slatedb 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 06b42247a14342b9550a9a10641900546ea79fd52001f4b98798e028f7f03cd4
+  data.tar.gz: f83cd6b19a0f4dea849e628068c8d3e4af338b0efe320870cc8ddd5e3d55fb8c
+SHA512:
+  metadata.gz: 6946b78b9f03073aee23c604443fa38fbe728c2298cba21b621d632c2d1e93d909fb900571eb976d638ac93c4e1efdfa372eb5fefd90d3e3db250f02cf3343b4
+  data.tar.gz: f161ed22a27ef14b899ec557bfdb4dadf39cc928f35e771a6e5025cc5840210109f05ea080349b7d57dc27b278c816c8e2bd842d1854937800ee772139c68a0f

data/Cargo.toml

@@ -0,0 +1,9 @@
+[workspace]
+members = ["ext/slatedb"]
+resolver = "2"
+
+[profile.release]
+strip = true
+
+[profile.dev]
+strip = true

data/LICENSE

@@ -0,0 +1,176 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to the Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS

data/README.md

@@ -0,0 +1,404 @@
+# SlateDB Ruby
+
+Ruby bindings for [SlateDB](https://slatedb.io), a cloud-native embedded key-value store built on object storage.
+
+[![Build status](https://badge.buildkite.com/a7ae51f3a0bc7809cf66981641ec47b3c70db8cf349a5e462f.svg)](https://buildkite.com/catkins-test/slatedb-rb)
+
+## Thread Safety
+
+**SlateDB is fully thread-safe and optimized for concurrent access.**
+
+- The `Database` class can be safely shared across multiple Ruby threads
+- All operations (get, put, delete, scan, transactions) are thread-safe
+- The Ruby bindings release the Global VM Lock (GVL) during I/O operations, allowing other Ruby threads to run concurrently
+- Perfect for use with multi-threaded Ruby applications like Puma, Sidekiq, and concurrent test suites
+
+```ruby
+db = SlateDb::Database.open("/tmp/mydb")
+
+# Safe to use from multiple threads
+threads = 10.times.map do |i|
+  Thread.new do
+    db.put("key-#{i}", "value-#{i}")
+    db.get("key-#{i}")
+  end
+end
+
+threads.each(&:join)
+```
+
+**Implementation details:**
+- The underlying SlateDB library uses `Arc` (atomic reference counting) and `RwLock` for internal state management
+- I/O operations release the Ruby GVL using `rb_thread_call_without_gvl`, preventing blocking other threads
+- A shared Tokio multi-threaded runtime handles all async operations efficiently
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'slatedb'
+```
+
+And then execute:
+
+```bash
+bundle install
+```
+
+Or install it yourself as:
+
+```bash
+gem install slatedb
+```
+
+## Usage
+
+### Basic Operations
+
+```ruby
+require 'slatedb'
+
+# Open a database with in-memory storage (for testing)
+db = SlateDb::Database.open("/tmp/mydb")
+
+# Store a value
+db.put("hello", "world")
+
+# Retrieve a value
+value = db.get("hello")  # => "world"
+
+# Delete a value
+db.delete("hello")
+
+# Close the database
+db.close
+```
+
+### Block Form (Recommended)
+
+The block form automatically closes the database when the block exits:
+
+```ruby
+SlateDb::Database.open("/tmp/mydb") do |db|
+  db.put("key", "value")
+  db.get("key")  # => "value"
+end  # automatically closed
+```
+
+### Persistent Storage
+
+For persistent storage, provide an object store URL:
+
+```ruby
+# Local filesystem
+SlateDb::Database.open("/tmp/mydb", url: "file:///tmp/mydb") do |db|
+  db.put("key", "value")
+end
+
+# S3 (requires AWS credentials)
+SlateDb::Database.open("mydb", url: "s3://mybucket/path") do |db|
+  db.put("key", "value")
+end
+
+# Azure Blob Storage
+SlateDb::Database.open("mydb", url: "az://container/path") do |db|
+  db.put("key", "value")
+end
+
+# Google Cloud Storage
+SlateDb::Database.open("mydb", url: "gs://bucket/path") do |db|
+  db.put("key", "value")
+end
+```
+
+#### Cloud Storage Credentials
+
+SlateDB uses the [object_store](https://docs.rs/object_store) crate, which automatically discovers credentials from standard environment variables and configuration files:
+
+**AWS S3:**
