Release v0.6.8: add background image OCR and optional Tesseract

2026-10-29 21:40:29 +02:00
parent 95c7199027
commit 107d2f8852
21 changed files with 590 additions and 37 deletions
@@ -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