kreuzberg 4.1.2 → 4.2.1

data/vendor/kreuzberg/tests/pptx_regression_tests.rs

@@ -1,13 +1,15 @@
 //! Regression tests for PPTX/PPSX extraction bugs
 //!
 //! GitHub Issue #321: PPTX extraction fails on shapes without txBody (image placeholders) + PPSX not supported
+//! GitHub Issue #329: Extracting images from PPTX results in reversed page numbers
 //!
 //! Bug 1: "No txBody found" - PPTX extraction fails when any shape lacks a text body
 //! Bug 2: PPSX not supported - PowerPoint Show files rejected entirely
+//! Bug 3: Image page numbers reversed - image on slide 1 reports page_number=2
 
 #![cfg(feature = "office")]
 
-use kreuzberg::{ExtractionConfig, extract_file};
+use kreuzberg::{ExtractionConfig, ImageExtractionConfig, extract_file};
 use std::io::Write;
 use tempfile::NamedTempFile;
 use zip::CompressionMethod;
@@ -25,9 +27,9 @@ use zip::write::{FileOptions, ZipWriter};
 async fn test_ppsx_slideshow_extraction() {
     let workspace_root = std::path::Path::new(env!("CARGO_MANIFEST_DIR"))
         .parent()
-        .unwrap()
+        .expect("Operation failed")
         .parent()
-        .unwrap();
+        .expect("Operation failed");
     let test_file = workspace_root.join("test_documents/presentations/sample.ppsx");
 
     if !test_file.exists() {
@@ -69,9 +71,9 @@ async fn test_ppsx_slideshow_extraction() {
 async fn test_ppsx_with_explicit_mime_type() {
     let workspace_root = std::path::Path::new(env!("CARGO_MANIFEST_DIR"))
         .parent()
-        .unwrap()
+        .expect("Operation failed")
         .parent()
-        .unwrap();
+        .expect("Operation failed");
     let test_file = workspace_root.join("test_documents/presentations/sample.ppsx");
 
     if !test_file.exists() {
@@ -120,24 +122,26 @@ async fn test_pptx_with_image_placeholder_no_txbody() {
         let options: FileOptions<()> = FileOptions::default().compression_method(CompressionMethod::Stored);
 
         // Add [Content_Types].xml
-        zip.start_file("[Content_Types].xml", options).unwrap();
+        zip.start_file("[Content_Types].xml", options)
+            .expect("Operation failed");
         zip.write_all(br#"<?xml version="1.0" encoding="UTF-8"?>
 <Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">
   <Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/>
   <Default Extension="xml" ContentType="application/xml"/>
   <Override PartName="/ppt/presentation.xml" ContentType="application/vnd.openxmlformats-officedocument.presentationml.presentation.main+xml"/>
   <Override PartName="/ppt/slides/slide1.xml" ContentType="application/vnd.openxmlformats-officedocument.presentationml.slide+xml"/>
-</Types>"#).unwrap();
+</Types>"#).expect("Operation failed");
 
         // Add _rels/.rels
-        zip.start_file("_rels/.rels", options).unwrap();
+        zip.start_file("_rels/.rels", options).expect("Operation failed");
         zip.write_all(br#"<?xml version="1.0" encoding="UTF-8"?>
 <Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
   <Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="ppt/presentation.xml"/>
-</Relationships>"#).unwrap();
+</Relationships>"#).expect("Operation failed");
 
         // Add ppt/presentation.xml
-        zip.start_file("ppt/presentation.xml", options).unwrap();
+        zip.start_file("ppt/presentation.xml", options)
+            .expect("Operation failed");
         zip.write_all(
             br#"<?xml version="1.0" encoding="UTF-8"?>
 <p:presentation xmlns:p="http://schemas.openxmlformats.org/presentationml/2006/main"
@@ -148,18 +152,20 @@ async fn test_pptx_with_image_placeholder_no_txbody() {
   </p:sldIdLst>
 </p:presentation>"#,
         )
-        .unwrap();
+        .expect("Operation failed");
 
