kreuzberg 4.1.2 → 4.2.0

data/vendor/kreuzberg/tests/docbook_extractor_tests.rs

@@ -11,9 +11,9 @@ fn test_file_path(filename: &str) -> PathBuf {
     let manifest_dir = env!("CARGO_MANIFEST_DIR");
     PathBuf::from(manifest_dir)
         .parent()
-        .unwrap()
+        .expect("Operation failed")
         .parent()
-        .unwrap()
+        .expect("Operation failed")
         .join("test_documents")
         .join("docbook")
         .join(filename)
@@ -72,7 +72,7 @@ async fn test_docbook4_chapter_extraction() {
     let result = extract_docbook4_file("docbook-chapter.docbook").await;
     assert!(result.is_ok(), "Failed to extract DocBook 4 chapter");
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     assert!(!result.content.is_empty(), "Content should not be empty");
     assert!(
         result.content.contains("Test Chapter"),
@@ -89,7 +89,7 @@ async fn test_docbook5_reader_extraction() {
     let result = extract_docbook5_file("docbook-reader.docbook").await;
     assert!(result.is_ok(), "Failed to extract DocBook 5 file");
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     assert!(!result.content.is_empty(), "Content should not be empty");
     assert!(
         result.content.contains("Pandoc Test Suite"),
@@ -102,7 +102,7 @@ async fn test_docbook_xref_extraction() {
     let result = extract_docbook4_file("docbook-xref.docbook").await;
     assert!(result.is_ok(), "Failed to extract DocBook with xref elements");
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     assert!(!result.content.is_empty(), "Content should not be empty");
     assert!(
         result.content.contains("An Example Book"),
@@ -119,7 +119,7 @@ async fn test_docbook_tables_extraction() {
     let result = extract_docbook4_file("tables.docbook4").await;
     assert!(result.is_ok(), "Failed to extract DocBook with tables");
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     assert!(!result.content.is_empty(), "Content should not be empty");
     assert!(!result.tables.is_empty(), "Should extract tables from DocBook");
 }
@@ -129,7 +129,7 @@ async fn test_docbook5_tables_extraction() {
     let result = extract_docbook5_file("tables.docbook5").await;
     assert!(result.is_ok(), "Failed to extract DocBook 5 with tables");
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     assert!(!result.content.is_empty(), "Content should not be empty");
     assert!(!result.tables.is_empty(), "Should extract tables from DocBook 5");
 }
@@ -139,7 +139,7 @@ async fn test_docbook_metadata_extraction() {
     let result = extract_docbook5_file("docbook-reader.docbook").await;
     assert!(result.is_ok());
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     assert!(!result.content.is_empty());
 }
 
@@ -148,7 +148,7 @@ async fn test_docbook_section_hierarchy() {
     let result = extract_docbook4_file("docbook-chapter.docbook").await;
     assert!(result.is_ok());
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     let content = &result.content;
 
     assert!(content.contains("Like a Sect1"));
@@ -162,7 +162,7 @@ async fn test_docbook_paragraph_extraction() {
     let result = extract_docbook4_file("docbook-chapter.docbook").await;
     assert!(result.is_ok());
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     assert!(
         result.content.contains("This chapter uses recursive sections"),
         "Should extract paragraph content"
@@ -183,7 +183,7 @@ async fn test_docbook_paragraph_content() {
     let result = extract_docbook_bytes(docbook.as_bytes(), "application/docbook+xml").await;
     assert!(result.is_ok());
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     assert!(result.content.contains("Test Article"));
     assert!(result.content.contains("This is a test paragraph"));
     assert!(result.content.contains("another paragraph"));
@@ -205,7 +205,7 @@ def hello():
     let result = extract_docbook_bytes(docbook.as_bytes(), "application/docbook+xml").await;
     assert!(result.is_ok());
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     assert!(result.content.contains("def hello"));
     assert!(result.content.contains("print"));
 }
@@ -229,7 +229,7 @@ async fn test_docbook_mixed_content() {
     let result = extract_docbook_bytes(docbook.as_bytes(), "application/docbook+xml").await;
     assert!(result.is_ok());
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     assert!(result.content.contains("Test Book"));
     assert!(result.content.contains("Chapter 1"));
     assert!(result.content.contains("Section 1.1"));
@@ -259,7 +259,7 @@ async fn test_docbook_namespaced_5x_parsing() {
     let result = extract_docbook_bytes(docbook5.as_bytes(), "application/docbook+xml").await;
     assert!(result.is_ok());
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     assert!(result.content.contains("DocBook 5 Article"));
     assert!(result.content.contains("Welcome to DocBook 5"));
 }
@@ -277,7 +277,7 @@ async fn test_docbook_link_handling() {
     let result = extract_docbook_bytes(docbook.as_bytes(), "application/docbook+xml").await;
     assert!(result.is_ok());
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     assert!(result.content.contains("example"));
 }
 
