feat(search): index PDF text, OCR scanned PDFs on import

Search now covers handwriting, the PDF text layer, AND scanned
(rasterized) PDFs.

- PdfTextIndexer runs at import: sums the embedded text layer across
  pages; if present it stores that as the document body, otherwise the
  PDF is rasterized and its rendered pages are OCR'd in the background.
  The result lands in the sidecar `pageText` field (distinct from
  `ocrText`, the handwriting OCR). Idempotent (skips a sidecar that
  already has pageText); degrades gracefully with no OCR engine.
- pdfrx_page_text_source abstracts text/render so it's testable.
- VaultSearchIndex now harvests title + typed text + handwriting OCR +
  PDF pageText, so search finds notes, typed PDFs and scanned PDFs.

analyze clean, 409 tests green.

lib/editor/persistence/sidecar_repository.dart

@@ -183,6 +183,18 @@ class SidecarRepository {
   /// The OCR text loaded from the sidecar, or null.
   String? get loadedOcrText => _sidecar.ocrText;
 
+  /// Replace the document-body search text (PDF embedded text layer, or
+  /// background OCR of a rasterized PDF — see [PdfTextIndexer]) and schedule a
+  /// save. No-op if unchanged. An empty string is normalized to null.
+  void schedulePageTextSave(String? pageText) {
+    final next = (pageText != null && pageText.isEmpty) ? null : pageText;
+    if (_sidecar.pageText == next) return;
+    _replace(pageText: next, clearPageText: next == null);
+  }
+
+  /// The document-body search text loaded from the sidecar, or null.
+  String? get loadedPageText => _sidecar.pageText;
+
   /// Replace the committed strokes for [pageIndex] and schedule a save.
   void scheduleStrokeSave(int pageIndex, List<EditorStroke> strokes) {
     final next = Map<int, List<EditorStroke>>.from(_sidecar.strokes);
@@ -321,6 +333,8 @@ class SidecarRepository {
     List<SidecarScratchLink>? scratchLinks,
     String? ocrText,
     bool clearOcrText = false,
+    String? pageText,
+    bool clearPageText = false,
     String? background,
   }) {
     if (_disposed) return;
@@ -339,6 +353,7 @@ class SidecarRepository {
       bookmarks: bookmarks ?? _sidecar.bookmarks,
       scratchLinks: scratchLinks ?? _sidecar.scratchLinks,
       ocrText: clearOcrText ? null : (ocrText ?? _sidecar.ocrText),
+      pageText: clearPageText ? null : (pageText ?? _sidecar.pageText),
       background: background ?? _sidecar.background,
     );
     _timer?.cancel();

lib/providers/ocr_provider.dart

@@ -1,11 +1,24 @@
 import 'package:flutter_riverpod/flutter_riverpod.dart';
 
 import '../services/ocr_service.dart';
+import '../services/pdf_text_indexer.dart';
+import '../services/pdfrx_page_text_source.dart';
 
 enum OcrStatus { none, processing, done, failed }
 
 final ocrServiceProvider = Provider<OcrService>((ref) => OcrService());
 
+/// The import-time PDF document-body indexer, wired to the pdfrx-backed embedded
+/// text + page-render OCR sources (see [PdfrxPageTextSource]). The import flow
+/// fires [PdfTextIndexer.indexPdf] (fire-and-forget) so a scanned PDF's text
+/// becomes searchable in the background without blocking the editor opening.
+final pdfTextIndexerProvider = Provider<PdfTextIndexer>(
+  (ref) => PdfTextIndexer(
+    loadEmbeddedText: PdfrxPageTextSource.loadEmbeddedText,
+    ocrPages: PdfrxPageTextSource.ocrPages,
+  ),
+);
+
 /// Tracks local OCR processing status per note ID.
 ///
 /// This map only ever holds an entry per note that has had OCR triggered in

