Release v0.6.8: add background image OCR and optional Tesseract
This commit is contained in:
+92
-1
@@ -269,8 +269,15 @@ App::~App()
|
||||
std::lock_guard lock(jobsMutex);
|
||||
stop = true;
|
||||
jobs.clear();
|
||||
pendingHistorySearch = {};
|
||||
}
|
||||
jobsReady.notify_all();
|
||||
historySearchReady.notify_all();
|
||||
historyOcrReady.notify_all();
|
||||
if (historyOcrWorker.joinable())
|
||||
historyOcrWorker.join();
|
||||
if (historySearchWorker.joinable())
|
||||
historySearchWorker.join();
|
||||
if (worker.joinable())
|
||||
worker.join();
|
||||
RemoveClipboardFormatListener(window);
|
||||
@@ -291,6 +298,83 @@ void App::enqueue(std::function<void()> job)
|
||||
}
|
||||
jobsReady.notify_one();
|
||||
}
|
||||
void App::enqueueHistorySearch(std::function<void()> job)
|
||||
{
|
||||
{
|
||||
std::lock_guard lock(jobsMutex);
|
||||
if (stop) return;
|
||||
// Only the latest query matters. Clipboard capture and OCR must not delay it.
|
||||
pendingHistorySearch = std::move(job);
|
||||
if (!historySearchWorker.joinable())
|
||||
historySearchWorker = std::thread([this]
|
||||
{
|
||||
for (;;)
|
||||
{
|
||||
std::function<void()> searchJob;
|
||||
{
|
||||
std::unique_lock lock(jobsMutex);
|
||||
historySearchReady.wait(lock, [&] { return stop || bool(pendingHistorySearch); });
|
||||
if (stop) return;
|
||||
searchJob = std::move(pendingHistorySearch);
|
||||
pendingHistorySearch = {};
|
||||
}
|
||||
try { searchJob(); }
|
||||
catch (const std::exception &e) { report(wide(e.what())); }
|
||||
}
|
||||
});
|
||||
}
|
||||
historySearchReady.notify_one();
|
||||
}
|
||||
void App::scheduleHistoryOcr(const Settings &config)
|
||||
{
|
||||
{
|
||||
std::lock_guard lock(jobsMutex);
|
||||
if (stop || !history || !config.history) return;
|
||||
historyOcrSettings = config;
|
||||
historyOcrRequested = true;
|
||||
if (!historyOcrWorker.joinable())
|
||||
historyOcrWorker = std::thread([this]
|
||||
{
|
||||
for (;;)
|
||||
{
|
||||
Settings config;
|
||||
{
|
||||
std::unique_lock lock(jobsMutex);
|
||||
historyOcrReady.wait(lock, [&] { return stop || historyOcrRequested; });
|
||||
if (stop) return;
|
||||
historyOcrRequested = false;
|
||||
config = historyOcrSettings;
|
||||
}
|
||||
for (const auto &entry : history->entries())
|
||||
{
|
||||
{ std::lock_guard lock(jobsMutex); if (stop) return; }
|
||||
auto profile = ocrProfile(config);
|
||||
if (!entry.image || (entry.ocrState != 1 && entry.ocrProfile == profile)) continue;
|
||||
try
|
||||
{
|
||||
auto text = recognizeText(history->load(entry.id), config);
|
||||
std::lock_guard lock(jobsMutex);
|
||||
if (stop || ocrProfile(historyOcrSettings) != profile) continue;
|
||||
if (history->saveOcr(entry.id, text, config))
|
||||
PostMessageW(window, HistoryMessage, 0, 0);
|
||||
}
|
||||
catch (const std::exception &e)
|
||||
{
|
||||
// Automatic OCR never changes the clipboard or opens error dialogs.
|
||||
log(L"History OCR: " + wide(e.what()));
|
||||
try {
|
||||
std::lock_guard lock(jobsMutex);
|
||||
if (!stop && ocrProfile(historyOcrSettings) == profile)
|
||||
history->saveOcr(entry.id, std::nullopt, config);
|
||||
}
|
||||
catch (const std::exception &saveError) { log(L"History OCR save: " + wide(saveError.what())); }
|
||||
}
|
||||
}
|
||||
}
|
||||
});
|
||||
}
|
||||
historyOcrReady.notify_one();
|
||||
}
|
||||
void App::report(const std::wstring &text)
|
||||
{
|
||||
log(text);
|
||||
@@ -333,6 +417,7 @@ void App::applySettings(const Settings &s)
|
||||
{
|
||||
bool autostartChanged = false;
|
||||
validateSettings(s);
|
||||
validateTesseract(s);
|
||||
if (s.autoCorrect)
|
||||
{
|
||||
AutoCorrector probe;
|
||||
@@ -375,6 +460,7 @@ void App::applySettings(const Settings &s)
|
||||
}
|
||||
// Clear on the worker so the next check reloads edits to dictionary files.
|
||||
enqueue([this] { autoCorrector.configure({}, {}); });
|
||||
scheduleHistoryOcr(s);
|
||||
SetThreadExecutionState(ES_CONTINUOUS |
|
||||
(settings.awake ? (ES_DISPLAY_REQUIRED | ES_SYSTEM_REQUIRED) : 0));
|
||||
}
|
||||
@@ -1051,6 +1137,7 @@ void App::captureHistory()
|
||||
!f.data[1] && !f.data[2] && !f.data[3])
|
||||
return;
|
||||
history->add(clip, app, config);
|
||||
scheduleHistoryOcr(config);
|
||||
PostMessageW(window, HistoryMessage, 0, 0);
|
||||
}
|
||||
catch (const std::exception &e)
|
||||
@@ -1078,7 +1165,9 @@ void App::recognizeEntry(std::wstring id)
|
||||
} reset{busy};
|
||||
try
|
||||
{
|
||||
auto text = recognizeText(history->load(id));
|
||||
auto cached = history->ocrText(id, ocrProfile(config));
|
||||
auto text = cached ? *cached : recognizeText(history->load(id), config);
|
||||
if (!cached) history->saveOcr(id, text, config);
|
||||
if (text.empty())
|
||||
{
|
||||
report(L"No text was found in the image.");
|
||||
@@ -1442,6 +1531,8 @@ int App::execute()
|
||||
if (!keyboardHook || !mouseHook)
|
||||
report(L"Input tracking could not start. Automatic recent-text conversion is unavailable.");
|
||||
AddClipboardFormatListener(window);
|
||||
// Resume pending OCR, including older images without a saved OCR state.
|
||||
scheduleHistoryOcr(settings);
|
||||
addTray();
|
||||
SetTimer(window, 1, 60000, nullptr);
|
||||
SetThreadExecutionState(ES_CONTINUOUS |
|
||||
|
||||
@@ -61,6 +61,7 @@ class App
|
||||
void recognizeEntry(std::wstring);
|
||||
void captureHistory();
|
||||
void enqueue(std::function<void()>);
|
||||
void enqueueHistorySearch(std::function<void()>);
|
||||
void report(const std::wstring &);
|
||||
void trayMenu();
|
||||
void addTray();
|
||||
@@ -83,6 +84,14 @@ class App
|
||||
std::condition_variable jobsReady;
|
||||
std::deque<std::function<void()>> jobs;
|
||||
std::thread worker;
|
||||
std::thread historySearchWorker;
|
||||
std::condition_variable historySearchReady;
|
||||
std::function<void()> pendingHistorySearch;
|
||||
std::thread historyOcrWorker;
|
||||
std::condition_variable historyOcrReady;
|
||||
bool historyOcrRequested{};
|
||||
Settings historyOcrSettings;
|
||||
void scheduleHistoryOcr(const Settings &);
|
||||
std::thread updateWorker;
|
||||
bool updateRunning{}, installingUpdate{};
|
||||
std::wstring availableUpdate, notifiedUpdate;
|
||||
|
||||
@@ -49,6 +49,9 @@ struct Settings
|
||||
bool autoCorrect = false;
|
||||
bool writeLog = true;
|
||||
bool screenshotAutoOpenEditor = false;
|
||||
bool useTesseract = false;
|
||||
std::wstring tesseractPath;
|
||||
std::wstring tesseractLanguages = L"ukr+eng+rus";
|
||||
int autoMaxRank = 0;
|
||||
int autoMinLength = 3;
|
||||
std::wstring autoPrefixChars = L"([{«“‘\"";
|
||||
|
||||
+115
@@ -271,4 +271,119 @@ std::wstring recognizeText(const Clip &clip)
|
||||
WindowsDeleteString(text);
|
||||
return out;
|
||||
}
|
||||
std::filesystem::path tesseractExecutable(const Settings &s)
|
||||
{
|
||||
if (!s.tesseractPath.empty())
|
||||
{
|
||||
std::filesystem::path path(s.tesseractPath);
|
||||
if (!path.is_absolute()) throw std::runtime_error("Select an absolute path to tesseract.exe");
|
||||
return path;
|
||||
}
|
||||
for (auto variable : {L"ProgramW6432", L"ProgramFiles", L"LOCALAPPDATA"})
|
||||
{
|
||||
wchar_t base[32768]{};
|
||||
auto length = GetEnvironmentVariableW(variable, base, std::size(base));
|
||||
if (!length || length >= std::size(base)) continue;
|
||||
auto root = std::filesystem::path(base);
|
||||
for (auto relative : {L"Tesseract-OCR/tesseract.exe", L"Programs/Tesseract-OCR/tesseract.exe"})
|
||||
if (std::filesystem::is_regular_file(root / relative)) return root / relative;
|
||||
}
|
||||
throw std::runtime_error("Tesseract was not found. Install the optional 64-bit Tesseract 5 package or select tesseract.exe in OCR options.");
|
||||
}
|
||||
std::wstring ocrProfile(const Settings &s)
|
||||
{
|
||||
return s.useTesseract ? L"tesseract:" + lower(s.tesseractPath) + L":" + s.tesseractLanguages : L"windows";
|
||||
}
|
||||
namespace
|
||||
{
|
||||
struct TessLibrary
|
||||
{
|
||||
HMODULE module{};
|
||||
explicit TessLibrary(const Settings &s)
|
||||
{
|
||||
auto exe = tesseractExecutable(s);
|
||||
if (!std::filesystem::is_regular_file(exe)) throw std::runtime_error("Tesseract executable does not exist");
|
||||
auto library = exe.parent_path() / L"libtesseract-5.dll";
|
||||
module = LoadLibraryExW(library.c_str(), nullptr,
|
||||
LOAD_LIBRARY_SEARCH_DLL_LOAD_DIR | LOAD_LIBRARY_SEARCH_DEFAULT_DIRS);
|
||||
if (!module) throw std::runtime_error("Cannot load Tesseract 5. Select a complete 64-bit installation with libtesseract-5.dll and its dependencies.");
|
||||
}
|
||||
~TessLibrary() { if (module) FreeLibrary(module); }
|
||||
template<class T> T symbol(const char *name)
|
||||
{
|
||||
auto address = GetProcAddress(module, name);
|
||||
if (!address) throw std::runtime_error(std::string("Unsupported Tesseract library: missing ") + name);
|
||||
T result; static_assert(sizeof(result) == sizeof(address));
|
||||
memcpy(&result, &address, sizeof(result));
|
||||
return result;
|
||||
}
|
||||
};
|
||||
struct TessEngine
|
||||
{
|
||||
TessLibrary library;
|
||||
void *handle{};
|
||||
void (*destroy)(void *){};
|
||||
explicit TessEngine(const Settings &s) : library(s)
|
||||
{
|
||||
auto folder = tesseractExecutable(s).parent_path() / L"tessdata";
|
||||
size_t start = 0;
|
||||
do
|
||||
{
|
||||
auto end = s.tesseractLanguages.find(L'+', start);
|
||||
auto language = s.tesseractLanguages.substr(start, end == std::wstring::npos ? end : end - start);
|
||||
if (!std::filesystem::is_regular_file(folder / (language + L".traineddata")))
|
||||
throw std::runtime_error("Tesseract language is not installed: " + utf8(language));
|
||||
if (end == std::wstring::npos) break;
|
||||
start = end + 1;
|
||||
} while (true);
|
||||
auto create = library.symbol<void *(*)()>("TessBaseAPICreate");
|
||||
destroy = library.symbol<void (*)(void *)>("TessBaseAPIDelete");
|
||||
auto init = library.symbol<int (*)(void *, const char *, const char *)>("TessBaseAPIInit3");
|
||||
handle = create();
|
||||
if (!handle) throw std::runtime_error("Cannot create Tesseract engine");
|
||||
if (init(handle, utf8(folder.wstring()).c_str(), utf8(s.tesseractLanguages).c_str()) != 0)
|
||||
{
|
||||
destroy(handle); handle = nullptr;
|
||||
throw std::runtime_error("Cannot initialize the selected Tesseract languages");
|
||||
}
|
||||
}
|
||||
~TessEngine() { if (handle) destroy(handle); }
|
||||
};
|
||||
}
|
||||
void validateTesseract(const Settings &s)
|
||||
{
|
||||
if (s.useTesseract) { TessEngine engine(s); }
|
||||
}
|
||||
std::wstring recognizeText(const Clip &clip, const Settings &s)
|
||||
{
|
||||
if (!s.useTesseract) return recognizeText(clip);
|
||||
auto apartmentResult = CoInitializeEx(nullptr, COINIT_MULTITHREADED);
|
||||
if (FAILED(apartmentResult) && apartmentResult != RPC_E_CHANGED_MODE) check(apartmentResult);
|
||||
struct Apartment { bool owned; ~Apartment() { if (owned) CoUninitialize(); } } apartment{SUCCEEDED(apartmentResult)};
|
||||
// Load the optional C API dynamically: Windows OCR users need no Tesseract DLLs.
