hrynco/hrynco-kswitcher
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 41 Wiki Activity

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

Browse Source
This commit is contained in:
Anatolii Hrynchuk
2026-10-29 21:40:29 +02:00
parent 95c7199027
commit 107d2f8852
21 changed files with 590 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/tests.cpp
+69
View File
@@ -468,6 +468,75 @@ int main(int argc, char **argv)
history.clear();
require(history.entries().empty(), "clear history");
}
{
ks::History history(temp / L"search");
history.add(ks::textClip(std::wstring(260, L'x') + L" hidden needle"), L"Test", settings);
history.add(ks::textClip(L"first\nsecond\tthird"), L"Test", settings);
require(history.search(L"hidden needle").size() == 1, "search beyond truncated preview");
require(history.search(L"first\nsecond").size() == 1, "search retains original newlines");
require(history.search(L"second\tthird").size() == 1, "search retains original tabs");
require(history.search(L"absent").empty(), "short previews reject unmatched queries");
require(history.search(L"FIRST").size() == 1, "short preview search ignores case");
}
{
auto folder = temp / L"ocr-history";
ks::History history(folder);
ks::Clip image{{ks::imageDib(ks::Pixels{2, 2, ks::Bytes(16, 255)})}};
history.add(image, L"OCR test", settings);
auto id = history.entries().front().id;
require(history.entries().front().ocrState == 1, "new images await background OCR");
require(ks::History(folder).entries().front().ocrState == 1, "pending OCR survives restart");
auto original = ks::encodeClip(history.load(id));
auto beforeBytes = history.entries().front().bytes;
require(history.saveOcr(id, L"Розпізнаний текст HELLO", settings), "save image OCR");
require(history.entries().front().bytes > beforeBytes, "OCR storage counts against history size");
require(ks::encodeClip(history.load(id)) == original, "OCR preserves original image formats");
require(!history.saveOcr(id, L"replacement", settings), "completed OCR is not overwritten");
ks::History restored(folder);
require(restored.search(L"розпізнаний").size() == 1, "persisted Ukrainian OCR is searchable");
require(restored.ocrText(id) == L"Розпізнаний текст HELLO", "OCR text survives restart");
auto raw = ks::readFile(folder / (id + L".ocr"), 2 * 1024 * 1024);
require(std::string(raw.begin(), raw.end()).find("HELLO") == std::string::npos, "OCR sidecar is encrypted");
restored.remove(id);
require(!std::filesystem::exists(folder / (id + L".ocr")), "deleting image removes OCR sidecar");
require(!restored.saveOcr(id, L"late result", settings), "late OCR cannot resurrect deleted image");
restored.add(image, L"OCR test", settings);
id = restored.entries().front().id;
restored.saveOcr(id, L"", settings);
require(restored.ocrText(id).has_value() && restored.ocrText(id)->empty(), "empty OCR is a completed result");
restored.clear();
require(!std::filesystem::exists(folder / (id + L".ocr")), "clear removes OCR sidecars");
restored.add(image, L"OCR test", settings);
id = restored.entries().front().id;
restored.saveOcr(id, std::nullopt, settings);
require(ks::History(folder).entries().front().ocrState == 3, "failed OCR is not retried on every search or restart");
restored.saveOcr(id, L"manual retry", settings);
require(restored.search(L"manual retry").size() == 1, "explicit retry can recover failed OCR");
restored.add(ks::textClip(L"newer"), L"test", settings);
auto limited = settings; limited.maxItems = 1;
restored.add(ks::textClip(L"newest"), L"test", limited);
require(!std::filesystem::exists(folder / (id + L".ocr")), "pruning image removes OCR sidecar");
}
{
ks::Settings options;
require(!options.useTesseract, "Tesseract is opt-in by default");
options.useTesseract = true;
options.tesseractPath = L"C:\\Program Files\\Tesseract-OCR\\tesseract.exe";
options.tesseractLanguages = L"ukr+eng+rus";
auto restored = ks::decodeSettings(ks::encodeSettings(options), {});
require(restored.useTesseract && restored.tesseractPath == options.tesseractPath &&
restored.tesseractLanguages == options.tesseractLanguages, "OCR settings roundtrip");
options.tesseractLanguages = L"ukr+../eng";
rejects([&] { ks::validateSettings(options); }, "OCR language paths rejected");
options.tesseractLanguages = L"ukr++eng";
rejects([&] { ks::validateSettings(options); }, "empty OCR language rejected");
options.tesseractLanguages = L"ukr+eng";
options.tesseractPath = L"C:\\missing-tesseract\\tesseract.exe";
rejects([&] { ks::validateTesseract(options); }, "missing optional Tesseract reports clear failure");
options.useTesseract = false;
ks::validateTesseract(options);
require(true, "Windows OCR works without optional installation");
}
// Test-owned directory only; never touch the user's clipboard or stored history.
std::filesystem::remove_all(temp);
CoUninitialize();