kaggle 0.0.1 → 0.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3ad655835decf29a7a46e8b9c1d62a91bf05975bb8a694e3fac92b9f5f141eb7
-  data.tar.gz: '0803369672874a9a8f275a53fca15baeb66b1f2a121b2d5bdf91b39349a3bab1'
+  metadata.gz: 56c5fd9c27bd8cdc20423167b912f171ee07d37e0413cfbbbcba2ea38140b7c6
+  data.tar.gz: 3f37e295dc32362f7606803790225af6a707021ba78b239d4f2a29567102fee6
 SHA512:
-  metadata.gz: 947d6474751ade9122c0ec9fcb7d7f533a1b23dc9903ba6f59d3e88f20c4b1ec38ff70c53bb242d3a9cafca7f374bee0b307c2fb74ccc52add31fa7555906864
-  data.tar.gz: ced4244587280c337dbab8455ffb133db8181631afed0de72bb2b0c773ea7f32b8eff6f30c0d7a6037d5d5ee59cd245e975f7c5f9bdf436da6c9ed9a490707cb
+  metadata.gz: 41b60fa4d87d5a78778247acdbf620bbbcb2a23add74b07c76ff25fa2a02ed5675e8fd3aa27dce6352c2c49c0dfcfb90f54d55cbd1219cb81b04c6a2b371d086
+  data.tar.gz: c3b887147a1e0aeb38fdf1440b63f3c722e8375feaab45bbc0a5e4e434b0a8f7cb06ea71437fe08d888704c732d60629c7e3f18443c40e339abb72c88a56e667

data/README.md

@@ -78,19 +78,6 @@ client = Kaggle::Client.new(
 )
 ```
 
-### List Datasets
-
-```ruby
-# List all datasets
-datasets = client.list_datasets
-
-# Search datasets
-datasets = client.list_datasets(search: 'housing')
-
-# Paginate results
-datasets = client.list_datasets(page: 2, page_size: 10)
-```
-
 ### Download Datasets
 
 ```ruby
@@ -131,12 +118,6 @@ data = client.parse_csv_to_json('/path/to/file.csv')
 The gem includes a command-line interface:
 
 ```bash
-# List datasets
-kaggle list
-
-# Search datasets
-kaggle list "housing"
-
 # Download dataset
 kaggle download zillow zecon
 

data/Rakefile

@@ -7,4 +7,4 @@ Rake::TestTask.new(:test) do |t|
   t.test_files = FileList['test/**/*_test.rb']
 end
 
-task default: :test
+task default: :test

data/kaggle.gemspec

@@ -28,19 +28,19 @@ Gem::Specification.new do |spec|
   spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
   spec.require_paths = ['lib']
 
-  spec.add_dependency 'httparty', '>= 0.23'
   spec.add_dependency 'csv', '>= 3.3'
-  spec.add_dependency 'oj', '3.16.11'
   spec.add_dependency 'fileutils', '>= 1.7'
+  spec.add_dependency 'httparty', '>= 0.23'
+  spec.add_dependency 'oj', '3.16.11'
   spec.add_dependency 'rubyzip', '>= 2.0'
 
-  spec.add_development_dependency 'rake', '~> 13.3.0'
   spec.add_development_dependency 'minitest', '~> 5.25.5'
   spec.add_development_dependency 'minitest-focus', '~> 1.4.0'
   spec.add_development_dependency 'minitest-reporters', '~> 1.7.1'
-  spec.add_development_dependency 'webmock', '~> 3.24.0'
   spec.add_development_dependency 'mocha', '~> 2.4.5'
   spec.add_development_dependency 'pry', '~> 0.15.2'
+  spec.add_development_dependency 'rake', '~> 13.3.0'
   spec.add_development_dependency 'simplecov', '~> 0.22.0'
   spec.add_development_dependency 'timecop', '~> 0.9.10'
+  spec.add_development_dependency 'webmock', '~> 3.24.0'
 end

data/lib/kaggle/client.rb

@@ -1,102 +1,109 @@
 module Kaggle
   class Client
     include HTTParty
-    
+
     base_uri Constants::BASE_URL
-    
-    attr_reader :username, :api_key, :download_path, :cache_path, :timeout
-    
-    def initialize(username: nil, api_key: nil, credentials_file: nil, download_path: nil, cache_path: nil, timeout: nil)
+
+    attr_reader :username, :api_key, :download_path, :cache_path, :timeout, :cache_only
+
+    def initialize(username: nil, api_key: nil, credentials_file: nil, download_path: nil, cache_path: nil,
+                   timeout: nil, cache_only: false)