|
||||
TessEngine engine(s);
|
||||
auto &lib = engine.library;
|
||||
auto image = lib.symbol<void (*)(void *, const unsigned char *, int, int, int, int)>("TessBaseAPISetImage");
|
||||
auto mode = lib.symbol<void (*)(void *, int)>("TessBaseAPISetPageSegMode");
|
||||
auto recognize = lib.symbol<int (*)(void *, void *)>("TessBaseAPIRecognize");
|
||||
auto getText = lib.symbol<char *(*)(void *)>("TessBaseAPIGetUTF8Text");
|
||||
auto freeText = lib.symbol<void (*)(const char *)>("TessDeleteText");
|
||||
auto createMonitor = lib.symbol<void *(*)()>("TessMonitorCreate");
|
||||
auto freeMonitor = lib.symbol<void (*)(void *)>("TessMonitorDelete");
|
||||
auto deadline = lib.symbol<void (*)(void *, int)>("TessMonitorSetDeadlineMSecs");
|
||||
std::unique_ptr<void, void (*)(void *)> monitor(createMonitor(), freeMonitor);
|
||||
if (!monitor) throw std::runtime_error("Cannot create Tesseract progress monitor");
|
||||
auto pixels = decodeImage(clip);
|
||||
Bytes gray(size_t(pixels.width) * pixels.height);
|
||||
for (size_t i = 0; i < gray.size(); ++i)
|
||||
gray[i] = BYTE((29 * pixels.bgra[4*i] + 150 * pixels.bgra[4*i+1] + 77 * pixels.bgra[4*i+2]) >> 8);
|
||||
image(engine.handle, gray.data(), pixels.width, pixels.height, 1, pixels.width);
|
||||
mode(engine.handle, 11); // Sparse text: screenshots often contain separate labels and paragraphs.
|
||||
deadline(monitor.get(), 30000);
|
||||
if (recognize(engine.handle, monitor.get()) != 0)
|
||||
throw std::runtime_error("Tesseract recognition failed or exceeded 30 seconds");
|
||||
std::unique_ptr<char, void (*)(const char *)> text(getText(engine.handle), freeText);
|
||||
if (!text) throw std::runtime_error("Tesseract returned no result");
|
||||
return wide(text.get());
|
||||
}
|
||||
} // namespace ks
|
||||
|
||||
@@ -10,4 +10,8 @@ struct Pixels
|
||||
Pixels decodeImage(const Clip &, UINT maxWidth = 0, UINT maxHeight = 0);
|
||||
Format imageDib(const Pixels &);
|
||||
std::wstring recognizeText(const Clip &);
|
||||
std::wstring recognizeText(const Clip &, const Settings &);
|
||||
std::filesystem::path tesseractExecutable(const Settings &);
|
||||
void validateTesseract(const Settings &);
|
||||
std::wstring ocrProfile(const Settings &);
|
||||
} // namespace ks
|
||||
|
||||
+1
-1
@@ -169,7 +169,7 @@ struct Capture
|
||||
bool editing{}, dragging{}, arrow{}, owned{}, copied{};
|
||||
bool autoOpenEditor;
|
||||
bool highlight{};
|
||||
bool pointer=true, freehand=false;
|
||||
bool pointer=false, freehand=true;
|
||||
bool straight{}, textTool{};
|
||||
Mark textDefaults{};
|
||||
ScreenshotShape shape=ScreenshotShape::None;
|
||||
|
||||
+76
-3
@@ -44,6 +44,13 @@ bool validId(const std::wstring &id)
|
||||
} // namespace
|
||||
void validateSettings(const Settings &s)
|
||||
{
|
||||
if (s.tesseractPath.size() > 32700 || s.tesseractPath.find_first_of(L"\r\n\"") != s.tesseractPath.npos)
|
||||
throw std::runtime_error("Invalid Tesseract executable path");
|
||||
if (s.tesseractLanguages.empty() || s.tesseractLanguages.size() > 128 ||
|
||||
s.tesseractLanguages.front() == L'+' || s.tesseractLanguages.back() == L'+' ||
|
||||
s.tesseractLanguages.find(L"++") != s.tesseractLanguages.npos ||
|
||||
s.tesseractLanguages.find_first_not_of(L"abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789_+") != s.tesseractLanguages.npos)
|
||||
throw std::runtime_error("Use Tesseract language codes separated by +, for example ukr+eng+rus");
|
||||
std::vector<Hotkey> used;
|
||||
std::vector<std::wstring> keys{s.toggle, s.casing, s.translit, s.undo, s.clipboard, s.screenshot};
|
||||
keys.insert(keys.end(), s.direct.begin(), s.direct.end());
|
||||
