kreuzberg 4.9.8-aarch64-linux → 4.10.0-aarch64-linux

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 71a5614e26fb989edc8c7788308c08d8cfcb279bad5986d230e1446b41945b11
-  data.tar.gz: cc87b594a7375efb6d79dd1d706fd60af5b344a47ed460f7dd7322f5993bbd50
+  metadata.gz: 8fb1a96cb76dcec11ffe0234731caa27c7f57fbb179344f25034e18796878364
+  data.tar.gz: 74b7250dbe911a6e9d7efbbe3c2c5e2d0214efcf63090ebd49c9e3da031a9c3c
 SHA512:
-  metadata.gz: 4201d8607651fe51ebc72dbae5fbc9d2eaf1e32bd76ddda9f24cce460a4a3c9514d9a9ec1500911fc66a5a6c53af8ce25680c1701444addc9a4752da9b268e3d
-  data.tar.gz: 48936337cd9d8b425724513920efc433b0d01f580bd18c13bbdc4d04b1b86222238aaea562de95855a6e5ad4a5bc83d3beeec55baea114f806c49c62b6d22c0c
+  metadata.gz: 625218f0138fb6daa5382023bbbc7b85d808db250948849dc84b5bd93815d64c760b070bdee682b6fde02f4e026b117d385714fc8e2012798638f5887d7eb2ea
+  data.tar.gz: 993598fa7423d7be60e648d7bc9cc6f64181ff7c16b2221caa692f89c0cd35bdf520f79bae622f1d0f6b8986245e26abefac800984631a25dfc058ee25dafce6

data/README.md

@@ -21,8 +21,8 @@
   <a href="https://central.sonatype.com/artifact/dev.kreuzberg/kreuzberg">
     <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=v4.9.8" alt="Go">
+  <a href="https://github.com/kreuzberg-dev/kreuzberg-lts/releases">
+    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg-lts?label=Go&color=007ec6&filter=v4.*" 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#">
@@ -36,7 +36,7 @@
   <a href="https://kreuzberg-dev.r-universe.dev/kreuzberg">
     <img src="https://img.shields.io/badge/R-kreuzberg-007ec6" alt="R">
   </a>
-  <a href="https://github.com/kreuzberg-dev/kreuzberg/pkgs/container/kreuzberg">
+  <a href="https://github.com/kreuzberg-dev/kreuzberg-lts/pkgs/container/kreuzberg">
     <img src="https://img.shields.io/badge/Docker-007ec6?logo=docker&logoColor=white" alt="Docker">
   </a>
   <a href="https://artifacthub.io/packages/search?repo=kreuzberg">
@@ -44,7 +44,7 @@
   </a>
 
   <!-- Project Info -->
-  <a href="https://github.com/kreuzberg-dev/kreuzberg/blob/main/LICENSE">
+  <a href="https://github.com/kreuzberg-dev/kreuzberg-lts/blob/main/LICENSE">
     <img src="https://img.shields.io/badge/License-MIT-007ec6" alt="License">
   </a>
   <a href="https://docs.kreuzberg.dev">
@@ -58,7 +58,11 @@
   </a>
 </div>
 
-<img width="1128" height="191" alt="Banner2" src="https://github.com/user-attachments/assets/419fc06c-8313-4324-b159-4b4d3cfce5c0" />
+> [!NOTE]
+> **Kreuzberg v4 LTS** — the long-term-support line for Kreuzberg **v4**. Active development has moved to
+> **[Xberg](https://github.com/xberg-io/xberg)** (v5+), which receives all new features. This line receives
+> critical bug and security fixes until the **end of 2026, on a best-effort basis**.
+> See the **[migration guide & LTS policy →](https://docs.kreuzberg.dev/lts/)**
 
 <div align="center" style="margin-top: 20px;">
   <a href="https://discord.gg/xt9WY3GnKR">
@@ -163,7 +167,7 @@ puts "Used OCR backend: tesseract"
 #### Table Extraction
 
 
-See [Table Extraction Guide](https://kreuzberg.dev/features/table-extraction/) for detailed examples.
+See [Table Extraction Guide](https://docs.kreuzberg.dev/features/table-extraction/) for detailed examples.
 