         // Add ppt/_rels/presentation.xml.rels
-        zip.start_file("ppt/_rels/presentation.xml.rels", options).unwrap();
+        zip.start_file("ppt/_rels/presentation.xml.rels", options)
+            .expect("Operation failed");
         zip.write_all(br#"<?xml version="1.0" encoding="UTF-8"?>
 <Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
   <Relationship Id="rId2" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/slide" Target="slides/slide1.xml"/>
-</Relationships>"#).unwrap();
+</Relationships>"#).expect("Operation failed");
 
         // Add ppt/slides/slide1.xml with a shape WITHOUT txBody (image placeholder)
         // This is the critical test case - a <p:sp> element with no <p:txBody>
-        zip.start_file("ppt/slides/slide1.xml", options).unwrap();
+        zip.start_file("ppt/slides/slide1.xml", options)
+            .expect("Operation failed");
         zip.write_all(
             br#"<?xml version="1.0" encoding="UTF-8"?>
 <p:sld xmlns:p="http://schemas.openxmlformats.org/presentationml/2006/main"
@@ -259,18 +265,19 @@ async fn test_pptx_with_image_placeholder_no_txbody() {
   </p:cSld>
 </p:sld>"#,
         )
-        .unwrap();
+        .expect("Operation failed");
 
         // Add ppt/slides/_rels/slide1.xml.rels (empty)
-        zip.start_file("ppt/slides/_rels/slide1.xml.rels", options).unwrap();
+        zip.start_file("ppt/slides/_rels/slide1.xml.rels", options)
+            .expect("Operation failed");
         zip.write_all(
             br#"<?xml version="1.0" encoding="UTF-8"?>
 <Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
 </Relationships>"#,
         )
-        .unwrap();
+        .expect("Operation failed");
 
-        zip.finish().unwrap();
+        zip.finish().expect("Operation failed");
     }
 
     // Extract the PPTX file
@@ -336,24 +343,26 @@ async fn test_pptx_mixed_shapes_extraction() {
         let options: FileOptions<()> = FileOptions::default().compression_method(CompressionMethod::Stored);
 
         // Add [Content_Types].xml
-        zip.start_file("[Content_Types].xml", options).unwrap();
+        zip.start_file("[Content_Types].xml", options)
+            .expect("Operation failed");
         zip.write_all(br#"<?xml version="1.0" encoding="UTF-8"?>
 <Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">
   <Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/>
   <Default Extension="xml" ContentType="application/xml"/>
   <Override PartName="/ppt/presentation.xml" ContentType="application/vnd.openxmlformats-officedocument.presentationml.presentation.main+xml"/>
   <Override PartName="/ppt/slides/slide1.xml" ContentType="application/vnd.openxmlformats-officedocument.presentationml.slide+xml"/>
-</Types>"#).unwrap();
+</Types>"#).expect("Operation failed");
 
         // Add _rels/.rels
-        zip.start_file("_rels/.rels", options).unwrap();
+        zip.start_file("_rels/.rels", options).expect("Operation failed");
         zip.write_all(br#"<?xml version="1.0" encoding="UTF-8"?>
 <Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
   <Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="ppt/presentation.xml"/>
-</Relationships>"#).unwrap();
+</Relationships>"#).expect("Operation failed");
 
         // Add ppt/presentation.xml
-        zip.start_file("ppt/presentation.xml", options).unwrap();
+        zip.start_file("ppt/presentation.xml", options)
+            .expect("Operation failed");
         zip.write_all(
             br#"<?xml version="1.0" encoding="UTF-8"?>
 <p:presentation xmlns:p="http://schemas.openxmlformats.org/presentationml/2006/main"
@@ -364,17 +373,19 @@ async fn test_pptx_mixed_shapes_extraction() {
   </p:sldIdLst>
 </p:presentation>"#,
         )
-        .unwrap();
+        .expect("Operation failed");
 