@@ -125,6 +132,9 @@ Settings decodeSettings(const Bytes &bytes, const std::vector<Layout> &layouts)
|
||||
s.switchLayout = j.value("switchSystemLayout", true);
|
||||
s.writeLog = j.value("writeLog", true);
|
||||
s.history = j.value("historyEnabled", true);
|
||||
s.useTesseract = j.value("useTesseract", false);
|
||||
s.tesseractPath = str(j, "tesseractPath");
|
||||
s.tesseractLanguages = str(j, "tesseractLanguages", s.tesseractLanguages);
|
||||
s.autostart = j.value("startWithSystem", false);
|
||||
s.elevatedAutostart = j.value("autostartAsAdministrator", false);
|
||||
s.awake = j.value("preventScreenLock", false);
|
||||
@@ -196,6 +206,9 @@ Bytes encodeSettings(const Settings &s)
|
||||
{"writeLog", s.writeLog},
|
||||
{"autostartAsAdministrator", s.elevatedAutostart},
|
||||
{"historyEnabled", s.history},
|
||||
{"useTesseract", s.useTesseract},
|
||||
{"tesseractPath", utf8(s.tesseractPath)},
|
||||
{"tesseractLanguages", utf8(s.tesseractLanguages)},
|
||||
{"startWithSystem", s.autostart},
|
||||
{"preventScreenLock", s.awake},
|
||||
{"maxItems", s.maxItems},
|
||||
@@ -297,7 +310,8 @@ History::History(const std::filesystem::path &folder) : folder_(folder)
|
||||
e.value("at", uint64_t{}),
|
||||
e.value("pinned", false),
|
||||
e.value("image", false),
|
||||
e.value("files", false)};
|
||||
e.value("files", false), e.value("ocrState", e.value("image", false) ? 1 : 0),
|
||||
str(e, "ocrProfile", L"windows")};
|
||||
if (validId(item.id) && std::filesystem::exists(folder_ / (item.id + L".dat")))
|
||||
entries_.push_back(std::move(item));
|
||||
}
|
||||
@@ -313,7 +327,7 @@ void History::saveIndex()
|
||||
{"at", e.at},
|
||||
{"pinned", e.pinned},
|
||||
{"image", e.image},
|
||||
{"files", e.files}});
|
||||
{"files", e.files}, {"ocrState", e.ocrState}, {"ocrProfile", utf8(e.ocrProfile)}});
|
||||
atomicWrite(folder_ / L"index.dat", protect(jsonBytes(j)));
|
||||
}
|
||||
std::vector<Entry> History::entries() const
|
||||
@@ -342,6 +356,7 @@ void History::prune(const Settings &s)
|
||||
total -= entries_[i].bytes;
|
||||
std::error_code ec;
|
||||
std::filesystem::remove(folder_ / (entries_[i].id + L".dat"), ec);
|
||||
std::filesystem::remove(folder_ / (entries_[i].id + L".ocr"), ec);
|
||||
entries_.erase(entries_.begin() + i);
|
||||
}
|
||||
}
|
||||
@@ -429,7 +444,8 @@ void History::add(const Clip &clip, const std::wstring &app, const Settings &s)
|
||||
GetSystemTimeAsFileTime(&now);
|
||||
entries_.insert(entries_.begin(),
|
||||
Entry{id, text, app, encrypted.size(),
|
||||
(uint64_t(now.dwHighDateTime) << 32) | now.dwLowDateTime, false, image, files});
|
||||
(uint64_t(now.dwHighDateTime) << 32) | now.dwLowDateTime, false, image, files,
|
||||
image ? 1 : 0, ocrProfile(s)});
|
||||
prune(s);
|
||||
saveIndex();
|
||||
}
|
||||
@@ -445,6 +461,7 @@ void History::remove(const std::wstring &id)
|
||||
saveIndex();
|
||||
std::error_code ec;
|
||||
std::filesystem::remove(folder_ / (id + L".dat"), ec);
|
||||
std::filesystem::remove(folder_ / (id + L".ocr"), ec);
|
||||
}
|
||||
void History::pin(const std::wstring &id)
|
||||
{
|
||||
@@ -464,8 +481,49 @@ void History::clear()
|
||||
{
|
||||
std::error_code ec;
|
||||
std::filesystem::remove(folder_ / (e.id + L".dat"), ec);
|
||||
std::filesystem::remove(folder_ / (e.id + L".ocr"), ec);
|
||||
}
|
||||
}
|
||||
bool History::saveOcr(const std::wstring &id, const std::optional<std::wstring> &text, const Settings &settings)
|
||||
{
|
||||
std::lock_guard lock(mutex_);
|
||||
auto it = std::find_if(entries_.begin(), entries_.end(), [&](auto &e) { return e.id == id; });
|
||||
// A late OCR completion must never recreate a deleted/pruned image.
