kreuzberg 4.1.1 → 4.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 0c1c0519fb3a58c45ec553994bd982b4f284835bd35ea0758461f6f381accfd6
-  data.tar.gz: 161c18cfabdd20bdaa520abda521cb16072dcc00f5fd2e41152d9da4acdb9d08
+  metadata.gz: 6550daabf58e5e396576e5a83c6a53f226e677f9c129920c9990bba309fbd7ba
+  data.tar.gz: 9595aa468666391d08a0962db589bbbc50d5bd1c8532e101efa234f6c523d7c5
 SHA512:
-  metadata.gz: 7c6e1768022dcfdef5eaaaa3557a8388e8ad45158a69ed022d852b07f7658cbb885ca7860fa32eda8f29b5f7ea4216f93033aad77614afb82578b9157ed92710
-  data.tar.gz: 96ca3f1f3c6d6f9ea6dc826f7704c1d741ffaab24f524f099c4eb294652211ac6b9f324874974bb24d417193e76b1bce951315330d6f1ccd8eb5b014fa7fc71f
+  metadata.gz: 0dea911deebe061515dd4cbff2b76b3a7947c68f196fcc576001d42d80386f6c53f8ed63e0e4acb8e719ad6f95c21e689df7aef5f6cbbbc0d1c92ef96ddb673c
+  data.tar.gz: 0df091f80f7c73dda0c17d89d4aa0571cd01f0f2b697b187fd9bae28f8dbcf96cd2e3a269f9831a442b8cf46ce40608586d3d6a242d84bb394fe6056cba3b492

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    kreuzberg (4.1.1)
+    kreuzberg (4.1.2)
 
 GEM
   remote: https://rubygems.org/
@@ -121,7 +121,7 @@ GEM
       rubocop (~> 1.81)
     ruby-progressbar (1.13.0)
     securerandom (0.4.1)
-    sorbet-runtime (0.6.12894)
+    sorbet-runtime (0.6.12897)
     steep (1.10.0)
       activesupport (>= 5.1)
       concurrent-ruby (>= 1.1.10)
@@ -207,7 +207,7 @@ CHECKSUMS
   i18n (1.14.8) sha256=285778639134865c5e0f6269e0b818256017e8cde89993fdfcbfb64d088824a5
   io-console (0.8.2) sha256=d6e3ae7a7cc7574f4b8893b4fca2162e57a825b223a177b7afa236c5ef9814cc
   json (2.18.0) sha256=b10506aee4183f5cf49e0efc48073d7b75843ce3782c68dbeb763351c08fd505
-  kreuzberg (4.1.1)
+  kreuzberg (4.1.2)
   language_server-protocol (3.17.0.5) sha256=fd1e39a51a28bf3eec959379985a72e296e9f9acfce46f6a79d31ca8760803cc
   lint_roller (1.1.0) sha256=2c0c845b632a7d172cb849cc90c1bce937a28c5c8ccccb50dfd46a485003cc87
   listen (3.10.0) sha256=c6e182db62143aeccc2e1960033bebe7445309c7272061979bb098d03760c9d2
@@ -242,7 +242,7 @@ CHECKSUMS
   rubocop-rspec (3.9.0) sha256=8fa70a3619408237d789aeecfb9beef40576acc855173e60939d63332fdb55e2
   ruby-progressbar (1.13.0) sha256=80fc9c47a9b640d6834e0dc7b3c94c9df37f08cb072b7761e4a71e22cff29b33
   securerandom (0.4.1) sha256=cc5193d414a4341b6e225f0cb4446aceca8e50d5e1888743fac16987638ea0b1
-  sorbet-runtime (0.6.12894) sha256=4f0cbe041d80dac973ec3a5a848679922074dd77cc19f46384b27a8b9ff4a90c
+  sorbet-runtime (0.6.12897) sha256=0348ab8803c4c3646977fee298083ded9b7e74d5b34b50c567c63eb7e36eb286
   steep (1.10.0) sha256=1b295b55f9aaff1b8d3ee42453ee55bc2a1078fda0268f288edb2dc014f4d7d1
   strscan (3.1.7) sha256=5f76462b94a3ea50b44973225b7d75b2cb96d4e1bee9ef1319b99ca117b72c8c
   terminal-table (4.0.0) sha256=f504793203f8251b2ea7c7068333053f0beeea26093ec9962e62ea79f94301d2

