kreuzberg 4.0.0.pre.rc.13 → 4.0.0.pre.rc.15

data/vendor/kreuzberg/README.md

@@ -1,230 +1,230 @@
-# Kreuzberg
-
-[![Rust](https://img.shields.io/crates/v/kreuzberg?label=Rust)](https://crates.io/crates/kreuzberg)
-[![Python](https://img.shields.io/pypi/v/kreuzberg?label=Python)](https://pypi.org/project/kreuzberg/)
-[![TypeScript](https://img.shields.io/npm/v/@kreuzberg/node?label=TypeScript)](https://www.npmjs.com/package/@kreuzberg/node)
-[![WASM](https://img.shields.io/npm/v/@kreuzberg/wasm?label=WASM)](https://www.npmjs.com/package/@kreuzberg/wasm)
-[![Ruby](https://img.shields.io/gem/v/kreuzberg?label=Ruby)](https://rubygems.org/gems/kreuzberg)
-[![Java](https://img.shields.io/maven-central/v/dev.kreuzberg/kreuzberg?label=Java)](https://central.sonatype.com/artifact/dev.kreuzberg/kreuzberg)
-[![Go](https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go)](https://pkg.go.dev/github.com/kreuzberg-dev/kreuzberg)
-[![C#](https://img.shields.io/nuget/v/Goldziher.Kreuzberg?label=C%23)](https://www.nuget.org/packages/Goldziher.Kreuzberg/)
-
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![Documentation](https://img.shields.io/badge/docs-kreuzberg.dev-blue)](https://kreuzberg.dev/)
-[![Discord](https://img.shields.io/badge/Discord-Join%20our%20community-7289da)](https://discord.gg/pXxagNK2zN)
-
-High-performance document intelligence library for Rust. Extract text, metadata, and structured information from PDFs, Office documents, images, and 56 formats.
-
-This is the core Rust library that powers the Python, TypeScript, and Ruby bindings.
-
-> **🚀 Version 4.0.0 Release Candidate**
-> This is a pre-release version. We invite you to test the library and [report any issues](https://github.com/kreuzberg-dev/kreuzberg/issues) you encounter.
->
-> **Note**: The Rust crate is not currently published to crates.io for this RC. Use git dependencies or language bindings (Python, TypeScript, Ruby) instead.
-
-## Installation
-
-```toml
-[dependencies]
-kreuzberg = "4.0"
-tokio = { version = "1", features = ["rt", "macros"] }
-```
-
-## System Requirements
-
-### ONNX Runtime (for embeddings)
-
-If using embeddings functionality, ONNX Runtime must be installed:
-
-```bash
-# macOS
-brew install onnxruntime
-
-# Ubuntu/Debian
-sudo apt install libonnxruntime libonnxruntime-dev
-
-# Windows (MSVC)
-scoop install onnxruntime
-# OR download from https://github.com/microsoft/onnxruntime/releases
-```
-
-Without ONNX Runtime, embeddings will raise `MissingDependencyError` with installation instructions.
