('${note.id}$kSidecarSuffix').exists()) {
|
|
final repo = await SidecarRepository.open(note.id, docType: 'notebook');
|
|
repo.scheduleOcrTextSave(combined);
|
|
await repo.flush();
|
|
repo.dispose();
|
|
}
|
|
|
|
// Also keep the legacy SQLite FTS cache warm (rebuildable; not the source
|
|
// of truth). Harmless if the row is never read.
|
|
final db = await DatabaseService.getInstance();
|
|
await db.appendOcrToFts(note.id, combined);
|
|
}
|
|
}
|