|
||||
auto profile = ocrProfile(settings);
|
||||
if (it == entries_.end() || !it->image || (it->ocrState == 2 && it->ocrProfile == profile)) return false;
|
||||
if (text)
|
||||
{
|
||||
auto utf = utf8(*text);
|
||||
if (utf.size() > 1024 * 1024) throw std::runtime_error("OCR text exceeds storage limit");
|
||||
// A version byte also makes empty recognition results encryptable by DPAPI.
|
||||
Bytes payload{1};
|
||||
payload.insert(payload.end(), utf.begin(), utf.end());
|
||||
auto encrypted = protect(payload);
|
||||
auto path = folder_ / (id + L".ocr");
|
||||
std::error_code ec;
|
||||
auto previousBytes = std::filesystem::file_size(path, ec);
|
||||
if (ec) previousBytes = 0;
|
||||
atomicWrite(path, encrypted);
|
||||
it->bytes = it->bytes - std::min(it->bytes, uint64_t(previousBytes)) + encrypted.size();
|
||||
it->ocrState = 2;
|
||||
}
|
||||
else it->ocrState = 3;
|
||||
it->ocrProfile = profile;
|
||||
prune(settings);
|
||||
saveIndex();
|
||||
return true;
|
||||
}
|
||||
std::optional<std::wstring> History::ocrText(const std::wstring &id, const std::wstring &profile) const
|
||||
{
|
||||
{
|
||||
std::lock_guard lock(mutex_);
|
||||
auto it = std::find_if(entries_.begin(), entries_.end(), [&](auto &e) { return e.id == id; });
|
||||
if (it == entries_.end() || it->ocrState != 2 || (!profile.empty() && it->ocrProfile != profile)) return std::nullopt;
|
||||
}
|
||||
auto bytes = unprotect(readFile(folder_ / (id + L".ocr"), 2 * 1024 * 1024));
|
||||
if (bytes.empty() || bytes.front() != 1) throw std::runtime_error("Invalid OCR text format");
|
||||
return wide(std::string(bytes.begin() + 1, bytes.end()));
|
||||
}
|
||||
std::vector<Entry> History::search(const std::wstring &query) const
|
||||
{
|
||||
auto items = entries();
|
||||
@@ -477,6 +535,21 @@ std::vector<Entry> History::search(const std::wstring &query) const
|
||||
{
|
||||
if (lower(e.preview + L" " + e.app).find(q) != q.npos)
|
||||
return false;
|
||||
if (e.ocrState == 2)
|
||||
{
|
||||
try
|
||||
{
|
||||
auto text = ocrText(e.id);
|
||||
if (text && lower(*text).find(q) != q.npos) return false;
|
||||
}
|
||||
catch (...) {} // Missing/corrupt OCR must not hide the original clip.
|
||||
}
|
||||
// Short previews contain the complete text (or a placeholder for
|
||||
// textless clips). Do not decrypt image payloads just to rule them out.
|
||||
// Newlines/tabs are flattened in previews, so those queries still
|
||||
// need the original text. Exactly 240 characters may be truncated.
|
||||
if (e.preview.size() < 240 && q.find_first_of(L"\r\n\t") == q.npos)
|
||||
return true;
|
||||
try
|
||||
{
|
||||
return lower(load(e.id).text()).find(q) == q.npos;
|
||||
|
||||
@@ -13,6 +13,8 @@ struct Entry
|
||||
std::wstring id, preview, app;
|
||||
uint64_t bytes{}, at{};
|
||||
bool pinned{}, image{}, files{};
|
||||
int ocrState{}; // 0: legacy/not applicable, 1: pending, 2: saved, 3: failed
|
||||
std::wstring ocrProfile = L"windows";
|
||||
};
|
||||
class History
|
||||
{
|
||||
@@ -27,6 +29,8 @@ class History
|
||||
std::vector<Entry> entries() const;
|
||||
Clip load(const std::wstring &id) const;
|
||||
void add(const Clip &, const std::wstring &app, const Settings &);
|
||||
bool saveOcr(const std::wstring &id, const std::optional<std::wstring> &, const Settings &);
|
||||
std::optional<std::wstring> ocrText(const std::wstring &id, const std::wstring &profile = L"") const;
|
||||
void remove(const std::wstring &);
|
||||
void pin(const std::wstring &);
|
||||
void clear();
|
||||
|
||||
+99
-2
@@ -420,7 +420,7 @@ void search(HWND w, HistoryView *v)
|
||||
auto generation = ++v->generation;
|
||||
v->pending.clear();
|
||||
auto *app = v->app;
|
||||
app->enqueue(
|
||||
app->enqueueHistorySearch(
|
||||
[w, app, q, generation]
|
||||
{
|
||||
try
|
||||
@@ -625,6 +625,8 @@ LRESULT CALLBACK historyProc(HWND w, UINT msg, WPARAM wp, LPARAM lp)
|
||||
int id = LOWORD(wp);
|
||||
if (id == 101 && HIWORD(wp) == EN_CHANGE)
|
||||
{
|
||||
// Reject an older result even during the debounce interval.
