csv-utils 0.3.24 → 0.3.25

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 56d81ad0c7a53bc4a738cc4f9643884fa301b6c2add83f9b961263dfdae1e896
-  data.tar.gz: 5db7f72a3df30a2933ffdafa8599a7ce46ae763124b4c0d6d88b775f2238422b
+  metadata.gz: 9b30f6d77e44b6d4abca4ee199142b4efa6cb73895df87ba630b82f50b964fbc
+  data.tar.gz: 10337ebbb358c3e60f5f4d47756297577468b45bbaeaf4e1b0b355b12c9083a4
 SHA512:
-  metadata.gz: bf3878abd3a7f0c5dfbdcd9cdcee6773dc20d43308464c3d0a984ee2fe147c055ba64627043478f8099604f8824b3e8630eabfe8f91ffc562d54fabed98b0535
-  data.tar.gz: 68feef79f89b7b415c40b37f9ac03b2feb6c800552af70c22006fa56a92d987a0753e0fc00b6449b8edca04463dfeaaefc4b647fbf46ce14227ccdde927a95dd
+  metadata.gz: 84432b88f8fc0aee4422fe46a36bab6e99cca1d604469608e2e4ced97c1f748be66796bc7f0c161b660d31e6424f5b155b38bfb034e9cee234fd8c71459bb2d3
+  data.tar.gz: ad864bb734d1c9f7d6a99d97aa2567811c66f8bf317571a947d56196776c61abf229d3d3aad0f5485f1a39b64d257e5be234ffa19dcc9c8a975a045fffcd95b1

data/.ruby-version

@@ -1 +1 @@
-3.1.0
+3.4.2

data/Gemfile

@@ -2,14 +2,12 @@
 
 source 'http://rubygems.org'
 
+gem 'csv'
 gem 'inheritance-helper'
 
 group :development do
   gem 'rake'
   gem 'rubocop'
-end
-
-group :spec do
   gem 'rspec'
   gem 'simplecov'
 end

data/Gemfile.lock

@@ -1,54 +1,67 @@
 GEM
   remote: http://rubygems.org/
   specs:
-    ast (2.4.2)
-    diff-lcs (1.5.0)
-    docile (1.4.0)
+    ast (2.4.3)
+    csv (3.3.4)
+    diff-lcs (1.6.2)
+    docile (1.4.1)
     inheritance-helper (0.2.5)
-    parallel (1.22.1)
-    parser (3.1.1.0)
+    json (2.12.0)
+    language_server-protocol (3.17.0.5)
+    lint_roller (1.1.0)
+    parallel (1.27.0)
+    parser (3.3.8.0)
       ast (~> 2.4.1)
+      racc
+    prism (1.4.0)
+    racc (1.8.1)
     rainbow (3.1.1)
-    rake (13.0.6)
-    regexp_parser (2.2.1)
-    rexml (3.2.5)
-    rspec (3.11.0)
-      rspec-core (~> 3.11.0)
-      rspec-expectations (~> 3.11.0)
-      rspec-mocks (~> 3.11.0)
-    rspec-core (3.11.0)
-      rspec-support (~> 3.11.0)
-    rspec-expectations (3.11.0)
+    rake (13.2.1)
+    regexp_parser (2.10.0)
+    rspec (3.13.0)
+      rspec-core (~> 3.13.0)
+      rspec-expectations (~> 3.13.0)
+      rspec-mocks (~> 3.13.0)
+    rspec-core (3.13.3)
+      rspec-support (~> 3.13.0)
+    rspec-expectations (3.13.4)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.11.0)
-    rspec-mocks (3.11.0)
+      rspec-support (~> 3.13.0)
+    rspec-mocks (3.13.4)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.11.0)
-    rspec-support (3.11.0)
-    rubocop (1.26.1)
+      rspec-support (~> 3.13.0)
+    rspec-support (3.13.3)
+    rubocop (1.75.6)
+      json (~> 2.3)
+      language_server-protocol (~> 3.17.0.2)
+      lint_roller (~> 1.1.0)
       parallel (~> 1.10)
-      parser (>= 3.1.0.0)
+      parser (>= 3.3.0.2)
       rainbow (>= 2.2.2, < 4.0)
-      regexp_parser (>= 1.8, < 3.0)
-      rexml
-      rubocop-ast (>= 1.16.0, < 2.0)
+      regexp_parser (>= 2.9.3, < 3.0)
+      rubocop-ast (>= 1.44.0, < 2.0)
       ruby-progressbar (~> 1.7)
-      unicode-display_width (>= 1.4.0, < 3.0)
-    rubocop-ast (1.16.0)
-      parser (>= 3.1.1.0)
-    ruby-progressbar (1.11.0)
-    simplecov (0.21.2)
+      unicode-display_width (>= 2.4.0, < 4.0)
+    rubocop-ast (1.44.1)
+      parser (>= 3.3.7.2)
+      prism (~> 1.4)
+    ruby-progressbar (1.13.0)
+    simplecov (0.22.0)
       docile (~> 1.1)
       simplecov-html (~> 0.11)
       simplecov_json_formatter (~> 0.1)
-    simplecov-html (0.12.3)
+    simplecov-html (0.13.1)
     simplecov_json_formatter (0.1.4)
-    unicode-display_width (2.1.0)
+    unicode-display_width (3.1.4)
+      unicode-emoji (~> 4.0, >= 4.0.4)
+    unicode-emoji (4.0.4)
 
