dedup_csv 0.1.0-x86_64-linux → 0.1.2-x86_64-linux

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 42de28c2a0451667a1520e37726a914fd07fd0d58a14b679fb6df1ba103a4b75
-  data.tar.gz: b27e2cb7f69bb92d29c30fc832c245cdf67811fac111c924026aaf89648453c7
+  metadata.gz: 399d31ac2650c0c79b87f474840f82e0eb85dab268b574a4edd7f5a4a451c30c
+  data.tar.gz: 6198e1a1cae8565395432d95222d89177c62f09e8edec07f0ea45c982d49fee9
 SHA512:
-  metadata.gz: a5969581f0b618658ba0802b51161f023a9d9683b39ed5db81e38b36484df70bc2e36c3a8abfc26d0f62a23532033cca074879849dba9828dd21a990fe0bba0e
-  data.tar.gz: 8ebe58c390a11c3d8a4e6926d28070a228c96d1137378c40db422ee575a5cff247545b02ae17700cf51aec591d4a78267d7c36c76c61ba4b3a8ccfa86fb167c4
+  metadata.gz: 64b7a354fb1a33c78040271c253559cb4a53a60d0854d24e1f73e97215abc9b7b3041e5a6f6cf23f4f5e57248154b3fb28ddc012d2dd3606e78921b9fd852fcb
+  data.tar.gz: '0579cd7b80eced5d733264c779f51f4563f71eabf17aea280dd7aa18d2331db9682cf0bfda38e5195cb3ba6147b89b0fccf1a2f464ca5a032a3fbb0c00981acd'

data/.rubocop.yml

@@ -7,6 +7,9 @@ Style/StringLiterals:
   Enabled: true
   EnforcedStyle: single_quotes
 
+Style/Documentation:
+  Enabled: false
+
 Style/StringLiteralsInInterpolation:
   Enabled: true
   EnforcedStyle: double_quotes

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    dedup_csv (0.1.0)
+    dedup_csv (0.1.2)
 
 GEM
   remote: https://rubygems.org/

data/README.md

@@ -2,6 +2,19 @@
 
 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'
+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

@@ -14,11 +14,11 @@ 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/**/*']
+# 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'

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

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module DedupCsv
-  VERSION = '0.1.0'
+  VERSION = '0.1.2'
 end

data/lib/dedup_csv.rb

@@ -1,9 +1,14 @@
 # frozen_string_literal: true
 
+# load native extension
+begin
+  ruby_version = /(\d+\.\d+)/.match(RUBY_VERSION)
+  require_relative "#{ruby_version}/dedup_csv"
+rescue LoadError
+  require_relative 'dedup_csv/dedup_csv'
+end
+
 require_relative 'dedup_csv/version'
-require_relative 'dedup_csv/dedup_csv'
 
 module DedupCsv
-  class Error < StandardError; end
-  # Your code goes here...
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: dedup_csv
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.2
 platform: x86_64-linux
 authors:
 - kingsley.hendrickse
@@ -10,7 +10,8 @@ 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
+description: Given 2 CSV files, remove all rows from the second CSV that are present
+  in the first CSV.
 email:
 - kingsley.hendrickse@patchwork.health
 executables: []
@@ -25,6 +26,9 @@ files:
 - 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
@@ -32,10 +36,11 @@ files:
 - lib/dedup_csv/3.2/dedup_csv.so
 - lib/dedup_csv/version.rb
 - sig/dedup_csv.rbs
-homepage: http://github.com
+homepage: http://github.com/kingsleyh/dedup_csv
 licenses: []
 metadata:
-  homepage_uri: http://github.com
+  homepage_uri: http://github.com/kingsleyh/dedup_csv
+  source_code_uri: http://github.com/kingsleyh/dedup_csv
   rubygems_mfa_required: 'true'
 post_install_message: 
 rdoc_options: []
@@ -53,7 +58,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 3.0.0
 requirements: []
 rubygems_version: 3.4.4
 signing_key: