kreuzberg 4.0.0.pre.rc.29 → 4.0.0.rc1

data/vendor/kreuzberg/tests/email_integration.rs

@@ -3,8 +3,6 @@
 //! Tests for .eml (RFC822) email extraction.
 //! Validates metadata extraction, content extraction, HTML/plain text handling, and attachments.
 
-#![cfg(feature = "email")]
-
 use kreuzberg::core::config::ExtractionConfig;
 use kreuzberg::core::extractor::extract_bytes;
 
@@ -52,7 +50,7 @@ This is the email body content.";
 
     assert!(email_meta.attachments.is_empty(), "Should have no attachments");
 
-    assert!(result.metadata.created_at.is_some());
+    assert!(result.metadata.date.is_some());
 
     assert!(result.content.contains("Subject: Test Email Subject"));
     assert!(result.content.contains("From: sender@example.com"));

data/vendor/kreuzberg/tests/error_handling.rs

@@ -12,7 +12,6 @@ mod helpers;
 
 /// Test truncated PDF - incomplete PDF file.
 #[tokio::test]
-#[cfg(feature = "pdf")]
 async fn test_truncated_pdf() {
     let config = ExtractionConfig::default();
 
@@ -32,7 +31,6 @@ async fn test_truncated_pdf() {
 
 /// Test corrupted ZIP - malformed archive.
 #[tokio::test]
-#[cfg(feature = "archives")]
 async fn test_corrupted_zip() {
     let config = ExtractionConfig::default();
 
@@ -52,7 +50,6 @@ async fn test_corrupted_zip() {
 
 /// Test invalid XML - bad XML syntax.
 #[tokio::test]
-#[cfg(feature = "xml")]
 async fn test_invalid_xml() {
     let config = ExtractionConfig::default();
 
@@ -83,7 +80,6 @@ async fn test_invalid_xml() {
 
 /// Test corrupted image - invalid image data.
 #[tokio::test]
-#[cfg(feature = "ocr")]
 async fn test_corrupted_image() {
     let config = ExtractionConfig::default();
 
@@ -116,28 +112,27 @@ async fn test_empty_file() {
 
     let empty_data = b"";
 
+    let result_pdf = extract_bytes(empty_data, "application/pdf", &config).await;
     let result_text = extract_bytes(empty_data, "text/plain", &config).await;
-    #[cfg(feature = "pdf")]
-    {
-        let result_pdf = extract_bytes(empty_data, "application/pdf", &config).await;
-        match result_pdf {
-            Ok(extraction) => {
-                assert!(
-                    extraction.content.is_empty(),
-                    "Empty PDF should have empty content if it succeeds"
-                );
-                assert!(extraction.chunks.is_none(), "Chunks should be None");
-            }
-            Err(error) => {
-                assert!(
-                    matches!(
-                        error,
-                        kreuzberg::KreuzbergError::Parsing { .. } | kreuzberg::KreuzbergError::Validation { .. }
-                    ),
-                    "Empty PDF should produce Parsing or Validation error, got: {:?}",
-                    error
-                );
-            }
+    let result_xml = extract_bytes(empty_data, "application/xml", &config).await;
+
+    match result_pdf {
+        Ok(extraction) => {
+            assert!(
+                extraction.content.is_empty(),
+                "Empty PDF should have empty content if it succeeds"
+            );
+            assert!(extraction.chunks.is_none(), "Chunks should be None");
+        }
+        Err(error) => {
+            assert!(
+                matches!(
+                    error,
+                    kreuzberg::KreuzbergError::Parsing { .. } | kreuzberg::KreuzbergError::Validation { .. }
+                ),
+                "Empty PDF should produce Parsing or Validation error, got: {:?}",
+                error
+            );
         }
     }
 
