dedup_csv 0.1.1-x64-mingw32

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 1dcbe3b008e5b30deb07a50b0b705bbbaed20483986584883c7172f35886e277
+  data.tar.gz: c99bbe5a65cde9b55dd214a3b9e51f7d67309a3e39a1f7ad7a84faddc4efd9f1
+SHA512:
+  metadata.gz: 3a8d7b974095956d59f6dc33120cb9cd8b70c67b01a39878094a607f0c9f1e3054a6ce9f3f1e36efbc32dc6bb8a1572f9057c1b3b32b6eaaf8ba36539b080ccb
+  data.tar.gz: 3119e73b752f6cdcff11d1bbfc4ac8e0670b98e6f109450a828152db4753da946a566a428e6136d0829671c0ea648445e9edad494041d8d661817c50546707f4

data/.rspec

@@ -0,0 +1,3 @@
+--format documentation
+--color
+--require spec_helper

data/.rubocop.yml

@@ -0,0 +1,24 @@
+AllCops:
+  TargetRubyVersion: 2.6
+  SuggestExtensions: false
+  NewCops: enable
+
+Style/StringLiterals:
+  Enabled: true
+  EnforcedStyle: single_quotes
+
+Style/StringLiteralsInInterpolation:
+  Enabled: true
+  EnforcedStyle: double_quotes
+
+Layout/LineLength:
+  Max: 120
+
+Metrics/BlockLength:
+  Max: 120
+
+
+
+
+
+