       load_credentials(username, api_key, credentials_file)
       @download_path = download_path || Constants::DEFAULT_DOWNLOAD_PATH
       @cache_path = cache_path || Constants::DEFAULT_CACHE_PATH
       @timeout = timeout || Constants::DEFAULT_TIMEOUT
-      
-      raise AuthenticationError, 'Username and API key are required' unless valid_credential?(@username) && valid_credential?(@api_key)
-      
+      @cache_only = cache_only
+
+      unless cache_only || (valid_credential?(@username) && valid_credential?(@api_key))
+        raise AuthenticationError,
+              'Username and API key are required (or set cache_only: true for cache-only access)'
+      end
+
       ensure_directories_exist
-      setup_httparty_options
+      setup_httparty_options unless cache_only
     end
-    
+
     def download_dataset(dataset_owner, dataset_name, options = {})
       dataset_path = "#{dataset_owner}/#{dataset_name}"
-      
+
       # Check cache first for parsed data
       if options[:use_cache] && options[:parse_csv]
         cache_key = generate_cache_key(dataset_path)
-        if cached_file_exists?(cache_key)
-          return load_from_cache(cache_key)
-        end
+        return load_from_cache(cache_key) if cached_file_exists?(cache_key)
       end
-      
+
       # Check if we already have extracted files for this dataset
       extracted_dir = get_extracted_dir(dataset_path)
       if options[:use_cache] && Dir.exist?(extracted_dir) && !Dir.empty?(extracted_dir)
         return handle_existing_dataset(extracted_dir, options)
       end
-      
+
+      # If cache_only mode and no cached data found, return nil or raise based on force_cache option
+      if @cache_only
+        if options[:force_cache]
+          raise CacheNotFoundError, "Dataset '#{dataset_path}' not found in cache and force_cache is enabled"
+        else
+          return nil # Gracefully return nil when cache_only but not forced
+        end
+      end
+
       # Download the zip file
       response = authenticated_request(:get, "#{Constants::DATASET_ENDPOINTS[:download]}/#{dataset_path}")
-      
-      unless response.success?
-        raise DownloadError, "Failed to download dataset: #{response.message}"
-      end
-      
+
+      raise DownloadError, "Failed to download dataset: #{response.message}" unless response.success?
+
       # Save zip file
       zip_file = save_zip_file(dataset_path, response.body)
-      
+
       # Extract zip file
       extract_zip_file(zip_file, extracted_dir)
-      
+
       # Clean up zip file
       File.delete(zip_file) if File.exist?(zip_file)
-      
+
       # Handle the extracted files
       result = handle_extracted_dataset(extracted_dir, options)
-      
+
       # Cache parsed CSV data if requested
       if options[:use_cache] && options[:parse_csv] && (result.is_a?(Hash) || result.is_a?(Array))
         cache_key = generate_cache_key(dataset_path)
         cache_parsed_data(cache_key, result)
       end
-      
+
       result
     end
-    
-    
+
     def dataset_files(dataset_owner, dataset_name)
       dataset_path = "#{dataset_owner}/#{dataset_name}"
       response = authenticated_request(:get, "#{Constants::DATASET_ENDPOINTS[:files]}/#{dataset_path}")
-      
-      unless response.success?
-        raise DatasetNotFoundError, "Dataset not found or accessible: #{dataset_path}"
-      end
-      
+
+      raise DatasetNotFoundError, "Dataset not found or accessible: #{dataset_path}" unless response.success?