lib/screens/home_screen.dart

@@ -1,3 +1,5 @@
+import 'dart:async';
+
 import 'package:file_picker/file_picker.dart';
 import 'package:flutter/material.dart';
 import 'package:flutter_riverpod/flutter_riverpod.dart';
@@ -8,6 +10,7 @@ import '../models/note.dart';
 import '../providers/document_provider.dart';
 import '../providers/note_provider.dart';
 import '../providers/ocr_provider.dart';
+import '../providers/search_provider.dart';
 import '../editor/canvas/pen_editor_screen.dart';
 import '../services/pptx_service.dart';
 import '../services/vault_service.dart';
@@ -250,6 +253,10 @@ class HomeScreen extends ConsumerWidget {
       final vaultPath = await vault.createNotebook(pickedPath);
       // Refresh the documents list so the new notebook shows on return.
       await ref.read(documentListProvider.notifier).loadDocuments();
+      // For a PDF, index its document body (embedded text layer, or background
+      // OCR of a rasterized/scanned PDF) into the sidecar so search covers it.
+      // Fire-and-forget: import returns and opens the editor immediately.
+      _indexPdfInBackground(ref, vaultPath);
       if (!context.mounted) return;
       await _openVaultFile(context, ref, vaultPath);
     } catch (e) {
@@ -257,6 +264,25 @@ class HomeScreen extends ConsumerWidget {
     }
   }
 
+  /// Kick off background document-body indexing for an in-vault PDF (no-op for
+  /// other types). Runs detached from the import await chain so the editor opens
+  /// immediately; on completion it bumps the search-index epoch so the newly
+  /// indexed text is searchable. Idempotency and graceful OCR degradation live in
+  /// [PdfTextIndexer]; failures here are swallowed (search just misses the body).
+  void _indexPdfInBackground(WidgetRef ref, String vaultPath) {
+    final ext = p.extension(vaultPath).replaceFirst('.', '').toLowerCase();
+    if (ext != 'pdf') return;
+    final indexer = ref.read(pdfTextIndexerProvider);
+    unawaited(() async {
+      final indexed = await indexer.indexPdf(vaultPath);
+      if (indexed != null && indexed.isNotEmpty) {
+        // Force the next search to re-scan the vault (picks up the new pageText).
+        final epoch = ref.read(searchIndexEpochProvider.notifier);
+        epoch.state = epoch.state + 1;
+      }
+    }());
+  }
+
   /// Route an in-vault [filePath] to the correct editor by extension:
   /// pdf → [PenEditorScreen]; pptx/ppt → [PenSlideScreen]; docx → convert to
   /// PDF (best-effort, LibreOffice) then open as PDF. Unsupported / failed

