philiprehberger-csv_kit 0.1.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: a3c2bc60fa0f4ed93e30547903b2ea5dac2d8fdf2f7fd8eae6519839f5d581f1
+  data.tar.gz: 105ed419b40775e09c72c00669e6c59d876684e8462566ce5f82d66cf0957792
+SHA512:
+  metadata.gz: 89f1b6c68c8b2ef72bc2e1d7be187605fc3680682fe2e0003819f4c2b85787e581ea9c8a25bd1ed4eb7ef42422e304bd0982b9e1f1d3c1a5c4fa0519e08de6e7
+  data.tar.gz: f187ca48f5a86a3bf530dcb715e2da6474c645836a5c9a2b9f872a674a30864f150bcb38bdb98fcd0883babd2d67d25e1e31b74ef0358f85efdf714434bdcc5a

data/CHANGELOG.md

@@ -0,0 +1,17 @@
+# Changelog
+
+All notable changes to this gem will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [Unreleased]
+
+## [0.1.0] - 2026-03-15
+
+### Added
+- Initial release
+- Streaming CSV processing with constant memory
+- Auto-detect delimiter
+- Type coercion and row validation
+- Quick load and filtering convenience methods

data/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 philiprehberger
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

data/README.md

@@ -0,0 +1,105 @@
+# philiprehberger-csv_kit
+
+[![Tests](https://github.com/philiprehberger/rb-csv-kit/actions/workflows/ci.yml/badge.svg)](https://github.com/philiprehberger/rb-csv-kit/actions/workflows/ci.yml)
+[![Gem Version](https://badge.fury.io/rb/philiprehberger-csv_kit.svg)](https://rubygems.org/gems/philiprehberger-csv_kit)
+
+Streaming CSV processor with type coercion and validation.
+
+## Requirements
+
+- Ruby >= 3.1
+
+## Installation
+
+Add to your Gemfile:
+
+```ruby
+gem 'philiprehberger-csv_kit'
+```
+
+Then run:
+
+```bash
+bundle install
+```
+
+Or install directly:
+
+```bash
+gem install philiprehberger-csv_kit
+```
+
+## Usage
+
+```ruby
+require 'philiprehberger/csv_kit'
+```
+
+### Quick Load
+
+```ruby
+rows = Philiprehberger::CsvKit.to_hashes('data.csv')
+# => [{name: "Alice", age: "30"}, ...]
+```
+
+### Pluck Columns
+
+```ruby
+names = Philiprehberger::CsvKit.pluck('data.csv', :name, :city)
+# => [{name: "Alice", city: "Berlin"}, ...]
+```
+
+### Filter Rows
+
+```ruby
+csv_string = Philiprehberger::CsvKit.filter('data.csv') do |row|
+  row[:age].to_i >= 30
+end
+```
+
+### Streaming Processor
+
+```ruby
+rows = Philiprehberger::CsvKit.process('data.csv') do |p|
+  p.transform(:age) { |v| v.to_i }
+  p.validate(:age) { |v| v.to_i.positive? }
+  p.reject { |row| row[:city] == 'Unknown' }
+  p.each { |row| puts row[:name] }
+end
+```
+
+### Delimiter Detection
+
+```ruby
+delimiter = Philiprehberger::CsvKit::Detector.detect('data.tsv')
+# => "\t"
+```
+
+## API
+
+| Method / Class | Description |
+|----------------|-------------|
+| `CsvKit.to_hashes(path)` | Load CSV into array of symbolized hashes |
+| `CsvKit.pluck(path, *keys)` | Extract specific columns |
+| `CsvKit.filter(path, &block)` | Filter rows, return CSV string |
+| `CsvKit.process(path_or_io, &block)` | Streaming DSL with transforms and validations |
+| `Processor#headers(*names)` | Override header names |
+| `Processor#transform(key, &block)` | Register column transform |
+| `Processor#validate(key, &block)` | Register column validation (skip invalid) |
+| `Processor#reject(&block)` | Reject rows matching predicate |
+| `Processor#each(&block)` | Callback for each processed row |
+| `Detector.detect(path_or_io)` | Auto-detect CSV delimiter |
+| `Row#[](key)` | Access value by symbol key |
+| `Row#to_h` | Convert row to plain hash |
+
+## Development
+
+```bash
+bundle install
+bundle exec rspec      # Run tests
+bundle exec rubocop    # Check code style
+```
+
+## License
+
+MIT