+
       Oj.load(response.body)
     rescue Oj::ParseError => e
       raise ParseError, "Failed to parse dataset files response: #{e.message}"
     end
-    
+
     def parse_csv_to_json(file_path)
       raise Error, "File does not exist: #{file_path}" unless File.exist?(file_path)
       raise Error, "File is not a CSV: #{file_path}" unless csv_file?(file_path)
-      
+
       data = []
       CSV.foreach(file_path, headers: true) do |row|
         data << row.to_hash
       end
-      
+
       data
     rescue CSV::MalformedCSVError => e
       raise ParseError, "Failed to parse CSV file: #{e.message}"
     end
-    
+
     private
-    
+
     def valid_credential?(credential)
       credential && !credential.to_s.strip.empty?
     end
-    
+
     def load_credentials(username, api_key, credentials_file)
       # Try provided credentials file first
       if credentials_file && File.exist?(credentials_file)
@@ -114,63 +121,63 @@ module Kaggle
         @api_key = api_key || ENV['KAGGLE_KEY']
       end
     end
-    
+
     def load_credentials_from_file(file_path)
       content = File.read(file_path)
       Oj.load(content)
     rescue Oj::ParseError => e
       raise AuthenticationError, "Invalid credentials file format: #{e.message}"
-    rescue => e
+    rescue StandardError => e
       raise AuthenticationError, "Failed to read credentials file: #{e.message}"
     end
-    
+
     def ensure_directories_exist
       FileUtils.mkdir_p(@download_path) unless Dir.exist?(@download_path)
       FileUtils.mkdir_p(@cache_path) unless Dir.exist?(@cache_path)
     end
-    
+
     def setup_httparty_options
       self.class.default_options.merge!({
-        headers: Constants::REQUIRED_HEADERS,
-        timeout: @timeout,
-        basic_auth: {
-          username: @username,
-          password: @api_key
-        }
-      })
-    end
-    
+                                          headers: Constants::REQUIRED_HEADERS,
+                                          timeout: @timeout,
+                                          basic_auth: {
+                                            username: @username,
+                                            password: @api_key
+                                          }
+                                        })
+    end
+
     def authenticated_request(method, endpoint, options = {})
       self.class.send(method, endpoint, options)
     rescue Timeout::Error, Net::ReadTimeout, Net::OpenTimeout
       raise Error, 'Request timed out'
-    rescue => e
+    rescue StandardError => e
       raise Error, "Request failed: #{e.message}"
     end
-    
+
     def get_extracted_dir(dataset_path)
       dir_name = dataset_path.gsub('/', '_')
       File.join(@download_path, dir_name)
     end
-    
+
     def save_zip_file(dataset_path, content)
       filename = "#{dataset_path.gsub('/', '_')}.zip"
       file_path = File.join(@download_path, filename)
-      
+
       File.open(file_path, 'wb') do |file|
         file.write(content)
       end
-      
+
       file_path
     end
-    
+
     def extract_zip_file(zip_file_path, extract_to_dir)
       FileUtils.mkdir_p(extract_to_dir)
-      
+
       Zip::File.open(zip_file_path) do |zip_file|
         zip_file.each do |entry|
           extract_path = File.join(extract_to_dir, entry.name)
-          
+
           if entry.directory?
             # Create directory
             FileUtils.mkdir_p(extract_path)
@@ -178,7 +185,7 @@ module Kaggle
             # Create parent directory if it doesn't exist
             parent_dir = File.dirname(extract_path)
             FileUtils.mkdir_p(parent_dir) unless Dir.exist?(parent_dir)
-            
+
             # Extract file manually to avoid path issues
             File.open(extract_path, 'wb') do |f|
               f.write entry.get_input_stream.read
@@ -189,16 +196,16 @@ module Kaggle
     rescue Zip::Error => e
       raise DownloadError, "Failed to extract zip file: #{e.message}"
     end
-    
+
     def handle_existing_dataset(extracted_dir, options)
       if options[:parse_csv]
         csv_files = find_csv_files(extracted_dir)
         return parse_csv_files_to_json(csv_files) unless csv_files.empty?