data/README.md

@@ -22,7 +22,7 @@
     <img src="https://img.shields.io/maven-central/v/dev.kreuzberg/kreuzberg?label=Java&color=007ec6" alt="Java">
   </a>
   <a href="https://github.com/kreuzberg-dev/kreuzberg/releases">
-    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go&color=007ec6&filter=v4.1.1" alt="Go">
+    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go&color=007ec6&filter=v4.1.2" alt="Go">
   </a>
   <a href="https://www.nuget.org/packages/Kreuzberg/">
     <img src="https://img.shields.io/nuget/v/Kreuzberg?label=C%23&color=007ec6" alt="C#">
@@ -86,10 +86,13 @@ gem 'kreuzberg'
 
 ### System Requirements
 
-- **Ruby 2.7+** required
+- **Ruby 3.2.0 or higher** required (including Ruby 4.x)
+- Ruby 4.0+ is fully supported with no code changes required
 - Optional: [ONNX Runtime](https://github.com/microsoft/onnxruntime/releases) version 1.22.x for embeddings support
 - Optional: [Tesseract OCR](https://github.com/tesseract-ocr/tesseract) for OCR functionality
 
+**Ruby 4.0 Compatibility:** Kreuzberg is fully compatible with Ruby 4.0 (released December 25, 2025) and all Ruby 4.x versions. All tests pass with 100% compatibility. The gem compiles without any breaking changes. Key Ruby 4.0 features like Ruby Box, ZJIT compiler, and Ractor improvements work seamlessly with Kreuzberg.
+
 
 
 ## Quick Start
@@ -202,9 +205,9 @@ puts "Processing time: #{result.metadata&.dig('processing_time')}ms"
 
 ## Features
 
-### Supported File Formats (56+)
+### Supported File Formats (57+)
 
-56 file formats across 8 major categories with intelligent format detection and comprehensive metadata extraction.
+57 file formats across 8 major categories with intelligent format detection and comprehensive metadata extraction.
 
 #### Office Documents
 
@@ -230,7 +233,7 @@ puts "Processing time: #{result.metadata&.dig('processing_time')}ms"
 |----------|---------|----------|
 | **Markup** | `.html`, `.htm`, `.xhtml`, `.xml`, `.svg` | DOM parsing, metadata (Open Graph, Twitter Card), link extraction |
 | **Structured Data** | `.json`, `.yaml`, `.yml`, `.toml`, `.csv`, `.tsv` | Schema detection, nested structures, validation |
-| **Text & Markdown** | `.txt`, `.md`, `.markdown`, `.rst`, `.org`, `.rtf` | CommonMark, GFM, reStructuredText, Org Mode |
+| **Text & Markdown** | `.txt`, `.md`, `.markdown`, `.djot`, `.rst`, `.org`, `.rtf` | CommonMark, GFM, Djot, reStructuredText, Org Mode |
 
 #### Email & Archives
 

data/ext/kreuzberg_rb/native/Cargo.toml

@@ -31,7 +31,7 @@ embeddings = ["kreuzberg/embeddings"]
 