data/Cargo.lock

@@ -0,0 +1,424 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 3
+
+[[package]]
+name = "aho-corasick"
+version = "1.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e60d3430d3a69478ad0993f19238d2df97c507009a52b3c10addcd7f6bcb916"
+dependencies = [
+ "memchr",
+]
+
+[[package]]
+name = "bindgen"
+version = "0.69.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a00dc851838a2120612785d195287475a3ac45514741da670b735818822129a0"
+dependencies = [
+ "bitflags",
+ "cexpr",
+ "clang-sys",
+ "itertools",
+ "lazy_static",
+ "lazycell",
+ "proc-macro2",
+ "quote",
+ "regex",
+ "rustc-hash",
+ "shlex",
+ "syn",
+]
+
+[[package]]
+name = "bitflags"
+version = "2.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b048fb63fd8b5923fc5aa7b340d8e156aec7ec02f0c78fa8a6ddc2613f6f71de"
+
+[[package]]
+name = "cexpr"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6fac387a98bb7c37292057cffc56d62ecb629900026402633ae9160df93a8766"
+dependencies = [
+ "nom",
+]
+
+[[package]]
+name = "cfg-if"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
+
+[[package]]
+name = "clang-sys"
+version = "1.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0b023947811758c97c59bf9d1c188fd619ad4718dcaa767947df1cadb14f39f4"
+dependencies = [
+ "glob",
+ "libc",
+ "libloading",
+]
+
+[[package]]
+name = "csv"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ac574ff4d437a7b5ad237ef331c17ccca63c46479e5b5453eb8e10bb99a759fe"
+dependencies = [
+ "csv-core",
+ "itoa",
+ "ryu",
+ "serde",
+]
+
+[[package]]
+name = "csv-core"
+version = "0.1.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5efa2b3d7902f4b634a20cae3c9c4e6209dc4779feb6863329607560143efa70"
+dependencies = [
+ "memchr",
+]
+
+[[package]]
+name = "dedup_csv"
+version = "0.1.0"
+dependencies = [
+ "csv",
+ "eyre",
+ "magnus",
+]
+
+[[package]]
+name = "either"
+version = "1.13.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "60b1af1c220855b6ceac025d3f6ecdd2b7c4894bfe9cd9bda4fbb4bc7c0d4cf0"
+
+[[package]]
+name = "eyre"
+version = "0.6.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7cd915d99f24784cdc19fd37ef22b97e3ff0ae756c7e492e9fbfe897d61e2aec"
+dependencies = [
+ "indenter",
+ "once_cell",
+]
+
+[[package]]
+name = "glob"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d2fabcfbdc87f4758337ca535fb41a6d701b65693ce38287d856d1674551ec9b"
+
+[[package]]
+name = "indenter"
+version = "0.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ce23b50ad8242c51a442f3ff322d56b02f08852c77e4c0b4d3fd684abc89c683"
+
+[[package]]
+name = "itertools"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ba291022dbbd398a455acf126c1e341954079855bc60dfdda641363bd6922569"
+dependencies = [
+ "either",
+]
+
+[[package]]
+name = "itoa"
+version = "1.0.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "49f1f14873335454500d59611f1cf4a4b0f786f9ac11f4312a78e4cf2566695b"
+
+[[package]]
+name = "lazy_static"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe"
+
+[[package]]
+name = "lazycell"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "830d08ce1d1d941e6b30645f1a0eb5643013d835ce3779a5fc208261dbe10f55"
+
+[[package]]
+name = "libc"
+version = "0.2.155"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "97b3888a4aecf77e811145cadf6eef5901f4782c53886191b2f693f24761847c"
+
+[[package]]
+name = "libloading"
+version = "0.8.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e310b3a6b5907f99202fcdb4960ff45b93735d7c7d96b760fcff8db2dc0e103d"
+dependencies = [
+ "cfg-if",
+ "windows-targets",
+]
+
+[[package]]
+name = "magnus"
+version = "0.7.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3d87ae53030f3a22e83879e666cb94e58a7bdf31706878a0ba48752994146dab"
+dependencies = [
+ "magnus-macros",
+ "rb-sys",
+ "rb-sys-env",
+ "seq-macro",
+]
+
+[[package]]
+name = "magnus-macros"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5968c820e2960565f647819f5928a42d6e874551cab9d88d75e3e0660d7f71e3"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "memchr"
+version = "2.7.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "78ca9ab1a0babb1e7d5695e3530886289c18cf2f87ec19a575a0abdce112e3a3"
+
+[[package]]
+name = "minimal-lexical"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a"
+
+[[package]]
+name = "nom"
+version = "7.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d273983c5a657a70a3e8f2a01329822f3b8c8172b73826411a55751e404a0a4a"
+dependencies = [
+ "memchr",
+ "minimal-lexical",
+]
+
+[[package]]
+name = "once_cell"
+version = "1.19.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3fdb12b2476b595f9358c5161aa467c2438859caa136dec86c26fdd2efe17b92"
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.86"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5e719e8df665df0d1c8fbfd238015744736151d4445ec0836b8e628aae103b77"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.36"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fa76aaf39101c457836aec0ce2316dbdc3ab723cdda1c6bd4e6ad4208acaca7"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "rb-sys"
+version = "0.9.98"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8914b2e6af10bd50dd7aaac8c5146872d3924d6012929b4ff504e988f6badd24"
+dependencies = [
+ "rb-sys-build",
+]
+
+[[package]]
+name = "rb-sys-build"
+version = "0.9.98"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "12af68c9757d419b82d65a12b5db538990dfe9416049fea3f0ba4b9a8ca108cd"
+dependencies = [
+ "bindgen",
+ "lazy_static",
+ "proc-macro2",
+ "quote",
+ "regex",
+ "shell-words",
+ "syn",
+]
+
+[[package]]
+name = "rb-sys-env"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a35802679f07360454b418a5d1735c89716bde01d35b1560fc953c1415a0b3bb"
+
+[[package]]
+name = "regex"
+version = "1.10.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b91213439dad192326a0d7c6ee3955910425f441d7038e0d6933b0aec5c4517f"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-automata",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-automata"
+version = "0.4.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "38caf58cc5ef2fed281f89292ef23f6365465ed9a41b7a7754eb4e26496c92df"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-syntax"
+version = "0.8.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7a66a03ae7c801facd77a29370b4faec201768915ac14a721ba36f20bc9c209b"
+
+[[package]]
+name = "rustc-hash"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2"
+
+[[package]]
+name = "ryu"
+version = "1.0.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f3cb5ba0dc43242ce17de99c180e96db90b235b8a9fdc9543c96d2209116bd9f"
+
+[[package]]
+name = "seq-macro"
+version = "0.3.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a3f0bf26fd526d2a95683cd0f87bf103b8539e2ca1ef48ce002d67aad59aa0b4"
+
+[[package]]
+name = "serde"
+version = "1.0.204"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bc76f558e0cbb2a839d37354c575f1dc3fdc6546b5be373ba43d95f231bf7c12"
+dependencies = [
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_derive"
+version = "1.0.204"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e0cd7e117be63d3c3678776753929474f3b04a43a080c744d6b0ae2a8c28e222"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "shell-words"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "24188a676b6ae68c3b2cb3a01be17fbf7240ce009799bb56d5b1409051e78fde"
+
+[[package]]
+name = "shlex"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
+
+[[package]]
+name = "syn"
+version = "2.0.71"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b146dcf730474b4bcd16c311627b31ede9ab149045db4d6088b3becaea046462"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b"
+
+[[package]]
+name = "windows-targets"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973"
+dependencies = [
+ "windows_aarch64_gnullvm",
+ "windows_aarch64_msvc",
+ "windows_i686_gnu",
+ "windows_i686_gnullvm",
+ "windows_i686_msvc",
+ "windows_x86_64_gnu",
+ "windows_x86_64_gnullvm",
+ "windows_x86_64_msvc",
+]
+
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3"
+
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469"
+
+[[package]]
+name = "windows_i686_gnu"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b"
+
+[[package]]
+name = "windows_i686_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66"
+
+[[package]]
+name = "windows_i686_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66"
+
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78"
+
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d"
+
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"