         // Add ppt/_rels/presentation.xml.rels
-        zip.start_file("ppt/_rels/presentation.xml.rels", options).unwrap();
+        zip.start_file("ppt/_rels/presentation.xml.rels", options)
+            .expect("Operation failed");
         zip.write_all(br#"<?xml version="1.0" encoding="UTF-8"?>
 <Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
   <Relationship Id="rId2" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/slide" Target="slides/slide1.xml"/>
-</Relationships>"#).unwrap();
+</Relationships>"#).expect("Operation failed");
 
         // Add slide with various shapes - some with txBody, some without
-        zip.start_file("ppt/slides/slide1.xml", options).unwrap();
+        zip.start_file("ppt/slides/slide1.xml", options)
+            .expect("Operation failed");
         zip.write_all(
             br#"<?xml version="1.0" encoding="UTF-8"?>
 <p:sld xmlns:p="http://schemas.openxmlformats.org/presentationml/2006/main"
@@ -453,18 +464,19 @@ async fn test_pptx_mixed_shapes_extraction() {
   </p:cSld>
 </p:sld>"#,
         )
-        .unwrap();
+        .expect("Operation failed");
 
         // Add empty rels
-        zip.start_file("ppt/slides/_rels/slide1.xml.rels", options).unwrap();
+        zip.start_file("ppt/slides/_rels/slide1.xml.rels", options)
+            .expect("Operation failed");
         zip.write_all(
             br#"<?xml version="1.0" encoding="UTF-8"?>
 <Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
 </Relationships>"#,
         )
-        .unwrap();
+        .expect("Operation failed");
 
-        zip.finish().unwrap();
+        zip.finish().expect("Operation failed");
     }
 