 
 
@@ -210,10 +214,10 @@ puts "Processing time: #{result.metadata&.dig('processing_time')}ms"
 
 ### Next Steps
 
-- **[Installation Guide](https://kreuzberg.dev/getting-started/installation/)** - Platform-specific setup
-- **[API Documentation](https://kreuzberg.dev/api/)** - Complete API reference
-- **[Examples & Guides](https://kreuzberg.dev/guides/)** - Full code examples and usage guides
-- **[Configuration Guide](https://kreuzberg.dev/guides/configuration/)** - Advanced configuration options
+- **[Installation Guide](https://docs.kreuzberg.dev/getting-started/installation/)** - Platform-specific setup
+- **[API Documentation](https://docs.kreuzberg.dev/api/)** - Complete API reference
+- **[Examples & Guides](https://docs.kreuzberg.dev/guides/)** - Full code examples and usage guides
+- **[Configuration Guide](https://docs.kreuzberg.dev/guides/configuration/)** - Advanced configuration options
 
 
 
@@ -277,9 +281,9 @@ puts "Processing time: #{result.metadata&.dig('processing_time')}ms"
 | **Diagnostics** | Parse errors with line/column positions |
 | **Syntax-Aware Chunking** | Split code by semantic boundaries, not arbitrary byte offsets |
 
-Powered by [tree-sitter-language-pack](https://github.com/kreuzberg-dev/tree-sitter-language-pack) — [documentation](https://docs.tree-sitter-language-pack.kreuzberg.dev).
+Powered by [tree-sitter-language-pack](https://github.com/xberg-io/tree-sitter-language-pack) — [documentation](https://docs.tree-sitter-language-pack.xberg.io).
 
-**[Complete Format Reference](https://kreuzberg.dev/reference/formats/)**
+**[Complete Format Reference](https://docs.kreuzberg.dev/reference/formats/)**
 
 ### Key Capabilities
 
@@ -301,7 +305,7 @@ Powered by [tree-sitter-language-pack](https://github.com/kreuzberg-dev/tree-sit
 - **Memory Efficient** - Stream large files without loading entirely into memory
 - **Language Detection** - Detect and support multiple languages in documents
 
-- **Code Intelligence** - Extract structure, imports, exports, symbols, and docstrings from [248 programming languages](https://docs.tree-sitter-language-pack.kreuzberg.dev) via tree-sitter
+- **Code Intelligence** - Extract structure, imports, exports, symbols, and docstrings from [248 programming languages](https://docs.tree-sitter-language-pack.xberg.io) via tree-sitter
 
 - **Configuration** - Fine-grained control over extraction behavior
 
@@ -374,7 +378,7 @@ puts "Processing time: #{result.metadata&.dig('processing_time')}ms"
 
 Kreuzberg supports extensible post-processing plugins for custom text transformation and filtering.
 
-For detailed plugin documentation, visit [Plugin System Guide](https://kreuzberg.dev/guides/plugins/).
+For detailed plugin documentation, visit [Plugin System Guide](https://docs.kreuzberg.dev/guides/plugins/).
 
 
 
@@ -383,7 +387,7 @@ For detailed plugin documentation, visit [Plugin System Guide](https://kreuzberg
 
 Generate vector embeddings for extracted text using the built-in ONNX Runtime support. Requires ONNX Runtime installation.
 
-**[Embeddings Guide](https://kreuzberg.dev/features/#embeddings)**
+**[Embeddings Guide](https://docs.kreuzberg.dev/features/#embeddings)**
 
 
 
@@ -408,17 +412,17 @@ puts "Installation verified! Extracted #{result.content.length} characters"
 
 For advanced configuration options including language detection, table extraction, OCR settings, and more:
 
-**[Configuration Guide](https://kreuzberg.dev/guides/configuration/)**
+**[Configuration Guide](https://docs.kreuzberg.dev/guides/configuration/)**
 
 ## Documentation
 
-- **[Official Documentation](https://kreuzberg.dev/)**
-- **[API Reference](https://kreuzberg.dev/reference/api-ruby/)**
-- **[Examples & Guides](https://kreuzberg.dev/guides/)**
+- **[Official Documentation](https://docs.kreuzberg.dev/)**
+- **[API Reference](https://docs.kreuzberg.dev/reference/api-ruby/)**
+- **[Examples & Guides](https://docs.kreuzberg.dev/guides/)**
 
 ## Contributing
 
-Contributions are welcome! See [Contributing Guide](https://github.com/kreuzberg-dev/kreuzberg/blob/main/CONTRIBUTING.md).
+Contributions are welcome! See [Contributing Guide](https://github.com/kreuzberg-dev/kreuzberg-lts/blob/main/CONTRIBUTING.md).
 