 PLATFORMS
-  x86_64-darwin-21
+  ruby
+  x86_64-darwin-24
 
 DEPENDENCIES
+  csv
   inheritance-helper
   rake
   rspec
@@ -56,4 +69,4 @@ DEPENDENCIES
   simplecov
 
 BUNDLED WITH
-   2.3.3
+   2.6.2

data/README.md

@@ -1,2 +1,86 @@
-# csv-utils
-CSV Utilities for manipulating csv files in code
+# CSV Utils
+
+A Ruby library providing a comprehensive set of utilities for manipulating and processing CSV files. This library offers a robust set of tools for comparing, transforming, sorting, and managing CSV data efficiently.
+
+## Features
+
+- **CSV Comparison**: Compare two CSV files and identify differences (creates, updates, and deletes)
+- **CSV Transformation**: Transform CSV data with customizable rules
+- **CSV Sorting**: Sort CSV files based on specified columns
+- **CSV Reporting**: Generate reports from CSV data
+- **CSV Iteration**: Efficient iteration over CSV files
+- **CSV Extension**: Extend CSV files with additional data
+- **CSV Wrapper**: Convenient wrapper for CSV operations
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'csv-utils'
+```
+
+And then execute:
+
+```bash
+$ bundle install
+```
+
+Or install it yourself as:
+
+```bash
+$ gem install csv-utils
+```
+
+## Usage
+
+### Comparing CSV Files
+
+```ruby
+require 'csv_utils'
+
+comparator = CSVUtils::CSVCompare.new('primary.csv', ['updated_at']) do |src, dest|
+  src['id'] <=> dest['id']
+end
+
+comparator.compare('secondary.csv') do |action, record|
+  case action
+  when :create
+    puts "Create: #{record}"
+  when :update
+    puts "Update: #{record}"
+  when :delete
+    puts "Delete: #{record}"
+  end
+end
+```
+
+### Sorting CSV Files
+
+```ruby
+sorter = CSVUtils::CSVSort.new('input.csv')
+sorter.sort('output.csv', ['id', 'name'])
+```
+
+### Transforming CSV Data
+
+```ruby
+transformer = CSVUtils::CSVTransformer.new('input.csv')
+transformer.transform('output.csv') do |row|
+  # Transform row data
+  row['new_column'] = row['old_column'].upcase
+  row
+end
+```
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests.
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/yourusername/csv-utils.
+
+## License
+
+The gem is available as open source under the terms of the MIT License.

data/csv-utils.gemspec

@@ -2,7 +2,7 @@
 
 Gem::Specification.new do |s|
   s.name        = 'csv-utils'
-  s.version     = '0.3.24'
+  s.version     = '0.3.25'
   s.licenses    = ['MIT']
   s.summary     = 'CSV Utils'
   s.description = 'Tools for debugging malformed CSV files'