     let result = extract_file(
@@ -502,3 +514,284 @@ async fn test_pptx_mixed_shapes_extraction() {
         }
     }
 }
+
+/// Test that images extracted from PPTX have correct page numbers.
+///
+/// When a PPTX has multiple slides and an image on slide 1, the extracted image
+/// should have page_number=1 (not reversed).
+///
+/// GitHub Issue #329: Image on slide 1 of 2-slide PPTX reports page_number=2
+#[tokio::test]
+async fn test_pptx_image_page_numbers_not_reversed() {
+    // Create a PPTX with 2 slides, image on slide 1
+    let mut temp_file = NamedTempFile::with_suffix(".pptx").expect("Failed to create temp file");
+
+    // A minimal 1x1 red PNG image (valid PNG format)
+    let png_image: &[u8] = &[
+        0x89, 0x50, 0x4E, 0x47, 0x0D, 0x0A, 0x1A, 0x0A, // PNG signature
+        0x00, 0x00, 0x00, 0x0D, // IHDR chunk length
+        0x49, 0x48, 0x44, 0x52, // "IHDR"
+        0x00, 0x00, 0x00, 0x01, // width: 1
+        0x00, 0x00, 0x00, 0x01, // height: 1
+        0x08, 0x02, // bit depth: 8, color type: RGB
+        0x00, 0x00, 0x00, // compression, filter, interlace
+        0x90, 0x77, 0x53, 0xDE, // IHDR CRC
+        0x00, 0x00, 0x00, 0x0C, // IDAT chunk length
+        0x49, 0x44, 0x41, 0x54, // "IDAT"
+        0x08, 0xD7, 0x63, 0xF8, 0xCF, 0xC0, 0x00, 0x00, // compressed data
+        0x01, 0x01, 0x01, 0x00, // checksum
+        0x18, 0xDD, 0x8D, 0xB4, // IDAT CRC
+        0x00, 0x00, 0x00, 0x00, // IEND chunk length
+        0x49, 0x45, 0x4E, 0x44, // "IEND"
+        0xAE, 0x42, 0x60, 0x82, // IEND CRC
+    ];
+
+    {
+        let mut zip = ZipWriter::new(&mut temp_file);
+        let options: FileOptions<()> = FileOptions::default().compression_method(CompressionMethod::Stored);
+
+        // Add [Content_Types].xml
+        zip.start_file("[Content_Types].xml", options)
+            .expect("Operation failed");
+        zip.write_all(br#"<?xml version="1.0" encoding="UTF-8"?>
+<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">
+  <Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/>
+  <Default Extension="xml" ContentType="application/xml"/>
+  <Default Extension="png" ContentType="image/png"/>
+  <Override PartName="/ppt/presentation.xml" ContentType="application/vnd.openxmlformats-officedocument.presentationml.presentation.main+xml"/>
+  <Override PartName="/ppt/slides/slide1.xml" ContentType="application/vnd.openxmlformats-officedocument.presentationml.slide+xml"/>
+  <Override PartName="/ppt/slides/slide2.xml" ContentType="application/vnd.openxmlformats-officedocument.presentationml.slide+xml"/>
+</Types>"#).expect("Operation failed");
+
+        // Add _rels/.rels
+        zip.start_file("_rels/.rels", options).expect("Operation failed");
+        zip.write_all(br#"<?xml version="1.0" encoding="UTF-8"?>
+<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
+  <Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="ppt/presentation.xml"/>
+</Relationships>"#).expect("Operation failed");
+
+        // Add ppt/presentation.xml
+        zip.start_file("ppt/presentation.xml", options)
+            .expect("Operation failed");
+        zip.write_all(
+            br#"<?xml version="1.0" encoding="UTF-8"?>
+<p:presentation xmlns:p="http://schemas.openxmlformats.org/presentationml/2006/main"
+                xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships">
+  <p:sldIdLst>
+    <p:sldId id="256" r:id="rId2"/>
+    <p:sldId id="257" r:id="rId3"/>
+  </p:sldIdLst>
+</p:presentation>"#,
+        )
+        .expect("Operation failed");
+
+        // Add ppt/_rels/presentation.xml.rels
+        // BUG REPRODUCTION: Slides listed in REVERSE order in XML (slide2 before slide1)
+        // This is valid XML - PowerPoint doesn't guarantee order in rels files
+        // GitHub Issue #329: This causes page numbers to be reversed
+        zip.start_file("ppt/_rels/presentation.xml.rels", options)
+            .expect("Operation failed");
+        zip.write_all(br#"<?xml version="1.0" encoding="UTF-8"?>
+<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
+  <Relationship Id="rId3" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/slide" Target="slides/slide2.xml"/>
+  <Relationship Id="rId2" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/slide" Target="slides/slide1.xml"/>
+</Relationships>"#).expect("Operation failed");
+
+        // Add the image file
+        zip.start_file("ppt/media/image1.png", options)
+            .expect("Operation failed");
+        zip.write_all(png_image).expect("Operation failed");
+
+        // Add slide 1 WITH an image
+        zip.start_file("ppt/slides/slide1.xml", options)
+            .expect("Operation failed");
+        zip.write_all(
+            br#"<?xml version="1.0" encoding="UTF-8"?>
+<p:sld xmlns:p="http://schemas.openxmlformats.org/presentationml/2006/main"
+       xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main"
+       xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships">
+  <p:cSld>
+    <p:spTree>
+      <p:nvGrpSpPr><p:cNvPr id="1" name=""/><p:cNvGrpSpPr/><p:nvPr/></p:nvGrpSpPr>
+      <p:grpSpPr/>
+      <p:sp>
+        <p:nvSpPr><p:cNvPr id="2" name="Title"/><p:cNvSpPr/><p:nvPr/></p:nvSpPr>
+        <p:spPr/>
+        <p:txBody><a:bodyPr/><a:lstStyle/><a:p><a:r><a:t>Slide 1 - Has Image</a:t></a:r></a:p></p:txBody>
+      </p:sp>
+      <p:pic>
+        <p:nvPicPr>
+          <p:cNvPr id="3" name="Picture 1"/>
+          <p:cNvPicPr><a:picLocks noChangeAspect="1"/></p:cNvPicPr>
+          <p:nvPr/>
+        </p:nvPicPr>
+        <p:blipFill>
+          <a:blip r:embed="rId2"/>
+          <a:stretch><a:fillRect/></a:stretch>
+        </p:blipFill>
+        <p:spPr>
+          <a:xfrm><a:off x="0" y="0"/><a:ext cx="100000" cy="100000"/></a:xfrm>
+          <a:prstGeom prst="rect"><a:avLst/></a:prstGeom>
+        </p:spPr>
+      </p:pic>