-
-## Quick Start
-
-```rust
-use kreuzberg::{extract_file_sync, ExtractionConfig};
-
-fn main() -> kreuzberg::Result<()> {
-    let config = ExtractionConfig::default();
-    let result = extract_file_sync("document.pdf", None, &config)?;
-    println!("{}", result.content);
-    Ok(())
-}
-```
-
-### Async Extraction
-
-```rust
-use kreuzberg::{extract_file, ExtractionConfig};
-
-#[tokio::main]
-async fn main() -> kreuzberg::Result<()> {
-    let config = ExtractionConfig::default();
-    let result = extract_file("document.pdf", None, &config).await?;
-    println!("{}", result.content);
-    Ok(())
-}
-```
-
-### Batch Processing
-
-```rust
-use kreuzberg::{batch_extract_file, ExtractionConfig};
-
-#[tokio::main]
-async fn main() -> kreuzberg::Result<()> {
-    let config = ExtractionConfig::default();
-    let files = vec!["doc1.pdf", "doc2.pdf", "doc3.pdf"];
-    let results = batch_extract_file(&files, None, &config).await?;
-
-    for result in results {
-        println!("{}", result.content);
-    }
-    Ok(())
-}
-```
-
-## OCR with Table Extraction
-
-```rust
-use kreuzberg::{extract_file_sync, ExtractionConfig, OcrConfig, TesseractConfig};
-
-fn main() -> kreuzberg::Result<()> {
-    let config = ExtractionConfig {
-        ocr: Some(OcrConfig {
-            backend: "tesseract".to_string(),
-            language: "eng".to_string(),
-            tesseract_config: Some(TesseractConfig {
-                enable_table_detection: true,
-                ..Default::default()
-            }),
-        }),
-        ..Default::default()
-    };
-
-    let result = extract_file_sync("invoice.pdf", None, &config)?;
-
-    for table in &result.tables {
-        println!("{}", table.markdown);
-    }
-    Ok(())
-}
-```
-
-## Password-Protected PDFs
-
-```rust
-use kreuzberg::{extract_file_sync, ExtractionConfig, PdfConfig};
-
-fn main() -> kreuzberg::Result<()> {
-    let config = ExtractionConfig {
-        pdf_options: Some(PdfConfig {
-            passwords: Some(vec!["password1".to_string(), "password2".to_string()]),
-            ..Default::default()
-        }),
-        ..Default::default()
-    };
-
-    let result = extract_file_sync("protected.pdf", None, &config)?;
-    Ok(())
-}
-```
-
-## Extract from Bytes
-
-```rust
-use kreuzberg::{extract_bytes_sync, ExtractionConfig};
-use std::fs;
-
-fn main() -> kreuzberg::Result<()> {
-    let data = fs::read("document.pdf")?;
-    let config = ExtractionConfig::default();
-    let result = extract_bytes_sync(&data, "application/pdf", &config)?;
-    println!("{}", result.content);
-    Ok(())
-}
-```
-
-## Features
-
-The crate uses feature flags for optional functionality:
-
-```toml
-[dependencies]
-kreuzberg = { version = "4.0", features = ["pdf", "excel", "ocr"] }
-```
-
-### Available Features
-
-| Feature | Description | Binary Size |
-|---------|-------------|-------------|
-| `pdf` | PDF extraction via pdfium | +25MB |
-| `excel` | Excel/spreadsheet parsing | +3MB |
-| `office` | DOCX, PPTX extraction | +1MB |
-| `email` | EML, MSG extraction | +500KB |
-| `html` | HTML to markdown | +1MB |
-| `xml` | XML streaming parser | +500KB |
-| `archives` | ZIP, TAR, 7Z extraction | +2MB |
-| `ocr` | OCR with Tesseract | +5MB |
-| `language-detection` | Language detection | +100KB |
-| `chunking` | Text chunking | +200KB |
-| `quality` | Text quality processing | +500KB |
-
-### Feature Bundles
-
-```toml
-kreuzberg = { version = "4.0", features = ["full"] }
-kreuzberg = { version = "4.0", features = ["server"] }
-kreuzberg = { version = "4.0", features = ["cli"] }
-```
-
-## PDF Support and Linking Options
-
-Kreuzberg supports three PDFium linking strategies. **Default is `bundled-pdfium`** (best developer experience).
-
-| Strategy | Feature | Use Case | Binary Size | Runtime Deps |
-|----------|---------|----------|-------------|--------------|
-| **Bundled (default)** | `bundled-pdfium` | Development, production | +8-15MB | None |
-| **Static** | `static-pdfium` | Docker, musl, standalone binaries | +200MB | None |
-| **System** | `system-pdfium` | Package managers, distros | +2MB | libpdfium.so |
-
-### Quick Start
-
-```toml
-# Default - bundled PDFium (recommended)
-[dependencies]
-kreuzberg = "4.0"
-
-# Static linking (Docker, musl)
-[dependencies]
-kreuzberg = { version = "4.0", features = ["static-pdfium"] }
-
-# System PDFium (package managers)
-[dependencies]
-kreuzberg = { version = "4.0", features = ["system-pdfium"] }
-```
-
-For detailed information, see the [PDFium Linking Guide](../../docs/guides/pdfium-linking.md).