lib/services/pdf_text_indexer.dart

@@ -0,0 +1,198 @@
+// lib/services/pdf_text_indexer.dart
+//
+// Import-time document-body text indexing for file-backed PDF notebooks, so the
+// vault-scan search index (VaultSearchIndex) covers the underlying document —
+// not just the user's annotations. Three text sources now feed search:
+//   (a) handwriting        → OCR'd into the sidecar's `ocrText` (OcrService),
+//   (b) a PDF text layer   → its embedded printed text, captured here,
+//   (c) a RASTERIZED PDF   → background OCR of the rendered pages, captured here.
+//
+// Flow (kicked off after VaultService.createNotebook, fire-and-forget):
+//   1. IDEMPOTENCY: if the sidecar already carries `pageText`, do nothing.
+//   2. EXTRACT the embedded text layer per page (pdfrx `loadText`).
+//   3. DECIDE text-layer vs rasterized: sum the embedded text length across all
+//      pages; if it clears [textLayerThreshold] the PDF has a usable text layer
+//      and we persist that. Otherwise the PDF is rasterized (scanned image, no
+//      text) and we OCR each rendered page.
+//   4. PERSIST the per-page text (joined by form-feed) into the sidecar's
+//      `pageText` field — writing THROUGH an open SidecarRepository when the
+//      editor already has the doc open (no race), else a transient handle.
+//
+// GRACEFUL DEGRADATION / HONESTY:
+//   * The OCR engine is whatever OcrService/OcrEngine resolves to: the bundled
+//     ONNX PP-OCR recognizer if present, else the native Windows OCR
+//     MethodChannel, else NONE. On a platform/CI without any backend, OCR
+//     returns null and a rasterized PDF simply gets no `pageText` — no crash,
+//     and the embedded-text path still works.
+//   * pdfrx render + native OCR can only be exercised on-device. The pdfrx-
+//     backed loaders are injected through [PdfTextIndexer] so unit tests fake
+//     them; the production wiring lives in [PdfrxPageTextSource].
+
+import 'dart:async';
+import 'dart:io';
+
+import '../editor/persistence/sidecar_repository.dart';
+import '../storage/badnote_sidecar.dart';
+import '../storage/sidecar_store.dart';
+
+/// Extracts a PDF's embedded text layer, one entry per page (page order). An
+/// empty list (or all-empty entries) means "no usable text layer".
+typedef PdfEmbeddedTextLoader = Future<List<String>> Function(String pdfPath);
+
+/// OCRs the rendered pages of a rasterized PDF, returning one entry per page
+/// (page order). Entries may be empty where a page yielded nothing. Returns an
+/// empty list when no OCR backend is available (a clean no-op).
+typedef PdfPageOcrRunner = Future<List<String>> Function(String pdfPath);
+
+/// Indexes a PDF's document body into its sidecar's `pageText` at import time.
+///
+/// Stateless apart from the two injected text sources; safe to construct per
+/// import. All disk/native work is awaited internally — call [indexPdf] without
+/// awaiting (fire-and-forget) from the import handler to keep import snappy.
+class PdfTextIndexer {
+  PdfTextIndexer({
+    required PdfEmbeddedTextLoader loadEmbeddedText,
+    required PdfPageOcrRunner ocrPages,
+    this.textLayerThreshold = 16,
+  })  : _loadEmbeddedText = loadEmbeddedText,
+        _ocrPages = ocrPages;
+
+  final PdfEmbeddedTextLoader _loadEmbeddedText;
+  final PdfPageOcrRunner _ocrPages;
+
+  /// Minimum total embedded-text length (across all pages, after trimming) for a
+  /// PDF to count as having a usable text layer. Below this it is treated as
+  /// rasterized and routed to OCR. Small on purpose: a scanned PDF typically
+  /// yields zero or a few stray ligature chars, while any real text page clears
+  /// it easily.
+  final int textLayerThreshold;
+
+  /// The page separator stored inside `pageText` (form feed). The search index
+  /// treats `pageText` as a flat blob, so this is purely cosmetic / future-proof.
+  static const String pageSeparator = '\f';
+
+  /// Index the PDF at [pdfPath] (an in-vault copy) into its sidecar's `pageText`.
+  ///
+  /// Idempotent: returns immediately if the sidecar already has non-empty
+  /// `pageText`. Never throws — any failure (unreadable PDF, missing OCR backend)
+  /// degrades to leaving `pageText` unset. Returns the text it persisted (for
+  /// tests), or null when nothing was indexed.