+    </p:spTree>
+  </p:cSld>
+</p:sld>"#,
+        )
+        .expect("Operation failed");
+
+        // Add slide 1 relationships (points to the image)
+        zip.start_file("ppt/slides/_rels/slide1.xml.rels", options)
+            .expect("Operation failed");
+        zip.write_all(br#"<?xml version="1.0" encoding="UTF-8"?>
+<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
+  <Relationship Id="rId2" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/image" Target="../media/image1.png"/>
+</Relationships>"#).expect("Operation failed");
+
+        // Add slide 2 WITHOUT an image
+        zip.start_file("ppt/slides/slide2.xml", options)
+            .expect("Operation failed");
+        zip.write_all(
+            br#"<?xml version="1.0" encoding="UTF-8"?>
+<p:sld xmlns:p="http://schemas.openxmlformats.org/presentationml/2006/main"
+       xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main"
+       xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships">
+  <p:cSld>
+    <p:spTree>
+      <p:nvGrpSpPr><p:cNvPr id="1" name=""/><p:cNvGrpSpPr/><p:nvPr/></p:nvGrpSpPr>
+      <p:grpSpPr/>
+      <p:sp>
+        <p:nvSpPr><p:cNvPr id="2" name="Title"/><p:cNvSpPr/><p:nvPr/></p:nvSpPr>
+        <p:spPr/>
+        <p:txBody><a:bodyPr/><a:lstStyle/><a:p><a:r><a:t>Slide 2 - No Image</a:t></a:r></a:p></p:txBody>
+      </p:sp>
+    </p:spTree>
+  </p:cSld>
+</p:sld>"#,
+        )
+        .expect("Operation failed");
+
+        // Add empty slide 2 relationships
+        zip.start_file("ppt/slides/_rels/slide2.xml.rels", options)
+            .expect("Operation failed");
+        zip.write_all(
+            br#"<?xml version="1.0" encoding="UTF-8"?>
+<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
+</Relationships>"#,
+        )
+        .expect("Operation failed");
+
+        zip.finish().expect("Operation failed");
+    }
+
+    // Extract with images enabled
+    let config = ExtractionConfig {
+        images: Some(ImageExtractionConfig {
+            extract_images: true,
+            target_dpi: 300,
+            max_image_dimension: 4096,
+            auto_adjust_dpi: true,
+            min_dpi: 72,
+            max_dpi: 600,
+        }),
+        ..Default::default()
+    };
+
+    let result = extract_file(
+        temp_file.path(),
+        Some("application/vnd.openxmlformats-officedocument.presentationml.presentation"),
+        &config,
+    )
+    .await;
+
+    match result {
+        Ok(extraction) => {
+            // Verify text extraction works
+            assert!(extraction.content.contains("Slide 1"), "Should extract slide 1 text");
+            assert!(extraction.content.contains("Slide 2"), "Should extract slide 2 text");
+
+            // Verify we got an image
+            let images = extraction.images.as_ref().expect("Images should be present");
+            assert!(!images.is_empty(), "Should extract at least one image");
+
+            // THE CRITICAL TEST: Image on slide 1 should have page_number=1, NOT 2
+            let image = &images[0];
+            assert_eq!(
+                image.page_number,
+                Some(1),
+                "GitHub Issue #329: Image on slide 1 should have page_number=1, but got {:?}. \
+                 The page numbers are reversed!",
+                image.page_number
+            );
+
+            println!("✅ PPTX image page numbers are correct!");
+            println!("   Image on slide 1 has page_number={:?}", image.page_number);
+        }
+        Err(e) => {
+            panic!("PPTX extraction failed: {:?}", e);
+        }
+    }
+}
+
+/// Test with actual user-provided PPTX file from GitHub Issue #329.
+///
+/// The user's file has slides listed in reverse order in presentation.xml.rels,
+/// which caused images to have incorrect page numbers.
+#[tokio::test]
+async fn test_pptx_image_page_numbers_issue329_user_file() {
+    let workspace_root = std::path::Path::new(env!("CARGO_MANIFEST_DIR"))
+        .parent()
+        .expect("Operation failed")
+        .parent()
+        .expect("Operation failed");
+    let test_file = workspace_root.join("test_documents/presentations/pptx_reversed_slide_order_issue329.pptx");
+
+    if !test_file.exists() {
+        println!("Skipping test: User file not found at {:?}", test_file);
+        return;
+    }
+
+    // Extract with images enabled
+    let config = ExtractionConfig {
+        images: Some(ImageExtractionConfig {
+            extract_images: true,
+            target_dpi: 300,
+            max_image_dimension: 4096,
+            auto_adjust_dpi: true,
+            min_dpi: 72,
+            max_dpi: 600,
+        }),
+        ..Default::default()
+    };
+
+    let result = extract_file(&test_file, None, &config).await;
+
+    match result {
+        Ok(extraction) => {
+            // The user's file has an image on slide 1
+            let images = extraction.images.as_ref().expect("Images should be extracted");
+
+            if images.is_empty() {
+                println!("No images extracted from user file (may not have embedded images)");
+                return;
+            }
+
+            // All images should have page_number = 1 since they're on the first slide
+            for (idx, image) in images.iter().enumerate() {
+                assert_eq!(
+                    image.page_number,
+                    Some(1),
+                    "GitHub Issue #329: Image {} should have page_number=1, but got {:?}",
+                    idx,
+                    image.page_number
+                );
+            }
+
+            println!("✅ User file from Issue #329 - image page numbers correct!");
+            println!("   Found {} images, all with page_number=1", images.len());
+        }
+        Err(e) => {
+            panic!("Failed to extract user file: {:?}", e);
+        }
+    }
+}