data/Cargo.toml

@@ -0,0 +1,7 @@
+# This Cargo.toml is here to let externals tools (IDEs, etc.) know that this is
+# a Rust project. Your extensions dependencies should be added to the Cargo.toml
+# in the ext/ directory.
+
+[workspace]
+members = ["./ext/dedup_csv"]
+resolver = "2"

data/Gemfile

@@ -0,0 +1,15 @@
+# frozen_string_literal: true
+
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in dedup_csv.gemspec
+gemspec
+
+gem 'rake', '~> 13.0'
+
+gem 'rake-compiler'
+gem 'rb_sys', '~> 0.9.63'
+
+gem 'rspec', '~> 3.0'
+
+gem 'rubocop', '~> 1.21'

data/Gemfile.lock

@@ -0,0 +1,70 @@
+PATH
+  remote: .
+  specs:
+    dedup_csv (0.1.1)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    ast (2.4.2)
+    diff-lcs (1.5.1)
+    json (2.7.2)
+    language_server-protocol (3.17.0.3)
+    parallel (1.25.1)
+    parser (3.3.4.0)
+      ast (~> 2.4.1)
+      racc
+    racc (1.8.0)
+    rainbow (3.1.1)
+    rake (13.2.1)
+    rake-compiler (1.2.7)
+      rake
+    rb_sys (0.9.98)
+    regexp_parser (2.9.2)
+    rexml (3.3.2)
+      strscan
+    rspec (3.13.0)
+      rspec-core (~> 3.13.0)
+      rspec-expectations (~> 3.13.0)
+      rspec-mocks (~> 3.13.0)
+    rspec-core (3.13.0)
+      rspec-support (~> 3.13.0)
+    rspec-expectations (3.13.1)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-mocks (3.13.1)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-support (3.13.1)
+    rubocop (1.65.0)
+      json (~> 2.3)
+      language_server-protocol (>= 3.17.0)
+      parallel (~> 1.10)
+      parser (>= 3.3.0.2)
+      rainbow (>= 2.2.2, < 4.0)
+      regexp_parser (>= 2.4, < 3.0)
+      rexml (>= 3.2.5, < 4.0)
+      rubocop-ast (>= 1.31.1, < 2.0)
+      ruby-progressbar (~> 1.7)
+      unicode-display_width (>= 2.4.0, < 3.0)
+    rubocop-ast (1.31.3)
+      parser (>= 3.3.1.0)
+    ruby-progressbar (1.13.0)
+    strscan (3.1.0)
+    unicode-display_width (2.5.0)
+
+PLATFORMS
+  arm64-darwin-22
+  arm64-darwin-23
+  x86_64-linux
+
+DEPENDENCIES
+  dedup_csv!
+  rake (~> 13.0)
+  rake-compiler
+  rb_sys (~> 0.9.63)
+  rspec (~> 3.0)
+  rubocop (~> 1.21)
+
+BUNDLED WITH
+   2.4.4

