Files
BadNote/windows/runner/ocr_channel.cpp
Akiba So 72428dc075
Some checks failed
CI / Test (Server, optional) (push) Failing after 2m10s
Windows Build / Build Windows (x64) (push) Failing after 29s
CI / Test (Flutter, Linux) (push) Has been cancelled
CI / Analyze (Flutter) (push) Has been cancelled
Fix bugs across app + server, optimize UI/UX, add Gitea CI
Bug fixes (Flutter):
- Wrap multi-statement DB writes (insert/update/delete note, deleteDocument,
  deletePageData, OCR FTS merge, migrations) in transactions to prevent data
  loss on interruption and a read-modify-write FTS race.
- Fix PdfDocument leaks on exception (try/finally dispose) and preserve image
  aspect ratio when stamping images onto PDF pages.
- Guard file-picker against empty selection (was .single -> crash).
- Fix eraser ConcurrentModificationError and unmodifiable-list crash on PDF
  pages; capture page synchronously on save to stop wrong-page data loss.
- Fix Riverpod DB-not-ready races, broken pull-to-refresh, settings load race,
  and search N+1; transform stored annotations on PDF page rotation.
- Normalize pen pressure for devices without a pressure range.
- PPT: single source of truth for slide strokes so ink displays and exports.

UI/UX:
- Material 3 typography, theme-aware colors (dark-mode fixes), hover cursors
  and right-click/visible actions on desktop, keyboard shortcuts (undo/redo/
  save/find), toolbar overflow handling, friendlier empty states, semantic OCR
  status badges, relative timestamps, 1-based page indicators, large-deck PPT
  navigation, and a scratchpad-scope label in split view.

Server (optional backend):
- Persist JWT secret (was per-process random), block path traversal in storage,
  fix CORS '*'+credentials, add OCR job ownership checks, last-writer-wins sync
  guard, constant-time login, and split out heavy OCR deps so the API/tests run
  without them.

CI: Gitea workflows for format+analyze+test (Linux, system sqlite) and a
Windows release build; pristine `flutter analyze`, all Flutter and server tests
green.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-21 03:18:00 +08:00

104 lines
2.9 KiB
C++

#include "ocr_channel.h"
#include <flutter/encodable_value.h>
#include <flutter/method_channel.h>
#include <flutter/standard_method_codec.h>
#include <memory>
#include <string>
#include <vector>
#include <winrt/Windows.Foundation.h>
#include <winrt/Windows.Graphics.Imaging.h>
#include <winrt/Windows.Media.Ocr.h>
#include <winrt/Windows.Storage.Streams.h>
#include <winrt/base.h>
namespace {
std::vector<uint8_t> ExtractBytes(const flutter::EncodableValue& value) {
if (const auto* bytes = std::get_if<std::vector<uint8_t>>(&value)) {
return *bytes;
}
if (const auto* list = std::get_if<flutter::EncodableList>(&value)) {
std::vector<uint8_t> out;
out.reserve(list->size());
for (const auto& item : *list) {
if (const auto* i = std::get_if<int32_t>(&item)) {
out.push_back(static_cast<uint8_t>(*i));
}
}
return out;
}
return {};
}
std::string RecognizePng(const std::vector<uint8_t>& bytes) {
if (bytes.empty()) {
return {};
}
using namespace winrt;
using namespace Windows::Storage::Streams;
using namespace Windows::Graphics::Imaging;
using namespace Windows::Media::Ocr;
InMemoryRandomAccessStream stream;
{
DataWriter writer{stream};
writer.WriteBytes(bytes);
writer.StoreAsync().get();
writer.DetachStream();
}
stream.Seek(0);
BitmapDecoder decoder = BitmapDecoder::CreateAsync(stream).get();
SoftwareBitmap bitmap = decoder.GetSoftwareBitmapAsync().get();
OcrEngine engine = OcrEngine::TryCreateFromUserProfileLanguages();
if (!engine) {
return {};
}
OcrResult result = engine.RecognizeAsync(bitmap).get();
return winrt::to_string(result.Text());
}
std::unique_ptr<flutter::MethodChannel<flutter::EncodableValue>> g_ocr_channel;
} // namespace
void RegisterOcrChannel(flutter::FlutterEngine* engine) {
winrt::init_apartment();
g_ocr_channel =
std::make_unique<flutter::MethodChannel<flutter::EncodableValue>>(
engine->messenger(), "badnote/ocr",
&flutter::StandardMethodCodec::GetInstance());
g_ocr_channel->SetMethodCallHandler(
[](const flutter::MethodCall<flutter::EncodableValue>& call,
std::unique_ptr<flutter::MethodResult<flutter::EncodableValue>>
result) {
if (call.method_name() != "recognize") {
result->NotImplemented();
return;
}
if (!call.arguments()) {
result->Error("invalid_args", "Expected PNG byte data");
return;
}
try {
const auto png_bytes = ExtractBytes(*call.arguments());
const auto text = RecognizePng(png_bytes);
result->Success(flutter::EncodableValue(text));
} catch (const winrt::hresult_error& error) {
result->Error("ocr_failed", winrt::to_string(error.message()));
} catch (...) {
result->Error("ocr_failed", "Unknown OCR error");
}
});
}