@@ -316,7 +316,7 @@ async fn test_docbook_empty_sections() {
     let result = extract_docbook_bytes(docbook.as_bytes(), "application/docbook+xml").await;
     assert!(result.is_ok());
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     assert!(result.content.contains("Empty Section"));
     assert!(result.content.contains("Section with Content"));
     assert!(result.content.contains("Content here"));
@@ -345,7 +345,7 @@ async fn test_docbook_itemized_list() {
     let result = extract_docbook_bytes(docbook.as_bytes(), "application/docbook+xml").await;
     assert!(result.is_ok());
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     assert!(result.content.contains("First item"));
     assert!(result.content.contains("Second item"));
     assert!(result.content.contains("Third item"));
@@ -375,7 +375,7 @@ async fn test_docbook_ordered_list() {
     let result = extract_docbook_bytes(docbook.as_bytes(), "application/docbook+xml").await;
     assert!(result.is_ok());
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     assert!(result.content.contains("First step"));
     assert!(result.content.contains("Second step"));
     assert!(result.content.contains("Third step"));
@@ -397,7 +397,7 @@ async fn test_docbook_blockquote() {
     let result = extract_docbook_bytes(docbook.as_bytes(), "application/docbook+xml").await;
     assert!(result.is_ok());
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     assert!(result.content.contains("quoted passage"));
     assert!(result.content.contains("> "), "Should contain blockquote marker");
 }
@@ -418,7 +418,7 @@ async fn test_docbook_figure() {
     let result = extract_docbook_bytes(docbook.as_bytes(), "application/docbook+xml").await;
     assert!(result.is_ok());
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     assert!(result.content.contains("Figure"));
 }
 
@@ -435,7 +435,7 @@ async fn test_docbook_footnote() {
     let result = extract_docbook_bytes(docbook.as_bytes(), "application/docbook+xml").await;
     assert!(result.is_ok());
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     assert!(result.content.contains("text with a footnote"));
     assert!(result.content.contains("footnote content"));
 }
@@ -465,7 +465,7 @@ code example
     let result = extract_docbook_bytes(docbook.as_bytes(), "application/docbook+xml").await;
     assert!(result.is_ok());
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     assert!(result.content.contains("Introduction paragraph"));
     assert!(result.content.contains("List item 1"));
     assert!(result.content.contains("List item 2"));
@@ -493,7 +493,7 @@ async fn test_docbook_namespaced_lists() {
     let result = extract_docbook_bytes(docbook5.as_bytes(), "application/docbook+xml").await;
     assert!(result.is_ok());
 
-    let result = result.unwrap();
+    let result = result.expect("Operation failed");
     assert!(result.content.contains("Namespaced item 1"));
     assert!(result.content.contains("Namespaced item 2"));
     assert!(result.content.contains("- "));

data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs

@@ -8,9 +8,9 @@ use kreuzberg::{ExtractionConfig, extract_file};
 async fn test_docx_full_metadata_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/documents/word_sample.docx");
 
     if !test_file.exists() {
@@ -91,9 +91,9 @@ async fn test_docx_full_metadata_extraction() {
 async fn test_docx_minimal_metadata_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/documents/lorem_ipsum.docx");
 
     if !test_file.exists() {
@@ -143,25 +143,26 @@ async fn test_docx_keywords_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="/word/document.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/>
   <Override PartName="/docProps/core.xml" ContentType="application/vnd.openxmlformats-package.core-properties+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="word/document.xml"/>
   <Relationship Id="rId2" Type="http://schemas.openxmlformats.org/package/2006/relationships/metadata/core-properties" Target="docProps/core.xml"/>
-</Relationships>"#).unwrap();
+</Relationships>"#).expect("Operation failed");
 
         // Add word/document.xml with simple content
-        zip.start_file("word/document.xml", options).unwrap();
+        zip.start_file("word/document.xml", options).expect("Operation failed");
         zip.write_all(
             br#"<?xml version="1.0" encoding="UTF-8"?>
 <w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
@@ -174,10 +175,10 @@ async fn test_docx_keywords_extraction() {
   </w:body>
 </w:document>"#,
         )
-        .unwrap();
+        .expect("Operation failed");
 
