datafile 0.3.0 → 0.3.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: e02f51529c40c3573f5bf51670b8e704e518306e
-  data.tar.gz: 309d29e81297fcf2a63b95a1c26f72003aa842b3
+SHA256:
+  metadata.gz: 54d6b53158bb55adfd268f9c79935c64bc3fb03ab6d1418cc09bffb2ce64970e
+  data.tar.gz: 9a47519a90bef056b1a7a4d892f88f027bb277331708418d899178a931e823fa
 SHA512:
-  metadata.gz: 77bf2afdca97946e52e99bb6f7b2ba96e714b5890a3be11df6f4a3a3b19e43281e30ee78002125928039535b6813c4ec362e1bd8ecf184fa0935e6487d7fa0e4
-  data.tar.gz: 41d975fe70d41f75e46031dd7ce006629375b9703dd9449199e6ee3fd3e6461b71db33618ac57720347a5c9fd99889f42caddf3c354bf72ea16aa05cad1a8180
+  metadata.gz: 7f87ecb6c27fc3c595dbd16281b496f92fa8174b5cbf2f710dd4c5d0778b09ca96388b85d2185db03b9a0e2279afed87be4149b6c027b4b4c6c7c8da0698b87a
+  data.tar.gz: 02af529638c97df49cf8bb1d6bd7cb68128a66c19c3b0c07b17d6f70ad319600cdd5f783580a4478203d1621285df52d22b5a9a1cfd1ded9da17e9c82315b046

data/CHANGELOG.md

@@ -1,3 +1,5 @@
+### 0.3.2
+
 ### 0.0.1 / 2014-11-27
 
 * Everything is new. First release.

data/Manifest.txt

@@ -13,11 +13,3 @@ lib/datafile/workers/file/registry.rb
 lib/datafile/workers/file/worker.rb
 lib/datafile/workers/zip/dataset.rb
 lib/datafile/workers/zip/worker.rb
-test/datafile/eurocup.rb
-test/datafile/stadiums.rb
-test/datafile/world.rb
-test/helper.rb
-test/test_builder.rb
-test/test_file_dataset_registry.rb
-test/test_file_worker.rb
-test/test_football_dataset.rb

data/README.md

@@ -1,9 +1,9 @@
 # datafile
 
-datafile gem - builder for downloading n reading datasets
+datafile gem - builder for downloading 'n' reading datasets
 
-* home  :: [github.com/rubylibs/datafile](https://github.com/rubylibs/datafile)
-* bugs  :: [github.com/rubylibs/datafile/issues](https://github.com/rubylibs/datafile/issues)
+* home  :: [github.com/rubycocos/datasets](https://github.com/rubycocos/datasets)
+* bugs  :: [github.com/rubycocos/datasets/issues](https://github.com/rubycocos/datasets/issues)
 * gem   :: [rubygems.org/gems/datafile](https://rubygems.org/gems/datafile)
 * rdoc  :: [rubydoc.info/gems/datafile](http://rubydoc.info/gems/datafile)
 

data/Rakefile

@@ -8,10 +8,10 @@ Hoe.spec 'datafile' do
   self.summary = 'datafile - builder for downloading n reading datasets'
   self.description = summary
 
-  self.urls    = ['https://github.com/rubylibs/datafile']
+  self.urls    = { home: 'https://github.com/rubycocos/datasets' }
 
   self.author  = 'Gerald Bauer'
-  self.email   = 'opensport@googlegroups.com'
+  self.email   = 'gerald.bauer@gmail.com'
 
   # switch extension to .markdown for gihub formatting
   self.readme_file  = 'README.md'

data/lib/datafile/builder.rb

@@ -1,11 +1,10 @@
-# encoding: utf-8
 
 module Datafile
 
 class Builder     ## "simple" builder (one file, one datafile)
 
   def self.load_file( path )
-    code = File.open( path, 'r:utf-8' ).read
+    code = File.open( path, 'r:utf-8' ) {|f| f.read }
     self.load( code )
   end
 

data/lib/datafile/datafile.rb

@@ -1,4 +1,3 @@
-# encoding: utf-8
 
 module Datafile
 
@@ -7,7 +6,7 @@ class Datafile
 
   ## convenience method - use like Datafile.load_file()
   def self.load_file( path='./Datafile' )
-    code = File.open( path, 'r:utf-8' ).read
+    code = File.open( path, 'r:utf-8' ) { |f| f.read }
     self.load( code )
   end
 