data/vendor/kreuzberg/tests/registry_integration_tests.rs

@@ -184,9 +184,9 @@ fn test_register_multiple_validators_succeeds() {
         should_fail: true,
     });
 
-    registry.register(v1).unwrap();
-    registry.register(v2).unwrap();
-    registry.register(v3).unwrap();
+    registry.register(v1).expect("Operation failed");
+    registry.register(v2).expect("Operation failed");
+    registry.register(v3).expect("Operation failed");
 
     let list = registry.list();
     assert_eq!(list.len(), 3, "Should have three validators");
@@ -205,7 +205,7 @@ fn test_validator_unregistration_succeeds() {
         should_fail: false,
     });
 
-    registry.register(validator).unwrap();
+    registry.register(validator).expect("Operation failed");
     assert_eq!(registry.list().len(), 1);
 
     let result = registry.remove("temp-validator");
@@ -298,8 +298,8 @@ fn test_clear_validators_succeeds() {
         should_fail: false,
     });
 
-    registry.register(v1).unwrap();
-    registry.register(v2).unwrap();
+    registry.register(v1).expect("Operation failed");
+    registry.register(v2).expect("Operation failed");
     assert_eq!(registry.list().len(), 2);
 
     let result = registry.shutdown_all();
@@ -355,9 +355,9 @@ fn test_get_all_validators_respects_priority() {
         priority: 100,
     });
 
-    registry.register(medium).unwrap();
-    registry.register(low).unwrap();
-    registry.register(high).unwrap();
+    registry.register(medium).expect("Operation failed");
+    registry.register(low).expect("Operation failed");
+    registry.register(high).expect("Operation failed");
 
     let all = registry.get_all();
     assert_eq!(all.len(), 3, "Should have three validators");
@@ -397,11 +397,11 @@ fn test_get_extractor_by_mime_type_succeeds() {
         priority: 50,
     });
 