data/docs/ARCHITECTURE.md

@@ -0,0 +1,134 @@
+# CSV Utils Architecture
+
+## Overview
+
+CSV Utils is a Ruby library designed to provide a comprehensive set of tools for CSV file manipulation. The architecture follows a modular design pattern, with each component handling a specific aspect of CSV processing.
+
+## Core Components
+
+### 1. CSVCompare
+- **Purpose**: Compares two CSV files to identify differences
+- **Key Features**:
+  - Identifies creates, updates, and deletes between files
+  - Supports custom comparison logic
+  - Handles BOM (Byte Order Mark) stripping
+  - Memory-efficient streaming comparison
+- **Dependencies**: None (uses standard Ruby CSV library)
+
+### 2. CSVTransformer
+- **Purpose**: Transforms CSV data according to custom rules
+- **Key Features**:
+  - Row-by-row transformation
+  - Custom transformation blocks
+  - Maintains header structure
+- **Dependencies**: None
+
+### 3. CSVSort
+- **Purpose**: Sorts CSV files based on specified columns
+- **Key Features**:
+  - Multi-column sorting
+  - Memory-efficient sorting
+  - Preserves header row
+- **Dependencies**: None
+
+### 4. CSVReport
+- **Purpose**: Generates reports from CSV data
+- **Key Features**:
+  - Custom report formatting
+  - Data aggregation
+  - Summary statistics
+- **Dependencies**: None
+
+### 5. CSVIterator
+- **Purpose**: Provides efficient iteration over CSV files
+- **Key Features**:
+  - Memory-efficient streaming
+  - Custom iteration blocks
+  - Header handling
+- **Dependencies**: None
+
+### 6. CSVExtender
+- **Purpose**: Extends CSV files with additional data
+- **Key Features**:
+  - Column addition
+  - Data enrichment
+  - Custom extension logic
+- **Dependencies**: None
+
+### 7. CSVWrapper
+- **Purpose**: Provides a convenient wrapper for CSV operations
+- **Key Features**:
+  - Simplified CSV access
+  - Common operation shortcuts
+  - Error handling
+- **Dependencies**: None
+
+## Design Principles
+
+1. **Modularity**: Each component is self-contained and focused on a single responsibility
+2. **Memory Efficiency**: Components are designed to handle large files through streaming
+3. **Extensibility**: Custom logic can be injected through blocks and callbacks
+4. **Error Handling**: Robust error handling and validation
+5. **Performance**: Optimized for large file processing
+
+## Data Flow
+
+1. **Input Processing**:
+   - Files are read using Ruby's CSV library
+   - BOM stripping is handled automatically
+   - Headers are preserved and validated
+
+2. **Processing**:
+   - Each component processes data in a streaming fashion
+   - Custom logic can be injected at various points
+   - Memory usage is optimized for large files
+
+3. **Output Generation**:
+   - Results are written to new files or returned as data structures
+   - Headers are preserved in output files
+   - Error states are properly handled
+
+## Error Handling
+
+- File not found errors
+- Invalid CSV format
+- Missing required columns
+- Permission issues
+- Memory constraints
+
+## Performance Considerations
+
+1. **Memory Usage**:
+   - Streaming processing for large files
+   - Minimal in-memory data storage
+   - Efficient data structures
+
+2. **Processing Speed**:
+   - Optimized comparison algorithms
+   - Efficient sorting mechanisms
+   - Minimal file I/O operations
+
+## Future Considerations
+
+1. **Potential Enhancements**:
+   - Parallel processing support
+   - Additional data format support
+   - Enhanced reporting capabilities
+   - Caching mechanisms
+
+2. **Scalability**:
+   - Support for distributed processing
+   - Cloud storage integration
+   - Batch processing capabilities
+
+## Testing Strategy
+
+1. **Unit Tests**:
+   - Individual component testing
+   - Edge case coverage
+   - Performance benchmarks
+
+2. **Integration Tests**:
+   - Component interaction testing
+   - End-to-end workflows
+   - Error scenario coverage 

data/lib/csv_utils/csv_iterator.rb

@@ -21,8 +21,8 @@ class CSVUtils::CSVIterator
     end
   end
 
-  def initialize(src_csv, csv_options = {})
-    @src_csv = CSVUtils::CSVWrapper.new(src_csv, 'rb', csv_options)
+  def initialize(src_csv, csv_options = {}, mode = 'rb')
+    @src_csv = CSVUtils::CSVWrapper.new(src_csv, mode, csv_options)
   end
 
   def each(headers = nil)

metadata

@@ -1,14 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: csv-utils
 version: !ruby/object:Gem::Version
-  version: 0.3.24
+  version: 0.3.25
 platform: ruby
 authors:
 - Doug Youch
-autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-03-21 00:00:00.000000000 Z
+date: 2025-07-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: csv
@@ -70,6 +69,7 @@ files:
 - bin/csv-splitter
 - bin/csv-validator
 - csv-utils.gemspec
+- docs/ARCHITECTURE.md
 - lib/csv-utils.rb
 - lib/csv_utils/csv_compare.rb
 - lib/csv_utils/csv_extender.rb
@@ -85,7 +85,6 @@ homepage: https://github.com/dougyouch/csv-utils
 licenses:
 - MIT
 metadata: {}
-post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -100,8 +99,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.3
-signing_key:
+rubygems_version: 3.6.2
 specification_version: 4
 summary: CSV Utils
 test_files: []