@@ -19,9 +18,6 @@ class Datafile
     # Note: return datafile (of course, NOT the builder)
     #  if you want a builder use Datafile::Builder ;-)
     datafile = builder.datafile
-    ## check for auto-configure (just guessing)
-    ##   zip or file worker
-    datafile.guess_file_or_zip_worker
     datafile
   end
 
@@ -56,18 +52,6 @@ class Datafile
   end
 
 
-  def guess_file_or_zip_worker   ## change/rename to configure_file_or_zip_worker - why? why not??
-    ## if opts file or zip exists do NOT change (assume set manually)
-    return  if @opts[:file] || @opts[:zip]
-
-    ## for now only change if single (just 1) dataset and it's present
-    if @datasets.size == 1 && @datasets[0].file?
-      puts "  bingo!! assume (in-situ) datafile; use file workers"
-      @worker = FileWorker.new( self )
-    end
-  end
-
-
   def run
     logger.info( "[datafile] begin - run" )
     download     # step 1 - download zips for datasets

data/lib/datafile/dataset.rb

@@ -1,12 +1,10 @@
-# encoding: utf-8
-
 
 ############
 # fix: move global method to ??
 
 def read_known_datasets( path )
     ary = []
-    lines = File.open( path, 'r:utf-8' ).read
+    lines = File.open( path, 'r:utf-8' ) {|f| f.read }
     lines.each_line do |line|
       ## skip blank and comments lines
       next   if /^\s*#/ =~ line || /^\s*$/ =~ line
@@ -32,35 +30,9 @@ class Dataset
   ## convenience helpers for known opts
   def setup()   @opts[:setup];           end    ## note: return nil if not found/set
   def format()  @opts[:format] || 'txt'; end    ## note: assume default is txt (other formats incl. csv) for now - why? wh not?
-
-
-  def file?                    # note: use file? (not exit? might use zip? later to check if zip exists? -why? why not?)
-    ## hack/convenience shortcut:
-    ##   1) check if dataset exists as local (in situ) file dataset
-    ##    e.g. working folder  == name of dataset
-    ##
-    ##   todo/fix: 2) also check
-    ##                   via (file)registry - why, why not??
-
-    ## split name in org/user + project (e.g. openfootball/at-austria)
-    parts = @name.split( '/' )
-
-    basename = parts[1]
-    ##  e.g.
-    ##  ./ (working folder) => at-austria
-    ##  openfootball/at-austria
-    if File.basename( Dir.getwd ) == basename
-      puts "  bingo!! working folder >#{basename}< matches dataset"
-      true     ## return true
-    else
-      false    ## return false
-    end
-  end  ## file?
-
 end # class Dataset
 
 
-
 class WorldDataset < Dataset
   def initialize( name_easy, opts={} )
 
@@ -129,6 +101,11 @@ class BeerDataset < Dataset
     super( name, opts )
   end
 end  # class BeerDataset
+end # module Datafile
 
 
-end # module Datafile
+## note:  add "known" dataset classes to global namespace - why? why not?
+##  add "global" shortcuts for now
+WorldDataset    = Datafile::WorldDataset
+FootballDataset = Datafile::FootballDataset
+BeerDataset     = Datafile::BeerDataset

data/lib/datafile/version.rb

@@ -1,10 +1,9 @@
-# encoding: utf-8
 
 module Datafile
 
   MAJOR = 0    ## todo: namespace inside version or something - why? why not??
   MINOR = 3
-  PATCH = 0
+  PATCH = 2
   VERSION = [MAJOR,MINOR,PATCH].join('.')
 