-
-**Note:** Language bindings (Python, TypeScript, Ruby, Java, Go) automatically bundle PDFium. No configuration needed.
-
-## Documentation
-
-**[API Documentation](https://docs.rs/kreuzberg)** – Complete API reference with examples
-
-**[https://kreuzberg.dev](https://kreuzberg.dev)** – User guide and tutorials
-
-## License
-
-MIT License - see [LICENSE](../../LICENSE) for details.
+# Kreuzberg
+
+[![Rust](https://img.shields.io/crates/v/kreuzberg?label=Rust)](https://crates.io/crates/kreuzberg)
+[![Python](https://img.shields.io/pypi/v/kreuzberg?label=Python)](https://pypi.org/project/kreuzberg/)
+[![TypeScript](https://img.shields.io/npm/v/@kreuzberg/node?label=TypeScript)](https://www.npmjs.com/package/@kreuzberg/node)
+[![WASM](https://img.shields.io/npm/v/@kreuzberg/wasm?label=WASM)](https://www.npmjs.com/package/@kreuzberg/wasm)
+[![Ruby](https://img.shields.io/gem/v/kreuzberg?label=Ruby)](https://rubygems.org/gems/kreuzberg)
+[![Java](https://img.shields.io/maven-central/v/dev.kreuzberg/kreuzberg?label=Java)](https://central.sonatype.com/artifact/dev.kreuzberg/kreuzberg)
+[![Go](https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go)](https://pkg.go.dev/github.com/kreuzberg-dev/kreuzberg)
+[![C#](https://img.shields.io/nuget/v/Goldziher.Kreuzberg?label=C%23)](https://www.nuget.org/packages/Goldziher.Kreuzberg/)
+
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Documentation](https://img.shields.io/badge/docs-kreuzberg.dev-blue)](https://kreuzberg.dev/)
+[![Discord](https://img.shields.io/badge/Discord-Join%20our%20community-7289da)](https://discord.gg/pXxagNK2zN)
+
+High-performance document intelligence library for Rust. Extract text, metadata, and structured information from PDFs, Office documents, images, and 56 formats.
+
+This is the core Rust library that powers the Python, TypeScript, and Ruby bindings.
+
+> **🚀 Version 4.0.0 Release Candidate**
+> This is a pre-release version. We invite you to test the library and [report any issues](https://github.com/kreuzberg-dev/kreuzberg/issues) you encounter.
+>
+> **Note**: The Rust crate is not currently published to crates.io for this RC. Use git dependencies or language bindings (Python, TypeScript, Ruby) instead.
+
+## Installation
+
+```toml
+[dependencies]
+kreuzberg = "4.0"
+tokio = { version = "1", features = ["rt", "macros"] }
+```
+
+## System Requirements
+
+### ONNX Runtime (for embeddings)
+
+If using embeddings functionality, ONNX Runtime must be installed:
+
+```bash
+# macOS
+brew install onnxruntime
+
+# Ubuntu/Debian
+sudo apt install libonnxruntime libonnxruntime-dev
+
+# Windows (MSVC)
+scoop install onnxruntime
+# OR download from https://github.com/microsoft/onnxruntime/releases
+```
+
+Without ONNX Runtime, embeddings will raise `MissingDependencyError` with installation instructions.