data/lib/philiprehberger/csv_kit/detector.rb

@@ -0,0 +1,43 @@
+# frozen_string_literal: true
+
+module Philiprehberger
+  module CsvKit
+    # Detects the most likely delimiter for a CSV file by sampling its first lines.
+    class Detector
+      DELIMITERS = [',', "\t", ';', '|'].freeze
+      SAMPLE_LINES = 5
+
+      # Detect the delimiter used in a file or IO.
+      #
+      # @param path_or_io [String, IO] file path or IO object
+      # @return [String] the detected delimiter
+      def self.detect(path_or_io)
+        lines = read_sample(path_or_io)
+        return ',' if lines.empty?
+
+        DELIMITERS.min_by { |d| variance(lines, d) }
+      end
+
+      # @api private
+      def self.read_sample(path_or_io)
+        if path_or_io.is_a?(String)
+          File.foreach(path_or_io).first(SAMPLE_LINES)
+        else
+          path_or_io.rewind if path_or_io.respond_to?(:rewind)
+          path_or_io.each_line.first(SAMPLE_LINES)
+        end
+      end
+
+      # @api private
+      def self.variance(lines, delimiter)
+        counts = lines.map { |l| l.count(delimiter) }
+        return Float::INFINITY if counts.all?(&:zero?)
+
+        mean = counts.sum.to_f / counts.size
+        counts.sum { |c| (c - mean)**2 } / counts.size
+      end
+
+      private_class_method :read_sample, :variance
+    end
+  end
+end

data/lib/philiprehberger/csv_kit/processor.rb

@@ -0,0 +1,107 @@
+# frozen_string_literal: true
+
+module Philiprehberger
+  module CsvKit
+    # Streaming CSV processor with a DSL for transforms, validations, and filtering.
+    class Processor
+      def initialize(path_or_io)
+        @path_or_io = path_or_io
+        @transforms = {}
+        @validations = {}
+        @reject_block = nil
+        @each_block = nil
+        @header_names = nil
+      end
+
+      # Override header names used for symbolized keys.
+      #
+      # @param names [Array<Symbol>] header names
+      def headers(*names)
+        @header_names = names.map(&:to_sym)
+      end
+
+      # Register a transform for a specific column.
+      #
+      # @param key [Symbol] column name
+      # @yield [String] raw cell value
+      def transform(key, &block)
+        @transforms[key] = block
+      end
+
+      # Register a validation for a specific column. Rows failing validation are skipped.
+      #
+      # @param key [Symbol] column name
+      # @yield [String] cell value
+      def validate(key, &block)
+        @validations[key] = block
+      end
+
+      # Register a reject predicate. Rows matching are excluded.
+      #
+      # @yield [Row] the row
+      def reject(&block)
+        @reject_block = block
+      end
+
+      # Register a callback for each processed row.
+      #
+      # @yield [Row] the row
+      def each(&block)
+        @each_block = block
+      end
+
+      # Execute the processor, streaming row by row.
+      #
+      # @return [Array<Row>] collected rows
+      def run
+        open_csv { |csv| process_rows(csv) }
+      end
+
+      private
+
+      def process_rows(csv)
+        csv.each_with_object([]) do |csv_row, results|
+          row = build_row(csv_row)
+          next unless valid?(row)
+          next if rejected?(row)
+
+          apply_transforms!(row)
+          @each_block&.call(row)
+          results << row
+        end
+      end
+
+      def open_csv(&block)
+        if @path_or_io.is_a?(String)
+          CSV.open(@path_or_io, headers: true, &block)
+        else
+          csv = CSV.new(@path_or_io, headers: true)
+          block.call(csv)
+        end
+      end
+
+      def build_row(csv_row)
+        data = csv_row.to_h
+        if @header_names
+          values = data.values
+          mapped = @header_names.zip(values).to_h
+          Row.new(mapped)
+        else
+          Row.new(data.transform_keys(&:to_sym))
+        end
+      end
+
+      def valid?(row)
+        @validations.all? { |key, blk| blk.call(row[key]) }
+      end
+
+      def rejected?(row)
+        @reject_block&.call(row) || false
+      end
+
+      def apply_transforms!(row)
+        @transforms.each { |key, blk| row[key] = blk.call(row[key]) }
+      end
+    end
+  end
+end

data/lib/philiprehberger/csv_kit/row.rb

@@ -0,0 +1,36 @@
+# frozen_string_literal: true
+
+module Philiprehberger
+  module CsvKit
+    # Wraps a CSV row as a hash with symbolized keys.
+    class Row
+      # @param data [Hash{Symbol => String}]
+      def initialize(data)
+        @data = data
+      end
+
+      # Access a value by symbolized key.
+      #
+      # @param key [Symbol] column name
+      # @return [Object]
+      def [](key)
+        @data[key]
+      end
+
+      # Set a value by symbolized key.
+      #
+      # @param key [Symbol] column name
+      # @param value [Object] new value
+      def []=(key, value)
+        @data[key] = value
+      end
+
+      # Return the row as a plain hash.
+      #
+      # @return [Hash{Symbol => Object}]
+      def to_h
+        @data.dup
+      end
+    end
+  end
+end

data/lib/philiprehberger/csv_kit/version.rb

@@ -0,0 +1,7 @@
+# frozen_string_literal: true
+
+module Philiprehberger
+  module CsvKit
+    VERSION = '0.1.1'
+  end
+end

data/lib/philiprehberger/csv_kit.rb

@@ -0,0 +1,59 @@
+# frozen_string_literal: true
+
+require 'csv'
+require_relative 'csv_kit/version'
+require_relative 'csv_kit/detector'
+require_relative 'csv_kit/row'
+require_relative 'csv_kit/processor'
+
+module Philiprehberger
+  module CsvKit
+    class Error < StandardError; end
+
+    # Streaming DSL — yields a Processor for configuration, then executes.
+    #
+    # @param path_or_io [String, IO] file path or IO object
+    # @yield [Processor] processor to configure transforms and validations
+    # @return [Array<Row>] collected rows
+    def self.process(path_or_io, &block)
+      processor = Processor.new(path_or_io)
+      block.call(processor)
+      processor.run
+    end
+
+    # Load an entire CSV into an array of symbolized hashes.
+    #
+    # @param path [String] file path
+    # @return [Array<Hash{Symbol => String}>]
+    def self.to_hashes(path)
+      CSV.foreach(path, headers: true).map do |row|
+        row.to_h.transform_keys(&:to_sym)
+      end
+    end
+
+    # Extract specific columns from a CSV.
+    #
+    # @param path [String] file path
+    # @param keys [Array<Symbol>] column names to extract
+    # @return [Array<Hash{Symbol => String}>]
+    def self.pluck(path, *keys)
+      to_hashes(path).map { |h| h.slice(*keys) }
+    end
+
+    # Filter rows and return matching rows as a CSV string.
+    #
+    # @param path [String] file path
+    # @yield [Hash{Symbol => String}] each row as a symbolized hash
+    # @return [String] CSV string with headers
+    def self.filter(path, &)
+      rows = to_hashes(path).select(&)
+      return '' if rows.empty?
+
+      headers = rows.first.keys
+      CSV.generate do |csv|
+        csv << headers
+        rows.each { |row| csv << headers.map { |k| row[k] } }
+      end
+    end
+  end
+end

metadata

@@ -0,0 +1,56 @@
+--- !ruby/object:Gem::Specification
+name: philiprehberger-csv_kit
+version: !ruby/object:Gem::Version
+  version: 0.1.1
+platform: ruby
+authors:
+- Philip Rehberger
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2026-03-15 00:00:00.000000000 Z
+dependencies: []
+description: Streaming CSV processor with row-by-row transforms, validations, column
+  plucking, filtering, and automatic delimiter detection.
+email:
+- me@philiprehberger.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- CHANGELOG.md
+- LICENSE
+- README.md
+- lib/philiprehberger/csv_kit.rb
+- lib/philiprehberger/csv_kit/detector.rb
+- lib/philiprehberger/csv_kit/processor.rb
+- lib/philiprehberger/csv_kit/row.rb
+- lib/philiprehberger/csv_kit/version.rb
+homepage: https://github.com/philiprehberger/rb-csv-kit
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/philiprehberger/rb-csv-kit
+  source_code_uri: https://github.com/philiprehberger/rb-csv-kit
+  changelog_uri: https://github.com/philiprehberger/rb-csv-kit/blob/main/CHANGELOG.md
+  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: 3.1.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.5.22
+signing_key:
+specification_version: 4
+summary: Streaming CSV processor with type coercion and validation
+test_files: []