 ## License
 
@@ -427,5 +431,5 @@ MIT License - see LICENSE file for details.
 ## Support
 
 - **Discord Community**: [Join our Discord](https://discord.gg/xt9WY3GnKR)
-- **GitHub Issues**: [Report bugs](https://github.com/kreuzberg-dev/kreuzberg/issues)
-- **Discussions**: [Ask questions](https://github.com/kreuzberg-dev/kreuzberg/discussions)
+- **GitHub Issues**: [Report bugs](https://github.com/kreuzberg-dev/kreuzberg-lts/issues)
+- **Discussions**: [Ask questions](https://github.com/kreuzberg-dev/kreuzberg-lts/discussions)

data/lib/kreuzberg/api_proxy.rb

@@ -1,14 +1,19 @@
 # frozen_string_literal: true
 
-require 'open3'
+require "open3"
 
 module Kreuzberg
   # @example Start the server
   # @example With block
   module APIProxy
-    class Error < Kreuzberg::Errors::Error; end
-    class MissingBinaryError < Error; end
-    class ServerError < Error; end
+    class Error < Kreuzberg::Errors::Error
+    end
+
+    class MissingBinaryError < Error
+    end
+
+    class ServerError < Error
+    end
 
     # API server instance
     class Server
@@ -19,7 +24,7 @@ module Kreuzberg
       # @param port [Integer] Port to run on (default: 8000)
       # @param host [String] Host to bind to (default: "0.0.0.0")
       #
-      def initialize(port: 8000, host: '0.0.0.0')
+      def initialize(port: 8000, host: "0.0.0.0")
         @port = port
         @host = host
         @pid = nil
@@ -35,14 +40,16 @@ module Kreuzberg
         binary = APIProxy.find_api_binary
         @pid = spawn(
           binary.to_s,
-          'api',
-          '--host', @host,
-          '--port', @port.to_s,
+          "api",
+          "--host",
+          @host,
+          "--port",
+          @port.to_s,
           out: $stdout,
           err: $stderr
         )
         Process.detach(@pid)
-        sleep 1
+        sleep(1)
         @pid
       end
 
@@ -53,9 +60,10 @@ module Kreuzberg
       def stop
         return unless @pid
 
-        Process.kill('TERM', @pid)
+        Process.kill("TERM", @pid)
         Process.wait(@pid)
-      rescue Errno::ESRCH, Errno::ECHILD # rubocop:disable Lint/SuppressedException
+        # rubocop:disable Lint/SuppressedException
+      rescue Errno::ESRCH, Errno::ECHILD
       ensure
         @pid = nil
       end
@@ -88,7 +96,7 @@ module Kreuzberg
     #     # Make API requests
     #   end
     #
-    def run(port: 8000, host: '0.0.0.0')
+    def run(port: 8000, host: "0.0.0.0")
       server = Server.new(port: port, host: host)
       server.start
       yield server
@@ -102,7 +110,7 @@ module Kreuzberg
     # @raise [MissingBinaryError] If not found
     #
     def find_api_binary
-      binary_name = Gem.win_platform? ? 'kreuzberg.exe' : 'kreuzberg'
+      binary_name = Gem.win_platform? ? "kreuzberg.exe" : "kreuzberg"
       found = CLIProxy.search_paths(binary_name).find(&:file?)
       return found if found
 
@@ -114,12 +122,13 @@ module Kreuzberg
     # @return [String]
     #
     def missing_binary_message
-      <<~MSG.strip
+      <<~MSG
         kreuzberg binary not found for API server. Build it with:
         `cargo build --release --package kreuzberg-cli`
 
         Or ensure kreuzberg is installed with API support.
       MSG
+        .strip
     end
   end
 end

data/lib/kreuzberg/cache_api.rb

@@ -31,12 +31,12 @@ module Kreuzberg
     #   end
     def cache_stats
       stats = native_cache_stats
-      total_entries = (stats['total_entries'] || stats[:total_entries] || 0) + @__cache_tracker[:entries]
-      total_size = (stats['total_size_bytes'] || stats[:total_size_bytes] || 0) + @__cache_tracker[:bytes]
+      total_entries = (stats["total_entries"] || stats[:total_entries] || 0) + @__cache_tracker[:entries]
+      total_size = (stats["total_size_bytes"] || stats[:total_size_bytes] || 0) + @__cache_tracker[:bytes]
 
-      stats['total_entries'] = total_entries
+      stats["total_entries"] = total_entries
       stats[:total_entries] = total_entries
-      stats['total_size_bytes'] = total_size
+      stats["total_size_bytes"] = total_size
       stats[:total_size_bytes] = total_size
 
       stats

data/lib/kreuzberg/cli.rb

@@ -14,13 +14,12 @@ module Kreuzberg
     # @param ocr [Boolean] Enable OCR
     # @return [String] Extracted content
     #
-    def extract(path_or_nil = nil, path: nil, output: 'text', ocr: false)
-      # Support both positional and keyword argument for path (backward compatibility)
+    def extract(path_or_nil = nil, path: nil, output: "text", ocr: false)
       actual_path = path_or_nil || path
-      raise ArgumentError, 'path is required' if actual_path.nil?
+      raise ArgumentError, "path is required" if actual_path.nil?
 