data/README.md

@@ -0,0 +1,20 @@
+# DedupCsv
+
+Given 2 CSV files, this gem will create a third CSV file that contains rows from the first CSV file that are not present in the second CSV file.
+
+## Installation
+
+```bash
+gem install dedup_csv
+```
+
+## Usage
+
+```irb
+require 'dedup_csv/3.2/dedup_csv'
+DedupCsv.dedup('file1.csv', 'file2.csv', 'output.csv')
+```
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/kingsleyh/dedup_csv.

data/Rakefile

@@ -0,0 +1,41 @@
+# frozen_string_literal: true
+
+require 'bundler/gem_tasks'
+require 'rspec/core/rake_task'
+
+RSpec::Core::RakeTask.new(:spec)
+
+require 'rubocop/rake_task'
+
+RuboCop::RakeTask.new
+
+require 'rb_sys/extensiontask'
+
+task build: :compile
+
+spec = Bundler.load_gemspec('dedup_csv.gemspec')
+# spec.requirements.clear
+# spec.required_ruby_version = nil
+# spec.required_rubygems_version = nil
+# spec.extensions.clear
+# spec.files -= Dir['ext/**/*']
+
+Rake::ExtensionTask.new('dedup_csv', spec) do |c|
+  c.lib_dir = 'lib/dedup_csv'
+  c.cross_compile = true
+  c.cross_platform = %w[
+    aarch64-linux
+    arm64-darwin
+    x64-mingw-ucrt
+    x64-mingw32
+    x86_64-darwin
+    x86_64-linux
+    x86_64-linux-musl
+  ]
+end
+
+RbSys::ExtensionTask.new('dedup_csv') do |ext|
+  ext.lib_dir = 'lib/dedup_csv'
+end
+
+task default: %i[compile spec rubocop]

data/ext/dedup_csv/Cargo.toml

@@ -0,0 +1,14 @@
+[package]
+name = "dedup_csv"
+version = "0.1.0"
+edition = "2021"
+authors = ["kingsley.hendrickse <kingsley.hendrickse@patchwork.health>"]
+publish = false
+
+[lib]
+crate-type = ["cdylib"]
+
+[dependencies]
+magnus = { version = "0.7.1" }
+csv = "1.3.0"
+eyre = "0.6.12"

