csv-utils 0.3.25 → 0.6.0

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: csv-utils
 version: !ruby/object:Gem::Version
-  version: 0.3.25
+  version: 0.6.0
 platform: ruby
 authors:
 - Doug Youch
 bindir: bin
 cert_chain: []
-date: 2025-07-03 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: csv
@@ -15,29 +15,39 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '3.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '3.0'
 - !ruby/object:Gem::Dependency
   name: inheritance-helper
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '0.2'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '2'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
-description: Tools for debugging malformed CSV files
+        version: '0.2'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '2'
+description: Streaming tools for CSV files too big or too broken to load into memory.
+  Compare two sorted files into create, update and delete actions, sort with an external
+  merge sort, transform and extend rows in batches, and build reports from Ruby objects.
+  Detects separators, byte order marks and encodings, and ships command line tools
+  that pinpoint malformed rows, diff, grep, split and validate CSV files.
 email: dougyouch@gmail.com
 executables:
 - csv-change-eol
@@ -52,11 +62,7 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
-- ".gitignore"
-- ".ruby-gemset"
-- ".ruby-version"
-- Gemfile
-- Gemfile.lock
+- CHANGELOG.md
 - LICENSE
 - README.md
 - bin/csv-change-eol
@@ -68,23 +74,28 @@ files:
 - bin/csv-readline
 - bin/csv-splitter
 - bin/csv-validator
-- csv-utils.gemspec
-- docs/ARCHITECTURE.md
 - lib/csv-utils.rb
+- lib/csv_utils/byte_order_mark.rb
 - lib/csv_utils/csv_compare.rb
 - lib/csv_utils/csv_extender.rb
 - lib/csv_utils/csv_iterator.rb
 - lib/csv_utils/csv_options.rb
 - lib/csv_utils/csv_report.rb
 - lib/csv_utils/csv_row.rb
+- lib/csv_utils/csv_row_matcher.rb
 - lib/csv_utils/csv_sort.rb
 - lib/csv_utils/csv_transformer.rb
 - lib/csv_utils/csv_wrapper.rb
-- script/console
+- lib/csv_utils/version.rb
 homepage: https://github.com/dougyouch/csv-utils
 licenses:
 - MIT
-metadata: {}
+metadata:
+  rubygems_mfa_required: 'true'
+  source_code_uri: https://github.com/dougyouch/csv-utils
+  changelog_uri: https://github.com/dougyouch/csv-utils/blob/master/CHANGELOG.md
+  bug_tracker_uri: https://github.com/dougyouch/csv-utils/issues
+  documentation_uri: https://rubydoc.info/gems/csv-utils
 rdoc_options: []
 require_paths:
 - lib
@@ -92,14 +103,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: '3.3'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.6.2
+rubygems_version: 4.0.20
 specification_version: 4
-summary: CSV Utils
+summary: Compare, sort, transform and debug large or malformed CSV files
 test_files: []

data/.gitignore

@@ -1,52 +0,0 @@
-*.gem
-*.rbc
-/.config
-/coverage/
-/InstalledFiles
-/pkg/
-/spec/reports/
-/spec/examples.txt
-/test/tmp/
-/test/version_tmp/
-/tmp/
-
-# Used by dotenv library to load environment variables.
-# .env
-
-## Specific to RubyMotion:
-.dat*
-.repl_history
-build/
-*.bridgesupport
-build-iPhoneOS/
-build-iPhoneSimulator/
-
-## Specific to RubyMotion (use of CocoaPods):
-#
-# We recommend against adding the Pods directory to your .gitignore. However
-# you should judge for yourself, the pros and cons are mentioned at:
-# https://guides.cocoapods.org/using/using-cocoapods.html#should-i-check-the-pods-directory-into-source-control
-#
-# vendor/Pods/
-
-## Documentation cache and generated files:
-/.yardoc/
-/_yardoc/
-/doc/
-/rdoc/
-
-## Environment normalization:
-/.bundle/
-/vendor/bundle
-/lib/bundler/man/
-
-# for a library or gem, you might want to ignore these files since the code is
-# intended to run in multiple environments; otherwise, check them in:
-# Gemfile.lock
-# .ruby-version
-# .ruby-gemset
-
-# unless supporting rvm < 1.11.0 or doing something fancy, ignore this:
-.rvmrc
-
-*~

data/.ruby-gemset

@@ -1 +0,0 @@
-csv-utils

data/.ruby-version

@@ -1 +0,0 @@
-3.4.2

data/Gemfile

@@ -1,13 +0,0 @@
-# frozen_string_literal: true
-
-source 'http://rubygems.org'
-
-gem 'csv'
-gem 'inheritance-helper'
-
-group :development do
-  gem 'rake'
-  gem 'rubocop'
-  gem 'rspec'
-  gem 'simplecov'
-end

data/Gemfile.lock

@@ -1,72 +0,0 @@
-GEM
-  remote: http://rubygems.org/
-  specs:
-    ast (2.4.3)
-    csv (3.3.4)
-    diff-lcs (1.6.2)
-    docile (1.4.1)
-    inheritance-helper (0.2.5)
-    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 (13.2.1)
-    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 (~> 3.13.0)
-    rspec-mocks (3.13.4)
-      diff-lcs (>= 1.2.0, < 2.0)
-      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 (>= 3.3.0.2)
-      rainbow (>= 2.2.2, < 4.0)
-      regexp_parser (>= 2.9.3, < 3.0)
-      rubocop-ast (>= 1.44.0, < 2.0)
-      ruby-progressbar (~> 1.7)
-      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 (0.13.1)
-    simplecov_json_formatter (0.1.4)
-    unicode-display_width (3.1.4)
-      unicode-emoji (~> 4.0, >= 4.0.4)
-    unicode-emoji (4.0.4)
-
-PLATFORMS
-  ruby
-  x86_64-darwin-24
-
-DEPENDENCIES
-  csv
-  inheritance-helper
-  rake
-  rspec
-  rubocop
-  simplecov
-
-BUNDLED WITH
-   2.6.2

data/csv-utils.gemspec

@@ -1,18 +0,0 @@
-# frozen_string_literal: true
-
-Gem::Specification.new do |s|
-  s.name        = 'csv-utils'
-  s.version     = '0.3.25'
-  s.licenses    = ['MIT']
-  s.summary     = 'CSV Utils'
-  s.description = 'Tools for debugging malformed CSV files'
-  s.authors     = ['Doug Youch']
-  s.email       = 'dougyouch@gmail.com'
-  s.homepage    = 'https://github.com/dougyouch/csv-utils'
-  s.files       = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
-  s.bindir      = 'bin'
-  s.executables = s.files.grep(%r{^bin/}) { |f| File.basename(f) }
-
-  s.add_runtime_dependency 'csv'
-  s.add_runtime_dependency 'inheritance-helper'
-end

data/docs/ARCHITECTURE.md

@@ -1,134 +0,0 @@
-# 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/script/console

@@ -1,7 +0,0 @@
-#!/usr/bin/env ruby
-# frozen_string_literal: true
-
-$LOAD_PATH << File.expand_path('../lib', __dir__)
-require 'csv-utils'
-require 'irb'
-IRB.start(__FILE__)