 [dependencies]
 async-trait = "0.1.89"
-kreuzberg = { path = "../../../../../crates/kreuzberg", default-features = false, features = [
+kreuzberg = { path = "../../../vendor/kreuzberg", default-features = false, features = [
     "pdf",
     "excel",
     "office",
@@ -51,7 +51,7 @@ kreuzberg = { path = "../../../../../crates/kreuzberg", default-features = false
     "bundled-pdfium",
     "tokio-runtime",
 ] }
-kreuzberg-ffi = { path = "../../../../../crates/kreuzberg-ffi" }
+kreuzberg-ffi = { path = "../../../vendor/kreuzberg-ffi" }
 magnus = { git = "https://github.com/matsadler/magnus", rev = "f6db11769efb517427bf7f121f9c32e18b059b38", features = [
     "rb-sys",
 ] }

data/ext/kreuzberg_rb/native/src/config/types.rs

@@ -1025,8 +1025,10 @@ pub fn config_from_file(path: String) -> Result<RHash, Error> {
         .and_then(|v| magnus::RHash::try_convert(v).map_err(|_| validation_error("Config must be a Hash")))
 }
 
-/// Discover extraction config from current directory
+/// Discover extraction config from current directory or parent directories
 pub fn config_discover() -> Result<Value, Error> {
+    use std::path::PathBuf;
+
     let ruby = Ruby::get().expect("Ruby not initialized");
 
     // Search for config files in order of precedence
@@ -1038,19 +1040,27 @@ pub fn config_discover() -> Result<Value, Error> {
         (".kreuzbergrc", "json"),
     ];
 
-    for (name, format) in config_files {
-        if let Ok(content) = fs::read_to_string(name) {
-            let json_value: serde_json::Value = match format {
-                "toml" => toml::from_str(&content)
-                    .map_err(|e| validation_error(format!("Invalid TOML in {}: {}", name, e)))?,
-                "yaml" => serde_yaml_ng::from_str(&content)
-                    .map_err(|e| validation_error(format!("Invalid YAML in {}: {}", name, e)))?,
-                "json" => serde_json::from_str(&content)
-                    .map_err(|e| validation_error(format!("Invalid JSON in {}: {}", name, e)))?,
-                _ => unreachable!(),
-            };
-            return json_value_to_ruby(&ruby, &json_value);
+    // Start from current directory and search up to parent directories
+    let mut current_dir: Option<PathBuf> = std::env::current_dir().ok();
+
+    while let Some(dir) = current_dir {
+        for (name, format) in &config_files {
+            let config_path = dir.join(name);
+            if let Ok(content) = fs::read_to_string(&config_path) {
+                let json_value: serde_json::Value = match *format {
+                    "toml" => toml::from_str(&content)
+                        .map_err(|e| validation_error(format!("Invalid TOML in {}: {}", config_path.display(), e)))?,
+                    "yaml" => serde_yaml_ng::from_str(&content)
+                        .map_err(|e| validation_error(format!("Invalid YAML in {}: {}", config_path.display(), e)))?,
+                    "json" => serde_json::from_str(&content)
+                        .map_err(|e| validation_error(format!("Invalid JSON in {}: {}", config_path.display(), e)))?,
+                    _ => unreachable!(),
+                };
+                return json_value_to_ruby(&ruby, &json_value);
+            }
         }
+        // Move to parent directory
+        current_dir = dir.parent().map(|p| p.to_path_buf());
     }
 
     // Return nil if no config found

data/kreuzberg.gemspec

@@ -165,7 +165,7 @@ Gem::Specification.new do |spec|
   DESC
   spec.homepage = 'https://github.com/kreuzberg-dev/kreuzberg'
   spec.license = 'MIT'
-  spec.required_ruby_version = '>= 3.2.0'
+  spec.required_ruby_version = '>= 3.2.0', '< 5.0'
 
   spec.metadata = {
     'homepage_uri' => spec.homepage,

data/lib/kreuzberg/api_proxy.rb

@@ -1,7 +1,6 @@
 # frozen_string_literal: true
 
 require 'open3'
-require 'pathname'
 
 module Kreuzberg
   # @example Start the server

data/lib/kreuzberg/cli_proxy.rb

@@ -1,7 +1,6 @@
 # frozen_string_literal: true
 
 require 'open3'
-require 'pathname'
 
 module Kreuzberg
   # @example

data/lib/kreuzberg/mcp_proxy.rb

@@ -1,7 +1,6 @@
 # frozen_string_literal: true
 
 require 'open3'
-require 'pathname'
 require 'json'
 
 module Kreuzberg

data/lib/kreuzberg/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Kreuzberg
-  VERSION = '4.1.1'
+  VERSION = '4.1.2'
 end

data/vendor/Cargo.toml

@@ -3,7 +3,7 @@ members = ["kreuzberg", "kreuzberg-tesseract", "kreuzberg-ffi"]
 resolver = "2"
 