@@ -154,24 +149,20 @@ async fn test_empty_file() {
         }
     }
 
-    #[cfg(feature = "xml")]
-    {
-        let result_xml = extract_bytes(empty_data, "application/xml", &config).await;
-        match result_xml {
-            Ok(extraction) => {
-                assert!(
-                    extraction.content.is_empty(),
-                    "Empty XML should have empty content if it succeeds"
-                );
-                assert!(extraction.chunks.is_none(), "Chunks should be None");
-            }
-            Err(error) => {
-                assert!(
-                    matches!(error, kreuzberg::KreuzbergError::Parsing { .. }),
-                    "Empty XML error should be Parsing type, got: {:?}",
-                    error
-                );
-            }
+    match result_xml {
+        Ok(extraction) => {
+            assert!(
+                extraction.content.is_empty(),
+                "Empty XML should have empty content if it succeeds"
+            );
+            assert!(extraction.chunks.is_none(), "Chunks should be None");
+        }
+        Err(error) => {
+            assert!(
+                matches!(error, kreuzberg::KreuzbergError::Parsing { .. }),
+                "Empty XML error should be Parsing type, got: {:?}",
+                error
+            );
         }
     }
 }

data/vendor/kreuzberg/tests/format_integration.rs

@@ -5,14 +5,9 @@
 //! asynchronous APIs or to graceful handling when optional system
 //! dependencies are missing.
 
-#![cfg(any(feature = "pdf", feature = "office", feature = "ocr"))]
-
 mod helpers;
 
-use helpers::{assert_mime_type, get_test_file_path, test_documents_available};
-
-#[cfg(any(feature = "office", feature = "ocr"))]
-use helpers::assert_non_empty_content;
+use helpers::{assert_mime_type, assert_non_empty_content, get_test_file_path, test_documents_available};
 use kreuzberg::core::config::ExtractionConfig;
 use kreuzberg::core::extractor::extract_file;
 
@@ -49,7 +44,6 @@ async fn test_pdf_password_protected_async() {
 
 #[cfg(feature = "office")]
 #[tokio::test]
-#[cfg_attr(target_os = "windows", ignore = "LibreOffice tests timeout on Windows CI")]
 async fn test_legacy_doc_extraction_async() {
     if !test_documents_available() {
         return;

data/vendor/kreuzberg/tests/helpers/mod.rs

@@ -121,66 +121,6 @@ pub fn test_config_with_ocr() -> kreuzberg::core::config::ExtractionConfig {
     }
 }
 
-// PDF-specific test helpers (only available with pdf feature)
-#[cfg(feature = "pdf")]
-pub mod pdf_helpers {
-    use kreuzberg::core::config::ExtractionConfig;
-    use kreuzberg::pdf::hierarchy::{BoundingBox, CharData};
-
-    /// Create a bounding box with simple coordinates.
-    ///
-    /// # Arguments
-    ///
-    /// * `left` - Left x-coordinate
-    /// * `top` - Top y-coordinate
-    /// * `right` - Right x-coordinate
-    /// * `bottom` - Bottom y-coordinate
-    ///
-    /// # Returns
-    ///
-    /// A new BoundingBox with the specified coordinates
-    pub fn create_bounding_box(left: f32, top: f32, right: f32, bottom: f32) -> BoundingBox {
-        BoundingBox {
-            left,
-            top,
-            right,
-            bottom,
-        }
-    }
-
-    /// Create a character data with minimal parameters.
-    ///
-    /// # Arguments
-    ///
-    /// * `text` - Character text content
-    /// * `x` - X position
-    /// * `y` - Y position
-    /// * `font_size` - Font size in points
-    ///
-    /// # Returns
-    ///
-    /// A new CharData with calculated width and height
-    pub fn create_char_data(text: &str, x: f32, y: f32, font_size: f32) -> CharData {
-        CharData {
-            text: text.to_string(),
-            x,
-            y,
-            font_size,
-            width: font_size * 0.6,
-            height: font_size,
-        }
-    }
-
-    /// Create a default extraction configuration for testing hierarchy extraction.
-    ///
-    /// # Returns
-    ///
-    /// A new ExtractionConfig with PDF hierarchy options enabled
-    pub fn create_hierarchy_extraction_config() -> ExtractionConfig {
-        ExtractionConfig::default()
-    }
-}
-
 #[cfg(test)]
 mod tests {
     use super::*;

data/vendor/kreuzberg/tests/image_integration.rs

@@ -11,8 +11,6 @@
 //! - Test OCR with various languages and layouts
 //! - Verify graceful handling of images without text
 
-#![cfg(feature = "ocr")]
-
 mod helpers;
 
 use helpers::*;

data/vendor/kreuzberg/tests/mime_detection.rs

@@ -276,23 +276,22 @@ async fn test_no_extension() {
 
     let detected = detect_mime_type(&temp_path, true);
 