|
||||
++v->generation;
|
||||
SetTimer(w, 1, 180, nullptr);
|
||||
return 0;
|
||||
}
|
||||
@@ -732,7 +734,7 @@ LRESULT CALLBACK historyProc(HWND w, UINT msg, WPARAM wp, LPARAM lp)
|
||||
AppendMenuW(menu, MF_STRING, 112, L"Pin / unpin");
|
||||
AppendMenuW(menu, MF_STRING, 113, L"Delete");
|
||||
AppendMenuW(menu, MF_STRING, 114, L"Open full item");
|
||||
AppendMenuW(menu, MF_STRING, 115, L"Copy text from image (Windows OCR)");
|
||||
AppendMenuW(menu, MF_STRING, 115, L"Copy text from image (OCR)");
|
||||
POINT p;
|
||||
GetCursorPos(&p);
|
||||
int cmd = TrackPopupMenu(menu, TPM_RETURNCMD, p.x, p.y, 0, w, nullptr);
|
||||
@@ -1057,6 +1059,99 @@ void showAutoOptions(HWND parent, SettingsView *v)
|
||||
showRequestedWindow(w);
|
||||
SetForegroundWindow(w);
|
||||
}
|
||||
struct OcrOptionsView { HWND parent; SettingsView *settings; };
|
||||
Settings ocrDraft(HWND w, OcrOptionsView *v)
|
||||
{
|
||||
auto draft = v->settings->draft;
|
||||
draft.useTesseract = checked(w, 501);
|
||||
draft.tesseractPath = value(w, 502);
|
||||
draft.tesseractLanguages = value(w, 503);
|
||||
validateSettings(draft);
|
||||
return draft;
|
||||
}
|
||||
LRESULT CALLBACK ocrOptionsProc(HWND w, UINT msg, WPARAM wp, LPARAM lp)
|
||||
{
|
||||
auto *v = reinterpret_cast<OcrOptionsView *>(GetWindowLongPtrW(w, GWLP_USERDATA));
|
||||
if (!v) return DefWindowProcW(w, msg, wp, lp);
|
||||
if (msg == WM_COMMAND)
|
||||
{
|
||||
int id = LOWORD(wp);
|
||||
try
|
||||
{
|
||||
if (id == 507)
|
||||
{
|
||||
if ((INT_PTR)ShellExecuteW(w, L"open", L"https://github.com/UB-Mannheim/tesseract/wiki#tesseract-installer-for-windows",
|
||||
nullptr, nullptr, SW_SHOWNORMAL) <= 32)
|
||||
throw std::runtime_error("Could not open the Tesseract download page in your browser");
|
||||
return 0;
|
||||
}
|
||||
if (id == 504)
|
||||
{
|
||||
wchar_t path[32768]{};
|
||||
OPENFILENAMEW picker{sizeof(picker)};
|
||||
picker.hwndOwner = w; picker.lpstrFile = path; picker.nMaxFile = std::size(path);
|
||||
picker.lpstrFilter = L"Tesseract executable (tesseract.exe)\0tesseract.exe\0Executables\0*.exe\0";
|
||||
picker.Flags = OFN_FILEMUSTEXIST | OFN_NOCHANGEDIR;
|
||||
if (GetOpenFileNameW(&picker)) value(w, 502, path);
|
||||
return 0;
|
||||
}
|
||||
if (id == 505 || id == IDOK)
|
||||
{
|
||||
auto draft = ocrDraft(w, v);
|
||||
if (id == 505)
|
||||
{
|
||||
draft.useTesseract = true;
|
||||
validateTesseract(draft);
|
||||
SetDlgItemTextW(w, 506, (L"Ready: " + draft.tesseractLanguages).c_str());
|
||||
return 0;
|
||||
}
|
||||
validateTesseract(draft);
|
||||
v->settings->draft.useTesseract = draft.useTesseract;
|
||||
v->settings->draft.tesseractPath = draft.tesseractPath;
|
||||
v->settings->draft.tesseractLanguages = draft.tesseractLanguages;
|
||||
DestroyWindow(w);
|
||||
return 0;
|
||||
}
|
||||
if (id == IDCANCEL) { DestroyWindow(w); return 0; }
|
||||
}
|
||||
catch (const std::exception &e) { error(w, e); return 0; }
|
||||
}
|
||||
if (msg == WM_CLOSE) { DestroyWindow(w); return 0; }
|
||||
if (msg == WM_NCDESTROY)
|
||||
{
|
||||
EnableWindow(v->parent, TRUE);