+- Environment variables: `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, `AWS_SESSION_TOKEN`, `AWS_REGION`
+- Credential files: `~/.aws/credentials`, `~/.aws/config`
+- IAM roles (when running on EC2/ECS/EKS)
+- Web identity tokens (for IRSA on EKS)
+
+**Azure Blob Storage:**
+- Environment variables: `AZURE_STORAGE_ACCOUNT_NAME`, `AZURE_STORAGE_ACCOUNT_KEY`, `AZURE_STORAGE_SAS_TOKEN`
+- Azure CLI credentials: `az login`
+- Managed Identity (when running on Azure)
+
+**Google Cloud Storage:**
+- Environment variables: `GOOGLE_SERVICE_ACCOUNT`, `GOOGLE_SERVICE_ACCOUNT_PATH`, `GOOGLE_SERVICE_ACCOUNT_KEY`
+- Application Default Credentials: `gcloud auth application-default login`
+- Service account key file: `GOOGLE_APPLICATION_CREDENTIALS=/path/to/key.json`
+
+Example with explicit AWS credentials:
+
+```ruby
+# Set credentials via environment
+ENV['AWS_ACCESS_KEY_ID'] = 'your-access-key'
+ENV['AWS_SECRET_ACCESS_KEY'] = 'your-secret-key'
+ENV['AWS_REGION'] = 'us-east-1'
+
+SlateDb::Database.open("mydb", url: "s3://mybucket/path") do |db|
+  db.put("key", "value")
+end
+```
+
+### Options
+
+#### Put Options
+
+```ruby
+# Set TTL (time-to-live) in milliseconds
+db.put("key", "value", ttl: 60_000)  # expires in 60 seconds
+
+# Don't wait for durability
+db.put("key", "value", await_durable: false)
+```
+
+#### Get Options
+
+```ruby
+# Filter by durability level
+db.get("key", durability_filter: "memory")
+db.get("key", durability_filter: "remote")
+
+# Include uncommitted data
+db.get("key", dirty: true)
+```
+
+#### Delete Options
+
+```ruby
+# Don't wait for durability
+db.delete("key", await_durable: false)
+```
+
+### Scanning
+
+Iterate over key ranges using the `scan` method:
+
+```ruby
+# Scan all keys from "a" onwards
+db.scan("a").each do |key, value|
+  puts "#{key}: #{value}"
+end
+
+# Scan a specific range [start, end)
+db.scan("a", "z").each do |key, value|
+  puts "#{key}: #{value}"
+end
+
+# Use Enumerable methods
+keys = db.scan("user:").map { |k, v| k }
+users = db.scan("user:").select { |k, v| v.include?("active") }
+
+# Convert to array
+all_entries = db.scan("").to_a
+```
+
+### Write Batches
+
+Perform multiple writes atomically:
+
+```ruby
+# Create a batch manually
+batch = SlateDb::WriteBatch.new
+batch.put("key1", "value1")
+batch.put("key2", "value2", ttl: 60_000)
+batch.delete("old_key")
+db.write(batch)
+
+# Or use the block helper
+db.batch do |b|
+  b.put("key1", "value1")
+  b.put("key2", "value2")
+  b.delete("old_key")
+end
+```
+
+### Transactions
+
+ACID transactions with snapshot or serializable isolation:
+
+```ruby
+# Block form (recommended) - auto-commits on success, rolls back on exception
+db.transaction do |txn|
+  balance = txn.get("balance").to_i
+  txn.put("balance", (balance - 100).to_s)
+  txn.put("withdrawal", "100")
+end
+
+# With serializable isolation for strict consistency
+db.transaction(isolation: :serializable) do |txn|
+  counter = txn.get("counter").to_i
+  txn.put("counter", (counter + 1).to_s)
+end
+
+# Manual transaction management
+txn = db.begin_transaction(isolation: :snapshot)
+txn.put("key", "value")
+txn.commit  # or txn.rollback
+```
+
+Transaction operations:
+
+```ruby
+db.transaction do |txn|
+  # Read
+  value = txn.get("key")
+  
+  # Write
+  txn.put("key", "value")
+  txn.put("expiring", "data", ttl: 30_000)
+  
+  # Delete
+  txn.delete("old_key")
+  
+  # Scan
+  txn.scan("prefix:").each do |k, v|
+    puts "#{k}: #{v}"
+  end
+end
+```
+
+### Snapshots
+
+Point-in-time consistent reads:
+
+```ruby
+# Block form (recommended)
+db.snapshot do |snap|
+  # All reads see the same consistent state
+  value1 = snap.get("key1")
+  value2 = snap.get("key2")
+  
+  snap.scan("prefix:").each do |k, v|
+    puts "#{k}: #{v}"
+  end
+end  # automatically closed
+
+# Manual management
+snap = db.snapshot