+
+## Quick Start
+
+```rust
+use kreuzberg::{extract_file_sync, ExtractionConfig};
+
+fn main() -> kreuzberg::Result<()> {
+    let config = ExtractionConfig::default();
+    let result = extract_file_sync("document.pdf", None, &config)?;
+    println!("{}", result.content);
+    Ok(())
+}
+```
+
+### Async Extraction
+
+```rust
+use kreuzberg::{extract_file, ExtractionConfig};
+
+#[tokio::main]
+async fn main() -> kreuzberg::Result<()> {
+    let config = ExtractionConfig::default();
+    let result = extract_file("document.pdf", None, &config).await?;
+    println!("{}", result.content);
+    Ok(())
+}
+```
+
+### Batch Processing
+
+```rust
+use kreuzberg::{batch_extract_file, ExtractionConfig};
+
+#[tokio::main]
+async fn main() -> kreuzberg::Result<()> {
+    let config = ExtractionConfig::default();
+    let files = vec!["doc1.pdf", "doc2.pdf", "doc3.pdf"];
+    let results = batch_extract_file(&files, None, &config).await?;
+
+    for result in results {
+        println!("{}", result.content);
+    }
+    Ok(())
+}
+```
+
+## OCR with Table Extraction
+
+```rust
+use kreuzberg::{extract_file_sync, ExtractionConfig, OcrConfig, TesseractConfig};
+
+fn main() -> kreuzberg::Result<()> {
+    let config = ExtractionConfig {
+        ocr: Some(OcrConfig {
+            backend: "tesseract".to_string(),
+            language: "eng".to_string(),
+            tesseract_config: Some(TesseractConfig {
+                enable_table_detection: true,
+                ..Default::default()
+            }),
+        }),
+        ..Default::default()
+    };
+
+    let result = extract_file_sync("invoice.pdf", None, &config)?;
+
+    for table in &result.tables {
+        println!("{}", table.markdown);
+    }
+    Ok(())
+}
+```
+
+## Password-Protected PDFs
+
+```rust
+use kreuzberg::{extract_file_sync, ExtractionConfig, PdfConfig};
+
+fn main() -> kreuzberg::Result<()> {
+    let config = ExtractionConfig {
+        pdf_options: Some(PdfConfig {
+            passwords: Some(vec!["password1".to_string(), "password2".to_string()]),
+            ..Default::default()
+        }),
+        ..Default::default()
+    };
+
+    let result = extract_file_sync("protected.pdf", None, &config)?;
+    Ok(())
+}
+```
+
+## Extract from Bytes
+
+```rust
+use kreuzberg::{extract_bytes_sync, ExtractionConfig};
+use std::fs;
+
+fn main() -> kreuzberg::Result<()> {
+    let data = fs::read("document.pdf")?;
+    let config = ExtractionConfig::default();
+    let result = extract_bytes_sync(&data, "application/pdf", &config)?;
+    println!("{}", result.content);
+    Ok(())
+}
+```
+
+## Features
+
+The crate uses feature flags for optional functionality:
+
+```toml
+[dependencies]
+kreuzberg = { version = "4.0", features = ["pdf", "excel", "ocr"] }
+```
+
+### Available Features
+
+| Feature | Description | Binary Size |
+|---------|-------------|-------------|
+| `pdf` | PDF extraction via pdfium | +25MB |
+| `excel` | Excel/spreadsheet parsing | +3MB |
+| `office` | DOCX, PPTX extraction | +1MB |
+| `email` | EML, MSG extraction | +500KB |
+| `html` | HTML to markdown | +1MB |
+| `xml` | XML streaming parser | +500KB |
+| `archives` | ZIP, TAR, 7Z extraction | +2MB |
+| `ocr` | OCR with Tesseract | +5MB |
+| `language-detection` | Language detection | +100KB |
+| `chunking` | Text chunking | +200KB |
+| `quality` | Text quality processing | +500KB |
+
+### Feature Bundles
+
+```toml
+kreuzberg = { version = "4.0", features = ["full"] }
+kreuzberg = { version = "4.0", features = ["server"] }
+kreuzberg = { version = "4.0", features = ["cli"] }
+```
+
+## PDF Support and Linking Options
+
+Kreuzberg supports three PDFium linking strategies. **Default is `bundled-pdfium`** (best developer experience).
+
+| Strategy | Feature | Use Case | Binary Size | Runtime Deps |
+|----------|---------|----------|-------------|--------------|
+| **Bundled (default)** | `bundled-pdfium` | Development, production | +8-15MB | None |
+| **Static** | `static-pdfium` | Docker, musl, standalone binaries | +200MB | None |
+| **System** | `system-pdfium` | Package managers, distros | +2MB | libpdfium.so |
+
+### Quick Start
+
+```toml
+# Default - bundled PDFium (recommended)
+[dependencies]
+kreuzberg = "4.0"
+
+# Static linking (Docker, musl)
+[dependencies]
+kreuzberg = { version = "4.0", features = ["static-pdfium"] }
+
+# System PDFium (package managers)
+[dependencies]
+kreuzberg = { version = "4.0", features = ["system-pdfium"] }
+```
+
+For detailed information, see the [PDFium Linking Guide](../../docs/guides/pdfium-linking.md).