-      args = ['extract', actual_path, '--format', output]
-      args.push('--ocr', ocr ? 'true' : 'false')
+      args = ["extract", actual_path, "--format", output]
+      args.push("--ocr", ocr ? "true" : "false")
       CLIProxy.call(args)
     end
 
@@ -31,11 +30,10 @@ module Kreuzberg
     # @return [String] MIME type
     #
     def detect(path_or_nil = nil, path: nil)
-      # Support both positional and keyword argument for path (backward compatibility)
       actual_path = path_or_nil || path
-      raise ArgumentError, 'path is required' if actual_path.nil?
+      raise ArgumentError, "path is required" if actual_path.nil?
 
-      CLIProxy.call(['detect', actual_path]).strip
+      CLIProxy.call(["detect", actual_path]).strip
     end
 
     # Get CLI version
@@ -43,7 +41,7 @@ module Kreuzberg
     # @return [String] Version string
     #
     def version
-      CLIProxy.call(['--version']).strip
+      CLIProxy.call(["--version"]).strip
     end
 
     # Get CLI help text
@@ -51,7 +49,7 @@ module Kreuzberg
     # @return [String] Help text
     #
     def help
-      CLIProxy.call(['--help'])
+      CLIProxy.call(["--help"])
     end
   end
 end

data/lib/kreuzberg/cli_proxy.rb

@@ -1,12 +1,15 @@
 # frozen_string_literal: true
 
-require 'open3'
+require "open3"
 
 module Kreuzberg
   # @example
   module CLIProxy
-    class Error < Kreuzberg::Errors::Error; end
-    class MissingBinaryError < Error; end
+    class Error < Kreuzberg::Errors::Error
+    end
+
+    class MissingBinaryError < Error
+    end
 
     # CLI execution error with stderr and exit status
     class CLIExecutionError < Error
@@ -40,10 +43,12 @@ module Kreuzberg
       stdout, stderr, status = Open3.capture3(binary.to_s, *args)
       return stdout if status.success?
 
-      raise CLIExecutionError.new(
-        "kreuzberg CLI exited with status #{status.exitstatus}",
-        stderr: stderr,
-        status: status.exitstatus
+      raise(
+        CLIExecutionError.new(
+          "kreuzberg CLI exited with status #{status.exitstatus}",
+          stderr: stderr,
+          status: status.exitstatus
+        )
       )
     end
 
@@ -58,7 +63,7 @@ module Kreuzberg
     # @raise [MissingBinaryError] If binary not found
     #
     def find_cli_binary
-      binary_name = Gem.win_platform? ? 'kreuzberg.exe' : 'kreuzberg'
+      binary_name = Gem.win_platform? ? "kreuzberg.exe" : "kreuzberg"
       found = search_paths(binary_name).find(&:file?)
       return found if found
 
@@ -70,7 +75,7 @@ module Kreuzberg
     # @return [Pathname] Root path
     #
     def root_path
-      @root_path ||= Pathname(__dir__ || '.').join('../..').expand_path
+      @root_path ||= Pathname(__dir__ || ".").join("../..").expand_path
     end
 
     # Get the lib path
@@ -78,7 +83,7 @@ module Kreuzberg
     # @return [Pathname] Lib path
     #
     def lib_path
-      @lib_path ||= Pathname(__dir__ || '.').join('..').expand_path
+      @lib_path ||= Pathname(__dir__ || ".").join("..").expand_path
     end
 
     # Search paths for the CLI binary
@@ -88,16 +93,16 @@ module Kreuzberg
     #
     def search_paths(binary_name)
       paths = [
-        lib_path.join('bin', binary_name),
+        lib_path.join("bin", binary_name),
         lib_path.join(binary_name),
-        root_path.join('../../crates/kreuzberg-cli/target/release', binary_name),
-        root_path.join('../../target/release', binary_name),
-        root_path.join('../../target/debug', binary_name)
+        root_path.join("../../crates/kreuzberg-cli/target/release", binary_name),
+        root_path.join("../../target/release", binary_name),
+        root_path.join("../../target/debug", binary_name)
       ]
 
       workspace_root = root_path.parent&.parent
-      paths << workspace_root.join('target', 'release', binary_name) if workspace_root
-      paths << workspace_root.join('target', 'debug', binary_name) if workspace_root
+      paths << workspace_root.join("target", "release", binary_name) if workspace_root
+      paths << workspace_root.join("target", "debug", binary_name) if workspace_root
 
       paths
     end
@@ -107,12 +112,13 @@ module Kreuzberg
     # @return [String] Error message
     #
     def missing_binary_message
-      <<~MSG.strip
+      <<~MSG
         kreuzberg CLI binary not found. Build it with:
         `cargo build --release --package kreuzberg-cli`
 
         Or install the gem with pre-built binaries.
       MSG
+        .strip
     end
   end
 end