         // Add docProps/core.xml with keywords (comma-separated string)
-        zip.start_file("docProps/core.xml", options).unwrap();
+        zip.start_file("docProps/core.xml", options).expect("Operation failed");
         zip.write_all(
             br#"<?xml version="1.0" encoding="UTF-8"?>
 <cp:coreProperties xmlns:cp="http://schemas.openxmlformats.org/package/2006/metadata/core-properties"
@@ -189,9 +190,9 @@ async fn test_docx_keywords_extraction() {
   <dc:subject>Testing keyword extraction</dc:subject>
 </cp:coreProperties>"#,
         )
-        .unwrap();
+        .expect("Operation failed");
 
-        zip.finish().unwrap();
+        zip.finish().expect("Operation failed");
     }
 
     // Extract the DOCX file
@@ -216,7 +217,7 @@ async fn test_docx_keywords_extraction() {
         "Keywords should be present in metadata.keywords"
     );
 
-    let keywords = result.metadata.keywords.as_ref().unwrap();
+    let keywords = result.metadata.keywords.as_ref().expect("Operation failed");
     assert_eq!(
         keywords.len(),
         5,

data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs

@@ -10,9 +10,9 @@ use kreuzberg::plugins::DocumentExtractor;
 async fn test_docx_kreuzberg_vs_pandoc_comparison() {
     let docx_path = std::path::Path::new(env!("CARGO_MANIFEST_DIR"))
         .parent()
-        .unwrap()
+        .expect("Operation failed")
         .parent()
-        .unwrap()
+        .expect("Operation failed")
         .join("test_documents/documents/word_sample.docx");
 
     if !docx_path.exists() {
@@ -319,9 +319,9 @@ Here are some interesting things a respectful duck could eat:
 async fn test_docx_lorem_ipsum_comparison() {
     let docx_path = std::path::Path::new(env!("CARGO_MANIFEST_DIR"))
         .parent()
-        .unwrap()
+        .expect("Operation failed")
         .parent()
-        .unwrap()
+        .expect("Operation failed")
         .join("test_documents/documents/lorem_ipsum.docx");
 
     if !docx_path.exists() {

data/vendor/kreuzberg/tests/email_integration.rs

@@ -32,7 +32,7 @@ This is the email body content.";
     assert_eq!(result.metadata.subject, Some("Test Email Subject".to_string()));
 
     assert!(result.metadata.format.is_some());
-    let email_meta = match result.metadata.format.as_ref().unwrap() {
+    let email_meta = match result.metadata.format.as_ref().expect("Operation failed") {
         kreuzberg::FormatMetadata::Email(meta) => meta,
         _ => panic!("Expected Email metadata"),
     };
@@ -44,7 +44,7 @@ This is the email body content.";
     assert!(email_meta.bcc_emails.is_empty(), "BCC should be empty");
 
     assert!(email_meta.message_id.is_some());
-    let msg_id = email_meta.message_id.clone().unwrap();
+    let msg_id = email_meta.message_id.clone().expect("Operation failed");
     assert!(
         msg_id.contains("unique123@example.com"),
         "Message ID should contain unique123@example.com"
@@ -86,7 +86,7 @@ Attachment content here.\r\n\
         .expect("Should extract EML with attachment");
 
     assert!(result.metadata.format.is_some());
-    let email_meta = match result.metadata.format.as_ref().unwrap() {
+    let email_meta = match result.metadata.format.as_ref().expect("Operation failed") {
         kreuzberg::FormatMetadata::Email(meta) => meta,
         _ => panic!("Expected Email metadata"),
     };
@@ -127,7 +127,7 @@ Content-Type: text/html; charset=utf-8\r\n\
     assert!(result.content.contains("HTML Heading") || result.content.contains("bold"));
 
     assert!(result.metadata.format.is_some());
-    let email_meta = match result.metadata.format.as_ref().unwrap() {
+    let email_meta = match result.metadata.format.as_ref().expect("Operation failed") {
         kreuzberg::FormatMetadata::Email(meta) => meta,
         _ => panic!("Expected Email metadata"),
     };
@@ -159,7 +159,7 @@ And preserves formatting.";
     assert!(result.content.contains("preserves formatting"));
 
     assert!(result.metadata.format.is_some());
-    let email_meta = match result.metadata.format.as_ref().unwrap() {
+    let email_meta = match result.metadata.format.as_ref().expect("Operation failed") {
         kreuzberg::FormatMetadata::Email(meta) => meta,
         _ => panic!("Expected Email metadata"),
     };
@@ -198,7 +198,7 @@ Content-Type: text/html\r\n\
     );
 
