deltalake-rb 0.1.0

data/Cargo.toml

@@ -0,0 +1,6 @@
+[workspace]
+members = ["ext/deltalake"]
+resolver = "2"
+
+[profile.release]
+strip = true

data/LICENSE.txt

@@ -0,0 +1,179 @@
+Copyright (2020) QP Hou and a number of other contributors.  All rights reserved.
+
+
+                                 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 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 +1,110 @@
+# delta-ruby
+
+[Delta Lake](https://delta.io/) for Ruby
+
+Supports local files and Amazon S3
+
+[![Build Status](https://github.com/ankane/delta-ruby/actions/workflows/build.yml/badge.svg)](https://github.com/ankane/delta-ruby/actions)
+
+## Installation
+
+Add this line to your application’s Gemfile:
+
+```ruby
+gem "deltalake-rb"
+```
+
+It can take a few minutes to compile the gem.
+
+## Getting Started
+
+Write data
+
+```ruby
+df = Polars::DataFrame.new({"a" => [1, 2], "b" => [3.0, 4.0]})
+DeltaLake.write("./data/delta", df)
+```
+
+Load a table
+
+```ruby
+dt = DeltaLake::Table.new("./data/delta")
+df2 = dt.to_polars
+```
+
+Get a lazy frame
+
+```ruby
+lf = dt.to_polars(eager: false)
+```
+
+Append rows
+
+```ruby
+DeltaLake.write("./data/delta", df, mode: "append")
+```
+
+Overwrite a table
+
+```ruby
+DeltaLake.write("./data/delta", df, mode: "overwrite")
+```
+
+Delete rows
+
+```ruby
+dt.delete("a > 1")
+```
+
+Vacuum
+
+```ruby
+dt.vacuum(dry_run: false)
+```
+
+Load a previous version of a table
+
+```ruby
+dt = DeltaLake::Table.new("./data/delta", version: 1)
+# or
+dt.load_as_version(1)
+```
+
+Get metadata
+
+```ruby
+dt.metadata
+```
+
+Get the schema
+
+```ruby
+dt.schema
+```
+
+## API
+
+This library follows the [Delta Lake Python API](https://delta-io.github.io/delta-rs/) (with a few changes to make it more Ruby-like). You can follow Python tutorials and convert the code to Ruby in many cases. Feel free to open an issue if you run into problems.
+
+## History
+
+View the [changelog](https://github.com/ankane/delta-ruby/blob/master/CHANGELOG.md)
+
+## Contributing
+
+Everyone is encouraged to help improve this project. Here are a few ways you can help:
+
+- [Report bugs](https://github.com/ankane/delta-ruby/issues)
+- Fix bugs and [submit pull requests](https://github.com/ankane/delta-ruby/pulls)
+- Write, clarify, or fix documentation
+- Suggest or add new features
+
+To get started with development:
+
+```sh
+git clone https://github.com/ankane/delta-ruby.git
+cd delta-ruby
+bundle install
+bundle exec rake compile
+bundle exec rake test
+```

data/ext/deltalake/Cargo.toml

@@ -0,0 +1,21 @@
+[package]
+name = "deltalake"
+version = "0.1.0"
+license = "Apache-2.0"
+authors = ["Andrew Kane <andrew@ankane.org>"]
+edition = "2021"
+rust-version = "1.70.0"
+publish = false
+
+[lib]
+crate-type = ["cdylib"]
+
+[dependencies]
+arrow = { version = "52", features = ["ffi"] }
+arrow-schema = { version = "52", features = ["serde"] }
+chrono = "0.4"
+deltalake = { version = "=0.21.0", features = ["datafusion", "s3"] }
+magnus = "0.7"
+serde = "1"
+serde_json = "1"
+tokio = { version = "1", features = ["rt-multi-thread"] }

data/ext/deltalake/extconf.rb

@@ -0,0 +1,4 @@
+require "mkmf"
+require "rb_sys/mkmf"
+
+create_rust_makefile("deltalake/deltalake")