   def self.version
@@ -12,11 +11,11 @@ module Datafile
   end
 
   def self.banner
-    "datafile/#{VERSION} on Ruby #{RUBY_VERSION} (#{RUBY_RELEASE_DATE}) [#{RUBY_PLATFORM}]"
+    "datafile/#{VERSION} on Ruby #{RUBY_VERSION} (#{RUBY_RELEASE_DATE}) [#{RUBY_PLATFORM}] in (#{root})"
   end
 
   def self.root
-    "#{File.expand_path( File.dirname(File.dirname(File.dirname(__FILE__))) )}"
+    File.expand_path( File.dirname(File.dirname(File.dirname(__FILE__))) )
   end
 
   def self.data_path

data/lib/datafile/workers/file/dataset.rb

@@ -1,4 +1,3 @@
-# encoding: utf-8
 
 module Datafile
 
@@ -18,18 +17,7 @@ class FileDataset
   end
 
   def repo_dir     ### check: use (rename to) include dir (or local_repo_dir) - why, why not ???
-    ## note: for easy testing allow "in situ" datasets
-    ##   e.g.  ./ (e.g. mu-mauritius)  is openfootball/mu-mauritius
-    ## split name in org/user + project (e.g. openfootball/at-austria)
-    parts = @dataset.name.split( '/' )
-
-    basename = parts[1]
-    if File.basename( Dir.getwd ) == basename
-      puts "  bingo!! working folder >#{basename}< matches dataset"
-      return Dir.getwd     ## assume working directory/folder is repo dir
-    end
-
-    registry.lookup( @dataset.name )
+    self.class.registry.lookup( @dataset.name )
   end
 
   def dump
@@ -48,9 +36,5 @@ class FileDataset
       logger.info( "TODO/FIX: read dataset (file) '#{@dataset.name}', '#{@dataset.setup}'; sorry" )
     end
   end
-
-
-private
-  def registry()  self.class.registry;  end    ## convenience method to access "static" shared class variable
 end # class FileDataset
 end # module Datafile

data/lib/datafile/workers/file/registry.rb

@@ -1,4 +1,3 @@
-# encoding: utf-8
 
 module Datafile
 

data/lib/datafile/workers/file/worker.rb

@@ -1,4 +1,4 @@
-# encoding: utf-8
+
 
 module Datafile
 

data/lib/datafile/workers/zip/dataset.rb

@@ -1,4 +1,3 @@
-# encoding: utf-8
 
 module Datafile
 
@@ -72,7 +71,7 @@ private
 
     ## make sure dest path exists
     dest_p = File.dirname( dest )
-    FileUtils.mkdir_p( dest_p )  unless File.exists?( dest_p )   ## use Dir.exists?? why? why not??
+    FileUtils.mkdir_p( dest_p )  unless File.exist?( dest_p )   ## use Dir.exist?? why? why not??
 
     worker = Fetcher::Worker.new
     worker.copy( url, dest )

data/lib/datafile/workers/zip/worker.rb

@@ -1,4 +1,4 @@
-# encoding: utf-8
+
 
 module Datafile
 

data/lib/datafile.rb

@@ -1,11 +1,10 @@
-# encoding: utf-8
-
 require 'logutils'
 require 'fetcher'    ## add (HTTP/S) download support (of blobs/binaries/zips)
 
 
 # our own code
-require 'datafile/version'  # let it always go first
+require_relative 'datafile/version'  # let it always go first
+
 
 
 module Datafile
@@ -31,19 +30,19 @@ module Datafile
 end   # module Datafile
 
 
-require 'datafile/dataset'
-require 'datafile/builder'
+require_relative 'datafile/dataset'
+require_relative 'datafile/builder'
 
 
-require 'datafile/workers/file/registry'
-require 'datafile/workers/file/dataset'
-require 'datafile/workers/file/worker'
+require_relative 'datafile/workers/file/registry'
+require_relative 'datafile/workers/file/dataset'
+require_relative 'datafile/workers/file/worker'
 
-require 'datafile/workers/zip/dataset'
-require 'datafile/workers/zip/worker'
+require_relative 'datafile/workers/zip/dataset'
+require_relative 'datafile/workers/zip/worker'
 
-require 'datafile/datafile'
+require_relative 'datafile/datafile'
 