 [workspace.package]
-version = "4.1.1"
+version = "4.1.2"
 edition = "2024"
 rust-version = "1.91"
 authors = ["Na'aman Hirschfeld <nhirschfeld@gmail.com>"]

data/vendor/kreuzberg/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "kreuzberg"
-version = "4.1.1"
+version = "4.1.2"
 edition = "2024"
 rust-version = "1.91"
 authors = ["Na'aman Hirschfeld <nhirschfeld@gmail.com>"]
@@ -142,7 +142,7 @@ mime_guess = "2.0"
 rmp-serde = "1.3"
 thiserror = { workspace = true }
 tokio = { workspace = true, optional = true }
-uuid = { version = "1.19.0", features = ["v4", "js"] }
+uuid = { version = "1.20.0", features = ["v4", "js"] }
 indexmap = "2.13.0"
 tracing = { workspace = true }
 pdfium-render = { package = "kreuzberg-pdfium-render", version = "0.9.0", features = [
@@ -198,7 +198,7 @@ rake = { version = "0.3.6", optional = true }
 axum = { version = "0.8", features = ["macros", "json", "multipart"], optional = true }
 tower = { version = "0.5", optional = true }
 tower-http = { version = "0.6", features = ["cors", "trace", "limit"], optional = true }
-rmcp = { version = "0.13.0", features = [
+rmcp = { version = "0.14.0", features = [
     "server",
     "macros",
     "base64",

data/vendor/kreuzberg/README.md

@@ -17,7 +17,7 @@ High-performance document intelligence library for Rust. Extract text, metadata,
 
 This is the core Rust library that powers the Python, TypeScript, and Ruby bindings.
 
-> **🚀 Version 4.1.1 Release**
+> **🚀 Version 4.1.2 Release**
 > 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.

data/vendor/kreuzberg-tesseract/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "kreuzberg-tesseract"
-version = "4.1.1"
+version = "4.1.2"
 edition = "2024"
 rust-version = "1.91"
 authors = ["Na'aman Hirschfeld <nhirschfeld@gmail.com>"]
@@ -21,10 +21,10 @@ libc = { workspace = true }
 thiserror = { workspace = true }
 
 [dev-dependencies]
-image = { workspace = true }
+image = { workspace = true, features = ["png"] }
 
 [build-dependencies]
-cc = { version = "^1.2.53", optional = true }
+cc = { version = "^1.2.54", optional = true }
 cmake = { version = "0.1.57", optional = true }
 zip = { version = "7.2.0", optional = true }
 

data/vendor/kreuzberg-tesseract/build.rs

@@ -38,7 +38,7 @@ mod build_tesseract {
                 return None;
             }
         }
-        Some(path.join("tesseract-rs-cache"))
+        Some(path.join("kreuzberg-tesseract-cache"))
     }
 
     fn get_preferred_out_dir() -> PathBuf {
@@ -63,14 +63,14 @@ mod build_tesseract {
             PathBuf::from(home_dir)
                 .join("Library")
                 .join("Application Support")
-                .join("tesseract-rs")
+                .join("kreuzberg-tesseract")
         } else if cfg!(target_os = "linux") {
             let home_dir = env::var("HOME").unwrap_or_else(|_| {
                 env::var("USER")
                     .map(|user| format!("/home/{}", user))
                     .expect("Neither HOME nor USER environment variable set")
             });
-            PathBuf::from(home_dir).join(".tesseract-rs")
+            PathBuf::from(home_dir).join(".kreuzberg-tesseract")
         } else {
             panic!("Unsupported operating system");
         }
@@ -117,7 +117,7 @@ mod build_tesseract {
                     "cargo:warning=Failed to create cache dir {:?}: {}. Falling back to temp dir.",
                     preferred, err
                 );
-                let fallback = env::temp_dir().join("tesseract-rs-cache");
+                let fallback = env::temp_dir().join("kreuzberg-tesseract-cache");
                 fs::create_dir_all(&fallback).expect("Failed to create fallback cache directory in temp dir");
                 fallback
             }