data/ext/deltalake/src/error.rs

@@ -0,0 +1,98 @@
+use arrow_schema::ArrowError;
+use deltalake::{errors::DeltaTableError, ObjectStoreError};
+use magnus::{exception, Error, Module, RModule, Ruby};
+use std::borrow::Cow;
+
+macro_rules! create_exception {
+    ($type:ident, $name:expr) => {
+        pub struct $type {}
+
+        impl $type {
+            pub fn new_err<T>(message: T) -> Error
+            where
+                T: Into<Cow<'static, str>>,
+            {
+                let class = Ruby::get()
+                    .unwrap()
+                    .class_object()
+                    .const_get::<_, RModule>("DeltaLake")
+                    .unwrap()
+                    .const_get($name)
+                    .unwrap();
+                Error::new(class, message)
+            }
+        }
+    };
+}
+
+create_exception!(DeltaError, "Error");
+create_exception!(TableNotFoundError, "TableNotFoundError");
+create_exception!(DeltaProtocolError, "DeltaProtocolError");
+create_exception!(CommitFailedError, "CommitFailedError");
+create_exception!(SchemaMismatchError, "SchemaMismatchError");
+
+fn inner_to_rb_err(err: DeltaTableError) -> Error {
+    match err {
+        DeltaTableError::NotATable(msg) => TableNotFoundError::new_err(msg),
+        DeltaTableError::InvalidTableLocation(msg) => TableNotFoundError::new_err(msg),
+
+        // protocol errors
+        DeltaTableError::InvalidJsonLog { .. } => DeltaProtocolError::new_err(err.to_string()),
+        DeltaTableError::InvalidStatsJson { .. } => DeltaProtocolError::new_err(err.to_string()),
+        DeltaTableError::InvalidData { violations } => {
+            DeltaProtocolError::new_err(format!("Invariant violations: {:?}", violations))
+        }
+
+        // commit errors
+        DeltaTableError::Transaction { source } => CommitFailedError::new_err(source.to_string()),
+
+        // ruby exceptions
+        DeltaTableError::ObjectStore { source } => object_store_to_rb(source),
+        DeltaTableError::Io { source } => Error::new(exception::io_error(), source.to_string()),
+
+        DeltaTableError::Arrow { source } => arrow_to_rb(source),
+
+        _ => DeltaError::new_err(err.to_string()),
+    }
+}
+
+fn object_store_to_rb(err: ObjectStoreError) -> Error {
+    match err {
+        ObjectStoreError::NotFound { .. } => Error::new(exception::io_error(), err.to_string()),
+        ObjectStoreError::Generic { source, .. }
+            if source.to_string().contains("AWS_S3_ALLOW_UNSAFE_RENAME") =>
+        {
+            DeltaProtocolError::new_err(source.to_string())
+        }
+        _ => Error::new(exception::io_error(), err.to_string()),
+    }
+}
+
+fn arrow_to_rb(err: ArrowError) -> Error {
+    match err {
+        ArrowError::IoError(msg, _) => Error::new(exception::io_error(), msg),
+        ArrowError::DivideByZero => Error::new(exception::arg_error(), "division by zero"),
+        ArrowError::InvalidArgumentError(msg) => Error::new(exception::arg_error(), msg),
+        ArrowError::NotYetImplemented(msg) => Error::new(exception::not_imp_error(), msg),
+        ArrowError::SchemaError(msg) => SchemaMismatchError::new_err(msg),
+        other => Error::new(exception::runtime_error(), other.to_string()),
+    }
+}
+
+pub enum RubyError {
+    DeltaTable(DeltaTableError),
+}
+
+impl From<DeltaTableError> for RubyError {
+    fn from(err: DeltaTableError) -> Self {
+        RubyError::DeltaTable(err)
+    }
+}
+
+impl From<RubyError> for Error {
+    fn from(value: RubyError) -> Self {
+        match value {
+            RubyError::DeltaTable(err) => inner_to_rb_err(err),
+        }
+    }
+}