 
 # say hello
-puts Datafile.banner    if defined?($RUBYCOCO_DEBUG) && $RUBYCOCO_DEBUG
+puts Datafile.banner    ##  if defined?($RUBYCOCO_DEBUG) && $RUBYCOCO_DEBUG

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: datafile
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.3.2
 platform: ruby
 authors:
 - Gerald Bauer
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2019-11-21 00:00:00.000000000 Z
+date: 2024-06-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: logutils
@@ -42,32 +42,38 @@ dependencies:
   name: rdoc
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
         version: '4.0'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '7'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
         version: '4.0'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '7'
 - !ruby/object:Gem::Dependency
   name: hoe
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.16'
+        version: '4.1'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.16'
+        version: '4.1'
 description: datafile - builder for downloading n reading datasets
-email: opensport@googlegroups.com
+email: gerald.bauer@gmail.com
 executables: []
 extensions: []
 extra_rdoc_files:
@@ -90,19 +96,11 @@ files:
 - lib/datafile/workers/file/worker.rb
 - lib/datafile/workers/zip/dataset.rb
 - lib/datafile/workers/zip/worker.rb
-- test/datafile/eurocup.rb
-- test/datafile/stadiums.rb
-- test/datafile/world.rb
-- test/helper.rb
-- test/test_builder.rb
-- test/test_file_dataset_registry.rb
-- test/test_file_worker.rb
-- test/test_football_dataset.rb
-homepage: https://github.com/rubylibs/datafile
+homepage: https://github.com/rubycocos/datasets
 licenses:
 - Public Domain
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options:
 - "--main"
 - README.md
@@ -119,9 +117,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.5.2
-signing_key: 
+rubygems_version: 3.4.10
+signing_key:
 specification_version: 4
 summary: datafile - builder for downloading n reading datasets
 test_files: []

data/test/datafile/eurocup.rb

@@ -1,6 +0,0 @@
-#####################
-# national teams
-
-football 'national-teams'
-football 'euro-cup'
-

data/test/datafile/stadiums.rb

@@ -1,3 +0,0 @@
-
-football 'stadiums'   ## NOTE: default is setup: 'all'
-

data/test/datafile/world.rb

@@ -1,3 +0,0 @@
-
-world 'world.db', setup: 'countries'
-

data/test/helper.rb

@@ -1,13 +0,0 @@
-
-## minitest setup
-require 'minitest/autorun'
-
-## deps
-
-### require 'worlddb'
-require 'sportdb/models'   # note: will include worlddb
-
-
-## our own code
-require 'datafile'
-

data/test/test_builder.rb

@@ -1,45 +0,0 @@
-# encoding: utf-8
-
-###
-#  to run use
-#     ruby -I ./lib -I ./test test/test_builder.rb
-
-
-require 'helper'
-
-class TestBuilder < MiniTest::Test
-
-  def test_builder
-    code =<<EOS
-## comments
-
-  world  'world.db', setup: 'countries'
-
-  football 'national-teams'      ## NOTE: default is setup: 'all
-
-  ### todo/fix: download archive only once(!!) even if included more than once
-  ## football 'world-cup', setup: '2014_quali'
-
-  football 'world-cup', setup: '2014'
-
-## more comments
-
-EOS
-
-    builder = Datafile::Builder.load( code )
-
-    datafile = builder.datafile
-    datafile.run
-
-    datafile.download
-    datafile.read
-    datafile.dump
-
-    ## change worker (defaults to ZipWorker)
-    datafile.worker = Datafile::FileWorker
-    datafile.dump
-
-    assert true  # if we get here - test success
-  end
-
-end # class TestBuilder