       end
-      
+
       extracted_dir
     end
-    
+
     def handle_extracted_dataset(extracted_dir, options)
       if options[:parse_csv]
         csv_files = find_csv_files(extracted_dir)
@@ -207,49 +214,48 @@ module Kaggle
           return parsed_data
         end
       end
-      
+
       extracted_dir
     end
-    
+
     def find_csv_files(directory)
       Dir.glob(File.join(directory, '**', '*.csv'))
     end
-    
+
     def parse_csv_files_to_json(csv_files)
       result = {}
-      
+
       csv_files.each do |csv_file|
         file_name = File.basename(csv_file, '.csv')
         result[file_name] = parse_csv_to_json(csv_file)
       end
-      
+
       # If there's only one CSV file, return its data directly
       result.length == 1 ? result.values.first : result
     end
-    
+
     def generate_cache_key(dataset_path)
       "#{dataset_path.gsub('/', '_')}_parsed.json"
     end
-    
+
     def cached_file_exists?(cache_key)
       File.exist?(File.join(@cache_path, cache_key))
     end
-    
+
     def load_from_cache(cache_key)
       cache_file_path = File.join(@cache_path, cache_key)
       Oj.load(File.read(cache_file_path))
     rescue Oj::ParseError => e
       raise ParseError, "Failed to parse cached data: #{e.message}"
     end
-    
+
     def cache_parsed_data(cache_key, data)
       cache_file_path = File.join(@cache_path, cache_key)
       File.write(cache_file_path, Oj.dump(data, mode: :compat, indent: 2))
     end
-    
+
     def csv_file?(file_path)
       File.extname(file_path).downcase == '.csv'
     end
-    
   end
-end
+end

data/lib/kaggle/constants.rb

@@ -1,23 +1,23 @@
 module Kaggle
   module Constants
     BASE_URL = 'https://www.kaggle.com/api/v1'
-    
+
     DEFAULT_DOWNLOAD_PATH = './downloads'
     DEFAULT_CACHE_PATH = './cache'
     DEFAULT_CREDENTIALS_FILE = './kaggle.json'
     DEFAULT_TIMEOUT = 30
-    
+
     SUPPORTED_FORMATS = %w[csv json].freeze
-    
+
     DATASET_ENDPOINTS = {
       view: '/datasets/view',
       download: '/datasets/download',
       files: '/datasets/data'
     }.freeze
-    
+
     REQUIRED_HEADERS = {
       'User-Agent' => 'Kaggle Ruby Client/0.0.1',
       'Accept' => 'application/json'
     }.freeze
   end
-end
+end

data/lib/kaggle/version.rb

@@ -1,3 +1,3 @@
 module Kaggle
-  VERSION = '0.0.1'
-end
+  VERSION = '0.0.3'
+end

data/lib/kaggle.rb

@@ -16,4 +16,5 @@ module Kaggle
   class DatasetNotFoundError < Error; end
   class DownloadError < Error; end
   class ParseError < Error; end
-end
+  class CacheNotFoundError < Error; end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: kaggle
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.3
 platform: ruby
 authors:
 - Your Name
@@ -10,61 +10,61 @@ cert_chain: []
 date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: httparty
+  name: csv
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0.23'
+        version: '3.3'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0.23'
+        version: '3.3'
 - !ruby/object:Gem::Dependency
-  name: csv
+  name: fileutils
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '3.3'
+        version: '1.7'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '3.3'
+        version: '1.7'
 - !ruby/object:Gem::Dependency
-  name: oj
+  name: httparty
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 3.16.11
+        version: '0.23'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 3.16.11
+        version: '0.23'
 - !ruby/object:Gem::Dependency
-  name: fileutils
+  name: oj
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '='
       - !ruby/object:Gem::Version
-        version: '1.7'
+        version: 3.16.11
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '='
       - !ruby/object:Gem::Version
-        version: '1.7'
+        version: 3.16.11
 - !ruby/object:Gem::Dependency
   name: rubyzip
   requirement: !ruby/object:Gem::Requirement
@@ -79,20 +79,6 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '2.0'
-- !ruby/object:Gem::Dependency
-  name: rake
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: 13.3.0
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: 13.3.0
 - !ruby/object:Gem::Dependency
   name: minitest
   requirement: !ruby/object:Gem::Requirement
