fix: address PR review comments

- Remove duplicate Cow imports in ocr.rs doctests
- Add Default to ExtractionConfig derive list in api-rust.md
- Use chars().take() instead of string slicing for UTF-8 safety
- Fix code fence title syntax in disk_cache.rs snippet
- Fix malformed markdown table in document-structure.md
- Fix admonition indentation in api-elixir.md

Author: Goldziher

crates/kreuzberg/src/plugins/ocr.rs

@@ -45,7 +45,6 @@ pub enum OcrBackendType {
 /// use async_trait::async_trait;
 /// use std::borrow::Cow;
 /// use std::path::Path;
-/// use std::borrow::Cow;
 /// use kreuzberg::types::{ExtractionResult, Metadata};
 ///
 /// struct CustomOcrBackend;
@@ -122,7 +121,6 @@ pub trait OcrBackend: Plugin {
     /// # use async_trait::async_trait;
     /// # use std::borrow::Cow;
     /// # use std::path::Path;
-    /// # use std::borrow::Cow;
     /// # use kreuzberg::types::{ExtractionResult, Metadata};
     /// # struct MyOcr;
     /// # impl Plugin for MyOcr {
@@ -315,7 +313,6 @@ pub trait OcrBackend: Plugin {
 /// use std::borrow::Cow;
 /// use std::sync::Arc;
 /// use std::path::Path;
-/// use std::borrow::Cow;
 ///
 /// struct CustomOcr;
 ///

docs/guides/document-structure.md

@@ -790,10 +790,10 @@ Page boundary marker in multi-page documents.
 Content layers classify nodes by their position and role in the document layout:
 
 | Layer        | Description            | Typical Nodes                               | Example                  |
-| ------------ | ---------------------- | ------------------------------------------- | ------------------------ | -------- |
+| ------------ | ---------------------- | ------------------------------------------- | ------------------------ |
 | **body**     | Main document content  | Headings, paragraphs, lists, tables, images | Chapter text, sections   |
 | **header**   | Page header content    | Title text, repeated headers                | "Chapter 5: Advanced ML" |
-| **footer**   | Page footer content    | Page numbers, copyright                     | "© 2025                  | Page 42" |
+| **footer**   | Page footer content    | Page numbers, copyright                     | "© 2025, Page 42"       |
 | **footnote** | Footnotes and endnotes | Footnote text, references                   | "1. See Smith (2020)"    |
 
 Access content layer:

docs/reference/api-elixir.md

@@ -838,7 +838,7 @@ IO.inspect(atom)
 ## Configuration
 
 !!! warning "Deprecated API"
-The `force_ocr` parameter has been deprecated in favor of the new `ocr` configuration object.
+    The `force_ocr` parameter has been deprecated in favor of the new `ocr` configuration object.
 
     **Old pattern (no longer supported):**
     ```elixir

docs/reference/api-rust.md

@@ -378,7 +378,7 @@ Main configuration struct for extraction operations.
 **Definition:**
 
 ```rust title="Rust"
-#[derive(Debug, Clone, Serialize, Deserialize)]
+#[derive(Debug, Clone, Serialize, Deserialize, Default)]
 pub struct ExtractionConfig {
     pub use_cache: bool,
     pub enable_quality_processing: bool,

docs/snippets/rust/advanced/advanced_config.md

@@ -33,7 +33,8 @@ fn main() -> kreuzberg::Result<()> {
 
     if let Some(chunks) = result.chunks {
         for chunk in chunks {
-            println!("Chunk: {}...", &chunk.content[..100.min(chunk.content.len())]);
+            let preview: String = chunk.content.chars().take(100).collect();
+            println!("Chunk: {}...", preview);
         }
     }
 

docs/snippets/rust/advanced/chunk_page_mapping.md

@@ -23,7 +23,7 @@ format!("Page {}", first)
 } else {
 format!("Pages {}-{}", first, last)
 };
-println!("Chunk: {}... ({})", &chunk.content[..50.min(chunk.content.len())], page_range);
+println!("Chunk: {}... ({})", chunk.content.chars().take(50).collect::<String>(), page_range);
 }
 }
 }

docs/snippets/rust/cache/disk_cache.rs

@@ -1,4 +1,4 @@
-```rust title=r#"disk_cache.rs"#
+```rust title="disk_cache.rs"
 use kreuzberg::{extract_file_sync, ExtractionConfig};
 
 fn main() -> kreuzberg::Result<()> {