     assert!(result.metadata.format.is_some());
-    let email_meta = match result.metadata.format.as_ref().unwrap() {
+    let email_meta = match result.metadata.format.as_ref().expect("Operation failed") {
         kreuzberg::FormatMetadata::Email(meta) => meta,
         _ => panic!("Expected Email metadata"),
     };
@@ -290,7 +290,7 @@ Email to multiple recipients.";
         .expect("Should extract email with multiple recipients");
 
     assert!(result.metadata.format.is_some());
-    let email_meta = match result.metadata.format.as_ref().unwrap() {
+    let email_meta = match result.metadata.format.as_ref().expect("Operation failed") {
         kreuzberg::FormatMetadata::Email(meta) => meta,
         _ => panic!("Expected Email metadata"),
     };

data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs

@@ -17,9 +17,9 @@ use std::path::PathBuf;
 fn get_test_epub_path(filename: &str) -> PathBuf {
     let workspace_root = std::path::Path::new(env!("CARGO_MANIFEST_DIR"))
         .parent()
-        .unwrap()
+        .expect("Operation failed")
         .parent()
-        .unwrap();
+        .expect("Operation failed");
     workspace_root.join(format!("test_documents/epub/{}", filename))
 }
 

data/vendor/kreuzberg/tests/error_handling.rs

@@ -187,7 +187,7 @@ async fn test_very_large_file() {
     let result = extract_bytes(large_bytes, "text/plain", &config).await;
 
     assert!(result.is_ok(), "Large file should be processed successfully");
-    let extraction = result.unwrap();
+    let extraction = result.expect("Operation failed");
 
     assert!(!extraction.content.is_empty(), "Large file content should not be empty");
     assert!(extraction.content.len() > 1_000_000, "Content should be large");
@@ -213,12 +213,14 @@ async fn test_unicode_filenames() {
     let config = ExtractionConfig::default();
 
     let mut temp_file = NamedTempFile::new().expect("Should create temp file");
-    temp_file.write_all(b"Test content with Unicode filename.").unwrap();
+    temp_file
+        .write_all(b"Test content with Unicode filename.")
+        .expect("Operation failed");
 
     let result = extract_file(temp_file.path(), Some("text/plain"), &config).await;
 
     assert!(result.is_ok(), "Unicode filename should be handled");
-    let extraction = result.unwrap();
+    let extraction = result.expect("Operation failed");
 
     assert!(
         extraction.content.contains("Test content"),
@@ -249,7 +251,7 @@ Math symbols: ∑ ∫ √ ≈ ∞";
     let result = extract_bytes(special_text.as_bytes(), "text/plain", &config).await;
 
     assert!(result.is_ok(), "Special characters should be handled");
-    let extraction = result.unwrap();
+    let extraction = result.expect("Operation failed");
 
     assert!(!extraction.content.is_empty(), "Content should not be empty");
     assert!(extraction.content.len() > 10, "Should have substantial content");
@@ -319,17 +321,17 @@ async fn test_permission_denied() {
     let config = ExtractionConfig::default();
 
     let mut temp_file = NamedTempFile::new().expect("Should create temp file");
-    temp_file.write_all(b"Test content").unwrap();
+    temp_file.write_all(b"Test content").expect("Operation failed");
 
-    let mut perms = fs::metadata(temp_file.path()).unwrap().permissions();
+    let mut perms = fs::metadata(temp_file.path()).expect("Operation failed").permissions();
     perms.set_mode(0o000);
-    fs::set_permissions(temp_file.path(), perms).unwrap();
+    fs::set_permissions(temp_file.path(), perms).expect("Operation failed");
 
     let result = extract_file(temp_file.path(), Some("text/plain"), &config).await;
 
-    let mut perms = fs::metadata(temp_file.path()).unwrap().permissions();
+    let mut perms = fs::metadata(temp_file.path()).expect("Operation failed").permissions();
     perms.set_mode(0o644);
-    fs::set_permissions(temp_file.path(), perms).unwrap();
+    fs::set_permissions(temp_file.path(), perms).expect("Operation failed");
 
     assert!(result.is_err(), "Permission denied should return error");
 }
@@ -356,7 +358,7 @@ async fn test_null_bytes_in_content() {
     let result = extract_bytes(data_with_nulls, "text/plain", &config).await;
 
     assert!(result.is_ok(), "Null bytes should be handled");
-    let extraction = result.unwrap();
+    let extraction = result.expect("Operation failed");
 
     assert!(!extraction.content.is_empty(), "Content should not be empty");
     assert!(
@@ -388,7 +390,7 @@ async fn test_concurrent_extractions() {
         let result = handle.await.expect("Task should complete");
         assert!(result.is_ok(), "Concurrent extraction should succeed");
 
