mirror of
https://github.com/storytold/pdfcraft.git
synced 2026-10-28 20:18:06 -06:00
966bd0ffce
The ui-egui integration tests drive the shell by its English labels, and `i18n::system_lang` returns `Lang::EN` under `cfg!(test)` so they can. That only covers the unit tests: an integration test links the library as it ships, where `cfg!(test)` is off, so `PdfCraftApp::new()` leaves `language` on `auto` and the shell is drawn in the system language. On a Spanish Windows eleven of the test binaries fail; a French, Russian, Chinese, Japanese, Portuguese, Czech or Telugu machine does the same. CI never sees it because its locale is English. `tests/theme.rs` and `tests/create.rs` already pin the option; the other 119 harnesses now do too, and the comment in `system_lang` says why, so a test copied from an existing one keeps the line. Also `i18n::tests::windows_display_language_query_returns_a_locale_tag` treated the return of `windows_ui_language()` as a single tag. It is the preferred-language list, one tag per line, as `first_supported` reads it, so on a Windows with two or more display languages the assertion tripped over the newline. It now checks the shape of every line. Co-authored-by: Fernando Areán <soporte@codebit.es> Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
68 lines
2.8 KiB
Rust
68 lines
2.8 KiB
Rust
//! Scan & OCR ▸ Recognize text in the real shell (egui_kittest): the dialog, the run and its
|
|
//! result (skipped without the OCR models: `cargo xtask models`).
|
|
|
|
use egui_kittest::Harness;
|
|
use egui_kittest::kittest::Queryable;
|
|
use pdfcraft_engine::{Session, export};
|
|
use pdfcraft_ui_egui::PdfCraftApp;
|
|
|
|
/// A one-page PDF that is only a picture of a sentence.
|
|
fn scan() -> Vec<u8> {
|
|
let mut s = Session::new();
|
|
let text = s.create_from_text("t", "Recognize these scanned words").unwrap();
|
|
let id = s.open("text.pdf", None, text, None).unwrap();
|
|
let png = export::Exporter::new(s.get(id).unwrap()).png(0, 150.0).unwrap();
|
|
s.create_from_images(&[("scan.png".into(), png)]).unwrap().to_vec()
|
|
}
|
|
|
|
#[test]
|
|
fn recognize_text_dialog_adds_searchable_text() {
|
|
let mut h = Harness::builder().with_size(egui::vec2(1400.0, 900.0)).build_eframe(|_cc| {
|
|
let mut app = PdfCraftApp::new();
|
|
app.set_option("language", "en").unwrap();
|
|
app.open_bytes("scan.pdf", None, scan()).unwrap();
|
|
app.run_inline = true;
|
|
app
|
|
});
|
|
h.run_steps(4);
|
|
assert!(h.state_mut().execute("ocr.recognize"));
|
|
h.run_steps(2);
|
|
h.get_by_label("Document language");
|
|
h.get_by_label("Output");
|
|
if !pdfcraft_engine::ocr::available() {
|
|
eprintln!("skipped: OCR models not installed");
|
|
return;
|
|
}
|
|
h.get_by_label("Recognize text").click();
|
|
h.run_steps(3);
|
|
assert!(h.state().ocr_run.is_none(), "finished");
|
|
let toast = h.state().toast.clone().unwrap().0;
|
|
assert!(toast.starts_with("Recognized ") && toast.contains("on 1 page"), "{toast}");
|
|
let app = h.state();
|
|
let id = app.active_ids().unwrap().1;
|
|
assert_eq!(app.session.get(id).unwrap().can_undo(), Some("Recognize text"));
|
|
}
|
|
|
|
#[test]
|
|
fn recognize_text_in_multiple_files_writes_searchable_copies() {
|
|
if !pdfcraft_engine::ocr::available() {
|
|
eprintln!("skipped: OCR models not installed");
|
|
return;
|
|
}
|
|
let dir = std::env::temp_dir().join(format!("pdfcraft-ocr-ui-{}", std::process::id()));
|
|
let _ = std::fs::remove_dir_all(&dir);
|
|
std::fs::create_dir_all(&dir).unwrap();
|
|
let mut app = PdfCraftApp::new();
|
|
app.set_option("language", "en").unwrap();
|
|
app.run_inline = true;
|
|
app.export_dir_override = Some(dir.to_string_lossy().into_owned());
|
|
app.use_files(pdfcraft_ui_egui::FilePurpose::Ocr, vec![("one.pdf".into(), scan()), ("two.pdf".into(), scan())]);
|
|
assert!(app.ocr_batch.is_none(), "finished");
|
|
let toast = app.toast.clone().unwrap().0;
|
|
assert!(toast.starts_with("Recognized ") && toast.ends_with("in 2 files"), "{toast}");
|
|
for name in ["one.pdf", "two.pdf"] {
|
|
let bytes = std::fs::read(dir.join(name)).unwrap();
|
|
assert!(bytes.len() > scan().len(), "an incremental update was appended");
|
|
}
|
|
}
|