+  Future<String?> indexPdf(String pdfPath) async {
+    try {
+      // 1. Idempotency: skip a doc whose body has already been indexed.
+      final existing = await _currentPageText(pdfPath);
+      if (existing != null && existing.trim().isNotEmpty) return null;
+
+      // 2. Embedded text layer.
+      final embedded = await _loadEmbeddedText(pdfPath);
+      final embeddedLen = embedded.fold<int>(
+        0,
+        (sum, page) => sum + page.trim().length,
+      );
+
+      // 3. Text-layer vs rasterized decision.
+      List<String> pages;
+      if (embeddedLen >= textLayerThreshold) {
+        pages = embedded;
+      } else {
+        // Rasterized (scanned, no text layer) → background OCR.
+        pages = await _ocrPages(pdfPath);
+      }
+
+      final joined = _joinPages(pages);
+      if (joined.isEmpty) return null;
+
+      // 4. Persist into the sidecar (through an open repo if the editor holds it).
+      await _persistPageText(pdfPath, joined);
+      return joined;
+    } catch (_) {
+      // Background indexing must never surface an error to the import flow.
+      return null;
+    }
+  }
+
+  /// Whether the embedded text in [embedded] clears [textLayerThreshold], i.e.
+  /// the PDF has a usable text layer (false → rasterized, needs OCR). Exposed for
+  /// unit-testing the decision in isolation.
+  bool hasUsableTextLayer(List<String> embedded) {
+    final len = embedded.fold<int>(0, (sum, p) => sum + p.trim().length);
+    return len >= textLayerThreshold;
+  }
+
+  static String _joinPages(List<String> pages) {
+    final nonEmpty = pages.map((p) => p.trim()).where((p) => p.isNotEmpty);
+    return nonEmpty.join(pageSeparator).trim();
+  }
+
+  /// Read the sidecar's current `pageText` (for the idempotency check), from the
+  /// open repo if present else from disk. Null when no sidecar exists yet.
+  Future<String?> _currentPageText(String pdfPath) async {
+    final open = SidecarRepositoryRegistry.forPath(pdfPath);
+    if (open != null) return open.loadedPageText;
+    final sidecar = await SidecarStore.read(
+      File('$pdfPath$kSidecarSuffix'),
+    );
+    return sidecar?.pageText;
+  }
+
+  /// Write [pageText] into the sidecar. Prefer the editor's already-open repo
+  /// (same in-memory sidecar — no race); otherwise merge into the on-disk
+  /// sidecar (creating one if the editor hasn't yet).
+  Future<void> _persistPageText(String pdfPath, String pageText) async {
+    final open = SidecarRepositoryRegistry.forPath(pdfPath);
+    if (open != null) {
+      open.schedulePageTextSave(pageText);
+      await open.flush();
+      return;
+    }
+
+    final file = File('$pdfPath$kSidecarSuffix');
+    final current = await SidecarStore.read(file);
+    final merged = _withPageText(current, pdfPath, pageText);
+    await SidecarStore.writeAtomic(file, merged);
+  }
+
+  /// Build a sidecar carrying [pageText], preserving every other field of
+  /// [current] (or a fresh minimal sidecar when none exists yet).
+  static BadnoteSidecar _withPageText(
+    BadnoteSidecar? current,
+    String pdfPath,
+    String pageText,
+  ) {
+    if (current == null) {
+      return BadnoteSidecar(
+        sourceFile: _basename(pdfPath),
+        docType: 'pdf',
+        createdAt: DateTime.now().toUtc(),
+        updatedAt: DateTime.now().toUtc(),
+        pageText: pageText,
+      );
+    }
+    return BadnoteSidecar(
+      version: current.version,
+      sourceFile: current.sourceFile,
+      docType: current.docType,
+      title: current.title,
+      pageCount: current.pageCount,
+      rotation: current.rotation,
+      createdAt: current.createdAt,
+      updatedAt: DateTime.now().toUtc(),
+      strokes: current.strokes,
+      highlights: current.highlights,
+      texts: current.texts,
+      bookmarks: current.bookmarks,
+      scratchLinks: current.scratchLinks,
+      legacyAnnotations: current.legacyAnnotations,
+      ocrText: current.ocrText,
+      pageText: pageText,
+      legacyId: current.legacyId,
+      background: current.background,
+    );
+  }
+
+  static String _basename(String path) {
+    final norm = path.replaceAll('\\', '/');
+    final i = norm.lastIndexOf('/');
+    return i == -1 ? norm : norm.substring(i + 1);
+  }
+}