+value = snap.get("key")
+snap.close
+```
+
+### Reader (Read-Only Access)
+
+Open a database in read-only mode, useful for replicas:
+
+```ruby
+# Basic read-only access
+SlateDb::Reader.open("/tmp/mydb", url: "s3://bucket/path") do |reader|
+  value = reader.get("key")
+  
+  reader.scan("prefix:").each do |k, v|
+    puts "#{k}: #{v}"
+  end
+end
+
+# Open at a specific checkpoint
+SlateDb::Reader.open("/tmp/mydb", 
+                     url: "s3://bucket/path",
+                     checkpoint_id: "uuid-here") do |reader|
+  reader.get("key")
+end
+```
+
+### Admin Operations
+
+Administrative operations for database management:
+
+```ruby
+admin = SlateDb::Admin.new("/tmp/mydb", url: "s3://bucket/path")
+
+# Manifests
+json = admin.read_manifest           # Latest manifest as JSON
+json = admin.read_manifest(123)      # Specific manifest by ID
+json = admin.list_manifests          # List all manifests
+json = admin.list_manifests(start: 1, end_id: 10)  # Range query
+
+# Checkpoints
+result = admin.create_checkpoint(name: "backup-2024")
+# => { id: "uuid-string", manifest_id: 7 }
+
+checkpoints = admin.list_checkpoints
+checkpoints = admin.list_checkpoints(name: "backup")  # Filter by name
+
+admin.refresh_checkpoint("uuid", lifetime: 3600_000)  # Extend lifetime
+admin.delete_checkpoint("uuid")
+
+# Garbage Collection
+admin.run_gc                                    # Run with default settings
+admin.run_gc(min_age: 3600_000)                 # Set min age for all directories (1 hour)
+admin.run_gc(manifest_min_age: 86400_000)       # Custom age for manifest (1 day)
+admin.run_gc(wal_min_age: 60_000)               # Custom age for WAL (1 minute)
+admin.run_gc(compacted_min_age: 60_000)         # Custom age for compacted (1 minute)
+```
+
+### Flushing
+
+Ensure all writes are persisted:
+
+```ruby
+db.put("key", "value")
+db.flush
+```
+
+## Error Handling
+
+SlateDB defines several exception classes:
+
+```ruby
+begin
+  db.put("", "value")  # empty key
+rescue SlateDb::InvalidArgumentError => e
+  puts "Invalid argument: #{e.message}"
+rescue SlateDb::TransactionError => e
+  puts "Transaction conflict: #{e.message}"
+rescue SlateDb::Error => e
+  puts "SlateDB error: #{e.message}"
+end
+```
+
+Exception hierarchy:
+
+- `SlateDb::Error` - Base class (inherits from `StandardError`)
+  - `SlateDb::TransactionError` - Transaction conflicts
+  - `SlateDb::ClosedError` - Database has been closed
+  - `SlateDb::UnavailableError` - Storage/network unavailable
+  - `SlateDb::InvalidArgumentError` - Invalid arguments
+  - `SlateDb::DataError` - Data corruption or format errors
+  - `SlateDb::InternalError` - Internal errors
+
+## Requirements
+
+- Ruby 3.1+
+- Rust toolchain (for building from source)
+
+## Development
+
+After checking out the repo, run:
+
+```bash
+bundle install
+bundle exec rake compile
+bundle exec rake spec
+```
+
+To run specific tests:
+
+```bash
+bundle exec rspec spec/database_spec.rb
+bundle exec rspec spec/transaction_spec.rb
+```
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/catkins/slatedb-rb.
+
+## License
+
+Apache-2.0

data/ext/slatedb/Cargo.toml

@@ -0,0 +1,22 @@
+[package]
+name = "slatedb"
+version = "0.1.0"
+edition = "2021"
+publish = false
+license = "Apache-2.0"
+description = "Ruby bindings for SlateDB"
+
+[lib]
+name = "slatedb"
+crate-type = ["cdylib"]
+
+[dependencies]
+slatedb = "0.9"
+magnus = { version = "0.8", features = ["rb-sys"] }
+rb-sys = { version = "0.9", features = ["stable-api-compiled-fallback"] }
+tokio = { version = "1", features = ["rt-multi-thread", "sync"] }
+bytes = "1"
+object_store = "0.12"
+once_cell = "1"
+log = "0.4"
+uuid = "1"

data/ext/slatedb/extconf.rb

@@ -0,0 +1,6 @@
+# frozen_string_literal: true
+
+require "mkmf"
+require "rb_sys/mkmf"
+
+create_rust_makefile("slatedb/slatedb")