feat(vision): expose OCR pipeline (#360)

* feat(vision): expose OCR pipeline

* fix(vision): harden OCR API

* refactor(vision): expose OCR API

tests/ocr_tests.rs

@@ -1,5 +1,9 @@
 #![cfg(all(feature = "ocr-oar", not(target_arch = "wasm32")))]
 
+#[cfg(feature = "ocr")]
+use pdf_inspector::vision::{
+    process_pdf_with_ocr_mem, ModelDownloadPolicy, OcrPdfOptions, PageContentSource,
+};
 use pdf_inspector::vision::{
     ModelStore, OarOcrEngine, OcrEngine, OcrMode, OcrOptions, PageTransform, RenderPixelFormat,
     RenderedPage, PP_OCR_V6_SMALL,
@@ -100,6 +104,34 @@ fn recognizes_a_pdfium_rendered_fixture_with_verified_models() {
     assert_usable_result(&results);
 }
 
+#[cfg(all(feature = "ocr", feature = "render-pdfium"))]
+#[test]
+fn complete_ocr_pipeline_routes_and_assembles_a_scanned_fixture() {
+    let Some(model_directory) = std::env::var_os(MODEL_DIRECTORY_ENV) else {
+        eprintln!("skipping OCR runtime test because {MODEL_DIRECTORY_ENV} is not set");
+        return;
+    };
+    let Some(_renderer) = load_renderer() else {
+        return;
+    };
+
+    let bytes = std::fs::read("tests/fixtures/scan_with_native_header_text.pdf").unwrap();
+    let ocr = OcrOptions::new()
+        .mode(OcrMode::Auto)
+        .minimum_confidence(0.3)
+        .model_directory(model_directory)
+        .model_downloads(ModelDownloadPolicy::Offline);
+    let result = process_pdf_with_ocr_mem(&bytes, OcrPdfOptions::new().ocr(ocr)).unwrap();
+
+    assert_eq!(result.pages_routed_to_ocr, vec![1]);
+    assert!(!result.markdown.trim().is_empty());
+    assert_eq!(result.pages[0].provenance.source, PageContentSource::Ocr);
+    assert_eq!(
+        result.pages[0].provenance.ocr_model.as_ref().unwrap().name,
+        PP_OCR_V6_SMALL.id
+    );
+}
+
 fn recognize(
     model_directory: &std::ffi::OsStr,
     pages: &[RenderedPage],