lib/services/pdfrx_page_text_source.dart

@@ -0,0 +1,111 @@
+// 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();
+    }
+  }
+}

lib/services/vault_search_index.dart

@@ -10,9 +10,12 @@
 //                              pages,
 //   * the handwriting OCR text persisted in the sidecar's `ocrText` field.
 //
-// It does NOT (yet) index a PDF's embedded text layer — that is a known gap (see
-// the REPORT in the task / the class doc below). Matching uses the existing pure
-// search primitives (normalize / rank / snippet), so CJK substring search works.
+// It ALSO indexes a file-backed PDF's document body text, captured once at
+// import into the sidecar's `pageText` field by [PdfTextIndexer]: the embedded
+// (printed) text layer for a normal PDF, or background OCR of the rendered pages
+// for a RASTERIZED / scanned PDF that has no text layer. Matching uses the
+// existing pure search primitives (normalize / rank / snippet), so CJK substring
+// search works.
 
 import 'dart:io';
 
@@ -71,13 +74,14 @@ class VaultSearchHit {
 /// source of truth).
 ///
 /// HONEST SCOPE (what search covers / does NOT):
-///   * COVERS: note/doc titles, typed text boxes, and handwriting OCR text that
-///     has been persisted into a sidecar's `ocrText` field.
-///   * DOES NOT cover: a PDF's embedded (printed) text layer — only the user's
-///     annotations are indexed, not the underlying document body. Indexing the
-///     PDF text layer would require rendering each page through pdfrx at scan
-///     time; deferred. OCR is only present where it has already been run and
-///     written back to the sidecar.
+///   * COVERS: note/doc titles, typed text boxes, handwriting OCR text persisted
+///     into a sidecar's `ocrText` field, AND a PDF's document body text persisted
+///     into `pageText` at import — the embedded text layer, or background OCR of
+///     a rasterized/scanned PDF (see [PdfTextIndexer]).
+///   * CAVEAT: `pageText` is only present once import-time indexing has run and
+///     written it back to the sidecar. A PDF imported before this feature (or
+///     whose OCR backend was unavailable) has no `pageText`, so only its
+///     annotations are searchable until it is re-indexed.
 class VaultSearchIndex {
   VaultSearchIndex(this._vault);
 
@@ -174,6 +178,11 @@ class VaultSearchIndex {
       }
       final ocr = sidecar.ocrText;
       if (ocr != null && ocr.trim().isNotEmpty) parts.add(ocr.trim());
+      // Document body text captured at import: the PDF's embedded text layer,
+      // or background OCR of a rasterized/scanned PDF. Covers the underlying
+      // document, not just the user's annotations.
+      final body = sidecar.pageText;
+      if (body != null && body.trim().isNotEmpty) parts.add(body.trim());
     }
     return parts.join('\n');
   }

lib/storage/badnote_sidecar.dart

@@ -313,6 +313,7 @@ class BadnoteSidecar {
     List<SidecarScratchLink>? scratchLinks,
     Map<int, String>? legacyAnnotations,
     this.ocrText,
+    this.pageText,
     this.legacyId,
     this.background,
   })  : strokes = strokes ?? <int, List<EditorStroke>>{},
@@ -368,6 +369,17 @@ class BadnoteSidecar {
   /// the notebook has no handwriting or OCR hasn't run.
   final String? ocrText;
 
+  /// Searchable text of the underlying DOCUMENT BODY for a file-backed notebook
+  /// (a PDF), captured ONCE at import time so the vault-scan search index covers
+  /// the document — not just the user's annotations. It is either the PDF's
+  /// embedded (printed) text layer, or — for a RASTERIZED / scanned PDF with no
+  /// text layer — the result of a background OCR pass over the rendered pages.
+  /// Pages are joined with `\f` (form feed) but the index treats it as a flat
+  /// blob. Null when the document has not been indexed yet (back-compat: an old
+  /// sidecar simply omits the field) or has no extractable/recognized text. This
+  /// is distinct from [ocrText], which holds ONLY handwriting OCR.
+  final String? pageText;
+
   /// The legacy SQLite row id this sidecar was migrated from (a `documents.id`
   /// or `notes.id`). Set ONLY by the one-time migration; it makes the migration
   /// idempotent (a re-run recognizes an already-migrated item by this id even if
@@ -413,6 +425,7 @@ class BadnoteSidecar {
               entry.key.toString(): entry.value,
           },
         if (ocrText != null && ocrText!.isNotEmpty) 'ocrText': ocrText,
+        if (pageText != null && pageText!.isNotEmpty) 'pageText': pageText,
         if (legacyId != null) 'legacyId': legacyId,
         if (background != null) 'background': background,
       };
@@ -470,6 +483,7 @@ class BadnoteSidecar {
         return out;
       }(),
       ocrText: json['ocrText'] as String?,
+      pageText: json['pageText'] as String?,
       legacyId: json['legacyId'] as String?,
       background: json['background'] as String?,
     );