data/ext/dedup_csv/extconf.rb

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

data/ext/dedup_csv/src/lib.rs

@@ -0,0 +1,77 @@
+use std::error::Error;
+use std::ffi::OsStr;
+use std::fs::File;
+use std::path::Path;
+use csv::{StringRecord, Writer};
+use magnus::{define_module, function, prelude::*, Ruby};
+
+fn dedup(ruby: &Ruby, previous_csv_path: String, new_csv_path: String, target_path: String) -> magnus::error::Result<()> {
+    if !previous_csv_path.has_extension(&["csv"]) {
+        return Err(magnus::Error::new(ruby.exception_exception(), "previous_csv_path must be a csv file".to_string()));
+    }
+    if !new_csv_path.has_extension(&["csv"]) {
+        return Err(magnus::Error::new(ruby.exception_exception(), "new_csv_path must be a csv file".to_string()));
+    }
+
+    let csv1 = File::open(previous_csv_path).map_err(|e| magnus_err(ruby, e, "previous_csv_path"))?;
+    let csv2 = File::open(new_csv_path).map_err(|e| magnus_err(ruby, e, "new_csv_path"))?;
+
+    let mut previous_csv: csv::Reader<File> = csv::Reader::from_reader(csv1);
+    let mut new_csv: csv::Reader<File> = csv::Reader::from_reader(csv2);
+
+    let mut wtr = Writer::from_path(target_path).map_err(|e| magnus_err(ruby, e, "target_path"))?;
+
+    let previous_headers = previous_csv.headers().map_err(|e| magnus_err(ruby, e, "previous_csv_path headers"))?;
+    let new_headers = new_csv.headers().map_err(|e| magnus_err(ruby, e, "new_csv_path headers"))?;
+
+    if previous_headers != new_headers {
+        return Err(magnus::Error::new(ruby.exception_exception(), "headers of both csv files must be the same".to_string()));
+    }
+
+    wtr.write_byte_record(previous_headers.as_byte_record()).unwrap();
+
+    let mut previous_records = vec![];
+    for previous_record in previous_csv.records() {
+        let previous_record = previous_record.map_err(|e| magnus_err(ruby, e, "previous_record"))?;
+        previous_records.push(previous_record)
+    }
+
+    for new_record in new_csv.records() {
+        let new_record = new_record.map_err(|e| magnus_err(ruby, e, "new_record"))?;
+        if !previous_records.contains(&new_record) {
+            let new_record = new_record.into_iter().map(|r| r.trim_end()).collect::<StringRecord>();
+            wtr.write_byte_record(new_record.as_byte_record()).unwrap();
+        }
+    }
+
+    wtr.flush().unwrap();
+
+    Ok(())
+}
+
+fn magnus_err<E: Error>(ruby: &Ruby, e: E, msg: &str) -> magnus::Error {
+    magnus::Error::new(ruby.exception_exception(), format!("{}: {}", msg, e.to_string()))
+}
+
+#[magnus::init]
+fn init() -> Result<(), magnus::Error> {
+    let module = define_module("DedupCsv")?;
+    module.define_singleton_method("dedup", function!(dedup, 3))?;
+    Ok(())
+}
+
+pub trait FileExtension {
+    fn has_extension<S: AsRef<str>>(&self, extensions: &[S]) -> bool;
+}
+
+impl<P: AsRef<Path>> FileExtension for P {
+    fn has_extension<S: AsRef<str>>(&self, extensions: &[S]) -> bool {
+        if let Some(ref extension) = self.as_ref().extension().and_then(OsStr::to_str) {
+            return extensions
+                .iter()
+                .any(|x| x.as_ref().eq_ignore_ascii_case(extension));
+        }
+
+        false
+    }
+}

data/lib/dedup_csv/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module DedupCsv
+  VERSION = '0.1.1'
+end

data/lib/dedup_csv.rb

@@ -0,0 +1,9 @@
+# frozen_string_literal: true
+
+require_relative 'dedup_csv/version'
+require_relative 'dedup_csv/dedup_csv'
+
+module DedupCsv
+  class Error < StandardError; end
+  # Your code goes here...
+end

data/sig/dedup_csv.rbs

@@ -0,0 +1,4 @@
+module DedupCsv
+  VERSION: String
+  # See the writing guide of rbs: https://github.com/ruby/rbs#guides
+end

metadata

@@ -0,0 +1,63 @@
+--- !ruby/object:Gem::Specification
+name: dedup_csv
+version: !ruby/object:Gem::Version
+  version: 0.1.1
+platform: x64-mingw32
+authors:
+- kingsley.hendrickse
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2024-07-18 00:00:00.000000000 Z
+dependencies: []
+description: Given 2 csv files of the same shape will find a delta
+email:
+- kingsley.hendrickse@patchwork.health
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".rspec"
+- ".rubocop.yml"
+- Cargo.lock
+- Cargo.toml
+- Gemfile
+- Gemfile.lock
+- README.md
+- Rakefile
+- ext/dedup_csv/Cargo.toml
+- ext/dedup_csv/extconf.rb
+- ext/dedup_csv/src/lib.rs
+- lib/dedup_csv.rb
+- lib/dedup_csv/2.7/dedup_csv.so
+- lib/dedup_csv/3.0/dedup_csv.so
+- lib/dedup_csv/version.rb
+- sig/dedup_csv.rbs
+homepage: http://github.com
+licenses: []
+metadata:
+  homepage_uri: http://github.com
+  rubygems_mfa_required: 'true'
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '2.7'
+  - - "<"
+    - !ruby/object:Gem::Version
+      version: 3.1.dev
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 3.0.0
+requirements: []
+rubygems_version: 3.4.4
+signing_key: 
+specification_version: 4
+summary: Fast CSV deduplicator
+test_files: []