data/vendor/kreuzberg-tesseract/src/lib.rs

@@ -6,16 +6,16 @@
 #![allow(clippy::not_unsafe_ptr_arg_deref)]
 #![allow(clippy::cmp_null)]
 
-//! # tesseract-rs
+//! # kreuzberg-tesseract
 //!
-//! `tesseract-rs` provides safe Rust bindings for Tesseract OCR with built-in compilation
+//! `kreuzberg-tesseract` provides safe Rust bindings for Tesseract OCR with built-in compilation
 //! of Tesseract and Leptonica libraries. This crate aims to make OCR functionality
 //! easily accessible in Rust projects while handling the complexity of interfacing
 //! with the underlying C++ libraries.
 //!
 //! ## Usage
 //!
-//! Here's a basic example of how to use `tesseract-rs`:
+//! Here's a basic example of how to use `kreuzberg-tesseract`:
 //!
 //! ```rust
 //! use std::path::PathBuf;
@@ -28,16 +28,16 @@
 //!         PathBuf::from(home_dir)
 //!             .join("Library")
 //!             .join("Application Support")
-//!             .join("tesseract-rs")
+//!             .join("kreuzberg-tesseract")
 //!             .join("tessdata")
 //!     } else if cfg!(target_os = "linux") {
 //!         let home_dir = std::env::var("HOME").expect("HOME environment variable not set");
 //!         PathBuf::from(home_dir)
-//!             .join(".tesseract-rs")
+//!             .join(".kreuzberg-tesseract")
 //!             .join("tessdata")
 //!     } else if cfg!(target_os = "windows") {
 //!         PathBuf::from(std::env::var("APPDATA").expect("APPDATA environment variable not set"))
-//!             .join("tesseract-rs")
+//!             .join("kreuzberg-tesseract")
 //!             .join("tessdata")
 //!     } else {
 //!         panic!("Unsupported operating system");

data/vendor/kreuzberg-tesseract/tests/integration_test.rs

@@ -7,7 +7,7 @@ fn get_default_tessdata_dir() -> PathBuf {
         PathBuf::from(home_dir)
             .join("Library")
             .join("Application Support")
-            .join("tesseract-rs")
+            .join("kreuzberg-tesseract")
             .join("tessdata")
     } else if cfg!(target_os = "linux") {
         let system_paths = [
@@ -20,10 +20,10 @@ fn get_default_tessdata_dir() -> PathBuf {
             }
         }
         let home_dir = std::env::var("HOME").expect("HOME environment variable not set");
-        PathBuf::from(home_dir).join(".tesseract-rs").join("tessdata")
+        PathBuf::from(home_dir).join(".kreuzberg-tesseract").join("tessdata")
     } else if cfg!(target_os = "windows") {
         PathBuf::from(std::env::var("APPDATA").expect("APPDATA environment variable not set"))
-            .join("tesseract-rs")
+            .join("kreuzberg-tesseract")
             .join("tessdata")
     } else {
         panic!("Unsupported operating system");

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: kreuzberg
 version: !ruby/object:Gem::Version
-  version: 4.1.1
+  version: 4.1.2
 platform: ruby
 authors:
 - Na'aman Hirschfeld
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-01-23 00:00:00.000000000 Z
+date: 2026-01-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -791,6 +791,9 @@ required_ruby_version: !ruby/object:Gem::Requirement
   - - ">="
     - !ruby/object:Gem::Version
       version: 3.2.0
+  - - "<"
+    - !ruby/object:Gem::Version
+      version: '5.0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="