+
+**Note:** Language bindings (Python, TypeScript, Ruby, Java, Go) automatically bundle PDFium. No configuration needed.
+
+## Documentation
+
+**[API Documentation](https://docs.rs/kreuzberg)** – Complete API reference with examples
+
+**[https://kreuzberg.dev](https://kreuzberg.dev)** – User guide and tutorials
+
+## License
+
+MIT License - see [LICENSE](../../LICENSE) for details.

data/vendor/kreuzberg/benches/otel_overhead.rs

@@ -1,48 +1,48 @@
-use criterion::{Criterion, criterion_group, criterion_main};
-use std::hint::black_box;
-
-fn bench_text_extraction(c: &mut Criterion) {
-    let runtime = tokio::runtime::Runtime::new().unwrap();
-
-    c.bench_function("extract_text_no_otel", |b| {
-        b.iter(|| {
-            runtime.block_on(async {
-                use kreuzberg::core::config::ExtractionConfig;
-                use kreuzberg::core::extractor::extract_bytes;
-
-                let test_content = black_box(b"Hello, World! This is a test document.");
-                let config = ExtractionConfig::default();
-
-                extract_bytes(test_content, "text/plain", &config).await
-            })
-        });
-    });
-}
-
-fn bench_cache_operations(c: &mut Criterion) {
-    use kreuzberg::cache::GenericCache;
-    use tempfile::tempdir;
-
-    let temp_dir = tempdir().unwrap();
-    let cache = GenericCache::new(
-        "bench".to_string(),
-        Some(temp_dir.path().to_str().unwrap().to_string()),
-        30.0,
-        500.0,
-        1000.0,
-    )
-    .unwrap();
-
-    c.bench_function("cache_set_get", |b| {
-        b.iter(|| {
-            let key = black_box("bench_key");
-            let data = black_box(b"benchmark data".to_vec());
-
-            cache.set(key, data.clone(), None).unwrap();
-            cache.get(key, None).unwrap()
-        });
-    });
-}
-
-criterion_group!(benches, bench_text_extraction, bench_cache_operations);
-criterion_main!(benches);
+use criterion::{Criterion, criterion_group, criterion_main};
+use std::hint::black_box;
+
+fn bench_text_extraction(c: &mut Criterion) {
+    let runtime = tokio::runtime::Runtime::new().unwrap();
+
+    c.bench_function("extract_text_no_otel", |b| {
+        b.iter(|| {
+            runtime.block_on(async {
+                use kreuzberg::core::config::ExtractionConfig;
+                use kreuzberg::core::extractor::extract_bytes;
+
+                let test_content = black_box(b"Hello, World! This is a test document.");
+                let config = ExtractionConfig::default();
+
+                extract_bytes(test_content, "text/plain", &config).await
+            })
+        });
+    });
+}
+
+fn bench_cache_operations(c: &mut Criterion) {
+    use kreuzberg::cache::GenericCache;
+    use tempfile::tempdir;
+
+    let temp_dir = tempdir().unwrap();
+    let cache = GenericCache::new(
+        "bench".to_string(),
+        Some(temp_dir.path().to_str().unwrap().to_string()),
+        30.0,
+        500.0,
+        1000.0,
+    )
+    .unwrap();
+
+    c.bench_function("cache_set_get", |b| {
+        b.iter(|| {
+            let key = black_box("bench_key");
+            let data = black_box(b"benchmark data".to_vec());
+
+            cache.set(key, data.clone(), None).unwrap();
+            cache.get(key, None).unwrap()
+        });
+    });
+}
+
+criterion_group!(benches, bench_text_extraction, bench_cache_operations);
+criterion_main!(benches);