@@ -136,47 +122,47 @@ dependencies:
       - !ruby/object:Gem::Version
         version: 1.7.1
 - !ruby/object:Gem::Dependency
-  name: webmock
+  name: mocha
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 3.24.0
+        version: 2.4.5
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 3.24.0
+        version: 2.4.5
 - !ruby/object:Gem::Dependency
-  name: mocha
+  name: pry
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.4.5
+        version: 0.15.2
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.4.5
+        version: 0.15.2
 - !ruby/object:Gem::Dependency
-  name: pry
+  name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.15.2
+        version: 13.3.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.15.2
+        version: 13.3.0
 - !ruby/object:Gem::Dependency
   name: simplecov
   requirement: !ruby/object:Gem::Requirement
@@ -205,6 +191,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 0.9.10
+- !ruby/object:Gem::Dependency
+  name: webmock
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.24.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.24.0
 description: A Ruby gem for interacting with the Kaggle API, including dataset downloads
   with caching support
 email:
@@ -228,7 +228,6 @@ files:
 - plans/benchmarks.md
 - plans/cli_tool.md
 - plans/initial_prompt.md
-- plans/lists.md
 - plans/models.md
 - plans/roadmap.md
 homepage: https://github.com/yourusername/kaggle

data/plans/lists.md

@@ -1,77 +0,0 @@
-# Lists Enhancement Plan
-
-## Overview
-Expand the current listing functionality to provide comprehensive discovery and filtering capabilities for Kaggle resources.
-
-## Current State
-- Basic dataset listing with search and pagination
-- Simple dataset file listing
-
-## Planned Enhancements
-
-### Phase 1: Enhanced Dataset Lists
-- [ ] **Advanced Filtering**: Filter by license, file formats, size, update date
-- [ ] **Sorting Options**: Sort by popularity, date, size, downloads
-- [ ] **Category Browsing**: Browse datasets by category/topic
-- [ ] **User/Organization Datasets**: List datasets by specific users or organizations
-- [ ] **Featured Datasets**: Highlight trending or featured datasets
-
-### Phase 2: Competition Lists
-- [ ] **Competition Discovery**: List active, completed, and upcoming competitions
-- [ ] **Competition Filtering**: Filter by category, prize pool, participant count
-- [ ] **Competition Search**: Search competitions by title, description, tags
-- [ ] **Personal Competitions**: List user's participated competitions
-- [ ] **Competition Metrics**: Show participation stats, deadlines, prizes
-
-### Phase 3: Model Lists  
-- [ ] **Model Discovery**: List available models and frameworks
-- [ ] **Model Filtering**: Filter by framework, task type, performance metrics
-- [ ] **Model Versions**: Track different versions of models
-- [ ] **Popular Models**: Highlight trending and highly-rated models
-- [ ] **User Models**: List models by specific users
-
-### Phase 4: Kernel/Notebook Lists
-- [ ] **Code Discovery**: List public kernels and notebooks
-- [ ] **Language Filtering**: Filter by programming language (R, Python, etc.)
-- [ ] **Topic Browsing**: Browse by dataset or competition
-- [ ] **Popular Code**: Highlight most-voted and most-forked notebooks
-- [ ] **Recent Activity**: Show recently updated kernels
-
-## Technical Implementation
-
-### API Endpoints
-- Implement consistent pagination across all list types
-- Add caching layer for frequently accessed lists
-- Support bulk operations for multiple list requests
-
-### CLI Enhancements
-- Interactive filtering and sorting in CLI
-- Export capabilities (CSV, JSON, XML)
-- Bookmarking and favorites functionality
-- Watchlist for monitoring specific items
-
-### Data Structures
-```ruby
-# Enhanced listing response format
-{
-  items: [],           # List of resources
-  pagination: {        # Pagination metadata
-    page: 1,
-    per_page: 20,
-    total_pages: 50,
-    total_count: 1000
-  },
-  filters: {           # Applied filters
-    category: 'finance',
-    license: 'cc-by',
-    updated_since: '2023-01-01'
-  },
-  sort: {              # Current sorting
-    field: 'popularity',
-    direction: 'desc'
-  }
-}
-```
-
-## Priority: High
-Target completion: Version 0.3.0