-        let extraction = result.unwrap();
+        let extraction = result.expect("Operation failed");
         assert!(
             extraction.content.contains("Concurrent extraction"),
             "Content should be extracted correctly"

data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs

@@ -9,9 +9,9 @@ fn test_file_path(filename: &str) -> PathBuf {
     let manifest_dir = env!("CARGO_MANIFEST_DIR");
     PathBuf::from(manifest_dir)
         .parent()
-        .unwrap()
+        .expect("Operation failed")
         .parent()
-        .unwrap()
+        .expect("Operation failed")
         .join("test_documents")
         .join("fictionbook")
         .join(filename)

data/vendor/kreuzberg/tests/html_table_test.rs

@@ -37,7 +37,7 @@ mod html_table_tests {
         let result = convert_html_to_markdown(html, None, None);
         assert!(result.is_ok(), "HTML to markdown conversion should succeed");
 
-        let markdown = result.unwrap();
+        let markdown = result.expect("Operation failed");
 
         println!("=== Basic Table Test ===");
         println!("Input HTML:\n{}", html);
@@ -79,7 +79,7 @@ mod html_table_tests {
         let result = convert_html_to_markdown(html, None, None);
         assert!(result.is_ok(), "Should convert to markdown");
 
-        let markdown = result.unwrap();
+        let markdown = result.expect("Operation failed");
 
         println!("=== Table Format Test ===");
         println!("Input HTML:\n{}", html);
@@ -143,7 +143,7 @@ mod html_table_tests {
         let result = convert_html_to_markdown(html, None, None);
         assert!(result.is_ok(), "Should convert complex table");
 
-        let markdown = result.unwrap();
+        let markdown = result.expect("Operation failed");
 
         println!("=== Complex Table Test ===");
         println!("Input HTML:\n{}", html);
@@ -194,7 +194,7 @@ mod html_table_tests {
         let result = convert_html_to_markdown(html, None, None);
         assert!(result.is_ok(), "Should handle merged cell table");
 
-        let markdown = result.unwrap();
+        let markdown = result.expect("Operation failed");
 
         println!("=== Merged Cells Test ===");
         println!("Input HTML:\n{}", html);
@@ -248,7 +248,7 @@ mod html_table_tests {
         let result = convert_html_to_markdown(html, None, None);
         assert!(result.is_ok(), "Should handle multiple tables");
 
-        let markdown = result.unwrap();
+        let markdown = result.expect("Operation failed");
 
         println!("=== Multiple Tables Test ===");
         println!("Input HTML:\n{}", html);
@@ -303,7 +303,7 @@ mod html_table_tests {
         let result = convert_html_to_markdown(html, None, None);
         assert!(result.is_ok(), "Should handle mixed header cells");
 
-        let markdown = result.unwrap();
+        let markdown = result.expect("Operation failed");
 
         println!("=== Mixed Header Cells Test ===");
         println!("Input HTML:\n{}", html);
@@ -349,7 +349,7 @@ mod html_table_tests {
         let result = convert_html_to_markdown(html, None, None);
         assert!(result.is_ok(), "Should handle table with caption");
 
-        let markdown = result.unwrap();
+        let markdown = result.expect("Operation failed");
 
         println!("=== Table with Caption Test ===");
         println!("Input HTML:\n{}", html);
@@ -385,7 +385,7 @@ mod html_table_tests {
         let result = convert_html_to_markdown(html, None, None);
         assert!(result.is_ok(), "Should handle flat table");
 
-        let markdown = result.unwrap();
+        let markdown = result.expect("Operation failed");
 
         println!("=== Simple Flat Table Test ===");
         println!("Input HTML:\n{}", html);
@@ -421,7 +421,7 @@ mod html_table_tests {
         let result = convert_html_to_markdown(html, None, None);
         assert!(result.is_ok(), "Should handle empty cells");
 
-        let markdown = result.unwrap();
+        let markdown = result.expect("Operation failed");
 
         println!("=== Empty Cells Test ===");
         println!("Input HTML:\n{}", html);
@@ -459,7 +459,7 @@ mod html_table_tests {
         let result = convert_html_to_markdown(html, None, None);
         assert!(result.is_ok(), "Should handle numeric table");
 