data/test/test_file_dataset_registry.rb

@@ -1,26 +0,0 @@
-# encoding: utf-8
-
-###
-#  to run use
-#     ruby -I ./lib -I ./test test/test_file_dataset_registry.rb
-
-
-require 'helper'
-
-class TestFileDatasetRegistry < MiniTest::Test
-
-  def test_lookup
-    registry = Datafile::FileDatasetRegistry.new
-    registry.merge( openfootball: '../../openfootball' )
-
-    assert_equal '../../openfootball/austria',    registry.lookup( 'openfootball/austria')
-    assert_equal '../../openmundi/world.db',      registry.lookup( 'openmundi/world.db' )
-
-    assert_equal '../../openfootball/austria',    registry.lookup!( 'openfootball/austria')
-    assert_equal '../../openmundi/world.db',      registry.lookup!( 'openmundi/world.db' )
-
-    assert_equal '../../openfootball/national-teams', registry.lookup( 'openfootball/national-teams')
-    assert_equal '../../openfootball/euro-cup',       registry.lookup( 'openfootball/euro-cup' )
-  end
-
-end # class TestFileDatasetRegistry

data/test/test_file_worker.rb

@@ -1,40 +0,0 @@
-# encoding: utf-8
-
-###
-#  to run use
-#     ruby -I ./lib -I ./test test/test_file_worker.rb
-
-
-require 'helper'
-
-class TestFileWorker < MiniTest::Test
-
-  def test_eurocup
-
-    world_datafile = Datafile::Datafile.load_file( "#{Datafile.root}/test/datafile/world.rb" )
-    world_datafile.dump
-
-    eurocup_datafile = Datafile::Datafile.load_file( "#{Datafile.root}/test/datafile/eurocup.rb" )
-    eurocup_datafile.dump
-
-    # database setup 'n' config
-    ActiveRecord::Base.establish_connection( adapter:  'sqlite3',
-                                             database: ':memory:' )
-    SportDb.create_all
-
-    ## change worker (defaults to ZipWorker)
-    world_datafile.worker = Datafile::FileWorker
-    world_datafile.dump
-##    world_datafile.read
-
-    registry = Datafile::FileDataset.registry
-    registry.merge( openfootball: '../../openfootball' )
-
-    eurocup_datafile.worker = Datafile::FileWorker
-    eurocup_datafile.dump
-##    eurocup_datafile.read
-
-    assert true  # if we get here - test success
-  end
-
-end # class TestFileWorker

data/test/test_football_dataset.rb

@@ -1,54 +0,0 @@
-# encoding: utf-8
-
-###
-#  to run use
-#     ruby -I ./lib -I ./test test/test_football_dataset.rb
-
-
-require 'helper'
-
-class TestFootballDataset < MiniTest::Test
-
-  def test_names
-    pp Datafile::FootballDataset.known_datasets
-
-    at   = Datafile::FootballDataset.new( 'austria' )
-    at2  = Datafile::FootballDataset.new( 'openfootball/austria' )
-    xxx  = Datafile::FootballDataset.new( 'xxx' )
-    xxx2 = Datafile::FootballDataset.new( 'openfootball/xxx' )
-
-    assert_equal 'openfootball/austria', at.name
-    assert_equal 'openfootball/austria', at2.name
-
-    assert_equal 'openfootball/xxx', xxx.name
-    assert_equal 'openfootball/xxx', xxx2.name
-  end
-
-  ## move to test datasets - why, why not ??
-  def test_world
-    at   = Datafile::WorldDataset.new( 'austria.db' )
-    at2  = Datafile::WorldDataset.new( 'openmundi/austria.db' )
-    xxx  = Datafile::WorldDataset.new( 'xxx' )
-    xxx2 = Datafile::WorldDataset.new( 'openmundi/xxx' )
-
-    assert_equal 'openmundi/austria.db', at.name
-    assert_equal 'openmundi/austria.db', at2.name
-
-    assert_equal 'openmundi/xxx', xxx.name
-    assert_equal 'openmundi/xxx', xxx2.name
-  end
-
-  def test_beer
-    at   = Datafile::BeerDataset.new( 'austria' )
-    at2  = Datafile::BeerDataset.new( 'openbeer/austria' )
-    xxx  = Datafile::BeerDataset.new( 'xxx' )
-    xxx2 = Datafile::BeerDataset.new( 'openbeer/xxx' )
-
-    assert_equal 'openbeer/austria', at.name
-    assert_equal 'openbeer/austria', at2.name
-
-    assert_equal 'openbeer/xxx', xxx.name
-    assert_equal 'openbeer/xxx', xxx2.name
-  end
-
-end # class TestFootballDataset