-    match detected {
-        Err(error) => {
-            assert!(
-                matches!(
-                    error,
-                    kreuzberg::KreuzbergError::Validation { .. } | kreuzberg::KreuzbergError::UnsupportedFormat(_)
-                ),
-                "Should return appropriate error for file without extension"
-            );
-        }
-        Ok(mime) => {
-            assert!(
-                mime.contains('/'),
-                "Detected MIME type should be valid format: {}",
-                mime
-            );
-        }
+    if detected.is_err() {
+        let error = detected.unwrap_err();
+        assert!(
+            matches!(
+                error,
+                kreuzberg::KreuzbergError::Validation { .. } | kreuzberg::KreuzbergError::UnsupportedFormat(_)
+            ),
+            "Should return appropriate error for file without extension"
+        );
+    } else {
+        let mime = detected.unwrap();
+        assert!(
+            mime.contains('/'),
+            "Detected MIME type should be valid format: {}",
+            mime
+        );
     }
 
     let _ = std::fs::remove_file(&temp_path);

data/vendor/kreuzberg/tests/ocr_configuration.rs

@@ -11,8 +11,6 @@
 //! - Verify configuration changes actually affect output
 //! - Test table detection with various settings
 
-#![cfg(feature = "ocr")]
-
 mod helpers;
 
 use helpers::*;
@@ -206,7 +204,6 @@ fn test_ocr_psm_single_line() {
 }
 
 #[test]
-#[cfg(feature = "pdf")]
 fn test_force_ocr_on_text_pdf() {
     if skip_if_missing("pdfs/fake_memo.pdf") {
         return;
@@ -236,7 +233,6 @@ fn test_force_ocr_on_text_pdf() {
 }
 
 #[test]
-#[cfg(feature = "pdf")]
 fn test_force_ocr_disabled() {
     if skip_if_missing("pdfs/fake_memo.pdf") {
         return;

data/vendor/kreuzberg/tests/ocr_errors.rs

@@ -13,8 +13,6 @@
 //! - Test recovery from transient failures
 //! - Validate resource limits and constraints
 
-#![cfg(feature = "ocr")]
-
 mod helpers;
 
 use helpers::*;
@@ -453,9 +451,6 @@ fn test_ocr_cache_disabled_then_enabled() {
     };
 
     let result1 = extract_file_sync(&file_path, None, &config_no_cache);
-    if matches!(result1, Err(KreuzbergError::MissingDependency(_))) {
-        return;
-    }
     assert!(result1.is_ok(), "First extraction should succeed");
 
     let config_with_cache = ExtractionConfig {
@@ -473,9 +468,6 @@ fn test_ocr_cache_disabled_then_enabled() {
     };
 
     let result2 = extract_file_sync(&file_path, None, &config_with_cache);
-    if matches!(result2, Err(KreuzbergError::MissingDependency(_))) {
-        return;
-    }
     assert!(result2.is_ok(), "Second extraction should succeed");
 
     assert_non_empty_content(&result1.unwrap());
@@ -503,13 +495,6 @@ fn test_ocr_concurrent_same_file() {
         ..Default::default()
     });
 
-    if matches!(
-        extract_file_sync(&*file_path, None, &config),
-        Err(KreuzbergError::MissingDependency(_))
-    ) {
-        return;
-    }
-
     let mut handles = vec![];
     for i in 0..5 {
         let file_path_clone = Arc::clone(&file_path);
@@ -569,13 +554,6 @@ fn test_ocr_concurrent_different_files() {
         ..Default::default()
     });
 
-    if matches!(
-        extract_file_sync(&files[0], None, &config),
-        Err(KreuzbergError::MissingDependency(_))
-    ) {
-        return;
-    }
-
     let mut handles = vec![];
     for (i, file_path) in files.iter().enumerate() {
         let file_path_clone = file_path.clone();

data/vendor/kreuzberg/tests/ocr_quality.rs

@@ -14,8 +14,6 @@
 //! - Verify layout preservation (line counts, structure)
 //! - Assert minimum quality thresholds
 
-#![cfg(all(feature = "ocr", feature = "pdf"))]
-
 mod helpers;
 
 use helpers::*;