-        let markdown = result.unwrap();
+        let markdown = result.expect("Operation failed");
 
         println!("=== Numeric Data Test ===");
         println!("Input HTML:\n{}", html);
@@ -502,7 +502,7 @@ mod html_table_tests {
         let result = convert_html_to_markdown(html, None, None);
         assert!(result.is_ok(), "Should handle unicode characters");
 
-        let markdown = result.unwrap();
+        let markdown = result.expect("Operation failed");
 
         println!("=== Special Characters Test ===");
         println!("Input HTML:\n{}", html);

data/vendor/kreuzberg/tests/instrumentation_test.rs

@@ -17,7 +17,10 @@ struct SpanCollector {
 
 impl<S: Subscriber + for<'a> LookupSpan<'a>> Layer<S> for SpanCollector {
     fn on_new_span(&self, attrs: &Attributes<'_>, _id: &Id, _ctx: Context<'_, S>) {
-        self.spans.lock().unwrap().push(attrs.metadata().name().to_string());
+        self.spans
+            .lock()
+            .expect("Operation failed")
+            .push(attrs.metadata().name().to_string());
     }
 }
 
@@ -32,21 +35,23 @@ async fn test_cache_instrumentation() {
     let subscriber = tracing_subscriber::registry().with(collector);
     let _guard = tracing::subscriber::set_default(subscriber);
 
-    let temp_dir = tempdir().unwrap();
+    let temp_dir = tempdir().expect("Operation failed");
     let cache = GenericCache::new(
         "test".to_string(),
-        Some(temp_dir.path().to_str().unwrap().to_string()),
+        Some(temp_dir.path().to_str().expect("Operation failed").to_string()),
         30.0,
         500.0,
         1000.0,
     )
-    .unwrap();
+    .expect("Operation failed");
 
-    cache.set("test_key", b"test data".to_vec(), None).unwrap();
+    cache
+        .set("test_key", b"test data".to_vec(), None)
+        .expect("Operation failed");
 
-    let _ = cache.get("test_key", None).unwrap();
+    let _ = cache.get("test_key", None).expect("Value not found");
 
-    let span_names = spans.lock().unwrap();
+    let span_names = spans.lock().expect("Operation failed");
     assert!(span_names.contains(&"set".to_string()), "Expected 'set' span");
     assert!(span_names.contains(&"get".to_string()), "Expected 'get' span");
 }
@@ -64,13 +69,13 @@ async fn test_ocr_instrumentation() {
     let subscriber = tracing_subscriber::registry().with(collector);
     let _guard = tracing::subscriber::set_default(subscriber);
 
-    let temp_dir = tempdir().unwrap();
-    let processor = OcrProcessor::new(Some(temp_dir.path().to_path_buf())).unwrap();
+    let temp_dir = tempdir().expect("Operation failed");
+    let processor = OcrProcessor::new(Some(temp_dir.path().to_path_buf())).expect("Operation failed");
 
     let mut test_image = Vec::new();
     let img = image::ImageBuffer::from_fn(1, 1, |_, _| image::Rgb([255u8, 255u8, 255u8]));
     img.write_to(&mut std::io::Cursor::new(&mut test_image), image::ImageFormat::Png)
-        .unwrap();
+        .expect("Operation failed");
 
     let config = TesseractConfig {
         output_format: "text".to_string(),
@@ -80,7 +85,7 @@ async fn test_ocr_instrumentation() {
 
     let _ = processor.process_image(&test_image, &config);
 
-    let span_names = spans.lock().unwrap();
+    let span_names = spans.lock().expect("Operation failed");
     assert!(
         span_names.contains(&"process_image".to_string()),
         "Expected 'process_image' span"
@@ -101,7 +106,7 @@ async fn test_registry_instrumentation() {
 
     let _ = registry.get("application/pdf");
 
-    let span_names = spans.lock().unwrap();
+    let span_names = spans.lock().expect("Operation failed");
     assert!(
         span_names.contains(&"get".to_string()),
         "Expected 'get' span from registry"
@@ -125,7 +130,7 @@ async fn test_span_hierarchy() {
 
     let _ = extract_bytes(test_content, "text/plain", &config).await;
 
-    let span_names = spans.lock().unwrap();
+    let span_names = spans.lock().expect("Operation failed");
     assert!(
         span_names.contains(&"extract_bytes".to_string()),
         "Expected 'extract_bytes' span"