-    registry.register(extractor).unwrap();
+    registry.register(extractor).expect("Operation failed");
 
     let result = registry.get("application/pdf");
     assert!(result.is_ok(), "Should find extractor for PDF");
-    assert_eq!(result.unwrap().name(), "pdf-extractor");
+    assert_eq!(result.expect("Operation failed").name(), "pdf-extractor");
 }
 
 /// Test extractor not found for unsupported MIME type.
@@ -437,10 +437,10 @@ fn test_extractor_priority_selection() {
         priority: 100,
     });
 
-    registry.register(low_priority).unwrap();
-    registry.register(high_priority).unwrap();
+    registry.register(low_priority).expect("Operation failed");
+    registry.register(high_priority).expect("Operation failed");
 
-    let result = registry.get("text/plain").unwrap();
+    let result = registry.get("text/plain").expect("Value not found");
     assert_eq!(
         result.name(),
         "high-priority-extractor",
@@ -459,15 +459,15 @@ fn test_extractor_wildcard_mime_matching() {
         priority: 50,
     });
 
-    registry.register(extractor).unwrap();
+    registry.register(extractor).expect("Operation failed");
 
     let result = registry.get("text/plain");
     assert!(result.is_ok(), "Should match text/plain with text/*");
-    assert_eq!(result.unwrap().name(), "text-extractor");
+    assert_eq!(result.expect("Operation failed").name(), "text-extractor");
 
     let result = registry.get("text/html");
     assert!(result.is_ok(), "Should match text/html with text/*");
-    assert_eq!(result.unwrap().name(), "text-extractor");
+    assert_eq!(result.expect("Operation failed").name(), "text-extractor");
 
     let result = registry.get("application/pdf");
     assert!(result.is_err(), "Should not match application/pdf with text/*");
@@ -484,7 +484,7 @@ fn test_extractor_unregistration_succeeds() {
         priority: 50,
     });
 
-    registry.register(extractor).unwrap();
+    registry.register(extractor).expect("Operation failed");
     assert_eq!(registry.list().len(), 1);
 
     let result = registry.remove("temp-extractor");
@@ -506,17 +506,20 @@ fn test_extractor_multiple_mime_types() {
         priority: 50,
     });
 
-    registry.register(extractor).unwrap();
+    registry.register(extractor).expect("Operation failed");
 
     assert!(registry.get("application/pdf").is_ok());
     assert!(registry.get("application/vnd.ms-excel").is_ok());
     assert!(registry.get("text/csv").is_ok());
 
     assert_eq!(
-        registry.get("application/pdf").unwrap().name(),
+        registry.get("application/pdf").expect("Value not found").name(),
+        "multi-format-extractor"
+    );
+    assert_eq!(
+        registry.get("text/csv").expect("Value not found").name(),
         "multi-format-extractor"
     );
-    assert_eq!(registry.get("text/csv").unwrap().name(), "multi-format-extractor");
 }
 
 /// Test clearing all extractors.
@@ -535,8 +538,8 @@ fn test_clear_extractors_succeeds() {
         priority: 50,
     });
 
-    registry.register(e1).unwrap();
-    registry.register(e2).unwrap();
+    registry.register(e1).expect("Operation failed");
+    registry.register(e2).expect("Operation failed");
     assert_eq!(registry.list().len(), 2);
 
     let result = registry.shutdown_all();

data/vendor/kreuzberg/tests/rst_extractor_tests.rs

@@ -686,7 +686,7 @@ async fn test_rst_extraction_no_errors() {
         result.err()
     );
 
-    let extraction = result.unwrap();
+    let extraction = result.expect("Operation failed");
 
     assert!(!extraction.content.is_empty(), "Extracted content should not be empty");