|
||||
SetForegroundWindow(v->parent);
|
||||
disposeFont(w); delete v;
|
||||
SetWindowLongPtrW(w, GWLP_USERDATA, 0);
|
||||
}
|
||||
return DefWindowProcW(w, msg, wp, lp);
|
||||
}
|
||||
void showOcrOptions(HWND parent, SettingsView *v)
|
||||
{
|
||||
HWND w = makeWindow(*v->app, L"KSwitcher.OcrOptions", L"Image text recognition", ocrOptionsProc, 640, 450);
|
||||
SetWindowLongPtrW(w, GWLP_HWNDPARENT, (LONG_PTR)parent);
|
||||
SetWindowLongPtrW(w, GWLP_USERDATA, (LONG_PTR)new OcrOptionsView{parent, v});
|
||||
label(w, L"Windows OCR is used by default. Recognition stays on this computer.", 18, 16, 600);
|
||||
checkbox(w, L"Use optional Tesseract 5 instead of Windows OCR", 501, 18, 48, 600);
|
||||
check(w, 501, v->draft.useTesseract);
|
||||
label(w, L"Tesseract executable (blank = detect installed location)", 18, 90, 600);
|
||||
edit(w, 502, 18, 118, 484);
|
||||
value(w, 502, v->draft.tesseractPath);
|
||||
button(w, L"Browse…", 504, 514, 117, 106);
|
||||
label(w, L"Languages used together (for example ukr+eng+rus)", 18, 160, 600);
|
||||
edit(w, 503, 18, 188, 602);
|
||||
value(w, 503, v->draft.tesseractLanguages);
|
||||
button(w, L"Check installation", 505, 18, 228, 180);
|
||||
control(w, L"STATIC", L"", 0, 506, 212, 232, 408, 24);
|
||||
button(w, L"Download Tesseract…", 507, 18, 266, 180);
|
||||
label(w, L"Opens the Windows installer page in your browser.", 212, 270, 408);
|
||||
label(w, L"Changing the engine or languages reprocesses saved images in the background.", 18, 314, 602);
|
||||
label(w, L"Click OK here, then Save in Settings to apply. No downloads are automatic.", 18, 344, 602);
|
||||
button(w, L"OK", IDOK, 406, 390, 100);
|
||||
button(w, L"Cancel", IDCANCEL, 520, 390, 100);
|
||||
EnableWindow(parent, FALSE);
|
||||
showRequestedWindow(w); SetForegroundWindow(w);
|
||||
}
|
||||
LRESULT CALLBACK settingsProc(HWND w, UINT msg, WPARAM wp, LPARAM lp)
|
||||
{
|
||||
if (msg == WM_DPICHANGED)
|
||||
@@ -1092,6 +1187,7 @@ LRESULT CALLBACK settingsProc(HWND w, UINT msg, WPARAM wp, LPARAM lp)
|
||||
showLogs(*v->app);
|
||||
return 0;
|
||||
}
|
||||
if (id == 257) { showOcrOptions(w, v); return 0; }
|
||||
if (id == 230)
|
||||
{
|
||||
collectLayout(w, v);
|
||||
@@ -1685,6 +1781,7 @@ void showSettings(App &app, bool visible)
|
||||
edit(w, 243, 18, 544, 742);
|
||||
button(w, L"Auto-correction options…", 255, 18, 575, 240);
|
||||
button(w, L"View log…", 256, 278, 575, 220);
|
||||
button(w, L"OCR options…", 257, 518, 575, 242);
|
||||
button(w, L"Import settings…", 250, 18, 606, 145);
|
||||
button(w, L"Export settings…", 251, 173, 606, 145);
|
||||
button(w, L"Snippets…", 252, 328, 606, 110);
|
||||
|
||||
+1
-1
@@ -2,7 +2,7 @@
|
||||
#include "platform.h"
|
||||
namespace ks
|
||||
{
|
||||
inline constexpr wchar_t AppVersion[] = L"0.6.7";
|
||||
inline constexpr wchar_t AppVersion[] = L"0.6.8";
|
||||
inline constexpr UINT UpdateMessage = WM_APP + 7;
|
||||
inline constexpr UINT UpdateCheckIntervalMs = 6 * 60 * 60 * 1000;
|
||||
struct UpdateResult
|
||||
|
||||
Reference in New Issue
Block a user