BadNote/lib/services/pdfrx_page_text_source.dart

// lib/services/pdfrx_page_text_source.dart
//
// Production wiring for [PdfTextIndexer]'s two injected text sources, backed by
// pdfrx (the same engine the editor renders with). Kept SEPARATE from
// PdfTextIndexer so the indexer's logic (the threshold decision, idempotency,
// sidecar persistence) is unit-testable without the native pdfium/OCR stack —
// only this file touches pdfrx, dart:ui, and the OCR engine, and it is exercised
// on-device, not in CI.

import 'dart:async';
import 'dart:typed_data';
import 'dart:ui' as ui;

import 'package:pdfrx/pdfrx.dart';

import 'ocr_engine.dart';

/// pdfrx-backed loaders for [PdfTextIndexer].
class PdfrxPageTextSource {
  const PdfrxPageTextSource._();

  /// Load the embedded text layer of every page (page order). Each entry is a
  /// page's raw text (possibly empty). Returns an empty list on any failure, so
  /// the indexer treats the PDF as having no text layer (→ OCR fallback).
  static Future<List<String>> loadEmbeddedText(String pdfPath) async {
    PdfDocument? doc;
    try {
      doc = await PdfDocument.openFile(pdfPath);
      final out = <String>[];
      for (final page in doc.pages) {
        final raw = await page.loadText();
        out.add(raw?.fullText ?? '');
      }
      return out;
    } catch (_) {
      return const [];
    } finally {
      await doc?.dispose();
    }
  }

  /// Render each page and OCR it (page order). Returns one entry per page
  /// (empty where nothing was recognized), or an empty list when the PDF can't
  /// be opened. Honours the OCR engine's own graceful no-op: when no backend is
  /// available every page comes back empty.
  ///
  /// Rendering is done at [renderScale]× the page's native 72-dpi size to give
  /// the recognizer enough resolution on scanned scans without exploding memory.
  static Future<List<String>> ocrPages(
    String pdfPath, {
    double renderScale = 2.0,
  }) async {
    PdfDocument? doc;
    try {
      doc = await PdfDocument.openFile(pdfPath);
      final out = <String>[];
      for (final page in doc.pages) {
        final text = await _ocrOnePage(page, renderScale);
        out.add(text ?? '');
      }
      return out;
    } catch (_) {
      return const [];
    } finally {
      await doc?.dispose();
    }
  }

  static Future<String?> _ocrOnePage(PdfPage page, double renderScale) async {
    PdfImage? image;
    try {
      final fullWidth = page.width * renderScale;
      final fullHeight = page.height * renderScale;
      image = await page.render(
        fullWidth: fullWidth,
        fullHeight: fullHeight,
      );
      if (image == null) return null;
      final png = await _bgraToPng(image.pixels, image.width, image.height);
      if (png == null) return null;
      return OcrEngine.recognizeImage(png);
    } catch (_) {
      return null;
    } finally {
      image?.dispose();
    }
  }

  /// Encode pdfrx's BGRA8888 raw pixels as PNG (the format [OcrEngine] expects).
  static Future<Uint8List?> _bgraToPng(
    Uint8List bgra,
    int width,
    int height,
  ) async {
    final completer = Completer<ui.Image>();
    ui.decodeImageFromPixels(
      bgra,
      width,
      height,
      ui.PixelFormat.bgra8888,
      completer.complete,
    );
    final image = await completer.future;
    try {
      final data = await image.toByteData(format: ui.ImageByteFormat.png);
      return data?.buffer.asUint8List();
    } finally {
      image.dispose();
    }
  }
}